{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 18291, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 5.467281735861951e-05, "grad_norm": 28.460283279418945, "learning_rate": 0.0, "loss": 3.1517, "step": 1 }, { "epoch": 0.00010934563471723902, "grad_norm": 25.368772506713867, "learning_rate": 1.8214936247723135e-07, "loss": 3.1885, "step": 2 }, { "epoch": 0.00016401845207585853, "grad_norm": 13.31208324432373, "learning_rate": 3.642987249544627e-07, "loss": 2.4463, "step": 3 }, { "epoch": 0.00021869126943447804, "grad_norm": 10.979389190673828, "learning_rate": 5.46448087431694e-07, "loss": 2.1214, "step": 4 }, { "epoch": 0.00027336408679309756, "grad_norm": 22.97323226928711, "learning_rate": 7.285974499089254e-07, "loss": 3.037, "step": 5 }, { "epoch": 0.00032803690415171707, "grad_norm": 11.927607536315918, "learning_rate": 9.107468123861568e-07, "loss": 2.2511, "step": 6 }, { "epoch": 0.00038270972151033657, "grad_norm": 19.47809410095215, "learning_rate": 1.092896174863388e-06, "loss": 2.8538, "step": 7 }, { "epoch": 0.00043738253886895607, "grad_norm": 14.783178329467773, "learning_rate": 1.2750455373406195e-06, "loss": 2.4498, "step": 8 }, { "epoch": 0.0004920553562275756, "grad_norm": 19.676525115966797, "learning_rate": 1.4571948998178508e-06, "loss": 2.9942, "step": 9 }, { "epoch": 0.0005467281735861951, "grad_norm": 23.361677169799805, "learning_rate": 1.639344262295082e-06, "loss": 2.8087, "step": 10 }, { "epoch": 0.0006014009909448146, "grad_norm": 13.264182090759277, "learning_rate": 1.8214936247723136e-06, "loss": 2.2614, "step": 11 }, { "epoch": 0.0006560738083034341, "grad_norm": 13.731310844421387, "learning_rate": 2.0036429872495447e-06, "loss": 2.3085, "step": 12 }, { "epoch": 0.0007107466256620537, "grad_norm": 23.810636520385742, "learning_rate": 2.185792349726776e-06, "loss": 3.1782, "step": 13 }, { "epoch": 0.0007654194430206731, "grad_norm": 14.393597602844238, "learning_rate": 2.3679417122040074e-06, "loss": 2.489, "step": 14 }, { "epoch": 0.0008200922603792927, "grad_norm": 20.092803955078125, "learning_rate": 2.550091074681239e-06, "loss": 2.9353, "step": 15 }, { "epoch": 0.0008747650777379121, "grad_norm": 11.418030738830566, "learning_rate": 2.73224043715847e-06, "loss": 2.0984, "step": 16 }, { "epoch": 0.0009294378950965317, "grad_norm": 18.569725036621094, "learning_rate": 2.9143897996357016e-06, "loss": 2.7949, "step": 17 }, { "epoch": 0.0009841107124551511, "grad_norm": 15.339882850646973, "learning_rate": 3.0965391621129327e-06, "loss": 2.4275, "step": 18 }, { "epoch": 0.0010387835298137707, "grad_norm": 13.320307731628418, "learning_rate": 3.278688524590164e-06, "loss": 2.2831, "step": 19 }, { "epoch": 0.0010934563471723903, "grad_norm": 13.647689819335938, "learning_rate": 3.4608378870673953e-06, "loss": 2.3586, "step": 20 }, { "epoch": 0.0011481291645310098, "grad_norm": 10.5294189453125, "learning_rate": 3.6429872495446273e-06, "loss": 2.1052, "step": 21 }, { "epoch": 0.0012028019818896292, "grad_norm": 19.467103958129883, "learning_rate": 3.825136612021858e-06, "loss": 3.2178, "step": 22 }, { "epoch": 0.0012574747992482487, "grad_norm": 26.56917381286621, "learning_rate": 4.0072859744990895e-06, "loss": 3.3733, "step": 23 }, { "epoch": 0.0013121476166068683, "grad_norm": 16.932470321655273, "learning_rate": 4.189435336976321e-06, "loss": 2.7673, "step": 24 }, { "epoch": 0.0013668204339654878, "grad_norm": 17.09805679321289, "learning_rate": 4.371584699453552e-06, "loss": 2.8947, "step": 25 }, { "epoch": 0.0014214932513241074, "grad_norm": 19.247739791870117, "learning_rate": 4.553734061930783e-06, "loss": 2.7807, "step": 26 }, { "epoch": 0.0014761660686827267, "grad_norm": 19.83827781677246, "learning_rate": 4.735883424408015e-06, "loss": 2.8281, "step": 27 }, { "epoch": 0.0015308388860413463, "grad_norm": 11.253808975219727, "learning_rate": 4.918032786885246e-06, "loss": 2.3134, "step": 28 }, { "epoch": 0.0015855117033999658, "grad_norm": 11.471559524536133, "learning_rate": 5.100182149362478e-06, "loss": 2.2909, "step": 29 }, { "epoch": 0.0016401845207585854, "grad_norm": 11.90311050415039, "learning_rate": 5.2823315118397085e-06, "loss": 2.3415, "step": 30 }, { "epoch": 0.001694857338117205, "grad_norm": 14.253375053405762, "learning_rate": 5.46448087431694e-06, "loss": 2.4544, "step": 31 }, { "epoch": 0.0017495301554758243, "grad_norm": 13.09131908416748, "learning_rate": 5.646630236794172e-06, "loss": 2.3967, "step": 32 }, { "epoch": 0.0018042029728344438, "grad_norm": 7.912752628326416, "learning_rate": 5.828779599271403e-06, "loss": 1.9628, "step": 33 }, { "epoch": 0.0018588757901930634, "grad_norm": 14.277321815490723, "learning_rate": 6.010928961748634e-06, "loss": 2.1304, "step": 34 }, { "epoch": 0.001913548607551683, "grad_norm": 14.618846893310547, "learning_rate": 6.193078324225865e-06, "loss": 2.3156, "step": 35 }, { "epoch": 0.0019682214249103023, "grad_norm": 8.873196601867676, "learning_rate": 6.375227686703098e-06, "loss": 2.045, "step": 36 }, { "epoch": 0.002022894242268922, "grad_norm": 22.42957878112793, "learning_rate": 6.557377049180328e-06, "loss": 2.8019, "step": 37 }, { "epoch": 0.0020775670596275414, "grad_norm": 9.077791213989258, "learning_rate": 6.73952641165756e-06, "loss": 2.1403, "step": 38 }, { "epoch": 0.002132239876986161, "grad_norm": 12.948487281799316, "learning_rate": 6.921675774134791e-06, "loss": 2.1753, "step": 39 }, { "epoch": 0.0021869126943447805, "grad_norm": 16.776201248168945, "learning_rate": 7.103825136612022e-06, "loss": 2.531, "step": 40 }, { "epoch": 0.0022415855117034, "grad_norm": 17.376293182373047, "learning_rate": 7.2859744990892545e-06, "loss": 2.7731, "step": 41 }, { "epoch": 0.0022962583290620196, "grad_norm": 20.873600006103516, "learning_rate": 7.468123861566485e-06, "loss": 2.8438, "step": 42 }, { "epoch": 0.002350931146420639, "grad_norm": 19.319124221801758, "learning_rate": 7.650273224043716e-06, "loss": 2.5578, "step": 43 }, { "epoch": 0.0024056039637792583, "grad_norm": 6.122952938079834, "learning_rate": 7.832422586520947e-06, "loss": 1.7158, "step": 44 }, { "epoch": 0.002460276781137878, "grad_norm": 17.713529586791992, "learning_rate": 8.014571948998179e-06, "loss": 2.3245, "step": 45 }, { "epoch": 0.0025149495984964974, "grad_norm": 10.67629623413086, "learning_rate": 8.196721311475409e-06, "loss": 1.9187, "step": 46 }, { "epoch": 0.002569622415855117, "grad_norm": 17.6468448638916, "learning_rate": 8.378870673952642e-06, "loss": 2.5125, "step": 47 }, { "epoch": 0.0026242952332137365, "grad_norm": 11.603192329406738, "learning_rate": 8.561020036429874e-06, "loss": 2.0872, "step": 48 }, { "epoch": 0.002678968050572356, "grad_norm": 26.021793365478516, "learning_rate": 8.743169398907103e-06, "loss": 2.8335, "step": 49 }, { "epoch": 0.0027336408679309756, "grad_norm": 10.207371711730957, "learning_rate": 8.925318761384335e-06, "loss": 1.9377, "step": 50 }, { "epoch": 0.002788313685289595, "grad_norm": 8.85833740234375, "learning_rate": 9.107468123861566e-06, "loss": 1.9671, "step": 51 }, { "epoch": 0.0028429865026482148, "grad_norm": 9.501017570495605, "learning_rate": 9.2896174863388e-06, "loss": 1.9158, "step": 52 }, { "epoch": 0.0028976593200068343, "grad_norm": 19.250812530517578, "learning_rate": 9.47176684881603e-06, "loss": 2.2857, "step": 53 }, { "epoch": 0.0029523321373654534, "grad_norm": 18.05318832397461, "learning_rate": 9.653916211293261e-06, "loss": 2.227, "step": 54 }, { "epoch": 0.003007004954724073, "grad_norm": 9.236148834228516, "learning_rate": 9.836065573770493e-06, "loss": 1.7907, "step": 55 }, { "epoch": 0.0030616777720826925, "grad_norm": 20.389095306396484, "learning_rate": 1.0018214936247722e-05, "loss": 2.241, "step": 56 }, { "epoch": 0.003116350589441312, "grad_norm": 18.461414337158203, "learning_rate": 1.0200364298724956e-05, "loss": 2.1725, "step": 57 }, { "epoch": 0.0031710234067999317, "grad_norm": 7.579362392425537, "learning_rate": 1.0382513661202187e-05, "loss": 1.556, "step": 58 }, { "epoch": 0.003225696224158551, "grad_norm": 10.144827842712402, "learning_rate": 1.0564663023679417e-05, "loss": 1.8624, "step": 59 }, { "epoch": 0.0032803690415171708, "grad_norm": 21.022857666015625, "learning_rate": 1.0746812386156649e-05, "loss": 2.154, "step": 60 }, { "epoch": 0.0033350418588757903, "grad_norm": 14.394145011901855, "learning_rate": 1.092896174863388e-05, "loss": 1.9029, "step": 61 }, { "epoch": 0.00338971467623441, "grad_norm": 17.054895401000977, "learning_rate": 1.1111111111111112e-05, "loss": 2.4945, "step": 62 }, { "epoch": 0.003444387493593029, "grad_norm": 14.781465530395508, "learning_rate": 1.1293260473588343e-05, "loss": 2.1318, "step": 63 }, { "epoch": 0.0034990603109516486, "grad_norm": 18.506019592285156, "learning_rate": 1.1475409836065575e-05, "loss": 2.2043, "step": 64 }, { "epoch": 0.003553733128310268, "grad_norm": 27.93775177001953, "learning_rate": 1.1657559198542806e-05, "loss": 2.5641, "step": 65 }, { "epoch": 0.0036084059456688877, "grad_norm": 9.547721862792969, "learning_rate": 1.1839708561020036e-05, "loss": 1.8082, "step": 66 }, { "epoch": 0.0036630787630275072, "grad_norm": 10.876938819885254, "learning_rate": 1.2021857923497268e-05, "loss": 1.8521, "step": 67 }, { "epoch": 0.003717751580386127, "grad_norm": 10.517918586730957, "learning_rate": 1.22040072859745e-05, "loss": 1.8812, "step": 68 }, { "epoch": 0.0037724243977447463, "grad_norm": 14.901288986206055, "learning_rate": 1.238615664845173e-05, "loss": 1.9636, "step": 69 }, { "epoch": 0.003827097215103366, "grad_norm": 14.896095275878906, "learning_rate": 1.2568306010928962e-05, "loss": 1.7586, "step": 70 }, { "epoch": 0.0038817700324619855, "grad_norm": 13.5922269821167, "learning_rate": 1.2750455373406195e-05, "loss": 2.0599, "step": 71 }, { "epoch": 0.003936442849820605, "grad_norm": 13.91616439819336, "learning_rate": 1.2932604735883425e-05, "loss": 1.8398, "step": 72 }, { "epoch": 0.003991115667179224, "grad_norm": 9.399290084838867, "learning_rate": 1.3114754098360657e-05, "loss": 1.7648, "step": 73 }, { "epoch": 0.004045788484537844, "grad_norm": 21.576637268066406, "learning_rate": 1.3296903460837887e-05, "loss": 2.0626, "step": 74 }, { "epoch": 0.004100461301896463, "grad_norm": 29.143434524536133, "learning_rate": 1.347905282331512e-05, "loss": 2.4754, "step": 75 }, { "epoch": 0.004155134119255083, "grad_norm": 29.12057113647461, "learning_rate": 1.3661202185792351e-05, "loss": 2.3333, "step": 76 }, { "epoch": 0.004209806936613702, "grad_norm": 10.83830451965332, "learning_rate": 1.3843351548269581e-05, "loss": 1.5288, "step": 77 }, { "epoch": 0.004264479753972322, "grad_norm": 12.7376070022583, "learning_rate": 1.4025500910746814e-05, "loss": 1.6549, "step": 78 }, { "epoch": 0.0043191525713309415, "grad_norm": 10.341575622558594, "learning_rate": 1.4207650273224044e-05, "loss": 1.6319, "step": 79 }, { "epoch": 0.004373825388689561, "grad_norm": 9.477974891662598, "learning_rate": 1.4389799635701276e-05, "loss": 1.5974, "step": 80 }, { "epoch": 0.004428498206048181, "grad_norm": 13.975724220275879, "learning_rate": 1.4571948998178509e-05, "loss": 1.9764, "step": 81 }, { "epoch": 0.0044831710234068, "grad_norm": 21.434688568115234, "learning_rate": 1.4754098360655739e-05, "loss": 2.1266, "step": 82 }, { "epoch": 0.00453784384076542, "grad_norm": 15.521931648254395, "learning_rate": 1.493624772313297e-05, "loss": 1.8837, "step": 83 }, { "epoch": 0.004592516658124039, "grad_norm": 8.442477226257324, "learning_rate": 1.51183970856102e-05, "loss": 1.536, "step": 84 }, { "epoch": 0.004647189475482659, "grad_norm": 15.9622163772583, "learning_rate": 1.5300546448087432e-05, "loss": 1.9455, "step": 85 }, { "epoch": 0.004701862292841278, "grad_norm": 16.949514389038086, "learning_rate": 1.548269581056466e-05, "loss": 1.9386, "step": 86 }, { "epoch": 0.004756535110199898, "grad_norm": 10.150044441223145, "learning_rate": 1.5664845173041895e-05, "loss": 1.6316, "step": 87 }, { "epoch": 0.004811207927558517, "grad_norm": 20.720458984375, "learning_rate": 1.5846994535519128e-05, "loss": 1.8999, "step": 88 }, { "epoch": 0.004865880744917136, "grad_norm": 13.875415802001953, "learning_rate": 1.6029143897996358e-05, "loss": 1.5791, "step": 89 }, { "epoch": 0.004920553562275756, "grad_norm": 13.246374130249023, "learning_rate": 1.621129326047359e-05, "loss": 1.6188, "step": 90 }, { "epoch": 0.004975226379634375, "grad_norm": 15.10468864440918, "learning_rate": 1.6393442622950818e-05, "loss": 1.7232, "step": 91 }, { "epoch": 0.005029899196992995, "grad_norm": 14.961130142211914, "learning_rate": 1.657559198542805e-05, "loss": 1.5586, "step": 92 }, { "epoch": 0.005084572014351614, "grad_norm": 14.230538368225098, "learning_rate": 1.6757741347905284e-05, "loss": 1.5046, "step": 93 }, { "epoch": 0.005139244831710234, "grad_norm": 12.765387535095215, "learning_rate": 1.6939890710382514e-05, "loss": 1.6392, "step": 94 }, { "epoch": 0.0051939176490688535, "grad_norm": 12.45035457611084, "learning_rate": 1.7122040072859747e-05, "loss": 1.7014, "step": 95 }, { "epoch": 0.005248590466427473, "grad_norm": 15.367644309997559, "learning_rate": 1.7304189435336977e-05, "loss": 1.7466, "step": 96 }, { "epoch": 0.005303263283786093, "grad_norm": 18.170072555541992, "learning_rate": 1.7486338797814207e-05, "loss": 1.8975, "step": 97 }, { "epoch": 0.005357936101144712, "grad_norm": 11.774588584899902, "learning_rate": 1.766848816029144e-05, "loss": 1.6591, "step": 98 }, { "epoch": 0.005412608918503332, "grad_norm": 11.772879600524902, "learning_rate": 1.785063752276867e-05, "loss": 1.6126, "step": 99 }, { "epoch": 0.005467281735861951, "grad_norm": 14.638187408447266, "learning_rate": 1.8032786885245903e-05, "loss": 1.8049, "step": 100 }, { "epoch": 0.005521954553220571, "grad_norm": 13.04010009765625, "learning_rate": 1.8214936247723133e-05, "loss": 1.6432, "step": 101 }, { "epoch": 0.00557662737057919, "grad_norm": 13.031495094299316, "learning_rate": 1.8397085610200366e-05, "loss": 1.621, "step": 102 }, { "epoch": 0.00563130018793781, "grad_norm": 18.751604080200195, "learning_rate": 1.85792349726776e-05, "loss": 1.6834, "step": 103 }, { "epoch": 0.0056859730052964295, "grad_norm": 21.921829223632812, "learning_rate": 1.8761384335154826e-05, "loss": 1.6026, "step": 104 }, { "epoch": 0.005740645822655049, "grad_norm": 21.12803840637207, "learning_rate": 1.894353369763206e-05, "loss": 1.6805, "step": 105 }, { "epoch": 0.005795318640013669, "grad_norm": 9.040517807006836, "learning_rate": 1.912568306010929e-05, "loss": 1.4716, "step": 106 }, { "epoch": 0.005849991457372287, "grad_norm": 13.935863494873047, "learning_rate": 1.9307832422586522e-05, "loss": 1.4692, "step": 107 }, { "epoch": 0.005904664274730907, "grad_norm": 12.691027641296387, "learning_rate": 1.9489981785063755e-05, "loss": 1.6656, "step": 108 }, { "epoch": 0.005959337092089526, "grad_norm": 23.265838623046875, "learning_rate": 1.9672131147540985e-05, "loss": 1.766, "step": 109 }, { "epoch": 0.006014009909448146, "grad_norm": 13.788040161132812, "learning_rate": 1.9854280510018215e-05, "loss": 1.5897, "step": 110 }, { "epoch": 0.0060686827268067655, "grad_norm": 8.813186645507812, "learning_rate": 2.0036429872495445e-05, "loss": 1.2736, "step": 111 }, { "epoch": 0.006123355544165385, "grad_norm": 8.550286293029785, "learning_rate": 2.0218579234972678e-05, "loss": 1.4036, "step": 112 }, { "epoch": 0.006178028361524005, "grad_norm": 16.14936637878418, "learning_rate": 2.040072859744991e-05, "loss": 1.6523, "step": 113 }, { "epoch": 0.006232701178882624, "grad_norm": 14.42675495147705, "learning_rate": 2.058287795992714e-05, "loss": 1.4437, "step": 114 }, { "epoch": 0.006287373996241244, "grad_norm": 18.53306007385254, "learning_rate": 2.0765027322404374e-05, "loss": 1.5294, "step": 115 }, { "epoch": 0.006342046813599863, "grad_norm": 14.630516052246094, "learning_rate": 2.0947176684881604e-05, "loss": 1.4235, "step": 116 }, { "epoch": 0.006396719630958483, "grad_norm": 9.806638717651367, "learning_rate": 2.1129326047358834e-05, "loss": 1.3059, "step": 117 }, { "epoch": 0.006451392448317102, "grad_norm": 11.434539794921875, "learning_rate": 2.1311475409836064e-05, "loss": 1.4447, "step": 118 }, { "epoch": 0.006506065265675722, "grad_norm": 10.221287727355957, "learning_rate": 2.1493624772313297e-05, "loss": 1.3583, "step": 119 }, { "epoch": 0.0065607380830343415, "grad_norm": 17.28177261352539, "learning_rate": 2.167577413479053e-05, "loss": 1.3987, "step": 120 }, { "epoch": 0.006615410900392961, "grad_norm": 11.70526123046875, "learning_rate": 2.185792349726776e-05, "loss": 1.4158, "step": 121 }, { "epoch": 0.006670083717751581, "grad_norm": 11.333802223205566, "learning_rate": 2.2040072859744993e-05, "loss": 1.4482, "step": 122 }, { "epoch": 0.0067247565351102, "grad_norm": 7.853899955749512, "learning_rate": 2.2222222222222223e-05, "loss": 1.5229, "step": 123 }, { "epoch": 0.00677942935246882, "grad_norm": 9.825787544250488, "learning_rate": 2.2404371584699453e-05, "loss": 1.3428, "step": 124 }, { "epoch": 0.006834102169827439, "grad_norm": 14.125246047973633, "learning_rate": 2.2586520947176686e-05, "loss": 1.2591, "step": 125 }, { "epoch": 0.006888774987186058, "grad_norm": 8.23925495147705, "learning_rate": 2.2768670309653916e-05, "loss": 1.3902, "step": 126 }, { "epoch": 0.006943447804544678, "grad_norm": 5.421191215515137, "learning_rate": 2.295081967213115e-05, "loss": 1.2601, "step": 127 }, { "epoch": 0.006998120621903297, "grad_norm": 8.788386344909668, "learning_rate": 2.313296903460838e-05, "loss": 1.4572, "step": 128 }, { "epoch": 0.007052793439261917, "grad_norm": 5.825864315032959, "learning_rate": 2.3315118397085612e-05, "loss": 1.2891, "step": 129 }, { "epoch": 0.007107466256620536, "grad_norm": 17.54123306274414, "learning_rate": 2.3497267759562842e-05, "loss": 1.1515, "step": 130 }, { "epoch": 0.007162139073979156, "grad_norm": 13.715216636657715, "learning_rate": 2.3679417122040072e-05, "loss": 1.3387, "step": 131 }, { "epoch": 0.007216811891337775, "grad_norm": 7.2021355628967285, "learning_rate": 2.3861566484517305e-05, "loss": 1.1207, "step": 132 }, { "epoch": 0.007271484708696395, "grad_norm": 12.499711990356445, "learning_rate": 2.4043715846994535e-05, "loss": 1.3451, "step": 133 }, { "epoch": 0.0073261575260550145, "grad_norm": 7.293931484222412, "learning_rate": 2.422586520947177e-05, "loss": 1.5046, "step": 134 }, { "epoch": 0.007380830343413634, "grad_norm": 5.499994277954102, "learning_rate": 2.4408014571949e-05, "loss": 1.1845, "step": 135 }, { "epoch": 0.007435503160772254, "grad_norm": 8.757645606994629, "learning_rate": 2.459016393442623e-05, "loss": 1.1236, "step": 136 }, { "epoch": 0.007490175978130873, "grad_norm": 11.20506763458252, "learning_rate": 2.477231329690346e-05, "loss": 1.2882, "step": 137 }, { "epoch": 0.007544848795489493, "grad_norm": 7.0046892166137695, "learning_rate": 2.495446265938069e-05, "loss": 1.4472, "step": 138 }, { "epoch": 0.007599521612848112, "grad_norm": 7.101222038269043, "learning_rate": 2.5136612021857924e-05, "loss": 1.4281, "step": 139 }, { "epoch": 0.007654194430206732, "grad_norm": 5.555123805999756, "learning_rate": 2.5318761384335154e-05, "loss": 1.3331, "step": 140 }, { "epoch": 0.007708867247565351, "grad_norm": 8.634552001953125, "learning_rate": 2.550091074681239e-05, "loss": 1.4178, "step": 141 }, { "epoch": 0.007763540064923971, "grad_norm": 7.001679420471191, "learning_rate": 2.568306010928962e-05, "loss": 1.3339, "step": 142 }, { "epoch": 0.00781821288228259, "grad_norm": 5.1437668800354, "learning_rate": 2.586520947176685e-05, "loss": 1.2199, "step": 143 }, { "epoch": 0.00787288569964121, "grad_norm": 5.938844680786133, "learning_rate": 2.604735883424408e-05, "loss": 1.3536, "step": 144 }, { "epoch": 0.00792755851699983, "grad_norm": 5.464634895324707, "learning_rate": 2.6229508196721314e-05, "loss": 1.2306, "step": 145 }, { "epoch": 0.007982231334358448, "grad_norm": 7.58903169631958, "learning_rate": 2.6411657559198543e-05, "loss": 1.3542, "step": 146 }, { "epoch": 0.008036904151717069, "grad_norm": 6.517548561096191, "learning_rate": 2.6593806921675773e-05, "loss": 1.4951, "step": 147 }, { "epoch": 0.008091576969075687, "grad_norm": 6.501460552215576, "learning_rate": 2.677595628415301e-05, "loss": 1.1904, "step": 148 }, { "epoch": 0.008146249786434308, "grad_norm": 6.028698444366455, "learning_rate": 2.695810564663024e-05, "loss": 1.3014, "step": 149 }, { "epoch": 0.008200922603792926, "grad_norm": 5.426022052764893, "learning_rate": 2.714025500910747e-05, "loss": 1.3378, "step": 150 }, { "epoch": 0.008255595421151547, "grad_norm": 5.6537957191467285, "learning_rate": 2.7322404371584703e-05, "loss": 1.1908, "step": 151 }, { "epoch": 0.008310268238510166, "grad_norm": 4.956148624420166, "learning_rate": 2.7504553734061933e-05, "loss": 1.1022, "step": 152 }, { "epoch": 0.008364941055868786, "grad_norm": 6.7156596183776855, "learning_rate": 2.7686703096539162e-05, "loss": 1.2539, "step": 153 }, { "epoch": 0.008419613873227405, "grad_norm": 8.486438751220703, "learning_rate": 2.7868852459016392e-05, "loss": 1.2593, "step": 154 }, { "epoch": 0.008474286690586023, "grad_norm": 5.87712287902832, "learning_rate": 2.805100182149363e-05, "loss": 1.3864, "step": 155 }, { "epoch": 0.008528959507944644, "grad_norm": 5.29139518737793, "learning_rate": 2.823315118397086e-05, "loss": 1.2119, "step": 156 }, { "epoch": 0.008583632325303263, "grad_norm": 6.166731834411621, "learning_rate": 2.841530054644809e-05, "loss": 1.4067, "step": 157 }, { "epoch": 0.008638305142661883, "grad_norm": 8.839431762695312, "learning_rate": 2.8597449908925322e-05, "loss": 1.3043, "step": 158 }, { "epoch": 0.008692977960020502, "grad_norm": 5.554182529449463, "learning_rate": 2.877959927140255e-05, "loss": 1.273, "step": 159 }, { "epoch": 0.008747650777379122, "grad_norm": 4.899946212768555, "learning_rate": 2.896174863387978e-05, "loss": 1.4259, "step": 160 }, { "epoch": 0.00880232359473774, "grad_norm": 6.332659721374512, "learning_rate": 2.9143897996357018e-05, "loss": 1.281, "step": 161 }, { "epoch": 0.008856996412096361, "grad_norm": 6.374397277832031, "learning_rate": 2.9326047358834248e-05, "loss": 1.088, "step": 162 }, { "epoch": 0.00891166922945498, "grad_norm": 10.225881576538086, "learning_rate": 2.9508196721311478e-05, "loss": 1.2375, "step": 163 }, { "epoch": 0.0089663420468136, "grad_norm": 6.209120273590088, "learning_rate": 2.9690346083788704e-05, "loss": 1.0868, "step": 164 }, { "epoch": 0.009021014864172219, "grad_norm": 5.230401515960693, "learning_rate": 2.987249544626594e-05, "loss": 1.3267, "step": 165 }, { "epoch": 0.00907568768153084, "grad_norm": 7.274537086486816, "learning_rate": 3.005464480874317e-05, "loss": 1.2879, "step": 166 }, { "epoch": 0.009130360498889458, "grad_norm": 6.208257675170898, "learning_rate": 3.02367941712204e-05, "loss": 1.5197, "step": 167 }, { "epoch": 0.009185033316248079, "grad_norm": 5.002009391784668, "learning_rate": 3.0418943533697637e-05, "loss": 1.1608, "step": 168 }, { "epoch": 0.009239706133606697, "grad_norm": 7.156376361846924, "learning_rate": 3.0601092896174864e-05, "loss": 1.0577, "step": 169 }, { "epoch": 0.009294378950965318, "grad_norm": 5.607086181640625, "learning_rate": 3.07832422586521e-05, "loss": 1.2783, "step": 170 }, { "epoch": 0.009349051768323936, "grad_norm": 10.958869934082031, "learning_rate": 3.096539162112932e-05, "loss": 1.2694, "step": 171 }, { "epoch": 0.009403724585682557, "grad_norm": 7.4468255043029785, "learning_rate": 3.114754098360656e-05, "loss": 1.4603, "step": 172 }, { "epoch": 0.009458397403041175, "grad_norm": 6.268348217010498, "learning_rate": 3.132969034608379e-05, "loss": 1.3624, "step": 173 }, { "epoch": 0.009513070220399796, "grad_norm": 6.239754676818848, "learning_rate": 3.1511839708561016e-05, "loss": 1.2772, "step": 174 }, { "epoch": 0.009567743037758415, "grad_norm": 4.770158290863037, "learning_rate": 3.1693989071038256e-05, "loss": 1.1731, "step": 175 }, { "epoch": 0.009622415855117033, "grad_norm": 5.3020853996276855, "learning_rate": 3.187613843351548e-05, "loss": 1.2574, "step": 176 }, { "epoch": 0.009677088672475654, "grad_norm": 13.075638771057129, "learning_rate": 3.2058287795992716e-05, "loss": 1.2729, "step": 177 }, { "epoch": 0.009731761489834272, "grad_norm": 5.946187496185303, "learning_rate": 3.224043715846995e-05, "loss": 1.3538, "step": 178 }, { "epoch": 0.009786434307192893, "grad_norm": 6.166831016540527, "learning_rate": 3.242258652094718e-05, "loss": 1.3409, "step": 179 }, { "epoch": 0.009841107124551511, "grad_norm": 6.734454154968262, "learning_rate": 3.260473588342441e-05, "loss": 1.5537, "step": 180 }, { "epoch": 0.009895779941910132, "grad_norm": 13.54556941986084, "learning_rate": 3.2786885245901635e-05, "loss": 1.2277, "step": 181 }, { "epoch": 0.00995045275926875, "grad_norm": 5.207752227783203, "learning_rate": 3.2969034608378875e-05, "loss": 1.4045, "step": 182 }, { "epoch": 0.010005125576627371, "grad_norm": 7.995291233062744, "learning_rate": 3.31511839708561e-05, "loss": 1.2132, "step": 183 }, { "epoch": 0.01005979839398599, "grad_norm": 4.545738697052002, "learning_rate": 3.3333333333333335e-05, "loss": 1.3149, "step": 184 }, { "epoch": 0.01011447121134461, "grad_norm": 5.020116329193115, "learning_rate": 3.351548269581057e-05, "loss": 1.2218, "step": 185 }, { "epoch": 0.010169144028703229, "grad_norm": 4.8123698234558105, "learning_rate": 3.36976320582878e-05, "loss": 1.1232, "step": 186 }, { "epoch": 0.01022381684606185, "grad_norm": 5.275303840637207, "learning_rate": 3.387978142076503e-05, "loss": 1.3112, "step": 187 }, { "epoch": 0.010278489663420468, "grad_norm": 5.11578369140625, "learning_rate": 3.406193078324226e-05, "loss": 1.3428, "step": 188 }, { "epoch": 0.010333162480779088, "grad_norm": 4.87942361831665, "learning_rate": 3.4244080145719494e-05, "loss": 1.265, "step": 189 }, { "epoch": 0.010387835298137707, "grad_norm": 8.654768943786621, "learning_rate": 3.442622950819672e-05, "loss": 1.2606, "step": 190 }, { "epoch": 0.010442508115496327, "grad_norm": 7.223742485046387, "learning_rate": 3.4608378870673954e-05, "loss": 1.2803, "step": 191 }, { "epoch": 0.010497180932854946, "grad_norm": 6.892421722412109, "learning_rate": 3.479052823315119e-05, "loss": 1.3759, "step": 192 }, { "epoch": 0.010551853750213567, "grad_norm": 8.362183570861816, "learning_rate": 3.4972677595628414e-05, "loss": 1.1036, "step": 193 }, { "epoch": 0.010606526567572185, "grad_norm": 5.560189247131348, "learning_rate": 3.515482695810565e-05, "loss": 1.3286, "step": 194 }, { "epoch": 0.010661199384930804, "grad_norm": 4.971956253051758, "learning_rate": 3.533697632058288e-05, "loss": 1.2612, "step": 195 }, { "epoch": 0.010715872202289424, "grad_norm": 6.246836185455322, "learning_rate": 3.551912568306011e-05, "loss": 1.3907, "step": 196 }, { "epoch": 0.010770545019648043, "grad_norm": 7.245604515075684, "learning_rate": 3.570127504553734e-05, "loss": 1.1952, "step": 197 }, { "epoch": 0.010825217837006663, "grad_norm": 4.652061939239502, "learning_rate": 3.588342440801457e-05, "loss": 1.2415, "step": 198 }, { "epoch": 0.010879890654365282, "grad_norm": 7.707137107849121, "learning_rate": 3.6065573770491806e-05, "loss": 1.4294, "step": 199 }, { "epoch": 0.010934563471723903, "grad_norm": 6.41841983795166, "learning_rate": 3.624772313296903e-05, "loss": 1.4202, "step": 200 }, { "epoch": 0.010989236289082521, "grad_norm": 5.144504070281982, "learning_rate": 3.6429872495446266e-05, "loss": 1.3121, "step": 201 }, { "epoch": 0.011043909106441142, "grad_norm": 5.423256874084473, "learning_rate": 3.66120218579235e-05, "loss": 1.2311, "step": 202 }, { "epoch": 0.01109858192379976, "grad_norm": 5.588386535644531, "learning_rate": 3.679417122040073e-05, "loss": 1.2439, "step": 203 }, { "epoch": 0.01115325474115838, "grad_norm": 5.386981010437012, "learning_rate": 3.697632058287796e-05, "loss": 1.2221, "step": 204 }, { "epoch": 0.011207927558517, "grad_norm": 4.725149631500244, "learning_rate": 3.71584699453552e-05, "loss": 1.2108, "step": 205 }, { "epoch": 0.01126260037587562, "grad_norm": 5.9655256271362305, "learning_rate": 3.7340619307832425e-05, "loss": 1.1207, "step": 206 }, { "epoch": 0.011317273193234239, "grad_norm": 6.1018805503845215, "learning_rate": 3.752276867030965e-05, "loss": 1.4132, "step": 207 }, { "epoch": 0.011371946010592859, "grad_norm": 7.918558120727539, "learning_rate": 3.7704918032786885e-05, "loss": 1.2249, "step": 208 }, { "epoch": 0.011426618827951478, "grad_norm": 5.514193534851074, "learning_rate": 3.788706739526412e-05, "loss": 1.198, "step": 209 }, { "epoch": 0.011481291645310098, "grad_norm": 5.6876912117004395, "learning_rate": 3.806921675774135e-05, "loss": 1.253, "step": 210 }, { "epoch": 0.011535964462668717, "grad_norm": 6.008302211761475, "learning_rate": 3.825136612021858e-05, "loss": 1.4238, "step": 211 }, { "epoch": 0.011590637280027337, "grad_norm": 5.4425249099731445, "learning_rate": 3.843351548269581e-05, "loss": 1.3102, "step": 212 }, { "epoch": 0.011645310097385956, "grad_norm": 9.065838813781738, "learning_rate": 3.8615664845173044e-05, "loss": 1.41, "step": 213 }, { "epoch": 0.011699982914744575, "grad_norm": 5.5311808586120605, "learning_rate": 3.879781420765027e-05, "loss": 1.3224, "step": 214 }, { "epoch": 0.011754655732103195, "grad_norm": 5.610389232635498, "learning_rate": 3.897996357012751e-05, "loss": 1.2684, "step": 215 }, { "epoch": 0.011809328549461814, "grad_norm": 4.4004740715026855, "learning_rate": 3.916211293260474e-05, "loss": 1.176, "step": 216 }, { "epoch": 0.011864001366820434, "grad_norm": 4.740638732910156, "learning_rate": 3.934426229508197e-05, "loss": 1.0368, "step": 217 }, { "epoch": 0.011918674184179053, "grad_norm": 5.568851470947266, "learning_rate": 3.95264116575592e-05, "loss": 1.2492, "step": 218 }, { "epoch": 0.011973347001537673, "grad_norm": 6.587883472442627, "learning_rate": 3.970856102003643e-05, "loss": 1.3041, "step": 219 }, { "epoch": 0.012028019818896292, "grad_norm": 5.165619373321533, "learning_rate": 3.989071038251366e-05, "loss": 1.4671, "step": 220 }, { "epoch": 0.012082692636254912, "grad_norm": 5.273097515106201, "learning_rate": 4.007285974499089e-05, "loss": 1.2491, "step": 221 }, { "epoch": 0.012137365453613531, "grad_norm": 5.628006935119629, "learning_rate": 4.025500910746813e-05, "loss": 1.46, "step": 222 }, { "epoch": 0.012192038270972151, "grad_norm": 5.804055690765381, "learning_rate": 4.0437158469945356e-05, "loss": 1.2897, "step": 223 }, { "epoch": 0.01224671108833077, "grad_norm": 4.5839619636535645, "learning_rate": 4.061930783242259e-05, "loss": 1.114, "step": 224 }, { "epoch": 0.01230138390568939, "grad_norm": 5.485470771789551, "learning_rate": 4.080145719489982e-05, "loss": 1.1249, "step": 225 }, { "epoch": 0.01235605672304801, "grad_norm": 5.1476640701293945, "learning_rate": 4.098360655737705e-05, "loss": 1.192, "step": 226 }, { "epoch": 0.01241072954040663, "grad_norm": 9.361919403076172, "learning_rate": 4.116575591985428e-05, "loss": 1.3224, "step": 227 }, { "epoch": 0.012465402357765248, "grad_norm": 9.0615873336792, "learning_rate": 4.134790528233151e-05, "loss": 1.1864, "step": 228 }, { "epoch": 0.012520075175123869, "grad_norm": 4.954155921936035, "learning_rate": 4.153005464480875e-05, "loss": 1.2903, "step": 229 }, { "epoch": 0.012574747992482488, "grad_norm": 6.022733688354492, "learning_rate": 4.1712204007285975e-05, "loss": 1.4686, "step": 230 }, { "epoch": 0.012629420809841108, "grad_norm": 4.501972675323486, "learning_rate": 4.189435336976321e-05, "loss": 1.1144, "step": 231 }, { "epoch": 0.012684093627199727, "grad_norm": 5.029186248779297, "learning_rate": 4.207650273224044e-05, "loss": 1.3165, "step": 232 }, { "epoch": 0.012738766444558345, "grad_norm": 5.231407165527344, "learning_rate": 4.225865209471767e-05, "loss": 1.3581, "step": 233 }, { "epoch": 0.012793439261916966, "grad_norm": 5.347891807556152, "learning_rate": 4.24408014571949e-05, "loss": 1.3997, "step": 234 }, { "epoch": 0.012848112079275584, "grad_norm": 6.3008222579956055, "learning_rate": 4.262295081967213e-05, "loss": 1.17, "step": 235 }, { "epoch": 0.012902784896634205, "grad_norm": 4.6670942306518555, "learning_rate": 4.280510018214937e-05, "loss": 1.4147, "step": 236 }, { "epoch": 0.012957457713992824, "grad_norm": 4.630072116851807, "learning_rate": 4.2987249544626594e-05, "loss": 1.4297, "step": 237 }, { "epoch": 0.013012130531351444, "grad_norm": 5.692249298095703, "learning_rate": 4.316939890710383e-05, "loss": 1.1353, "step": 238 }, { "epoch": 0.013066803348710063, "grad_norm": 4.915284633636475, "learning_rate": 4.335154826958106e-05, "loss": 1.1024, "step": 239 }, { "epoch": 0.013121476166068683, "grad_norm": 4.357940196990967, "learning_rate": 4.353369763205829e-05, "loss": 1.1581, "step": 240 }, { "epoch": 0.013176148983427302, "grad_norm": 4.692545413970947, "learning_rate": 4.371584699453552e-05, "loss": 1.1555, "step": 241 }, { "epoch": 0.013230821800785922, "grad_norm": 12.898009300231934, "learning_rate": 4.3897996357012754e-05, "loss": 1.1224, "step": 242 }, { "epoch": 0.013285494618144541, "grad_norm": 4.385805130004883, "learning_rate": 4.408014571948999e-05, "loss": 1.2241, "step": 243 }, { "epoch": 0.013340167435503161, "grad_norm": 7.696259498596191, "learning_rate": 4.426229508196721e-05, "loss": 1.2221, "step": 244 }, { "epoch": 0.01339484025286178, "grad_norm": 5.261298179626465, "learning_rate": 4.4444444444444447e-05, "loss": 1.2408, "step": 245 }, { "epoch": 0.0134495130702204, "grad_norm": 4.866325855255127, "learning_rate": 4.462659380692168e-05, "loss": 1.4002, "step": 246 }, { "epoch": 0.013504185887579019, "grad_norm": 5.806476593017578, "learning_rate": 4.4808743169398906e-05, "loss": 1.3085, "step": 247 }, { "epoch": 0.01355885870493764, "grad_norm": 7.195845127105713, "learning_rate": 4.499089253187614e-05, "loss": 1.1657, "step": 248 }, { "epoch": 0.013613531522296258, "grad_norm": 4.703783988952637, "learning_rate": 4.517304189435337e-05, "loss": 1.3583, "step": 249 }, { "epoch": 0.013668204339654879, "grad_norm": 5.553247451782227, "learning_rate": 4.5355191256830606e-05, "loss": 1.2737, "step": 250 }, { "epoch": 0.013722877157013497, "grad_norm": 5.0438690185546875, "learning_rate": 4.553734061930783e-05, "loss": 1.3674, "step": 251 }, { "epoch": 0.013777549974372116, "grad_norm": 4.614986419677734, "learning_rate": 4.5719489981785066e-05, "loss": 1.1973, "step": 252 }, { "epoch": 0.013832222791730736, "grad_norm": 4.356905937194824, "learning_rate": 4.59016393442623e-05, "loss": 1.2411, "step": 253 }, { "epoch": 0.013886895609089355, "grad_norm": 4.9625325202941895, "learning_rate": 4.6083788706739525e-05, "loss": 1.2609, "step": 254 }, { "epoch": 0.013941568426447976, "grad_norm": 5.020370006561279, "learning_rate": 4.626593806921676e-05, "loss": 1.2744, "step": 255 }, { "epoch": 0.013996241243806594, "grad_norm": 4.236820220947266, "learning_rate": 4.644808743169399e-05, "loss": 1.0663, "step": 256 }, { "epoch": 0.014050914061165215, "grad_norm": 5.291215896606445, "learning_rate": 4.6630236794171225e-05, "loss": 1.0233, "step": 257 }, { "epoch": 0.014105586878523833, "grad_norm": 5.626501083374023, "learning_rate": 4.681238615664845e-05, "loss": 1.0727, "step": 258 }, { "epoch": 0.014160259695882454, "grad_norm": 5.531919956207275, "learning_rate": 4.6994535519125685e-05, "loss": 1.2285, "step": 259 }, { "epoch": 0.014214932513241072, "grad_norm": 4.7246503829956055, "learning_rate": 4.717668488160292e-05, "loss": 1.2663, "step": 260 }, { "epoch": 0.014269605330599693, "grad_norm": 4.229510307312012, "learning_rate": 4.7358834244080144e-05, "loss": 1.2093, "step": 261 }, { "epoch": 0.014324278147958312, "grad_norm": 3.288661241531372, "learning_rate": 4.754098360655738e-05, "loss": 1.0018, "step": 262 }, { "epoch": 0.014378950965316932, "grad_norm": 5.4604949951171875, "learning_rate": 4.772313296903461e-05, "loss": 1.3243, "step": 263 }, { "epoch": 0.01443362378267555, "grad_norm": 4.167967319488525, "learning_rate": 4.7905282331511844e-05, "loss": 1.0894, "step": 264 }, { "epoch": 0.014488296600034171, "grad_norm": 4.674919605255127, "learning_rate": 4.808743169398907e-05, "loss": 1.2486, "step": 265 }, { "epoch": 0.01454296941739279, "grad_norm": 4.00681734085083, "learning_rate": 4.8269581056466304e-05, "loss": 1.2846, "step": 266 }, { "epoch": 0.01459764223475141, "grad_norm": 6.664625644683838, "learning_rate": 4.845173041894354e-05, "loss": 1.3227, "step": 267 }, { "epoch": 0.014652315052110029, "grad_norm": 6.352639675140381, "learning_rate": 4.863387978142076e-05, "loss": 1.5377, "step": 268 }, { "epoch": 0.01470698786946865, "grad_norm": 4.691588401794434, "learning_rate": 4.8816029143898e-05, "loss": 1.3176, "step": 269 }, { "epoch": 0.014761660686827268, "grad_norm": 5.036170959472656, "learning_rate": 4.899817850637523e-05, "loss": 1.1919, "step": 270 }, { "epoch": 0.014816333504185887, "grad_norm": 3.8355014324188232, "learning_rate": 4.918032786885246e-05, "loss": 1.1991, "step": 271 }, { "epoch": 0.014871006321544507, "grad_norm": 5.025354385375977, "learning_rate": 4.936247723132969e-05, "loss": 1.3055, "step": 272 }, { "epoch": 0.014925679138903126, "grad_norm": 4.814261436462402, "learning_rate": 4.954462659380692e-05, "loss": 1.2063, "step": 273 }, { "epoch": 0.014980351956261746, "grad_norm": 5.226828098297119, "learning_rate": 4.9726775956284156e-05, "loss": 1.2989, "step": 274 }, { "epoch": 0.015035024773620365, "grad_norm": 4.727778434753418, "learning_rate": 4.990892531876138e-05, "loss": 1.2519, "step": 275 }, { "epoch": 0.015089697590978985, "grad_norm": 6.931808948516846, "learning_rate": 5.0091074681238616e-05, "loss": 1.1447, "step": 276 }, { "epoch": 0.015144370408337604, "grad_norm": 4.820164203643799, "learning_rate": 5.027322404371585e-05, "loss": 1.3968, "step": 277 }, { "epoch": 0.015199043225696224, "grad_norm": 4.782267093658447, "learning_rate": 5.045537340619308e-05, "loss": 1.1967, "step": 278 }, { "epoch": 0.015253716043054843, "grad_norm": 4.778230667114258, "learning_rate": 5.063752276867031e-05, "loss": 1.2986, "step": 279 }, { "epoch": 0.015308388860413464, "grad_norm": 4.811721324920654, "learning_rate": 5.081967213114754e-05, "loss": 1.0698, "step": 280 }, { "epoch": 0.015363061677772082, "grad_norm": 4.495142936706543, "learning_rate": 5.100182149362478e-05, "loss": 1.362, "step": 281 }, { "epoch": 0.015417734495130703, "grad_norm": 3.646454095840454, "learning_rate": 5.1183970856102e-05, "loss": 1.1042, "step": 282 }, { "epoch": 0.015472407312489321, "grad_norm": 3.724478244781494, "learning_rate": 5.136612021857924e-05, "loss": 1.1734, "step": 283 }, { "epoch": 0.015527080129847942, "grad_norm": 5.7866530418396, "learning_rate": 5.1548269581056475e-05, "loss": 1.2434, "step": 284 }, { "epoch": 0.01558175294720656, "grad_norm": 5.301814556121826, "learning_rate": 5.17304189435337e-05, "loss": 1.4546, "step": 285 }, { "epoch": 0.01563642576456518, "grad_norm": 5.364645957946777, "learning_rate": 5.1912568306010934e-05, "loss": 1.5209, "step": 286 }, { "epoch": 0.0156910985819238, "grad_norm": 4.240237236022949, "learning_rate": 5.209471766848816e-05, "loss": 1.3352, "step": 287 }, { "epoch": 0.01574577139928242, "grad_norm": 4.846477508544922, "learning_rate": 5.2276867030965394e-05, "loss": 1.2667, "step": 288 }, { "epoch": 0.01580044421664104, "grad_norm": 5.056898593902588, "learning_rate": 5.245901639344263e-05, "loss": 1.2025, "step": 289 }, { "epoch": 0.01585511703399966, "grad_norm": 3.7635505199432373, "learning_rate": 5.2641165755919854e-05, "loss": 1.0998, "step": 290 }, { "epoch": 0.015909789851358276, "grad_norm": 4.354694366455078, "learning_rate": 5.282331511839709e-05, "loss": 1.2301, "step": 291 }, { "epoch": 0.015964462668716897, "grad_norm": 5.376453876495361, "learning_rate": 5.300546448087432e-05, "loss": 0.9043, "step": 292 }, { "epoch": 0.016019135486075517, "grad_norm": 4.02829122543335, "learning_rate": 5.3187613843351547e-05, "loss": 1.159, "step": 293 }, { "epoch": 0.016073808303434137, "grad_norm": 5.687942981719971, "learning_rate": 5.336976320582878e-05, "loss": 1.2375, "step": 294 }, { "epoch": 0.016128481120792754, "grad_norm": 7.284438133239746, "learning_rate": 5.355191256830602e-05, "loss": 1.2457, "step": 295 }, { "epoch": 0.016183153938151375, "grad_norm": 6.8061933517456055, "learning_rate": 5.373406193078324e-05, "loss": 1.1315, "step": 296 }, { "epoch": 0.016237826755509995, "grad_norm": 4.251850128173828, "learning_rate": 5.391621129326048e-05, "loss": 1.3502, "step": 297 }, { "epoch": 0.016292499572868616, "grad_norm": 5.382966995239258, "learning_rate": 5.409836065573771e-05, "loss": 1.1937, "step": 298 }, { "epoch": 0.016347172390227233, "grad_norm": 4.4090046882629395, "learning_rate": 5.428051001821494e-05, "loss": 1.3528, "step": 299 }, { "epoch": 0.016401845207585853, "grad_norm": 5.212709903717041, "learning_rate": 5.446265938069217e-05, "loss": 1.1485, "step": 300 }, { "epoch": 0.016456518024944473, "grad_norm": 5.025577068328857, "learning_rate": 5.4644808743169406e-05, "loss": 1.3301, "step": 301 }, { "epoch": 0.016511190842303094, "grad_norm": 4.359682083129883, "learning_rate": 5.482695810564663e-05, "loss": 1.1083, "step": 302 }, { "epoch": 0.01656586365966171, "grad_norm": 6.2318525314331055, "learning_rate": 5.5009107468123865e-05, "loss": 1.3576, "step": 303 }, { "epoch": 0.01662053647702033, "grad_norm": 5.135866165161133, "learning_rate": 5.519125683060109e-05, "loss": 1.1647, "step": 304 }, { "epoch": 0.01667520929437895, "grad_norm": 6.481905937194824, "learning_rate": 5.5373406193078325e-05, "loss": 1.2161, "step": 305 }, { "epoch": 0.016729882111737572, "grad_norm": 4.391627788543701, "learning_rate": 5.555555555555556e-05, "loss": 1.2031, "step": 306 }, { "epoch": 0.01678455492909619, "grad_norm": 7.409335613250732, "learning_rate": 5.5737704918032785e-05, "loss": 1.2269, "step": 307 }, { "epoch": 0.01683922774645481, "grad_norm": 4.224527359008789, "learning_rate": 5.591985428051002e-05, "loss": 1.2439, "step": 308 }, { "epoch": 0.01689390056381343, "grad_norm": 8.111490249633789, "learning_rate": 5.610200364298726e-05, "loss": 1.2319, "step": 309 }, { "epoch": 0.016948573381172047, "grad_norm": 4.006392002105713, "learning_rate": 5.628415300546448e-05, "loss": 1.125, "step": 310 }, { "epoch": 0.017003246198530667, "grad_norm": 4.925905704498291, "learning_rate": 5.646630236794172e-05, "loss": 1.3335, "step": 311 }, { "epoch": 0.017057919015889288, "grad_norm": 4.426554203033447, "learning_rate": 5.664845173041895e-05, "loss": 1.356, "step": 312 }, { "epoch": 0.017112591833247908, "grad_norm": 5.135465621948242, "learning_rate": 5.683060109289618e-05, "loss": 1.2712, "step": 313 }, { "epoch": 0.017167264650606525, "grad_norm": 7.007083892822266, "learning_rate": 5.701275045537341e-05, "loss": 1.2725, "step": 314 }, { "epoch": 0.017221937467965145, "grad_norm": 6.052837371826172, "learning_rate": 5.7194899817850644e-05, "loss": 1.1096, "step": 315 }, { "epoch": 0.017276610285323766, "grad_norm": 6.429623603820801, "learning_rate": 5.737704918032787e-05, "loss": 1.3646, "step": 316 }, { "epoch": 0.017331283102682386, "grad_norm": 5.151021480560303, "learning_rate": 5.75591985428051e-05, "loss": 1.2803, "step": 317 }, { "epoch": 0.017385955920041003, "grad_norm": 5.677551746368408, "learning_rate": 5.7741347905282337e-05, "loss": 1.23, "step": 318 }, { "epoch": 0.017440628737399624, "grad_norm": 5.288049221038818, "learning_rate": 5.792349726775956e-05, "loss": 1.466, "step": 319 }, { "epoch": 0.017495301554758244, "grad_norm": 4.376389503479004, "learning_rate": 5.8105646630236796e-05, "loss": 1.2633, "step": 320 }, { "epoch": 0.017549974372116865, "grad_norm": 6.498226642608643, "learning_rate": 5.8287795992714036e-05, "loss": 1.3612, "step": 321 }, { "epoch": 0.01760464718947548, "grad_norm": 4.679076194763184, "learning_rate": 5.8469945355191256e-05, "loss": 1.5044, "step": 322 }, { "epoch": 0.017659320006834102, "grad_norm": 5.078037738800049, "learning_rate": 5.8652094717668496e-05, "loss": 1.3004, "step": 323 }, { "epoch": 0.017713992824192722, "grad_norm": 4.243954658508301, "learning_rate": 5.8834244080145716e-05, "loss": 1.2364, "step": 324 }, { "epoch": 0.017768665641551343, "grad_norm": 4.049468994140625, "learning_rate": 5.9016393442622956e-05, "loss": 1.3108, "step": 325 }, { "epoch": 0.01782333845890996, "grad_norm": 4.059385776519775, "learning_rate": 5.919854280510019e-05, "loss": 1.3168, "step": 326 }, { "epoch": 0.01787801127626858, "grad_norm": 9.680340766906738, "learning_rate": 5.938069216757741e-05, "loss": 1.364, "step": 327 }, { "epoch": 0.0179326840936272, "grad_norm": 4.7617316246032715, "learning_rate": 5.956284153005465e-05, "loss": 1.3132, "step": 328 }, { "epoch": 0.017987356910985818, "grad_norm": 4.3002448081970215, "learning_rate": 5.974499089253188e-05, "loss": 1.3361, "step": 329 }, { "epoch": 0.018042029728344438, "grad_norm": 3.888028144836426, "learning_rate": 5.992714025500911e-05, "loss": 1.1886, "step": 330 }, { "epoch": 0.01809670254570306, "grad_norm": 7.7236433029174805, "learning_rate": 6.010928961748634e-05, "loss": 1.3599, "step": 331 }, { "epoch": 0.01815137536306168, "grad_norm": 4.129274845123291, "learning_rate": 6.0291438979963575e-05, "loss": 1.1521, "step": 332 }, { "epoch": 0.018206048180420296, "grad_norm": 4.988646984100342, "learning_rate": 6.04735883424408e-05, "loss": 1.2093, "step": 333 }, { "epoch": 0.018260720997778916, "grad_norm": 5.7189435958862305, "learning_rate": 6.0655737704918034e-05, "loss": 1.2119, "step": 334 }, { "epoch": 0.018315393815137537, "grad_norm": 5.635006904602051, "learning_rate": 6.0837887067395274e-05, "loss": 1.4675, "step": 335 }, { "epoch": 0.018370066632496157, "grad_norm": 4.865622043609619, "learning_rate": 6.1020036429872494e-05, "loss": 1.1462, "step": 336 }, { "epoch": 0.018424739449854774, "grad_norm": 3.662990093231201, "learning_rate": 6.120218579234973e-05, "loss": 1.2409, "step": 337 }, { "epoch": 0.018479412267213394, "grad_norm": 4.565425395965576, "learning_rate": 6.138433515482697e-05, "loss": 1.1871, "step": 338 }, { "epoch": 0.018534085084572015, "grad_norm": 4.9033284187316895, "learning_rate": 6.15664845173042e-05, "loss": 1.3498, "step": 339 }, { "epoch": 0.018588757901930635, "grad_norm": 6.082408905029297, "learning_rate": 6.174863387978142e-05, "loss": 1.1991, "step": 340 }, { "epoch": 0.018643430719289252, "grad_norm": 5.080456733703613, "learning_rate": 6.193078324225865e-05, "loss": 1.3464, "step": 341 }, { "epoch": 0.018698103536647873, "grad_norm": 10.702225685119629, "learning_rate": 6.211293260473589e-05, "loss": 1.2385, "step": 342 }, { "epoch": 0.018752776354006493, "grad_norm": 4.619863986968994, "learning_rate": 6.229508196721313e-05, "loss": 1.3991, "step": 343 }, { "epoch": 0.018807449171365113, "grad_norm": 3.754971981048584, "learning_rate": 6.247723132969034e-05, "loss": 1.184, "step": 344 }, { "epoch": 0.01886212198872373, "grad_norm": 10.164576530456543, "learning_rate": 6.265938069216758e-05, "loss": 1.0131, "step": 345 }, { "epoch": 0.01891679480608235, "grad_norm": 5.000475883483887, "learning_rate": 6.284153005464482e-05, "loss": 1.3047, "step": 346 }, { "epoch": 0.01897146762344097, "grad_norm": 4.730653285980225, "learning_rate": 6.302367941712203e-05, "loss": 1.406, "step": 347 }, { "epoch": 0.01902614044079959, "grad_norm": 3.428260564804077, "learning_rate": 6.320582877959927e-05, "loss": 1.0843, "step": 348 }, { "epoch": 0.01908081325815821, "grad_norm": 4.281787395477295, "learning_rate": 6.338797814207651e-05, "loss": 1.4496, "step": 349 }, { "epoch": 0.01913548607551683, "grad_norm": 8.092382431030273, "learning_rate": 6.357012750455374e-05, "loss": 1.4112, "step": 350 }, { "epoch": 0.01919015889287545, "grad_norm": 3.6590614318847656, "learning_rate": 6.375227686703097e-05, "loss": 1.2311, "step": 351 }, { "epoch": 0.019244831710234066, "grad_norm": 4.936667442321777, "learning_rate": 6.39344262295082e-05, "loss": 1.5167, "step": 352 }, { "epoch": 0.019299504527592687, "grad_norm": 3.8982415199279785, "learning_rate": 6.411657559198543e-05, "loss": 1.2348, "step": 353 }, { "epoch": 0.019354177344951307, "grad_norm": 3.6725752353668213, "learning_rate": 6.429872495446266e-05, "loss": 1.158, "step": 354 }, { "epoch": 0.019408850162309928, "grad_norm": 5.4555230140686035, "learning_rate": 6.44808743169399e-05, "loss": 1.2346, "step": 355 }, { "epoch": 0.019463522979668545, "grad_norm": 4.837955474853516, "learning_rate": 6.466302367941712e-05, "loss": 1.09, "step": 356 }, { "epoch": 0.019518195797027165, "grad_norm": 3.6703908443450928, "learning_rate": 6.484517304189436e-05, "loss": 1.1964, "step": 357 }, { "epoch": 0.019572868614385786, "grad_norm": 5.229437351226807, "learning_rate": 6.502732240437158e-05, "loss": 1.2217, "step": 358 }, { "epoch": 0.019627541431744406, "grad_norm": 4.135477066040039, "learning_rate": 6.520947176684882e-05, "loss": 1.1774, "step": 359 }, { "epoch": 0.019682214249103023, "grad_norm": 5.0106658935546875, "learning_rate": 6.539162112932606e-05, "loss": 1.0905, "step": 360 }, { "epoch": 0.019736887066461643, "grad_norm": 5.7101664543151855, "learning_rate": 6.557377049180327e-05, "loss": 1.1764, "step": 361 }, { "epoch": 0.019791559883820264, "grad_norm": 5.1612725257873535, "learning_rate": 6.575591985428051e-05, "loss": 1.2729, "step": 362 }, { "epoch": 0.019846232701178884, "grad_norm": 4.533981800079346, "learning_rate": 6.593806921675775e-05, "loss": 1.2675, "step": 363 }, { "epoch": 0.0199009055185375, "grad_norm": 5.20145845413208, "learning_rate": 6.612021857923498e-05, "loss": 1.3969, "step": 364 }, { "epoch": 0.01995557833589612, "grad_norm": 5.775331497192383, "learning_rate": 6.63023679417122e-05, "loss": 1.1974, "step": 365 }, { "epoch": 0.020010251153254742, "grad_norm": 4.659386157989502, "learning_rate": 6.648451730418944e-05, "loss": 1.4943, "step": 366 }, { "epoch": 0.020064923970613362, "grad_norm": 3.9063363075256348, "learning_rate": 6.666666666666667e-05, "loss": 1.2398, "step": 367 }, { "epoch": 0.02011959678797198, "grad_norm": 9.13119888305664, "learning_rate": 6.68488160291439e-05, "loss": 1.1308, "step": 368 }, { "epoch": 0.0201742696053306, "grad_norm": 4.634507656097412, "learning_rate": 6.703096539162114e-05, "loss": 1.26, "step": 369 }, { "epoch": 0.02022894242268922, "grad_norm": 4.7934417724609375, "learning_rate": 6.721311475409836e-05, "loss": 1.2492, "step": 370 }, { "epoch": 0.020283615240047837, "grad_norm": 3.5732781887054443, "learning_rate": 6.73952641165756e-05, "loss": 1.3154, "step": 371 }, { "epoch": 0.020338288057406458, "grad_norm": 4.962832927703857, "learning_rate": 6.757741347905283e-05, "loss": 1.4705, "step": 372 }, { "epoch": 0.020392960874765078, "grad_norm": 5.929553508758545, "learning_rate": 6.775956284153006e-05, "loss": 1.2228, "step": 373 }, { "epoch": 0.0204476336921237, "grad_norm": 3.9831957817077637, "learning_rate": 6.79417122040073e-05, "loss": 1.1906, "step": 374 }, { "epoch": 0.020502306509482315, "grad_norm": 5.050657272338867, "learning_rate": 6.812386156648452e-05, "loss": 1.3095, "step": 375 }, { "epoch": 0.020556979326840936, "grad_norm": 6.155956268310547, "learning_rate": 6.830601092896175e-05, "loss": 1.1813, "step": 376 }, { "epoch": 0.020611652144199556, "grad_norm": 5.8696160316467285, "learning_rate": 6.848816029143899e-05, "loss": 1.2389, "step": 377 }, { "epoch": 0.020666324961558177, "grad_norm": 4.854856491088867, "learning_rate": 6.867030965391622e-05, "loss": 1.407, "step": 378 }, { "epoch": 0.020720997778916794, "grad_norm": 4.041303634643555, "learning_rate": 6.885245901639344e-05, "loss": 1.297, "step": 379 }, { "epoch": 0.020775670596275414, "grad_norm": 3.9702742099761963, "learning_rate": 6.903460837887068e-05, "loss": 1.2079, "step": 380 }, { "epoch": 0.020830343413634034, "grad_norm": 3.7796168327331543, "learning_rate": 6.921675774134791e-05, "loss": 1.2785, "step": 381 }, { "epoch": 0.020885016230992655, "grad_norm": 4.466314315795898, "learning_rate": 6.939890710382513e-05, "loss": 1.3808, "step": 382 }, { "epoch": 0.020939689048351272, "grad_norm": 5.905083656311035, "learning_rate": 6.958105646630237e-05, "loss": 1.3263, "step": 383 }, { "epoch": 0.020994361865709892, "grad_norm": 4.071369171142578, "learning_rate": 6.97632058287796e-05, "loss": 1.2179, "step": 384 }, { "epoch": 0.021049034683068513, "grad_norm": 4.386070251464844, "learning_rate": 6.994535519125683e-05, "loss": 0.9537, "step": 385 }, { "epoch": 0.021103707500427133, "grad_norm": 6.073006629943848, "learning_rate": 7.012750455373407e-05, "loss": 1.4414, "step": 386 }, { "epoch": 0.02115838031778575, "grad_norm": 4.372027397155762, "learning_rate": 7.03096539162113e-05, "loss": 1.299, "step": 387 }, { "epoch": 0.02121305313514437, "grad_norm": 4.207513809204102, "learning_rate": 7.049180327868853e-05, "loss": 1.1177, "step": 388 }, { "epoch": 0.02126772595250299, "grad_norm": 4.108957767486572, "learning_rate": 7.067395264116576e-05, "loss": 1.2811, "step": 389 }, { "epoch": 0.021322398769861608, "grad_norm": 3.881462574005127, "learning_rate": 7.085610200364299e-05, "loss": 1.3211, "step": 390 }, { "epoch": 0.02137707158722023, "grad_norm": 4.414498329162598, "learning_rate": 7.103825136612023e-05, "loss": 1.3268, "step": 391 }, { "epoch": 0.02143174440457885, "grad_norm": 5.134377956390381, "learning_rate": 7.122040072859745e-05, "loss": 1.238, "step": 392 }, { "epoch": 0.02148641722193747, "grad_norm": 2.8670942783355713, "learning_rate": 7.140255009107468e-05, "loss": 1.0289, "step": 393 }, { "epoch": 0.021541090039296086, "grad_norm": 4.1255645751953125, "learning_rate": 7.158469945355192e-05, "loss": 1.0508, "step": 394 }, { "epoch": 0.021595762856654706, "grad_norm": 4.3180365562438965, "learning_rate": 7.176684881602915e-05, "loss": 1.2749, "step": 395 }, { "epoch": 0.021650435674013327, "grad_norm": 3.099848985671997, "learning_rate": 7.194899817850637e-05, "loss": 1.0931, "step": 396 }, { "epoch": 0.021705108491371947, "grad_norm": 4.56344747543335, "learning_rate": 7.213114754098361e-05, "loss": 1.3095, "step": 397 }, { "epoch": 0.021759781308730564, "grad_norm": 4.787050247192383, "learning_rate": 7.231329690346084e-05, "loss": 1.4211, "step": 398 }, { "epoch": 0.021814454126089185, "grad_norm": 4.530440807342529, "learning_rate": 7.249544626593807e-05, "loss": 1.2774, "step": 399 }, { "epoch": 0.021869126943447805, "grad_norm": 3.4045395851135254, "learning_rate": 7.26775956284153e-05, "loss": 1.3049, "step": 400 }, { "epoch": 0.021923799760806426, "grad_norm": 5.23744010925293, "learning_rate": 7.285974499089253e-05, "loss": 1.2503, "step": 401 }, { "epoch": 0.021978472578165043, "grad_norm": 4.58358097076416, "learning_rate": 7.304189435336977e-05, "loss": 1.2386, "step": 402 }, { "epoch": 0.022033145395523663, "grad_norm": 4.7051310539245605, "learning_rate": 7.3224043715847e-05, "loss": 1.4503, "step": 403 }, { "epoch": 0.022087818212882283, "grad_norm": 5.888301849365234, "learning_rate": 7.340619307832422e-05, "loss": 1.5097, "step": 404 }, { "epoch": 0.022142491030240904, "grad_norm": 3.8463521003723145, "learning_rate": 7.358834244080146e-05, "loss": 1.234, "step": 405 }, { "epoch": 0.02219716384759952, "grad_norm": 12.972883224487305, "learning_rate": 7.377049180327869e-05, "loss": 1.0532, "step": 406 }, { "epoch": 0.02225183666495814, "grad_norm": 6.061314582824707, "learning_rate": 7.395264116575592e-05, "loss": 1.1584, "step": 407 }, { "epoch": 0.02230650948231676, "grad_norm": 10.298271179199219, "learning_rate": 7.413479052823316e-05, "loss": 1.4603, "step": 408 }, { "epoch": 0.02236118229967538, "grad_norm": 6.758336067199707, "learning_rate": 7.43169398907104e-05, "loss": 1.3729, "step": 409 }, { "epoch": 0.022415855117034, "grad_norm": 3.377289056777954, "learning_rate": 7.449908925318761e-05, "loss": 0.8071, "step": 410 }, { "epoch": 0.02247052793439262, "grad_norm": 4.219804763793945, "learning_rate": 7.468123861566485e-05, "loss": 1.1475, "step": 411 }, { "epoch": 0.02252520075175124, "grad_norm": 3.809671401977539, "learning_rate": 7.486338797814209e-05, "loss": 1.3205, "step": 412 }, { "epoch": 0.022579873569109857, "grad_norm": 7.283710479736328, "learning_rate": 7.50455373406193e-05, "loss": 1.2512, "step": 413 }, { "epoch": 0.022634546386468477, "grad_norm": 4.118873119354248, "learning_rate": 7.522768670309654e-05, "loss": 1.1872, "step": 414 }, { "epoch": 0.022689219203827098, "grad_norm": 6.953093528747559, "learning_rate": 7.540983606557377e-05, "loss": 1.4251, "step": 415 }, { "epoch": 0.022743892021185718, "grad_norm": 3.4966814517974854, "learning_rate": 7.559198542805101e-05, "loss": 1.2718, "step": 416 }, { "epoch": 0.022798564838544335, "grad_norm": 4.704705238342285, "learning_rate": 7.577413479052824e-05, "loss": 1.376, "step": 417 }, { "epoch": 0.022853237655902955, "grad_norm": 4.3632707595825195, "learning_rate": 7.595628415300546e-05, "loss": 1.2445, "step": 418 }, { "epoch": 0.022907910473261576, "grad_norm": 4.633521556854248, "learning_rate": 7.61384335154827e-05, "loss": 1.4632, "step": 419 }, { "epoch": 0.022962583290620196, "grad_norm": 5.454129695892334, "learning_rate": 7.632058287795993e-05, "loss": 1.5698, "step": 420 }, { "epoch": 0.023017256107978813, "grad_norm": 5.356945037841797, "learning_rate": 7.650273224043716e-05, "loss": 1.2054, "step": 421 }, { "epoch": 0.023071928925337434, "grad_norm": 4.571005344390869, "learning_rate": 7.66848816029144e-05, "loss": 1.2392, "step": 422 }, { "epoch": 0.023126601742696054, "grad_norm": 5.410041332244873, "learning_rate": 7.686703096539162e-05, "loss": 1.0854, "step": 423 }, { "epoch": 0.023181274560054674, "grad_norm": 4.143610000610352, "learning_rate": 7.704918032786885e-05, "loss": 1.3137, "step": 424 }, { "epoch": 0.02323594737741329, "grad_norm": 8.110079765319824, "learning_rate": 7.723132969034609e-05, "loss": 1.6147, "step": 425 }, { "epoch": 0.023290620194771912, "grad_norm": 4.295373916625977, "learning_rate": 7.741347905282333e-05, "loss": 1.4095, "step": 426 }, { "epoch": 0.023345293012130532, "grad_norm": 3.852883815765381, "learning_rate": 7.759562841530054e-05, "loss": 1.4217, "step": 427 }, { "epoch": 0.02339996582948915, "grad_norm": 4.189336776733398, "learning_rate": 7.777777777777778e-05, "loss": 1.2323, "step": 428 }, { "epoch": 0.02345463864684777, "grad_norm": 4.092170715332031, "learning_rate": 7.795992714025502e-05, "loss": 1.2294, "step": 429 }, { "epoch": 0.02350931146420639, "grad_norm": 4.066003322601318, "learning_rate": 7.814207650273225e-05, "loss": 1.3044, "step": 430 }, { "epoch": 0.02356398428156501, "grad_norm": 4.7297682762146, "learning_rate": 7.832422586520947e-05, "loss": 1.2684, "step": 431 }, { "epoch": 0.023618657098923627, "grad_norm": 4.22698974609375, "learning_rate": 7.85063752276867e-05, "loss": 1.3322, "step": 432 }, { "epoch": 0.023673329916282248, "grad_norm": 4.348628997802734, "learning_rate": 7.868852459016394e-05, "loss": 1.349, "step": 433 }, { "epoch": 0.02372800273364087, "grad_norm": 5.589132308959961, "learning_rate": 7.887067395264117e-05, "loss": 1.3513, "step": 434 }, { "epoch": 0.02378267555099949, "grad_norm": 5.469600677490234, "learning_rate": 7.90528233151184e-05, "loss": 1.6962, "step": 435 }, { "epoch": 0.023837348368358106, "grad_norm": 5.780651092529297, "learning_rate": 7.923497267759563e-05, "loss": 1.1884, "step": 436 }, { "epoch": 0.023892021185716726, "grad_norm": 4.792544364929199, "learning_rate": 7.941712204007286e-05, "loss": 1.3529, "step": 437 }, { "epoch": 0.023946694003075347, "grad_norm": 3.606487274169922, "learning_rate": 7.959927140255009e-05, "loss": 1.0319, "step": 438 }, { "epoch": 0.024001366820433967, "grad_norm": 4.958981990814209, "learning_rate": 7.978142076502733e-05, "loss": 1.3242, "step": 439 }, { "epoch": 0.024056039637792584, "grad_norm": 4.096409797668457, "learning_rate": 7.996357012750457e-05, "loss": 1.4333, "step": 440 }, { "epoch": 0.024110712455151204, "grad_norm": 4.03978157043457, "learning_rate": 8.014571948998178e-05, "loss": 1.2319, "step": 441 }, { "epoch": 0.024165385272509825, "grad_norm": 5.2809553146362305, "learning_rate": 8.032786885245902e-05, "loss": 1.4678, "step": 442 }, { "epoch": 0.024220058089868445, "grad_norm": 4.837563514709473, "learning_rate": 8.051001821493626e-05, "loss": 1.335, "step": 443 }, { "epoch": 0.024274730907227062, "grad_norm": 4.238574981689453, "learning_rate": 8.069216757741349e-05, "loss": 1.3735, "step": 444 }, { "epoch": 0.024329403724585683, "grad_norm": 4.818048000335693, "learning_rate": 8.087431693989071e-05, "loss": 1.1769, "step": 445 }, { "epoch": 0.024384076541944303, "grad_norm": 4.467388153076172, "learning_rate": 8.105646630236795e-05, "loss": 1.2614, "step": 446 }, { "epoch": 0.02443874935930292, "grad_norm": 3.7806038856506348, "learning_rate": 8.123861566484518e-05, "loss": 1.4018, "step": 447 }, { "epoch": 0.02449342217666154, "grad_norm": 3.640195846557617, "learning_rate": 8.14207650273224e-05, "loss": 1.2317, "step": 448 }, { "epoch": 0.02454809499402016, "grad_norm": 2.861065149307251, "learning_rate": 8.160291438979965e-05, "loss": 1.1102, "step": 449 }, { "epoch": 0.02460276781137878, "grad_norm": 5.553698539733887, "learning_rate": 8.178506375227687e-05, "loss": 1.5168, "step": 450 }, { "epoch": 0.024657440628737398, "grad_norm": 4.07728910446167, "learning_rate": 8.19672131147541e-05, "loss": 1.3961, "step": 451 }, { "epoch": 0.02471211344609602, "grad_norm": 3.161546468734741, "learning_rate": 8.214936247723132e-05, "loss": 1.1766, "step": 452 }, { "epoch": 0.02476678626345464, "grad_norm": 4.888837814331055, "learning_rate": 8.233151183970856e-05, "loss": 1.2634, "step": 453 }, { "epoch": 0.02482145908081326, "grad_norm": 6.287647724151611, "learning_rate": 8.25136612021858e-05, "loss": 1.2548, "step": 454 }, { "epoch": 0.024876131898171876, "grad_norm": 4.321473121643066, "learning_rate": 8.269581056466302e-05, "loss": 1.2519, "step": 455 }, { "epoch": 0.024930804715530497, "grad_norm": 7.678456783294678, "learning_rate": 8.287795992714026e-05, "loss": 1.3548, "step": 456 }, { "epoch": 0.024985477532889117, "grad_norm": 3.8814826011657715, "learning_rate": 8.30601092896175e-05, "loss": 1.3835, "step": 457 }, { "epoch": 0.025040150350247738, "grad_norm": 3.637253522872925, "learning_rate": 8.324225865209472e-05, "loss": 1.406, "step": 458 }, { "epoch": 0.025094823167606355, "grad_norm": 6.175656318664551, "learning_rate": 8.342440801457195e-05, "loss": 1.2472, "step": 459 }, { "epoch": 0.025149495984964975, "grad_norm": 4.331820487976074, "learning_rate": 8.360655737704919e-05, "loss": 1.3313, "step": 460 }, { "epoch": 0.025204168802323595, "grad_norm": 4.5089826583862305, "learning_rate": 8.378870673952642e-05, "loss": 1.4161, "step": 461 }, { "epoch": 0.025258841619682216, "grad_norm": 4.035447120666504, "learning_rate": 8.397085610200364e-05, "loss": 1.3542, "step": 462 }, { "epoch": 0.025313514437040833, "grad_norm": 5.031638145446777, "learning_rate": 8.415300546448088e-05, "loss": 1.3011, "step": 463 }, { "epoch": 0.025368187254399453, "grad_norm": 3.880075454711914, "learning_rate": 8.433515482695811e-05, "loss": 1.3341, "step": 464 }, { "epoch": 0.025422860071758074, "grad_norm": 4.641855239868164, "learning_rate": 8.451730418943534e-05, "loss": 1.3562, "step": 465 }, { "epoch": 0.02547753288911669, "grad_norm": 3.4645678997039795, "learning_rate": 8.469945355191258e-05, "loss": 1.4405, "step": 466 }, { "epoch": 0.02553220570647531, "grad_norm": 4.437983512878418, "learning_rate": 8.48816029143898e-05, "loss": 1.3925, "step": 467 }, { "epoch": 0.02558687852383393, "grad_norm": 3.690854549407959, "learning_rate": 8.506375227686704e-05, "loss": 1.3357, "step": 468 }, { "epoch": 0.025641551341192552, "grad_norm": 4.296029090881348, "learning_rate": 8.524590163934426e-05, "loss": 1.4263, "step": 469 }, { "epoch": 0.02569622415855117, "grad_norm": 4.276191234588623, "learning_rate": 8.54280510018215e-05, "loss": 1.4819, "step": 470 }, { "epoch": 0.02575089697590979, "grad_norm": 4.3417510986328125, "learning_rate": 8.561020036429874e-05, "loss": 1.2053, "step": 471 }, { "epoch": 0.02580556979326841, "grad_norm": 4.348049163818359, "learning_rate": 8.579234972677596e-05, "loss": 1.3349, "step": 472 }, { "epoch": 0.02586024261062703, "grad_norm": 5.3231096267700195, "learning_rate": 8.597449908925319e-05, "loss": 1.1316, "step": 473 }, { "epoch": 0.025914915427985647, "grad_norm": 4.585947036743164, "learning_rate": 8.615664845173043e-05, "loss": 1.4832, "step": 474 }, { "epoch": 0.025969588245344268, "grad_norm": 4.07829475402832, "learning_rate": 8.633879781420766e-05, "loss": 1.4141, "step": 475 }, { "epoch": 0.026024261062702888, "grad_norm": 5.068504333496094, "learning_rate": 8.652094717668488e-05, "loss": 1.5077, "step": 476 }, { "epoch": 0.02607893388006151, "grad_norm": 4.209282398223877, "learning_rate": 8.670309653916212e-05, "loss": 1.2735, "step": 477 }, { "epoch": 0.026133606697420125, "grad_norm": 3.44846773147583, "learning_rate": 8.688524590163935e-05, "loss": 1.1684, "step": 478 }, { "epoch": 0.026188279514778746, "grad_norm": 3.2176129817962646, "learning_rate": 8.706739526411657e-05, "loss": 1.2403, "step": 479 }, { "epoch": 0.026242952332137366, "grad_norm": 4.811584949493408, "learning_rate": 8.724954462659381e-05, "loss": 1.2913, "step": 480 }, { "epoch": 0.026297625149495987, "grad_norm": 4.772687911987305, "learning_rate": 8.743169398907104e-05, "loss": 0.9627, "step": 481 }, { "epoch": 0.026352297966854604, "grad_norm": 3.71602463722229, "learning_rate": 8.761384335154828e-05, "loss": 1.2075, "step": 482 }, { "epoch": 0.026406970784213224, "grad_norm": 3.5427513122558594, "learning_rate": 8.779599271402551e-05, "loss": 1.2951, "step": 483 }, { "epoch": 0.026461643601571844, "grad_norm": 2.9463284015655518, "learning_rate": 8.797814207650273e-05, "loss": 1.2155, "step": 484 }, { "epoch": 0.02651631641893046, "grad_norm": 4.205928802490234, "learning_rate": 8.816029143897997e-05, "loss": 1.4118, "step": 485 }, { "epoch": 0.026570989236289082, "grad_norm": 6.0372819900512695, "learning_rate": 8.83424408014572e-05, "loss": 1.1092, "step": 486 }, { "epoch": 0.026625662053647702, "grad_norm": 4.638123512268066, "learning_rate": 8.852459016393443e-05, "loss": 1.3308, "step": 487 }, { "epoch": 0.026680334871006323, "grad_norm": 4.086511135101318, "learning_rate": 8.870673952641167e-05, "loss": 1.3138, "step": 488 }, { "epoch": 0.02673500768836494, "grad_norm": 3.378574848175049, "learning_rate": 8.888888888888889e-05, "loss": 1.211, "step": 489 }, { "epoch": 0.02678968050572356, "grad_norm": 6.084384918212891, "learning_rate": 8.907103825136612e-05, "loss": 1.1976, "step": 490 }, { "epoch": 0.02684435332308218, "grad_norm": 5.210426330566406, "learning_rate": 8.925318761384336e-05, "loss": 1.1206, "step": 491 }, { "epoch": 0.0268990261404408, "grad_norm": 3.398314952850342, "learning_rate": 8.943533697632059e-05, "loss": 1.161, "step": 492 }, { "epoch": 0.026953698957799418, "grad_norm": 4.051161766052246, "learning_rate": 8.961748633879781e-05, "loss": 1.3892, "step": 493 }, { "epoch": 0.027008371775158038, "grad_norm": 4.024576187133789, "learning_rate": 8.979963570127505e-05, "loss": 1.3884, "step": 494 }, { "epoch": 0.02706304459251666, "grad_norm": 4.568589210510254, "learning_rate": 8.998178506375228e-05, "loss": 1.3368, "step": 495 }, { "epoch": 0.02711771740987528, "grad_norm": 4.280048847198486, "learning_rate": 9.016393442622952e-05, "loss": 1.3243, "step": 496 }, { "epoch": 0.027172390227233896, "grad_norm": 4.831751823425293, "learning_rate": 9.034608378870675e-05, "loss": 1.5671, "step": 497 }, { "epoch": 0.027227063044592516, "grad_norm": 2.890814781188965, "learning_rate": 9.052823315118397e-05, "loss": 1.0464, "step": 498 }, { "epoch": 0.027281735861951137, "grad_norm": 4.356666088104248, "learning_rate": 9.071038251366121e-05, "loss": 1.2705, "step": 499 }, { "epoch": 0.027336408679309757, "grad_norm": 3.4500718116760254, "learning_rate": 9.089253187613844e-05, "loss": 1.3524, "step": 500 }, { "epoch": 0.027391081496668374, "grad_norm": 4.12678337097168, "learning_rate": 9.107468123861566e-05, "loss": 1.2787, "step": 501 }, { "epoch": 0.027445754314026995, "grad_norm": 3.609076738357544, "learning_rate": 9.12568306010929e-05, "loss": 1.4056, "step": 502 }, { "epoch": 0.027500427131385615, "grad_norm": 3.7414371967315674, "learning_rate": 9.143897996357013e-05, "loss": 1.3881, "step": 503 }, { "epoch": 0.027555099948744232, "grad_norm": 3.26664137840271, "learning_rate": 9.162112932604736e-05, "loss": 1.3183, "step": 504 }, { "epoch": 0.027609772766102852, "grad_norm": 5.210188865661621, "learning_rate": 9.18032786885246e-05, "loss": 1.4579, "step": 505 }, { "epoch": 0.027664445583461473, "grad_norm": 3.9507503509521484, "learning_rate": 9.198542805100182e-05, "loss": 1.2625, "step": 506 }, { "epoch": 0.027719118400820093, "grad_norm": 4.376821041107178, "learning_rate": 9.216757741347905e-05, "loss": 1.3757, "step": 507 }, { "epoch": 0.02777379121817871, "grad_norm": 3.5136475563049316, "learning_rate": 9.234972677595629e-05, "loss": 1.2499, "step": 508 }, { "epoch": 0.02782846403553733, "grad_norm": 4.900085926055908, "learning_rate": 9.253187613843352e-05, "loss": 1.173, "step": 509 }, { "epoch": 0.02788313685289595, "grad_norm": 2.8927440643310547, "learning_rate": 9.271402550091076e-05, "loss": 1.1485, "step": 510 }, { "epoch": 0.02793780967025457, "grad_norm": 5.062407970428467, "learning_rate": 9.289617486338798e-05, "loss": 1.6669, "step": 511 }, { "epoch": 0.02799248248761319, "grad_norm": 4.33477783203125, "learning_rate": 9.307832422586521e-05, "loss": 1.266, "step": 512 }, { "epoch": 0.02804715530497181, "grad_norm": 4.010003566741943, "learning_rate": 9.326047358834245e-05, "loss": 1.4171, "step": 513 }, { "epoch": 0.02810182812233043, "grad_norm": 3.94482159614563, "learning_rate": 9.344262295081968e-05, "loss": 1.3718, "step": 514 }, { "epoch": 0.02815650093968905, "grad_norm": 3.9183835983276367, "learning_rate": 9.36247723132969e-05, "loss": 1.4526, "step": 515 }, { "epoch": 0.028211173757047667, "grad_norm": 5.3234052658081055, "learning_rate": 9.380692167577414e-05, "loss": 1.2744, "step": 516 }, { "epoch": 0.028265846574406287, "grad_norm": 4.113526344299316, "learning_rate": 9.398907103825137e-05, "loss": 1.2841, "step": 517 }, { "epoch": 0.028320519391764908, "grad_norm": 3.254534959793091, "learning_rate": 9.41712204007286e-05, "loss": 1.3161, "step": 518 }, { "epoch": 0.028375192209123528, "grad_norm": 3.3223202228546143, "learning_rate": 9.435336976320584e-05, "loss": 1.2694, "step": 519 }, { "epoch": 0.028429865026482145, "grad_norm": 3.2001311779022217, "learning_rate": 9.453551912568308e-05, "loss": 1.2303, "step": 520 }, { "epoch": 0.028484537843840765, "grad_norm": 4.774428367614746, "learning_rate": 9.471766848816029e-05, "loss": 1.5047, "step": 521 }, { "epoch": 0.028539210661199386, "grad_norm": 3.7908053398132324, "learning_rate": 9.489981785063753e-05, "loss": 1.2554, "step": 522 }, { "epoch": 0.028593883478558003, "grad_norm": 3.5563745498657227, "learning_rate": 9.508196721311476e-05, "loss": 1.3173, "step": 523 }, { "epoch": 0.028648556295916623, "grad_norm": 3.906862258911133, "learning_rate": 9.5264116575592e-05, "loss": 1.5067, "step": 524 }, { "epoch": 0.028703229113275244, "grad_norm": 4.1342973709106445, "learning_rate": 9.544626593806922e-05, "loss": 1.4679, "step": 525 }, { "epoch": 0.028757901930633864, "grad_norm": 5.337989330291748, "learning_rate": 9.562841530054645e-05, "loss": 1.4584, "step": 526 }, { "epoch": 0.02881257474799248, "grad_norm": 3.7935397624969482, "learning_rate": 9.581056466302369e-05, "loss": 1.3417, "step": 527 }, { "epoch": 0.0288672475653511, "grad_norm": 3.5447211265563965, "learning_rate": 9.599271402550091e-05, "loss": 1.2197, "step": 528 }, { "epoch": 0.028921920382709722, "grad_norm": 4.080278396606445, "learning_rate": 9.617486338797814e-05, "loss": 1.4477, "step": 529 }, { "epoch": 0.028976593200068342, "grad_norm": 3.279963970184326, "learning_rate": 9.635701275045538e-05, "loss": 1.4926, "step": 530 }, { "epoch": 0.02903126601742696, "grad_norm": 4.035837173461914, "learning_rate": 9.653916211293261e-05, "loss": 1.4969, "step": 531 }, { "epoch": 0.02908593883478558, "grad_norm": 7.136292457580566, "learning_rate": 9.672131147540983e-05, "loss": 1.4182, "step": 532 }, { "epoch": 0.0291406116521442, "grad_norm": 4.837482452392578, "learning_rate": 9.690346083788707e-05, "loss": 1.49, "step": 533 }, { "epoch": 0.02919528446950282, "grad_norm": 3.5301408767700195, "learning_rate": 9.708561020036431e-05, "loss": 1.3825, "step": 534 }, { "epoch": 0.029249957286861437, "grad_norm": 3.406857967376709, "learning_rate": 9.726775956284153e-05, "loss": 1.34, "step": 535 }, { "epoch": 0.029304630104220058, "grad_norm": 3.6014537811279297, "learning_rate": 9.744990892531877e-05, "loss": 1.4, "step": 536 }, { "epoch": 0.02935930292157868, "grad_norm": 3.076314926147461, "learning_rate": 9.7632058287796e-05, "loss": 1.2364, "step": 537 }, { "epoch": 0.0294139757389373, "grad_norm": 3.944206476211548, "learning_rate": 9.781420765027322e-05, "loss": 1.1941, "step": 538 }, { "epoch": 0.029468648556295916, "grad_norm": 3.1980302333831787, "learning_rate": 9.799635701275046e-05, "loss": 1.202, "step": 539 }, { "epoch": 0.029523321373654536, "grad_norm": 4.221316814422607, "learning_rate": 9.81785063752277e-05, "loss": 1.4504, "step": 540 }, { "epoch": 0.029577994191013156, "grad_norm": 3.9971935749053955, "learning_rate": 9.836065573770493e-05, "loss": 1.4133, "step": 541 }, { "epoch": 0.029632667008371773, "grad_norm": 4.647497653961182, "learning_rate": 9.854280510018215e-05, "loss": 1.4768, "step": 542 }, { "epoch": 0.029687339825730394, "grad_norm": 3.378541946411133, "learning_rate": 9.872495446265938e-05, "loss": 1.3075, "step": 543 }, { "epoch": 0.029742012643089014, "grad_norm": 3.7452707290649414, "learning_rate": 9.890710382513662e-05, "loss": 1.3331, "step": 544 }, { "epoch": 0.029796685460447635, "grad_norm": 4.309234619140625, "learning_rate": 9.908925318761385e-05, "loss": 1.4246, "step": 545 }, { "epoch": 0.02985135827780625, "grad_norm": 3.385349750518799, "learning_rate": 9.927140255009107e-05, "loss": 1.2334, "step": 546 }, { "epoch": 0.029906031095164872, "grad_norm": 4.975132942199707, "learning_rate": 9.945355191256831e-05, "loss": 1.41, "step": 547 }, { "epoch": 0.029960703912523493, "grad_norm": 4.2791314125061035, "learning_rate": 9.963570127504555e-05, "loss": 1.3838, "step": 548 }, { "epoch": 0.030015376729882113, "grad_norm": 3.3676462173461914, "learning_rate": 9.981785063752276e-05, "loss": 1.4514, "step": 549 }, { "epoch": 0.03007004954724073, "grad_norm": 4.837583541870117, "learning_rate": 0.0001, "loss": 1.2915, "step": 550 }, { "epoch": 0.03012472236459935, "grad_norm": 4.814086437225342, "learning_rate": 9.999999921614704e-05, "loss": 1.3267, "step": 551 }, { "epoch": 0.03017939518195797, "grad_norm": 3.255797863006592, "learning_rate": 9.999999686458818e-05, "loss": 1.2689, "step": 552 }, { "epoch": 0.03023406799931659, "grad_norm": 3.9846770763397217, "learning_rate": 9.99999929453235e-05, "loss": 1.3859, "step": 553 }, { "epoch": 0.030288740816675208, "grad_norm": 3.687631845474243, "learning_rate": 9.999998745835313e-05, "loss": 1.4651, "step": 554 }, { "epoch": 0.03034341363403383, "grad_norm": 3.7236273288726807, "learning_rate": 9.999998040367722e-05, "loss": 1.3185, "step": 555 }, { "epoch": 0.03039808645139245, "grad_norm": 2.7627060413360596, "learning_rate": 9.999997178129599e-05, "loss": 1.3004, "step": 556 }, { "epoch": 0.03045275926875107, "grad_norm": 4.213595390319824, "learning_rate": 9.999996159120975e-05, "loss": 1.4232, "step": 557 }, { "epoch": 0.030507432086109686, "grad_norm": 3.683349132537842, "learning_rate": 9.999994983341877e-05, "loss": 1.3829, "step": 558 }, { "epoch": 0.030562104903468307, "grad_norm": 3.5564422607421875, "learning_rate": 9.999993650792346e-05, "loss": 1.2893, "step": 559 }, { "epoch": 0.030616777720826927, "grad_norm": 4.515560150146484, "learning_rate": 9.99999216147242e-05, "loss": 1.37, "step": 560 }, { "epoch": 0.030671450538185544, "grad_norm": 5.873238563537598, "learning_rate": 9.99999051538215e-05, "loss": 1.3494, "step": 561 }, { "epoch": 0.030726123355544165, "grad_norm": 3.3253173828125, "learning_rate": 9.999988712521582e-05, "loss": 1.2877, "step": 562 }, { "epoch": 0.030780796172902785, "grad_norm": 7.070398330688477, "learning_rate": 9.999986752890778e-05, "loss": 1.2168, "step": 563 }, { "epoch": 0.030835468990261405, "grad_norm": 6.598282337188721, "learning_rate": 9.999984636489797e-05, "loss": 1.2152, "step": 564 }, { "epoch": 0.030890141807620022, "grad_norm": 3.9105396270751953, "learning_rate": 9.999982363318705e-05, "loss": 1.2115, "step": 565 }, { "epoch": 0.030944814624978643, "grad_norm": 3.9879937171936035, "learning_rate": 9.999979933377574e-05, "loss": 1.359, "step": 566 }, { "epoch": 0.030999487442337263, "grad_norm": 10.791892051696777, "learning_rate": 9.999977346666481e-05, "loss": 1.4654, "step": 567 }, { "epoch": 0.031054160259695884, "grad_norm": 4.262570381164551, "learning_rate": 9.999974603185504e-05, "loss": 1.4009, "step": 568 }, { "epoch": 0.0311088330770545, "grad_norm": 3.515204906463623, "learning_rate": 9.999971702934733e-05, "loss": 1.3107, "step": 569 }, { "epoch": 0.03116350589441312, "grad_norm": 3.8201746940612793, "learning_rate": 9.999968645914257e-05, "loss": 1.3957, "step": 570 }, { "epoch": 0.03121817871177174, "grad_norm": 4.190408706665039, "learning_rate": 9.999965432124171e-05, "loss": 1.3976, "step": 571 }, { "epoch": 0.03127285152913036, "grad_norm": 3.300948143005371, "learning_rate": 9.999962061564578e-05, "loss": 1.5506, "step": 572 }, { "epoch": 0.03132752434648898, "grad_norm": 3.8606693744659424, "learning_rate": 9.99995853423558e-05, "loss": 1.2556, "step": 573 }, { "epoch": 0.0313821971638476, "grad_norm": 3.823758363723755, "learning_rate": 9.999954850137292e-05, "loss": 1.3533, "step": 574 }, { "epoch": 0.03143686998120622, "grad_norm": 4.219339370727539, "learning_rate": 9.999951009269827e-05, "loss": 1.3617, "step": 575 }, { "epoch": 0.03149154279856484, "grad_norm": 3.373399019241333, "learning_rate": 9.999947011633306e-05, "loss": 1.3918, "step": 576 }, { "epoch": 0.03154621561592346, "grad_norm": 3.2110278606414795, "learning_rate": 9.999942857227853e-05, "loss": 1.4418, "step": 577 }, { "epoch": 0.03160088843328208, "grad_norm": 5.392617225646973, "learning_rate": 9.999938546053601e-05, "loss": 1.34, "step": 578 }, { "epoch": 0.031655561250640694, "grad_norm": 3.1591789722442627, "learning_rate": 9.999934078110683e-05, "loss": 1.2373, "step": 579 }, { "epoch": 0.03171023406799932, "grad_norm": 3.20074725151062, "learning_rate": 9.99992945339924e-05, "loss": 1.4197, "step": 580 }, { "epoch": 0.031764906885357935, "grad_norm": 3.496417284011841, "learning_rate": 9.999924671919418e-05, "loss": 1.3726, "step": 581 }, { "epoch": 0.03181957970271655, "grad_norm": 4.988031387329102, "learning_rate": 9.999919733671364e-05, "loss": 1.5888, "step": 582 }, { "epoch": 0.031874252520075176, "grad_norm": 2.5863277912139893, "learning_rate": 9.999914638655235e-05, "loss": 1.185, "step": 583 }, { "epoch": 0.03192892533743379, "grad_norm": 3.6305177211761475, "learning_rate": 9.999909386871189e-05, "loss": 1.2977, "step": 584 }, { "epoch": 0.03198359815479242, "grad_norm": 3.5276849269866943, "learning_rate": 9.999903978319394e-05, "loss": 1.4154, "step": 585 }, { "epoch": 0.032038270972151034, "grad_norm": 3.744565725326538, "learning_rate": 9.999898413000018e-05, "loss": 1.3688, "step": 586 }, { "epoch": 0.03209294378950965, "grad_norm": 3.5075113773345947, "learning_rate": 9.999892690913233e-05, "loss": 1.4434, "step": 587 }, { "epoch": 0.032147616606868275, "grad_norm": 3.9923110008239746, "learning_rate": 9.99988681205922e-05, "loss": 1.4433, "step": 588 }, { "epoch": 0.03220228942422689, "grad_norm": 4.409431457519531, "learning_rate": 9.999880776438166e-05, "loss": 1.1879, "step": 589 }, { "epoch": 0.03225696224158551, "grad_norm": 3.466489791870117, "learning_rate": 9.999874584050256e-05, "loss": 1.4673, "step": 590 }, { "epoch": 0.03231163505894413, "grad_norm": 4.259871006011963, "learning_rate": 9.999868234895688e-05, "loss": 1.4276, "step": 591 }, { "epoch": 0.03236630787630275, "grad_norm": 3.0953750610351562, "learning_rate": 9.999861728974658e-05, "loss": 1.2348, "step": 592 }, { "epoch": 0.03242098069366137, "grad_norm": 3.0041961669921875, "learning_rate": 9.999855066287371e-05, "loss": 1.1068, "step": 593 }, { "epoch": 0.03247565351101999, "grad_norm": 2.8114311695098877, "learning_rate": 9.999848246834036e-05, "loss": 1.248, "step": 594 }, { "epoch": 0.03253032632837861, "grad_norm": 5.457528114318848, "learning_rate": 9.999841270614868e-05, "loss": 1.1422, "step": 595 }, { "epoch": 0.03258499914573723, "grad_norm": 4.022302627563477, "learning_rate": 9.999834137630084e-05, "loss": 1.3299, "step": 596 }, { "epoch": 0.03263967196309585, "grad_norm": 4.3841962814331055, "learning_rate": 9.999826847879909e-05, "loss": 1.6112, "step": 597 }, { "epoch": 0.032694344780454465, "grad_norm": 3.6467909812927246, "learning_rate": 9.99981940136457e-05, "loss": 1.2807, "step": 598 }, { "epoch": 0.03274901759781309, "grad_norm": 4.183506488800049, "learning_rate": 9.999811798084302e-05, "loss": 1.364, "step": 599 }, { "epoch": 0.032803690415171706, "grad_norm": 3.595435857772827, "learning_rate": 9.999804038039342e-05, "loss": 1.4542, "step": 600 }, { "epoch": 0.03285836323253032, "grad_norm": 2.6858060359954834, "learning_rate": 9.999796121229934e-05, "loss": 1.2186, "step": 601 }, { "epoch": 0.03291303604988895, "grad_norm": 3.6792807579040527, "learning_rate": 9.999788047656328e-05, "loss": 1.3703, "step": 602 }, { "epoch": 0.032967708867247564, "grad_norm": 3.1009621620178223, "learning_rate": 9.999779817318774e-05, "loss": 1.3564, "step": 603 }, { "epoch": 0.03302238168460619, "grad_norm": 3.7735109329223633, "learning_rate": 9.999771430217532e-05, "loss": 1.5281, "step": 604 }, { "epoch": 0.033077054501964805, "grad_norm": 4.051596641540527, "learning_rate": 9.999762886352863e-05, "loss": 1.2325, "step": 605 }, { "epoch": 0.03313172731932342, "grad_norm": 5.635488986968994, "learning_rate": 9.999754185725039e-05, "loss": 1.2599, "step": 606 }, { "epoch": 0.033186400136682045, "grad_norm": 3.799712657928467, "learning_rate": 9.999745328334327e-05, "loss": 1.4042, "step": 607 }, { "epoch": 0.03324107295404066, "grad_norm": 4.097114562988281, "learning_rate": 9.999736314181009e-05, "loss": 0.9693, "step": 608 }, { "epoch": 0.03329574577139928, "grad_norm": 4.450078010559082, "learning_rate": 9.999727143265368e-05, "loss": 1.2462, "step": 609 }, { "epoch": 0.0333504185887579, "grad_norm": 3.27534818649292, "learning_rate": 9.999717815587689e-05, "loss": 1.2712, "step": 610 }, { "epoch": 0.03340509140611652, "grad_norm": 3.5236120223999023, "learning_rate": 9.999708331148266e-05, "loss": 1.403, "step": 611 }, { "epoch": 0.033459764223475144, "grad_norm": 3.469472646713257, "learning_rate": 9.999698689947395e-05, "loss": 1.484, "step": 612 }, { "epoch": 0.03351443704083376, "grad_norm": 5.606902122497559, "learning_rate": 9.999688891985379e-05, "loss": 1.6904, "step": 613 }, { "epoch": 0.03356910985819238, "grad_norm": 3.675304651260376, "learning_rate": 9.999678937262527e-05, "loss": 1.3893, "step": 614 }, { "epoch": 0.033623782675551, "grad_norm": 3.920269727706909, "learning_rate": 9.999668825779147e-05, "loss": 1.4753, "step": 615 }, { "epoch": 0.03367845549290962, "grad_norm": 3.5589873790740967, "learning_rate": 9.99965855753556e-05, "loss": 1.2576, "step": 616 }, { "epoch": 0.033733128310268236, "grad_norm": 3.733863115310669, "learning_rate": 9.999648132532086e-05, "loss": 1.4685, "step": 617 }, { "epoch": 0.03378780112762686, "grad_norm": 3.289186477661133, "learning_rate": 9.999637550769053e-05, "loss": 1.2118, "step": 618 }, { "epoch": 0.03384247394498548, "grad_norm": 3.2992756366729736, "learning_rate": 9.999626812246792e-05, "loss": 1.2645, "step": 619 }, { "epoch": 0.033897146762344094, "grad_norm": 9.785859107971191, "learning_rate": 9.999615916965639e-05, "loss": 1.369, "step": 620 }, { "epoch": 0.03395181957970272, "grad_norm": 4.018148422241211, "learning_rate": 9.999604864925938e-05, "loss": 1.5824, "step": 621 }, { "epoch": 0.034006492397061334, "grad_norm": 3.775534152984619, "learning_rate": 9.999593656128032e-05, "loss": 1.3983, "step": 622 }, { "epoch": 0.03406116521441996, "grad_norm": 2.6757652759552, "learning_rate": 9.999582290572275e-05, "loss": 1.2638, "step": 623 }, { "epoch": 0.034115838031778575, "grad_norm": 2.8758280277252197, "learning_rate": 9.999570768259023e-05, "loss": 1.1671, "step": 624 }, { "epoch": 0.03417051084913719, "grad_norm": 3.0830256938934326, "learning_rate": 9.999559089188639e-05, "loss": 1.3152, "step": 625 }, { "epoch": 0.034225183666495816, "grad_norm": 3.688011884689331, "learning_rate": 9.999547253361485e-05, "loss": 1.3595, "step": 626 }, { "epoch": 0.03427985648385443, "grad_norm": 3.9333853721618652, "learning_rate": 9.999535260777934e-05, "loss": 1.1144, "step": 627 }, { "epoch": 0.03433452930121305, "grad_norm": 5.853853225708008, "learning_rate": 9.999523111438362e-05, "loss": 1.259, "step": 628 }, { "epoch": 0.034389202118571674, "grad_norm": 2.8043289184570312, "learning_rate": 9.999510805343153e-05, "loss": 1.344, "step": 629 }, { "epoch": 0.03444387493593029, "grad_norm": 2.746051549911499, "learning_rate": 9.999498342492688e-05, "loss": 1.2496, "step": 630 }, { "epoch": 0.034498547753288915, "grad_norm": 3.2410452365875244, "learning_rate": 9.999485722887361e-05, "loss": 1.1987, "step": 631 }, { "epoch": 0.03455322057064753, "grad_norm": 3.1683595180511475, "learning_rate": 9.999472946527565e-05, "loss": 1.3397, "step": 632 }, { "epoch": 0.03460789338800615, "grad_norm": 3.448471784591675, "learning_rate": 9.999460013413702e-05, "loss": 1.4759, "step": 633 }, { "epoch": 0.03466256620536477, "grad_norm": 3.026221513748169, "learning_rate": 9.99944692354618e-05, "loss": 1.1624, "step": 634 }, { "epoch": 0.03471723902272339, "grad_norm": 3.4444632530212402, "learning_rate": 9.999433676925405e-05, "loss": 1.5838, "step": 635 }, { "epoch": 0.034771911840082007, "grad_norm": 3.518807888031006, "learning_rate": 9.999420273551795e-05, "loss": 1.3278, "step": 636 }, { "epoch": 0.03482658465744063, "grad_norm": 4.057284355163574, "learning_rate": 9.99940671342577e-05, "loss": 1.325, "step": 637 }, { "epoch": 0.03488125747479925, "grad_norm": 2.9284632205963135, "learning_rate": 9.999392996547754e-05, "loss": 1.3296, "step": 638 }, { "epoch": 0.034935930292157864, "grad_norm": 5.730686187744141, "learning_rate": 9.999379122918179e-05, "loss": 1.3851, "step": 639 }, { "epoch": 0.03499060310951649, "grad_norm": 3.439176082611084, "learning_rate": 9.999365092537479e-05, "loss": 1.5026, "step": 640 }, { "epoch": 0.035045275926875105, "grad_norm": 3.2460174560546875, "learning_rate": 9.999350905406092e-05, "loss": 1.3767, "step": 641 }, { "epoch": 0.03509994874423373, "grad_norm": 3.885889768600464, "learning_rate": 9.999336561524467e-05, "loss": 1.3512, "step": 642 }, { "epoch": 0.035154621561592346, "grad_norm": 3.384258270263672, "learning_rate": 9.99932206089305e-05, "loss": 1.5798, "step": 643 }, { "epoch": 0.03520929437895096, "grad_norm": 4.264559745788574, "learning_rate": 9.999307403512297e-05, "loss": 1.6199, "step": 644 }, { "epoch": 0.03526396719630959, "grad_norm": 2.9892468452453613, "learning_rate": 9.999292589382667e-05, "loss": 1.1195, "step": 645 }, { "epoch": 0.035318640013668204, "grad_norm": 4.689758777618408, "learning_rate": 9.999277618504625e-05, "loss": 1.2095, "step": 646 }, { "epoch": 0.03537331283102682, "grad_norm": 5.443565368652344, "learning_rate": 9.999262490878642e-05, "loss": 1.3858, "step": 647 }, { "epoch": 0.035427985648385445, "grad_norm": 3.2192461490631104, "learning_rate": 9.999247206505191e-05, "loss": 1.3689, "step": 648 }, { "epoch": 0.03548265846574406, "grad_norm": 4.189196586608887, "learning_rate": 9.99923176538475e-05, "loss": 1.5658, "step": 649 }, { "epoch": 0.035537331283102686, "grad_norm": 3.111745834350586, "learning_rate": 9.999216167517805e-05, "loss": 1.4706, "step": 650 }, { "epoch": 0.0355920041004613, "grad_norm": 3.525500774383545, "learning_rate": 9.999200412904842e-05, "loss": 1.2506, "step": 651 }, { "epoch": 0.03564667691781992, "grad_norm": 4.429937362670898, "learning_rate": 9.999184501546359e-05, "loss": 1.3107, "step": 652 }, { "epoch": 0.03570134973517854, "grad_norm": 3.3541460037231445, "learning_rate": 9.999168433442853e-05, "loss": 1.3464, "step": 653 }, { "epoch": 0.03575602255253716, "grad_norm": 3.0833256244659424, "learning_rate": 9.999152208594827e-05, "loss": 1.2386, "step": 654 }, { "epoch": 0.03581069536989578, "grad_norm": 3.529439687728882, "learning_rate": 9.999135827002793e-05, "loss": 1.5087, "step": 655 }, { "epoch": 0.0358653681872544, "grad_norm": 2.963900089263916, "learning_rate": 9.999119288667259e-05, "loss": 1.3349, "step": 656 }, { "epoch": 0.03592004100461302, "grad_norm": 3.3468267917633057, "learning_rate": 9.999102593588748e-05, "loss": 1.5033, "step": 657 }, { "epoch": 0.035974713821971635, "grad_norm": 3.549858808517456, "learning_rate": 9.999085741767783e-05, "loss": 1.3179, "step": 658 }, { "epoch": 0.03602938663933026, "grad_norm": 3.3914902210235596, "learning_rate": 9.99906873320489e-05, "loss": 1.3897, "step": 659 }, { "epoch": 0.036084059456688876, "grad_norm": 2.599684476852417, "learning_rate": 9.999051567900606e-05, "loss": 1.2712, "step": 660 }, { "epoch": 0.0361387322740475, "grad_norm": 4.5590949058532715, "learning_rate": 9.999034245855466e-05, "loss": 1.419, "step": 661 }, { "epoch": 0.03619340509140612, "grad_norm": 4.719365119934082, "learning_rate": 9.999016767070016e-05, "loss": 1.207, "step": 662 }, { "epoch": 0.036248077908764734, "grad_norm": 4.166406154632568, "learning_rate": 9.998999131544799e-05, "loss": 1.5033, "step": 663 }, { "epoch": 0.03630275072612336, "grad_norm": 3.794735908508301, "learning_rate": 9.998981339280373e-05, "loss": 1.2791, "step": 664 }, { "epoch": 0.036357423543481975, "grad_norm": 3.09086275100708, "learning_rate": 9.998963390277295e-05, "loss": 1.1993, "step": 665 }, { "epoch": 0.03641209636084059, "grad_norm": 3.0870578289031982, "learning_rate": 9.998945284536125e-05, "loss": 1.3969, "step": 666 }, { "epoch": 0.036466769178199215, "grad_norm": 2.871570587158203, "learning_rate": 9.998927022057432e-05, "loss": 1.3561, "step": 667 }, { "epoch": 0.03652144199555783, "grad_norm": 3.819312572479248, "learning_rate": 9.99890860284179e-05, "loss": 1.1961, "step": 668 }, { "epoch": 0.036576114812916456, "grad_norm": 3.5681169033050537, "learning_rate": 9.998890026889775e-05, "loss": 1.3132, "step": 669 }, { "epoch": 0.03663078763027507, "grad_norm": 2.8131062984466553, "learning_rate": 9.998871294201973e-05, "loss": 1.3677, "step": 670 }, { "epoch": 0.03668546044763369, "grad_norm": 2.921414852142334, "learning_rate": 9.998852404778965e-05, "loss": 1.1942, "step": 671 }, { "epoch": 0.036740133264992314, "grad_norm": 3.256760358810425, "learning_rate": 9.99883335862135e-05, "loss": 1.5009, "step": 672 }, { "epoch": 0.03679480608235093, "grad_norm": 4.207677364349365, "learning_rate": 9.99881415572972e-05, "loss": 1.0968, "step": 673 }, { "epoch": 0.03684947889970955, "grad_norm": 2.732407331466675, "learning_rate": 9.998794796104678e-05, "loss": 1.3057, "step": 674 }, { "epoch": 0.03690415171706817, "grad_norm": 3.0601024627685547, "learning_rate": 9.998775279746833e-05, "loss": 1.2657, "step": 675 }, { "epoch": 0.03695882453442679, "grad_norm": 3.0050911903381348, "learning_rate": 9.998755606656796e-05, "loss": 1.2741, "step": 676 }, { "epoch": 0.037013497351785406, "grad_norm": 3.2041215896606445, "learning_rate": 9.998735776835181e-05, "loss": 1.4681, "step": 677 }, { "epoch": 0.03706817016914403, "grad_norm": 3.0066111087799072, "learning_rate": 9.998715790282615e-05, "loss": 1.2956, "step": 678 }, { "epoch": 0.03712284298650265, "grad_norm": 2.8952550888061523, "learning_rate": 9.998695646999723e-05, "loss": 1.2599, "step": 679 }, { "epoch": 0.03717751580386127, "grad_norm": 3.105340003967285, "learning_rate": 9.998675346987134e-05, "loss": 1.2714, "step": 680 }, { "epoch": 0.03723218862121989, "grad_norm": 3.1114556789398193, "learning_rate": 9.998654890245486e-05, "loss": 1.4387, "step": 681 }, { "epoch": 0.037286861438578504, "grad_norm": 4.604922771453857, "learning_rate": 9.998634276775423e-05, "loss": 1.4288, "step": 682 }, { "epoch": 0.03734153425593713, "grad_norm": 3.694889783859253, "learning_rate": 9.998613506577588e-05, "loss": 1.4267, "step": 683 }, { "epoch": 0.037396207073295745, "grad_norm": 4.5518012046813965, "learning_rate": 9.998592579652631e-05, "loss": 1.4666, "step": 684 }, { "epoch": 0.03745087989065436, "grad_norm": 3.1954989433288574, "learning_rate": 9.998571496001212e-05, "loss": 1.3293, "step": 685 }, { "epoch": 0.037505552708012986, "grad_norm": 2.6701345443725586, "learning_rate": 9.998550255623991e-05, "loss": 1.1483, "step": 686 }, { "epoch": 0.0375602255253716, "grad_norm": 2.9661879539489746, "learning_rate": 9.998528858521632e-05, "loss": 1.1979, "step": 687 }, { "epoch": 0.03761489834273023, "grad_norm": 5.800083160400391, "learning_rate": 9.998507304694806e-05, "loss": 1.4552, "step": 688 }, { "epoch": 0.037669571160088844, "grad_norm": 6.563797473907471, "learning_rate": 9.998485594144192e-05, "loss": 1.3883, "step": 689 }, { "epoch": 0.03772424397744746, "grad_norm": 4.0115461349487305, "learning_rate": 9.998463726870468e-05, "loss": 1.6519, "step": 690 }, { "epoch": 0.037778916794806085, "grad_norm": 3.796632766723633, "learning_rate": 9.998441702874321e-05, "loss": 1.4895, "step": 691 }, { "epoch": 0.0378335896121647, "grad_norm": 3.6231956481933594, "learning_rate": 9.99841952215644e-05, "loss": 1.5201, "step": 692 }, { "epoch": 0.03788826242952332, "grad_norm": 2.993523359298706, "learning_rate": 9.998397184717521e-05, "loss": 1.2958, "step": 693 }, { "epoch": 0.03794293524688194, "grad_norm": 3.1052205562591553, "learning_rate": 9.998374690558265e-05, "loss": 1.192, "step": 694 }, { "epoch": 0.03799760806424056, "grad_norm": 4.169399738311768, "learning_rate": 9.998352039679378e-05, "loss": 1.3984, "step": 695 }, { "epoch": 0.03805228088159918, "grad_norm": 4.816753387451172, "learning_rate": 9.998329232081569e-05, "loss": 1.2583, "step": 696 }, { "epoch": 0.0381069536989578, "grad_norm": 3.360452651977539, "learning_rate": 9.998306267765554e-05, "loss": 1.4232, "step": 697 }, { "epoch": 0.03816162651631642, "grad_norm": 2.941601037979126, "learning_rate": 9.99828314673205e-05, "loss": 1.3131, "step": 698 }, { "epoch": 0.03821629933367504, "grad_norm": 4.190195083618164, "learning_rate": 9.998259868981785e-05, "loss": 1.434, "step": 699 }, { "epoch": 0.03827097215103366, "grad_norm": 3.504560708999634, "learning_rate": 9.998236434515488e-05, "loss": 1.3775, "step": 700 }, { "epoch": 0.038325644968392275, "grad_norm": 6.479394912719727, "learning_rate": 9.998212843333896e-05, "loss": 1.4591, "step": 701 }, { "epoch": 0.0383803177857509, "grad_norm": 2.98636794090271, "learning_rate": 9.998189095437744e-05, "loss": 1.3211, "step": 702 }, { "epoch": 0.038434990603109516, "grad_norm": 4.117654800415039, "learning_rate": 9.998165190827781e-05, "loss": 1.3992, "step": 703 }, { "epoch": 0.03848966342046813, "grad_norm": 3.325253486633301, "learning_rate": 9.998141129504753e-05, "loss": 1.315, "step": 704 }, { "epoch": 0.03854433623782676, "grad_norm": 4.073615074157715, "learning_rate": 9.998116911469418e-05, "loss": 1.266, "step": 705 }, { "epoch": 0.038599009055185374, "grad_norm": 3.670665740966797, "learning_rate": 9.998092536722533e-05, "loss": 1.5966, "step": 706 }, { "epoch": 0.038653681872544, "grad_norm": 3.078049898147583, "learning_rate": 9.99806800526486e-05, "loss": 1.1945, "step": 707 }, { "epoch": 0.038708354689902615, "grad_norm": 4.731141567230225, "learning_rate": 9.998043317097175e-05, "loss": 1.1807, "step": 708 }, { "epoch": 0.03876302750726123, "grad_norm": 3.2017507553100586, "learning_rate": 9.998018472220245e-05, "loss": 1.1665, "step": 709 }, { "epoch": 0.038817700324619855, "grad_norm": 2.4313130378723145, "learning_rate": 9.997993470634852e-05, "loss": 1.2425, "step": 710 }, { "epoch": 0.03887237314197847, "grad_norm": 6.021180152893066, "learning_rate": 9.997968312341782e-05, "loss": 1.6378, "step": 711 }, { "epoch": 0.03892704595933709, "grad_norm": 3.580941677093506, "learning_rate": 9.997942997341818e-05, "loss": 1.623, "step": 712 }, { "epoch": 0.03898171877669571, "grad_norm": 3.9569809436798096, "learning_rate": 9.99791752563576e-05, "loss": 1.4714, "step": 713 }, { "epoch": 0.03903639159405433, "grad_norm": 3.6244354248046875, "learning_rate": 9.997891897224403e-05, "loss": 1.432, "step": 714 }, { "epoch": 0.039091064411412954, "grad_norm": 3.1339969635009766, "learning_rate": 9.997866112108553e-05, "loss": 1.4017, "step": 715 }, { "epoch": 0.03914573722877157, "grad_norm": 2.950774908065796, "learning_rate": 9.997840170289016e-05, "loss": 1.3163, "step": 716 }, { "epoch": 0.03920041004613019, "grad_norm": 5.0477375984191895, "learning_rate": 9.997814071766606e-05, "loss": 1.5134, "step": 717 }, { "epoch": 0.03925508286348881, "grad_norm": 3.4796488285064697, "learning_rate": 9.997787816542141e-05, "loss": 1.4785, "step": 718 }, { "epoch": 0.03930975568084743, "grad_norm": 3.082700252532959, "learning_rate": 9.997761404616447e-05, "loss": 1.3414, "step": 719 }, { "epoch": 0.039364428498206046, "grad_norm": 2.5211663246154785, "learning_rate": 9.997734835990349e-05, "loss": 1.2086, "step": 720 }, { "epoch": 0.03941910131556467, "grad_norm": 4.233959674835205, "learning_rate": 9.997708110664681e-05, "loss": 1.2636, "step": 721 }, { "epoch": 0.03947377413292329, "grad_norm": 4.157278537750244, "learning_rate": 9.99768122864028e-05, "loss": 1.441, "step": 722 }, { "epoch": 0.039528446950281904, "grad_norm": 3.370680332183838, "learning_rate": 9.997654189917993e-05, "loss": 1.3901, "step": 723 }, { "epoch": 0.03958311976764053, "grad_norm": 2.4422435760498047, "learning_rate": 9.997626994498662e-05, "loss": 1.2455, "step": 724 }, { "epoch": 0.039637792584999144, "grad_norm": 3.6123228073120117, "learning_rate": 9.997599642383143e-05, "loss": 1.2793, "step": 725 }, { "epoch": 0.03969246540235777, "grad_norm": 3.2370338439941406, "learning_rate": 9.997572133572293e-05, "loss": 1.2504, "step": 726 }, { "epoch": 0.039747138219716385, "grad_norm": 4.084872245788574, "learning_rate": 9.997544468066973e-05, "loss": 1.337, "step": 727 }, { "epoch": 0.039801811037075, "grad_norm": 2.869335412979126, "learning_rate": 9.997516645868054e-05, "loss": 1.24, "step": 728 }, { "epoch": 0.039856483854433626, "grad_norm": 3.735180139541626, "learning_rate": 9.997488666976406e-05, "loss": 1.5927, "step": 729 }, { "epoch": 0.03991115667179224, "grad_norm": 3.0242972373962402, "learning_rate": 9.997460531392906e-05, "loss": 1.3559, "step": 730 }, { "epoch": 0.03996582948915086, "grad_norm": 3.1583235263824463, "learning_rate": 9.997432239118436e-05, "loss": 1.3366, "step": 731 }, { "epoch": 0.040020502306509484, "grad_norm": 2.4718377590179443, "learning_rate": 9.997403790153886e-05, "loss": 1.1619, "step": 732 }, { "epoch": 0.0400751751238681, "grad_norm": 2.767158031463623, "learning_rate": 9.997375184500143e-05, "loss": 1.4446, "step": 733 }, { "epoch": 0.040129847941226725, "grad_norm": 5.482166290283203, "learning_rate": 9.997346422158107e-05, "loss": 1.3339, "step": 734 }, { "epoch": 0.04018452075858534, "grad_norm": 4.74503231048584, "learning_rate": 9.99731750312868e-05, "loss": 1.5198, "step": 735 }, { "epoch": 0.04023919357594396, "grad_norm": 3.4647650718688965, "learning_rate": 9.997288427412769e-05, "loss": 1.5723, "step": 736 }, { "epoch": 0.04029386639330258, "grad_norm": 2.5953469276428223, "learning_rate": 9.997259195011284e-05, "loss": 1.0534, "step": 737 }, { "epoch": 0.0403485392106612, "grad_norm": 3.0433762073516846, "learning_rate": 9.997229805925142e-05, "loss": 1.5283, "step": 738 }, { "epoch": 0.040403212028019816, "grad_norm": 2.668264389038086, "learning_rate": 9.997200260155267e-05, "loss": 1.1509, "step": 739 }, { "epoch": 0.04045788484537844, "grad_norm": 2.3588573932647705, "learning_rate": 9.99717055770258e-05, "loss": 0.9931, "step": 740 }, { "epoch": 0.04051255766273706, "grad_norm": 3.537348508834839, "learning_rate": 9.997140698568016e-05, "loss": 1.2921, "step": 741 }, { "epoch": 0.040567230480095674, "grad_norm": 4.646623134613037, "learning_rate": 9.997110682752513e-05, "loss": 1.4025, "step": 742 }, { "epoch": 0.0406219032974543, "grad_norm": 3.6900482177734375, "learning_rate": 9.997080510257008e-05, "loss": 1.0735, "step": 743 }, { "epoch": 0.040676576114812915, "grad_norm": 3.5957300662994385, "learning_rate": 9.997050181082451e-05, "loss": 1.2363, "step": 744 }, { "epoch": 0.04073124893217154, "grad_norm": 3.7097702026367188, "learning_rate": 9.997019695229787e-05, "loss": 1.1729, "step": 745 }, { "epoch": 0.040785921749530156, "grad_norm": 2.94211483001709, "learning_rate": 9.996989052699979e-05, "loss": 1.331, "step": 746 }, { "epoch": 0.04084059456688877, "grad_norm": 3.2476449012756348, "learning_rate": 9.996958253493983e-05, "loss": 1.4622, "step": 747 }, { "epoch": 0.0408952673842474, "grad_norm": 3.146294116973877, "learning_rate": 9.996927297612766e-05, "loss": 1.2333, "step": 748 }, { "epoch": 0.040949940201606014, "grad_norm": 7.205667018890381, "learning_rate": 9.9968961850573e-05, "loss": 1.3063, "step": 749 }, { "epoch": 0.04100461301896463, "grad_norm": 5.231132984161377, "learning_rate": 9.996864915828559e-05, "loss": 1.5493, "step": 750 }, { "epoch": 0.041059285836323255, "grad_norm": 4.628636837005615, "learning_rate": 9.996833489927521e-05, "loss": 1.1945, "step": 751 }, { "epoch": 0.04111395865368187, "grad_norm": 3.21201229095459, "learning_rate": 9.996801907355178e-05, "loss": 1.234, "step": 752 }, { "epoch": 0.041168631471040495, "grad_norm": 3.7187142372131348, "learning_rate": 9.996770168112514e-05, "loss": 1.3192, "step": 753 }, { "epoch": 0.04122330428839911, "grad_norm": 3.152798652648926, "learning_rate": 9.996738272200525e-05, "loss": 1.3518, "step": 754 }, { "epoch": 0.04127797710575773, "grad_norm": 2.7550339698791504, "learning_rate": 9.996706219620215e-05, "loss": 1.2608, "step": 755 }, { "epoch": 0.04133264992311635, "grad_norm": 3.5993006229400635, "learning_rate": 9.996674010372586e-05, "loss": 0.9165, "step": 756 }, { "epoch": 0.04138732274047497, "grad_norm": 3.1402506828308105, "learning_rate": 9.996641644458647e-05, "loss": 1.3942, "step": 757 }, { "epoch": 0.04144199555783359, "grad_norm": 3.495856523513794, "learning_rate": 9.996609121879415e-05, "loss": 1.4629, "step": 758 }, { "epoch": 0.04149666837519221, "grad_norm": 4.404745101928711, "learning_rate": 9.99657644263591e-05, "loss": 1.2109, "step": 759 }, { "epoch": 0.04155134119255083, "grad_norm": 2.853426694869995, "learning_rate": 9.996543606729154e-05, "loss": 1.2535, "step": 760 }, { "epoch": 0.041606014009909445, "grad_norm": 2.6906094551086426, "learning_rate": 9.996510614160177e-05, "loss": 1.2536, "step": 761 }, { "epoch": 0.04166068682726807, "grad_norm": 4.236656665802002, "learning_rate": 9.996477464930016e-05, "loss": 1.2852, "step": 762 }, { "epoch": 0.041715359644626686, "grad_norm": 4.92156982421875, "learning_rate": 9.996444159039708e-05, "loss": 1.3542, "step": 763 }, { "epoch": 0.04177003246198531, "grad_norm": 2.942744255065918, "learning_rate": 9.996410696490299e-05, "loss": 1.2701, "step": 764 }, { "epoch": 0.04182470527934393, "grad_norm": 4.4763503074646, "learning_rate": 9.996377077282837e-05, "loss": 1.6179, "step": 765 }, { "epoch": 0.041879378096702544, "grad_norm": 3.526514768600464, "learning_rate": 9.996343301418376e-05, "loss": 1.2755, "step": 766 }, { "epoch": 0.04193405091406117, "grad_norm": 3.077793598175049, "learning_rate": 9.996309368897976e-05, "loss": 1.3962, "step": 767 }, { "epoch": 0.041988723731419784, "grad_norm": 3.3678314685821533, "learning_rate": 9.9962752797227e-05, "loss": 1.09, "step": 768 }, { "epoch": 0.0420433965487784, "grad_norm": 3.667591094970703, "learning_rate": 9.996241033893617e-05, "loss": 1.5156, "step": 769 }, { "epoch": 0.042098069366137025, "grad_norm": 3.52693247795105, "learning_rate": 9.996206631411802e-05, "loss": 1.3003, "step": 770 }, { "epoch": 0.04215274218349564, "grad_norm": 2.4471352100372314, "learning_rate": 9.996172072278332e-05, "loss": 1.2361, "step": 771 }, { "epoch": 0.042207415000854266, "grad_norm": 3.3584964275360107, "learning_rate": 9.996137356494291e-05, "loss": 1.3321, "step": 772 }, { "epoch": 0.04226208781821288, "grad_norm": 3.5210177898406982, "learning_rate": 9.996102484060768e-05, "loss": 1.2177, "step": 773 }, { "epoch": 0.0423167606355715, "grad_norm": 3.1249117851257324, "learning_rate": 9.996067454978854e-05, "loss": 1.2183, "step": 774 }, { "epoch": 0.042371433452930124, "grad_norm": 5.008331775665283, "learning_rate": 9.996032269249652e-05, "loss": 1.2446, "step": 775 }, { "epoch": 0.04242610627028874, "grad_norm": 3.0899384021759033, "learning_rate": 9.99599692687426e-05, "loss": 1.2735, "step": 776 }, { "epoch": 0.04248077908764736, "grad_norm": 2.736722946166992, "learning_rate": 9.99596142785379e-05, "loss": 1.2405, "step": 777 }, { "epoch": 0.04253545190500598, "grad_norm": 3.556192636489868, "learning_rate": 9.995925772189355e-05, "loss": 1.3726, "step": 778 }, { "epoch": 0.0425901247223646, "grad_norm": 3.651853322982788, "learning_rate": 9.99588995988207e-05, "loss": 1.1283, "step": 779 }, { "epoch": 0.042644797539723216, "grad_norm": 4.0728068351745605, "learning_rate": 9.995853990933059e-05, "loss": 1.3442, "step": 780 }, { "epoch": 0.04269947035708184, "grad_norm": 2.7438242435455322, "learning_rate": 9.995817865343452e-05, "loss": 1.217, "step": 781 }, { "epoch": 0.04275414317444046, "grad_norm": 3.623056650161743, "learning_rate": 9.995781583114379e-05, "loss": 1.4113, "step": 782 }, { "epoch": 0.04280881599179908, "grad_norm": 2.5377025604248047, "learning_rate": 9.995745144246978e-05, "loss": 0.9746, "step": 783 }, { "epoch": 0.0428634888091577, "grad_norm": 3.2803287506103516, "learning_rate": 9.995708548742393e-05, "loss": 1.2623, "step": 784 }, { "epoch": 0.042918161626516314, "grad_norm": 2.6584019660949707, "learning_rate": 9.995671796601771e-05, "loss": 1.2956, "step": 785 }, { "epoch": 0.04297283444387494, "grad_norm": 3.286008358001709, "learning_rate": 9.995634887826264e-05, "loss": 1.3033, "step": 786 }, { "epoch": 0.043027507261233555, "grad_norm": 3.6072192192077637, "learning_rate": 9.995597822417027e-05, "loss": 1.2955, "step": 787 }, { "epoch": 0.04308218007859217, "grad_norm": 4.404749393463135, "learning_rate": 9.995560600375227e-05, "loss": 1.4539, "step": 788 }, { "epoch": 0.043136852895950796, "grad_norm": 3.5708868503570557, "learning_rate": 9.995523221702026e-05, "loss": 1.4006, "step": 789 }, { "epoch": 0.04319152571330941, "grad_norm": 2.9449222087860107, "learning_rate": 9.995485686398599e-05, "loss": 1.3454, "step": 790 }, { "epoch": 0.04324619853066804, "grad_norm": 5.674149990081787, "learning_rate": 9.995447994466123e-05, "loss": 1.492, "step": 791 }, { "epoch": 0.043300871348026654, "grad_norm": 3.5295205116271973, "learning_rate": 9.995410145905777e-05, "loss": 1.2999, "step": 792 }, { "epoch": 0.04335554416538527, "grad_norm": 3.2200772762298584, "learning_rate": 9.995372140718752e-05, "loss": 1.2443, "step": 793 }, { "epoch": 0.043410216982743895, "grad_norm": 3.4185476303100586, "learning_rate": 9.995333978906236e-05, "loss": 1.1039, "step": 794 }, { "epoch": 0.04346488980010251, "grad_norm": 2.8470656871795654, "learning_rate": 9.995295660469427e-05, "loss": 1.3574, "step": 795 }, { "epoch": 0.04351956261746113, "grad_norm": 2.798461437225342, "learning_rate": 9.995257185409527e-05, "loss": 1.2132, "step": 796 }, { "epoch": 0.04357423543481975, "grad_norm": 2.9777426719665527, "learning_rate": 9.99521855372774e-05, "loss": 1.2552, "step": 797 }, { "epoch": 0.04362890825217837, "grad_norm": 2.2671854496002197, "learning_rate": 9.99517976542528e-05, "loss": 0.9278, "step": 798 }, { "epoch": 0.043683581069536986, "grad_norm": 8.107407569885254, "learning_rate": 9.995140820503361e-05, "loss": 1.7804, "step": 799 }, { "epoch": 0.04373825388689561, "grad_norm": 2.965252637863159, "learning_rate": 9.995101718963206e-05, "loss": 1.5043, "step": 800 }, { "epoch": 0.04379292670425423, "grad_norm": 4.377320289611816, "learning_rate": 9.995062460806041e-05, "loss": 1.5003, "step": 801 }, { "epoch": 0.04384759952161285, "grad_norm": 2.826545000076294, "learning_rate": 9.995023046033096e-05, "loss": 1.3383, "step": 802 }, { "epoch": 0.04390227233897147, "grad_norm": 3.578474998474121, "learning_rate": 9.994983474645605e-05, "loss": 1.5429, "step": 803 }, { "epoch": 0.043956945156330085, "grad_norm": 7.758432388305664, "learning_rate": 9.994943746644812e-05, "loss": 1.2844, "step": 804 }, { "epoch": 0.04401161797368871, "grad_norm": 2.779608726501465, "learning_rate": 9.994903862031962e-05, "loss": 1.3653, "step": 805 }, { "epoch": 0.044066290791047326, "grad_norm": 2.998023271560669, "learning_rate": 9.994863820808302e-05, "loss": 1.2692, "step": 806 }, { "epoch": 0.04412096360840594, "grad_norm": 2.623445510864258, "learning_rate": 9.994823622975093e-05, "loss": 1.1841, "step": 807 }, { "epoch": 0.04417563642576457, "grad_norm": 3.1243231296539307, "learning_rate": 9.994783268533591e-05, "loss": 1.1946, "step": 808 }, { "epoch": 0.044230309243123184, "grad_norm": 3.1028072834014893, "learning_rate": 9.994742757485063e-05, "loss": 1.4193, "step": 809 }, { "epoch": 0.04428498206048181, "grad_norm": 3.3827664852142334, "learning_rate": 9.994702089830778e-05, "loss": 1.3968, "step": 810 }, { "epoch": 0.044339654877840425, "grad_norm": 3.301424026489258, "learning_rate": 9.994661265572014e-05, "loss": 1.3093, "step": 811 }, { "epoch": 0.04439432769519904, "grad_norm": 3.9152023792266846, "learning_rate": 9.99462028471005e-05, "loss": 1.351, "step": 812 }, { "epoch": 0.044449000512557665, "grad_norm": 9.098402976989746, "learning_rate": 9.994579147246169e-05, "loss": 1.5215, "step": 813 }, { "epoch": 0.04450367332991628, "grad_norm": 2.801636219024658, "learning_rate": 9.99453785318166e-05, "loss": 1.377, "step": 814 }, { "epoch": 0.0445583461472749, "grad_norm": 3.1413025856018066, "learning_rate": 9.994496402517821e-05, "loss": 1.0281, "step": 815 }, { "epoch": 0.04461301896463352, "grad_norm": 2.82747483253479, "learning_rate": 9.994454795255951e-05, "loss": 1.3167, "step": 816 }, { "epoch": 0.04466769178199214, "grad_norm": 3.0673155784606934, "learning_rate": 9.994413031397354e-05, "loss": 1.2313, "step": 817 }, { "epoch": 0.04472236459935076, "grad_norm": 3.2486791610717773, "learning_rate": 9.994371110943338e-05, "loss": 1.3753, "step": 818 }, { "epoch": 0.04477703741670938, "grad_norm": 3.371751308441162, "learning_rate": 9.99432903389522e-05, "loss": 1.3741, "step": 819 }, { "epoch": 0.044831710234068, "grad_norm": 4.450608253479004, "learning_rate": 9.994286800254317e-05, "loss": 1.6132, "step": 820 }, { "epoch": 0.04488638305142662, "grad_norm": 4.358305931091309, "learning_rate": 9.994244410021953e-05, "loss": 1.3146, "step": 821 }, { "epoch": 0.04494105586878524, "grad_norm": 2.856736660003662, "learning_rate": 9.994201863199461e-05, "loss": 1.3739, "step": 822 }, { "epoch": 0.044995728686143856, "grad_norm": 2.985762596130371, "learning_rate": 9.994159159788171e-05, "loss": 1.1276, "step": 823 }, { "epoch": 0.04505040150350248, "grad_norm": 3.7747809886932373, "learning_rate": 9.994116299789423e-05, "loss": 1.1989, "step": 824 }, { "epoch": 0.0451050743208611, "grad_norm": 2.787238836288452, "learning_rate": 9.994073283204561e-05, "loss": 1.149, "step": 825 }, { "epoch": 0.045159747138219714, "grad_norm": 4.346312046051025, "learning_rate": 9.994030110034935e-05, "loss": 1.3373, "step": 826 }, { "epoch": 0.04521441995557834, "grad_norm": 5.352482795715332, "learning_rate": 9.993986780281896e-05, "loss": 1.5932, "step": 827 }, { "epoch": 0.045269092772936954, "grad_norm": 2.54325270652771, "learning_rate": 9.993943293946806e-05, "loss": 1.1158, "step": 828 }, { "epoch": 0.04532376559029558, "grad_norm": 3.6087162494659424, "learning_rate": 9.993899651031024e-05, "loss": 1.4071, "step": 829 }, { "epoch": 0.045378438407654195, "grad_norm": 3.2993111610412598, "learning_rate": 9.993855851535922e-05, "loss": 1.387, "step": 830 }, { "epoch": 0.04543311122501281, "grad_norm": 2.747972011566162, "learning_rate": 9.993811895462873e-05, "loss": 1.0332, "step": 831 }, { "epoch": 0.045487784042371436, "grad_norm": 3.145001173019409, "learning_rate": 9.993767782813255e-05, "loss": 1.3544, "step": 832 }, { "epoch": 0.04554245685973005, "grad_norm": 2.7547669410705566, "learning_rate": 9.993723513588449e-05, "loss": 1.2419, "step": 833 }, { "epoch": 0.04559712967708867, "grad_norm": 2.641359806060791, "learning_rate": 9.993679087789845e-05, "loss": 1.3588, "step": 834 }, { "epoch": 0.045651802494447294, "grad_norm": 3.822997570037842, "learning_rate": 9.993634505418835e-05, "loss": 1.3809, "step": 835 }, { "epoch": 0.04570647531180591, "grad_norm": 2.593686819076538, "learning_rate": 9.993589766476817e-05, "loss": 1.123, "step": 836 }, { "epoch": 0.04576114812916453, "grad_norm": 3.9383296966552734, "learning_rate": 9.993544870965195e-05, "loss": 1.2072, "step": 837 }, { "epoch": 0.04581582094652315, "grad_norm": 3.3944382667541504, "learning_rate": 9.993499818885375e-05, "loss": 1.3163, "step": 838 }, { "epoch": 0.04587049376388177, "grad_norm": 2.7392311096191406, "learning_rate": 9.993454610238771e-05, "loss": 1.2532, "step": 839 }, { "epoch": 0.04592516658124039, "grad_norm": 3.4453814029693604, "learning_rate": 9.9934092450268e-05, "loss": 1.507, "step": 840 }, { "epoch": 0.04597983939859901, "grad_norm": 2.5714504718780518, "learning_rate": 9.993363723250883e-05, "loss": 1.1797, "step": 841 }, { "epoch": 0.046034512215957626, "grad_norm": 2.758089303970337, "learning_rate": 9.99331804491245e-05, "loss": 1.1917, "step": 842 }, { "epoch": 0.04608918503331625, "grad_norm": 3.158881187438965, "learning_rate": 9.99327221001293e-05, "loss": 1.2854, "step": 843 }, { "epoch": 0.04614385785067487, "grad_norm": 3.2946977615356445, "learning_rate": 9.993226218553764e-05, "loss": 1.2473, "step": 844 }, { "epoch": 0.046198530668033484, "grad_norm": 3.4306983947753906, "learning_rate": 9.99318007053639e-05, "loss": 1.4297, "step": 845 }, { "epoch": 0.04625320348539211, "grad_norm": 3.2575879096984863, "learning_rate": 9.993133765962257e-05, "loss": 1.3187, "step": 846 }, { "epoch": 0.046307876302750725, "grad_norm": 6.901745796203613, "learning_rate": 9.993087304832816e-05, "loss": 1.2149, "step": 847 }, { "epoch": 0.04636254912010935, "grad_norm": 3.278554916381836, "learning_rate": 9.993040687149525e-05, "loss": 1.3876, "step": 848 }, { "epoch": 0.046417221937467966, "grad_norm": 3.5653531551361084, "learning_rate": 9.992993912913845e-05, "loss": 1.4802, "step": 849 }, { "epoch": 0.04647189475482658, "grad_norm": 2.696547746658325, "learning_rate": 9.992946982127242e-05, "loss": 1.2891, "step": 850 }, { "epoch": 0.04652656757218521, "grad_norm": 2.4611926078796387, "learning_rate": 9.99289989479119e-05, "loss": 1.4423, "step": 851 }, { "epoch": 0.046581240389543824, "grad_norm": 3.3949756622314453, "learning_rate": 9.992852650907161e-05, "loss": 1.3273, "step": 852 }, { "epoch": 0.04663591320690244, "grad_norm": 5.029465675354004, "learning_rate": 9.992805250476639e-05, "loss": 1.2456, "step": 853 }, { "epoch": 0.046690586024261065, "grad_norm": 3.279466390609741, "learning_rate": 9.99275769350111e-05, "loss": 1.318, "step": 854 }, { "epoch": 0.04674525884161968, "grad_norm": 5.2058491706848145, "learning_rate": 9.992709979982065e-05, "loss": 1.4063, "step": 855 }, { "epoch": 0.0467999316589783, "grad_norm": 4.823375701904297, "learning_rate": 9.992662109921e-05, "loss": 1.4588, "step": 856 }, { "epoch": 0.04685460447633692, "grad_norm": 3.298656702041626, "learning_rate": 9.992614083319417e-05, "loss": 1.3697, "step": 857 }, { "epoch": 0.04690927729369554, "grad_norm": 3.1327853202819824, "learning_rate": 9.992565900178821e-05, "loss": 1.3514, "step": 858 }, { "epoch": 0.04696395011105416, "grad_norm": 3.236065149307251, "learning_rate": 9.992517560500721e-05, "loss": 1.424, "step": 859 }, { "epoch": 0.04701862292841278, "grad_norm": 2.8767788410186768, "learning_rate": 9.992469064286634e-05, "loss": 1.2923, "step": 860 }, { "epoch": 0.0470732957457714, "grad_norm": 3.492424726486206, "learning_rate": 9.992420411538082e-05, "loss": 1.3478, "step": 861 }, { "epoch": 0.04712796856313002, "grad_norm": 5.134586811065674, "learning_rate": 9.992371602256588e-05, "loss": 1.3447, "step": 862 }, { "epoch": 0.04718264138048864, "grad_norm": 2.5642683506011963, "learning_rate": 9.992322636443684e-05, "loss": 1.0987, "step": 863 }, { "epoch": 0.047237314197847255, "grad_norm": 3.960570812225342, "learning_rate": 9.992273514100904e-05, "loss": 1.2369, "step": 864 }, { "epoch": 0.04729198701520588, "grad_norm": 2.596143960952759, "learning_rate": 9.992224235229791e-05, "loss": 1.235, "step": 865 }, { "epoch": 0.047346659832564496, "grad_norm": 2.8801844120025635, "learning_rate": 9.992174799831886e-05, "loss": 1.1299, "step": 866 }, { "epoch": 0.04740133264992312, "grad_norm": 3.510607957839966, "learning_rate": 9.992125207908743e-05, "loss": 1.4036, "step": 867 }, { "epoch": 0.04745600546728174, "grad_norm": 2.6505212783813477, "learning_rate": 9.992075459461914e-05, "loss": 1.2166, "step": 868 }, { "epoch": 0.047510678284640354, "grad_norm": 2.5436336994171143, "learning_rate": 9.992025554492958e-05, "loss": 0.896, "step": 869 }, { "epoch": 0.04756535110199898, "grad_norm": 2.675527334213257, "learning_rate": 9.991975493003445e-05, "loss": 1.2418, "step": 870 }, { "epoch": 0.047620023919357594, "grad_norm": 3.1890478134155273, "learning_rate": 9.99192527499494e-05, "loss": 1.3834, "step": 871 }, { "epoch": 0.04767469673671621, "grad_norm": 2.7601044178009033, "learning_rate": 9.991874900469018e-05, "loss": 1.1862, "step": 872 }, { "epoch": 0.047729369554074835, "grad_norm": 3.6997532844543457, "learning_rate": 9.991824369427258e-05, "loss": 1.5594, "step": 873 }, { "epoch": 0.04778404237143345, "grad_norm": 6.060854911804199, "learning_rate": 9.991773681871249e-05, "loss": 1.6146, "step": 874 }, { "epoch": 0.04783871518879207, "grad_norm": 3.44290828704834, "learning_rate": 9.991722837802573e-05, "loss": 1.4112, "step": 875 }, { "epoch": 0.04789338800615069, "grad_norm": 3.6229779720306396, "learning_rate": 9.99167183722283e-05, "loss": 1.3155, "step": 876 }, { "epoch": 0.04794806082350931, "grad_norm": 3.1178555488586426, "learning_rate": 9.991620680133617e-05, "loss": 1.3223, "step": 877 }, { "epoch": 0.048002733640867934, "grad_norm": 2.7942867279052734, "learning_rate": 9.991569366536538e-05, "loss": 1.0419, "step": 878 }, { "epoch": 0.04805740645822655, "grad_norm": 2.9192869663238525, "learning_rate": 9.991517896433202e-05, "loss": 1.2152, "step": 879 }, { "epoch": 0.04811207927558517, "grad_norm": 2.7915189266204834, "learning_rate": 9.991466269825222e-05, "loss": 1.4362, "step": 880 }, { "epoch": 0.04816675209294379, "grad_norm": 3.059234380722046, "learning_rate": 9.991414486714219e-05, "loss": 1.1481, "step": 881 }, { "epoch": 0.04822142491030241, "grad_norm": 3.7785017490386963, "learning_rate": 9.991362547101812e-05, "loss": 1.3574, "step": 882 }, { "epoch": 0.048276097727661026, "grad_norm": 2.9877097606658936, "learning_rate": 9.991310450989635e-05, "loss": 1.3636, "step": 883 }, { "epoch": 0.04833077054501965, "grad_norm": 4.031594753265381, "learning_rate": 9.991258198379319e-05, "loss": 1.2512, "step": 884 }, { "epoch": 0.048385443362378266, "grad_norm": 3.317444086074829, "learning_rate": 9.991205789272503e-05, "loss": 1.4825, "step": 885 }, { "epoch": 0.04844011617973689, "grad_norm": 3.071451187133789, "learning_rate": 9.991153223670828e-05, "loss": 1.3656, "step": 886 }, { "epoch": 0.04849478899709551, "grad_norm": 3.4264774322509766, "learning_rate": 9.991100501575943e-05, "loss": 1.3298, "step": 887 }, { "epoch": 0.048549461814454124, "grad_norm": 2.6540071964263916, "learning_rate": 9.991047622989503e-05, "loss": 1.2179, "step": 888 }, { "epoch": 0.04860413463181275, "grad_norm": 2.6939680576324463, "learning_rate": 9.990994587913165e-05, "loss": 1.2512, "step": 889 }, { "epoch": 0.048658807449171365, "grad_norm": 2.8187129497528076, "learning_rate": 9.990941396348591e-05, "loss": 1.3506, "step": 890 }, { "epoch": 0.04871348026652998, "grad_norm": 3.4242074489593506, "learning_rate": 9.99088804829745e-05, "loss": 1.1245, "step": 891 }, { "epoch": 0.048768153083888606, "grad_norm": 3.065969228744507, "learning_rate": 9.990834543761413e-05, "loss": 1.3124, "step": 892 }, { "epoch": 0.04882282590124722, "grad_norm": 2.9929630756378174, "learning_rate": 9.990780882742159e-05, "loss": 1.0752, "step": 893 }, { "epoch": 0.04887749871860584, "grad_norm": 3.5239782333374023, "learning_rate": 9.99072706524137e-05, "loss": 1.4104, "step": 894 }, { "epoch": 0.048932171535964464, "grad_norm": 3.878384828567505, "learning_rate": 9.990673091260735e-05, "loss": 1.2632, "step": 895 }, { "epoch": 0.04898684435332308, "grad_norm": 3.346930980682373, "learning_rate": 9.990618960801945e-05, "loss": 1.2408, "step": 896 }, { "epoch": 0.049041517170681705, "grad_norm": 3.560689926147461, "learning_rate": 9.990564673866695e-05, "loss": 1.3459, "step": 897 }, { "epoch": 0.04909618998804032, "grad_norm": 3.301510810852051, "learning_rate": 9.99051023045669e-05, "loss": 1.1862, "step": 898 }, { "epoch": 0.04915086280539894, "grad_norm": 3.0741207599639893, "learning_rate": 9.990455630573636e-05, "loss": 1.3967, "step": 899 }, { "epoch": 0.04920553562275756, "grad_norm": 3.3099169731140137, "learning_rate": 9.990400874219246e-05, "loss": 1.5836, "step": 900 }, { "epoch": 0.04926020844011618, "grad_norm": 3.146062135696411, "learning_rate": 9.990345961395236e-05, "loss": 1.2435, "step": 901 }, { "epoch": 0.049314881257474796, "grad_norm": 3.078651189804077, "learning_rate": 9.990290892103327e-05, "loss": 1.24, "step": 902 }, { "epoch": 0.04936955407483342, "grad_norm": 2.586205244064331, "learning_rate": 9.990235666345244e-05, "loss": 1.0457, "step": 903 }, { "epoch": 0.04942422689219204, "grad_norm": 3.6581342220306396, "learning_rate": 9.990180284122726e-05, "loss": 1.57, "step": 904 }, { "epoch": 0.04947889970955066, "grad_norm": 3.288209915161133, "learning_rate": 9.9901247454375e-05, "loss": 1.4139, "step": 905 }, { "epoch": 0.04953357252690928, "grad_norm": 3.7012534141540527, "learning_rate": 9.990069050291314e-05, "loss": 1.4034, "step": 906 }, { "epoch": 0.049588245344267895, "grad_norm": 3.080392360687256, "learning_rate": 9.990013198685911e-05, "loss": 1.1523, "step": 907 }, { "epoch": 0.04964291816162652, "grad_norm": 4.256407737731934, "learning_rate": 9.989957190623044e-05, "loss": 1.2281, "step": 908 }, { "epoch": 0.049697590978985136, "grad_norm": 2.6678390502929688, "learning_rate": 9.989901026104467e-05, "loss": 1.2808, "step": 909 }, { "epoch": 0.04975226379634375, "grad_norm": 3.215116024017334, "learning_rate": 9.989844705131945e-05, "loss": 1.3061, "step": 910 }, { "epoch": 0.04980693661370238, "grad_norm": 3.0413904190063477, "learning_rate": 9.989788227707239e-05, "loss": 1.3842, "step": 911 }, { "epoch": 0.049861609431060994, "grad_norm": 2.995195150375366, "learning_rate": 9.989731593832121e-05, "loss": 1.3494, "step": 912 }, { "epoch": 0.04991628224841961, "grad_norm": 3.1070446968078613, "learning_rate": 9.98967480350837e-05, "loss": 1.3761, "step": 913 }, { "epoch": 0.049970955065778234, "grad_norm": 3.059375047683716, "learning_rate": 9.989617856737763e-05, "loss": 1.4193, "step": 914 }, { "epoch": 0.05002562788313685, "grad_norm": 3.259608268737793, "learning_rate": 9.989560753522087e-05, "loss": 1.4125, "step": 915 }, { "epoch": 0.050080300700495475, "grad_norm": 3.082369565963745, "learning_rate": 9.989503493863133e-05, "loss": 1.3763, "step": 916 }, { "epoch": 0.05013497351785409, "grad_norm": 3.3736093044281006, "learning_rate": 9.989446077762694e-05, "loss": 1.1672, "step": 917 }, { "epoch": 0.05018964633521271, "grad_norm": 6.635425567626953, "learning_rate": 9.989388505222574e-05, "loss": 1.2311, "step": 918 }, { "epoch": 0.05024431915257133, "grad_norm": 2.822723388671875, "learning_rate": 9.989330776244574e-05, "loss": 1.2542, "step": 919 }, { "epoch": 0.05029899196992995, "grad_norm": 3.5820693969726562, "learning_rate": 9.989272890830505e-05, "loss": 1.3037, "step": 920 }, { "epoch": 0.05035366478728857, "grad_norm": 3.391211748123169, "learning_rate": 9.989214848982185e-05, "loss": 1.4286, "step": 921 }, { "epoch": 0.05040833760464719, "grad_norm": 3.9102885723114014, "learning_rate": 9.989156650701432e-05, "loss": 1.3388, "step": 922 }, { "epoch": 0.05046301042200581, "grad_norm": 3.0421438217163086, "learning_rate": 9.98909829599007e-05, "loss": 1.1383, "step": 923 }, { "epoch": 0.05051768323936443, "grad_norm": 3.3635647296905518, "learning_rate": 9.989039784849927e-05, "loss": 1.2942, "step": 924 }, { "epoch": 0.05057235605672305, "grad_norm": 5.374729156494141, "learning_rate": 9.988981117282843e-05, "loss": 1.3532, "step": 925 }, { "epoch": 0.050627028874081666, "grad_norm": 2.8930277824401855, "learning_rate": 9.988922293290653e-05, "loss": 1.4603, "step": 926 }, { "epoch": 0.05068170169144029, "grad_norm": 3.4361751079559326, "learning_rate": 9.988863312875201e-05, "loss": 1.2473, "step": 927 }, { "epoch": 0.05073637450879891, "grad_norm": 4.606387615203857, "learning_rate": 9.98880417603834e-05, "loss": 1.4361, "step": 928 }, { "epoch": 0.050791047326157523, "grad_norm": 5.237675189971924, "learning_rate": 9.98874488278192e-05, "loss": 1.5252, "step": 929 }, { "epoch": 0.05084572014351615, "grad_norm": 5.414903163909912, "learning_rate": 9.988685433107803e-05, "loss": 1.0884, "step": 930 }, { "epoch": 0.050900392960874764, "grad_norm": 3.164548397064209, "learning_rate": 9.988625827017853e-05, "loss": 1.377, "step": 931 }, { "epoch": 0.05095506577823338, "grad_norm": 3.494619131088257, "learning_rate": 9.988566064513938e-05, "loss": 1.2781, "step": 932 }, { "epoch": 0.051009738595592005, "grad_norm": 3.9153919219970703, "learning_rate": 9.988506145597931e-05, "loss": 1.1946, "step": 933 }, { "epoch": 0.05106441141295062, "grad_norm": 2.5503013134002686, "learning_rate": 9.988446070271711e-05, "loss": 1.3987, "step": 934 }, { "epoch": 0.051119084230309246, "grad_norm": 2.5413811206817627, "learning_rate": 9.988385838537163e-05, "loss": 1.2872, "step": 935 }, { "epoch": 0.05117375704766786, "grad_norm": 3.616142988204956, "learning_rate": 9.988325450396175e-05, "loss": 1.4316, "step": 936 }, { "epoch": 0.05122842986502648, "grad_norm": 2.56367826461792, "learning_rate": 9.98826490585064e-05, "loss": 1.2543, "step": 937 }, { "epoch": 0.051283102682385104, "grad_norm": 3.6869430541992188, "learning_rate": 9.988204204902456e-05, "loss": 1.2791, "step": 938 }, { "epoch": 0.05133777549974372, "grad_norm": 3.01824688911438, "learning_rate": 9.988143347553525e-05, "loss": 1.2907, "step": 939 }, { "epoch": 0.05139244831710234, "grad_norm": 2.6602227687835693, "learning_rate": 9.988082333805759e-05, "loss": 1.3146, "step": 940 }, { "epoch": 0.05144712113446096, "grad_norm": 3.14501953125, "learning_rate": 9.988021163661067e-05, "loss": 1.4476, "step": 941 }, { "epoch": 0.05150179395181958, "grad_norm": 2.8764562606811523, "learning_rate": 9.98795983712137e-05, "loss": 1.1984, "step": 942 }, { "epoch": 0.0515564667691782, "grad_norm": 3.120243787765503, "learning_rate": 9.98789835418859e-05, "loss": 1.1872, "step": 943 }, { "epoch": 0.05161113958653682, "grad_norm": 3.3116955757141113, "learning_rate": 9.987836714864654e-05, "loss": 1.4404, "step": 944 }, { "epoch": 0.051665812403895436, "grad_norm": 3.0905375480651855, "learning_rate": 9.987774919151493e-05, "loss": 1.2733, "step": 945 }, { "epoch": 0.05172048522125406, "grad_norm": 3.0662543773651123, "learning_rate": 9.987712967051049e-05, "loss": 1.4154, "step": 946 }, { "epoch": 0.05177515803861268, "grad_norm": 3.040316104888916, "learning_rate": 9.98765085856526e-05, "loss": 1.4814, "step": 947 }, { "epoch": 0.051829830855971294, "grad_norm": 3.1942622661590576, "learning_rate": 9.987588593696077e-05, "loss": 1.3308, "step": 948 }, { "epoch": 0.05188450367332992, "grad_norm": 2.980666399002075, "learning_rate": 9.987526172445449e-05, "loss": 1.3592, "step": 949 }, { "epoch": 0.051939176490688535, "grad_norm": 3.0293197631835938, "learning_rate": 9.987463594815336e-05, "loss": 1.4347, "step": 950 }, { "epoch": 0.05199384930804715, "grad_norm": 3.092862606048584, "learning_rate": 9.987400860807699e-05, "loss": 1.5474, "step": 951 }, { "epoch": 0.052048522125405776, "grad_norm": 3.675027847290039, "learning_rate": 9.987337970424503e-05, "loss": 1.3495, "step": 952 }, { "epoch": 0.05210319494276439, "grad_norm": 4.167640209197998, "learning_rate": 9.987274923667723e-05, "loss": 1.2072, "step": 953 }, { "epoch": 0.05215786776012302, "grad_norm": 3.0870726108551025, "learning_rate": 9.987211720539334e-05, "loss": 1.4329, "step": 954 }, { "epoch": 0.052212540577481634, "grad_norm": 2.816863536834717, "learning_rate": 9.987148361041317e-05, "loss": 1.2427, "step": 955 }, { "epoch": 0.05226721339484025, "grad_norm": 3.230062246322632, "learning_rate": 9.987084845175661e-05, "loss": 1.3103, "step": 956 }, { "epoch": 0.052321886212198875, "grad_norm": 4.2282023429870605, "learning_rate": 9.987021172944355e-05, "loss": 1.364, "step": 957 }, { "epoch": 0.05237655902955749, "grad_norm": 2.5452067852020264, "learning_rate": 9.986957344349399e-05, "loss": 1.2679, "step": 958 }, { "epoch": 0.05243123184691611, "grad_norm": 2.627654790878296, "learning_rate": 9.986893359392789e-05, "loss": 1.3679, "step": 959 }, { "epoch": 0.05248590466427473, "grad_norm": 3.626636028289795, "learning_rate": 9.986829218076535e-05, "loss": 1.3405, "step": 960 }, { "epoch": 0.05254057748163335, "grad_norm": 3.303236246109009, "learning_rate": 9.986764920402647e-05, "loss": 1.2555, "step": 961 }, { "epoch": 0.05259525029899197, "grad_norm": 3.213870048522949, "learning_rate": 9.986700466373142e-05, "loss": 1.4115, "step": 962 }, { "epoch": 0.05264992311635059, "grad_norm": 2.6096231937408447, "learning_rate": 9.986635855990038e-05, "loss": 1.265, "step": 963 }, { "epoch": 0.05270459593370921, "grad_norm": 2.444409132003784, "learning_rate": 9.986571089255365e-05, "loss": 1.1924, "step": 964 }, { "epoch": 0.05275926875106783, "grad_norm": 4.033829212188721, "learning_rate": 9.98650616617115e-05, "loss": 1.2849, "step": 965 }, { "epoch": 0.05281394156842645, "grad_norm": 3.410506248474121, "learning_rate": 9.986441086739431e-05, "loss": 1.4993, "step": 966 }, { "epoch": 0.052868614385785065, "grad_norm": 3.9923934936523438, "learning_rate": 9.986375850962249e-05, "loss": 1.2923, "step": 967 }, { "epoch": 0.05292328720314369, "grad_norm": 2.6876509189605713, "learning_rate": 9.986310458841646e-05, "loss": 1.2431, "step": 968 }, { "epoch": 0.052977960020502306, "grad_norm": 4.804879188537598, "learning_rate": 9.986244910379674e-05, "loss": 1.3345, "step": 969 }, { "epoch": 0.05303263283786092, "grad_norm": 2.9113752841949463, "learning_rate": 9.98617920557839e-05, "loss": 1.3752, "step": 970 }, { "epoch": 0.05308730565521955, "grad_norm": 4.392089366912842, "learning_rate": 9.986113344439851e-05, "loss": 1.1085, "step": 971 }, { "epoch": 0.053141978472578164, "grad_norm": 3.03684663772583, "learning_rate": 9.986047326966125e-05, "loss": 1.439, "step": 972 }, { "epoch": 0.05319665128993679, "grad_norm": 2.788100242614746, "learning_rate": 9.98598115315928e-05, "loss": 1.4089, "step": 973 }, { "epoch": 0.053251324107295404, "grad_norm": 3.0662050247192383, "learning_rate": 9.985914823021392e-05, "loss": 1.3761, "step": 974 }, { "epoch": 0.05330599692465402, "grad_norm": 4.235529899597168, "learning_rate": 9.98584833655454e-05, "loss": 1.3743, "step": 975 }, { "epoch": 0.053360669742012645, "grad_norm": 3.5239624977111816, "learning_rate": 9.985781693760807e-05, "loss": 1.3021, "step": 976 }, { "epoch": 0.05341534255937126, "grad_norm": 3.0605313777923584, "learning_rate": 9.985714894642287e-05, "loss": 1.3919, "step": 977 }, { "epoch": 0.05347001537672988, "grad_norm": 3.572803020477295, "learning_rate": 9.985647939201071e-05, "loss": 1.3275, "step": 978 }, { "epoch": 0.0535246881940885, "grad_norm": 2.8393304347991943, "learning_rate": 9.985580827439258e-05, "loss": 1.121, "step": 979 }, { "epoch": 0.05357936101144712, "grad_norm": 3.17966365814209, "learning_rate": 9.985513559358955e-05, "loss": 1.221, "step": 980 }, { "epoch": 0.053634033828805744, "grad_norm": 3.2980844974517822, "learning_rate": 9.985446134962267e-05, "loss": 1.5173, "step": 981 }, { "epoch": 0.05368870664616436, "grad_norm": 2.786996364593506, "learning_rate": 9.985378554251313e-05, "loss": 1.196, "step": 982 }, { "epoch": 0.05374337946352298, "grad_norm": 2.763888359069824, "learning_rate": 9.985310817228207e-05, "loss": 1.3342, "step": 983 }, { "epoch": 0.0537980522808816, "grad_norm": 2.8185060024261475, "learning_rate": 9.985242923895077e-05, "loss": 1.4049, "step": 984 }, { "epoch": 0.05385272509824022, "grad_norm": 3.660822868347168, "learning_rate": 9.985174874254048e-05, "loss": 1.2402, "step": 985 }, { "epoch": 0.053907397915598836, "grad_norm": 2.886265993118286, "learning_rate": 9.985106668307259e-05, "loss": 1.52, "step": 986 }, { "epoch": 0.05396207073295746, "grad_norm": 2.6469337940216064, "learning_rate": 9.985038306056841e-05, "loss": 1.4365, "step": 987 }, { "epoch": 0.054016743550316076, "grad_norm": 2.8111748695373535, "learning_rate": 9.984969787504946e-05, "loss": 1.47, "step": 988 }, { "epoch": 0.05407141636767469, "grad_norm": 3.3193061351776123, "learning_rate": 9.984901112653715e-05, "loss": 1.5655, "step": 989 }, { "epoch": 0.05412608918503332, "grad_norm": 2.9857053756713867, "learning_rate": 9.984832281505305e-05, "loss": 1.4723, "step": 990 }, { "epoch": 0.054180762002391934, "grad_norm": 2.601958990097046, "learning_rate": 9.984763294061872e-05, "loss": 1.1065, "step": 991 }, { "epoch": 0.05423543481975056, "grad_norm": 2.4595015048980713, "learning_rate": 9.984694150325582e-05, "loss": 1.1974, "step": 992 }, { "epoch": 0.054290107637109175, "grad_norm": 3.8203179836273193, "learning_rate": 9.9846248502986e-05, "loss": 1.3718, "step": 993 }, { "epoch": 0.05434478045446779, "grad_norm": 2.6273961067199707, "learning_rate": 9.984555393983101e-05, "loss": 1.212, "step": 994 }, { "epoch": 0.054399453271826416, "grad_norm": 3.343003034591675, "learning_rate": 9.98448578138126e-05, "loss": 1.3659, "step": 995 }, { "epoch": 0.05445412608918503, "grad_norm": 3.281155824661255, "learning_rate": 9.984416012495263e-05, "loss": 1.1653, "step": 996 }, { "epoch": 0.05450879890654365, "grad_norm": 2.6718480587005615, "learning_rate": 9.984346087327298e-05, "loss": 1.1209, "step": 997 }, { "epoch": 0.054563471723902274, "grad_norm": 2.881364107131958, "learning_rate": 9.984276005879553e-05, "loss": 1.24, "step": 998 }, { "epoch": 0.05461814454126089, "grad_norm": 4.162655830383301, "learning_rate": 9.984205768154229e-05, "loss": 1.4506, "step": 999 }, { "epoch": 0.054672817358619515, "grad_norm": 2.632993221282959, "learning_rate": 9.984135374153526e-05, "loss": 1.3167, "step": 1000 }, { "epoch": 0.05472749017597813, "grad_norm": 2.8842685222625732, "learning_rate": 9.984064823879654e-05, "loss": 1.3639, "step": 1001 }, { "epoch": 0.05478216299333675, "grad_norm": 2.3463938236236572, "learning_rate": 9.98399411733482e-05, "loss": 1.2179, "step": 1002 }, { "epoch": 0.05483683581069537, "grad_norm": 3.3997864723205566, "learning_rate": 9.983923254521246e-05, "loss": 1.3858, "step": 1003 }, { "epoch": 0.05489150862805399, "grad_norm": 3.144026756286621, "learning_rate": 9.983852235441152e-05, "loss": 1.4649, "step": 1004 }, { "epoch": 0.054946181445412606, "grad_norm": 3.428051471710205, "learning_rate": 9.983781060096766e-05, "loss": 1.2902, "step": 1005 }, { "epoch": 0.05500085426277123, "grad_norm": 2.585994005203247, "learning_rate": 9.983709728490316e-05, "loss": 1.1112, "step": 1006 }, { "epoch": 0.05505552708012985, "grad_norm": 4.83320426940918, "learning_rate": 9.983638240624042e-05, "loss": 1.2354, "step": 1007 }, { "epoch": 0.055110199897488464, "grad_norm": 2.6613073348999023, "learning_rate": 9.983566596500185e-05, "loss": 1.2515, "step": 1008 }, { "epoch": 0.05516487271484709, "grad_norm": 2.5704708099365234, "learning_rate": 9.98349479612099e-05, "loss": 1.0904, "step": 1009 }, { "epoch": 0.055219545532205705, "grad_norm": 2.9935786724090576, "learning_rate": 9.98342283948871e-05, "loss": 1.2145, "step": 1010 }, { "epoch": 0.05527421834956433, "grad_norm": 4.512402534484863, "learning_rate": 9.983350726605599e-05, "loss": 1.2805, "step": 1011 }, { "epoch": 0.055328891166922946, "grad_norm": 3.1063170433044434, "learning_rate": 9.983278457473919e-05, "loss": 1.4467, "step": 1012 }, { "epoch": 0.05538356398428156, "grad_norm": 3.1415441036224365, "learning_rate": 9.983206032095937e-05, "loss": 1.3017, "step": 1013 }, { "epoch": 0.05543823680164019, "grad_norm": 2.716264247894287, "learning_rate": 9.983133450473923e-05, "loss": 1.269, "step": 1014 }, { "epoch": 0.055492909618998804, "grad_norm": 2.6811039447784424, "learning_rate": 9.983060712610152e-05, "loss": 1.3418, "step": 1015 }, { "epoch": 0.05554758243635742, "grad_norm": 2.8368403911590576, "learning_rate": 9.982987818506905e-05, "loss": 1.2118, "step": 1016 }, { "epoch": 0.055602255253716044, "grad_norm": 3.4746811389923096, "learning_rate": 9.982914768166468e-05, "loss": 1.3449, "step": 1017 }, { "epoch": 0.05565692807107466, "grad_norm": 2.568033456802368, "learning_rate": 9.982841561591132e-05, "loss": 1.2063, "step": 1018 }, { "epoch": 0.055711600888433285, "grad_norm": 2.902223587036133, "learning_rate": 9.98276819878319e-05, "loss": 1.0798, "step": 1019 }, { "epoch": 0.0557662737057919, "grad_norm": 3.302494764328003, "learning_rate": 9.982694679744944e-05, "loss": 1.2277, "step": 1020 }, { "epoch": 0.05582094652315052, "grad_norm": 4.66242790222168, "learning_rate": 9.9826210044787e-05, "loss": 0.9993, "step": 1021 }, { "epoch": 0.05587561934050914, "grad_norm": 2.7152721881866455, "learning_rate": 9.982547172986767e-05, "loss": 1.1468, "step": 1022 }, { "epoch": 0.05593029215786776, "grad_norm": 3.670745849609375, "learning_rate": 9.982473185271459e-05, "loss": 1.4073, "step": 1023 }, { "epoch": 0.05598496497522638, "grad_norm": 3.120640516281128, "learning_rate": 9.982399041335098e-05, "loss": 1.1228, "step": 1024 }, { "epoch": 0.056039637792585, "grad_norm": 2.728053331375122, "learning_rate": 9.982324741180007e-05, "loss": 1.2882, "step": 1025 }, { "epoch": 0.05609431060994362, "grad_norm": 2.850733757019043, "learning_rate": 9.982250284808515e-05, "loss": 1.3515, "step": 1026 }, { "epoch": 0.056148983427302235, "grad_norm": 3.8680202960968018, "learning_rate": 9.982175672222957e-05, "loss": 1.352, "step": 1027 }, { "epoch": 0.05620365624466086, "grad_norm": 2.826016664505005, "learning_rate": 9.982100903425675e-05, "loss": 1.312, "step": 1028 }, { "epoch": 0.056258329062019476, "grad_norm": 2.767817735671997, "learning_rate": 9.98202597841901e-05, "loss": 1.1576, "step": 1029 }, { "epoch": 0.0563130018793781, "grad_norm": 2.6698451042175293, "learning_rate": 9.981950897205312e-05, "loss": 1.2251, "step": 1030 }, { "epoch": 0.056367674696736716, "grad_norm": 2.6472790241241455, "learning_rate": 9.981875659786937e-05, "loss": 1.0581, "step": 1031 }, { "epoch": 0.05642234751409533, "grad_norm": 2.397871732711792, "learning_rate": 9.98180026616624e-05, "loss": 1.246, "step": 1032 }, { "epoch": 0.05647702033145396, "grad_norm": 2.894929885864258, "learning_rate": 9.98172471634559e-05, "loss": 1.3782, "step": 1033 }, { "epoch": 0.056531693148812574, "grad_norm": 3.049736738204956, "learning_rate": 9.981649010327352e-05, "loss": 1.4505, "step": 1034 }, { "epoch": 0.05658636596617119, "grad_norm": 2.9585788249969482, "learning_rate": 9.981573148113901e-05, "loss": 1.2969, "step": 1035 }, { "epoch": 0.056641038783529815, "grad_norm": 2.389463186264038, "learning_rate": 9.981497129707617e-05, "loss": 1.0322, "step": 1036 }, { "epoch": 0.05669571160088843, "grad_norm": 3.0742452144622803, "learning_rate": 9.981420955110881e-05, "loss": 1.3291, "step": 1037 }, { "epoch": 0.056750384418247056, "grad_norm": 2.2048466205596924, "learning_rate": 9.981344624326082e-05, "loss": 1.079, "step": 1038 }, { "epoch": 0.05680505723560567, "grad_norm": 2.7157156467437744, "learning_rate": 9.981268137355614e-05, "loss": 1.1416, "step": 1039 }, { "epoch": 0.05685973005296429, "grad_norm": 3.216317653656006, "learning_rate": 9.981191494201875e-05, "loss": 1.4132, "step": 1040 }, { "epoch": 0.056914402870322914, "grad_norm": 3.390780448913574, "learning_rate": 9.981114694867268e-05, "loss": 1.4752, "step": 1041 }, { "epoch": 0.05696907568768153, "grad_norm": 3.0015616416931152, "learning_rate": 9.9810377393542e-05, "loss": 1.3297, "step": 1042 }, { "epoch": 0.05702374850504015, "grad_norm": 2.6009562015533447, "learning_rate": 9.980960627665086e-05, "loss": 1.2482, "step": 1043 }, { "epoch": 0.05707842132239877, "grad_norm": 2.8577523231506348, "learning_rate": 9.980883359802342e-05, "loss": 1.2443, "step": 1044 }, { "epoch": 0.05713309413975739, "grad_norm": 2.732733964920044, "learning_rate": 9.980805935768392e-05, "loss": 1.1315, "step": 1045 }, { "epoch": 0.057187766957116005, "grad_norm": 2.478128433227539, "learning_rate": 9.980728355565663e-05, "loss": 1.182, "step": 1046 }, { "epoch": 0.05724243977447463, "grad_norm": 2.7823734283447266, "learning_rate": 9.980650619196585e-05, "loss": 1.0725, "step": 1047 }, { "epoch": 0.057297112591833246, "grad_norm": 2.6528117656707764, "learning_rate": 9.980572726663599e-05, "loss": 1.3046, "step": 1048 }, { "epoch": 0.05735178540919187, "grad_norm": 2.865417003631592, "learning_rate": 9.980494677969147e-05, "loss": 1.2692, "step": 1049 }, { "epoch": 0.05740645822655049, "grad_norm": 3.636530876159668, "learning_rate": 9.980416473115673e-05, "loss": 1.5131, "step": 1050 }, { "epoch": 0.057461131043909104, "grad_norm": 3.380950450897217, "learning_rate": 9.980338112105632e-05, "loss": 1.5068, "step": 1051 }, { "epoch": 0.05751580386126773, "grad_norm": 2.8676857948303223, "learning_rate": 9.980259594941481e-05, "loss": 1.1515, "step": 1052 }, { "epoch": 0.057570476678626345, "grad_norm": 2.970770835876465, "learning_rate": 9.980180921625679e-05, "loss": 1.3459, "step": 1053 }, { "epoch": 0.05762514949598496, "grad_norm": 2.36824631690979, "learning_rate": 9.980102092160696e-05, "loss": 1.1528, "step": 1054 }, { "epoch": 0.057679822313343586, "grad_norm": 2.301144599914551, "learning_rate": 9.980023106549001e-05, "loss": 1.0189, "step": 1055 }, { "epoch": 0.0577344951307022, "grad_norm": 3.4560911655426025, "learning_rate": 9.979943964793073e-05, "loss": 1.5117, "step": 1056 }, { "epoch": 0.05778916794806083, "grad_norm": 3.0791592597961426, "learning_rate": 9.979864666895392e-05, "loss": 1.246, "step": 1057 }, { "epoch": 0.057843840765419444, "grad_norm": 2.643343687057495, "learning_rate": 9.979785212858443e-05, "loss": 1.3293, "step": 1058 }, { "epoch": 0.05789851358277806, "grad_norm": 2.634178400039673, "learning_rate": 9.979705602684722e-05, "loss": 1.2925, "step": 1059 }, { "epoch": 0.057953186400136684, "grad_norm": 3.6997182369232178, "learning_rate": 9.979625836376718e-05, "loss": 1.3586, "step": 1060 }, { "epoch": 0.0580078592174953, "grad_norm": 3.3648600578308105, "learning_rate": 9.979545913936938e-05, "loss": 1.3151, "step": 1061 }, { "epoch": 0.05806253203485392, "grad_norm": 2.8945791721343994, "learning_rate": 9.979465835367885e-05, "loss": 1.218, "step": 1062 }, { "epoch": 0.05811720485221254, "grad_norm": 7.190388202667236, "learning_rate": 9.97938560067207e-05, "loss": 1.4239, "step": 1063 }, { "epoch": 0.05817187766957116, "grad_norm": 3.243140459060669, "learning_rate": 9.97930520985201e-05, "loss": 1.2566, "step": 1064 }, { "epoch": 0.058226550486929776, "grad_norm": 2.646904945373535, "learning_rate": 9.979224662910224e-05, "loss": 1.286, "step": 1065 }, { "epoch": 0.0582812233042884, "grad_norm": 4.091334342956543, "learning_rate": 9.979143959849238e-05, "loss": 1.1074, "step": 1066 }, { "epoch": 0.05833589612164702, "grad_norm": 2.6073107719421387, "learning_rate": 9.979063100671584e-05, "loss": 1.2514, "step": 1067 }, { "epoch": 0.05839056893900564, "grad_norm": 2.9360649585723877, "learning_rate": 9.978982085379794e-05, "loss": 1.2325, "step": 1068 }, { "epoch": 0.05844524175636426, "grad_norm": 3.0930280685424805, "learning_rate": 9.978900913976412e-05, "loss": 1.2272, "step": 1069 }, { "epoch": 0.058499914573722875, "grad_norm": 4.125236511230469, "learning_rate": 9.978819586463979e-05, "loss": 1.4089, "step": 1070 }, { "epoch": 0.0585545873910815, "grad_norm": 2.718137502670288, "learning_rate": 9.978738102845049e-05, "loss": 1.213, "step": 1071 }, { "epoch": 0.058609260208440116, "grad_norm": 3.275705337524414, "learning_rate": 9.978656463122174e-05, "loss": 1.1928, "step": 1072 }, { "epoch": 0.05866393302579873, "grad_norm": 4.430373191833496, "learning_rate": 9.978574667297915e-05, "loss": 1.4061, "step": 1073 }, { "epoch": 0.05871860584315736, "grad_norm": 2.499393939971924, "learning_rate": 9.978492715374835e-05, "loss": 1.0572, "step": 1074 }, { "epoch": 0.058773278660515973, "grad_norm": 3.3554000854492188, "learning_rate": 9.978410607355506e-05, "loss": 1.1591, "step": 1075 }, { "epoch": 0.0588279514778746, "grad_norm": 3.3017494678497314, "learning_rate": 9.978328343242501e-05, "loss": 1.2184, "step": 1076 }, { "epoch": 0.058882624295233214, "grad_norm": 2.9671430587768555, "learning_rate": 9.9782459230384e-05, "loss": 1.4531, "step": 1077 }, { "epoch": 0.05893729711259183, "grad_norm": 2.975383758544922, "learning_rate": 9.978163346745786e-05, "loss": 1.3352, "step": 1078 }, { "epoch": 0.058991969929950455, "grad_norm": 2.610569477081299, "learning_rate": 9.978080614367248e-05, "loss": 1.1591, "step": 1079 }, { "epoch": 0.05904664274730907, "grad_norm": 3.1875569820404053, "learning_rate": 9.977997725905384e-05, "loss": 1.2952, "step": 1080 }, { "epoch": 0.05910131556466769, "grad_norm": 4.463154315948486, "learning_rate": 9.977914681362787e-05, "loss": 1.3074, "step": 1081 }, { "epoch": 0.05915598838202631, "grad_norm": 2.4730799198150635, "learning_rate": 9.977831480742064e-05, "loss": 1.244, "step": 1082 }, { "epoch": 0.05921066119938493, "grad_norm": 2.916236162185669, "learning_rate": 9.977748124045823e-05, "loss": 1.3996, "step": 1083 }, { "epoch": 0.05926533401674355, "grad_norm": 3.2154085636138916, "learning_rate": 9.977664611276678e-05, "loss": 1.1316, "step": 1084 }, { "epoch": 0.05932000683410217, "grad_norm": 3.046143054962158, "learning_rate": 9.977580942437248e-05, "loss": 1.3832, "step": 1085 }, { "epoch": 0.05937467965146079, "grad_norm": 2.8957982063293457, "learning_rate": 9.977497117530155e-05, "loss": 1.3888, "step": 1086 }, { "epoch": 0.05942935246881941, "grad_norm": 2.8679089546203613, "learning_rate": 9.977413136558028e-05, "loss": 1.1929, "step": 1087 }, { "epoch": 0.05948402528617803, "grad_norm": 4.68980598449707, "learning_rate": 9.977328999523501e-05, "loss": 1.4927, "step": 1088 }, { "epoch": 0.059538698103536646, "grad_norm": 2.7491819858551025, "learning_rate": 9.97724470642921e-05, "loss": 1.3731, "step": 1089 }, { "epoch": 0.05959337092089527, "grad_norm": 3.084284543991089, "learning_rate": 9.977160257277797e-05, "loss": 1.2814, "step": 1090 }, { "epoch": 0.059648043738253886, "grad_norm": 2.624800443649292, "learning_rate": 9.977075652071916e-05, "loss": 1.4772, "step": 1091 }, { "epoch": 0.0597027165556125, "grad_norm": 3.24432373046875, "learning_rate": 9.976990890814212e-05, "loss": 1.2325, "step": 1092 }, { "epoch": 0.05975738937297113, "grad_norm": 3.4086873531341553, "learning_rate": 9.97690597350735e-05, "loss": 1.2387, "step": 1093 }, { "epoch": 0.059812062190329744, "grad_norm": 3.582352638244629, "learning_rate": 9.976820900153984e-05, "loss": 1.3124, "step": 1094 }, { "epoch": 0.05986673500768837, "grad_norm": 3.8752903938293457, "learning_rate": 9.97673567075679e-05, "loss": 1.2884, "step": 1095 }, { "epoch": 0.059921407825046985, "grad_norm": 2.641395330429077, "learning_rate": 9.976650285318434e-05, "loss": 1.2743, "step": 1096 }, { "epoch": 0.0599760806424056, "grad_norm": 2.744433879852295, "learning_rate": 9.976564743841597e-05, "loss": 1.3294, "step": 1097 }, { "epoch": 0.060030753459764226, "grad_norm": 4.151787281036377, "learning_rate": 9.97647904632896e-05, "loss": 1.4366, "step": 1098 }, { "epoch": 0.06008542627712284, "grad_norm": 2.5977349281311035, "learning_rate": 9.976393192783208e-05, "loss": 1.3726, "step": 1099 }, { "epoch": 0.06014009909448146, "grad_norm": 3.253208875656128, "learning_rate": 9.976307183207035e-05, "loss": 1.3601, "step": 1100 }, { "epoch": 0.060194771911840084, "grad_norm": 3.256904363632202, "learning_rate": 9.976221017603138e-05, "loss": 1.2373, "step": 1101 }, { "epoch": 0.0602494447291987, "grad_norm": 3.2421674728393555, "learning_rate": 9.976134695974217e-05, "loss": 1.1663, "step": 1102 }, { "epoch": 0.06030411754655732, "grad_norm": 2.4713172912597656, "learning_rate": 9.97604821832298e-05, "loss": 1.2486, "step": 1103 }, { "epoch": 0.06035879036391594, "grad_norm": 5.214735984802246, "learning_rate": 9.975961584652137e-05, "loss": 1.3463, "step": 1104 }, { "epoch": 0.06041346318127456, "grad_norm": 2.6295297145843506, "learning_rate": 9.975874794964406e-05, "loss": 1.1686, "step": 1105 }, { "epoch": 0.06046813599863318, "grad_norm": 3.1353185176849365, "learning_rate": 9.975787849262507e-05, "loss": 1.4909, "step": 1106 }, { "epoch": 0.0605228088159918, "grad_norm": 3.7455780506134033, "learning_rate": 9.975700747549166e-05, "loss": 1.2933, "step": 1107 }, { "epoch": 0.060577481633350416, "grad_norm": 4.816866874694824, "learning_rate": 9.975613489827115e-05, "loss": 1.3886, "step": 1108 }, { "epoch": 0.06063215445070904, "grad_norm": 2.9560048580169678, "learning_rate": 9.97552607609909e-05, "loss": 1.2504, "step": 1109 }, { "epoch": 0.06068682726806766, "grad_norm": 2.9343245029449463, "learning_rate": 9.97543850636783e-05, "loss": 1.4346, "step": 1110 }, { "epoch": 0.060741500085426274, "grad_norm": 3.4014170169830322, "learning_rate": 9.975350780636084e-05, "loss": 1.3064, "step": 1111 }, { "epoch": 0.0607961729027849, "grad_norm": 3.135084629058838, "learning_rate": 9.975262898906598e-05, "loss": 1.352, "step": 1112 }, { "epoch": 0.060850845720143515, "grad_norm": 3.0103487968444824, "learning_rate": 9.975174861182131e-05, "loss": 1.2521, "step": 1113 }, { "epoch": 0.06090551853750214, "grad_norm": 3.1102004051208496, "learning_rate": 9.97508666746544e-05, "loss": 1.0792, "step": 1114 }, { "epoch": 0.060960191354860756, "grad_norm": 2.9402997493743896, "learning_rate": 9.974998317759295e-05, "loss": 1.2659, "step": 1115 }, { "epoch": 0.06101486417221937, "grad_norm": 3.2184438705444336, "learning_rate": 9.974909812066463e-05, "loss": 1.3756, "step": 1116 }, { "epoch": 0.061069536989578, "grad_norm": 2.478386402130127, "learning_rate": 9.97482115038972e-05, "loss": 1.2016, "step": 1117 }, { "epoch": 0.061124209806936614, "grad_norm": 3.3951504230499268, "learning_rate": 9.974732332731844e-05, "loss": 1.2552, "step": 1118 }, { "epoch": 0.06117888262429523, "grad_norm": 2.8514411449432373, "learning_rate": 9.974643359095622e-05, "loss": 1.3017, "step": 1119 }, { "epoch": 0.061233555441653854, "grad_norm": 2.9047467708587646, "learning_rate": 9.974554229483843e-05, "loss": 1.2233, "step": 1120 }, { "epoch": 0.06128822825901247, "grad_norm": 4.006479740142822, "learning_rate": 9.974464943899302e-05, "loss": 1.3857, "step": 1121 }, { "epoch": 0.06134290107637109, "grad_norm": 3.2650306224823, "learning_rate": 9.974375502344797e-05, "loss": 1.4706, "step": 1122 }, { "epoch": 0.06139757389372971, "grad_norm": 4.847167491912842, "learning_rate": 9.974285904823135e-05, "loss": 1.3371, "step": 1123 }, { "epoch": 0.06145224671108833, "grad_norm": 3.3596270084381104, "learning_rate": 9.974196151337123e-05, "loss": 1.1823, "step": 1124 }, { "epoch": 0.06150691952844695, "grad_norm": 3.0602216720581055, "learning_rate": 9.974106241889574e-05, "loss": 1.1639, "step": 1125 }, { "epoch": 0.06156159234580557, "grad_norm": 2.350632429122925, "learning_rate": 9.97401617648331e-05, "loss": 1.1652, "step": 1126 }, { "epoch": 0.06161626516316419, "grad_norm": 3.037463665008545, "learning_rate": 9.973925955121155e-05, "loss": 1.1813, "step": 1127 }, { "epoch": 0.06167093798052281, "grad_norm": 3.361849069595337, "learning_rate": 9.973835577805934e-05, "loss": 1.259, "step": 1128 }, { "epoch": 0.06172561079788143, "grad_norm": 2.6697258949279785, "learning_rate": 9.973745044540485e-05, "loss": 1.2492, "step": 1129 }, { "epoch": 0.061780283615240045, "grad_norm": 3.198054552078247, "learning_rate": 9.973654355327645e-05, "loss": 0.8953, "step": 1130 }, { "epoch": 0.06183495643259867, "grad_norm": 4.200682163238525, "learning_rate": 9.973563510170257e-05, "loss": 1.3409, "step": 1131 }, { "epoch": 0.061889629249957286, "grad_norm": 3.985783815383911, "learning_rate": 9.97347250907117e-05, "loss": 1.3049, "step": 1132 }, { "epoch": 0.06194430206731591, "grad_norm": 2.338402509689331, "learning_rate": 9.973381352033236e-05, "loss": 1.1014, "step": 1133 }, { "epoch": 0.061998974884674526, "grad_norm": 3.574634075164795, "learning_rate": 9.973290039059315e-05, "loss": 1.1148, "step": 1134 }, { "epoch": 0.06205364770203314, "grad_norm": 2.8271286487579346, "learning_rate": 9.97319857015227e-05, "loss": 1.1713, "step": 1135 }, { "epoch": 0.06210832051939177, "grad_norm": 3.259526252746582, "learning_rate": 9.973106945314965e-05, "loss": 1.2385, "step": 1136 }, { "epoch": 0.062162993336750384, "grad_norm": 3.0887911319732666, "learning_rate": 9.973015164550278e-05, "loss": 1.4927, "step": 1137 }, { "epoch": 0.062217666154109, "grad_norm": 2.661522626876831, "learning_rate": 9.972923227861084e-05, "loss": 1.1099, "step": 1138 }, { "epoch": 0.062272338971467625, "grad_norm": 4.079415321350098, "learning_rate": 9.972831135250266e-05, "loss": 1.1799, "step": 1139 }, { "epoch": 0.06232701178882624, "grad_norm": 3.215791940689087, "learning_rate": 9.972738886720711e-05, "loss": 1.4023, "step": 1140 }, { "epoch": 0.06238168460618486, "grad_norm": 4.063586711883545, "learning_rate": 9.972646482275314e-05, "loss": 1.4262, "step": 1141 }, { "epoch": 0.06243635742354348, "grad_norm": 2.7686080932617188, "learning_rate": 9.972553921916969e-05, "loss": 1.1091, "step": 1142 }, { "epoch": 0.0624910302409021, "grad_norm": 2.4708251953125, "learning_rate": 9.97246120564858e-05, "loss": 1.1776, "step": 1143 }, { "epoch": 0.06254570305826072, "grad_norm": 3.585613489151001, "learning_rate": 9.972368333473052e-05, "loss": 1.3681, "step": 1144 }, { "epoch": 0.06260037587561934, "grad_norm": 5.362015247344971, "learning_rate": 9.9722753053933e-05, "loss": 1.3624, "step": 1145 }, { "epoch": 0.06265504869297796, "grad_norm": 3.109851598739624, "learning_rate": 9.97218212141224e-05, "loss": 1.1229, "step": 1146 }, { "epoch": 0.06270972151033657, "grad_norm": 2.436037302017212, "learning_rate": 9.972088781532791e-05, "loss": 1.0861, "step": 1147 }, { "epoch": 0.0627643943276952, "grad_norm": 4.233614921569824, "learning_rate": 9.971995285757882e-05, "loss": 1.2306, "step": 1148 }, { "epoch": 0.06281906714505382, "grad_norm": 3.3524727821350098, "learning_rate": 9.971901634090443e-05, "loss": 1.3096, "step": 1149 }, { "epoch": 0.06287373996241244, "grad_norm": 2.8518126010894775, "learning_rate": 9.971807826533412e-05, "loss": 1.2933, "step": 1150 }, { "epoch": 0.06292841277977106, "grad_norm": 3.844884157180786, "learning_rate": 9.971713863089731e-05, "loss": 1.1957, "step": 1151 }, { "epoch": 0.06298308559712967, "grad_norm": 3.5749423503875732, "learning_rate": 9.971619743762344e-05, "loss": 1.2081, "step": 1152 }, { "epoch": 0.06303775841448829, "grad_norm": 3.004061222076416, "learning_rate": 9.971525468554203e-05, "loss": 1.3342, "step": 1153 }, { "epoch": 0.06309243123184692, "grad_norm": 2.9612627029418945, "learning_rate": 9.971431037468263e-05, "loss": 1.2664, "step": 1154 }, { "epoch": 0.06314710404920554, "grad_norm": 3.0958399772644043, "learning_rate": 9.971336450507484e-05, "loss": 1.1825, "step": 1155 }, { "epoch": 0.06320177686656415, "grad_norm": 3.080594778060913, "learning_rate": 9.971241707674837e-05, "loss": 1.4374, "step": 1156 }, { "epoch": 0.06325644968392277, "grad_norm": 2.9613139629364014, "learning_rate": 9.971146808973286e-05, "loss": 1.3929, "step": 1157 }, { "epoch": 0.06331112250128139, "grad_norm": 2.7342538833618164, "learning_rate": 9.971051754405808e-05, "loss": 1.3354, "step": 1158 }, { "epoch": 0.06336579531864002, "grad_norm": 11.17332649230957, "learning_rate": 9.970956543975387e-05, "loss": 1.28, "step": 1159 }, { "epoch": 0.06342046813599864, "grad_norm": 6.421639919281006, "learning_rate": 9.970861177685006e-05, "loss": 1.4532, "step": 1160 }, { "epoch": 0.06347514095335725, "grad_norm": 2.459536552429199, "learning_rate": 9.970765655537654e-05, "loss": 1.2772, "step": 1161 }, { "epoch": 0.06352981377071587, "grad_norm": 2.76959228515625, "learning_rate": 9.970669977536326e-05, "loss": 1.2814, "step": 1162 }, { "epoch": 0.06358448658807449, "grad_norm": 4.672016620635986, "learning_rate": 9.970574143684025e-05, "loss": 1.0049, "step": 1163 }, { "epoch": 0.0636391594054331, "grad_norm": 3.108855724334717, "learning_rate": 9.970478153983752e-05, "loss": 1.3486, "step": 1164 }, { "epoch": 0.06369383222279174, "grad_norm": 4.482064247131348, "learning_rate": 9.97038200843852e-05, "loss": 1.3926, "step": 1165 }, { "epoch": 0.06374850504015035, "grad_norm": 2.953866720199585, "learning_rate": 9.97028570705134e-05, "loss": 1.085, "step": 1166 }, { "epoch": 0.06380317785750897, "grad_norm": 2.5647926330566406, "learning_rate": 9.970189249825233e-05, "loss": 1.3612, "step": 1167 }, { "epoch": 0.06385785067486759, "grad_norm": 3.213636875152588, "learning_rate": 9.970092636763226e-05, "loss": 1.3761, "step": 1168 }, { "epoch": 0.0639125234922262, "grad_norm": 2.9525811672210693, "learning_rate": 9.969995867868343e-05, "loss": 1.1684, "step": 1169 }, { "epoch": 0.06396719630958483, "grad_norm": 2.629426956176758, "learning_rate": 9.969898943143623e-05, "loss": 0.9172, "step": 1170 }, { "epoch": 0.06402186912694345, "grad_norm": 3.232708692550659, "learning_rate": 9.969801862592103e-05, "loss": 1.3078, "step": 1171 }, { "epoch": 0.06407654194430207, "grad_norm": 2.8195998668670654, "learning_rate": 9.969704626216825e-05, "loss": 1.3344, "step": 1172 }, { "epoch": 0.06413121476166068, "grad_norm": 3.453538179397583, "learning_rate": 9.969607234020841e-05, "loss": 1.4536, "step": 1173 }, { "epoch": 0.0641858875790193, "grad_norm": 2.872023105621338, "learning_rate": 9.969509686007203e-05, "loss": 1.4072, "step": 1174 }, { "epoch": 0.06424056039637793, "grad_norm": 2.7853989601135254, "learning_rate": 9.96941198217897e-05, "loss": 1.1504, "step": 1175 }, { "epoch": 0.06429523321373655, "grad_norm": 3.466041326522827, "learning_rate": 9.969314122539205e-05, "loss": 1.2152, "step": 1176 }, { "epoch": 0.06434990603109517, "grad_norm": 3.013793706893921, "learning_rate": 9.969216107090976e-05, "loss": 1.2315, "step": 1177 }, { "epoch": 0.06440457884845378, "grad_norm": 3.329185962677002, "learning_rate": 9.969117935837358e-05, "loss": 1.5577, "step": 1178 }, { "epoch": 0.0644592516658124, "grad_norm": 3.09785532951355, "learning_rate": 9.969019608781426e-05, "loss": 1.5006, "step": 1179 }, { "epoch": 0.06451392448317102, "grad_norm": 2.711700677871704, "learning_rate": 9.968921125926265e-05, "loss": 1.2291, "step": 1180 }, { "epoch": 0.06456859730052965, "grad_norm": 2.5664002895355225, "learning_rate": 9.968822487274964e-05, "loss": 1.208, "step": 1181 }, { "epoch": 0.06462327011788827, "grad_norm": 3.4262049198150635, "learning_rate": 9.968723692830613e-05, "loss": 1.2837, "step": 1182 }, { "epoch": 0.06467794293524688, "grad_norm": 3.326744318008423, "learning_rate": 9.968624742596311e-05, "loss": 1.3982, "step": 1183 }, { "epoch": 0.0647326157526055, "grad_norm": 3.0842323303222656, "learning_rate": 9.968525636575162e-05, "loss": 1.4644, "step": 1184 }, { "epoch": 0.06478728856996412, "grad_norm": 2.7643394470214844, "learning_rate": 9.968426374770269e-05, "loss": 1.3107, "step": 1185 }, { "epoch": 0.06484196138732275, "grad_norm": 3.1236608028411865, "learning_rate": 9.968326957184748e-05, "loss": 1.0864, "step": 1186 }, { "epoch": 0.06489663420468136, "grad_norm": 2.96262788772583, "learning_rate": 9.968227383821716e-05, "loss": 1.2756, "step": 1187 }, { "epoch": 0.06495130702203998, "grad_norm": 2.6253631114959717, "learning_rate": 9.968127654684294e-05, "loss": 1.1749, "step": 1188 }, { "epoch": 0.0650059798393986, "grad_norm": 2.5244791507720947, "learning_rate": 9.968027769775609e-05, "loss": 1.1255, "step": 1189 }, { "epoch": 0.06506065265675721, "grad_norm": 2.482658624649048, "learning_rate": 9.967927729098792e-05, "loss": 1.3384, "step": 1190 }, { "epoch": 0.06511532547411583, "grad_norm": 5.379077434539795, "learning_rate": 9.967827532656981e-05, "loss": 1.3346, "step": 1191 }, { "epoch": 0.06516999829147446, "grad_norm": 2.8473780155181885, "learning_rate": 9.967727180453317e-05, "loss": 1.3738, "step": 1192 }, { "epoch": 0.06522467110883308, "grad_norm": 2.294861078262329, "learning_rate": 9.967626672490948e-05, "loss": 1.1562, "step": 1193 }, { "epoch": 0.0652793439261917, "grad_norm": 2.3054893016815186, "learning_rate": 9.967526008773024e-05, "loss": 1.1556, "step": 1194 }, { "epoch": 0.06533401674355031, "grad_norm": 3.4803733825683594, "learning_rate": 9.967425189302701e-05, "loss": 1.163, "step": 1195 }, { "epoch": 0.06538868956090893, "grad_norm": 3.4547059535980225, "learning_rate": 9.967324214083139e-05, "loss": 1.2602, "step": 1196 }, { "epoch": 0.06544336237826756, "grad_norm": 2.46250581741333, "learning_rate": 9.967223083117506e-05, "loss": 1.301, "step": 1197 }, { "epoch": 0.06549803519562618, "grad_norm": 2.392826795578003, "learning_rate": 9.967121796408973e-05, "loss": 1.1943, "step": 1198 }, { "epoch": 0.0655527080129848, "grad_norm": 3.1746788024902344, "learning_rate": 9.967020353960714e-05, "loss": 1.3025, "step": 1199 }, { "epoch": 0.06560738083034341, "grad_norm": 2.8645687103271484, "learning_rate": 9.96691875577591e-05, "loss": 1.2486, "step": 1200 }, { "epoch": 0.06566205364770203, "grad_norm": 3.0285768508911133, "learning_rate": 9.966817001857749e-05, "loss": 1.0592, "step": 1201 }, { "epoch": 0.06571672646506065, "grad_norm": 5.4207377433776855, "learning_rate": 9.966715092209418e-05, "loss": 1.4003, "step": 1202 }, { "epoch": 0.06577139928241928, "grad_norm": 4.361091613769531, "learning_rate": 9.966613026834114e-05, "loss": 1.1498, "step": 1203 }, { "epoch": 0.0658260720997779, "grad_norm": 3.028454065322876, "learning_rate": 9.966510805735037e-05, "loss": 1.2024, "step": 1204 }, { "epoch": 0.06588074491713651, "grad_norm": 3.0849456787109375, "learning_rate": 9.966408428915393e-05, "loss": 1.2946, "step": 1205 }, { "epoch": 0.06593541773449513, "grad_norm": 3.0613226890563965, "learning_rate": 9.96630589637839e-05, "loss": 1.3917, "step": 1206 }, { "epoch": 0.06599009055185374, "grad_norm": 3.688934803009033, "learning_rate": 9.966203208127242e-05, "loss": 1.1538, "step": 1207 }, { "epoch": 0.06604476336921238, "grad_norm": 3.029249668121338, "learning_rate": 9.966100364165172e-05, "loss": 1.3286, "step": 1208 }, { "epoch": 0.06609943618657099, "grad_norm": 2.8651721477508545, "learning_rate": 9.965997364495404e-05, "loss": 1.2945, "step": 1209 }, { "epoch": 0.06615410900392961, "grad_norm": 3.0531368255615234, "learning_rate": 9.965894209121166e-05, "loss": 1.2868, "step": 1210 }, { "epoch": 0.06620878182128823, "grad_norm": 2.6356093883514404, "learning_rate": 9.965790898045693e-05, "loss": 1.3691, "step": 1211 }, { "epoch": 0.06626345463864684, "grad_norm": 4.433219909667969, "learning_rate": 9.965687431272223e-05, "loss": 1.5092, "step": 1212 }, { "epoch": 0.06631812745600547, "grad_norm": 2.302971601486206, "learning_rate": 9.965583808804001e-05, "loss": 0.9721, "step": 1213 }, { "epoch": 0.06637280027336409, "grad_norm": 2.443340539932251, "learning_rate": 9.965480030644278e-05, "loss": 1.1504, "step": 1214 }, { "epoch": 0.06642747309072271, "grad_norm": 4.688911437988281, "learning_rate": 9.965376096796306e-05, "loss": 1.316, "step": 1215 }, { "epoch": 0.06648214590808132, "grad_norm": 3.3032777309417725, "learning_rate": 9.965272007263342e-05, "loss": 1.3352, "step": 1216 }, { "epoch": 0.06653681872543994, "grad_norm": 3.0987071990966797, "learning_rate": 9.965167762048652e-05, "loss": 1.4543, "step": 1217 }, { "epoch": 0.06659149154279856, "grad_norm": 3.0757484436035156, "learning_rate": 9.965063361155505e-05, "loss": 1.3666, "step": 1218 }, { "epoch": 0.06664616436015719, "grad_norm": 2.8456475734710693, "learning_rate": 9.964958804587172e-05, "loss": 1.4008, "step": 1219 }, { "epoch": 0.0667008371775158, "grad_norm": 3.1078925132751465, "learning_rate": 9.964854092346934e-05, "loss": 1.3286, "step": 1220 }, { "epoch": 0.06675550999487442, "grad_norm": 4.082042694091797, "learning_rate": 9.964749224438073e-05, "loss": 1.3778, "step": 1221 }, { "epoch": 0.06681018281223304, "grad_norm": 2.9642889499664307, "learning_rate": 9.964644200863876e-05, "loss": 1.3881, "step": 1222 }, { "epoch": 0.06686485562959166, "grad_norm": 2.86824631690979, "learning_rate": 9.964539021627636e-05, "loss": 1.2431, "step": 1223 }, { "epoch": 0.06691952844695029, "grad_norm": 2.760932445526123, "learning_rate": 9.964433686732652e-05, "loss": 1.2221, "step": 1224 }, { "epoch": 0.0669742012643089, "grad_norm": 2.4347891807556152, "learning_rate": 9.964328196182227e-05, "loss": 1.2647, "step": 1225 }, { "epoch": 0.06702887408166752, "grad_norm": 2.8266255855560303, "learning_rate": 9.964222549979667e-05, "loss": 1.1498, "step": 1226 }, { "epoch": 0.06708354689902614, "grad_norm": 3.360856056213379, "learning_rate": 9.964116748128286e-05, "loss": 1.1705, "step": 1227 }, { "epoch": 0.06713821971638476, "grad_norm": 3.2457752227783203, "learning_rate": 9.9640107906314e-05, "loss": 1.4143, "step": 1228 }, { "epoch": 0.06719289253374337, "grad_norm": 2.6739935874938965, "learning_rate": 9.963904677492333e-05, "loss": 1.1276, "step": 1229 }, { "epoch": 0.067247565351102, "grad_norm": 2.735355854034424, "learning_rate": 9.963798408714408e-05, "loss": 1.3012, "step": 1230 }, { "epoch": 0.06730223816846062, "grad_norm": 3.8571364879608154, "learning_rate": 9.963691984300963e-05, "loss": 1.0924, "step": 1231 }, { "epoch": 0.06735691098581924, "grad_norm": 2.8226187229156494, "learning_rate": 9.963585404255329e-05, "loss": 1.2049, "step": 1232 }, { "epoch": 0.06741158380317785, "grad_norm": 2.8700714111328125, "learning_rate": 9.963478668580853e-05, "loss": 1.2616, "step": 1233 }, { "epoch": 0.06746625662053647, "grad_norm": 2.7845005989074707, "learning_rate": 9.963371777280876e-05, "loss": 1.0031, "step": 1234 }, { "epoch": 0.0675209294378951, "grad_norm": 2.5957083702087402, "learning_rate": 9.963264730358755e-05, "loss": 1.0302, "step": 1235 }, { "epoch": 0.06757560225525372, "grad_norm": 3.7438857555389404, "learning_rate": 9.963157527817843e-05, "loss": 1.2439, "step": 1236 }, { "epoch": 0.06763027507261234, "grad_norm": 9.691255569458008, "learning_rate": 9.963050169661502e-05, "loss": 1.3626, "step": 1237 }, { "epoch": 0.06768494788997095, "grad_norm": 3.1050262451171875, "learning_rate": 9.962942655893098e-05, "loss": 1.2513, "step": 1238 }, { "epoch": 0.06773962070732957, "grad_norm": 2.9312949180603027, "learning_rate": 9.962834986516003e-05, "loss": 1.3077, "step": 1239 }, { "epoch": 0.06779429352468819, "grad_norm": 2.4073383808135986, "learning_rate": 9.962727161533591e-05, "loss": 1.3703, "step": 1240 }, { "epoch": 0.06784896634204682, "grad_norm": 3.6893069744110107, "learning_rate": 9.962619180949244e-05, "loss": 1.4984, "step": 1241 }, { "epoch": 0.06790363915940544, "grad_norm": 2.9991042613983154, "learning_rate": 9.962511044766349e-05, "loss": 1.1233, "step": 1242 }, { "epoch": 0.06795831197676405, "grad_norm": 2.918757438659668, "learning_rate": 9.962402752988293e-05, "loss": 1.1992, "step": 1243 }, { "epoch": 0.06801298479412267, "grad_norm": 2.7819020748138428, "learning_rate": 9.962294305618474e-05, "loss": 1.3861, "step": 1244 }, { "epoch": 0.06806765761148129, "grad_norm": 2.9611878395080566, "learning_rate": 9.962185702660292e-05, "loss": 1.2263, "step": 1245 }, { "epoch": 0.06812233042883992, "grad_norm": 2.556828260421753, "learning_rate": 9.962076944117153e-05, "loss": 1.2832, "step": 1246 }, { "epoch": 0.06817700324619853, "grad_norm": 3.1720223426818848, "learning_rate": 9.961968029992464e-05, "loss": 1.1509, "step": 1247 }, { "epoch": 0.06823167606355715, "grad_norm": 2.5334055423736572, "learning_rate": 9.961858960289642e-05, "loss": 1.1118, "step": 1248 }, { "epoch": 0.06828634888091577, "grad_norm": 2.963111400604248, "learning_rate": 9.961749735012107e-05, "loss": 1.0898, "step": 1249 }, { "epoch": 0.06834102169827438, "grad_norm": 2.424762010574341, "learning_rate": 9.961640354163282e-05, "loss": 1.3292, "step": 1250 }, { "epoch": 0.06839569451563302, "grad_norm": 2.9486465454101562, "learning_rate": 9.9615308177466e-05, "loss": 1.2567, "step": 1251 }, { "epoch": 0.06845036733299163, "grad_norm": 2.911628246307373, "learning_rate": 9.961421125765491e-05, "loss": 1.415, "step": 1252 }, { "epoch": 0.06850504015035025, "grad_norm": 2.797104835510254, "learning_rate": 9.961311278223397e-05, "loss": 1.5114, "step": 1253 }, { "epoch": 0.06855971296770887, "grad_norm": 4.380715370178223, "learning_rate": 9.961201275123761e-05, "loss": 1.4603, "step": 1254 }, { "epoch": 0.06861438578506748, "grad_norm": 3.1560170650482178, "learning_rate": 9.961091116470033e-05, "loss": 1.3484, "step": 1255 }, { "epoch": 0.0686690586024261, "grad_norm": 2.4502711296081543, "learning_rate": 9.960980802265669e-05, "loss": 0.9908, "step": 1256 }, { "epoch": 0.06872373141978473, "grad_norm": 3.2405943870544434, "learning_rate": 9.960870332514122e-05, "loss": 1.357, "step": 1257 }, { "epoch": 0.06877840423714335, "grad_norm": 2.7486772537231445, "learning_rate": 9.96075970721886e-05, "loss": 1.1873, "step": 1258 }, { "epoch": 0.06883307705450196, "grad_norm": 3.078512191772461, "learning_rate": 9.960648926383353e-05, "loss": 1.3157, "step": 1259 }, { "epoch": 0.06888774987186058, "grad_norm": 3.7927494049072266, "learning_rate": 9.96053799001107e-05, "loss": 1.2758, "step": 1260 }, { "epoch": 0.0689424226892192, "grad_norm": 3.149925708770752, "learning_rate": 9.960426898105492e-05, "loss": 1.0878, "step": 1261 }, { "epoch": 0.06899709550657783, "grad_norm": 3.0482048988342285, "learning_rate": 9.9603156506701e-05, "loss": 1.2975, "step": 1262 }, { "epoch": 0.06905176832393645, "grad_norm": 3.4727180004119873, "learning_rate": 9.960204247708386e-05, "loss": 1.4172, "step": 1263 }, { "epoch": 0.06910644114129506, "grad_norm": 3.1559383869171143, "learning_rate": 9.960092689223839e-05, "loss": 1.2585, "step": 1264 }, { "epoch": 0.06916111395865368, "grad_norm": 3.1082985401153564, "learning_rate": 9.959980975219959e-05, "loss": 1.2213, "step": 1265 }, { "epoch": 0.0692157867760123, "grad_norm": 4.034595012664795, "learning_rate": 9.959869105700248e-05, "loss": 1.4912, "step": 1266 }, { "epoch": 0.06927045959337091, "grad_norm": 3.1899547576904297, "learning_rate": 9.959757080668213e-05, "loss": 1.556, "step": 1267 }, { "epoch": 0.06932513241072955, "grad_norm": 2.9658150672912598, "learning_rate": 9.959644900127367e-05, "loss": 1.4297, "step": 1268 }, { "epoch": 0.06937980522808816, "grad_norm": 2.989241123199463, "learning_rate": 9.959532564081229e-05, "loss": 1.3191, "step": 1269 }, { "epoch": 0.06943447804544678, "grad_norm": 1.948395848274231, "learning_rate": 9.959420072533319e-05, "loss": 0.9807, "step": 1270 }, { "epoch": 0.0694891508628054, "grad_norm": 3.107602119445801, "learning_rate": 9.959307425487163e-05, "loss": 1.4284, "step": 1271 }, { "epoch": 0.06954382368016401, "grad_norm": 2.733191728591919, "learning_rate": 9.959194622946298e-05, "loss": 1.0819, "step": 1272 }, { "epoch": 0.06959849649752264, "grad_norm": 2.4270496368408203, "learning_rate": 9.959081664914254e-05, "loss": 1.2007, "step": 1273 }, { "epoch": 0.06965316931488126, "grad_norm": 2.600531578063965, "learning_rate": 9.958968551394579e-05, "loss": 1.1923, "step": 1274 }, { "epoch": 0.06970784213223988, "grad_norm": 3.1621296405792236, "learning_rate": 9.958855282390815e-05, "loss": 1.3233, "step": 1275 }, { "epoch": 0.0697625149495985, "grad_norm": 4.675756931304932, "learning_rate": 9.958741857906515e-05, "loss": 1.1026, "step": 1276 }, { "epoch": 0.06981718776695711, "grad_norm": 3.2832155227661133, "learning_rate": 9.958628277945237e-05, "loss": 1.1465, "step": 1277 }, { "epoch": 0.06987186058431573, "grad_norm": 2.72103214263916, "learning_rate": 9.958514542510539e-05, "loss": 1.3705, "step": 1278 }, { "epoch": 0.06992653340167436, "grad_norm": 2.780719041824341, "learning_rate": 9.95840065160599e-05, "loss": 1.2539, "step": 1279 }, { "epoch": 0.06998120621903298, "grad_norm": 2.896466016769409, "learning_rate": 9.958286605235159e-05, "loss": 1.4368, "step": 1280 }, { "epoch": 0.0700358790363916, "grad_norm": 2.7478652000427246, "learning_rate": 9.958172403401622e-05, "loss": 1.143, "step": 1281 }, { "epoch": 0.07009055185375021, "grad_norm": 2.8938474655151367, "learning_rate": 9.958058046108963e-05, "loss": 1.3326, "step": 1282 }, { "epoch": 0.07014522467110883, "grad_norm": 3.1276018619537354, "learning_rate": 9.957943533360761e-05, "loss": 1.4357, "step": 1283 }, { "epoch": 0.07019989748846746, "grad_norm": 2.7564942836761475, "learning_rate": 9.957828865160612e-05, "loss": 1.2377, "step": 1284 }, { "epoch": 0.07025457030582608, "grad_norm": 2.8129255771636963, "learning_rate": 9.957714041512111e-05, "loss": 1.1172, "step": 1285 }, { "epoch": 0.07030924312318469, "grad_norm": 2.9022626876831055, "learning_rate": 9.957599062418855e-05, "loss": 1.0991, "step": 1286 }, { "epoch": 0.07036391594054331, "grad_norm": 2.799588203430176, "learning_rate": 9.957483927884452e-05, "loss": 1.2295, "step": 1287 }, { "epoch": 0.07041858875790193, "grad_norm": 4.005642890930176, "learning_rate": 9.95736863791251e-05, "loss": 1.2468, "step": 1288 }, { "epoch": 0.07047326157526056, "grad_norm": 2.864431381225586, "learning_rate": 9.957253192506645e-05, "loss": 1.1725, "step": 1289 }, { "epoch": 0.07052793439261917, "grad_norm": 2.74397873878479, "learning_rate": 9.957137591670477e-05, "loss": 1.1899, "step": 1290 }, { "epoch": 0.07058260720997779, "grad_norm": 4.124104976654053, "learning_rate": 9.95702183540763e-05, "loss": 1.2027, "step": 1291 }, { "epoch": 0.07063728002733641, "grad_norm": 3.1307034492492676, "learning_rate": 9.956905923721731e-05, "loss": 1.2926, "step": 1292 }, { "epoch": 0.07069195284469502, "grad_norm": 3.0703465938568115, "learning_rate": 9.956789856616417e-05, "loss": 1.2124, "step": 1293 }, { "epoch": 0.07074662566205364, "grad_norm": 3.112626552581787, "learning_rate": 9.956673634095329e-05, "loss": 1.3198, "step": 1294 }, { "epoch": 0.07080129847941227, "grad_norm": 2.53468656539917, "learning_rate": 9.956557256162108e-05, "loss": 1.0117, "step": 1295 }, { "epoch": 0.07085597129677089, "grad_norm": 2.6955947875976562, "learning_rate": 9.956440722820404e-05, "loss": 1.1843, "step": 1296 }, { "epoch": 0.0709106441141295, "grad_norm": 3.076930284500122, "learning_rate": 9.95632403407387e-05, "loss": 1.1622, "step": 1297 }, { "epoch": 0.07096531693148812, "grad_norm": 4.894091606140137, "learning_rate": 9.956207189926164e-05, "loss": 1.2807, "step": 1298 }, { "epoch": 0.07101998974884674, "grad_norm": 2.6830832958221436, "learning_rate": 9.956090190380953e-05, "loss": 1.3508, "step": 1299 }, { "epoch": 0.07107466256620537, "grad_norm": 2.5362987518310547, "learning_rate": 9.9559730354419e-05, "loss": 1.2725, "step": 1300 }, { "epoch": 0.07112933538356399, "grad_norm": 2.9525177478790283, "learning_rate": 9.955855725112686e-05, "loss": 1.2702, "step": 1301 }, { "epoch": 0.0711840082009226, "grad_norm": 5.12347412109375, "learning_rate": 9.955738259396983e-05, "loss": 1.2961, "step": 1302 }, { "epoch": 0.07123868101828122, "grad_norm": 2.7042007446289062, "learning_rate": 9.955620638298475e-05, "loss": 1.2337, "step": 1303 }, { "epoch": 0.07129335383563984, "grad_norm": 3.16499924659729, "learning_rate": 9.95550286182085e-05, "loss": 1.0112, "step": 1304 }, { "epoch": 0.07134802665299846, "grad_norm": 2.775885581970215, "learning_rate": 9.955384929967803e-05, "loss": 0.9773, "step": 1305 }, { "epoch": 0.07140269947035709, "grad_norm": 3.202441930770874, "learning_rate": 9.955266842743028e-05, "loss": 1.3058, "step": 1306 }, { "epoch": 0.0714573722877157, "grad_norm": 3.0125997066497803, "learning_rate": 9.955148600150232e-05, "loss": 1.2066, "step": 1307 }, { "epoch": 0.07151204510507432, "grad_norm": 5.066065311431885, "learning_rate": 9.955030202193118e-05, "loss": 1.6852, "step": 1308 }, { "epoch": 0.07156671792243294, "grad_norm": 2.79713773727417, "learning_rate": 9.9549116488754e-05, "loss": 1.3921, "step": 1309 }, { "epoch": 0.07162139073979155, "grad_norm": 2.7590177059173584, "learning_rate": 9.954792940200796e-05, "loss": 1.336, "step": 1310 }, { "epoch": 0.07167606355715019, "grad_norm": 3.3026347160339355, "learning_rate": 9.954674076173029e-05, "loss": 1.3659, "step": 1311 }, { "epoch": 0.0717307363745088, "grad_norm": 2.7318167686462402, "learning_rate": 9.954555056795822e-05, "loss": 1.2887, "step": 1312 }, { "epoch": 0.07178540919186742, "grad_norm": 2.827549934387207, "learning_rate": 9.95443588207291e-05, "loss": 1.2866, "step": 1313 }, { "epoch": 0.07184008200922604, "grad_norm": 2.684077024459839, "learning_rate": 9.95431655200803e-05, "loss": 1.2756, "step": 1314 }, { "epoch": 0.07189475482658465, "grad_norm": 3.159667730331421, "learning_rate": 9.95419706660492e-05, "loss": 1.1495, "step": 1315 }, { "epoch": 0.07194942764394327, "grad_norm": 2.7958881855010986, "learning_rate": 9.954077425867327e-05, "loss": 1.3358, "step": 1316 }, { "epoch": 0.0720041004613019, "grad_norm": 5.424653053283691, "learning_rate": 9.953957629799007e-05, "loss": 1.5339, "step": 1317 }, { "epoch": 0.07205877327866052, "grad_norm": 2.405972480773926, "learning_rate": 9.953837678403711e-05, "loss": 0.9961, "step": 1318 }, { "epoch": 0.07211344609601913, "grad_norm": 3.0941219329833984, "learning_rate": 9.953717571685202e-05, "loss": 1.5183, "step": 1319 }, { "epoch": 0.07216811891337775, "grad_norm": 3.2201552391052246, "learning_rate": 9.953597309647246e-05, "loss": 1.2587, "step": 1320 }, { "epoch": 0.07222279173073637, "grad_norm": 2.689987897872925, "learning_rate": 9.953476892293613e-05, "loss": 1.3232, "step": 1321 }, { "epoch": 0.072277464548095, "grad_norm": 3.6934351921081543, "learning_rate": 9.953356319628079e-05, "loss": 1.4114, "step": 1322 }, { "epoch": 0.07233213736545362, "grad_norm": 10.254509925842285, "learning_rate": 9.953235591654424e-05, "loss": 1.2403, "step": 1323 }, { "epoch": 0.07238681018281223, "grad_norm": 3.5215158462524414, "learning_rate": 9.953114708376434e-05, "loss": 1.3377, "step": 1324 }, { "epoch": 0.07244148300017085, "grad_norm": 2.82356595993042, "learning_rate": 9.952993669797899e-05, "loss": 1.3267, "step": 1325 }, { "epoch": 0.07249615581752947, "grad_norm": 4.740293025970459, "learning_rate": 9.952872475922613e-05, "loss": 1.3003, "step": 1326 }, { "epoch": 0.0725508286348881, "grad_norm": 2.6899473667144775, "learning_rate": 9.952751126754377e-05, "loss": 1.1065, "step": 1327 }, { "epoch": 0.07260550145224672, "grad_norm": 2.7527804374694824, "learning_rate": 9.952629622296996e-05, "loss": 1.4386, "step": 1328 }, { "epoch": 0.07266017426960533, "grad_norm": 4.191379070281982, "learning_rate": 9.952507962554279e-05, "loss": 1.315, "step": 1329 }, { "epoch": 0.07271484708696395, "grad_norm": 2.558533191680908, "learning_rate": 9.952386147530041e-05, "loss": 1.2727, "step": 1330 }, { "epoch": 0.07276951990432257, "grad_norm": 3.219099283218384, "learning_rate": 9.952264177228102e-05, "loss": 1.295, "step": 1331 }, { "epoch": 0.07282419272168118, "grad_norm": 2.656418800354004, "learning_rate": 9.952142051652285e-05, "loss": 1.361, "step": 1332 }, { "epoch": 0.07287886553903981, "grad_norm": 3.0643961429595947, "learning_rate": 9.952019770806419e-05, "loss": 1.3881, "step": 1333 }, { "epoch": 0.07293353835639843, "grad_norm": 2.9424047470092773, "learning_rate": 9.951897334694339e-05, "loss": 1.488, "step": 1334 }, { "epoch": 0.07298821117375705, "grad_norm": 2.3519976139068604, "learning_rate": 9.951774743319883e-05, "loss": 1.2573, "step": 1335 }, { "epoch": 0.07304288399111566, "grad_norm": 2.9282615184783936, "learning_rate": 9.951651996686897e-05, "loss": 1.1603, "step": 1336 }, { "epoch": 0.07309755680847428, "grad_norm": 3.0539681911468506, "learning_rate": 9.951529094799226e-05, "loss": 1.1881, "step": 1337 }, { "epoch": 0.07315222962583291, "grad_norm": 2.6102631092071533, "learning_rate": 9.951406037660726e-05, "loss": 1.2849, "step": 1338 }, { "epoch": 0.07320690244319153, "grad_norm": 2.595069646835327, "learning_rate": 9.951282825275255e-05, "loss": 1.2668, "step": 1339 }, { "epoch": 0.07326157526055015, "grad_norm": 2.7455785274505615, "learning_rate": 9.951159457646675e-05, "loss": 1.1817, "step": 1340 }, { "epoch": 0.07331624807790876, "grad_norm": 2.2635838985443115, "learning_rate": 9.951035934778856e-05, "loss": 1.0745, "step": 1341 }, { "epoch": 0.07337092089526738, "grad_norm": 2.6309926509857178, "learning_rate": 9.950912256675668e-05, "loss": 1.1605, "step": 1342 }, { "epoch": 0.073425593712626, "grad_norm": 2.7953124046325684, "learning_rate": 9.950788423340993e-05, "loss": 1.2455, "step": 1343 }, { "epoch": 0.07348026652998463, "grad_norm": 3.15358304977417, "learning_rate": 9.950664434778711e-05, "loss": 1.3384, "step": 1344 }, { "epoch": 0.07353493934734324, "grad_norm": 2.4778690338134766, "learning_rate": 9.950540290992709e-05, "loss": 1.1704, "step": 1345 }, { "epoch": 0.07358961216470186, "grad_norm": 2.7707459926605225, "learning_rate": 9.950415991986883e-05, "loss": 1.2377, "step": 1346 }, { "epoch": 0.07364428498206048, "grad_norm": 2.587721824645996, "learning_rate": 9.950291537765125e-05, "loss": 1.2003, "step": 1347 }, { "epoch": 0.0736989577994191, "grad_norm": 2.7171711921691895, "learning_rate": 9.950166928331342e-05, "loss": 1.3023, "step": 1348 }, { "epoch": 0.07375363061677773, "grad_norm": 2.818211317062378, "learning_rate": 9.950042163689436e-05, "loss": 1.3068, "step": 1349 }, { "epoch": 0.07380830343413634, "grad_norm": 3.0621607303619385, "learning_rate": 9.949917243843323e-05, "loss": 1.5185, "step": 1350 }, { "epoch": 0.07386297625149496, "grad_norm": 2.8769032955169678, "learning_rate": 9.949792168796919e-05, "loss": 1.1368, "step": 1351 }, { "epoch": 0.07391764906885358, "grad_norm": 3.257737636566162, "learning_rate": 9.949666938554145e-05, "loss": 1.2215, "step": 1352 }, { "epoch": 0.0739723218862122, "grad_norm": 2.715465784072876, "learning_rate": 9.949541553118929e-05, "loss": 1.2526, "step": 1353 }, { "epoch": 0.07402699470357081, "grad_norm": 5.189927577972412, "learning_rate": 9.949416012495199e-05, "loss": 1.4491, "step": 1354 }, { "epoch": 0.07408166752092944, "grad_norm": 2.7249631881713867, "learning_rate": 9.949290316686893e-05, "loss": 1.3073, "step": 1355 }, { "epoch": 0.07413634033828806, "grad_norm": 2.5983097553253174, "learning_rate": 9.949164465697953e-05, "loss": 0.9663, "step": 1356 }, { "epoch": 0.07419101315564668, "grad_norm": 2.5040383338928223, "learning_rate": 9.949038459532325e-05, "loss": 1.2082, "step": 1357 }, { "epoch": 0.0742456859730053, "grad_norm": 2.8282470703125, "learning_rate": 9.948912298193957e-05, "loss": 1.28, "step": 1358 }, { "epoch": 0.07430035879036391, "grad_norm": 3.1502950191497803, "learning_rate": 9.948785981686807e-05, "loss": 1.3152, "step": 1359 }, { "epoch": 0.07435503160772254, "grad_norm": 3.389733076095581, "learning_rate": 9.948659510014837e-05, "loss": 1.0663, "step": 1360 }, { "epoch": 0.07440970442508116, "grad_norm": 2.497204065322876, "learning_rate": 9.94853288318201e-05, "loss": 1.1256, "step": 1361 }, { "epoch": 0.07446437724243977, "grad_norm": 2.629662036895752, "learning_rate": 9.948406101192297e-05, "loss": 1.2691, "step": 1362 }, { "epoch": 0.07451905005979839, "grad_norm": 4.089420795440674, "learning_rate": 9.948279164049673e-05, "loss": 1.2121, "step": 1363 }, { "epoch": 0.07457372287715701, "grad_norm": 2.6013646125793457, "learning_rate": 9.948152071758117e-05, "loss": 1.3032, "step": 1364 }, { "epoch": 0.07462839569451564, "grad_norm": 3.079089403152466, "learning_rate": 9.948024824321616e-05, "loss": 1.2426, "step": 1365 }, { "epoch": 0.07468306851187426, "grad_norm": 2.6636204719543457, "learning_rate": 9.94789742174416e-05, "loss": 1.1971, "step": 1366 }, { "epoch": 0.07473774132923287, "grad_norm": 4.015671730041504, "learning_rate": 9.947769864029738e-05, "loss": 1.3238, "step": 1367 }, { "epoch": 0.07479241414659149, "grad_norm": 2.9034533500671387, "learning_rate": 9.947642151182358e-05, "loss": 1.1443, "step": 1368 }, { "epoch": 0.07484708696395011, "grad_norm": 2.938277006149292, "learning_rate": 9.947514283206019e-05, "loss": 1.1828, "step": 1369 }, { "epoch": 0.07490175978130872, "grad_norm": 3.5133869647979736, "learning_rate": 9.94738626010473e-05, "loss": 1.1679, "step": 1370 }, { "epoch": 0.07495643259866736, "grad_norm": 2.6020588874816895, "learning_rate": 9.947258081882507e-05, "loss": 1.2416, "step": 1371 }, { "epoch": 0.07501110541602597, "grad_norm": 2.238354206085205, "learning_rate": 9.947129748543368e-05, "loss": 1.1517, "step": 1372 }, { "epoch": 0.07506577823338459, "grad_norm": 3.127913475036621, "learning_rate": 9.947001260091338e-05, "loss": 1.3092, "step": 1373 }, { "epoch": 0.0751204510507432, "grad_norm": 2.8926713466644287, "learning_rate": 9.946872616530443e-05, "loss": 1.1084, "step": 1374 }, { "epoch": 0.07517512386810182, "grad_norm": 2.6371376514434814, "learning_rate": 9.946743817864719e-05, "loss": 1.1205, "step": 1375 }, { "epoch": 0.07522979668546045, "grad_norm": 2.3728721141815186, "learning_rate": 9.946614864098202e-05, "loss": 1.1555, "step": 1376 }, { "epoch": 0.07528446950281907, "grad_norm": 3.245851755142212, "learning_rate": 9.946485755234938e-05, "loss": 1.3324, "step": 1377 }, { "epoch": 0.07533914232017769, "grad_norm": 2.3245091438293457, "learning_rate": 9.946356491278974e-05, "loss": 1.3198, "step": 1378 }, { "epoch": 0.0753938151375363, "grad_norm": 2.7858664989471436, "learning_rate": 9.946227072234364e-05, "loss": 1.2979, "step": 1379 }, { "epoch": 0.07544848795489492, "grad_norm": 3.4722445011138916, "learning_rate": 9.946097498105162e-05, "loss": 1.191, "step": 1380 }, { "epoch": 0.07550316077225354, "grad_norm": 3.3616652488708496, "learning_rate": 9.945967768895435e-05, "loss": 1.3804, "step": 1381 }, { "epoch": 0.07555783358961217, "grad_norm": 2.6369497776031494, "learning_rate": 9.945837884609249e-05, "loss": 1.2471, "step": 1382 }, { "epoch": 0.07561250640697079, "grad_norm": 3.3838915824890137, "learning_rate": 9.945707845250675e-05, "loss": 1.2178, "step": 1383 }, { "epoch": 0.0756671792243294, "grad_norm": 2.7527291774749756, "learning_rate": 9.945577650823792e-05, "loss": 1.2071, "step": 1384 }, { "epoch": 0.07572185204168802, "grad_norm": 3.043516159057617, "learning_rate": 9.94544730133268e-05, "loss": 1.3343, "step": 1385 }, { "epoch": 0.07577652485904664, "grad_norm": 3.3353283405303955, "learning_rate": 9.94531679678143e-05, "loss": 1.3259, "step": 1386 }, { "epoch": 0.07583119767640527, "grad_norm": 2.656104326248169, "learning_rate": 9.94518613717413e-05, "loss": 1.2916, "step": 1387 }, { "epoch": 0.07588587049376389, "grad_norm": 3.0484302043914795, "learning_rate": 9.94505532251488e-05, "loss": 1.356, "step": 1388 }, { "epoch": 0.0759405433111225, "grad_norm": 4.324151039123535, "learning_rate": 9.944924352807778e-05, "loss": 1.3682, "step": 1389 }, { "epoch": 0.07599521612848112, "grad_norm": 2.555994749069214, "learning_rate": 9.944793228056934e-05, "loss": 1.1808, "step": 1390 }, { "epoch": 0.07604988894583974, "grad_norm": 3.18792724609375, "learning_rate": 9.944661948266456e-05, "loss": 1.4177, "step": 1391 }, { "epoch": 0.07610456176319837, "grad_norm": 4.398812770843506, "learning_rate": 9.944530513440462e-05, "loss": 1.2222, "step": 1392 }, { "epoch": 0.07615923458055698, "grad_norm": 2.913490056991577, "learning_rate": 9.944398923583073e-05, "loss": 1.1707, "step": 1393 }, { "epoch": 0.0762139073979156, "grad_norm": 2.7172646522521973, "learning_rate": 9.944267178698414e-05, "loss": 0.9764, "step": 1394 }, { "epoch": 0.07626858021527422, "grad_norm": 3.44706130027771, "learning_rate": 9.944135278790616e-05, "loss": 1.3862, "step": 1395 }, { "epoch": 0.07632325303263283, "grad_norm": 2.214087724685669, "learning_rate": 9.944003223863816e-05, "loss": 1.2611, "step": 1396 }, { "epoch": 0.07637792584999145, "grad_norm": 2.70990252494812, "learning_rate": 9.943871013922152e-05, "loss": 1.3972, "step": 1397 }, { "epoch": 0.07643259866735008, "grad_norm": 3.183504819869995, "learning_rate": 9.943738648969773e-05, "loss": 1.0876, "step": 1398 }, { "epoch": 0.0764872714847087, "grad_norm": 2.602583885192871, "learning_rate": 9.943606129010826e-05, "loss": 1.2893, "step": 1399 }, { "epoch": 0.07654194430206732, "grad_norm": 2.8252129554748535, "learning_rate": 9.943473454049466e-05, "loss": 1.2876, "step": 1400 }, { "epoch": 0.07659661711942593, "grad_norm": 3.0042166709899902, "learning_rate": 9.943340624089854e-05, "loss": 1.3164, "step": 1401 }, { "epoch": 0.07665128993678455, "grad_norm": 3.323491096496582, "learning_rate": 9.943207639136155e-05, "loss": 1.429, "step": 1402 }, { "epoch": 0.07670596275414318, "grad_norm": 2.36964750289917, "learning_rate": 9.943074499192538e-05, "loss": 1.1228, "step": 1403 }, { "epoch": 0.0767606355715018, "grad_norm": 3.1359989643096924, "learning_rate": 9.942941204263178e-05, "loss": 1.1912, "step": 1404 }, { "epoch": 0.07681530838886041, "grad_norm": 2.6746621131896973, "learning_rate": 9.942807754352254e-05, "loss": 1.2575, "step": 1405 }, { "epoch": 0.07686998120621903, "grad_norm": 2.531785726547241, "learning_rate": 9.942674149463951e-05, "loss": 1.1846, "step": 1406 }, { "epoch": 0.07692465402357765, "grad_norm": 2.2457354068756104, "learning_rate": 9.942540389602457e-05, "loss": 1.1403, "step": 1407 }, { "epoch": 0.07697932684093627, "grad_norm": 3.5673465728759766, "learning_rate": 9.942406474771965e-05, "loss": 1.1681, "step": 1408 }, { "epoch": 0.0770339996582949, "grad_norm": 3.377995014190674, "learning_rate": 9.942272404976676e-05, "loss": 1.4359, "step": 1409 }, { "epoch": 0.07708867247565351, "grad_norm": 2.75551176071167, "learning_rate": 9.942138180220793e-05, "loss": 1.2429, "step": 1410 }, { "epoch": 0.07714334529301213, "grad_norm": 2.7843210697174072, "learning_rate": 9.942003800508524e-05, "loss": 1.2649, "step": 1411 }, { "epoch": 0.07719801811037075, "grad_norm": 2.854088544845581, "learning_rate": 9.941869265844082e-05, "loss": 1.2084, "step": 1412 }, { "epoch": 0.07725269092772936, "grad_norm": 2.783453941345215, "learning_rate": 9.941734576231688e-05, "loss": 1.2035, "step": 1413 }, { "epoch": 0.077307363745088, "grad_norm": 2.7098236083984375, "learning_rate": 9.94159973167556e-05, "loss": 1.2303, "step": 1414 }, { "epoch": 0.07736203656244661, "grad_norm": 2.4150731563568115, "learning_rate": 9.94146473217993e-05, "loss": 1.2043, "step": 1415 }, { "epoch": 0.07741670937980523, "grad_norm": 2.7605109214782715, "learning_rate": 9.94132957774903e-05, "loss": 1.2697, "step": 1416 }, { "epoch": 0.07747138219716385, "grad_norm": 2.7581558227539062, "learning_rate": 9.941194268387095e-05, "loss": 1.3308, "step": 1417 }, { "epoch": 0.07752605501452246, "grad_norm": 2.8739442825317383, "learning_rate": 9.941058804098372e-05, "loss": 1.252, "step": 1418 }, { "epoch": 0.07758072783188108, "grad_norm": 3.0961575508117676, "learning_rate": 9.940923184887106e-05, "loss": 1.3336, "step": 1419 }, { "epoch": 0.07763540064923971, "grad_norm": 4.767187595367432, "learning_rate": 9.940787410757548e-05, "loss": 1.1911, "step": 1420 }, { "epoch": 0.07769007346659833, "grad_norm": 2.5235414505004883, "learning_rate": 9.940651481713958e-05, "loss": 1.1584, "step": 1421 }, { "epoch": 0.07774474628395694, "grad_norm": 2.2292110919952393, "learning_rate": 9.940515397760595e-05, "loss": 1.1537, "step": 1422 }, { "epoch": 0.07779941910131556, "grad_norm": 3.3649911880493164, "learning_rate": 9.940379158901727e-05, "loss": 1.4905, "step": 1423 }, { "epoch": 0.07785409191867418, "grad_norm": 4.594551086425781, "learning_rate": 9.940242765141627e-05, "loss": 1.1336, "step": 1424 }, { "epoch": 0.07790876473603281, "grad_norm": 2.6169588565826416, "learning_rate": 9.940106216484569e-05, "loss": 1.1519, "step": 1425 }, { "epoch": 0.07796343755339143, "grad_norm": 3.7132821083068848, "learning_rate": 9.939969512934837e-05, "loss": 1.2325, "step": 1426 }, { "epoch": 0.07801811037075004, "grad_norm": 3.421273708343506, "learning_rate": 9.939832654496715e-05, "loss": 1.4164, "step": 1427 }, { "epoch": 0.07807278318810866, "grad_norm": 2.1036605834960938, "learning_rate": 9.939695641174495e-05, "loss": 0.9901, "step": 1428 }, { "epoch": 0.07812745600546728, "grad_norm": 2.5037155151367188, "learning_rate": 9.939558472972472e-05, "loss": 1.279, "step": 1429 }, { "epoch": 0.07818212882282591, "grad_norm": 2.209092617034912, "learning_rate": 9.939421149894949e-05, "loss": 1.1565, "step": 1430 }, { "epoch": 0.07823680164018453, "grad_norm": 2.0054283142089844, "learning_rate": 9.939283671946228e-05, "loss": 1.0346, "step": 1431 }, { "epoch": 0.07829147445754314, "grad_norm": 2.774066686630249, "learning_rate": 9.939146039130624e-05, "loss": 1.073, "step": 1432 }, { "epoch": 0.07834614727490176, "grad_norm": 2.718606948852539, "learning_rate": 9.93900825145245e-05, "loss": 1.1215, "step": 1433 }, { "epoch": 0.07840082009226038, "grad_norm": 3.2103793621063232, "learning_rate": 9.938870308916026e-05, "loss": 1.3591, "step": 1434 }, { "epoch": 0.07845549290961899, "grad_norm": 3.1882758140563965, "learning_rate": 9.938732211525679e-05, "loss": 1.0986, "step": 1435 }, { "epoch": 0.07851016572697762, "grad_norm": 2.4409759044647217, "learning_rate": 9.938593959285735e-05, "loss": 1.1062, "step": 1436 }, { "epoch": 0.07856483854433624, "grad_norm": 2.5118556022644043, "learning_rate": 9.938455552200532e-05, "loss": 1.1456, "step": 1437 }, { "epoch": 0.07861951136169486, "grad_norm": 2.2229864597320557, "learning_rate": 9.938316990274408e-05, "loss": 1.245, "step": 1438 }, { "epoch": 0.07867418417905347, "grad_norm": 3.1759250164031982, "learning_rate": 9.93817827351171e-05, "loss": 0.9834, "step": 1439 }, { "epoch": 0.07872885699641209, "grad_norm": 2.947946071624756, "learning_rate": 9.938039401916784e-05, "loss": 1.0557, "step": 1440 }, { "epoch": 0.07878352981377072, "grad_norm": 2.863176107406616, "learning_rate": 9.937900375493985e-05, "loss": 1.0358, "step": 1441 }, { "epoch": 0.07883820263112934, "grad_norm": 2.787738800048828, "learning_rate": 9.937761194247675e-05, "loss": 1.1019, "step": 1442 }, { "epoch": 0.07889287544848796, "grad_norm": 3.1443560123443604, "learning_rate": 9.937621858182215e-05, "loss": 1.3484, "step": 1443 }, { "epoch": 0.07894754826584657, "grad_norm": 3.140784978866577, "learning_rate": 9.937482367301974e-05, "loss": 1.3671, "step": 1444 }, { "epoch": 0.07900222108320519, "grad_norm": 2.8213493824005127, "learning_rate": 9.937342721611327e-05, "loss": 1.2173, "step": 1445 }, { "epoch": 0.07905689390056381, "grad_norm": 2.6796116828918457, "learning_rate": 9.93720292111465e-05, "loss": 1.1337, "step": 1446 }, { "epoch": 0.07911156671792244, "grad_norm": 2.629633665084839, "learning_rate": 9.937062965816329e-05, "loss": 1.3332, "step": 1447 }, { "epoch": 0.07916623953528105, "grad_norm": 3.042583465576172, "learning_rate": 9.93692285572075e-05, "loss": 1.3654, "step": 1448 }, { "epoch": 0.07922091235263967, "grad_norm": 3.82564115524292, "learning_rate": 9.936782590832308e-05, "loss": 1.3688, "step": 1449 }, { "epoch": 0.07927558516999829, "grad_norm": 2.90874981880188, "learning_rate": 9.936642171155402e-05, "loss": 1.4185, "step": 1450 }, { "epoch": 0.0793302579873569, "grad_norm": 2.5990822315216064, "learning_rate": 9.93650159669443e-05, "loss": 1.19, "step": 1451 }, { "epoch": 0.07938493080471554, "grad_norm": 2.713651180267334, "learning_rate": 9.936360867453802e-05, "loss": 1.1642, "step": 1452 }, { "epoch": 0.07943960362207415, "grad_norm": 3.2333316802978516, "learning_rate": 9.936219983437932e-05, "loss": 1.1285, "step": 1453 }, { "epoch": 0.07949427643943277, "grad_norm": 3.7523882389068604, "learning_rate": 9.936078944651236e-05, "loss": 1.4861, "step": 1454 }, { "epoch": 0.07954894925679139, "grad_norm": 2.6376943588256836, "learning_rate": 9.935937751098136e-05, "loss": 1.2816, "step": 1455 }, { "epoch": 0.07960362207415, "grad_norm": 2.9682319164276123, "learning_rate": 9.935796402783059e-05, "loss": 1.2982, "step": 1456 }, { "epoch": 0.07965829489150862, "grad_norm": 3.702467679977417, "learning_rate": 9.935654899710437e-05, "loss": 1.2605, "step": 1457 }, { "epoch": 0.07971296770886725, "grad_norm": 5.21343994140625, "learning_rate": 9.935513241884706e-05, "loss": 1.2231, "step": 1458 }, { "epoch": 0.07976764052622587, "grad_norm": 3.3261237144470215, "learning_rate": 9.93537142931031e-05, "loss": 1.4135, "step": 1459 }, { "epoch": 0.07982231334358449, "grad_norm": 2.7892918586730957, "learning_rate": 9.935229461991693e-05, "loss": 1.1761, "step": 1460 }, { "epoch": 0.0798769861609431, "grad_norm": 2.7024593353271484, "learning_rate": 9.935087339933307e-05, "loss": 1.2894, "step": 1461 }, { "epoch": 0.07993165897830172, "grad_norm": 3.0336062908172607, "learning_rate": 9.934945063139608e-05, "loss": 1.2274, "step": 1462 }, { "epoch": 0.07998633179566035, "grad_norm": 3.00003719329834, "learning_rate": 9.934802631615056e-05, "loss": 1.1651, "step": 1463 }, { "epoch": 0.08004100461301897, "grad_norm": 2.6730005741119385, "learning_rate": 9.934660045364119e-05, "loss": 1.1494, "step": 1464 }, { "epoch": 0.08009567743037758, "grad_norm": 3.1394524574279785, "learning_rate": 9.934517304391266e-05, "loss": 1.2399, "step": 1465 }, { "epoch": 0.0801503502477362, "grad_norm": 3.452927350997925, "learning_rate": 9.934374408700975e-05, "loss": 1.3515, "step": 1466 }, { "epoch": 0.08020502306509482, "grad_norm": 2.655416250228882, "learning_rate": 9.934231358297722e-05, "loss": 1.2114, "step": 1467 }, { "epoch": 0.08025969588245345, "grad_norm": 3.618638277053833, "learning_rate": 9.934088153185995e-05, "loss": 1.1326, "step": 1468 }, { "epoch": 0.08031436869981207, "grad_norm": 4.485189437866211, "learning_rate": 9.933944793370284e-05, "loss": 1.2883, "step": 1469 }, { "epoch": 0.08036904151717068, "grad_norm": 2.429926633834839, "learning_rate": 9.933801278855083e-05, "loss": 1.1172, "step": 1470 }, { "epoch": 0.0804237143345293, "grad_norm": 2.7427995204925537, "learning_rate": 9.933657609644895e-05, "loss": 1.3614, "step": 1471 }, { "epoch": 0.08047838715188792, "grad_norm": 4.538589954376221, "learning_rate": 9.93351378574422e-05, "loss": 1.2442, "step": 1472 }, { "epoch": 0.08053305996924653, "grad_norm": 2.4770150184631348, "learning_rate": 9.933369807157569e-05, "loss": 1.0682, "step": 1473 }, { "epoch": 0.08058773278660517, "grad_norm": 3.1731116771698, "learning_rate": 9.933225673889457e-05, "loss": 1.2613, "step": 1474 }, { "epoch": 0.08064240560396378, "grad_norm": 2.6879098415374756, "learning_rate": 9.933081385944404e-05, "loss": 1.2696, "step": 1475 }, { "epoch": 0.0806970784213224, "grad_norm": 2.9496891498565674, "learning_rate": 9.932936943326932e-05, "loss": 1.2341, "step": 1476 }, { "epoch": 0.08075175123868102, "grad_norm": 3.2106521129608154, "learning_rate": 9.93279234604157e-05, "loss": 1.2552, "step": 1477 }, { "epoch": 0.08080642405603963, "grad_norm": 3.2933547496795654, "learning_rate": 9.932647594092855e-05, "loss": 1.2848, "step": 1478 }, { "epoch": 0.08086109687339826, "grad_norm": 3.9660401344299316, "learning_rate": 9.932502687485322e-05, "loss": 1.2229, "step": 1479 }, { "epoch": 0.08091576969075688, "grad_norm": 2.9801769256591797, "learning_rate": 9.932357626223515e-05, "loss": 1.2229, "step": 1480 }, { "epoch": 0.0809704425081155, "grad_norm": 5.477286338806152, "learning_rate": 9.932212410311984e-05, "loss": 1.3683, "step": 1481 }, { "epoch": 0.08102511532547411, "grad_norm": 2.589305877685547, "learning_rate": 9.93206703975528e-05, "loss": 1.1627, "step": 1482 }, { "epoch": 0.08107978814283273, "grad_norm": 5.164231300354004, "learning_rate": 9.931921514557963e-05, "loss": 1.1728, "step": 1483 }, { "epoch": 0.08113446096019135, "grad_norm": 2.8703694343566895, "learning_rate": 9.931775834724593e-05, "loss": 1.2422, "step": 1484 }, { "epoch": 0.08118913377754998, "grad_norm": 3.6066880226135254, "learning_rate": 9.931630000259741e-05, "loss": 1.4736, "step": 1485 }, { "epoch": 0.0812438065949086, "grad_norm": 3.113518238067627, "learning_rate": 9.931484011167977e-05, "loss": 0.9757, "step": 1486 }, { "epoch": 0.08129847941226721, "grad_norm": 3.0666003227233887, "learning_rate": 9.931337867453879e-05, "loss": 1.2556, "step": 1487 }, { "epoch": 0.08135315222962583, "grad_norm": 1.9725855588912964, "learning_rate": 9.931191569122032e-05, "loss": 1.0534, "step": 1488 }, { "epoch": 0.08140782504698445, "grad_norm": 2.794358730316162, "learning_rate": 9.931045116177018e-05, "loss": 1.3516, "step": 1489 }, { "epoch": 0.08146249786434308, "grad_norm": 2.4861040115356445, "learning_rate": 9.930898508623432e-05, "loss": 1.0649, "step": 1490 }, { "epoch": 0.0815171706817017, "grad_norm": 3.197385787963867, "learning_rate": 9.930751746465869e-05, "loss": 1.3257, "step": 1491 }, { "epoch": 0.08157184349906031, "grad_norm": 3.293813943862915, "learning_rate": 9.930604829708934e-05, "loss": 1.2311, "step": 1492 }, { "epoch": 0.08162651631641893, "grad_norm": 2.2439026832580566, "learning_rate": 9.93045775835723e-05, "loss": 1.0003, "step": 1493 }, { "epoch": 0.08168118913377755, "grad_norm": 2.7086315155029297, "learning_rate": 9.93031053241537e-05, "loss": 1.0455, "step": 1494 }, { "epoch": 0.08173586195113616, "grad_norm": 4.281039237976074, "learning_rate": 9.930163151887969e-05, "loss": 1.386, "step": 1495 }, { "epoch": 0.0817905347684948, "grad_norm": 4.42319917678833, "learning_rate": 9.930015616779648e-05, "loss": 1.3109, "step": 1496 }, { "epoch": 0.08184520758585341, "grad_norm": 3.3185575008392334, "learning_rate": 9.929867927095036e-05, "loss": 1.1761, "step": 1497 }, { "epoch": 0.08189988040321203, "grad_norm": 2.548248291015625, "learning_rate": 9.929720082838759e-05, "loss": 1.2084, "step": 1498 }, { "epoch": 0.08195455322057064, "grad_norm": 3.320856809616089, "learning_rate": 9.929572084015455e-05, "loss": 1.1147, "step": 1499 }, { "epoch": 0.08200922603792926, "grad_norm": 2.778195381164551, "learning_rate": 9.929423930629764e-05, "loss": 1.3305, "step": 1500 }, { "epoch": 0.08206389885528789, "grad_norm": 2.680318832397461, "learning_rate": 9.929275622686333e-05, "loss": 1.2788, "step": 1501 }, { "epoch": 0.08211857167264651, "grad_norm": 2.6127307415008545, "learning_rate": 9.929127160189809e-05, "loss": 1.2664, "step": 1502 }, { "epoch": 0.08217324449000513, "grad_norm": 2.419023036956787, "learning_rate": 9.928978543144848e-05, "loss": 1.182, "step": 1503 }, { "epoch": 0.08222791730736374, "grad_norm": 2.5703625679016113, "learning_rate": 9.928829771556111e-05, "loss": 1.1686, "step": 1504 }, { "epoch": 0.08228259012472236, "grad_norm": 2.6429600715637207, "learning_rate": 9.92868084542826e-05, "loss": 1.1146, "step": 1505 }, { "epoch": 0.08233726294208099, "grad_norm": 2.4154114723205566, "learning_rate": 9.928531764765968e-05, "loss": 1.2156, "step": 1506 }, { "epoch": 0.08239193575943961, "grad_norm": 2.4145021438598633, "learning_rate": 9.928382529573905e-05, "loss": 1.3058, "step": 1507 }, { "epoch": 0.08244660857679822, "grad_norm": 2.6559534072875977, "learning_rate": 9.928233139856755e-05, "loss": 1.1128, "step": 1508 }, { "epoch": 0.08250128139415684, "grad_norm": 6.103301048278809, "learning_rate": 9.928083595619198e-05, "loss": 1.3678, "step": 1509 }, { "epoch": 0.08255595421151546, "grad_norm": 4.156901836395264, "learning_rate": 9.927933896865924e-05, "loss": 1.1911, "step": 1510 }, { "epoch": 0.08261062702887408, "grad_norm": 2.494107961654663, "learning_rate": 9.927784043601629e-05, "loss": 1.0647, "step": 1511 }, { "epoch": 0.0826652998462327, "grad_norm": 2.3144726753234863, "learning_rate": 9.927634035831009e-05, "loss": 1.182, "step": 1512 }, { "epoch": 0.08271997266359132, "grad_norm": 2.50085711479187, "learning_rate": 9.927483873558765e-05, "loss": 1.3769, "step": 1513 }, { "epoch": 0.08277464548094994, "grad_norm": 4.448266983032227, "learning_rate": 9.927333556789611e-05, "loss": 1.329, "step": 1514 }, { "epoch": 0.08282931829830856, "grad_norm": 2.7896692752838135, "learning_rate": 9.927183085528256e-05, "loss": 1.3664, "step": 1515 }, { "epoch": 0.08288399111566717, "grad_norm": 3.196200370788574, "learning_rate": 9.927032459779419e-05, "loss": 1.1941, "step": 1516 }, { "epoch": 0.0829386639330258, "grad_norm": 2.3318803310394287, "learning_rate": 9.926881679547823e-05, "loss": 1.0219, "step": 1517 }, { "epoch": 0.08299333675038442, "grad_norm": 3.01855206489563, "learning_rate": 9.926730744838195e-05, "loss": 1.4063, "step": 1518 }, { "epoch": 0.08304800956774304, "grad_norm": 4.2217512130737305, "learning_rate": 9.926579655655268e-05, "loss": 1.1838, "step": 1519 }, { "epoch": 0.08310268238510166, "grad_norm": 2.4929823875427246, "learning_rate": 9.926428412003779e-05, "loss": 1.2626, "step": 1520 }, { "epoch": 0.08315735520246027, "grad_norm": 2.5650031566619873, "learning_rate": 9.92627701388847e-05, "loss": 1.0873, "step": 1521 }, { "epoch": 0.08321202801981889, "grad_norm": 2.758730888366699, "learning_rate": 9.926125461314088e-05, "loss": 1.3039, "step": 1522 }, { "epoch": 0.08326670083717752, "grad_norm": 3.150059938430786, "learning_rate": 9.925973754285385e-05, "loss": 1.4766, "step": 1523 }, { "epoch": 0.08332137365453614, "grad_norm": 2.5382115840911865, "learning_rate": 9.925821892807118e-05, "loss": 1.2171, "step": 1524 }, { "epoch": 0.08337604647189475, "grad_norm": 2.1867687702178955, "learning_rate": 9.925669876884048e-05, "loss": 1.201, "step": 1525 }, { "epoch": 0.08343071928925337, "grad_norm": 3.5314724445343018, "learning_rate": 9.92551770652094e-05, "loss": 1.5557, "step": 1526 }, { "epoch": 0.08348539210661199, "grad_norm": 3.021332025527954, "learning_rate": 9.925365381722568e-05, "loss": 1.3767, "step": 1527 }, { "epoch": 0.08354006492397062, "grad_norm": 4.5249342918396, "learning_rate": 9.925212902493706e-05, "loss": 1.1353, "step": 1528 }, { "epoch": 0.08359473774132924, "grad_norm": 3.128572940826416, "learning_rate": 9.925060268839135e-05, "loss": 1.3509, "step": 1529 }, { "epoch": 0.08364941055868785, "grad_norm": 2.71026349067688, "learning_rate": 9.924907480763642e-05, "loss": 1.0664, "step": 1530 }, { "epoch": 0.08370408337604647, "grad_norm": 3.37335467338562, "learning_rate": 9.924754538272015e-05, "loss": 1.217, "step": 1531 }, { "epoch": 0.08375875619340509, "grad_norm": 3.681637763977051, "learning_rate": 9.924601441369053e-05, "loss": 1.0849, "step": 1532 }, { "epoch": 0.0838134290107637, "grad_norm": 2.4017555713653564, "learning_rate": 9.924448190059552e-05, "loss": 1.1963, "step": 1533 }, { "epoch": 0.08386810182812234, "grad_norm": 6.326871395111084, "learning_rate": 9.924294784348321e-05, "loss": 1.2396, "step": 1534 }, { "epoch": 0.08392277464548095, "grad_norm": 3.6948156356811523, "learning_rate": 9.924141224240167e-05, "loss": 1.3848, "step": 1535 }, { "epoch": 0.08397744746283957, "grad_norm": 3.21486759185791, "learning_rate": 9.923987509739906e-05, "loss": 1.3164, "step": 1536 }, { "epoch": 0.08403212028019819, "grad_norm": 3.373936653137207, "learning_rate": 9.923833640852358e-05, "loss": 1.1314, "step": 1537 }, { "epoch": 0.0840867930975568, "grad_norm": 2.702047109603882, "learning_rate": 9.923679617582347e-05, "loss": 1.3225, "step": 1538 }, { "epoch": 0.08414146591491543, "grad_norm": 4.237392425537109, "learning_rate": 9.923525439934701e-05, "loss": 1.3043, "step": 1539 }, { "epoch": 0.08419613873227405, "grad_norm": 3.549440383911133, "learning_rate": 9.923371107914257e-05, "loss": 1.1904, "step": 1540 }, { "epoch": 0.08425081154963267, "grad_norm": 4.531394958496094, "learning_rate": 9.92321662152585e-05, "loss": 1.2867, "step": 1541 }, { "epoch": 0.08430548436699128, "grad_norm": 2.395585298538208, "learning_rate": 9.923061980774328e-05, "loss": 1.1248, "step": 1542 }, { "epoch": 0.0843601571843499, "grad_norm": 3.2949724197387695, "learning_rate": 9.922907185664536e-05, "loss": 1.3446, "step": 1543 }, { "epoch": 0.08441483000170853, "grad_norm": 3.2386810779571533, "learning_rate": 9.922752236201331e-05, "loss": 1.3347, "step": 1544 }, { "epoch": 0.08446950281906715, "grad_norm": 2.299243450164795, "learning_rate": 9.922597132389568e-05, "loss": 1.14, "step": 1545 }, { "epoch": 0.08452417563642577, "grad_norm": 2.878592014312744, "learning_rate": 9.922441874234112e-05, "loss": 1.2097, "step": 1546 }, { "epoch": 0.08457884845378438, "grad_norm": 2.241407871246338, "learning_rate": 9.92228646173983e-05, "loss": 1.2745, "step": 1547 }, { "epoch": 0.084633521271143, "grad_norm": 3.2366058826446533, "learning_rate": 9.922130894911597e-05, "loss": 1.382, "step": 1548 }, { "epoch": 0.08468819408850162, "grad_norm": 3.0817618370056152, "learning_rate": 9.921975173754286e-05, "loss": 1.211, "step": 1549 }, { "epoch": 0.08474286690586025, "grad_norm": 3.002657890319824, "learning_rate": 9.921819298272786e-05, "loss": 1.4121, "step": 1550 }, { "epoch": 0.08479753972321886, "grad_norm": 6.065298080444336, "learning_rate": 9.921663268471977e-05, "loss": 1.3593, "step": 1551 }, { "epoch": 0.08485221254057748, "grad_norm": 3.3550941944122314, "learning_rate": 9.921507084356758e-05, "loss": 1.5502, "step": 1552 }, { "epoch": 0.0849068853579361, "grad_norm": 3.228168487548828, "learning_rate": 9.921350745932021e-05, "loss": 1.0039, "step": 1553 }, { "epoch": 0.08496155817529472, "grad_norm": 2.5541138648986816, "learning_rate": 9.921194253202672e-05, "loss": 1.1632, "step": 1554 }, { "epoch": 0.08501623099265335, "grad_norm": 5.0920729637146, "learning_rate": 9.921037606173613e-05, "loss": 1.3131, "step": 1555 }, { "epoch": 0.08507090381001196, "grad_norm": 2.869779109954834, "learning_rate": 9.920880804849761e-05, "loss": 1.2679, "step": 1556 }, { "epoch": 0.08512557662737058, "grad_norm": 2.69856333732605, "learning_rate": 9.920723849236026e-05, "loss": 1.1565, "step": 1557 }, { "epoch": 0.0851802494447292, "grad_norm": 2.9567816257476807, "learning_rate": 9.920566739337336e-05, "loss": 1.3645, "step": 1558 }, { "epoch": 0.08523492226208781, "grad_norm": 2.1918911933898926, "learning_rate": 9.920409475158612e-05, "loss": 1.2472, "step": 1559 }, { "epoch": 0.08528959507944643, "grad_norm": 2.7438161373138428, "learning_rate": 9.920252056704786e-05, "loss": 1.3198, "step": 1560 }, { "epoch": 0.08534426789680506, "grad_norm": 2.7241625785827637, "learning_rate": 9.920094483980797e-05, "loss": 1.325, "step": 1561 }, { "epoch": 0.08539894071416368, "grad_norm": 2.532430410385132, "learning_rate": 9.91993675699158e-05, "loss": 1.1411, "step": 1562 }, { "epoch": 0.0854536135315223, "grad_norm": 2.4519591331481934, "learning_rate": 9.919778875742085e-05, "loss": 1.2784, "step": 1563 }, { "epoch": 0.08550828634888091, "grad_norm": 2.5517849922180176, "learning_rate": 9.91962084023726e-05, "loss": 1.1752, "step": 1564 }, { "epoch": 0.08556295916623953, "grad_norm": 3.852989435195923, "learning_rate": 9.91946265048206e-05, "loss": 1.4629, "step": 1565 }, { "epoch": 0.08561763198359816, "grad_norm": 2.2279365062713623, "learning_rate": 9.919304306481445e-05, "loss": 0.9974, "step": 1566 }, { "epoch": 0.08567230480095678, "grad_norm": 2.3906660079956055, "learning_rate": 9.919145808240382e-05, "loss": 1.1301, "step": 1567 }, { "epoch": 0.0857269776183154, "grad_norm": 3.0406508445739746, "learning_rate": 9.918987155763837e-05, "loss": 1.4127, "step": 1568 }, { "epoch": 0.08578165043567401, "grad_norm": 2.716064214706421, "learning_rate": 9.918828349056788e-05, "loss": 1.256, "step": 1569 }, { "epoch": 0.08583632325303263, "grad_norm": 2.810495615005493, "learning_rate": 9.91866938812421e-05, "loss": 1.4095, "step": 1570 }, { "epoch": 0.08589099607039125, "grad_norm": 2.591315269470215, "learning_rate": 9.918510272971091e-05, "loss": 1.2442, "step": 1571 }, { "epoch": 0.08594566888774988, "grad_norm": 2.4868485927581787, "learning_rate": 9.918351003602417e-05, "loss": 1.1062, "step": 1572 }, { "epoch": 0.0860003417051085, "grad_norm": 3.0756003856658936, "learning_rate": 9.918191580023186e-05, "loss": 1.2608, "step": 1573 }, { "epoch": 0.08605501452246711, "grad_norm": 2.3654253482818604, "learning_rate": 9.918032002238391e-05, "loss": 1.3202, "step": 1574 }, { "epoch": 0.08610968733982573, "grad_norm": 2.370706081390381, "learning_rate": 9.91787227025304e-05, "loss": 1.3246, "step": 1575 }, { "epoch": 0.08616436015718434, "grad_norm": 2.6252965927124023, "learning_rate": 9.917712384072137e-05, "loss": 1.3186, "step": 1576 }, { "epoch": 0.08621903297454298, "grad_norm": 2.529247283935547, "learning_rate": 9.917552343700701e-05, "loss": 1.0123, "step": 1577 }, { "epoch": 0.08627370579190159, "grad_norm": 2.847043514251709, "learning_rate": 9.917392149143744e-05, "loss": 1.1774, "step": 1578 }, { "epoch": 0.08632837860926021, "grad_norm": 3.13879656791687, "learning_rate": 9.917231800406292e-05, "loss": 1.3382, "step": 1579 }, { "epoch": 0.08638305142661883, "grad_norm": 3.796342134475708, "learning_rate": 9.91707129749337e-05, "loss": 1.3544, "step": 1580 }, { "epoch": 0.08643772424397744, "grad_norm": 2.890038251876831, "learning_rate": 9.916910640410014e-05, "loss": 1.3251, "step": 1581 }, { "epoch": 0.08649239706133607, "grad_norm": 2.2827343940734863, "learning_rate": 9.916749829161261e-05, "loss": 1.1576, "step": 1582 }, { "epoch": 0.08654706987869469, "grad_norm": 2.187830924987793, "learning_rate": 9.916588863752148e-05, "loss": 1.1911, "step": 1583 }, { "epoch": 0.08660174269605331, "grad_norm": 2.5148043632507324, "learning_rate": 9.916427744187727e-05, "loss": 1.3773, "step": 1584 }, { "epoch": 0.08665641551341192, "grad_norm": 2.903503656387329, "learning_rate": 9.916266470473049e-05, "loss": 1.3489, "step": 1585 }, { "epoch": 0.08671108833077054, "grad_norm": 2.9133739471435547, "learning_rate": 9.916105042613169e-05, "loss": 1.0642, "step": 1586 }, { "epoch": 0.08676576114812916, "grad_norm": 2.347426414489746, "learning_rate": 9.91594346061315e-05, "loss": 1.2589, "step": 1587 }, { "epoch": 0.08682043396548779, "grad_norm": 2.9687464237213135, "learning_rate": 9.915781724478057e-05, "loss": 1.2786, "step": 1588 }, { "epoch": 0.0868751067828464, "grad_norm": 3.237635374069214, "learning_rate": 9.915619834212961e-05, "loss": 1.2527, "step": 1589 }, { "epoch": 0.08692977960020502, "grad_norm": 2.503286600112915, "learning_rate": 9.91545778982294e-05, "loss": 1.233, "step": 1590 }, { "epoch": 0.08698445241756364, "grad_norm": 4.204772472381592, "learning_rate": 9.915295591313072e-05, "loss": 1.0201, "step": 1591 }, { "epoch": 0.08703912523492226, "grad_norm": 2.7182650566101074, "learning_rate": 9.915133238688445e-05, "loss": 1.1865, "step": 1592 }, { "epoch": 0.08709379805228089, "grad_norm": 2.837278366088867, "learning_rate": 9.914970731954147e-05, "loss": 1.4256, "step": 1593 }, { "epoch": 0.0871484708696395, "grad_norm": 2.979473352432251, "learning_rate": 9.914808071115276e-05, "loss": 1.3712, "step": 1594 }, { "epoch": 0.08720314368699812, "grad_norm": 2.4439339637756348, "learning_rate": 9.91464525617693e-05, "loss": 1.0024, "step": 1595 }, { "epoch": 0.08725781650435674, "grad_norm": 5.130122661590576, "learning_rate": 9.914482287144214e-05, "loss": 1.3081, "step": 1596 }, { "epoch": 0.08731248932171536, "grad_norm": 2.869086265563965, "learning_rate": 9.914319164022239e-05, "loss": 1.3221, "step": 1597 }, { "epoch": 0.08736716213907397, "grad_norm": 3.17793607711792, "learning_rate": 9.914155886816119e-05, "loss": 1.473, "step": 1598 }, { "epoch": 0.0874218349564326, "grad_norm": 2.8371222019195557, "learning_rate": 9.913992455530974e-05, "loss": 1.2659, "step": 1599 }, { "epoch": 0.08747650777379122, "grad_norm": 2.5223779678344727, "learning_rate": 9.913828870171927e-05, "loss": 1.273, "step": 1600 }, { "epoch": 0.08753118059114984, "grad_norm": 2.749974250793457, "learning_rate": 9.913665130744108e-05, "loss": 1.1851, "step": 1601 }, { "epoch": 0.08758585340850845, "grad_norm": 2.719724655151367, "learning_rate": 9.91350123725265e-05, "loss": 1.4341, "step": 1602 }, { "epoch": 0.08764052622586707, "grad_norm": 2.8822498321533203, "learning_rate": 9.913337189702691e-05, "loss": 0.9505, "step": 1603 }, { "epoch": 0.0876951990432257, "grad_norm": 2.802650213241577, "learning_rate": 9.913172988099378e-05, "loss": 1.1118, "step": 1604 }, { "epoch": 0.08774987186058432, "grad_norm": 2.7611074447631836, "learning_rate": 9.913008632447855e-05, "loss": 1.3562, "step": 1605 }, { "epoch": 0.08780454467794294, "grad_norm": 2.6780073642730713, "learning_rate": 9.91284412275328e-05, "loss": 1.1862, "step": 1606 }, { "epoch": 0.08785921749530155, "grad_norm": 2.379751682281494, "learning_rate": 9.912679459020807e-05, "loss": 1.2712, "step": 1607 }, { "epoch": 0.08791389031266017, "grad_norm": 3.166029691696167, "learning_rate": 9.912514641255601e-05, "loss": 1.0056, "step": 1608 }, { "epoch": 0.08796856313001879, "grad_norm": 2.768951892852783, "learning_rate": 9.912349669462829e-05, "loss": 1.3217, "step": 1609 }, { "epoch": 0.08802323594737742, "grad_norm": 3.3737709522247314, "learning_rate": 9.912184543647665e-05, "loss": 1.3401, "step": 1610 }, { "epoch": 0.08807790876473603, "grad_norm": 3.0680758953094482, "learning_rate": 9.912019263815282e-05, "loss": 1.4066, "step": 1611 }, { "epoch": 0.08813258158209465, "grad_norm": 4.7100982666015625, "learning_rate": 9.911853829970868e-05, "loss": 1.1167, "step": 1612 }, { "epoch": 0.08818725439945327, "grad_norm": 2.60017991065979, "learning_rate": 9.911688242119605e-05, "loss": 1.2959, "step": 1613 }, { "epoch": 0.08824192721681189, "grad_norm": 2.8513083457946777, "learning_rate": 9.91152250026669e-05, "loss": 1.335, "step": 1614 }, { "epoch": 0.08829660003417052, "grad_norm": 2.5518877506256104, "learning_rate": 9.911356604417315e-05, "loss": 1.2762, "step": 1615 }, { "epoch": 0.08835127285152913, "grad_norm": 2.4432499408721924, "learning_rate": 9.911190554576684e-05, "loss": 1.1585, "step": 1616 }, { "epoch": 0.08840594566888775, "grad_norm": 2.8603696823120117, "learning_rate": 9.911024350750002e-05, "loss": 1.3285, "step": 1617 }, { "epoch": 0.08846061848624637, "grad_norm": 3.3365628719329834, "learning_rate": 9.910857992942482e-05, "loss": 1.3474, "step": 1618 }, { "epoch": 0.08851529130360498, "grad_norm": 2.632127285003662, "learning_rate": 9.910691481159338e-05, "loss": 1.2716, "step": 1619 }, { "epoch": 0.08856996412096362, "grad_norm": 3.2499308586120605, "learning_rate": 9.910524815405791e-05, "loss": 1.0936, "step": 1620 }, { "epoch": 0.08862463693832223, "grad_norm": 2.6461331844329834, "learning_rate": 9.91035799568707e-05, "loss": 1.1067, "step": 1621 }, { "epoch": 0.08867930975568085, "grad_norm": 3.2770016193389893, "learning_rate": 9.9101910220084e-05, "loss": 1.0956, "step": 1622 }, { "epoch": 0.08873398257303947, "grad_norm": 2.8569798469543457, "learning_rate": 9.91002389437502e-05, "loss": 1.4535, "step": 1623 }, { "epoch": 0.08878865539039808, "grad_norm": 3.1926522254943848, "learning_rate": 9.90985661279217e-05, "loss": 1.1974, "step": 1624 }, { "epoch": 0.0888433282077567, "grad_norm": 2.8908345699310303, "learning_rate": 9.909689177265094e-05, "loss": 1.3361, "step": 1625 }, { "epoch": 0.08889800102511533, "grad_norm": 5.377919673919678, "learning_rate": 9.909521587799042e-05, "loss": 1.1022, "step": 1626 }, { "epoch": 0.08895267384247395, "grad_norm": 2.3386447429656982, "learning_rate": 9.909353844399269e-05, "loss": 1.2266, "step": 1627 }, { "epoch": 0.08900734665983256, "grad_norm": 2.3576080799102783, "learning_rate": 9.909185947071033e-05, "loss": 1.3515, "step": 1628 }, { "epoch": 0.08906201947719118, "grad_norm": 3.084132671356201, "learning_rate": 9.909017895819601e-05, "loss": 1.2252, "step": 1629 }, { "epoch": 0.0891166922945498, "grad_norm": 2.4940667152404785, "learning_rate": 9.908849690650239e-05, "loss": 1.2776, "step": 1630 }, { "epoch": 0.08917136511190843, "grad_norm": 3.0247251987457275, "learning_rate": 9.908681331568224e-05, "loss": 1.139, "step": 1631 }, { "epoch": 0.08922603792926705, "grad_norm": 2.469775915145874, "learning_rate": 9.908512818578832e-05, "loss": 1.1979, "step": 1632 }, { "epoch": 0.08928071074662566, "grad_norm": 3.3128089904785156, "learning_rate": 9.908344151687348e-05, "loss": 1.33, "step": 1633 }, { "epoch": 0.08933538356398428, "grad_norm": 3.805436611175537, "learning_rate": 9.908175330899061e-05, "loss": 1.1995, "step": 1634 }, { "epoch": 0.0893900563813429, "grad_norm": 4.4696760177612305, "learning_rate": 9.908006356219261e-05, "loss": 1.311, "step": 1635 }, { "epoch": 0.08944472919870151, "grad_norm": 3.0176219940185547, "learning_rate": 9.907837227653252e-05, "loss": 1.1679, "step": 1636 }, { "epoch": 0.08949940201606015, "grad_norm": 2.6006133556365967, "learning_rate": 9.907667945206331e-05, "loss": 1.1653, "step": 1637 }, { "epoch": 0.08955407483341876, "grad_norm": 3.1501946449279785, "learning_rate": 9.907498508883808e-05, "loss": 1.0691, "step": 1638 }, { "epoch": 0.08960874765077738, "grad_norm": 2.7287967205047607, "learning_rate": 9.907328918690997e-05, "loss": 1.3647, "step": 1639 }, { "epoch": 0.089663420468136, "grad_norm": 2.6435136795043945, "learning_rate": 9.907159174633212e-05, "loss": 1.246, "step": 1640 }, { "epoch": 0.08971809328549461, "grad_norm": 2.504364490509033, "learning_rate": 9.906989276715779e-05, "loss": 1.1875, "step": 1641 }, { "epoch": 0.08977276610285324, "grad_norm": 3.0720956325531006, "learning_rate": 9.906819224944021e-05, "loss": 1.4542, "step": 1642 }, { "epoch": 0.08982743892021186, "grad_norm": 2.2408981323242188, "learning_rate": 9.906649019323273e-05, "loss": 1.0262, "step": 1643 }, { "epoch": 0.08988211173757048, "grad_norm": 3.5656256675720215, "learning_rate": 9.906478659858871e-05, "loss": 1.2099, "step": 1644 }, { "epoch": 0.0899367845549291, "grad_norm": 2.3036885261535645, "learning_rate": 9.906308146556156e-05, "loss": 1.0801, "step": 1645 }, { "epoch": 0.08999145737228771, "grad_norm": 2.6877787113189697, "learning_rate": 9.906137479420474e-05, "loss": 1.2269, "step": 1646 }, { "epoch": 0.09004613018964633, "grad_norm": 2.794618844985962, "learning_rate": 9.905966658457175e-05, "loss": 1.2592, "step": 1647 }, { "epoch": 0.09010080300700496, "grad_norm": 2.62658429145813, "learning_rate": 9.90579568367162e-05, "loss": 1.3771, "step": 1648 }, { "epoch": 0.09015547582436358, "grad_norm": 3.0906949043273926, "learning_rate": 9.905624555069163e-05, "loss": 1.2999, "step": 1649 }, { "epoch": 0.0902101486417222, "grad_norm": 2.803546905517578, "learning_rate": 9.905453272655173e-05, "loss": 1.2013, "step": 1650 }, { "epoch": 0.09026482145908081, "grad_norm": 2.254859447479248, "learning_rate": 9.90528183643502e-05, "loss": 1.0884, "step": 1651 }, { "epoch": 0.09031949427643943, "grad_norm": 2.4956538677215576, "learning_rate": 9.905110246414081e-05, "loss": 1.3056, "step": 1652 }, { "epoch": 0.09037416709379806, "grad_norm": 3.192894220352173, "learning_rate": 9.904938502597733e-05, "loss": 1.4311, "step": 1653 }, { "epoch": 0.09042883991115667, "grad_norm": 2.7158522605895996, "learning_rate": 9.904766604991363e-05, "loss": 1.1037, "step": 1654 }, { "epoch": 0.09048351272851529, "grad_norm": 2.4201934337615967, "learning_rate": 9.904594553600359e-05, "loss": 1.2066, "step": 1655 }, { "epoch": 0.09053818554587391, "grad_norm": 3.1291913986206055, "learning_rate": 9.904422348430118e-05, "loss": 1.1513, "step": 1656 }, { "epoch": 0.09059285836323253, "grad_norm": 2.4915099143981934, "learning_rate": 9.904249989486037e-05, "loss": 1.1716, "step": 1657 }, { "epoch": 0.09064753118059116, "grad_norm": 3.370617389678955, "learning_rate": 9.904077476773521e-05, "loss": 1.3658, "step": 1658 }, { "epoch": 0.09070220399794977, "grad_norm": 3.0588345527648926, "learning_rate": 9.90390481029798e-05, "loss": 1.424, "step": 1659 }, { "epoch": 0.09075687681530839, "grad_norm": 2.985919237136841, "learning_rate": 9.903731990064826e-05, "loss": 1.2841, "step": 1660 }, { "epoch": 0.09081154963266701, "grad_norm": 5.195987701416016, "learning_rate": 9.903559016079478e-05, "loss": 1.2972, "step": 1661 }, { "epoch": 0.09086622245002562, "grad_norm": 2.338212013244629, "learning_rate": 9.90338588834736e-05, "loss": 1.1658, "step": 1662 }, { "epoch": 0.09092089526738424, "grad_norm": 2.852987051010132, "learning_rate": 9.903212606873901e-05, "loss": 1.1022, "step": 1663 }, { "epoch": 0.09097556808474287, "grad_norm": 2.9962472915649414, "learning_rate": 9.903039171664532e-05, "loss": 1.2665, "step": 1664 }, { "epoch": 0.09103024090210149, "grad_norm": 2.120899200439453, "learning_rate": 9.902865582724692e-05, "loss": 1.2264, "step": 1665 }, { "epoch": 0.0910849137194601, "grad_norm": 5.473898410797119, "learning_rate": 9.902691840059826e-05, "loss": 1.2406, "step": 1666 }, { "epoch": 0.09113958653681872, "grad_norm": 2.6220381259918213, "learning_rate": 9.902517943675378e-05, "loss": 1.2851, "step": 1667 }, { "epoch": 0.09119425935417734, "grad_norm": 3.020942211151123, "learning_rate": 9.902343893576801e-05, "loss": 1.374, "step": 1668 }, { "epoch": 0.09124893217153597, "grad_norm": 3.885592222213745, "learning_rate": 9.902169689769554e-05, "loss": 1.2169, "step": 1669 }, { "epoch": 0.09130360498889459, "grad_norm": 2.732008934020996, "learning_rate": 9.901995332259098e-05, "loss": 1.1476, "step": 1670 }, { "epoch": 0.0913582778062532, "grad_norm": 2.560692548751831, "learning_rate": 9.9018208210509e-05, "loss": 1.2508, "step": 1671 }, { "epoch": 0.09141295062361182, "grad_norm": 2.971052885055542, "learning_rate": 9.90164615615043e-05, "loss": 1.3656, "step": 1672 }, { "epoch": 0.09146762344097044, "grad_norm": 3.2016420364379883, "learning_rate": 9.901471337563166e-05, "loss": 1.3406, "step": 1673 }, { "epoch": 0.09152229625832906, "grad_norm": 3.156562328338623, "learning_rate": 9.901296365294591e-05, "loss": 1.1617, "step": 1674 }, { "epoch": 0.09157696907568769, "grad_norm": 2.9032633304595947, "learning_rate": 9.901121239350188e-05, "loss": 1.2591, "step": 1675 }, { "epoch": 0.0916316418930463, "grad_norm": 3.104708194732666, "learning_rate": 9.90094595973545e-05, "loss": 1.1456, "step": 1676 }, { "epoch": 0.09168631471040492, "grad_norm": 2.6880581378936768, "learning_rate": 9.900770526455872e-05, "loss": 1.2687, "step": 1677 }, { "epoch": 0.09174098752776354, "grad_norm": 2.8596134185791016, "learning_rate": 9.900594939516954e-05, "loss": 0.9595, "step": 1678 }, { "epoch": 0.09179566034512215, "grad_norm": 2.9463555812835693, "learning_rate": 9.900419198924203e-05, "loss": 1.2579, "step": 1679 }, { "epoch": 0.09185033316248079, "grad_norm": 2.539997100830078, "learning_rate": 9.900243304683126e-05, "loss": 1.2221, "step": 1680 }, { "epoch": 0.0919050059798394, "grad_norm": 2.10227632522583, "learning_rate": 9.900067256799241e-05, "loss": 1.2132, "step": 1681 }, { "epoch": 0.09195967879719802, "grad_norm": 4.575279712677002, "learning_rate": 9.899891055278067e-05, "loss": 1.5278, "step": 1682 }, { "epoch": 0.09201435161455664, "grad_norm": 3.0287139415740967, "learning_rate": 9.899714700125129e-05, "loss": 1.0109, "step": 1683 }, { "epoch": 0.09206902443191525, "grad_norm": 2.7277891635894775, "learning_rate": 9.899538191345955e-05, "loss": 1.3752, "step": 1684 }, { "epoch": 0.09212369724927387, "grad_norm": 2.6151058673858643, "learning_rate": 9.899361528946081e-05, "loss": 1.1452, "step": 1685 }, { "epoch": 0.0921783700666325, "grad_norm": 2.491774559020996, "learning_rate": 9.899184712931044e-05, "loss": 1.1062, "step": 1686 }, { "epoch": 0.09223304288399112, "grad_norm": 3.3872766494750977, "learning_rate": 9.899007743306392e-05, "loss": 1.4567, "step": 1687 }, { "epoch": 0.09228771570134973, "grad_norm": 2.9335174560546875, "learning_rate": 9.89883062007767e-05, "loss": 1.3259, "step": 1688 }, { "epoch": 0.09234238851870835, "grad_norm": 2.2800488471984863, "learning_rate": 9.898653343250431e-05, "loss": 1.174, "step": 1689 }, { "epoch": 0.09239706133606697, "grad_norm": 3.0704665184020996, "learning_rate": 9.898475912830236e-05, "loss": 1.3853, "step": 1690 }, { "epoch": 0.0924517341534256, "grad_norm": 3.9985897541046143, "learning_rate": 9.898298328822647e-05, "loss": 1.2279, "step": 1691 }, { "epoch": 0.09250640697078422, "grad_norm": 2.1990158557891846, "learning_rate": 9.898120591233233e-05, "loss": 1.0231, "step": 1692 }, { "epoch": 0.09256107978814283, "grad_norm": 2.423032283782959, "learning_rate": 9.897942700067564e-05, "loss": 1.0887, "step": 1693 }, { "epoch": 0.09261575260550145, "grad_norm": 2.4035513401031494, "learning_rate": 9.89776465533122e-05, "loss": 1.2139, "step": 1694 }, { "epoch": 0.09267042542286007, "grad_norm": 2.723304271697998, "learning_rate": 9.897586457029785e-05, "loss": 1.1426, "step": 1695 }, { "epoch": 0.0927250982402187, "grad_norm": 2.8715908527374268, "learning_rate": 9.897408105168842e-05, "loss": 1.193, "step": 1696 }, { "epoch": 0.09277977105757731, "grad_norm": 2.907489538192749, "learning_rate": 9.897229599753986e-05, "loss": 1.1463, "step": 1697 }, { "epoch": 0.09283444387493593, "grad_norm": 2.318943500518799, "learning_rate": 9.897050940790815e-05, "loss": 1.1422, "step": 1698 }, { "epoch": 0.09288911669229455, "grad_norm": 3.0512754917144775, "learning_rate": 9.896872128284926e-05, "loss": 1.2625, "step": 1699 }, { "epoch": 0.09294378950965317, "grad_norm": 2.332623243331909, "learning_rate": 9.89669316224193e-05, "loss": 1.2448, "step": 1700 }, { "epoch": 0.09299846232701178, "grad_norm": 2.4535610675811768, "learning_rate": 9.896514042667436e-05, "loss": 1.3508, "step": 1701 }, { "epoch": 0.09305313514437041, "grad_norm": 3.108004570007324, "learning_rate": 9.89633476956706e-05, "loss": 1.3152, "step": 1702 }, { "epoch": 0.09310780796172903, "grad_norm": 2.551837921142578, "learning_rate": 9.896155342946425e-05, "loss": 1.2712, "step": 1703 }, { "epoch": 0.09316248077908765, "grad_norm": 2.4753823280334473, "learning_rate": 9.895975762811155e-05, "loss": 1.1709, "step": 1704 }, { "epoch": 0.09321715359644626, "grad_norm": 3.212083101272583, "learning_rate": 9.895796029166881e-05, "loss": 1.1924, "step": 1705 }, { "epoch": 0.09327182641380488, "grad_norm": 2.9527132511138916, "learning_rate": 9.895616142019239e-05, "loss": 1.2948, "step": 1706 }, { "epoch": 0.09332649923116351, "grad_norm": 2.310084342956543, "learning_rate": 9.895436101373868e-05, "loss": 1.2321, "step": 1707 }, { "epoch": 0.09338117204852213, "grad_norm": 2.995300054550171, "learning_rate": 9.895255907236414e-05, "loss": 1.15, "step": 1708 }, { "epoch": 0.09343584486588075, "grad_norm": 3.0050742626190186, "learning_rate": 9.895075559612528e-05, "loss": 1.2073, "step": 1709 }, { "epoch": 0.09349051768323936, "grad_norm": 2.573638916015625, "learning_rate": 9.89489505850786e-05, "loss": 1.2714, "step": 1710 }, { "epoch": 0.09354519050059798, "grad_norm": 2.419379711151123, "learning_rate": 9.894714403928076e-05, "loss": 1.0447, "step": 1711 }, { "epoch": 0.0935998633179566, "grad_norm": 2.353797435760498, "learning_rate": 9.894533595878835e-05, "loss": 1.2145, "step": 1712 }, { "epoch": 0.09365453613531523, "grad_norm": 2.5074315071105957, "learning_rate": 9.894352634365808e-05, "loss": 1.2732, "step": 1713 }, { "epoch": 0.09370920895267384, "grad_norm": 2.8927574157714844, "learning_rate": 9.89417151939467e-05, "loss": 1.492, "step": 1714 }, { "epoch": 0.09376388177003246, "grad_norm": 3.0355916023254395, "learning_rate": 9.893990250971096e-05, "loss": 1.0055, "step": 1715 }, { "epoch": 0.09381855458739108, "grad_norm": 2.496157169342041, "learning_rate": 9.893808829100775e-05, "loss": 0.8857, "step": 1716 }, { "epoch": 0.0938732274047497, "grad_norm": 2.4785001277923584, "learning_rate": 9.893627253789391e-05, "loss": 1.1802, "step": 1717 }, { "epoch": 0.09392790022210833, "grad_norm": 2.3578097820281982, "learning_rate": 9.893445525042638e-05, "loss": 1.078, "step": 1718 }, { "epoch": 0.09398257303946694, "grad_norm": 2.7151994705200195, "learning_rate": 9.893263642866215e-05, "loss": 1.271, "step": 1719 }, { "epoch": 0.09403724585682556, "grad_norm": 2.8046252727508545, "learning_rate": 9.893081607265825e-05, "loss": 1.2528, "step": 1720 }, { "epoch": 0.09409191867418418, "grad_norm": 2.788609266281128, "learning_rate": 9.892899418247175e-05, "loss": 1.2408, "step": 1721 }, { "epoch": 0.0941465914915428, "grad_norm": 4.901615142822266, "learning_rate": 9.892717075815977e-05, "loss": 1.2871, "step": 1722 }, { "epoch": 0.09420126430890141, "grad_norm": 6.183658599853516, "learning_rate": 9.892534579977946e-05, "loss": 1.43, "step": 1723 }, { "epoch": 0.09425593712626004, "grad_norm": 2.196901798248291, "learning_rate": 9.892351930738808e-05, "loss": 1.1816, "step": 1724 }, { "epoch": 0.09431060994361866, "grad_norm": 3.295125722885132, "learning_rate": 9.892169128104289e-05, "loss": 1.4666, "step": 1725 }, { "epoch": 0.09436528276097728, "grad_norm": 3.0331945419311523, "learning_rate": 9.89198617208012e-05, "loss": 1.2657, "step": 1726 }, { "epoch": 0.09441995557833589, "grad_norm": 2.540419578552246, "learning_rate": 9.891803062672035e-05, "loss": 1.2879, "step": 1727 }, { "epoch": 0.09447462839569451, "grad_norm": 3.29960298538208, "learning_rate": 9.891619799885779e-05, "loss": 1.6853, "step": 1728 }, { "epoch": 0.09452930121305314, "grad_norm": 3.4407286643981934, "learning_rate": 9.891436383727095e-05, "loss": 1.3203, "step": 1729 }, { "epoch": 0.09458397403041176, "grad_norm": 3.002228021621704, "learning_rate": 9.891252814201737e-05, "loss": 1.3367, "step": 1730 }, { "epoch": 0.09463864684777037, "grad_norm": 3.1627089977264404, "learning_rate": 9.891069091315458e-05, "loss": 1.0362, "step": 1731 }, { "epoch": 0.09469331966512899, "grad_norm": 2.803483009338379, "learning_rate": 9.89088521507402e-05, "loss": 1.3676, "step": 1732 }, { "epoch": 0.09474799248248761, "grad_norm": 2.395719289779663, "learning_rate": 9.890701185483187e-05, "loss": 1.2274, "step": 1733 }, { "epoch": 0.09480266529984624, "grad_norm": 3.4306914806365967, "learning_rate": 9.890517002548732e-05, "loss": 1.19, "step": 1734 }, { "epoch": 0.09485733811720486, "grad_norm": 3.5958480834960938, "learning_rate": 9.890332666276425e-05, "loss": 0.9302, "step": 1735 }, { "epoch": 0.09491201093456347, "grad_norm": 3.3064801692962646, "learning_rate": 9.890148176672049e-05, "loss": 1.0457, "step": 1736 }, { "epoch": 0.09496668375192209, "grad_norm": 2.910724401473999, "learning_rate": 9.88996353374139e-05, "loss": 1.2704, "step": 1737 }, { "epoch": 0.09502135656928071, "grad_norm": 2.925143241882324, "learning_rate": 9.889778737490232e-05, "loss": 1.0486, "step": 1738 }, { "epoch": 0.09507602938663932, "grad_norm": 2.5507490634918213, "learning_rate": 9.889593787924374e-05, "loss": 1.1931, "step": 1739 }, { "epoch": 0.09513070220399795, "grad_norm": 2.612460136413574, "learning_rate": 9.889408685049615e-05, "loss": 1.3788, "step": 1740 }, { "epoch": 0.09518537502135657, "grad_norm": 2.778674840927124, "learning_rate": 9.889223428871755e-05, "loss": 1.0764, "step": 1741 }, { "epoch": 0.09524004783871519, "grad_norm": 3.3049330711364746, "learning_rate": 9.889038019396604e-05, "loss": 1.3245, "step": 1742 }, { "epoch": 0.0952947206560738, "grad_norm": 2.1636970043182373, "learning_rate": 9.888852456629977e-05, "loss": 1.0165, "step": 1743 }, { "epoch": 0.09534939347343242, "grad_norm": 2.691335439682007, "learning_rate": 9.888666740577691e-05, "loss": 1.3331, "step": 1744 }, { "epoch": 0.09540406629079105, "grad_norm": 2.8599865436553955, "learning_rate": 9.88848087124557e-05, "loss": 1.2083, "step": 1745 }, { "epoch": 0.09545873910814967, "grad_norm": 2.7806169986724854, "learning_rate": 9.888294848639439e-05, "loss": 1.3711, "step": 1746 }, { "epoch": 0.09551341192550829, "grad_norm": 3.295180082321167, "learning_rate": 9.888108672765132e-05, "loss": 1.3131, "step": 1747 }, { "epoch": 0.0955680847428669, "grad_norm": 3.3268661499023438, "learning_rate": 9.887922343628488e-05, "loss": 1.3684, "step": 1748 }, { "epoch": 0.09562275756022552, "grad_norm": 2.5856058597564697, "learning_rate": 9.88773586123535e-05, "loss": 1.1939, "step": 1749 }, { "epoch": 0.09567743037758414, "grad_norm": 3.077516794204712, "learning_rate": 9.887549225591559e-05, "loss": 1.3476, "step": 1750 }, { "epoch": 0.09573210319494277, "grad_norm": 2.6115474700927734, "learning_rate": 9.887362436702974e-05, "loss": 1.3311, "step": 1751 }, { "epoch": 0.09578677601230139, "grad_norm": 3.973267078399658, "learning_rate": 9.887175494575447e-05, "loss": 1.436, "step": 1752 }, { "epoch": 0.09584144882966, "grad_norm": 2.7810866832733154, "learning_rate": 9.886988399214841e-05, "loss": 1.4473, "step": 1753 }, { "epoch": 0.09589612164701862, "grad_norm": 2.829869031906128, "learning_rate": 9.886801150627021e-05, "loss": 1.1745, "step": 1754 }, { "epoch": 0.09595079446437724, "grad_norm": 2.316978693008423, "learning_rate": 9.88661374881786e-05, "loss": 1.2294, "step": 1755 }, { "epoch": 0.09600546728173587, "grad_norm": 3.399916410446167, "learning_rate": 9.886426193793232e-05, "loss": 0.99, "step": 1756 }, { "epoch": 0.09606014009909448, "grad_norm": 2.9704771041870117, "learning_rate": 9.886238485559019e-05, "loss": 1.132, "step": 1757 }, { "epoch": 0.0961148129164531, "grad_norm": 2.723158597946167, "learning_rate": 9.886050624121106e-05, "loss": 1.3005, "step": 1758 }, { "epoch": 0.09616948573381172, "grad_norm": 2.751192331314087, "learning_rate": 9.885862609485383e-05, "loss": 1.1585, "step": 1759 }, { "epoch": 0.09622415855117034, "grad_norm": 3.213379383087158, "learning_rate": 9.885674441657744e-05, "loss": 1.3374, "step": 1760 }, { "epoch": 0.09627883136852895, "grad_norm": 2.486988067626953, "learning_rate": 9.88548612064409e-05, "loss": 1.0689, "step": 1761 }, { "epoch": 0.09633350418588758, "grad_norm": 2.8810107707977295, "learning_rate": 9.885297646450327e-05, "loss": 1.2858, "step": 1762 }, { "epoch": 0.0963881770032462, "grad_norm": 2.3442444801330566, "learning_rate": 9.885109019082362e-05, "loss": 1.0429, "step": 1763 }, { "epoch": 0.09644284982060482, "grad_norm": 4.3059821128845215, "learning_rate": 9.884920238546112e-05, "loss": 1.3913, "step": 1764 }, { "epoch": 0.09649752263796343, "grad_norm": 2.809410572052002, "learning_rate": 9.884731304847492e-05, "loss": 1.1919, "step": 1765 }, { "epoch": 0.09655219545532205, "grad_norm": 2.29012131690979, "learning_rate": 9.88454221799243e-05, "loss": 1.2021, "step": 1766 }, { "epoch": 0.09660686827268068, "grad_norm": 2.6560332775115967, "learning_rate": 9.884352977986851e-05, "loss": 1.2626, "step": 1767 }, { "epoch": 0.0966615410900393, "grad_norm": 2.744647264480591, "learning_rate": 9.884163584836692e-05, "loss": 1.0042, "step": 1768 }, { "epoch": 0.09671621390739792, "grad_norm": 2.941131114959717, "learning_rate": 9.883974038547887e-05, "loss": 1.2101, "step": 1769 }, { "epoch": 0.09677088672475653, "grad_norm": 3.386199474334717, "learning_rate": 9.883784339126385e-05, "loss": 1.3747, "step": 1770 }, { "epoch": 0.09682555954211515, "grad_norm": 2.9722259044647217, "learning_rate": 9.883594486578128e-05, "loss": 1.3043, "step": 1771 }, { "epoch": 0.09688023235947378, "grad_norm": 3.0657784938812256, "learning_rate": 9.883404480909072e-05, "loss": 1.3949, "step": 1772 }, { "epoch": 0.0969349051768324, "grad_norm": 3.0396385192871094, "learning_rate": 9.883214322125174e-05, "loss": 1.3347, "step": 1773 }, { "epoch": 0.09698957799419101, "grad_norm": 2.244410276412964, "learning_rate": 9.883024010232394e-05, "loss": 0.9545, "step": 1774 }, { "epoch": 0.09704425081154963, "grad_norm": 3.3378219604492188, "learning_rate": 9.882833545236703e-05, "loss": 1.4032, "step": 1775 }, { "epoch": 0.09709892362890825, "grad_norm": 2.5050344467163086, "learning_rate": 9.88264292714407e-05, "loss": 1.3154, "step": 1776 }, { "epoch": 0.09715359644626687, "grad_norm": 2.80977463722229, "learning_rate": 9.882452155960471e-05, "loss": 1.2519, "step": 1777 }, { "epoch": 0.0972082692636255, "grad_norm": 2.480940818786621, "learning_rate": 9.882261231691891e-05, "loss": 1.0584, "step": 1778 }, { "epoch": 0.09726294208098411, "grad_norm": 2.5448832511901855, "learning_rate": 9.882070154344312e-05, "loss": 1.2439, "step": 1779 }, { "epoch": 0.09731761489834273, "grad_norm": 2.7444405555725098, "learning_rate": 9.88187892392373e-05, "loss": 1.1371, "step": 1780 }, { "epoch": 0.09737228771570135, "grad_norm": 2.261296272277832, "learning_rate": 9.881687540436136e-05, "loss": 1.0841, "step": 1781 }, { "epoch": 0.09742696053305996, "grad_norm": 2.340007781982422, "learning_rate": 9.881496003887533e-05, "loss": 1.0983, "step": 1782 }, { "epoch": 0.0974816333504186, "grad_norm": 2.3909218311309814, "learning_rate": 9.881304314283927e-05, "loss": 1.0904, "step": 1783 }, { "epoch": 0.09753630616777721, "grad_norm": 2.2192089557647705, "learning_rate": 9.881112471631326e-05, "loss": 1.1008, "step": 1784 }, { "epoch": 0.09759097898513583, "grad_norm": 2.7981929779052734, "learning_rate": 9.880920475935748e-05, "loss": 1.2812, "step": 1785 }, { "epoch": 0.09764565180249445, "grad_norm": 2.5945775508880615, "learning_rate": 9.88072832720321e-05, "loss": 1.2034, "step": 1786 }, { "epoch": 0.09770032461985306, "grad_norm": 2.7197132110595703, "learning_rate": 9.88053602543974e-05, "loss": 1.2639, "step": 1787 }, { "epoch": 0.09775499743721168, "grad_norm": 2.278454542160034, "learning_rate": 9.880343570651363e-05, "loss": 1.1781, "step": 1788 }, { "epoch": 0.09780967025457031, "grad_norm": 4.364202499389648, "learning_rate": 9.880150962844116e-05, "loss": 1.2447, "step": 1789 }, { "epoch": 0.09786434307192893, "grad_norm": 2.1722116470336914, "learning_rate": 9.87995820202404e-05, "loss": 1.0817, "step": 1790 }, { "epoch": 0.09791901588928754, "grad_norm": 2.7912986278533936, "learning_rate": 9.879765288197173e-05, "loss": 0.9883, "step": 1791 }, { "epoch": 0.09797368870664616, "grad_norm": 2.549956798553467, "learning_rate": 9.879572221369571e-05, "loss": 1.0575, "step": 1792 }, { "epoch": 0.09802836152400478, "grad_norm": 2.482320785522461, "learning_rate": 9.879379001547281e-05, "loss": 1.1384, "step": 1793 }, { "epoch": 0.09808303434136341, "grad_norm": 3.034369707107544, "learning_rate": 9.879185628736366e-05, "loss": 1.4186, "step": 1794 }, { "epoch": 0.09813770715872203, "grad_norm": 3.1540980339050293, "learning_rate": 9.878992102942885e-05, "loss": 1.0287, "step": 1795 }, { "epoch": 0.09819237997608064, "grad_norm": 3.7905216217041016, "learning_rate": 9.87879842417291e-05, "loss": 1.0947, "step": 1796 }, { "epoch": 0.09824705279343926, "grad_norm": 2.526474952697754, "learning_rate": 9.87860459243251e-05, "loss": 1.2629, "step": 1797 }, { "epoch": 0.09830172561079788, "grad_norm": 3.3054745197296143, "learning_rate": 9.878410607727764e-05, "loss": 1.0833, "step": 1798 }, { "epoch": 0.0983563984281565, "grad_norm": 3.220684289932251, "learning_rate": 9.878216470064753e-05, "loss": 1.3948, "step": 1799 }, { "epoch": 0.09841107124551512, "grad_norm": 4.402083396911621, "learning_rate": 9.878022179449567e-05, "loss": 1.208, "step": 1800 }, { "epoch": 0.09846574406287374, "grad_norm": 2.442448616027832, "learning_rate": 9.877827735888294e-05, "loss": 1.0645, "step": 1801 }, { "epoch": 0.09852041688023236, "grad_norm": 3.052736282348633, "learning_rate": 9.877633139387033e-05, "loss": 1.1497, "step": 1802 }, { "epoch": 0.09857508969759098, "grad_norm": 2.5376293659210205, "learning_rate": 9.877438389951885e-05, "loss": 1.2573, "step": 1803 }, { "epoch": 0.09862976251494959, "grad_norm": 4.009627819061279, "learning_rate": 9.877243487588958e-05, "loss": 1.254, "step": 1804 }, { "epoch": 0.09868443533230822, "grad_norm": 3.3942341804504395, "learning_rate": 9.877048432304359e-05, "loss": 1.1368, "step": 1805 }, { "epoch": 0.09873910814966684, "grad_norm": 5.029207229614258, "learning_rate": 9.876853224104205e-05, "loss": 1.1849, "step": 1806 }, { "epoch": 0.09879378096702546, "grad_norm": 3.1785521507263184, "learning_rate": 9.87665786299462e-05, "loss": 1.0428, "step": 1807 }, { "epoch": 0.09884845378438407, "grad_norm": 2.1852641105651855, "learning_rate": 9.876462348981725e-05, "loss": 1.0882, "step": 1808 }, { "epoch": 0.09890312660174269, "grad_norm": 4.160054683685303, "learning_rate": 9.876266682071654e-05, "loss": 1.1877, "step": 1809 }, { "epoch": 0.09895779941910132, "grad_norm": 4.269983768463135, "learning_rate": 9.876070862270536e-05, "loss": 1.1625, "step": 1810 }, { "epoch": 0.09901247223645994, "grad_norm": 2.8090732097625732, "learning_rate": 9.875874889584518e-05, "loss": 1.1922, "step": 1811 }, { "epoch": 0.09906714505381856, "grad_norm": 3.0890188217163086, "learning_rate": 9.87567876401974e-05, "loss": 1.3329, "step": 1812 }, { "epoch": 0.09912181787117717, "grad_norm": 3.817171812057495, "learning_rate": 9.875482485582353e-05, "loss": 1.0341, "step": 1813 }, { "epoch": 0.09917649068853579, "grad_norm": 2.490506410598755, "learning_rate": 9.875286054278512e-05, "loss": 1.2957, "step": 1814 }, { "epoch": 0.0992311635058944, "grad_norm": 2.2578489780426025, "learning_rate": 9.875089470114373e-05, "loss": 1.3058, "step": 1815 }, { "epoch": 0.09928583632325304, "grad_norm": 3.0862648487091064, "learning_rate": 9.874892733096101e-05, "loss": 1.3263, "step": 1816 }, { "epoch": 0.09934050914061165, "grad_norm": 2.2228341102600098, "learning_rate": 9.874695843229866e-05, "loss": 1.1367, "step": 1817 }, { "epoch": 0.09939518195797027, "grad_norm": 2.882876396179199, "learning_rate": 9.874498800521841e-05, "loss": 1.1109, "step": 1818 }, { "epoch": 0.09944985477532889, "grad_norm": 2.504615068435669, "learning_rate": 9.874301604978203e-05, "loss": 1.1083, "step": 1819 }, { "epoch": 0.0995045275926875, "grad_norm": 2.4058287143707275, "learning_rate": 9.874104256605132e-05, "loss": 1.1369, "step": 1820 }, { "epoch": 0.09955920041004614, "grad_norm": 2.9587717056274414, "learning_rate": 9.873906755408821e-05, "loss": 1.3752, "step": 1821 }, { "epoch": 0.09961387322740475, "grad_norm": 3.1746692657470703, "learning_rate": 9.873709101395462e-05, "loss": 0.9462, "step": 1822 }, { "epoch": 0.09966854604476337, "grad_norm": 2.565247058868408, "learning_rate": 9.87351129457125e-05, "loss": 1.0721, "step": 1823 }, { "epoch": 0.09972321886212199, "grad_norm": 2.971658945083618, "learning_rate": 9.873313334942386e-05, "loss": 1.4544, "step": 1824 }, { "epoch": 0.0997778916794806, "grad_norm": 3.0744574069976807, "learning_rate": 9.87311522251508e-05, "loss": 1.1715, "step": 1825 }, { "epoch": 0.09983256449683922, "grad_norm": 2.970545768737793, "learning_rate": 9.872916957295542e-05, "loss": 1.2239, "step": 1826 }, { "epoch": 0.09988723731419785, "grad_norm": 3.110495090484619, "learning_rate": 9.872718539289989e-05, "loss": 1.3644, "step": 1827 }, { "epoch": 0.09994191013155647, "grad_norm": 2.755202054977417, "learning_rate": 9.872519968504641e-05, "loss": 1.2467, "step": 1828 }, { "epoch": 0.09999658294891509, "grad_norm": 2.668565034866333, "learning_rate": 9.872321244945725e-05, "loss": 1.3346, "step": 1829 }, { "epoch": 0.1000512557662737, "grad_norm": 2.7075634002685547, "learning_rate": 9.872122368619472e-05, "loss": 1.4088, "step": 1830 }, { "epoch": 0.10010592858363232, "grad_norm": 3.10394549369812, "learning_rate": 9.871923339532116e-05, "loss": 1.4299, "step": 1831 }, { "epoch": 0.10016060140099095, "grad_norm": 2.695322036743164, "learning_rate": 9.8717241576899e-05, "loss": 1.1805, "step": 1832 }, { "epoch": 0.10021527421834957, "grad_norm": 2.925097703933716, "learning_rate": 9.871524823099067e-05, "loss": 1.1858, "step": 1833 }, { "epoch": 0.10026994703570818, "grad_norm": 3.3315136432647705, "learning_rate": 9.871325335765868e-05, "loss": 1.2881, "step": 1834 }, { "epoch": 0.1003246198530668, "grad_norm": 3.2320680618286133, "learning_rate": 9.871125695696558e-05, "loss": 1.2609, "step": 1835 }, { "epoch": 0.10037929267042542, "grad_norm": 3.30849552154541, "learning_rate": 9.870925902897395e-05, "loss": 1.5755, "step": 1836 }, { "epoch": 0.10043396548778405, "grad_norm": 2.824286699295044, "learning_rate": 9.870725957374645e-05, "loss": 1.2574, "step": 1837 }, { "epoch": 0.10048863830514267, "grad_norm": 4.0235209465026855, "learning_rate": 9.870525859134578e-05, "loss": 1.2547, "step": 1838 }, { "epoch": 0.10054331112250128, "grad_norm": 3.110530138015747, "learning_rate": 9.870325608183465e-05, "loss": 1.1989, "step": 1839 }, { "epoch": 0.1005979839398599, "grad_norm": 2.615035057067871, "learning_rate": 9.870125204527585e-05, "loss": 1.0459, "step": 1840 }, { "epoch": 0.10065265675721852, "grad_norm": 2.3247365951538086, "learning_rate": 9.869924648173224e-05, "loss": 1.2229, "step": 1841 }, { "epoch": 0.10070732957457713, "grad_norm": 2.8798136711120605, "learning_rate": 9.869723939126668e-05, "loss": 1.3384, "step": 1842 }, { "epoch": 0.10076200239193576, "grad_norm": 2.392671585083008, "learning_rate": 9.869523077394211e-05, "loss": 1.255, "step": 1843 }, { "epoch": 0.10081667520929438, "grad_norm": 2.27565598487854, "learning_rate": 9.869322062982151e-05, "loss": 1.1457, "step": 1844 }, { "epoch": 0.100871348026653, "grad_norm": 3.093404531478882, "learning_rate": 9.869120895896791e-05, "loss": 0.8592, "step": 1845 }, { "epoch": 0.10092602084401162, "grad_norm": 2.78855299949646, "learning_rate": 9.868919576144437e-05, "loss": 1.1617, "step": 1846 }, { "epoch": 0.10098069366137023, "grad_norm": 2.7230541706085205, "learning_rate": 9.868718103731403e-05, "loss": 1.2388, "step": 1847 }, { "epoch": 0.10103536647872886, "grad_norm": 2.9686408042907715, "learning_rate": 9.868516478664003e-05, "loss": 1.3149, "step": 1848 }, { "epoch": 0.10109003929608748, "grad_norm": 3.167048454284668, "learning_rate": 9.868314700948562e-05, "loss": 1.2565, "step": 1849 }, { "epoch": 0.1011447121134461, "grad_norm": 2.87930965423584, "learning_rate": 9.868112770591404e-05, "loss": 1.1965, "step": 1850 }, { "epoch": 0.10119938493080471, "grad_norm": 2.332636833190918, "learning_rate": 9.867910687598864e-05, "loss": 1.1049, "step": 1851 }, { "epoch": 0.10125405774816333, "grad_norm": 2.6866395473480225, "learning_rate": 9.867708451977275e-05, "loss": 1.1162, "step": 1852 }, { "epoch": 0.10130873056552195, "grad_norm": 2.5072436332702637, "learning_rate": 9.867506063732979e-05, "loss": 1.2257, "step": 1853 }, { "epoch": 0.10136340338288058, "grad_norm": 2.8741068840026855, "learning_rate": 9.86730352287232e-05, "loss": 1.2733, "step": 1854 }, { "epoch": 0.1014180762002392, "grad_norm": 2.6504709720611572, "learning_rate": 9.867100829401649e-05, "loss": 1.0143, "step": 1855 }, { "epoch": 0.10147274901759781, "grad_norm": 2.8348352909088135, "learning_rate": 9.866897983327326e-05, "loss": 1.279, "step": 1856 }, { "epoch": 0.10152742183495643, "grad_norm": 3.409512996673584, "learning_rate": 9.866694984655705e-05, "loss": 1.2984, "step": 1857 }, { "epoch": 0.10158209465231505, "grad_norm": 4.679818153381348, "learning_rate": 9.866491833393153e-05, "loss": 1.3983, "step": 1858 }, { "epoch": 0.10163676746967368, "grad_norm": 3.070343017578125, "learning_rate": 9.866288529546039e-05, "loss": 1.3432, "step": 1859 }, { "epoch": 0.1016914402870323, "grad_norm": 2.506696939468384, "learning_rate": 9.866085073120738e-05, "loss": 1.3849, "step": 1860 }, { "epoch": 0.10174611310439091, "grad_norm": 2.8898181915283203, "learning_rate": 9.865881464123631e-05, "loss": 1.2152, "step": 1861 }, { "epoch": 0.10180078592174953, "grad_norm": 2.3092286586761475, "learning_rate": 9.865677702561101e-05, "loss": 1.0674, "step": 1862 }, { "epoch": 0.10185545873910815, "grad_norm": 4.593172550201416, "learning_rate": 9.865473788439533e-05, "loss": 1.1972, "step": 1863 }, { "epoch": 0.10191013155646676, "grad_norm": 3.8869142532348633, "learning_rate": 9.865269721765326e-05, "loss": 1.2049, "step": 1864 }, { "epoch": 0.1019648043738254, "grad_norm": 3.074493885040283, "learning_rate": 9.865065502544874e-05, "loss": 1.1743, "step": 1865 }, { "epoch": 0.10201947719118401, "grad_norm": 2.7111122608184814, "learning_rate": 9.864861130784584e-05, "loss": 1.2444, "step": 1866 }, { "epoch": 0.10207415000854263, "grad_norm": 4.592868328094482, "learning_rate": 9.86465660649086e-05, "loss": 1.2797, "step": 1867 }, { "epoch": 0.10212882282590124, "grad_norm": 2.5317931175231934, "learning_rate": 9.86445192967012e-05, "loss": 1.4071, "step": 1868 }, { "epoch": 0.10218349564325986, "grad_norm": 2.409573793411255, "learning_rate": 9.864247100328775e-05, "loss": 1.2352, "step": 1869 }, { "epoch": 0.10223816846061849, "grad_norm": 2.2654740810394287, "learning_rate": 9.864042118473251e-05, "loss": 0.933, "step": 1870 }, { "epoch": 0.10229284127797711, "grad_norm": 2.7753522396087646, "learning_rate": 9.863836984109975e-05, "loss": 1.1709, "step": 1871 }, { "epoch": 0.10234751409533573, "grad_norm": 2.5252280235290527, "learning_rate": 9.863631697245377e-05, "loss": 1.0963, "step": 1872 }, { "epoch": 0.10240218691269434, "grad_norm": 2.821141242980957, "learning_rate": 9.863426257885896e-05, "loss": 1.3423, "step": 1873 }, { "epoch": 0.10245685973005296, "grad_norm": 2.387444019317627, "learning_rate": 9.863220666037971e-05, "loss": 1.1803, "step": 1874 }, { "epoch": 0.10251153254741159, "grad_norm": 2.6895222663879395, "learning_rate": 9.863014921708051e-05, "loss": 1.3192, "step": 1875 }, { "epoch": 0.10256620536477021, "grad_norm": 2.1601381301879883, "learning_rate": 9.862809024902584e-05, "loss": 1.2779, "step": 1876 }, { "epoch": 0.10262087818212882, "grad_norm": 2.685864210128784, "learning_rate": 9.862602975628027e-05, "loss": 1.1639, "step": 1877 }, { "epoch": 0.10267555099948744, "grad_norm": 2.896244764328003, "learning_rate": 9.862396773890841e-05, "loss": 1.2102, "step": 1878 }, { "epoch": 0.10273022381684606, "grad_norm": 2.143688917160034, "learning_rate": 9.86219041969749e-05, "loss": 1.1055, "step": 1879 }, { "epoch": 0.10278489663420468, "grad_norm": 2.607002019882202, "learning_rate": 9.861983913054444e-05, "loss": 1.1922, "step": 1880 }, { "epoch": 0.1028395694515633, "grad_norm": 2.7420060634613037, "learning_rate": 9.861777253968181e-05, "loss": 1.2915, "step": 1881 }, { "epoch": 0.10289424226892192, "grad_norm": 2.6208691596984863, "learning_rate": 9.861570442445176e-05, "loss": 1.2221, "step": 1882 }, { "epoch": 0.10294891508628054, "grad_norm": 2.7346584796905518, "learning_rate": 9.861363478491917e-05, "loss": 1.0072, "step": 1883 }, { "epoch": 0.10300358790363916, "grad_norm": 2.7790422439575195, "learning_rate": 9.861156362114889e-05, "loss": 1.0625, "step": 1884 }, { "epoch": 0.10305826072099777, "grad_norm": 3.028980255126953, "learning_rate": 9.860949093320592e-05, "loss": 1.2022, "step": 1885 }, { "epoch": 0.1031129335383564, "grad_norm": 2.4159791469573975, "learning_rate": 9.86074167211552e-05, "loss": 1.1417, "step": 1886 }, { "epoch": 0.10316760635571502, "grad_norm": 2.2601819038391113, "learning_rate": 9.860534098506178e-05, "loss": 1.2397, "step": 1887 }, { "epoch": 0.10322227917307364, "grad_norm": 2.71634578704834, "learning_rate": 9.860326372499074e-05, "loss": 1.1295, "step": 1888 }, { "epoch": 0.10327695199043226, "grad_norm": 2.508166790008545, "learning_rate": 9.860118494100722e-05, "loss": 1.3492, "step": 1889 }, { "epoch": 0.10333162480779087, "grad_norm": 3.505206823348999, "learning_rate": 9.859910463317639e-05, "loss": 1.2164, "step": 1890 }, { "epoch": 0.10338629762514949, "grad_norm": 2.8393356800079346, "learning_rate": 9.859702280156347e-05, "loss": 1.4029, "step": 1891 }, { "epoch": 0.10344097044250812, "grad_norm": 2.6344351768493652, "learning_rate": 9.859493944623375e-05, "loss": 1.2067, "step": 1892 }, { "epoch": 0.10349564325986674, "grad_norm": 2.698103904724121, "learning_rate": 9.859285456725254e-05, "loss": 1.1538, "step": 1893 }, { "epoch": 0.10355031607722535, "grad_norm": 2.80039381980896, "learning_rate": 9.859076816468522e-05, "loss": 1.3482, "step": 1894 }, { "epoch": 0.10360498889458397, "grad_norm": 2.3635520935058594, "learning_rate": 9.858868023859719e-05, "loss": 1.1035, "step": 1895 }, { "epoch": 0.10365966171194259, "grad_norm": 2.662224769592285, "learning_rate": 9.858659078905393e-05, "loss": 1.1929, "step": 1896 }, { "epoch": 0.10371433452930122, "grad_norm": 2.956852912902832, "learning_rate": 9.858449981612095e-05, "loss": 1.3466, "step": 1897 }, { "epoch": 0.10376900734665984, "grad_norm": 2.9060893058776855, "learning_rate": 9.858240731986382e-05, "loss": 1.0904, "step": 1898 }, { "epoch": 0.10382368016401845, "grad_norm": 2.3982999324798584, "learning_rate": 9.858031330034812e-05, "loss": 1.1307, "step": 1899 }, { "epoch": 0.10387835298137707, "grad_norm": 2.082970380783081, "learning_rate": 9.85782177576395e-05, "loss": 1.228, "step": 1900 }, { "epoch": 0.10393302579873569, "grad_norm": 2.77587628364563, "learning_rate": 9.857612069180373e-05, "loss": 1.3505, "step": 1901 }, { "epoch": 0.1039876986160943, "grad_norm": 2.4448907375335693, "learning_rate": 9.857402210290651e-05, "loss": 1.2582, "step": 1902 }, { "epoch": 0.10404237143345293, "grad_norm": 2.846430540084839, "learning_rate": 9.857192199101364e-05, "loss": 1.0769, "step": 1903 }, { "epoch": 0.10409704425081155, "grad_norm": 2.2128303050994873, "learning_rate": 9.856982035619098e-05, "loss": 1.2404, "step": 1904 }, { "epoch": 0.10415171706817017, "grad_norm": 2.510291814804077, "learning_rate": 9.856771719850442e-05, "loss": 1.1234, "step": 1905 }, { "epoch": 0.10420638988552879, "grad_norm": 3.541752815246582, "learning_rate": 9.85656125180199e-05, "loss": 1.5187, "step": 1906 }, { "epoch": 0.1042610627028874, "grad_norm": 2.9023430347442627, "learning_rate": 9.856350631480341e-05, "loss": 1.316, "step": 1907 }, { "epoch": 0.10431573552024603, "grad_norm": 2.3143398761749268, "learning_rate": 9.856139858892099e-05, "loss": 1.1926, "step": 1908 }, { "epoch": 0.10437040833760465, "grad_norm": 2.5107309818267822, "learning_rate": 9.855928934043874e-05, "loss": 1.0983, "step": 1909 }, { "epoch": 0.10442508115496327, "grad_norm": 2.5651438236236572, "learning_rate": 9.855717856942277e-05, "loss": 1.311, "step": 1910 }, { "epoch": 0.10447975397232188, "grad_norm": 2.1934242248535156, "learning_rate": 9.855506627593928e-05, "loss": 0.9382, "step": 1911 }, { "epoch": 0.1045344267896805, "grad_norm": 2.7997255325317383, "learning_rate": 9.85529524600545e-05, "loss": 1.271, "step": 1912 }, { "epoch": 0.10458909960703913, "grad_norm": 3.1591172218322754, "learning_rate": 9.855083712183467e-05, "loss": 1.3527, "step": 1913 }, { "epoch": 0.10464377242439775, "grad_norm": 2.7480714321136475, "learning_rate": 9.854872026134616e-05, "loss": 1.2218, "step": 1914 }, { "epoch": 0.10469844524175637, "grad_norm": 2.5177223682403564, "learning_rate": 9.854660187865532e-05, "loss": 1.2211, "step": 1915 }, { "epoch": 0.10475311805911498, "grad_norm": 4.509466648101807, "learning_rate": 9.85444819738286e-05, "loss": 1.3153, "step": 1916 }, { "epoch": 0.1048077908764736, "grad_norm": 3.0879597663879395, "learning_rate": 9.854236054693242e-05, "loss": 1.1034, "step": 1917 }, { "epoch": 0.10486246369383222, "grad_norm": 2.624624252319336, "learning_rate": 9.854023759803332e-05, "loss": 1.1387, "step": 1918 }, { "epoch": 0.10491713651119085, "grad_norm": 3.1775989532470703, "learning_rate": 9.853811312719785e-05, "loss": 1.235, "step": 1919 }, { "epoch": 0.10497180932854946, "grad_norm": 2.839766502380371, "learning_rate": 9.853598713449265e-05, "loss": 1.2037, "step": 1920 }, { "epoch": 0.10502648214590808, "grad_norm": 2.7832415103912354, "learning_rate": 9.853385961998435e-05, "loss": 1.2426, "step": 1921 }, { "epoch": 0.1050811549632667, "grad_norm": 4.832685470581055, "learning_rate": 9.853173058373967e-05, "loss": 1.1506, "step": 1922 }, { "epoch": 0.10513582778062532, "grad_norm": 2.6120829582214355, "learning_rate": 9.852960002582539e-05, "loss": 1.3505, "step": 1923 }, { "epoch": 0.10519050059798395, "grad_norm": 2.9222264289855957, "learning_rate": 9.852746794630825e-05, "loss": 1.2544, "step": 1924 }, { "epoch": 0.10524517341534256, "grad_norm": 2.6067793369293213, "learning_rate": 9.852533434525513e-05, "loss": 1.1748, "step": 1925 }, { "epoch": 0.10529984623270118, "grad_norm": 3.133209705352783, "learning_rate": 9.852319922273295e-05, "loss": 1.493, "step": 1926 }, { "epoch": 0.1053545190500598, "grad_norm": 3.917985677719116, "learning_rate": 9.852106257880863e-05, "loss": 1.1711, "step": 1927 }, { "epoch": 0.10540919186741841, "grad_norm": 2.9953267574310303, "learning_rate": 9.851892441354916e-05, "loss": 1.2427, "step": 1928 }, { "epoch": 0.10546386468477703, "grad_norm": 2.5118603706359863, "learning_rate": 9.85167847270216e-05, "loss": 1.1924, "step": 1929 }, { "epoch": 0.10551853750213566, "grad_norm": 2.420402765274048, "learning_rate": 9.851464351929301e-05, "loss": 1.2257, "step": 1930 }, { "epoch": 0.10557321031949428, "grad_norm": 3.2011516094207764, "learning_rate": 9.851250079043055e-05, "loss": 1.176, "step": 1931 }, { "epoch": 0.1056278831368529, "grad_norm": 2.605638027191162, "learning_rate": 9.85103565405014e-05, "loss": 1.3206, "step": 1932 }, { "epoch": 0.10568255595421151, "grad_norm": 2.7903478145599365, "learning_rate": 9.850821076957277e-05, "loss": 1.0605, "step": 1933 }, { "epoch": 0.10573722877157013, "grad_norm": 3.7138659954071045, "learning_rate": 9.850606347771197e-05, "loss": 1.3965, "step": 1934 }, { "epoch": 0.10579190158892876, "grad_norm": 2.359379291534424, "learning_rate": 9.850391466498632e-05, "loss": 1.2837, "step": 1935 }, { "epoch": 0.10584657440628738, "grad_norm": 2.775702476501465, "learning_rate": 9.850176433146316e-05, "loss": 1.2595, "step": 1936 }, { "epoch": 0.105901247223646, "grad_norm": 2.468634843826294, "learning_rate": 9.849961247720996e-05, "loss": 1.0415, "step": 1937 }, { "epoch": 0.10595592004100461, "grad_norm": 2.6022822856903076, "learning_rate": 9.849745910229415e-05, "loss": 1.3244, "step": 1938 }, { "epoch": 0.10601059285836323, "grad_norm": 3.3233184814453125, "learning_rate": 9.849530420678326e-05, "loss": 1.4179, "step": 1939 }, { "epoch": 0.10606526567572185, "grad_norm": 2.510768175125122, "learning_rate": 9.849314779074487e-05, "loss": 1.2707, "step": 1940 }, { "epoch": 0.10611993849308048, "grad_norm": 4.7268500328063965, "learning_rate": 9.849098985424658e-05, "loss": 1.2147, "step": 1941 }, { "epoch": 0.1061746113104391, "grad_norm": 2.5459346771240234, "learning_rate": 9.848883039735604e-05, "loss": 1.3459, "step": 1942 }, { "epoch": 0.10622928412779771, "grad_norm": 3.157034397125244, "learning_rate": 9.848666942014099e-05, "loss": 1.26, "step": 1943 }, { "epoch": 0.10628395694515633, "grad_norm": 3.2413172721862793, "learning_rate": 9.848450692266915e-05, "loss": 1.2651, "step": 1944 }, { "epoch": 0.10633862976251494, "grad_norm": 3.1237378120422363, "learning_rate": 9.848234290500834e-05, "loss": 1.205, "step": 1945 }, { "epoch": 0.10639330257987357, "grad_norm": 2.815924644470215, "learning_rate": 9.848017736722641e-05, "loss": 1.2078, "step": 1946 }, { "epoch": 0.10644797539723219, "grad_norm": 3.0700788497924805, "learning_rate": 9.847801030939125e-05, "loss": 1.1348, "step": 1947 }, { "epoch": 0.10650264821459081, "grad_norm": 3.5447466373443604, "learning_rate": 9.847584173157083e-05, "loss": 1.284, "step": 1948 }, { "epoch": 0.10655732103194943, "grad_norm": 2.430490255355835, "learning_rate": 9.847367163383312e-05, "loss": 1.3024, "step": 1949 }, { "epoch": 0.10661199384930804, "grad_norm": 3.0048744678497314, "learning_rate": 9.847150001624617e-05, "loss": 1.1904, "step": 1950 }, { "epoch": 0.10666666666666667, "grad_norm": 3.1586387157440186, "learning_rate": 9.846932687887806e-05, "loss": 1.2166, "step": 1951 }, { "epoch": 0.10672133948402529, "grad_norm": 2.5996289253234863, "learning_rate": 9.846715222179694e-05, "loss": 1.2551, "step": 1952 }, { "epoch": 0.10677601230138391, "grad_norm": 2.453247547149658, "learning_rate": 9.846497604507099e-05, "loss": 1.1901, "step": 1953 }, { "epoch": 0.10683068511874252, "grad_norm": 2.958327054977417, "learning_rate": 9.846279834876843e-05, "loss": 1.3484, "step": 1954 }, { "epoch": 0.10688535793610114, "grad_norm": 3.1028637886047363, "learning_rate": 9.846061913295756e-05, "loss": 1.2007, "step": 1955 }, { "epoch": 0.10694003075345976, "grad_norm": 2.363243818283081, "learning_rate": 9.84584383977067e-05, "loss": 1.0994, "step": 1956 }, { "epoch": 0.10699470357081839, "grad_norm": 2.887937545776367, "learning_rate": 9.845625614308422e-05, "loss": 1.129, "step": 1957 }, { "epoch": 0.107049376388177, "grad_norm": 3.525960922241211, "learning_rate": 9.845407236915856e-05, "loss": 1.1567, "step": 1958 }, { "epoch": 0.10710404920553562, "grad_norm": 3.868436336517334, "learning_rate": 9.845188707599816e-05, "loss": 1.4324, "step": 1959 }, { "epoch": 0.10715872202289424, "grad_norm": 3.8474137783050537, "learning_rate": 9.844970026367156e-05, "loss": 0.9783, "step": 1960 }, { "epoch": 0.10721339484025286, "grad_norm": 2.828603506088257, "learning_rate": 9.844751193224733e-05, "loss": 1.3402, "step": 1961 }, { "epoch": 0.10726806765761149, "grad_norm": 2.4713499546051025, "learning_rate": 9.844532208179404e-05, "loss": 1.2927, "step": 1962 }, { "epoch": 0.1073227404749701, "grad_norm": 2.331968307495117, "learning_rate": 9.844313071238043e-05, "loss": 1.1821, "step": 1963 }, { "epoch": 0.10737741329232872, "grad_norm": 2.839514970779419, "learning_rate": 9.844093782407512e-05, "loss": 1.3003, "step": 1964 }, { "epoch": 0.10743208610968734, "grad_norm": 2.853970766067505, "learning_rate": 9.843874341694695e-05, "loss": 1.4109, "step": 1965 }, { "epoch": 0.10748675892704596, "grad_norm": 2.681037664413452, "learning_rate": 9.843654749106464e-05, "loss": 1.0962, "step": 1966 }, { "epoch": 0.10754143174440457, "grad_norm": 2.8800771236419678, "learning_rate": 9.84343500464971e-05, "loss": 1.3065, "step": 1967 }, { "epoch": 0.1075961045617632, "grad_norm": 3.8457961082458496, "learning_rate": 9.843215108331323e-05, "loss": 1.159, "step": 1968 }, { "epoch": 0.10765077737912182, "grad_norm": 2.361459493637085, "learning_rate": 9.842995060158195e-05, "loss": 1.1664, "step": 1969 }, { "epoch": 0.10770545019648044, "grad_norm": 3.585655450820923, "learning_rate": 9.842774860137225e-05, "loss": 1.2051, "step": 1970 }, { "epoch": 0.10776012301383905, "grad_norm": 2.178375720977783, "learning_rate": 9.842554508275319e-05, "loss": 1.2131, "step": 1971 }, { "epoch": 0.10781479583119767, "grad_norm": 2.1078829765319824, "learning_rate": 9.842334004579385e-05, "loss": 1.0059, "step": 1972 }, { "epoch": 0.1078694686485563, "grad_norm": 2.6689348220825195, "learning_rate": 9.842113349056338e-05, "loss": 1.1851, "step": 1973 }, { "epoch": 0.10792414146591492, "grad_norm": 3.223984718322754, "learning_rate": 9.841892541713095e-05, "loss": 1.4033, "step": 1974 }, { "epoch": 0.10797881428327354, "grad_norm": 2.8045828342437744, "learning_rate": 9.841671582556582e-05, "loss": 1.0638, "step": 1975 }, { "epoch": 0.10803348710063215, "grad_norm": 3.0552282333374023, "learning_rate": 9.841450471593723e-05, "loss": 1.0398, "step": 1976 }, { "epoch": 0.10808815991799077, "grad_norm": 3.734665870666504, "learning_rate": 9.841229208831453e-05, "loss": 1.3761, "step": 1977 }, { "epoch": 0.10814283273534939, "grad_norm": 3.330939531326294, "learning_rate": 9.841007794276708e-05, "loss": 1.3543, "step": 1978 }, { "epoch": 0.10819750555270802, "grad_norm": 2.4812612533569336, "learning_rate": 9.840786227936432e-05, "loss": 1.2793, "step": 1979 }, { "epoch": 0.10825217837006663, "grad_norm": 5.193505764007568, "learning_rate": 9.840564509817571e-05, "loss": 1.2242, "step": 1980 }, { "epoch": 0.10830685118742525, "grad_norm": 2.3745641708374023, "learning_rate": 9.840342639927078e-05, "loss": 1.3164, "step": 1981 }, { "epoch": 0.10836152400478387, "grad_norm": 2.8014233112335205, "learning_rate": 9.840120618271909e-05, "loss": 1.1985, "step": 1982 }, { "epoch": 0.10841619682214249, "grad_norm": 2.123680353164673, "learning_rate": 9.839898444859024e-05, "loss": 1.1517, "step": 1983 }, { "epoch": 0.10847086963950112, "grad_norm": 3.1124258041381836, "learning_rate": 9.83967611969539e-05, "loss": 1.276, "step": 1984 }, { "epoch": 0.10852554245685973, "grad_norm": 2.951864719390869, "learning_rate": 9.839453642787977e-05, "loss": 1.3594, "step": 1985 }, { "epoch": 0.10858021527421835, "grad_norm": 3.1966567039489746, "learning_rate": 9.839231014143761e-05, "loss": 1.017, "step": 1986 }, { "epoch": 0.10863488809157697, "grad_norm": 2.3172943592071533, "learning_rate": 9.839008233769725e-05, "loss": 1.0186, "step": 1987 }, { "epoch": 0.10868956090893558, "grad_norm": 2.6815478801727295, "learning_rate": 9.838785301672849e-05, "loss": 1.1061, "step": 1988 }, { "epoch": 0.10874423372629421, "grad_norm": 5.353212356567383, "learning_rate": 9.838562217860128e-05, "loss": 1.3928, "step": 1989 }, { "epoch": 0.10879890654365283, "grad_norm": 2.7174453735351562, "learning_rate": 9.838338982338554e-05, "loss": 1.2358, "step": 1990 }, { "epoch": 0.10885357936101145, "grad_norm": 3.813222646713257, "learning_rate": 9.838115595115125e-05, "loss": 1.1416, "step": 1991 }, { "epoch": 0.10890825217837007, "grad_norm": 2.9941303730010986, "learning_rate": 9.837892056196846e-05, "loss": 1.3533, "step": 1992 }, { "epoch": 0.10896292499572868, "grad_norm": 4.14890193939209, "learning_rate": 9.837668365590728e-05, "loss": 1.4038, "step": 1993 }, { "epoch": 0.1090175978130873, "grad_norm": 2.332630157470703, "learning_rate": 9.837444523303783e-05, "loss": 1.1019, "step": 1994 }, { "epoch": 0.10907227063044593, "grad_norm": 2.973099946975708, "learning_rate": 9.83722052934303e-05, "loss": 1.0685, "step": 1995 }, { "epoch": 0.10912694344780455, "grad_norm": 3.0258846282958984, "learning_rate": 9.836996383715491e-05, "loss": 1.26, "step": 1996 }, { "epoch": 0.10918161626516316, "grad_norm": 3.099308967590332, "learning_rate": 9.836772086428194e-05, "loss": 1.3845, "step": 1997 }, { "epoch": 0.10923628908252178, "grad_norm": 2.22924542427063, "learning_rate": 9.836547637488173e-05, "loss": 0.8974, "step": 1998 }, { "epoch": 0.1092909618998804, "grad_norm": 4.993710994720459, "learning_rate": 9.836323036902464e-05, "loss": 1.2512, "step": 1999 }, { "epoch": 0.10934563471723903, "grad_norm": 2.330472230911255, "learning_rate": 9.836098284678111e-05, "loss": 1.2454, "step": 2000 }, { "epoch": 0.10940030753459765, "grad_norm": 2.391878843307495, "learning_rate": 9.83587338082216e-05, "loss": 1.3582, "step": 2001 }, { "epoch": 0.10945498035195626, "grad_norm": 2.3138468265533447, "learning_rate": 9.83564832534166e-05, "loss": 1.1984, "step": 2002 }, { "epoch": 0.10950965316931488, "grad_norm": 2.6073548793792725, "learning_rate": 9.835423118243672e-05, "loss": 0.8831, "step": 2003 }, { "epoch": 0.1095643259866735, "grad_norm": 2.159296989440918, "learning_rate": 9.835197759535252e-05, "loss": 1.2172, "step": 2004 }, { "epoch": 0.10961899880403211, "grad_norm": 3.06188702583313, "learning_rate": 9.83497224922347e-05, "loss": 1.3681, "step": 2005 }, { "epoch": 0.10967367162139074, "grad_norm": 2.3014636039733887, "learning_rate": 9.834746587315398e-05, "loss": 1.0931, "step": 2006 }, { "epoch": 0.10972834443874936, "grad_norm": 2.612788438796997, "learning_rate": 9.834520773818105e-05, "loss": 1.0984, "step": 2007 }, { "epoch": 0.10978301725610798, "grad_norm": 2.9825682640075684, "learning_rate": 9.834294808738677e-05, "loss": 1.2599, "step": 2008 }, { "epoch": 0.1098376900734666, "grad_norm": 3.2806904315948486, "learning_rate": 9.834068692084198e-05, "loss": 1.4081, "step": 2009 }, { "epoch": 0.10989236289082521, "grad_norm": 2.9605040550231934, "learning_rate": 9.833842423861756e-05, "loss": 1.3518, "step": 2010 }, { "epoch": 0.10994703570818384, "grad_norm": 2.8352768421173096, "learning_rate": 9.833616004078446e-05, "loss": 1.1141, "step": 2011 }, { "epoch": 0.11000170852554246, "grad_norm": 2.787681818008423, "learning_rate": 9.833389432741366e-05, "loss": 1.3743, "step": 2012 }, { "epoch": 0.11005638134290108, "grad_norm": 2.687716007232666, "learning_rate": 9.833162709857624e-05, "loss": 1.0266, "step": 2013 }, { "epoch": 0.1101110541602597, "grad_norm": 2.07192325592041, "learning_rate": 9.832935835434324e-05, "loss": 1.1509, "step": 2014 }, { "epoch": 0.11016572697761831, "grad_norm": 2.5676071643829346, "learning_rate": 9.832708809478583e-05, "loss": 1.2312, "step": 2015 }, { "epoch": 0.11022039979497693, "grad_norm": 2.948906898498535, "learning_rate": 9.832481631997516e-05, "loss": 1.3049, "step": 2016 }, { "epoch": 0.11027507261233556, "grad_norm": 2.602590799331665, "learning_rate": 9.832254302998248e-05, "loss": 1.3086, "step": 2017 }, { "epoch": 0.11032974542969418, "grad_norm": 2.6379597187042236, "learning_rate": 9.832026822487907e-05, "loss": 1.2867, "step": 2018 }, { "epoch": 0.11038441824705279, "grad_norm": 2.9023232460021973, "learning_rate": 9.831799190473625e-05, "loss": 1.0453, "step": 2019 }, { "epoch": 0.11043909106441141, "grad_norm": 2.5776658058166504, "learning_rate": 9.831571406962538e-05, "loss": 1.2993, "step": 2020 }, { "epoch": 0.11049376388177003, "grad_norm": 4.098097801208496, "learning_rate": 9.83134347196179e-05, "loss": 1.2276, "step": 2021 }, { "epoch": 0.11054843669912866, "grad_norm": 2.614043712615967, "learning_rate": 9.831115385478524e-05, "loss": 1.3443, "step": 2022 }, { "epoch": 0.11060310951648727, "grad_norm": 2.6498866081237793, "learning_rate": 9.830887147519897e-05, "loss": 1.3483, "step": 2023 }, { "epoch": 0.11065778233384589, "grad_norm": 3.6932995319366455, "learning_rate": 9.830658758093061e-05, "loss": 1.2791, "step": 2024 }, { "epoch": 0.11071245515120451, "grad_norm": 2.192544460296631, "learning_rate": 9.830430217205177e-05, "loss": 1.178, "step": 2025 }, { "epoch": 0.11076712796856313, "grad_norm": 3.5184223651885986, "learning_rate": 9.830201524863414e-05, "loss": 1.0786, "step": 2026 }, { "epoch": 0.11082180078592176, "grad_norm": 2.8582091331481934, "learning_rate": 9.829972681074939e-05, "loss": 1.2221, "step": 2027 }, { "epoch": 0.11087647360328037, "grad_norm": 3.8408024311065674, "learning_rate": 9.829743685846929e-05, "loss": 1.1284, "step": 2028 }, { "epoch": 0.11093114642063899, "grad_norm": 2.366097927093506, "learning_rate": 9.829514539186564e-05, "loss": 1.185, "step": 2029 }, { "epoch": 0.11098581923799761, "grad_norm": 2.4270453453063965, "learning_rate": 9.829285241101027e-05, "loss": 1.4329, "step": 2030 }, { "epoch": 0.11104049205535622, "grad_norm": 3.113908290863037, "learning_rate": 9.82905579159751e-05, "loss": 1.4152, "step": 2031 }, { "epoch": 0.11109516487271484, "grad_norm": 2.676079750061035, "learning_rate": 9.828826190683204e-05, "loss": 1.1849, "step": 2032 }, { "epoch": 0.11114983769007347, "grad_norm": 2.424586057662964, "learning_rate": 9.828596438365312e-05, "loss": 1.1823, "step": 2033 }, { "epoch": 0.11120451050743209, "grad_norm": 3.151569366455078, "learning_rate": 9.828366534651034e-05, "loss": 1.4912, "step": 2034 }, { "epoch": 0.1112591833247907, "grad_norm": 3.3440961837768555, "learning_rate": 9.82813647954758e-05, "loss": 1.2192, "step": 2035 }, { "epoch": 0.11131385614214932, "grad_norm": 2.7987778186798096, "learning_rate": 9.827906273062163e-05, "loss": 1.1472, "step": 2036 }, { "epoch": 0.11136852895950794, "grad_norm": 2.5076234340667725, "learning_rate": 9.827675915202002e-05, "loss": 1.1939, "step": 2037 }, { "epoch": 0.11142320177686657, "grad_norm": 2.8832037448883057, "learning_rate": 9.827445405974316e-05, "loss": 1.1306, "step": 2038 }, { "epoch": 0.11147787459422519, "grad_norm": 2.8713276386260986, "learning_rate": 9.827214745386337e-05, "loss": 1.4564, "step": 2039 }, { "epoch": 0.1115325474115838, "grad_norm": 3.644868850708008, "learning_rate": 9.826983933445295e-05, "loss": 1.5978, "step": 2040 }, { "epoch": 0.11158722022894242, "grad_norm": 2.174003839492798, "learning_rate": 9.826752970158427e-05, "loss": 0.9116, "step": 2041 }, { "epoch": 0.11164189304630104, "grad_norm": 3.06832218170166, "learning_rate": 9.826521855532975e-05, "loss": 0.9792, "step": 2042 }, { "epoch": 0.11169656586365966, "grad_norm": 2.2988083362579346, "learning_rate": 9.826290589576184e-05, "loss": 1.1774, "step": 2043 }, { "epoch": 0.11175123868101829, "grad_norm": 2.551147699356079, "learning_rate": 9.826059172295308e-05, "loss": 1.2624, "step": 2044 }, { "epoch": 0.1118059114983769, "grad_norm": 3.2290091514587402, "learning_rate": 9.8258276036976e-05, "loss": 1.2476, "step": 2045 }, { "epoch": 0.11186058431573552, "grad_norm": 3.47540545463562, "learning_rate": 9.825595883790321e-05, "loss": 1.3329, "step": 2046 }, { "epoch": 0.11191525713309414, "grad_norm": 2.4857966899871826, "learning_rate": 9.825364012580739e-05, "loss": 1.2493, "step": 2047 }, { "epoch": 0.11196992995045275, "grad_norm": 2.681241512298584, "learning_rate": 9.825131990076121e-05, "loss": 1.2557, "step": 2048 }, { "epoch": 0.11202460276781138, "grad_norm": 2.5024843215942383, "learning_rate": 9.824899816283743e-05, "loss": 1.2154, "step": 2049 }, { "epoch": 0.11207927558517, "grad_norm": 2.0925962924957275, "learning_rate": 9.824667491210886e-05, "loss": 1.0819, "step": 2050 }, { "epoch": 0.11213394840252862, "grad_norm": 2.7400407791137695, "learning_rate": 9.824435014864832e-05, "loss": 1.1418, "step": 2051 }, { "epoch": 0.11218862121988724, "grad_norm": 2.0747787952423096, "learning_rate": 9.824202387252872e-05, "loss": 0.9667, "step": 2052 }, { "epoch": 0.11224329403724585, "grad_norm": 2.915093421936035, "learning_rate": 9.823969608382298e-05, "loss": 1.243, "step": 2053 }, { "epoch": 0.11229796685460447, "grad_norm": 3.7058591842651367, "learning_rate": 9.823736678260411e-05, "loss": 1.4157, "step": 2054 }, { "epoch": 0.1123526396719631, "grad_norm": 3.2272391319274902, "learning_rate": 9.823503596894512e-05, "loss": 1.1745, "step": 2055 }, { "epoch": 0.11240731248932172, "grad_norm": 2.8185622692108154, "learning_rate": 9.82327036429191e-05, "loss": 1.4354, "step": 2056 }, { "epoch": 0.11246198530668033, "grad_norm": 2.4234726428985596, "learning_rate": 9.823036980459917e-05, "loss": 1.1081, "step": 2057 }, { "epoch": 0.11251665812403895, "grad_norm": 2.337110996246338, "learning_rate": 9.822803445405853e-05, "loss": 1.044, "step": 2058 }, { "epoch": 0.11257133094139757, "grad_norm": 3.0338337421417236, "learning_rate": 9.822569759137037e-05, "loss": 1.169, "step": 2059 }, { "epoch": 0.1126260037587562, "grad_norm": 3.525392770767212, "learning_rate": 9.8223359216608e-05, "loss": 1.1577, "step": 2060 }, { "epoch": 0.11268067657611482, "grad_norm": 3.1791467666625977, "learning_rate": 9.822101932984468e-05, "loss": 1.3055, "step": 2061 }, { "epoch": 0.11273534939347343, "grad_norm": 3.262397289276123, "learning_rate": 9.821867793115384e-05, "loss": 1.4082, "step": 2062 }, { "epoch": 0.11279002221083205, "grad_norm": 2.7196149826049805, "learning_rate": 9.821633502060884e-05, "loss": 0.8674, "step": 2063 }, { "epoch": 0.11284469502819067, "grad_norm": 2.5184226036071777, "learning_rate": 9.821399059828317e-05, "loss": 1.1449, "step": 2064 }, { "epoch": 0.1128993678455493, "grad_norm": 2.4584672451019287, "learning_rate": 9.821164466425033e-05, "loss": 1.1367, "step": 2065 }, { "epoch": 0.11295404066290791, "grad_norm": 2.3565094470977783, "learning_rate": 9.820929721858387e-05, "loss": 0.9666, "step": 2066 }, { "epoch": 0.11300871348026653, "grad_norm": 3.004467248916626, "learning_rate": 9.82069482613574e-05, "loss": 1.1993, "step": 2067 }, { "epoch": 0.11306338629762515, "grad_norm": 2.946885347366333, "learning_rate": 9.820459779264457e-05, "loss": 1.2629, "step": 2068 }, { "epoch": 0.11311805911498377, "grad_norm": 2.462745428085327, "learning_rate": 9.820224581251905e-05, "loss": 1.1301, "step": 2069 }, { "epoch": 0.11317273193234238, "grad_norm": 2.6176211833953857, "learning_rate": 9.819989232105462e-05, "loss": 1.0272, "step": 2070 }, { "epoch": 0.11322740474970101, "grad_norm": 2.726381301879883, "learning_rate": 9.819753731832506e-05, "loss": 1.204, "step": 2071 }, { "epoch": 0.11328207756705963, "grad_norm": 2.3364758491516113, "learning_rate": 9.819518080440422e-05, "loss": 1.1185, "step": 2072 }, { "epoch": 0.11333675038441825, "grad_norm": 7.884298324584961, "learning_rate": 9.819282277936594e-05, "loss": 1.3637, "step": 2073 }, { "epoch": 0.11339142320177686, "grad_norm": 2.894266128540039, "learning_rate": 9.819046324328422e-05, "loss": 1.3351, "step": 2074 }, { "epoch": 0.11344609601913548, "grad_norm": 2.8250482082366943, "learning_rate": 9.818810219623299e-05, "loss": 1.038, "step": 2075 }, { "epoch": 0.11350076883649411, "grad_norm": 2.183751106262207, "learning_rate": 9.81857396382863e-05, "loss": 0.9675, "step": 2076 }, { "epoch": 0.11355544165385273, "grad_norm": 3.0840959548950195, "learning_rate": 9.818337556951823e-05, "loss": 1.1154, "step": 2077 }, { "epoch": 0.11361011447121135, "grad_norm": 2.948810577392578, "learning_rate": 9.818100999000288e-05, "loss": 1.3341, "step": 2078 }, { "epoch": 0.11366478728856996, "grad_norm": 3.3496413230895996, "learning_rate": 9.817864289981445e-05, "loss": 1.311, "step": 2079 }, { "epoch": 0.11371946010592858, "grad_norm": 3.8484737873077393, "learning_rate": 9.817627429902714e-05, "loss": 1.3292, "step": 2080 }, { "epoch": 0.1137741329232872, "grad_norm": 2.958376407623291, "learning_rate": 9.817390418771522e-05, "loss": 1.1638, "step": 2081 }, { "epoch": 0.11382880574064583, "grad_norm": 3.3151376247406006, "learning_rate": 9.8171532565953e-05, "loss": 1.165, "step": 2082 }, { "epoch": 0.11388347855800444, "grad_norm": 4.2158637046813965, "learning_rate": 9.816915943381484e-05, "loss": 1.2076, "step": 2083 }, { "epoch": 0.11393815137536306, "grad_norm": 3.559943914413452, "learning_rate": 9.816678479137515e-05, "loss": 1.2304, "step": 2084 }, { "epoch": 0.11399282419272168, "grad_norm": 2.6015686988830566, "learning_rate": 9.81644086387084e-05, "loss": 1.3429, "step": 2085 }, { "epoch": 0.1140474970100803, "grad_norm": 3.796093702316284, "learning_rate": 9.816203097588908e-05, "loss": 1.2997, "step": 2086 }, { "epoch": 0.11410216982743893, "grad_norm": 2.525873899459839, "learning_rate": 9.815965180299171e-05, "loss": 1.0478, "step": 2087 }, { "epoch": 0.11415684264479754, "grad_norm": 4.17246150970459, "learning_rate": 9.815727112009094e-05, "loss": 1.1537, "step": 2088 }, { "epoch": 0.11421151546215616, "grad_norm": 2.3321869373321533, "learning_rate": 9.815488892726137e-05, "loss": 0.8843, "step": 2089 }, { "epoch": 0.11426618827951478, "grad_norm": 2.195918321609497, "learning_rate": 9.815250522457773e-05, "loss": 1.1313, "step": 2090 }, { "epoch": 0.1143208610968734, "grad_norm": 2.357438087463379, "learning_rate": 9.815012001211472e-05, "loss": 1.1256, "step": 2091 }, { "epoch": 0.11437553391423201, "grad_norm": 2.983806848526001, "learning_rate": 9.814773328994715e-05, "loss": 1.1314, "step": 2092 }, { "epoch": 0.11443020673159064, "grad_norm": 2.3295912742614746, "learning_rate": 9.814534505814985e-05, "loss": 1.0353, "step": 2093 }, { "epoch": 0.11448487954894926, "grad_norm": 3.5797348022460938, "learning_rate": 9.81429553167977e-05, "loss": 1.2843, "step": 2094 }, { "epoch": 0.11453955236630788, "grad_norm": 2.484433174133301, "learning_rate": 9.814056406596561e-05, "loss": 1.1446, "step": 2095 }, { "epoch": 0.11459422518366649, "grad_norm": 2.8943662643432617, "learning_rate": 9.81381713057286e-05, "loss": 1.1385, "step": 2096 }, { "epoch": 0.11464889800102511, "grad_norm": 2.9219329357147217, "learning_rate": 9.813577703616165e-05, "loss": 1.3182, "step": 2097 }, { "epoch": 0.11470357081838374, "grad_norm": 3.3065083026885986, "learning_rate": 9.813338125733984e-05, "loss": 1.3378, "step": 2098 }, { "epoch": 0.11475824363574236, "grad_norm": 2.6958513259887695, "learning_rate": 9.813098396933831e-05, "loss": 1.2373, "step": 2099 }, { "epoch": 0.11481291645310097, "grad_norm": 3.081394910812378, "learning_rate": 9.81285851722322e-05, "loss": 1.4762, "step": 2100 }, { "epoch": 0.11486758927045959, "grad_norm": 2.736555337905884, "learning_rate": 9.812618486609674e-05, "loss": 1.1771, "step": 2101 }, { "epoch": 0.11492226208781821, "grad_norm": 2.5520524978637695, "learning_rate": 9.812378305100717e-05, "loss": 1.1562, "step": 2102 }, { "epoch": 0.11497693490517684, "grad_norm": 2.5860490798950195, "learning_rate": 9.812137972703881e-05, "loss": 1.2743, "step": 2103 }, { "epoch": 0.11503160772253546, "grad_norm": 5.102787971496582, "learning_rate": 9.8118974894267e-05, "loss": 1.3412, "step": 2104 }, { "epoch": 0.11508628053989407, "grad_norm": 2.4635262489318848, "learning_rate": 9.811656855276716e-05, "loss": 1.4928, "step": 2105 }, { "epoch": 0.11514095335725269, "grad_norm": 3.10379695892334, "learning_rate": 9.811416070261474e-05, "loss": 1.2139, "step": 2106 }, { "epoch": 0.1151956261746113, "grad_norm": 2.997119903564453, "learning_rate": 9.811175134388522e-05, "loss": 1.3665, "step": 2107 }, { "epoch": 0.11525029899196992, "grad_norm": 2.3759765625, "learning_rate": 9.810934047665416e-05, "loss": 1.0477, "step": 2108 }, { "epoch": 0.11530497180932855, "grad_norm": 3.0368006229400635, "learning_rate": 9.810692810099714e-05, "loss": 1.3453, "step": 2109 }, { "epoch": 0.11535964462668717, "grad_norm": 3.445826292037964, "learning_rate": 9.810451421698978e-05, "loss": 1.4447, "step": 2110 }, { "epoch": 0.11541431744404579, "grad_norm": 3.418518304824829, "learning_rate": 9.81020988247078e-05, "loss": 1.3675, "step": 2111 }, { "epoch": 0.1154689902614044, "grad_norm": 2.469977378845215, "learning_rate": 9.809968192422691e-05, "loss": 1.1319, "step": 2112 }, { "epoch": 0.11552366307876302, "grad_norm": 4.845503330230713, "learning_rate": 9.809726351562289e-05, "loss": 1.0334, "step": 2113 }, { "epoch": 0.11557833589612165, "grad_norm": 4.1583662033081055, "learning_rate": 9.809484359897159e-05, "loss": 1.2323, "step": 2114 }, { "epoch": 0.11563300871348027, "grad_norm": 2.527451515197754, "learning_rate": 9.809242217434885e-05, "loss": 1.1934, "step": 2115 }, { "epoch": 0.11568768153083889, "grad_norm": 2.0379652976989746, "learning_rate": 9.808999924183063e-05, "loss": 1.0513, "step": 2116 }, { "epoch": 0.1157423543481975, "grad_norm": 3.114434242248535, "learning_rate": 9.808757480149286e-05, "loss": 1.2057, "step": 2117 }, { "epoch": 0.11579702716555612, "grad_norm": 2.351358413696289, "learning_rate": 9.808514885341158e-05, "loss": 1.3463, "step": 2118 }, { "epoch": 0.11585169998291474, "grad_norm": 2.570380926132202, "learning_rate": 9.808272139766285e-05, "loss": 1.1034, "step": 2119 }, { "epoch": 0.11590637280027337, "grad_norm": 2.743391752243042, "learning_rate": 9.808029243432278e-05, "loss": 1.2888, "step": 2120 }, { "epoch": 0.11596104561763199, "grad_norm": 2.7682294845581055, "learning_rate": 9.807786196346754e-05, "loss": 1.4786, "step": 2121 }, { "epoch": 0.1160157184349906, "grad_norm": 4.671858310699463, "learning_rate": 9.807542998517329e-05, "loss": 1.1702, "step": 2122 }, { "epoch": 0.11607039125234922, "grad_norm": 3.08518385887146, "learning_rate": 9.807299649951633e-05, "loss": 1.2963, "step": 2123 }, { "epoch": 0.11612506406970784, "grad_norm": 2.7872416973114014, "learning_rate": 9.807056150657296e-05, "loss": 1.0472, "step": 2124 }, { "epoch": 0.11617973688706647, "grad_norm": 2.7131965160369873, "learning_rate": 9.806812500641949e-05, "loss": 1.1305, "step": 2125 }, { "epoch": 0.11623440970442508, "grad_norm": 3.002528667449951, "learning_rate": 9.806568699913235e-05, "loss": 1.1849, "step": 2126 }, { "epoch": 0.1162890825217837, "grad_norm": 3.0502891540527344, "learning_rate": 9.806324748478795e-05, "loss": 1.1835, "step": 2127 }, { "epoch": 0.11634375533914232, "grad_norm": 2.623072624206543, "learning_rate": 9.806080646346282e-05, "loss": 0.9538, "step": 2128 }, { "epoch": 0.11639842815650094, "grad_norm": 2.827875852584839, "learning_rate": 9.805836393523346e-05, "loss": 1.4497, "step": 2129 }, { "epoch": 0.11645310097385955, "grad_norm": 3.6159324645996094, "learning_rate": 9.805591990017647e-05, "loss": 1.166, "step": 2130 }, { "epoch": 0.11650777379121818, "grad_norm": 3.575636625289917, "learning_rate": 9.805347435836847e-05, "loss": 1.0882, "step": 2131 }, { "epoch": 0.1165624466085768, "grad_norm": 2.7233951091766357, "learning_rate": 9.805102730988614e-05, "loss": 1.1043, "step": 2132 }, { "epoch": 0.11661711942593542, "grad_norm": 2.326841115951538, "learning_rate": 9.804857875480623e-05, "loss": 1.2577, "step": 2133 }, { "epoch": 0.11667179224329403, "grad_norm": 2.726508378982544, "learning_rate": 9.804612869320547e-05, "loss": 1.1989, "step": 2134 }, { "epoch": 0.11672646506065265, "grad_norm": 3.0412402153015137, "learning_rate": 9.80436771251607e-05, "loss": 1.2251, "step": 2135 }, { "epoch": 0.11678113787801128, "grad_norm": 3.0291748046875, "learning_rate": 9.804122405074878e-05, "loss": 1.2047, "step": 2136 }, { "epoch": 0.1168358106953699, "grad_norm": 2.547515869140625, "learning_rate": 9.803876947004665e-05, "loss": 1.0945, "step": 2137 }, { "epoch": 0.11689048351272852, "grad_norm": 2.780421495437622, "learning_rate": 9.803631338313125e-05, "loss": 1.3463, "step": 2138 }, { "epoch": 0.11694515633008713, "grad_norm": 2.3485922813415527, "learning_rate": 9.80338557900796e-05, "loss": 1.1421, "step": 2139 }, { "epoch": 0.11699982914744575, "grad_norm": 2.827349901199341, "learning_rate": 9.803139669096873e-05, "loss": 1.2681, "step": 2140 }, { "epoch": 0.11705450196480438, "grad_norm": 2.3866264820098877, "learning_rate": 9.802893608587577e-05, "loss": 1.2565, "step": 2141 }, { "epoch": 0.117109174782163, "grad_norm": 2.3724148273468018, "learning_rate": 9.802647397487785e-05, "loss": 1.1001, "step": 2142 }, { "epoch": 0.11716384759952161, "grad_norm": 3.484034776687622, "learning_rate": 9.802401035805218e-05, "loss": 1.3555, "step": 2143 }, { "epoch": 0.11721852041688023, "grad_norm": 3.207676410675049, "learning_rate": 9.8021545235476e-05, "loss": 1.2493, "step": 2144 }, { "epoch": 0.11727319323423885, "grad_norm": 2.3025410175323486, "learning_rate": 9.801907860722661e-05, "loss": 1.276, "step": 2145 }, { "epoch": 0.11732786605159747, "grad_norm": 2.910670518875122, "learning_rate": 9.801661047338135e-05, "loss": 1.0658, "step": 2146 }, { "epoch": 0.1173825388689561, "grad_norm": 3.597992420196533, "learning_rate": 9.801414083401758e-05, "loss": 0.9147, "step": 2147 }, { "epoch": 0.11743721168631471, "grad_norm": 2.808253526687622, "learning_rate": 9.801166968921276e-05, "loss": 1.0891, "step": 2148 }, { "epoch": 0.11749188450367333, "grad_norm": 4.186591148376465, "learning_rate": 9.800919703904436e-05, "loss": 1.2618, "step": 2149 }, { "epoch": 0.11754655732103195, "grad_norm": 1.9258185625076294, "learning_rate": 9.800672288358993e-05, "loss": 1.0111, "step": 2150 }, { "epoch": 0.11760123013839056, "grad_norm": 3.785597324371338, "learning_rate": 9.8004247222927e-05, "loss": 1.3235, "step": 2151 }, { "epoch": 0.1176559029557492, "grad_norm": 3.5523691177368164, "learning_rate": 9.800177005713322e-05, "loss": 1.2813, "step": 2152 }, { "epoch": 0.11771057577310781, "grad_norm": 3.375602960586548, "learning_rate": 9.799929138628627e-05, "loss": 1.2681, "step": 2153 }, { "epoch": 0.11776524859046643, "grad_norm": 4.312098503112793, "learning_rate": 9.799681121046385e-05, "loss": 1.4075, "step": 2154 }, { "epoch": 0.11781992140782505, "grad_norm": 2.2035727500915527, "learning_rate": 9.799432952974373e-05, "loss": 1.2294, "step": 2155 }, { "epoch": 0.11787459422518366, "grad_norm": 2.3583076000213623, "learning_rate": 9.799184634420371e-05, "loss": 1.068, "step": 2156 }, { "epoch": 0.11792926704254228, "grad_norm": 2.562464714050293, "learning_rate": 9.798936165392165e-05, "loss": 1.2423, "step": 2157 }, { "epoch": 0.11798393985990091, "grad_norm": 2.7348508834838867, "learning_rate": 9.798687545897548e-05, "loss": 1.2528, "step": 2158 }, { "epoch": 0.11803861267725953, "grad_norm": 2.422203302383423, "learning_rate": 9.798438775944311e-05, "loss": 1.2263, "step": 2159 }, { "epoch": 0.11809328549461814, "grad_norm": 3.3253636360168457, "learning_rate": 9.798189855540258e-05, "loss": 1.3904, "step": 2160 }, { "epoch": 0.11814795831197676, "grad_norm": 2.509442090988159, "learning_rate": 9.797940784693192e-05, "loss": 1.3145, "step": 2161 }, { "epoch": 0.11820263112933538, "grad_norm": 2.4848318099975586, "learning_rate": 9.797691563410921e-05, "loss": 1.2362, "step": 2162 }, { "epoch": 0.11825730394669401, "grad_norm": 2.120748519897461, "learning_rate": 9.797442191701262e-05, "loss": 1.0419, "step": 2163 }, { "epoch": 0.11831197676405263, "grad_norm": 2.6335031986236572, "learning_rate": 9.797192669572031e-05, "loss": 1.1856, "step": 2164 }, { "epoch": 0.11836664958141124, "grad_norm": 4.064426422119141, "learning_rate": 9.796942997031053e-05, "loss": 1.1211, "step": 2165 }, { "epoch": 0.11842132239876986, "grad_norm": 2.661484956741333, "learning_rate": 9.796693174086158e-05, "loss": 1.18, "step": 2166 }, { "epoch": 0.11847599521612848, "grad_norm": 2.8092057704925537, "learning_rate": 9.796443200745176e-05, "loss": 1.2439, "step": 2167 }, { "epoch": 0.1185306680334871, "grad_norm": 2.7988743782043457, "learning_rate": 9.796193077015947e-05, "loss": 1.1742, "step": 2168 }, { "epoch": 0.11858534085084572, "grad_norm": 2.640409469604492, "learning_rate": 9.795942802906311e-05, "loss": 1.116, "step": 2169 }, { "epoch": 0.11864001366820434, "grad_norm": 3.052806854248047, "learning_rate": 9.795692378424115e-05, "loss": 1.2635, "step": 2170 }, { "epoch": 0.11869468648556296, "grad_norm": 2.7568204402923584, "learning_rate": 9.795441803577214e-05, "loss": 1.2703, "step": 2171 }, { "epoch": 0.11874935930292158, "grad_norm": 2.630012273788452, "learning_rate": 9.795191078373463e-05, "loss": 1.2929, "step": 2172 }, { "epoch": 0.11880403212028019, "grad_norm": 4.959126949310303, "learning_rate": 9.794940202820721e-05, "loss": 1.2281, "step": 2173 }, { "epoch": 0.11885870493763882, "grad_norm": 2.270050048828125, "learning_rate": 9.794689176926859e-05, "loss": 1.082, "step": 2174 }, { "epoch": 0.11891337775499744, "grad_norm": 3.3521015644073486, "learning_rate": 9.794438000699742e-05, "loss": 1.2748, "step": 2175 }, { "epoch": 0.11896805057235606, "grad_norm": 3.1868464946746826, "learning_rate": 9.79418667414725e-05, "loss": 0.9883, "step": 2176 }, { "epoch": 0.11902272338971467, "grad_norm": 2.745011329650879, "learning_rate": 9.793935197277261e-05, "loss": 1.2707, "step": 2177 }, { "epoch": 0.11907739620707329, "grad_norm": 3.3431766033172607, "learning_rate": 9.793683570097659e-05, "loss": 1.0739, "step": 2178 }, { "epoch": 0.11913206902443192, "grad_norm": 3.349195718765259, "learning_rate": 9.793431792616337e-05, "loss": 1.3208, "step": 2179 }, { "epoch": 0.11918674184179054, "grad_norm": 3.150573492050171, "learning_rate": 9.793179864841184e-05, "loss": 1.3946, "step": 2180 }, { "epoch": 0.11924141465914916, "grad_norm": 2.6651649475097656, "learning_rate": 9.792927786780102e-05, "loss": 1.0513, "step": 2181 }, { "epoch": 0.11929608747650777, "grad_norm": 2.8119966983795166, "learning_rate": 9.792675558440995e-05, "loss": 1.1993, "step": 2182 }, { "epoch": 0.11935076029386639, "grad_norm": 2.9119269847869873, "learning_rate": 9.792423179831773e-05, "loss": 1.3195, "step": 2183 }, { "epoch": 0.119405433111225, "grad_norm": 2.8307526111602783, "learning_rate": 9.792170650960347e-05, "loss": 1.1518, "step": 2184 }, { "epoch": 0.11946010592858364, "grad_norm": 2.8693549633026123, "learning_rate": 9.791917971834632e-05, "loss": 1.383, "step": 2185 }, { "epoch": 0.11951477874594225, "grad_norm": 2.6528751850128174, "learning_rate": 9.791665142462553e-05, "loss": 1.2949, "step": 2186 }, { "epoch": 0.11956945156330087, "grad_norm": 3.2658870220184326, "learning_rate": 9.79141216285204e-05, "loss": 1.1853, "step": 2187 }, { "epoch": 0.11962412438065949, "grad_norm": 2.347538948059082, "learning_rate": 9.791159033011024e-05, "loss": 0.9665, "step": 2188 }, { "epoch": 0.1196787971980181, "grad_norm": 2.6293299198150635, "learning_rate": 9.790905752947436e-05, "loss": 0.9915, "step": 2189 }, { "epoch": 0.11973347001537674, "grad_norm": 3.3250374794006348, "learning_rate": 9.790652322669225e-05, "loss": 1.3124, "step": 2190 }, { "epoch": 0.11978814283273535, "grad_norm": 3.354754686355591, "learning_rate": 9.790398742184332e-05, "loss": 1.3282, "step": 2191 }, { "epoch": 0.11984281565009397, "grad_norm": 3.4277846813201904, "learning_rate": 9.790145011500711e-05, "loss": 1.3213, "step": 2192 }, { "epoch": 0.11989748846745259, "grad_norm": 3.2516934871673584, "learning_rate": 9.789891130626313e-05, "loss": 1.194, "step": 2193 }, { "epoch": 0.1199521612848112, "grad_norm": 2.751819610595703, "learning_rate": 9.789637099569105e-05, "loss": 1.2769, "step": 2194 }, { "epoch": 0.12000683410216982, "grad_norm": 2.9659011363983154, "learning_rate": 9.789382918337046e-05, "loss": 0.9918, "step": 2195 }, { "epoch": 0.12006150691952845, "grad_norm": 3.1296944618225098, "learning_rate": 9.789128586938109e-05, "loss": 1.179, "step": 2196 }, { "epoch": 0.12011617973688707, "grad_norm": 2.425395965576172, "learning_rate": 9.788874105380265e-05, "loss": 1.024, "step": 2197 }, { "epoch": 0.12017085255424569, "grad_norm": 2.73769211769104, "learning_rate": 9.788619473671497e-05, "loss": 1.2366, "step": 2198 }, { "epoch": 0.1202255253716043, "grad_norm": 3.1253206729888916, "learning_rate": 9.788364691819787e-05, "loss": 1.1877, "step": 2199 }, { "epoch": 0.12028019818896292, "grad_norm": 2.8556506633758545, "learning_rate": 9.788109759833122e-05, "loss": 1.0873, "step": 2200 }, { "epoch": 0.12033487100632155, "grad_norm": 2.837815046310425, "learning_rate": 9.787854677719497e-05, "loss": 1.164, "step": 2201 }, { "epoch": 0.12038954382368017, "grad_norm": 3.731074333190918, "learning_rate": 9.78759944548691e-05, "loss": 1.2427, "step": 2202 }, { "epoch": 0.12044421664103878, "grad_norm": 2.7205750942230225, "learning_rate": 9.787344063143363e-05, "loss": 1.293, "step": 2203 }, { "epoch": 0.1204988894583974, "grad_norm": 2.52589750289917, "learning_rate": 9.787088530696864e-05, "loss": 1.0937, "step": 2204 }, { "epoch": 0.12055356227575602, "grad_norm": 2.8687331676483154, "learning_rate": 9.786832848155423e-05, "loss": 1.3767, "step": 2205 }, { "epoch": 0.12060823509311464, "grad_norm": 2.271531820297241, "learning_rate": 9.786577015527057e-05, "loss": 1.1409, "step": 2206 }, { "epoch": 0.12066290791047327, "grad_norm": 2.315534830093384, "learning_rate": 9.78632103281979e-05, "loss": 1.2011, "step": 2207 }, { "epoch": 0.12071758072783188, "grad_norm": 3.4736993312835693, "learning_rate": 9.786064900041647e-05, "loss": 1.2837, "step": 2208 }, { "epoch": 0.1207722535451905, "grad_norm": 3.583428382873535, "learning_rate": 9.785808617200657e-05, "loss": 1.152, "step": 2209 }, { "epoch": 0.12082692636254912, "grad_norm": 2.4214439392089844, "learning_rate": 9.785552184304857e-05, "loss": 1.2163, "step": 2210 }, { "epoch": 0.12088159917990773, "grad_norm": 2.52964186668396, "learning_rate": 9.785295601362288e-05, "loss": 1.1908, "step": 2211 }, { "epoch": 0.12093627199726636, "grad_norm": 2.8570759296417236, "learning_rate": 9.785038868380993e-05, "loss": 1.273, "step": 2212 }, { "epoch": 0.12099094481462498, "grad_norm": 2.8831820487976074, "learning_rate": 9.784781985369023e-05, "loss": 1.2207, "step": 2213 }, { "epoch": 0.1210456176319836, "grad_norm": 4.417760372161865, "learning_rate": 9.784524952334431e-05, "loss": 1.2225, "step": 2214 }, { "epoch": 0.12110029044934222, "grad_norm": 2.827775478363037, "learning_rate": 9.784267769285278e-05, "loss": 1.2767, "step": 2215 }, { "epoch": 0.12115496326670083, "grad_norm": 2.656156539916992, "learning_rate": 9.784010436229626e-05, "loss": 1.4502, "step": 2216 }, { "epoch": 0.12120963608405946, "grad_norm": 2.7974743843078613, "learning_rate": 9.783752953175545e-05, "loss": 1.1767, "step": 2217 }, { "epoch": 0.12126430890141808, "grad_norm": 2.8449220657348633, "learning_rate": 9.783495320131107e-05, "loss": 1.2713, "step": 2218 }, { "epoch": 0.1213189817187767, "grad_norm": 3.9073333740234375, "learning_rate": 9.783237537104391e-05, "loss": 1.3413, "step": 2219 }, { "epoch": 0.12137365453613531, "grad_norm": 2.6746084690093994, "learning_rate": 9.782979604103477e-05, "loss": 1.0789, "step": 2220 }, { "epoch": 0.12142832735349393, "grad_norm": 2.641939401626587, "learning_rate": 9.782721521136455e-05, "loss": 1.2482, "step": 2221 }, { "epoch": 0.12148300017085255, "grad_norm": 2.7569851875305176, "learning_rate": 9.782463288211416e-05, "loss": 1.3073, "step": 2222 }, { "epoch": 0.12153767298821118, "grad_norm": 2.2488656044006348, "learning_rate": 9.782204905336457e-05, "loss": 1.3338, "step": 2223 }, { "epoch": 0.1215923458055698, "grad_norm": 2.8956074714660645, "learning_rate": 9.781946372519678e-05, "loss": 1.2132, "step": 2224 }, { "epoch": 0.12164701862292841, "grad_norm": 2.460723400115967, "learning_rate": 9.781687689769188e-05, "loss": 1.175, "step": 2225 }, { "epoch": 0.12170169144028703, "grad_norm": 2.8272175788879395, "learning_rate": 9.781428857093095e-05, "loss": 1.2154, "step": 2226 }, { "epoch": 0.12175636425764565, "grad_norm": 2.433572292327881, "learning_rate": 9.781169874499515e-05, "loss": 1.1601, "step": 2227 }, { "epoch": 0.12181103707500428, "grad_norm": 2.49306583404541, "learning_rate": 9.780910741996569e-05, "loss": 1.1425, "step": 2228 }, { "epoch": 0.1218657098923629, "grad_norm": 2.7250592708587646, "learning_rate": 9.780651459592381e-05, "loss": 1.398, "step": 2229 }, { "epoch": 0.12192038270972151, "grad_norm": 2.5944342613220215, "learning_rate": 9.78039202729508e-05, "loss": 1.1619, "step": 2230 }, { "epoch": 0.12197505552708013, "grad_norm": 3.8224008083343506, "learning_rate": 9.780132445112804e-05, "loss": 1.0888, "step": 2231 }, { "epoch": 0.12202972834443875, "grad_norm": 1.9559725522994995, "learning_rate": 9.779872713053685e-05, "loss": 1.0472, "step": 2232 }, { "epoch": 0.12208440116179736, "grad_norm": 2.9240105152130127, "learning_rate": 9.779612831125875e-05, "loss": 1.4728, "step": 2233 }, { "epoch": 0.122139073979156, "grad_norm": 2.795682907104492, "learning_rate": 9.779352799337517e-05, "loss": 1.3509, "step": 2234 }, { "epoch": 0.12219374679651461, "grad_norm": 2.9550235271453857, "learning_rate": 9.779092617696765e-05, "loss": 1.5397, "step": 2235 }, { "epoch": 0.12224841961387323, "grad_norm": 2.5983054637908936, "learning_rate": 9.778832286211777e-05, "loss": 1.2472, "step": 2236 }, { "epoch": 0.12230309243123184, "grad_norm": 3.097517728805542, "learning_rate": 9.778571804890714e-05, "loss": 1.2177, "step": 2237 }, { "epoch": 0.12235776524859046, "grad_norm": 2.916092872619629, "learning_rate": 9.778311173741748e-05, "loss": 1.1075, "step": 2238 }, { "epoch": 0.12241243806594909, "grad_norm": 3.35366153717041, "learning_rate": 9.778050392773045e-05, "loss": 0.9546, "step": 2239 }, { "epoch": 0.12246711088330771, "grad_norm": 3.254155397415161, "learning_rate": 9.777789461992784e-05, "loss": 1.409, "step": 2240 }, { "epoch": 0.12252178370066633, "grad_norm": 2.5118331909179688, "learning_rate": 9.777528381409148e-05, "loss": 1.0908, "step": 2241 }, { "epoch": 0.12257645651802494, "grad_norm": 2.9484763145446777, "learning_rate": 9.77726715103032e-05, "loss": 1.3151, "step": 2242 }, { "epoch": 0.12263112933538356, "grad_norm": 2.559272527694702, "learning_rate": 9.777005770864493e-05, "loss": 1.1336, "step": 2243 }, { "epoch": 0.12268580215274218, "grad_norm": 2.5101938247680664, "learning_rate": 9.77674424091986e-05, "loss": 1.1417, "step": 2244 }, { "epoch": 0.12274047497010081, "grad_norm": 2.4018869400024414, "learning_rate": 9.776482561204623e-05, "loss": 1.1483, "step": 2245 }, { "epoch": 0.12279514778745942, "grad_norm": 2.2229435443878174, "learning_rate": 9.776220731726987e-05, "loss": 1.1636, "step": 2246 }, { "epoch": 0.12284982060481804, "grad_norm": 2.892185688018799, "learning_rate": 9.77595875249516e-05, "loss": 1.4908, "step": 2247 }, { "epoch": 0.12290449342217666, "grad_norm": 2.5043818950653076, "learning_rate": 9.775696623517357e-05, "loss": 1.1472, "step": 2248 }, { "epoch": 0.12295916623953528, "grad_norm": 2.6822011470794678, "learning_rate": 9.775434344801795e-05, "loss": 1.0807, "step": 2249 }, { "epoch": 0.1230138390568939, "grad_norm": 2.1886978149414062, "learning_rate": 9.7751719163567e-05, "loss": 1.0433, "step": 2250 }, { "epoch": 0.12306851187425252, "grad_norm": 2.749629020690918, "learning_rate": 9.774909338190299e-05, "loss": 1.2641, "step": 2251 }, { "epoch": 0.12312318469161114, "grad_norm": 2.8325870037078857, "learning_rate": 9.774646610310825e-05, "loss": 1.3206, "step": 2252 }, { "epoch": 0.12317785750896976, "grad_norm": 2.2086997032165527, "learning_rate": 9.774383732726517e-05, "loss": 1.0034, "step": 2253 }, { "epoch": 0.12323253032632837, "grad_norm": 2.1033716201782227, "learning_rate": 9.774120705445614e-05, "loss": 1.056, "step": 2254 }, { "epoch": 0.123287203143687, "grad_norm": 2.6309967041015625, "learning_rate": 9.773857528476367e-05, "loss": 1.1272, "step": 2255 }, { "epoch": 0.12334187596104562, "grad_norm": 2.5856571197509766, "learning_rate": 9.773594201827023e-05, "loss": 1.1855, "step": 2256 }, { "epoch": 0.12339654877840424, "grad_norm": 2.792578935623169, "learning_rate": 9.773330725505843e-05, "loss": 1.1486, "step": 2257 }, { "epoch": 0.12345122159576286, "grad_norm": 3.4305503368377686, "learning_rate": 9.773067099521087e-05, "loss": 1.4477, "step": 2258 }, { "epoch": 0.12350589441312147, "grad_norm": 2.1754887104034424, "learning_rate": 9.772803323881018e-05, "loss": 1.1623, "step": 2259 }, { "epoch": 0.12356056723048009, "grad_norm": 2.617069959640503, "learning_rate": 9.772539398593908e-05, "loss": 1.1126, "step": 2260 }, { "epoch": 0.12361524004783872, "grad_norm": 2.8401129245758057, "learning_rate": 9.772275323668034e-05, "loss": 1.2819, "step": 2261 }, { "epoch": 0.12366991286519734, "grad_norm": 2.2092926502227783, "learning_rate": 9.772011099111674e-05, "loss": 1.1374, "step": 2262 }, { "epoch": 0.12372458568255595, "grad_norm": 2.4339773654937744, "learning_rate": 9.771746724933113e-05, "loss": 1.2741, "step": 2263 }, { "epoch": 0.12377925849991457, "grad_norm": 3.3935670852661133, "learning_rate": 9.771482201140639e-05, "loss": 0.884, "step": 2264 }, { "epoch": 0.12383393131727319, "grad_norm": 2.6641459465026855, "learning_rate": 9.771217527742548e-05, "loss": 1.1892, "step": 2265 }, { "epoch": 0.12388860413463182, "grad_norm": 2.1706104278564453, "learning_rate": 9.770952704747138e-05, "loss": 1.0495, "step": 2266 }, { "epoch": 0.12394327695199044, "grad_norm": 3.1372718811035156, "learning_rate": 9.77068773216271e-05, "loss": 1.2898, "step": 2267 }, { "epoch": 0.12399794976934905, "grad_norm": 2.5149924755096436, "learning_rate": 9.770422609997575e-05, "loss": 1.2249, "step": 2268 }, { "epoch": 0.12405262258670767, "grad_norm": 2.294039011001587, "learning_rate": 9.770157338260044e-05, "loss": 1.1434, "step": 2269 }, { "epoch": 0.12410729540406629, "grad_norm": 2.497464179992676, "learning_rate": 9.769891916958436e-05, "loss": 1.1577, "step": 2270 }, { "epoch": 0.1241619682214249, "grad_norm": 2.1986703872680664, "learning_rate": 9.76962634610107e-05, "loss": 1.0512, "step": 2271 }, { "epoch": 0.12421664103878353, "grad_norm": 2.974933385848999, "learning_rate": 9.769360625696278e-05, "loss": 1.3805, "step": 2272 }, { "epoch": 0.12427131385614215, "grad_norm": 3.2065510749816895, "learning_rate": 9.769094755752385e-05, "loss": 1.3178, "step": 2273 }, { "epoch": 0.12432598667350077, "grad_norm": 3.0364174842834473, "learning_rate": 9.768828736277731e-05, "loss": 1.2508, "step": 2274 }, { "epoch": 0.12438065949085939, "grad_norm": 3.7681891918182373, "learning_rate": 9.768562567280657e-05, "loss": 1.3596, "step": 2275 }, { "epoch": 0.124435332308218, "grad_norm": 2.3556604385375977, "learning_rate": 9.768296248769506e-05, "loss": 1.1154, "step": 2276 }, { "epoch": 0.12449000512557663, "grad_norm": 3.472663640975952, "learning_rate": 9.76802978075263e-05, "loss": 1.2264, "step": 2277 }, { "epoch": 0.12454467794293525, "grad_norm": 3.3880324363708496, "learning_rate": 9.767763163238385e-05, "loss": 1.0071, "step": 2278 }, { "epoch": 0.12459935076029387, "grad_norm": 2.8247900009155273, "learning_rate": 9.767496396235128e-05, "loss": 1.3564, "step": 2279 }, { "epoch": 0.12465402357765248, "grad_norm": 2.3295392990112305, "learning_rate": 9.767229479751226e-05, "loss": 1.1627, "step": 2280 }, { "epoch": 0.1247086963950111, "grad_norm": 2.8229804039001465, "learning_rate": 9.766962413795045e-05, "loss": 1.2501, "step": 2281 }, { "epoch": 0.12476336921236972, "grad_norm": 2.3674392700195312, "learning_rate": 9.766695198374957e-05, "loss": 1.1515, "step": 2282 }, { "epoch": 0.12481804202972835, "grad_norm": 2.564512252807617, "learning_rate": 9.766427833499347e-05, "loss": 1.3248, "step": 2283 }, { "epoch": 0.12487271484708697, "grad_norm": 2.9237804412841797, "learning_rate": 9.766160319176594e-05, "loss": 1.2877, "step": 2284 }, { "epoch": 0.12492738766444558, "grad_norm": 2.6875178813934326, "learning_rate": 9.765892655415085e-05, "loss": 1.2775, "step": 2285 }, { "epoch": 0.1249820604818042, "grad_norm": 2.612534999847412, "learning_rate": 9.765624842223213e-05, "loss": 1.2799, "step": 2286 }, { "epoch": 0.12503673329916282, "grad_norm": 2.5502803325653076, "learning_rate": 9.765356879609376e-05, "loss": 1.2205, "step": 2287 }, { "epoch": 0.12509140611652145, "grad_norm": 2.9904470443725586, "learning_rate": 9.765088767581975e-05, "loss": 0.9916, "step": 2288 }, { "epoch": 0.12514607893388005, "grad_norm": 2.823906421661377, "learning_rate": 9.764820506149416e-05, "loss": 1.2675, "step": 2289 }, { "epoch": 0.12520075175123868, "grad_norm": 2.066227912902832, "learning_rate": 9.76455209532011e-05, "loss": 1.1561, "step": 2290 }, { "epoch": 0.1252554245685973, "grad_norm": 4.036117076873779, "learning_rate": 9.764283535102475e-05, "loss": 0.9962, "step": 2291 }, { "epoch": 0.12531009738595592, "grad_norm": 3.014282703399658, "learning_rate": 9.764014825504928e-05, "loss": 1.147, "step": 2292 }, { "epoch": 0.12536477020331455, "grad_norm": 2.5844953060150146, "learning_rate": 9.763745966535897e-05, "loss": 1.1857, "step": 2293 }, { "epoch": 0.12541944302067315, "grad_norm": 2.4328882694244385, "learning_rate": 9.76347695820381e-05, "loss": 1.1061, "step": 2294 }, { "epoch": 0.12547411583803178, "grad_norm": 2.4246835708618164, "learning_rate": 9.763207800517104e-05, "loss": 1.2003, "step": 2295 }, { "epoch": 0.1255287886553904, "grad_norm": 2.314267635345459, "learning_rate": 9.762938493484215e-05, "loss": 1.0849, "step": 2296 }, { "epoch": 0.12558346147274901, "grad_norm": 3.2277188301086426, "learning_rate": 9.762669037113589e-05, "loss": 1.3046, "step": 2297 }, { "epoch": 0.12563813429010764, "grad_norm": 2.210263967514038, "learning_rate": 9.762399431413673e-05, "loss": 1.0856, "step": 2298 }, { "epoch": 0.12569280710746625, "grad_norm": 2.699976682662964, "learning_rate": 9.762129676392922e-05, "loss": 1.2365, "step": 2299 }, { "epoch": 0.12574747992482488, "grad_norm": 2.645148992538452, "learning_rate": 9.761859772059794e-05, "loss": 1.1681, "step": 2300 }, { "epoch": 0.1258021527421835, "grad_norm": 2.3749663829803467, "learning_rate": 9.76158971842275e-05, "loss": 1.2987, "step": 2301 }, { "epoch": 0.1258568255595421, "grad_norm": 2.1917459964752197, "learning_rate": 9.761319515490258e-05, "loss": 1.1322, "step": 2302 }, { "epoch": 0.12591149837690074, "grad_norm": 2.181333541870117, "learning_rate": 9.761049163270789e-05, "loss": 1.1656, "step": 2303 }, { "epoch": 0.12596617119425935, "grad_norm": 3.998082399368286, "learning_rate": 9.760778661772822e-05, "loss": 1.4517, "step": 2304 }, { "epoch": 0.12602084401161798, "grad_norm": 2.3388452529907227, "learning_rate": 9.760508011004837e-05, "loss": 1.2475, "step": 2305 }, { "epoch": 0.12607551682897658, "grad_norm": 1.9950642585754395, "learning_rate": 9.760237210975319e-05, "loss": 0.9773, "step": 2306 }, { "epoch": 0.1261301896463352, "grad_norm": 2.427173376083374, "learning_rate": 9.759966261692761e-05, "loss": 1.1494, "step": 2307 }, { "epoch": 0.12618486246369384, "grad_norm": 3.146314859390259, "learning_rate": 9.759695163165657e-05, "loss": 1.1401, "step": 2308 }, { "epoch": 0.12623953528105245, "grad_norm": 2.228706121444702, "learning_rate": 9.759423915402506e-05, "loss": 1.1709, "step": 2309 }, { "epoch": 0.12629420809841108, "grad_norm": 3.236130952835083, "learning_rate": 9.759152518411814e-05, "loss": 1.341, "step": 2310 }, { "epoch": 0.12634888091576968, "grad_norm": 2.566089153289795, "learning_rate": 9.758880972202091e-05, "loss": 1.4108, "step": 2311 }, { "epoch": 0.1264035537331283, "grad_norm": 2.8819429874420166, "learning_rate": 9.758609276781849e-05, "loss": 1.4254, "step": 2312 }, { "epoch": 0.12645822655048694, "grad_norm": 4.060896873474121, "learning_rate": 9.75833743215961e-05, "loss": 1.2596, "step": 2313 }, { "epoch": 0.12651289936784554, "grad_norm": 2.3556456565856934, "learning_rate": 9.758065438343895e-05, "loss": 1.071, "step": 2314 }, { "epoch": 0.12656757218520417, "grad_norm": 2.999502182006836, "learning_rate": 9.757793295343233e-05, "loss": 1.4054, "step": 2315 }, { "epoch": 0.12662224500256278, "grad_norm": 2.5528717041015625, "learning_rate": 9.757521003166156e-05, "loss": 1.1142, "step": 2316 }, { "epoch": 0.1266769178199214, "grad_norm": 3.9657487869262695, "learning_rate": 9.757248561821202e-05, "loss": 1.1818, "step": 2317 }, { "epoch": 0.12673159063728004, "grad_norm": 2.5066168308258057, "learning_rate": 9.756975971316914e-05, "loss": 1.1452, "step": 2318 }, { "epoch": 0.12678626345463864, "grad_norm": 2.833725929260254, "learning_rate": 9.756703231661837e-05, "loss": 1.2639, "step": 2319 }, { "epoch": 0.12684093627199727, "grad_norm": 2.392021894454956, "learning_rate": 9.756430342864524e-05, "loss": 1.2036, "step": 2320 }, { "epoch": 0.12689560908935588, "grad_norm": 2.8294870853424072, "learning_rate": 9.75615730493353e-05, "loss": 1.2588, "step": 2321 }, { "epoch": 0.1269502819067145, "grad_norm": 2.400804281234741, "learning_rate": 9.755884117877418e-05, "loss": 1.0533, "step": 2322 }, { "epoch": 0.12700495472407314, "grad_norm": 4.9208478927612305, "learning_rate": 9.755610781704751e-05, "loss": 1.1877, "step": 2323 }, { "epoch": 0.12705962754143174, "grad_norm": 2.5058953762054443, "learning_rate": 9.755337296424101e-05, "loss": 1.1319, "step": 2324 }, { "epoch": 0.12711430035879037, "grad_norm": 3.4267947673797607, "learning_rate": 9.755063662044043e-05, "loss": 1.0697, "step": 2325 }, { "epoch": 0.12716897317614898, "grad_norm": 2.57534122467041, "learning_rate": 9.754789878573154e-05, "loss": 1.1763, "step": 2326 }, { "epoch": 0.1272236459935076, "grad_norm": 2.6961238384246826, "learning_rate": 9.754515946020021e-05, "loss": 1.3112, "step": 2327 }, { "epoch": 0.1272783188108662, "grad_norm": 2.564211368560791, "learning_rate": 9.754241864393231e-05, "loss": 1.1157, "step": 2328 }, { "epoch": 0.12733299162822484, "grad_norm": 1.9217497110366821, "learning_rate": 9.753967633701381e-05, "loss": 1.1358, "step": 2329 }, { "epoch": 0.12738766444558347, "grad_norm": 2.499805450439453, "learning_rate": 9.753693253953064e-05, "loss": 1.2105, "step": 2330 }, { "epoch": 0.12744233726294207, "grad_norm": 2.069547653198242, "learning_rate": 9.753418725156887e-05, "loss": 1.1486, "step": 2331 }, { "epoch": 0.1274970100803007, "grad_norm": 3.129936456680298, "learning_rate": 9.753144047321457e-05, "loss": 1.15, "step": 2332 }, { "epoch": 0.1275516828976593, "grad_norm": 2.787630081176758, "learning_rate": 9.752869220455385e-05, "loss": 1.1809, "step": 2333 }, { "epoch": 0.12760635571501794, "grad_norm": 2.6146504878997803, "learning_rate": 9.752594244567288e-05, "loss": 1.1964, "step": 2334 }, { "epoch": 0.12766102853237657, "grad_norm": 2.355475425720215, "learning_rate": 9.752319119665789e-05, "loss": 1.03, "step": 2335 }, { "epoch": 0.12771570134973517, "grad_norm": 2.6963140964508057, "learning_rate": 9.752043845759513e-05, "loss": 1.1043, "step": 2336 }, { "epoch": 0.1277703741670938, "grad_norm": 3.161379098892212, "learning_rate": 9.751768422857092e-05, "loss": 1.3788, "step": 2337 }, { "epoch": 0.1278250469844524, "grad_norm": 2.394878625869751, "learning_rate": 9.75149285096716e-05, "loss": 1.1029, "step": 2338 }, { "epoch": 0.12787971980181104, "grad_norm": 2.1323719024658203, "learning_rate": 9.75121713009836e-05, "loss": 1.2133, "step": 2339 }, { "epoch": 0.12793439261916967, "grad_norm": 2.323197841644287, "learning_rate": 9.750941260259334e-05, "loss": 1.1322, "step": 2340 }, { "epoch": 0.12798906543652827, "grad_norm": 2.543790578842163, "learning_rate": 9.750665241458733e-05, "loss": 1.1299, "step": 2341 }, { "epoch": 0.1280437382538869, "grad_norm": 2.5762948989868164, "learning_rate": 9.750389073705213e-05, "loss": 1.089, "step": 2342 }, { "epoch": 0.1280984110712455, "grad_norm": 2.9014475345611572, "learning_rate": 9.75011275700743e-05, "loss": 1.0116, "step": 2343 }, { "epoch": 0.12815308388860414, "grad_norm": 2.865630865097046, "learning_rate": 9.749836291374048e-05, "loss": 1.1254, "step": 2344 }, { "epoch": 0.12820775670596277, "grad_norm": 2.5686659812927246, "learning_rate": 9.749559676813739e-05, "loss": 1.2022, "step": 2345 }, { "epoch": 0.12826242952332137, "grad_norm": 3.074042320251465, "learning_rate": 9.749282913335172e-05, "loss": 1.4206, "step": 2346 }, { "epoch": 0.12831710234068, "grad_norm": 2.6578195095062256, "learning_rate": 9.749006000947027e-05, "loss": 1.233, "step": 2347 }, { "epoch": 0.1283717751580386, "grad_norm": 2.3090014457702637, "learning_rate": 9.748728939657984e-05, "loss": 1.0971, "step": 2348 }, { "epoch": 0.12842644797539723, "grad_norm": 2.5767199993133545, "learning_rate": 9.748451729476731e-05, "loss": 1.3009, "step": 2349 }, { "epoch": 0.12848112079275587, "grad_norm": 2.423391819000244, "learning_rate": 9.748174370411962e-05, "loss": 1.2558, "step": 2350 }, { "epoch": 0.12853579361011447, "grad_norm": 2.722571611404419, "learning_rate": 9.747896862472371e-05, "loss": 1.1717, "step": 2351 }, { "epoch": 0.1285904664274731, "grad_norm": 3.2200160026550293, "learning_rate": 9.747619205666658e-05, "loss": 1.2102, "step": 2352 }, { "epoch": 0.1286451392448317, "grad_norm": 2.3810982704162598, "learning_rate": 9.747341400003532e-05, "loss": 1.1537, "step": 2353 }, { "epoch": 0.12869981206219033, "grad_norm": 2.302288293838501, "learning_rate": 9.7470634454917e-05, "loss": 1.3112, "step": 2354 }, { "epoch": 0.12875448487954894, "grad_norm": 2.6239004135131836, "learning_rate": 9.74678534213988e-05, "loss": 1.2775, "step": 2355 }, { "epoch": 0.12880915769690757, "grad_norm": 2.5691332817077637, "learning_rate": 9.74650708995679e-05, "loss": 1.0087, "step": 2356 }, { "epoch": 0.1288638305142662, "grad_norm": 2.4801318645477295, "learning_rate": 9.746228688951153e-05, "loss": 1.1294, "step": 2357 }, { "epoch": 0.1289185033316248, "grad_norm": 2.545941114425659, "learning_rate": 9.7459501391317e-05, "loss": 1.2888, "step": 2358 }, { "epoch": 0.12897317614898343, "grad_norm": 3.0250091552734375, "learning_rate": 9.745671440507166e-05, "loss": 1.2851, "step": 2359 }, { "epoch": 0.12902784896634203, "grad_norm": 2.3154618740081787, "learning_rate": 9.745392593086287e-05, "loss": 1.085, "step": 2360 }, { "epoch": 0.12908252178370067, "grad_norm": 2.6111721992492676, "learning_rate": 9.745113596877807e-05, "loss": 1.2216, "step": 2361 }, { "epoch": 0.1291371946010593, "grad_norm": 2.7659668922424316, "learning_rate": 9.744834451890472e-05, "loss": 1.1225, "step": 2362 }, { "epoch": 0.1291918674184179, "grad_norm": 2.705397844314575, "learning_rate": 9.744555158133036e-05, "loss": 1.0934, "step": 2363 }, { "epoch": 0.12924654023577653, "grad_norm": 2.337796926498413, "learning_rate": 9.744275715614256e-05, "loss": 0.9895, "step": 2364 }, { "epoch": 0.12930121305313513, "grad_norm": 7.8253960609436035, "learning_rate": 9.743996124342893e-05, "loss": 1.2137, "step": 2365 }, { "epoch": 0.12935588587049376, "grad_norm": 3.3058555126190186, "learning_rate": 9.743716384327714e-05, "loss": 1.3239, "step": 2366 }, { "epoch": 0.1294105586878524, "grad_norm": 4.316788196563721, "learning_rate": 9.743436495577489e-05, "loss": 1.2709, "step": 2367 }, { "epoch": 0.129465231505211, "grad_norm": 2.6973390579223633, "learning_rate": 9.743156458100996e-05, "loss": 1.1203, "step": 2368 }, { "epoch": 0.12951990432256963, "grad_norm": 2.6554856300354004, "learning_rate": 9.742876271907012e-05, "loss": 1.3727, "step": 2369 }, { "epoch": 0.12957457713992823, "grad_norm": 3.1184535026550293, "learning_rate": 9.742595937004324e-05, "loss": 1.2372, "step": 2370 }, { "epoch": 0.12962924995728686, "grad_norm": 4.035940647125244, "learning_rate": 9.742315453401722e-05, "loss": 1.3128, "step": 2371 }, { "epoch": 0.1296839227746455, "grad_norm": 2.5301706790924072, "learning_rate": 9.742034821107999e-05, "loss": 1.0871, "step": 2372 }, { "epoch": 0.1297385955920041, "grad_norm": 2.4218757152557373, "learning_rate": 9.741754040131955e-05, "loss": 1.1281, "step": 2373 }, { "epoch": 0.12979326840936273, "grad_norm": 2.5796265602111816, "learning_rate": 9.741473110482392e-05, "loss": 1.0916, "step": 2374 }, { "epoch": 0.12984794122672133, "grad_norm": 2.232534170150757, "learning_rate": 9.741192032168122e-05, "loss": 1.1462, "step": 2375 }, { "epoch": 0.12990261404407996, "grad_norm": 3.2774157524108887, "learning_rate": 9.740910805197954e-05, "loss": 1.2338, "step": 2376 }, { "epoch": 0.1299572868614386, "grad_norm": 2.591276168823242, "learning_rate": 9.740629429580708e-05, "loss": 1.312, "step": 2377 }, { "epoch": 0.1300119596787972, "grad_norm": 2.387791872024536, "learning_rate": 9.740347905325204e-05, "loss": 1.0476, "step": 2378 }, { "epoch": 0.13006663249615583, "grad_norm": 2.883255958557129, "learning_rate": 9.74006623244027e-05, "loss": 1.0886, "step": 2379 }, { "epoch": 0.13012130531351443, "grad_norm": 2.1010749340057373, "learning_rate": 9.73978441093474e-05, "loss": 1.0647, "step": 2380 }, { "epoch": 0.13017597813087306, "grad_norm": 2.0051753520965576, "learning_rate": 9.739502440817447e-05, "loss": 1.0179, "step": 2381 }, { "epoch": 0.13023065094823166, "grad_norm": 2.2089762687683105, "learning_rate": 9.739220322097234e-05, "loss": 1.106, "step": 2382 }, { "epoch": 0.1302853237655903, "grad_norm": 2.98158860206604, "learning_rate": 9.738938054782944e-05, "loss": 1.1601, "step": 2383 }, { "epoch": 0.13033999658294892, "grad_norm": 2.561429023742676, "learning_rate": 9.738655638883432e-05, "loss": 0.9376, "step": 2384 }, { "epoch": 0.13039466940030753, "grad_norm": 2.0525174140930176, "learning_rate": 9.738373074407548e-05, "loss": 0.916, "step": 2385 }, { "epoch": 0.13044934221766616, "grad_norm": 2.65058970451355, "learning_rate": 9.738090361364153e-05, "loss": 1.1153, "step": 2386 }, { "epoch": 0.13050401503502476, "grad_norm": 3.087862253189087, "learning_rate": 9.737807499762113e-05, "loss": 1.2596, "step": 2387 }, { "epoch": 0.1305586878523834, "grad_norm": 2.7348856925964355, "learning_rate": 9.737524489610294e-05, "loss": 1.3399, "step": 2388 }, { "epoch": 0.13061336066974202, "grad_norm": 2.1699042320251465, "learning_rate": 9.737241330917573e-05, "loss": 0.9714, "step": 2389 }, { "epoch": 0.13066803348710063, "grad_norm": 2.564190626144409, "learning_rate": 9.736958023692824e-05, "loss": 1.1539, "step": 2390 }, { "epoch": 0.13072270630445926, "grad_norm": 3.1535797119140625, "learning_rate": 9.736674567944933e-05, "loss": 1.1928, "step": 2391 }, { "epoch": 0.13077737912181786, "grad_norm": 3.063603401184082, "learning_rate": 9.736390963682787e-05, "loss": 1.2112, "step": 2392 }, { "epoch": 0.1308320519391765, "grad_norm": 2.1664931774139404, "learning_rate": 9.736107210915277e-05, "loss": 0.8485, "step": 2393 }, { "epoch": 0.13088672475653512, "grad_norm": 2.7209298610687256, "learning_rate": 9.735823309651302e-05, "loss": 1.1234, "step": 2394 }, { "epoch": 0.13094139757389373, "grad_norm": 3.1797568798065186, "learning_rate": 9.735539259899762e-05, "loss": 0.9718, "step": 2395 }, { "epoch": 0.13099607039125236, "grad_norm": 2.731646776199341, "learning_rate": 9.735255061669562e-05, "loss": 1.2871, "step": 2396 }, { "epoch": 0.13105074320861096, "grad_norm": 2.3998258113861084, "learning_rate": 9.734970714969615e-05, "loss": 1.1577, "step": 2397 }, { "epoch": 0.1311054160259696, "grad_norm": 6.026516437530518, "learning_rate": 9.734686219808836e-05, "loss": 1.1191, "step": 2398 }, { "epoch": 0.13116008884332822, "grad_norm": 3.0342366695404053, "learning_rate": 9.734401576196142e-05, "loss": 1.2835, "step": 2399 }, { "epoch": 0.13121476166068682, "grad_norm": 2.28859543800354, "learning_rate": 9.734116784140461e-05, "loss": 0.9475, "step": 2400 }, { "epoch": 0.13126943447804545, "grad_norm": 2.4999780654907227, "learning_rate": 9.733831843650722e-05, "loss": 1.1889, "step": 2401 }, { "epoch": 0.13132410729540406, "grad_norm": 2.3595712184906006, "learning_rate": 9.73354675473586e-05, "loss": 1.2667, "step": 2402 }, { "epoch": 0.1313787801127627, "grad_norm": 2.6269943714141846, "learning_rate": 9.733261517404813e-05, "loss": 1.4098, "step": 2403 }, { "epoch": 0.1314334529301213, "grad_norm": 2.7416515350341797, "learning_rate": 9.732976131666522e-05, "loss": 1.1617, "step": 2404 }, { "epoch": 0.13148812574747992, "grad_norm": 4.087407112121582, "learning_rate": 9.732690597529936e-05, "loss": 1.218, "step": 2405 }, { "epoch": 0.13154279856483855, "grad_norm": 2.017443895339966, "learning_rate": 9.732404915004011e-05, "loss": 1.0974, "step": 2406 }, { "epoch": 0.13159747138219716, "grad_norm": 2.343332290649414, "learning_rate": 9.7321190840977e-05, "loss": 0.9913, "step": 2407 }, { "epoch": 0.1316521441995558, "grad_norm": 2.6511778831481934, "learning_rate": 9.731833104819967e-05, "loss": 1.1667, "step": 2408 }, { "epoch": 0.1317068170169144, "grad_norm": 2.272090435028076, "learning_rate": 9.73154697717978e-05, "loss": 1.1723, "step": 2409 }, { "epoch": 0.13176148983427302, "grad_norm": 2.3108150959014893, "learning_rate": 9.731260701186107e-05, "loss": 1.1759, "step": 2410 }, { "epoch": 0.13181616265163165, "grad_norm": 2.863957405090332, "learning_rate": 9.730974276847926e-05, "loss": 1.0978, "step": 2411 }, { "epoch": 0.13187083546899026, "grad_norm": 2.380298137664795, "learning_rate": 9.730687704174218e-05, "loss": 1.1098, "step": 2412 }, { "epoch": 0.13192550828634889, "grad_norm": 2.7276854515075684, "learning_rate": 9.730400983173966e-05, "loss": 1.3083, "step": 2413 }, { "epoch": 0.1319801811037075, "grad_norm": 2.74884295463562, "learning_rate": 9.730114113856164e-05, "loss": 0.9604, "step": 2414 }, { "epoch": 0.13203485392106612, "grad_norm": 3.486035108566284, "learning_rate": 9.729827096229803e-05, "loss": 1.3728, "step": 2415 }, { "epoch": 0.13208952673842475, "grad_norm": 2.7503747940063477, "learning_rate": 9.729539930303882e-05, "loss": 1.1373, "step": 2416 }, { "epoch": 0.13214419955578335, "grad_norm": 2.8895184993743896, "learning_rate": 9.729252616087406e-05, "loss": 1.2794, "step": 2417 }, { "epoch": 0.13219887237314198, "grad_norm": 2.914687156677246, "learning_rate": 9.728965153589382e-05, "loss": 1.2529, "step": 2418 }, { "epoch": 0.1322535451905006, "grad_norm": 2.418670892715454, "learning_rate": 9.728677542818827e-05, "loss": 1.0633, "step": 2419 }, { "epoch": 0.13230821800785922, "grad_norm": 2.7203612327575684, "learning_rate": 9.728389783784755e-05, "loss": 1.2331, "step": 2420 }, { "epoch": 0.13236289082521785, "grad_norm": 2.4717626571655273, "learning_rate": 9.72810187649619e-05, "loss": 1.1058, "step": 2421 }, { "epoch": 0.13241756364257645, "grad_norm": 2.866366386413574, "learning_rate": 9.727813820962159e-05, "loss": 1.3882, "step": 2422 }, { "epoch": 0.13247223645993508, "grad_norm": 2.282989263534546, "learning_rate": 9.727525617191692e-05, "loss": 1.2358, "step": 2423 }, { "epoch": 0.1325269092772937, "grad_norm": 2.2205941677093506, "learning_rate": 9.727237265193829e-05, "loss": 1.0749, "step": 2424 }, { "epoch": 0.13258158209465232, "grad_norm": 4.0653076171875, "learning_rate": 9.726948764977608e-05, "loss": 1.3489, "step": 2425 }, { "epoch": 0.13263625491201095, "grad_norm": 2.640634775161743, "learning_rate": 9.726660116552077e-05, "loss": 1.2792, "step": 2426 }, { "epoch": 0.13269092772936955, "grad_norm": 3.836965560913086, "learning_rate": 9.726371319926282e-05, "loss": 1.3822, "step": 2427 }, { "epoch": 0.13274560054672818, "grad_norm": 2.153934955596924, "learning_rate": 9.726082375109285e-05, "loss": 0.9738, "step": 2428 }, { "epoch": 0.13280027336408678, "grad_norm": 2.3065199851989746, "learning_rate": 9.725793282110139e-05, "loss": 1.1067, "step": 2429 }, { "epoch": 0.13285494618144542, "grad_norm": 2.76137638092041, "learning_rate": 9.725504040937909e-05, "loss": 1.3886, "step": 2430 }, { "epoch": 0.13290961899880402, "grad_norm": 2.8451201915740967, "learning_rate": 9.725214651601668e-05, "loss": 1.1895, "step": 2431 }, { "epoch": 0.13296429181616265, "grad_norm": 2.8913352489471436, "learning_rate": 9.724925114110486e-05, "loss": 1.1696, "step": 2432 }, { "epoch": 0.13301896463352128, "grad_norm": 3.2482917308807373, "learning_rate": 9.724635428473444e-05, "loss": 1.2939, "step": 2433 }, { "epoch": 0.13307363745087988, "grad_norm": 2.0922579765319824, "learning_rate": 9.724345594699623e-05, "loss": 1.1717, "step": 2434 }, { "epoch": 0.13312831026823851, "grad_norm": 2.938441514968872, "learning_rate": 9.724055612798109e-05, "loss": 1.3544, "step": 2435 }, { "epoch": 0.13318298308559712, "grad_norm": 2.7105846405029297, "learning_rate": 9.723765482777998e-05, "loss": 1.3303, "step": 2436 }, { "epoch": 0.13323765590295575, "grad_norm": 2.68056321144104, "learning_rate": 9.723475204648383e-05, "loss": 1.0295, "step": 2437 }, { "epoch": 0.13329232872031438, "grad_norm": 2.561039447784424, "learning_rate": 9.723184778418368e-05, "loss": 1.1919, "step": 2438 }, { "epoch": 0.13334700153767298, "grad_norm": 2.2826359272003174, "learning_rate": 9.722894204097058e-05, "loss": 0.8297, "step": 2439 }, { "epoch": 0.1334016743550316, "grad_norm": 3.969183921813965, "learning_rate": 9.722603481693562e-05, "loss": 1.1445, "step": 2440 }, { "epoch": 0.13345634717239022, "grad_norm": 2.794861078262329, "learning_rate": 9.722312611217e-05, "loss": 1.154, "step": 2441 }, { "epoch": 0.13351101998974885, "grad_norm": 2.865280866622925, "learning_rate": 9.722021592676487e-05, "loss": 1.2139, "step": 2442 }, { "epoch": 0.13356569280710748, "grad_norm": 2.74538516998291, "learning_rate": 9.72173042608115e-05, "loss": 1.3219, "step": 2443 }, { "epoch": 0.13362036562446608, "grad_norm": 2.2806992530822754, "learning_rate": 9.72143911144012e-05, "loss": 1.107, "step": 2444 }, { "epoch": 0.1336750384418247, "grad_norm": 2.9333009719848633, "learning_rate": 9.721147648762526e-05, "loss": 1.0452, "step": 2445 }, { "epoch": 0.13372971125918331, "grad_norm": 2.2296664714813232, "learning_rate": 9.720856038057511e-05, "loss": 1.2656, "step": 2446 }, { "epoch": 0.13378438407654195, "grad_norm": 2.460491180419922, "learning_rate": 9.720564279334217e-05, "loss": 0.9559, "step": 2447 }, { "epoch": 0.13383905689390058, "grad_norm": 2.7371468544006348, "learning_rate": 9.720272372601791e-05, "loss": 1.2363, "step": 2448 }, { "epoch": 0.13389372971125918, "grad_norm": 2.3610522747039795, "learning_rate": 9.719980317869386e-05, "loss": 1.1807, "step": 2449 }, { "epoch": 0.1339484025286178, "grad_norm": 7.091941833496094, "learning_rate": 9.719688115146159e-05, "loss": 1.4061, "step": 2450 }, { "epoch": 0.1340030753459764, "grad_norm": 2.571425437927246, "learning_rate": 9.719395764441272e-05, "loss": 1.1657, "step": 2451 }, { "epoch": 0.13405774816333504, "grad_norm": 3.306361436843872, "learning_rate": 9.719103265763892e-05, "loss": 1.0527, "step": 2452 }, { "epoch": 0.13411242098069368, "grad_norm": 2.90105938911438, "learning_rate": 9.718810619123189e-05, "loss": 1.4497, "step": 2453 }, { "epoch": 0.13416709379805228, "grad_norm": 3.4533419609069824, "learning_rate": 9.718517824528339e-05, "loss": 0.9566, "step": 2454 }, { "epoch": 0.1342217666154109, "grad_norm": 3.093214273452759, "learning_rate": 9.71822488198852e-05, "loss": 1.1708, "step": 2455 }, { "epoch": 0.1342764394327695, "grad_norm": 3.1950979232788086, "learning_rate": 9.717931791512923e-05, "loss": 1.4836, "step": 2456 }, { "epoch": 0.13433111225012814, "grad_norm": 2.7514126300811768, "learning_rate": 9.717638553110732e-05, "loss": 1.2496, "step": 2457 }, { "epoch": 0.13438578506748675, "grad_norm": 2.430166482925415, "learning_rate": 9.717345166791143e-05, "loss": 1.1139, "step": 2458 }, { "epoch": 0.13444045788484538, "grad_norm": 2.8079817295074463, "learning_rate": 9.717051632563354e-05, "loss": 1.3736, "step": 2459 }, { "epoch": 0.134495130702204, "grad_norm": 2.7502329349517822, "learning_rate": 9.716757950436572e-05, "loss": 1.0765, "step": 2460 }, { "epoch": 0.1345498035195626, "grad_norm": 2.3222768306732178, "learning_rate": 9.716464120420001e-05, "loss": 1.1619, "step": 2461 }, { "epoch": 0.13460447633692124, "grad_norm": 2.9098479747772217, "learning_rate": 9.716170142522856e-05, "loss": 1.2331, "step": 2462 }, { "epoch": 0.13465914915427984, "grad_norm": 2.1160879135131836, "learning_rate": 9.715876016754353e-05, "loss": 1.0472, "step": 2463 }, { "epoch": 0.13471382197163848, "grad_norm": 2.6244301795959473, "learning_rate": 9.715581743123715e-05, "loss": 1.304, "step": 2464 }, { "epoch": 0.1347684947889971, "grad_norm": 2.208228349685669, "learning_rate": 9.71528732164017e-05, "loss": 1.2087, "step": 2465 }, { "epoch": 0.1348231676063557, "grad_norm": 2.445863962173462, "learning_rate": 9.714992752312946e-05, "loss": 1.1171, "step": 2466 }, { "epoch": 0.13487784042371434, "grad_norm": 2.8905153274536133, "learning_rate": 9.714698035151281e-05, "loss": 1.2281, "step": 2467 }, { "epoch": 0.13493251324107294, "grad_norm": 2.5998313426971436, "learning_rate": 9.714403170164416e-05, "loss": 1.242, "step": 2468 }, { "epoch": 0.13498718605843157, "grad_norm": 2.2290658950805664, "learning_rate": 9.714108157361597e-05, "loss": 1.2413, "step": 2469 }, { "epoch": 0.1350418588757902, "grad_norm": 4.470305442810059, "learning_rate": 9.713812996752069e-05, "loss": 1.2056, "step": 2470 }, { "epoch": 0.1350965316931488, "grad_norm": 3.670459747314453, "learning_rate": 9.713517688345093e-05, "loss": 1.148, "step": 2471 }, { "epoch": 0.13515120451050744, "grad_norm": 2.419490337371826, "learning_rate": 9.713222232149925e-05, "loss": 1.1272, "step": 2472 }, { "epoch": 0.13520587732786604, "grad_norm": 3.4044816493988037, "learning_rate": 9.712926628175828e-05, "loss": 1.2795, "step": 2473 }, { "epoch": 0.13526055014522467, "grad_norm": 3.770841360092163, "learning_rate": 9.712630876432072e-05, "loss": 1.4723, "step": 2474 }, { "epoch": 0.1353152229625833, "grad_norm": 2.4612531661987305, "learning_rate": 9.712334976927928e-05, "loss": 1.0923, "step": 2475 }, { "epoch": 0.1353698957799419, "grad_norm": 2.2743563652038574, "learning_rate": 9.712038929672678e-05, "loss": 1.1367, "step": 2476 }, { "epoch": 0.13542456859730054, "grad_norm": 1.9740891456604004, "learning_rate": 9.711742734675599e-05, "loss": 1.1703, "step": 2477 }, { "epoch": 0.13547924141465914, "grad_norm": 2.346616744995117, "learning_rate": 9.711446391945979e-05, "loss": 1.3221, "step": 2478 }, { "epoch": 0.13553391423201777, "grad_norm": 2.686964273452759, "learning_rate": 9.711149901493114e-05, "loss": 1.1973, "step": 2479 }, { "epoch": 0.13558858704937637, "grad_norm": 2.640040159225464, "learning_rate": 9.710853263326295e-05, "loss": 1.1847, "step": 2480 }, { "epoch": 0.135643259866735, "grad_norm": 3.4144208431243896, "learning_rate": 9.710556477454827e-05, "loss": 1.2306, "step": 2481 }, { "epoch": 0.13569793268409364, "grad_norm": 2.5118067264556885, "learning_rate": 9.710259543888011e-05, "loss": 1.2314, "step": 2482 }, { "epoch": 0.13575260550145224, "grad_norm": 3.0827996730804443, "learning_rate": 9.70996246263516e-05, "loss": 1.1224, "step": 2483 }, { "epoch": 0.13580727831881087, "grad_norm": 3.0672600269317627, "learning_rate": 9.709665233705588e-05, "loss": 1.1028, "step": 2484 }, { "epoch": 0.13586195113616947, "grad_norm": 2.3719732761383057, "learning_rate": 9.709367857108615e-05, "loss": 1.1787, "step": 2485 }, { "epoch": 0.1359166239535281, "grad_norm": 2.874037027359009, "learning_rate": 9.709070332853565e-05, "loss": 1.1063, "step": 2486 }, { "epoch": 0.13597129677088673, "grad_norm": 2.4075136184692383, "learning_rate": 9.708772660949765e-05, "loss": 0.9673, "step": 2487 }, { "epoch": 0.13602596958824534, "grad_norm": 2.8021817207336426, "learning_rate": 9.70847484140655e-05, "loss": 1.1294, "step": 2488 }, { "epoch": 0.13608064240560397, "grad_norm": 2.948164939880371, "learning_rate": 9.708176874233257e-05, "loss": 1.0444, "step": 2489 }, { "epoch": 0.13613531522296257, "grad_norm": 2.9791133403778076, "learning_rate": 9.707878759439229e-05, "loss": 0.8892, "step": 2490 }, { "epoch": 0.1361899880403212, "grad_norm": 2.7042839527130127, "learning_rate": 9.707580497033812e-05, "loss": 1.2751, "step": 2491 }, { "epoch": 0.13624466085767983, "grad_norm": 2.2523398399353027, "learning_rate": 9.707282087026359e-05, "loss": 1.3019, "step": 2492 }, { "epoch": 0.13629933367503844, "grad_norm": 2.6830379962921143, "learning_rate": 9.706983529426225e-05, "loss": 1.4079, "step": 2493 }, { "epoch": 0.13635400649239707, "grad_norm": 3.106304168701172, "learning_rate": 9.706684824242774e-05, "loss": 1.3092, "step": 2494 }, { "epoch": 0.13640867930975567, "grad_norm": 2.7277004718780518, "learning_rate": 9.706385971485367e-05, "loss": 1.2562, "step": 2495 }, { "epoch": 0.1364633521271143, "grad_norm": 3.032376289367676, "learning_rate": 9.70608697116338e-05, "loss": 1.4565, "step": 2496 }, { "epoch": 0.13651802494447293, "grad_norm": 3.9209821224212646, "learning_rate": 9.705787823286183e-05, "loss": 1.0407, "step": 2497 }, { "epoch": 0.13657269776183154, "grad_norm": 3.6684210300445557, "learning_rate": 9.705488527863158e-05, "loss": 1.1912, "step": 2498 }, { "epoch": 0.13662737057919017, "grad_norm": 2.954439401626587, "learning_rate": 9.705189084903688e-05, "loss": 1.3601, "step": 2499 }, { "epoch": 0.13668204339654877, "grad_norm": 3.1324307918548584, "learning_rate": 9.704889494417162e-05, "loss": 1.3957, "step": 2500 }, { "epoch": 0.1367367162139074, "grad_norm": 2.9238810539245605, "learning_rate": 9.704589756412973e-05, "loss": 1.052, "step": 2501 }, { "epoch": 0.13679138903126603, "grad_norm": 3.0702672004699707, "learning_rate": 9.70428987090052e-05, "loss": 1.1819, "step": 2502 }, { "epoch": 0.13684606184862463, "grad_norm": 4.795729637145996, "learning_rate": 9.703989837889206e-05, "loss": 1.2826, "step": 2503 }, { "epoch": 0.13690073466598326, "grad_norm": 2.6208269596099854, "learning_rate": 9.703689657388437e-05, "loss": 1.2986, "step": 2504 }, { "epoch": 0.13695540748334187, "grad_norm": 2.57900071144104, "learning_rate": 9.703389329407625e-05, "loss": 1.1888, "step": 2505 }, { "epoch": 0.1370100803007005, "grad_norm": 3.3245227336883545, "learning_rate": 9.703088853956188e-05, "loss": 1.4869, "step": 2506 }, { "epoch": 0.1370647531180591, "grad_norm": 2.5994155406951904, "learning_rate": 9.702788231043545e-05, "loss": 1.3544, "step": 2507 }, { "epoch": 0.13711942593541773, "grad_norm": 4.934140205383301, "learning_rate": 9.702487460679124e-05, "loss": 1.1393, "step": 2508 }, { "epoch": 0.13717409875277636, "grad_norm": 2.681506872177124, "learning_rate": 9.702186542872354e-05, "loss": 1.1146, "step": 2509 }, { "epoch": 0.13722877157013497, "grad_norm": 2.4622621536254883, "learning_rate": 9.701885477632669e-05, "loss": 1.2134, "step": 2510 }, { "epoch": 0.1372834443874936, "grad_norm": 2.9091293811798096, "learning_rate": 9.70158426496951e-05, "loss": 1.2052, "step": 2511 }, { "epoch": 0.1373381172048522, "grad_norm": 1.9908561706542969, "learning_rate": 9.701282904892322e-05, "loss": 1.0037, "step": 2512 }, { "epoch": 0.13739279002221083, "grad_norm": 2.4007744789123535, "learning_rate": 9.700981397410553e-05, "loss": 1.2687, "step": 2513 }, { "epoch": 0.13744746283956946, "grad_norm": 2.517925262451172, "learning_rate": 9.700679742533656e-05, "loss": 1.2513, "step": 2514 }, { "epoch": 0.13750213565692807, "grad_norm": 2.9341697692871094, "learning_rate": 9.70037794027109e-05, "loss": 1.4288, "step": 2515 }, { "epoch": 0.1375568084742867, "grad_norm": 2.4429194927215576, "learning_rate": 9.700075990632318e-05, "loss": 1.2237, "step": 2516 }, { "epoch": 0.1376114812916453, "grad_norm": 2.9150116443634033, "learning_rate": 9.699773893626806e-05, "loss": 1.132, "step": 2517 }, { "epoch": 0.13766615410900393, "grad_norm": 2.6775221824645996, "learning_rate": 9.699471649264027e-05, "loss": 1.038, "step": 2518 }, { "epoch": 0.13772082692636256, "grad_norm": 2.3867130279541016, "learning_rate": 9.699169257553458e-05, "loss": 1.1591, "step": 2519 }, { "epoch": 0.13777549974372116, "grad_norm": 2.379812002182007, "learning_rate": 9.698866718504578e-05, "loss": 1.1124, "step": 2520 }, { "epoch": 0.1378301725610798, "grad_norm": 3.184605598449707, "learning_rate": 9.698564032126875e-05, "loss": 1.4147, "step": 2521 }, { "epoch": 0.1378848453784384, "grad_norm": 2.680893898010254, "learning_rate": 9.698261198429839e-05, "loss": 1.3262, "step": 2522 }, { "epoch": 0.13793951819579703, "grad_norm": 3.0726189613342285, "learning_rate": 9.697958217422965e-05, "loss": 1.3066, "step": 2523 }, { "epoch": 0.13799419101315566, "grad_norm": 2.8268048763275146, "learning_rate": 9.697655089115754e-05, "loss": 1.4437, "step": 2524 }, { "epoch": 0.13804886383051426, "grad_norm": 2.658485174179077, "learning_rate": 9.697351813517706e-05, "loss": 1.1746, "step": 2525 }, { "epoch": 0.1381035366478729, "grad_norm": 2.7561490535736084, "learning_rate": 9.697048390638335e-05, "loss": 1.2751, "step": 2526 }, { "epoch": 0.1381582094652315, "grad_norm": 2.6356801986694336, "learning_rate": 9.696744820487153e-05, "loss": 1.3536, "step": 2527 }, { "epoch": 0.13821288228259013, "grad_norm": 2.649775981903076, "learning_rate": 9.696441103073677e-05, "loss": 1.1461, "step": 2528 }, { "epoch": 0.13826755509994876, "grad_norm": 2.8048412799835205, "learning_rate": 9.69613723840743e-05, "loss": 1.3549, "step": 2529 }, { "epoch": 0.13832222791730736, "grad_norm": 2.4008357524871826, "learning_rate": 9.69583322649794e-05, "loss": 1.1386, "step": 2530 }, { "epoch": 0.138376900734666, "grad_norm": 2.1891469955444336, "learning_rate": 9.695529067354739e-05, "loss": 0.9152, "step": 2531 }, { "epoch": 0.1384315735520246, "grad_norm": 2.5453009605407715, "learning_rate": 9.695224760987362e-05, "loss": 0.8484, "step": 2532 }, { "epoch": 0.13848624636938323, "grad_norm": 2.9346542358398438, "learning_rate": 9.694920307405354e-05, "loss": 1.3125, "step": 2533 }, { "epoch": 0.13854091918674183, "grad_norm": 3.1741814613342285, "learning_rate": 9.694615706618257e-05, "loss": 1.2435, "step": 2534 }, { "epoch": 0.13859559200410046, "grad_norm": 2.4932656288146973, "learning_rate": 9.694310958635625e-05, "loss": 1.1206, "step": 2535 }, { "epoch": 0.1386502648214591, "grad_norm": 3.103329658508301, "learning_rate": 9.69400606346701e-05, "loss": 1.3944, "step": 2536 }, { "epoch": 0.1387049376388177, "grad_norm": 2.517487049102783, "learning_rate": 9.693701021121974e-05, "loss": 1.1126, "step": 2537 }, { "epoch": 0.13875961045617632, "grad_norm": 3.230497121810913, "learning_rate": 9.693395831610079e-05, "loss": 1.2232, "step": 2538 }, { "epoch": 0.13881428327353493, "grad_norm": 2.2657358646392822, "learning_rate": 9.693090494940897e-05, "loss": 1.1652, "step": 2539 }, { "epoch": 0.13886895609089356, "grad_norm": 2.3794431686401367, "learning_rate": 9.692785011123998e-05, "loss": 1.1935, "step": 2540 }, { "epoch": 0.1389236289082522, "grad_norm": 2.784278392791748, "learning_rate": 9.692479380168962e-05, "loss": 1.2548, "step": 2541 }, { "epoch": 0.1389783017256108, "grad_norm": 2.811981439590454, "learning_rate": 9.692173602085372e-05, "loss": 1.2107, "step": 2542 }, { "epoch": 0.13903297454296942, "grad_norm": 2.75136661529541, "learning_rate": 9.691867676882816e-05, "loss": 1.3933, "step": 2543 }, { "epoch": 0.13908764736032803, "grad_norm": 2.7969985008239746, "learning_rate": 9.691561604570885e-05, "loss": 1.2074, "step": 2544 }, { "epoch": 0.13914232017768666, "grad_norm": 2.535810947418213, "learning_rate": 9.691255385159176e-05, "loss": 1.2488, "step": 2545 }, { "epoch": 0.1391969929950453, "grad_norm": 2.7578930854797363, "learning_rate": 9.69094901865729e-05, "loss": 1.3116, "step": 2546 }, { "epoch": 0.1392516658124039, "grad_norm": 3.767651081085205, "learning_rate": 9.690642505074831e-05, "loss": 1.1852, "step": 2547 }, { "epoch": 0.13930633862976252, "grad_norm": 2.285776138305664, "learning_rate": 9.690335844421415e-05, "loss": 1.2546, "step": 2548 }, { "epoch": 0.13936101144712112, "grad_norm": 2.239151954650879, "learning_rate": 9.69002903670665e-05, "loss": 1.0307, "step": 2549 }, { "epoch": 0.13941568426447976, "grad_norm": 3.2796790599823, "learning_rate": 9.689722081940161e-05, "loss": 1.4114, "step": 2550 }, { "epoch": 0.1394703570818384, "grad_norm": 5.182728290557861, "learning_rate": 9.68941498013157e-05, "loss": 1.2032, "step": 2551 }, { "epoch": 0.139525029899197, "grad_norm": 2.4776482582092285, "learning_rate": 9.689107731290507e-05, "loss": 1.254, "step": 2552 }, { "epoch": 0.13957970271655562, "grad_norm": 3.2668204307556152, "learning_rate": 9.688800335426604e-05, "loss": 1.398, "step": 2553 }, { "epoch": 0.13963437553391422, "grad_norm": 2.5686464309692383, "learning_rate": 9.688492792549499e-05, "loss": 1.1631, "step": 2554 }, { "epoch": 0.13968904835127285, "grad_norm": 2.2997066974639893, "learning_rate": 9.688185102668838e-05, "loss": 1.1395, "step": 2555 }, { "epoch": 0.13974372116863146, "grad_norm": 2.997830867767334, "learning_rate": 9.687877265794265e-05, "loss": 1.2941, "step": 2556 }, { "epoch": 0.1397983939859901, "grad_norm": 1.8610848188400269, "learning_rate": 9.687569281935432e-05, "loss": 0.9765, "step": 2557 }, { "epoch": 0.13985306680334872, "grad_norm": 2.455756425857544, "learning_rate": 9.687261151101998e-05, "loss": 1.3387, "step": 2558 }, { "epoch": 0.13990773962070732, "grad_norm": 4.312567234039307, "learning_rate": 9.686952873303623e-05, "loss": 0.9823, "step": 2559 }, { "epoch": 0.13996241243806595, "grad_norm": 2.9298980236053467, "learning_rate": 9.686644448549971e-05, "loss": 1.1754, "step": 2560 }, { "epoch": 0.14001708525542456, "grad_norm": 2.2732293605804443, "learning_rate": 9.686335876850716e-05, "loss": 1.0615, "step": 2561 }, { "epoch": 0.1400717580727832, "grad_norm": 2.5426111221313477, "learning_rate": 9.686027158215529e-05, "loss": 0.9515, "step": 2562 }, { "epoch": 0.14012643089014182, "grad_norm": 2.32326340675354, "learning_rate": 9.685718292654091e-05, "loss": 0.9634, "step": 2563 }, { "epoch": 0.14018110370750042, "grad_norm": 4.085017204284668, "learning_rate": 9.685409280176088e-05, "loss": 1.3141, "step": 2564 }, { "epoch": 0.14023577652485905, "grad_norm": 2.4764413833618164, "learning_rate": 9.685100120791208e-05, "loss": 1.0093, "step": 2565 }, { "epoch": 0.14029044934221765, "grad_norm": 2.769397497177124, "learning_rate": 9.684790814509144e-05, "loss": 1.1732, "step": 2566 }, { "epoch": 0.14034512215957629, "grad_norm": 2.4652352333068848, "learning_rate": 9.684481361339592e-05, "loss": 1.1546, "step": 2567 }, { "epoch": 0.14039979497693492, "grad_norm": 2.647388458251953, "learning_rate": 9.684171761292258e-05, "loss": 1.4377, "step": 2568 }, { "epoch": 0.14045446779429352, "grad_norm": 3.187009334564209, "learning_rate": 9.683862014376847e-05, "loss": 1.2607, "step": 2569 }, { "epoch": 0.14050914061165215, "grad_norm": 2.3718278408050537, "learning_rate": 9.683552120603074e-05, "loss": 1.0416, "step": 2570 }, { "epoch": 0.14056381342901075, "grad_norm": 3.572965621948242, "learning_rate": 9.683242079980651e-05, "loss": 1.0356, "step": 2571 }, { "epoch": 0.14061848624636938, "grad_norm": 2.843700647354126, "learning_rate": 9.682931892519302e-05, "loss": 1.3691, "step": 2572 }, { "epoch": 0.14067315906372801, "grad_norm": 2.9946680068969727, "learning_rate": 9.682621558228752e-05, "loss": 1.2786, "step": 2573 }, { "epoch": 0.14072783188108662, "grad_norm": 2.3386433124542236, "learning_rate": 9.682311077118731e-05, "loss": 1.0329, "step": 2574 }, { "epoch": 0.14078250469844525, "grad_norm": 2.620063066482544, "learning_rate": 9.682000449198973e-05, "loss": 1.0516, "step": 2575 }, { "epoch": 0.14083717751580385, "grad_norm": 3.688831090927124, "learning_rate": 9.68168967447922e-05, "loss": 1.2063, "step": 2576 }, { "epoch": 0.14089185033316248, "grad_norm": 2.8194925785064697, "learning_rate": 9.681378752969212e-05, "loss": 1.2545, "step": 2577 }, { "epoch": 0.1409465231505211, "grad_norm": 2.540987014770508, "learning_rate": 9.681067684678702e-05, "loss": 1.3711, "step": 2578 }, { "epoch": 0.14100119596787972, "grad_norm": 2.5950522422790527, "learning_rate": 9.680756469617442e-05, "loss": 1.1367, "step": 2579 }, { "epoch": 0.14105586878523835, "grad_norm": 2.2104408740997314, "learning_rate": 9.680445107795189e-05, "loss": 1.3273, "step": 2580 }, { "epoch": 0.14111054160259695, "grad_norm": 2.6727302074432373, "learning_rate": 9.680133599221704e-05, "loss": 1.2017, "step": 2581 }, { "epoch": 0.14116521441995558, "grad_norm": 3.7067995071411133, "learning_rate": 9.679821943906757e-05, "loss": 0.9127, "step": 2582 }, { "epoch": 0.14121988723731418, "grad_norm": 2.8616113662719727, "learning_rate": 9.67951014186012e-05, "loss": 1.3739, "step": 2583 }, { "epoch": 0.14127456005467282, "grad_norm": 2.695082902908325, "learning_rate": 9.679198193091565e-05, "loss": 1.1733, "step": 2584 }, { "epoch": 0.14132923287203145, "grad_norm": 2.4037864208221436, "learning_rate": 9.678886097610878e-05, "loss": 1.2177, "step": 2585 }, { "epoch": 0.14138390568939005, "grad_norm": 2.5906543731689453, "learning_rate": 9.678573855427842e-05, "loss": 1.3827, "step": 2586 }, { "epoch": 0.14143857850674868, "grad_norm": 2.4067957401275635, "learning_rate": 9.678261466552246e-05, "loss": 1.0708, "step": 2587 }, { "epoch": 0.14149325132410728, "grad_norm": 2.9281883239746094, "learning_rate": 9.677948930993886e-05, "loss": 1.1985, "step": 2588 }, { "epoch": 0.14154792414146591, "grad_norm": 2.5166375637054443, "learning_rate": 9.677636248762562e-05, "loss": 1.1898, "step": 2589 }, { "epoch": 0.14160259695882454, "grad_norm": 2.7880616188049316, "learning_rate": 9.677323419868076e-05, "loss": 1.2882, "step": 2590 }, { "epoch": 0.14165726977618315, "grad_norm": 2.3991167545318604, "learning_rate": 9.677010444320237e-05, "loss": 1.1834, "step": 2591 }, { "epoch": 0.14171194259354178, "grad_norm": 2.485356092453003, "learning_rate": 9.676697322128862e-05, "loss": 0.9714, "step": 2592 }, { "epoch": 0.14176661541090038, "grad_norm": 3.1405253410339355, "learning_rate": 9.676384053303762e-05, "loss": 1.0179, "step": 2593 }, { "epoch": 0.141821288228259, "grad_norm": 3.099097728729248, "learning_rate": 9.676070637854764e-05, "loss": 1.2289, "step": 2594 }, { "epoch": 0.14187596104561764, "grad_norm": 3.954411029815674, "learning_rate": 9.675757075791694e-05, "loss": 1.3683, "step": 2595 }, { "epoch": 0.14193063386297625, "grad_norm": 3.2042529582977295, "learning_rate": 9.675443367124382e-05, "loss": 1.2423, "step": 2596 }, { "epoch": 0.14198530668033488, "grad_norm": 2.298722743988037, "learning_rate": 9.675129511862665e-05, "loss": 1.0571, "step": 2597 }, { "epoch": 0.14203997949769348, "grad_norm": 2.9176716804504395, "learning_rate": 9.674815510016383e-05, "loss": 1.2751, "step": 2598 }, { "epoch": 0.1420946523150521, "grad_norm": 3.094783067703247, "learning_rate": 9.674501361595383e-05, "loss": 1.158, "step": 2599 }, { "epoch": 0.14214932513241074, "grad_norm": 2.3895089626312256, "learning_rate": 9.674187066609513e-05, "loss": 0.9661, "step": 2600 }, { "epoch": 0.14220399794976935, "grad_norm": 2.258237361907959, "learning_rate": 9.673872625068628e-05, "loss": 1.1088, "step": 2601 }, { "epoch": 0.14225867076712798, "grad_norm": 2.4388952255249023, "learning_rate": 9.673558036982589e-05, "loss": 1.1897, "step": 2602 }, { "epoch": 0.14231334358448658, "grad_norm": 4.0305023193359375, "learning_rate": 9.673243302361255e-05, "loss": 1.2878, "step": 2603 }, { "epoch": 0.1423680164018452, "grad_norm": 3.1855385303497314, "learning_rate": 9.672928421214499e-05, "loss": 1.1748, "step": 2604 }, { "epoch": 0.14242268921920384, "grad_norm": 2.881788730621338, "learning_rate": 9.672613393552192e-05, "loss": 1.2282, "step": 2605 }, { "epoch": 0.14247736203656244, "grad_norm": 2.8861663341522217, "learning_rate": 9.672298219384209e-05, "loss": 1.0347, "step": 2606 }, { "epoch": 0.14253203485392107, "grad_norm": 2.3911635875701904, "learning_rate": 9.671982898720437e-05, "loss": 1.2161, "step": 2607 }, { "epoch": 0.14258670767127968, "grad_norm": 2.6215264797210693, "learning_rate": 9.671667431570757e-05, "loss": 1.0621, "step": 2608 }, { "epoch": 0.1426413804886383, "grad_norm": 2.13920259475708, "learning_rate": 9.671351817945066e-05, "loss": 1.0883, "step": 2609 }, { "epoch": 0.1426960533059969, "grad_norm": 2.1463706493377686, "learning_rate": 9.671036057853255e-05, "loss": 1.1587, "step": 2610 }, { "epoch": 0.14275072612335554, "grad_norm": 3.3528406620025635, "learning_rate": 9.670720151305226e-05, "loss": 1.2577, "step": 2611 }, { "epoch": 0.14280539894071417, "grad_norm": 3.1773886680603027, "learning_rate": 9.670404098310886e-05, "loss": 0.9451, "step": 2612 }, { "epoch": 0.14286007175807278, "grad_norm": 2.415973424911499, "learning_rate": 9.670087898880143e-05, "loss": 1.1336, "step": 2613 }, { "epoch": 0.1429147445754314, "grad_norm": 3.7465243339538574, "learning_rate": 9.669771553022909e-05, "loss": 1.2814, "step": 2614 }, { "epoch": 0.14296941739279, "grad_norm": 2.4550607204437256, "learning_rate": 9.669455060749106e-05, "loss": 1.0908, "step": 2615 }, { "epoch": 0.14302409021014864, "grad_norm": 3.3298044204711914, "learning_rate": 9.669138422068656e-05, "loss": 0.8328, "step": 2616 }, { "epoch": 0.14307876302750727, "grad_norm": 2.5709216594696045, "learning_rate": 9.668821636991486e-05, "loss": 1.1621, "step": 2617 }, { "epoch": 0.14313343584486588, "grad_norm": 2.087970733642578, "learning_rate": 9.668504705527529e-05, "loss": 1.0932, "step": 2618 }, { "epoch": 0.1431881086622245, "grad_norm": 2.358309745788574, "learning_rate": 9.668187627686725e-05, "loss": 1.0549, "step": 2619 }, { "epoch": 0.1432427814795831, "grad_norm": 2.8178508281707764, "learning_rate": 9.667870403479011e-05, "loss": 1.3645, "step": 2620 }, { "epoch": 0.14329745429694174, "grad_norm": 4.090738296508789, "learning_rate": 9.667553032914336e-05, "loss": 1.3692, "step": 2621 }, { "epoch": 0.14335212711430037, "grad_norm": 2.9479000568389893, "learning_rate": 9.667235516002651e-05, "loss": 1.0784, "step": 2622 }, { "epoch": 0.14340679993165897, "grad_norm": 2.383580207824707, "learning_rate": 9.66691785275391e-05, "loss": 1.074, "step": 2623 }, { "epoch": 0.1434614727490176, "grad_norm": 2.5413196086883545, "learning_rate": 9.666600043178075e-05, "loss": 1.3025, "step": 2624 }, { "epoch": 0.1435161455663762, "grad_norm": 3.2545957565307617, "learning_rate": 9.666282087285107e-05, "loss": 1.2894, "step": 2625 }, { "epoch": 0.14357081838373484, "grad_norm": 2.11566424369812, "learning_rate": 9.665963985084982e-05, "loss": 0.9891, "step": 2626 }, { "epoch": 0.14362549120109347, "grad_norm": 2.61551570892334, "learning_rate": 9.665645736587668e-05, "loss": 0.9163, "step": 2627 }, { "epoch": 0.14368016401845207, "grad_norm": 2.3663485050201416, "learning_rate": 9.665327341803143e-05, "loss": 1.018, "step": 2628 }, { "epoch": 0.1437348368358107, "grad_norm": 2.559213638305664, "learning_rate": 9.665008800741394e-05, "loss": 1.3609, "step": 2629 }, { "epoch": 0.1437895096531693, "grad_norm": 2.6833138465881348, "learning_rate": 9.664690113412406e-05, "loss": 1.076, "step": 2630 }, { "epoch": 0.14384418247052794, "grad_norm": 2.8994178771972656, "learning_rate": 9.664371279826172e-05, "loss": 1.1174, "step": 2631 }, { "epoch": 0.14389885528788654, "grad_norm": 2.592900037765503, "learning_rate": 9.664052299992689e-05, "loss": 1.0612, "step": 2632 }, { "epoch": 0.14395352810524517, "grad_norm": 4.411976337432861, "learning_rate": 9.663733173921957e-05, "loss": 1.286, "step": 2633 }, { "epoch": 0.1440082009226038, "grad_norm": 2.892045497894287, "learning_rate": 9.663413901623983e-05, "loss": 1.2228, "step": 2634 }, { "epoch": 0.1440628737399624, "grad_norm": 2.8214902877807617, "learning_rate": 9.663094483108777e-05, "loss": 1.179, "step": 2635 }, { "epoch": 0.14411754655732104, "grad_norm": 3.225001573562622, "learning_rate": 9.662774918386354e-05, "loss": 1.3451, "step": 2636 }, { "epoch": 0.14417221937467964, "grad_norm": 2.690248966217041, "learning_rate": 9.662455207466734e-05, "loss": 1.2716, "step": 2637 }, { "epoch": 0.14422689219203827, "grad_norm": 2.407762050628662, "learning_rate": 9.662135350359942e-05, "loss": 1.2428, "step": 2638 }, { "epoch": 0.1442815650093969, "grad_norm": 2.5987517833709717, "learning_rate": 9.661815347076007e-05, "loss": 1.1062, "step": 2639 }, { "epoch": 0.1443362378267555, "grad_norm": 2.772397756576538, "learning_rate": 9.661495197624959e-05, "loss": 1.2413, "step": 2640 }, { "epoch": 0.14439091064411413, "grad_norm": 2.5583510398864746, "learning_rate": 9.66117490201684e-05, "loss": 1.3502, "step": 2641 }, { "epoch": 0.14444558346147274, "grad_norm": 2.683321237564087, "learning_rate": 9.66085446026169e-05, "loss": 1.416, "step": 2642 }, { "epoch": 0.14450025627883137, "grad_norm": 4.21413516998291, "learning_rate": 9.660533872369559e-05, "loss": 1.2941, "step": 2643 }, { "epoch": 0.14455492909619, "grad_norm": 2.8731696605682373, "learning_rate": 9.660213138350495e-05, "loss": 1.334, "step": 2644 }, { "epoch": 0.1446096019135486, "grad_norm": 2.036329746246338, "learning_rate": 9.659892258214558e-05, "loss": 0.9686, "step": 2645 }, { "epoch": 0.14466427473090723, "grad_norm": 2.5934109687805176, "learning_rate": 9.659571231971807e-05, "loss": 1.2164, "step": 2646 }, { "epoch": 0.14471894754826584, "grad_norm": 2.966914653778076, "learning_rate": 9.659250059632307e-05, "loss": 1.1638, "step": 2647 }, { "epoch": 0.14477362036562447, "grad_norm": 2.9636037349700928, "learning_rate": 9.65892874120613e-05, "loss": 1.2503, "step": 2648 }, { "epoch": 0.1448282931829831, "grad_norm": 2.7000625133514404, "learning_rate": 9.658607276703349e-05, "loss": 1.407, "step": 2649 }, { "epoch": 0.1448829660003417, "grad_norm": 2.4200387001037598, "learning_rate": 9.658285666134043e-05, "loss": 1.0661, "step": 2650 }, { "epoch": 0.14493763881770033, "grad_norm": 3.2757694721221924, "learning_rate": 9.657963909508296e-05, "loss": 1.4043, "step": 2651 }, { "epoch": 0.14499231163505893, "grad_norm": 2.779061794281006, "learning_rate": 9.657642006836199e-05, "loss": 1.294, "step": 2652 }, { "epoch": 0.14504698445241757, "grad_norm": 2.0945703983306885, "learning_rate": 9.657319958127842e-05, "loss": 1.185, "step": 2653 }, { "epoch": 0.1451016572697762, "grad_norm": 2.1098544597625732, "learning_rate": 9.656997763393323e-05, "loss": 1.1391, "step": 2654 }, { "epoch": 0.1451563300871348, "grad_norm": 3.0990402698516846, "learning_rate": 9.656675422642744e-05, "loss": 1.3159, "step": 2655 }, { "epoch": 0.14521100290449343, "grad_norm": 2.3365564346313477, "learning_rate": 9.656352935886215e-05, "loss": 1.2107, "step": 2656 }, { "epoch": 0.14526567572185203, "grad_norm": 2.7363414764404297, "learning_rate": 9.656030303133842e-05, "loss": 1.217, "step": 2657 }, { "epoch": 0.14532034853921066, "grad_norm": 3.385660409927368, "learning_rate": 9.655707524395744e-05, "loss": 1.2936, "step": 2658 }, { "epoch": 0.14537502135656927, "grad_norm": 3.050760507583618, "learning_rate": 9.655384599682043e-05, "loss": 1.2203, "step": 2659 }, { "epoch": 0.1454296941739279, "grad_norm": 2.915323495864868, "learning_rate": 9.655061529002859e-05, "loss": 1.2765, "step": 2660 }, { "epoch": 0.14548436699128653, "grad_norm": 3.2257144451141357, "learning_rate": 9.654738312368326e-05, "loss": 1.2939, "step": 2661 }, { "epoch": 0.14553903980864513, "grad_norm": 2.9724957942962646, "learning_rate": 9.654414949788575e-05, "loss": 1.2236, "step": 2662 }, { "epoch": 0.14559371262600376, "grad_norm": 2.7549829483032227, "learning_rate": 9.65409144127375e-05, "loss": 1.2232, "step": 2663 }, { "epoch": 0.14564838544336237, "grad_norm": 4.9888596534729, "learning_rate": 9.653767786833987e-05, "loss": 1.3655, "step": 2664 }, { "epoch": 0.145703058260721, "grad_norm": 3.2602181434631348, "learning_rate": 9.653443986479439e-05, "loss": 1.1879, "step": 2665 }, { "epoch": 0.14575773107807963, "grad_norm": 2.34775447845459, "learning_rate": 9.653120040220258e-05, "loss": 1.2217, "step": 2666 }, { "epoch": 0.14581240389543823, "grad_norm": 2.158933639526367, "learning_rate": 9.6527959480666e-05, "loss": 1.1989, "step": 2667 }, { "epoch": 0.14586707671279686, "grad_norm": 2.5865306854248047, "learning_rate": 9.652471710028626e-05, "loss": 1.1389, "step": 2668 }, { "epoch": 0.14592174953015546, "grad_norm": 2.4027934074401855, "learning_rate": 9.652147326116503e-05, "loss": 1.039, "step": 2669 }, { "epoch": 0.1459764223475141, "grad_norm": 2.7259035110473633, "learning_rate": 9.651822796340401e-05, "loss": 1.3141, "step": 2670 }, { "epoch": 0.14603109516487273, "grad_norm": 2.606125831604004, "learning_rate": 9.651498120710498e-05, "loss": 1.1017, "step": 2671 }, { "epoch": 0.14608576798223133, "grad_norm": 2.4571609497070312, "learning_rate": 9.651173299236971e-05, "loss": 1.0763, "step": 2672 }, { "epoch": 0.14614044079958996, "grad_norm": 2.7996068000793457, "learning_rate": 9.650848331930006e-05, "loss": 1.3131, "step": 2673 }, { "epoch": 0.14619511361694856, "grad_norm": 3.8049206733703613, "learning_rate": 9.650523218799791e-05, "loss": 0.7853, "step": 2674 }, { "epoch": 0.1462497864343072, "grad_norm": 2.5408270359039307, "learning_rate": 9.65019795985652e-05, "loss": 1.1956, "step": 2675 }, { "epoch": 0.14630445925166582, "grad_norm": 3.4386422634124756, "learning_rate": 9.649872555110394e-05, "loss": 1.1386, "step": 2676 }, { "epoch": 0.14635913206902443, "grad_norm": 2.712651014328003, "learning_rate": 9.649547004571611e-05, "loss": 1.2235, "step": 2677 }, { "epoch": 0.14641380488638306, "grad_norm": 2.91253924369812, "learning_rate": 9.64922130825038e-05, "loss": 1.3807, "step": 2678 }, { "epoch": 0.14646847770374166, "grad_norm": 3.4821698665618896, "learning_rate": 9.648895466156915e-05, "loss": 1.1952, "step": 2679 }, { "epoch": 0.1465231505211003, "grad_norm": 3.2793023586273193, "learning_rate": 9.64856947830143e-05, "loss": 1.3758, "step": 2680 }, { "epoch": 0.14657782333845892, "grad_norm": 3.5823891162872314, "learning_rate": 9.648243344694147e-05, "loss": 1.0623, "step": 2681 }, { "epoch": 0.14663249615581753, "grad_norm": 2.0865895748138428, "learning_rate": 9.647917065345291e-05, "loss": 1.1372, "step": 2682 }, { "epoch": 0.14668716897317616, "grad_norm": 2.8424875736236572, "learning_rate": 9.647590640265093e-05, "loss": 1.127, "step": 2683 }, { "epoch": 0.14674184179053476, "grad_norm": 3.414565086364746, "learning_rate": 9.647264069463791e-05, "loss": 0.8632, "step": 2684 }, { "epoch": 0.1467965146078934, "grad_norm": 3.0753462314605713, "learning_rate": 9.646937352951617e-05, "loss": 1.3615, "step": 2685 }, { "epoch": 0.146851187425252, "grad_norm": 2.54318904876709, "learning_rate": 9.64661049073882e-05, "loss": 1.0536, "step": 2686 }, { "epoch": 0.14690586024261063, "grad_norm": 2.926490545272827, "learning_rate": 9.646283482835648e-05, "loss": 1.533, "step": 2687 }, { "epoch": 0.14696053305996926, "grad_norm": 2.923243999481201, "learning_rate": 9.645956329252355e-05, "loss": 0.8103, "step": 2688 }, { "epoch": 0.14701520587732786, "grad_norm": 3.848139524459839, "learning_rate": 9.645629029999194e-05, "loss": 1.1384, "step": 2689 }, { "epoch": 0.1470698786946865, "grad_norm": 2.4604742527008057, "learning_rate": 9.645301585086432e-05, "loss": 1.1122, "step": 2690 }, { "epoch": 0.1471245515120451, "grad_norm": 2.145197868347168, "learning_rate": 9.644973994524334e-05, "loss": 1.0652, "step": 2691 }, { "epoch": 0.14717922432940372, "grad_norm": 2.7883358001708984, "learning_rate": 9.64464625832317e-05, "loss": 1.0933, "step": 2692 }, { "epoch": 0.14723389714676235, "grad_norm": 5.470052719116211, "learning_rate": 9.644318376493217e-05, "loss": 1.376, "step": 2693 }, { "epoch": 0.14728856996412096, "grad_norm": 4.880026817321777, "learning_rate": 9.643990349044755e-05, "loss": 1.2918, "step": 2694 }, { "epoch": 0.1473432427814796, "grad_norm": 2.6512207984924316, "learning_rate": 9.643662175988073e-05, "loss": 1.3413, "step": 2695 }, { "epoch": 0.1473979155988382, "grad_norm": 2.1864378452301025, "learning_rate": 9.643333857333455e-05, "loss": 0.8925, "step": 2696 }, { "epoch": 0.14745258841619682, "grad_norm": 2.535369873046875, "learning_rate": 9.643005393091198e-05, "loss": 1.1712, "step": 2697 }, { "epoch": 0.14750726123355545, "grad_norm": 3.5793297290802, "learning_rate": 9.642676783271598e-05, "loss": 1.5206, "step": 2698 }, { "epoch": 0.14756193405091406, "grad_norm": 2.776611328125, "learning_rate": 9.642348027884962e-05, "loss": 1.1868, "step": 2699 }, { "epoch": 0.1476166068682727, "grad_norm": 3.0587947368621826, "learning_rate": 9.642019126941596e-05, "loss": 0.9047, "step": 2700 }, { "epoch": 0.1476712796856313, "grad_norm": 2.6060335636138916, "learning_rate": 9.641690080451813e-05, "loss": 1.2222, "step": 2701 }, { "epoch": 0.14772595250298992, "grad_norm": 2.604562282562256, "learning_rate": 9.641360888425928e-05, "loss": 1.1786, "step": 2702 }, { "epoch": 0.14778062532034855, "grad_norm": 3.485973834991455, "learning_rate": 9.641031550874266e-05, "loss": 1.1198, "step": 2703 }, { "epoch": 0.14783529813770716, "grad_norm": 2.4818074703216553, "learning_rate": 9.64070206780715e-05, "loss": 0.8898, "step": 2704 }, { "epoch": 0.14788997095506579, "grad_norm": 2.555957317352295, "learning_rate": 9.640372439234912e-05, "loss": 1.3575, "step": 2705 }, { "epoch": 0.1479446437724244, "grad_norm": 3.7139761447906494, "learning_rate": 9.640042665167887e-05, "loss": 1.2185, "step": 2706 }, { "epoch": 0.14799931658978302, "grad_norm": 2.945145845413208, "learning_rate": 9.639712745616413e-05, "loss": 1.284, "step": 2707 }, { "epoch": 0.14805398940714162, "grad_norm": 2.8403706550598145, "learning_rate": 9.639382680590838e-05, "loss": 1.0368, "step": 2708 }, { "epoch": 0.14810866222450025, "grad_norm": 2.190619468688965, "learning_rate": 9.639052470101509e-05, "loss": 1.2831, "step": 2709 }, { "epoch": 0.14816333504185888, "grad_norm": 2.790635108947754, "learning_rate": 9.638722114158779e-05, "loss": 1.2047, "step": 2710 }, { "epoch": 0.1482180078592175, "grad_norm": 2.9456942081451416, "learning_rate": 9.638391612773006e-05, "loss": 1.2169, "step": 2711 }, { "epoch": 0.14827268067657612, "grad_norm": 2.550530195236206, "learning_rate": 9.638060965954554e-05, "loss": 1.2077, "step": 2712 }, { "epoch": 0.14832735349393472, "grad_norm": 2.807201385498047, "learning_rate": 9.63773017371379e-05, "loss": 1.3122, "step": 2713 }, { "epoch": 0.14838202631129335, "grad_norm": 1.6814769506454468, "learning_rate": 9.637399236061082e-05, "loss": 1.0223, "step": 2714 }, { "epoch": 0.14843669912865198, "grad_norm": 2.6171367168426514, "learning_rate": 9.637068153006811e-05, "loss": 1.1459, "step": 2715 }, { "epoch": 0.1484913719460106, "grad_norm": 2.680626153945923, "learning_rate": 9.636736924561356e-05, "loss": 1.1506, "step": 2716 }, { "epoch": 0.14854604476336922, "grad_norm": 2.909864664077759, "learning_rate": 9.636405550735102e-05, "loss": 1.0518, "step": 2717 }, { "epoch": 0.14860071758072782, "grad_norm": 2.299182891845703, "learning_rate": 9.63607403153844e-05, "loss": 0.987, "step": 2718 }, { "epoch": 0.14865539039808645, "grad_norm": 2.6424291133880615, "learning_rate": 9.635742366981764e-05, "loss": 0.9587, "step": 2719 }, { "epoch": 0.14871006321544508, "grad_norm": 2.2251813411712646, "learning_rate": 9.63541055707547e-05, "loss": 1.1698, "step": 2720 }, { "epoch": 0.14876473603280368, "grad_norm": 2.3461697101593018, "learning_rate": 9.635078601829968e-05, "loss": 1.1614, "step": 2721 }, { "epoch": 0.14881940885016232, "grad_norm": 2.5264010429382324, "learning_rate": 9.634746501255661e-05, "loss": 1.3597, "step": 2722 }, { "epoch": 0.14887408166752092, "grad_norm": 2.5698649883270264, "learning_rate": 9.634414255362962e-05, "loss": 1.2587, "step": 2723 }, { "epoch": 0.14892875448487955, "grad_norm": 2.5925052165985107, "learning_rate": 9.63408186416229e-05, "loss": 1.1822, "step": 2724 }, { "epoch": 0.14898342730223818, "grad_norm": 2.275144100189209, "learning_rate": 9.633749327664068e-05, "loss": 1.1453, "step": 2725 }, { "epoch": 0.14903810011959678, "grad_norm": 2.867455005645752, "learning_rate": 9.63341664587872e-05, "loss": 1.1705, "step": 2726 }, { "epoch": 0.14909277293695541, "grad_norm": 4.642012596130371, "learning_rate": 9.633083818816678e-05, "loss": 1.0899, "step": 2727 }, { "epoch": 0.14914744575431402, "grad_norm": 4.138620853424072, "learning_rate": 9.632750846488376e-05, "loss": 1.0861, "step": 2728 }, { "epoch": 0.14920211857167265, "grad_norm": 3.09584379196167, "learning_rate": 9.632417728904257e-05, "loss": 1.2574, "step": 2729 }, { "epoch": 0.14925679138903128, "grad_norm": 2.2433204650878906, "learning_rate": 9.632084466074764e-05, "loss": 1.0046, "step": 2730 }, { "epoch": 0.14931146420638988, "grad_norm": 3.1027040481567383, "learning_rate": 9.631751058010344e-05, "loss": 1.2305, "step": 2731 }, { "epoch": 0.1493661370237485, "grad_norm": 2.701761245727539, "learning_rate": 9.631417504721454e-05, "loss": 1.3321, "step": 2732 }, { "epoch": 0.14942080984110712, "grad_norm": 2.6864936351776123, "learning_rate": 9.631083806218552e-05, "loss": 1.1222, "step": 2733 }, { "epoch": 0.14947548265846575, "grad_norm": 3.080955743789673, "learning_rate": 9.630749962512098e-05, "loss": 1.2985, "step": 2734 }, { "epoch": 0.14953015547582435, "grad_norm": 2.798328161239624, "learning_rate": 9.630415973612563e-05, "loss": 1.1198, "step": 2735 }, { "epoch": 0.14958482829318298, "grad_norm": 3.381042242050171, "learning_rate": 9.630081839530416e-05, "loss": 1.314, "step": 2736 }, { "epoch": 0.1496395011105416, "grad_norm": 2.711793899536133, "learning_rate": 9.629747560276135e-05, "loss": 1.2514, "step": 2737 }, { "epoch": 0.14969417392790021, "grad_norm": 2.5234498977661133, "learning_rate": 9.629413135860201e-05, "loss": 1.2175, "step": 2738 }, { "epoch": 0.14974884674525885, "grad_norm": 2.473778247833252, "learning_rate": 9.6290785662931e-05, "loss": 1.2583, "step": 2739 }, { "epoch": 0.14980351956261745, "grad_norm": 2.59407114982605, "learning_rate": 9.62874385158532e-05, "loss": 1.299, "step": 2740 }, { "epoch": 0.14985819237997608, "grad_norm": 2.1623032093048096, "learning_rate": 9.628408991747357e-05, "loss": 1.1948, "step": 2741 }, { "epoch": 0.1499128651973347, "grad_norm": 2.670290470123291, "learning_rate": 9.628073986789711e-05, "loss": 1.2449, "step": 2742 }, { "epoch": 0.1499675380146933, "grad_norm": 2.4772818088531494, "learning_rate": 9.627738836722884e-05, "loss": 1.2164, "step": 2743 }, { "epoch": 0.15002221083205194, "grad_norm": 2.5122861862182617, "learning_rate": 9.627403541557387e-05, "loss": 0.9774, "step": 2744 }, { "epoch": 0.15007688364941055, "grad_norm": 2.245208978652954, "learning_rate": 9.627068101303732e-05, "loss": 1.1534, "step": 2745 }, { "epoch": 0.15013155646676918, "grad_norm": 2.735213041305542, "learning_rate": 9.626732515972433e-05, "loss": 1.13, "step": 2746 }, { "epoch": 0.1501862292841278, "grad_norm": 2.394698143005371, "learning_rate": 9.626396785574017e-05, "loss": 1.0301, "step": 2747 }, { "epoch": 0.1502409021014864, "grad_norm": 2.9060654640197754, "learning_rate": 9.626060910119008e-05, "loss": 1.3198, "step": 2748 }, { "epoch": 0.15029557491884504, "grad_norm": 1.8617892265319824, "learning_rate": 9.625724889617935e-05, "loss": 1.0623, "step": 2749 }, { "epoch": 0.15035024773620365, "grad_norm": 2.476884126663208, "learning_rate": 9.625388724081339e-05, "loss": 1.3077, "step": 2750 }, { "epoch": 0.15040492055356228, "grad_norm": 2.537691354751587, "learning_rate": 9.625052413519755e-05, "loss": 1.2698, "step": 2751 }, { "epoch": 0.1504595933709209, "grad_norm": 2.1832358837127686, "learning_rate": 9.624715957943731e-05, "loss": 1.1847, "step": 2752 }, { "epoch": 0.1505142661882795, "grad_norm": 2.5044145584106445, "learning_rate": 9.624379357363815e-05, "loss": 1.0265, "step": 2753 }, { "epoch": 0.15056893900563814, "grad_norm": 4.727229595184326, "learning_rate": 9.62404261179056e-05, "loss": 1.312, "step": 2754 }, { "epoch": 0.15062361182299674, "grad_norm": 2.6294000148773193, "learning_rate": 9.623705721234527e-05, "loss": 1.227, "step": 2755 }, { "epoch": 0.15067828464035538, "grad_norm": 2.14772891998291, "learning_rate": 9.623368685706276e-05, "loss": 1.0108, "step": 2756 }, { "epoch": 0.150732957457714, "grad_norm": 2.487983465194702, "learning_rate": 9.623031505216377e-05, "loss": 1.2613, "step": 2757 }, { "epoch": 0.1507876302750726, "grad_norm": 2.6559128761291504, "learning_rate": 9.6226941797754e-05, "loss": 1.2545, "step": 2758 }, { "epoch": 0.15084230309243124, "grad_norm": 2.438321590423584, "learning_rate": 9.622356709393922e-05, "loss": 1.0735, "step": 2759 }, { "epoch": 0.15089697590978984, "grad_norm": 2.3143980503082275, "learning_rate": 9.622019094082524e-05, "loss": 1.198, "step": 2760 }, { "epoch": 0.15095164872714847, "grad_norm": 2.1902453899383545, "learning_rate": 9.621681333851793e-05, "loss": 0.9768, "step": 2761 }, { "epoch": 0.15100632154450708, "grad_norm": 2.866309881210327, "learning_rate": 9.621343428712317e-05, "loss": 1.2653, "step": 2762 }, { "epoch": 0.1510609943618657, "grad_norm": 2.0382585525512695, "learning_rate": 9.621005378674692e-05, "loss": 0.9583, "step": 2763 }, { "epoch": 0.15111566717922434, "grad_norm": 3.1339380741119385, "learning_rate": 9.620667183749516e-05, "loss": 1.2119, "step": 2764 }, { "epoch": 0.15117033999658294, "grad_norm": 3.1860034465789795, "learning_rate": 9.620328843947397e-05, "loss": 1.4442, "step": 2765 }, { "epoch": 0.15122501281394157, "grad_norm": 2.534177303314209, "learning_rate": 9.619990359278938e-05, "loss": 1.1324, "step": 2766 }, { "epoch": 0.15127968563130018, "grad_norm": 2.863154172897339, "learning_rate": 9.619651729754756e-05, "loss": 1.0216, "step": 2767 }, { "epoch": 0.1513343584486588, "grad_norm": 2.6230831146240234, "learning_rate": 9.619312955385463e-05, "loss": 1.1803, "step": 2768 }, { "epoch": 0.15138903126601744, "grad_norm": 2.693027973175049, "learning_rate": 9.618974036181687e-05, "loss": 1.0958, "step": 2769 }, { "epoch": 0.15144370408337604, "grad_norm": 2.721266984939575, "learning_rate": 9.618634972154052e-05, "loss": 1.2128, "step": 2770 }, { "epoch": 0.15149837690073467, "grad_norm": 2.8616299629211426, "learning_rate": 9.618295763313189e-05, "loss": 1.4392, "step": 2771 }, { "epoch": 0.15155304971809327, "grad_norm": 2.7075798511505127, "learning_rate": 9.617956409669733e-05, "loss": 1.338, "step": 2772 }, { "epoch": 0.1516077225354519, "grad_norm": 2.2014882564544678, "learning_rate": 9.617616911234325e-05, "loss": 1.1161, "step": 2773 }, { "epoch": 0.15166239535281054, "grad_norm": 2.017191171646118, "learning_rate": 9.617277268017611e-05, "loss": 1.07, "step": 2774 }, { "epoch": 0.15171706817016914, "grad_norm": 2.691263198852539, "learning_rate": 9.616937480030237e-05, "loss": 1.2182, "step": 2775 }, { "epoch": 0.15177174098752777, "grad_norm": 2.9321510791778564, "learning_rate": 9.616597547282858e-05, "loss": 1.1944, "step": 2776 }, { "epoch": 0.15182641380488637, "grad_norm": 2.409658193588257, "learning_rate": 9.616257469786134e-05, "loss": 0.9204, "step": 2777 }, { "epoch": 0.151881086622245, "grad_norm": 2.1607141494750977, "learning_rate": 9.615917247550726e-05, "loss": 1.0987, "step": 2778 }, { "epoch": 0.15193575943960363, "grad_norm": 1.9589158296585083, "learning_rate": 9.615576880587303e-05, "loss": 1.0727, "step": 2779 }, { "epoch": 0.15199043225696224, "grad_norm": 2.7378854751586914, "learning_rate": 9.615236368906535e-05, "loss": 1.1568, "step": 2780 }, { "epoch": 0.15204510507432087, "grad_norm": 3.3103461265563965, "learning_rate": 9.614895712519098e-05, "loss": 1.2401, "step": 2781 }, { "epoch": 0.15209977789167947, "grad_norm": 2.123918056488037, "learning_rate": 9.614554911435676e-05, "loss": 0.9982, "step": 2782 }, { "epoch": 0.1521544507090381, "grad_norm": 2.676015615463257, "learning_rate": 9.614213965666955e-05, "loss": 1.1794, "step": 2783 }, { "epoch": 0.15220912352639673, "grad_norm": 2.388760566711426, "learning_rate": 9.613872875223619e-05, "loss": 1.0996, "step": 2784 }, { "epoch": 0.15226379634375534, "grad_norm": 2.5170981884002686, "learning_rate": 9.613531640116367e-05, "loss": 1.3085, "step": 2785 }, { "epoch": 0.15231846916111397, "grad_norm": 3.2403955459594727, "learning_rate": 9.613190260355898e-05, "loss": 1.281, "step": 2786 }, { "epoch": 0.15237314197847257, "grad_norm": 2.1028592586517334, "learning_rate": 9.612848735952916e-05, "loss": 0.9084, "step": 2787 }, { "epoch": 0.1524278147958312, "grad_norm": 2.350607395172119, "learning_rate": 9.612507066918129e-05, "loss": 1.2201, "step": 2788 }, { "epoch": 0.1524824876131898, "grad_norm": 2.563037157058716, "learning_rate": 9.612165253262247e-05, "loss": 1.0209, "step": 2789 }, { "epoch": 0.15253716043054844, "grad_norm": 2.504692554473877, "learning_rate": 9.61182329499599e-05, "loss": 1.3102, "step": 2790 }, { "epoch": 0.15259183324790707, "grad_norm": 2.276845693588257, "learning_rate": 9.61148119213008e-05, "loss": 1.0819, "step": 2791 }, { "epoch": 0.15264650606526567, "grad_norm": 4.675583839416504, "learning_rate": 9.611138944675242e-05, "loss": 1.3848, "step": 2792 }, { "epoch": 0.1527011788826243, "grad_norm": 2.198295831680298, "learning_rate": 9.610796552642209e-05, "loss": 1.1191, "step": 2793 }, { "epoch": 0.1527558516999829, "grad_norm": 2.2970848083496094, "learning_rate": 9.610454016041713e-05, "loss": 1.0295, "step": 2794 }, { "epoch": 0.15281052451734153, "grad_norm": 2.7131083011627197, "learning_rate": 9.610111334884497e-05, "loss": 1.2973, "step": 2795 }, { "epoch": 0.15286519733470016, "grad_norm": 2.4304358959198, "learning_rate": 9.609768509181303e-05, "loss": 1.0911, "step": 2796 }, { "epoch": 0.15291987015205877, "grad_norm": 3.7183473110198975, "learning_rate": 9.609425538942882e-05, "loss": 1.2195, "step": 2797 }, { "epoch": 0.1529745429694174, "grad_norm": 2.776768922805786, "learning_rate": 9.609082424179988e-05, "loss": 1.1745, "step": 2798 }, { "epoch": 0.153029215786776, "grad_norm": 3.1967580318450928, "learning_rate": 9.608739164903375e-05, "loss": 1.3296, "step": 2799 }, { "epoch": 0.15308388860413463, "grad_norm": 3.217176675796509, "learning_rate": 9.608395761123809e-05, "loss": 1.2764, "step": 2800 }, { "epoch": 0.15313856142149326, "grad_norm": 2.722865343093872, "learning_rate": 9.608052212852058e-05, "loss": 1.2906, "step": 2801 }, { "epoch": 0.15319323423885187, "grad_norm": 2.410531997680664, "learning_rate": 9.60770852009889e-05, "loss": 1.2171, "step": 2802 }, { "epoch": 0.1532479070562105, "grad_norm": 2.560739040374756, "learning_rate": 9.607364682875087e-05, "loss": 1.2535, "step": 2803 }, { "epoch": 0.1533025798735691, "grad_norm": 5.159134864807129, "learning_rate": 9.607020701191422e-05, "loss": 1.4024, "step": 2804 }, { "epoch": 0.15335725269092773, "grad_norm": 2.781959056854248, "learning_rate": 9.606676575058688e-05, "loss": 1.2357, "step": 2805 }, { "epoch": 0.15341192550828636, "grad_norm": 2.2434885501861572, "learning_rate": 9.606332304487669e-05, "loss": 1.1514, "step": 2806 }, { "epoch": 0.15346659832564497, "grad_norm": 2.4238078594207764, "learning_rate": 9.605987889489161e-05, "loss": 1.1772, "step": 2807 }, { "epoch": 0.1535212711430036, "grad_norm": 2.264535903930664, "learning_rate": 9.605643330073964e-05, "loss": 1.1843, "step": 2808 }, { "epoch": 0.1535759439603622, "grad_norm": 2.410006284713745, "learning_rate": 9.605298626252881e-05, "loss": 1.0453, "step": 2809 }, { "epoch": 0.15363061677772083, "grad_norm": 2.2723512649536133, "learning_rate": 9.604953778036718e-05, "loss": 1.2945, "step": 2810 }, { "epoch": 0.15368528959507943, "grad_norm": 2.775592088699341, "learning_rate": 9.604608785436291e-05, "loss": 1.1875, "step": 2811 }, { "epoch": 0.15373996241243806, "grad_norm": 2.3098342418670654, "learning_rate": 9.604263648462412e-05, "loss": 1.1244, "step": 2812 }, { "epoch": 0.1537946352297967, "grad_norm": 2.9982049465179443, "learning_rate": 9.603918367125908e-05, "loss": 1.2421, "step": 2813 }, { "epoch": 0.1538493080471553, "grad_norm": 2.6710779666900635, "learning_rate": 9.603572941437602e-05, "loss": 1.2784, "step": 2814 }, { "epoch": 0.15390398086451393, "grad_norm": 2.0445027351379395, "learning_rate": 9.603227371408324e-05, "loss": 1.0685, "step": 2815 }, { "epoch": 0.15395865368187253, "grad_norm": 2.55045485496521, "learning_rate": 9.602881657048909e-05, "loss": 1.3022, "step": 2816 }, { "epoch": 0.15401332649923116, "grad_norm": 3.1795754432678223, "learning_rate": 9.602535798370198e-05, "loss": 1.3805, "step": 2817 }, { "epoch": 0.1540679993165898, "grad_norm": 3.23185396194458, "learning_rate": 9.602189795383036e-05, "loss": 1.2105, "step": 2818 }, { "epoch": 0.1541226721339484, "grad_norm": 9.859277725219727, "learning_rate": 9.601843648098268e-05, "loss": 1.195, "step": 2819 }, { "epoch": 0.15417734495130703, "grad_norm": 1.9902057647705078, "learning_rate": 9.60149735652675e-05, "loss": 0.8568, "step": 2820 }, { "epoch": 0.15423201776866563, "grad_norm": 2.29365873336792, "learning_rate": 9.601150920679338e-05, "loss": 1.0772, "step": 2821 }, { "epoch": 0.15428669058602426, "grad_norm": 7.133058547973633, "learning_rate": 9.600804340566897e-05, "loss": 1.3585, "step": 2822 }, { "epoch": 0.1543413634033829, "grad_norm": 3.715589761734009, "learning_rate": 9.600457616200291e-05, "loss": 1.182, "step": 2823 }, { "epoch": 0.1543960362207415, "grad_norm": 2.9411513805389404, "learning_rate": 9.600110747590391e-05, "loss": 1.2932, "step": 2824 }, { "epoch": 0.15445070903810013, "grad_norm": 2.237104892730713, "learning_rate": 9.599763734748075e-05, "loss": 1.1924, "step": 2825 }, { "epoch": 0.15450538185545873, "grad_norm": 2.594135284423828, "learning_rate": 9.599416577684222e-05, "loss": 1.0568, "step": 2826 }, { "epoch": 0.15456005467281736, "grad_norm": 3.0108416080474854, "learning_rate": 9.599069276409718e-05, "loss": 0.9798, "step": 2827 }, { "epoch": 0.154614727490176, "grad_norm": 2.2773470878601074, "learning_rate": 9.598721830935448e-05, "loss": 1.1376, "step": 2828 }, { "epoch": 0.1546694003075346, "grad_norm": 2.517512559890747, "learning_rate": 9.598374241272311e-05, "loss": 1.2726, "step": 2829 }, { "epoch": 0.15472407312489322, "grad_norm": 2.8943519592285156, "learning_rate": 9.598026507431205e-05, "loss": 1.3137, "step": 2830 }, { "epoch": 0.15477874594225183, "grad_norm": 3.2271981239318848, "learning_rate": 9.59767862942303e-05, "loss": 1.2076, "step": 2831 }, { "epoch": 0.15483341875961046, "grad_norm": 2.668272018432617, "learning_rate": 9.597330607258695e-05, "loss": 1.2976, "step": 2832 }, { "epoch": 0.1548880915769691, "grad_norm": 2.628754138946533, "learning_rate": 9.596982440949112e-05, "loss": 1.107, "step": 2833 }, { "epoch": 0.1549427643943277, "grad_norm": 2.7551755905151367, "learning_rate": 9.596634130505195e-05, "loss": 1.2337, "step": 2834 }, { "epoch": 0.15499743721168632, "grad_norm": 2.456183910369873, "learning_rate": 9.59628567593787e-05, "loss": 1.2808, "step": 2835 }, { "epoch": 0.15505211002904493, "grad_norm": 4.087589263916016, "learning_rate": 9.595937077258057e-05, "loss": 1.0922, "step": 2836 }, { "epoch": 0.15510678284640356, "grad_norm": 2.8535165786743164, "learning_rate": 9.59558833447669e-05, "loss": 0.9338, "step": 2837 }, { "epoch": 0.15516145566376216, "grad_norm": 2.4313087463378906, "learning_rate": 9.595239447604702e-05, "loss": 1.2624, "step": 2838 }, { "epoch": 0.1552161284811208, "grad_norm": 2.487269163131714, "learning_rate": 9.594890416653031e-05, "loss": 1.0799, "step": 2839 }, { "epoch": 0.15527080129847942, "grad_norm": 2.2390198707580566, "learning_rate": 9.594541241632625e-05, "loss": 1.2342, "step": 2840 }, { "epoch": 0.15532547411583802, "grad_norm": 2.2078874111175537, "learning_rate": 9.594191922554426e-05, "loss": 1.0802, "step": 2841 }, { "epoch": 0.15538014693319666, "grad_norm": 3.7208216190338135, "learning_rate": 9.593842459429389e-05, "loss": 1.155, "step": 2842 }, { "epoch": 0.15543481975055526, "grad_norm": 3.269822359085083, "learning_rate": 9.593492852268472e-05, "loss": 1.234, "step": 2843 }, { "epoch": 0.1554894925679139, "grad_norm": 2.8425891399383545, "learning_rate": 9.593143101082635e-05, "loss": 1.3258, "step": 2844 }, { "epoch": 0.15554416538527252, "grad_norm": 3.590325117111206, "learning_rate": 9.592793205882848e-05, "loss": 1.2519, "step": 2845 }, { "epoch": 0.15559883820263112, "grad_norm": 2.964221477508545, "learning_rate": 9.592443166680077e-05, "loss": 1.2644, "step": 2846 }, { "epoch": 0.15565351101998975, "grad_norm": 2.235567092895508, "learning_rate": 9.592092983485298e-05, "loss": 1.2732, "step": 2847 }, { "epoch": 0.15570818383734836, "grad_norm": 2.4479713439941406, "learning_rate": 9.591742656309494e-05, "loss": 1.1405, "step": 2848 }, { "epoch": 0.155762856654707, "grad_norm": 2.550034284591675, "learning_rate": 9.591392185163648e-05, "loss": 1.3798, "step": 2849 }, { "epoch": 0.15581752947206562, "grad_norm": 2.5956645011901855, "learning_rate": 9.591041570058745e-05, "loss": 1.2407, "step": 2850 }, { "epoch": 0.15587220228942422, "grad_norm": 3.2392032146453857, "learning_rate": 9.590690811005783e-05, "loss": 1.272, "step": 2851 }, { "epoch": 0.15592687510678285, "grad_norm": 2.818166971206665, "learning_rate": 9.590339908015756e-05, "loss": 1.2779, "step": 2852 }, { "epoch": 0.15598154792414146, "grad_norm": 2.55081844329834, "learning_rate": 9.589988861099669e-05, "loss": 1.227, "step": 2853 }, { "epoch": 0.1560362207415001, "grad_norm": 2.2943625450134277, "learning_rate": 9.589637670268526e-05, "loss": 0.986, "step": 2854 }, { "epoch": 0.15609089355885872, "grad_norm": 2.392882823944092, "learning_rate": 9.58928633553334e-05, "loss": 1.1919, "step": 2855 }, { "epoch": 0.15614556637621732, "grad_norm": 3.3579154014587402, "learning_rate": 9.588934856905127e-05, "loss": 1.1984, "step": 2856 }, { "epoch": 0.15620023919357595, "grad_norm": 3.485020637512207, "learning_rate": 9.588583234394909e-05, "loss": 0.9591, "step": 2857 }, { "epoch": 0.15625491201093455, "grad_norm": 3.015575408935547, "learning_rate": 9.588231468013707e-05, "loss": 1.2062, "step": 2858 }, { "epoch": 0.15630958482829319, "grad_norm": 2.2110652923583984, "learning_rate": 9.587879557772552e-05, "loss": 1.1526, "step": 2859 }, { "epoch": 0.15636425764565182, "grad_norm": 2.4562368392944336, "learning_rate": 9.587527503682479e-05, "loss": 1.1613, "step": 2860 }, { "epoch": 0.15641893046301042, "grad_norm": 3.1487507820129395, "learning_rate": 9.587175305754525e-05, "loss": 1.2242, "step": 2861 }, { "epoch": 0.15647360328036905, "grad_norm": 3.192607879638672, "learning_rate": 9.586822963999734e-05, "loss": 1.064, "step": 2862 }, { "epoch": 0.15652827609772765, "grad_norm": 2.2376227378845215, "learning_rate": 9.586470478429152e-05, "loss": 1.2159, "step": 2863 }, { "epoch": 0.15658294891508628, "grad_norm": 2.949202537536621, "learning_rate": 9.58611784905383e-05, "loss": 1.2493, "step": 2864 }, { "epoch": 0.1566376217324449, "grad_norm": 2.669738531112671, "learning_rate": 9.585765075884827e-05, "loss": 1.2859, "step": 2865 }, { "epoch": 0.15669229454980352, "grad_norm": 2.4079806804656982, "learning_rate": 9.585412158933202e-05, "loss": 1.123, "step": 2866 }, { "epoch": 0.15674696736716215, "grad_norm": 2.5422744750976562, "learning_rate": 9.585059098210022e-05, "loss": 1.1016, "step": 2867 }, { "epoch": 0.15680164018452075, "grad_norm": 2.8841781616210938, "learning_rate": 9.584705893726356e-05, "loss": 1.1394, "step": 2868 }, { "epoch": 0.15685631300187938, "grad_norm": 2.8126986026763916, "learning_rate": 9.584352545493279e-05, "loss": 1.3527, "step": 2869 }, { "epoch": 0.15691098581923799, "grad_norm": 2.581357717514038, "learning_rate": 9.583999053521868e-05, "loss": 1.1618, "step": 2870 }, { "epoch": 0.15696565863659662, "grad_norm": 2.5244967937469482, "learning_rate": 9.583645417823209e-05, "loss": 1.0811, "step": 2871 }, { "epoch": 0.15702033145395525, "grad_norm": 3.4968955516815186, "learning_rate": 9.583291638408388e-05, "loss": 1.4035, "step": 2872 }, { "epoch": 0.15707500427131385, "grad_norm": 2.7631733417510986, "learning_rate": 9.582937715288498e-05, "loss": 1.2182, "step": 2873 }, { "epoch": 0.15712967708867248, "grad_norm": 2.4840946197509766, "learning_rate": 9.582583648474636e-05, "loss": 1.2089, "step": 2874 }, { "epoch": 0.15718434990603108, "grad_norm": 5.042304515838623, "learning_rate": 9.582229437977905e-05, "loss": 1.3526, "step": 2875 }, { "epoch": 0.15723902272338972, "grad_norm": 2.8803257942199707, "learning_rate": 9.581875083809409e-05, "loss": 1.2353, "step": 2876 }, { "epoch": 0.15729369554074835, "grad_norm": 2.3345699310302734, "learning_rate": 9.581520585980257e-05, "loss": 1.2337, "step": 2877 }, { "epoch": 0.15734836835810695, "grad_norm": 2.5796327590942383, "learning_rate": 9.581165944501569e-05, "loss": 1.1922, "step": 2878 }, { "epoch": 0.15740304117546558, "grad_norm": 7.116581439971924, "learning_rate": 9.58081115938446e-05, "loss": 1.4251, "step": 2879 }, { "epoch": 0.15745771399282418, "grad_norm": 4.0824103355407715, "learning_rate": 9.580456230640053e-05, "loss": 1.4783, "step": 2880 }, { "epoch": 0.15751238681018281, "grad_norm": 2.528773069381714, "learning_rate": 9.580101158279482e-05, "loss": 1.0887, "step": 2881 }, { "epoch": 0.15756705962754144, "grad_norm": 2.2412261962890625, "learning_rate": 9.579745942313875e-05, "loss": 1.0994, "step": 2882 }, { "epoch": 0.15762173244490005, "grad_norm": 2.9588775634765625, "learning_rate": 9.579390582754373e-05, "loss": 1.29, "step": 2883 }, { "epoch": 0.15767640526225868, "grad_norm": 2.8792805671691895, "learning_rate": 9.579035079612116e-05, "loss": 1.1966, "step": 2884 }, { "epoch": 0.15773107807961728, "grad_norm": 2.5609593391418457, "learning_rate": 9.57867943289825e-05, "loss": 1.0121, "step": 2885 }, { "epoch": 0.1577857508969759, "grad_norm": 3.9193315505981445, "learning_rate": 9.578323642623928e-05, "loss": 1.4419, "step": 2886 }, { "epoch": 0.15784042371433452, "grad_norm": 2.3989920616149902, "learning_rate": 9.577967708800303e-05, "loss": 1.1936, "step": 2887 }, { "epoch": 0.15789509653169315, "grad_norm": 3.223438024520874, "learning_rate": 9.577611631438537e-05, "loss": 1.0584, "step": 2888 }, { "epoch": 0.15794976934905178, "grad_norm": 2.9838266372680664, "learning_rate": 9.577255410549795e-05, "loss": 1.1437, "step": 2889 }, { "epoch": 0.15800444216641038, "grad_norm": 2.391441822052002, "learning_rate": 9.576899046145242e-05, "loss": 1.0773, "step": 2890 }, { "epoch": 0.158059114983769, "grad_norm": 3.197221040725708, "learning_rate": 9.576542538236055e-05, "loss": 1.2854, "step": 2891 }, { "epoch": 0.15811378780112761, "grad_norm": 2.6146135330200195, "learning_rate": 9.576185886833413e-05, "loss": 1.3156, "step": 2892 }, { "epoch": 0.15816846061848625, "grad_norm": 4.425673484802246, "learning_rate": 9.575829091948495e-05, "loss": 1.1873, "step": 2893 }, { "epoch": 0.15822313343584488, "grad_norm": 2.7985312938690186, "learning_rate": 9.575472153592491e-05, "loss": 1.2517, "step": 2894 }, { "epoch": 0.15827780625320348, "grad_norm": 2.185634136199951, "learning_rate": 9.57511507177659e-05, "loss": 1.2136, "step": 2895 }, { "epoch": 0.1583324790705621, "grad_norm": 2.4530727863311768, "learning_rate": 9.57475784651199e-05, "loss": 1.0193, "step": 2896 }, { "epoch": 0.1583871518879207, "grad_norm": 2.564724922180176, "learning_rate": 9.57440047780989e-05, "loss": 1.3803, "step": 2897 }, { "epoch": 0.15844182470527934, "grad_norm": 2.8516950607299805, "learning_rate": 9.574042965681497e-05, "loss": 1.0428, "step": 2898 }, { "epoch": 0.15849649752263797, "grad_norm": 2.081348180770874, "learning_rate": 9.573685310138018e-05, "loss": 0.9507, "step": 2899 }, { "epoch": 0.15855117033999658, "grad_norm": 2.3527941703796387, "learning_rate": 9.573327511190668e-05, "loss": 1.1361, "step": 2900 }, { "epoch": 0.1586058431573552, "grad_norm": 3.541799306869507, "learning_rate": 9.572969568850667e-05, "loss": 1.398, "step": 2901 }, { "epoch": 0.1586605159747138, "grad_norm": 2.8174221515655518, "learning_rate": 9.572611483129234e-05, "loss": 1.3321, "step": 2902 }, { "epoch": 0.15871518879207244, "grad_norm": 6.966251373291016, "learning_rate": 9.572253254037602e-05, "loss": 1.2907, "step": 2903 }, { "epoch": 0.15876986160943107, "grad_norm": 2.473205327987671, "learning_rate": 9.571894881586998e-05, "loss": 1.0776, "step": 2904 }, { "epoch": 0.15882453442678968, "grad_norm": 2.4028115272521973, "learning_rate": 9.57153636578866e-05, "loss": 1.1155, "step": 2905 }, { "epoch": 0.1588792072441483, "grad_norm": 3.396967649459839, "learning_rate": 9.57117770665383e-05, "loss": 1.3317, "step": 2906 }, { "epoch": 0.1589338800615069, "grad_norm": 2.746793508529663, "learning_rate": 9.570818904193755e-05, "loss": 1.161, "step": 2907 }, { "epoch": 0.15898855287886554, "grad_norm": 3.2565019130706787, "learning_rate": 9.57045995841968e-05, "loss": 1.3367, "step": 2908 }, { "epoch": 0.15904322569622417, "grad_norm": 2.3705809116363525, "learning_rate": 9.570100869342862e-05, "loss": 1.0337, "step": 2909 }, { "epoch": 0.15909789851358278, "grad_norm": 3.492144823074341, "learning_rate": 9.569741636974562e-05, "loss": 1.3241, "step": 2910 }, { "epoch": 0.1591525713309414, "grad_norm": 2.6361358165740967, "learning_rate": 9.569382261326041e-05, "loss": 1.1424, "step": 2911 }, { "epoch": 0.1592072441483, "grad_norm": 2.586139440536499, "learning_rate": 9.569022742408567e-05, "loss": 1.2126, "step": 2912 }, { "epoch": 0.15926191696565864, "grad_norm": 2.5128908157348633, "learning_rate": 9.568663080233413e-05, "loss": 1.2356, "step": 2913 }, { "epoch": 0.15931658978301724, "grad_norm": 4.566465377807617, "learning_rate": 9.568303274811856e-05, "loss": 1.0344, "step": 2914 }, { "epoch": 0.15937126260037587, "grad_norm": 2.4845516681671143, "learning_rate": 9.567943326155176e-05, "loss": 1.1356, "step": 2915 }, { "epoch": 0.1594259354177345, "grad_norm": 2.923640489578247, "learning_rate": 9.567583234274661e-05, "loss": 1.1981, "step": 2916 }, { "epoch": 0.1594806082350931, "grad_norm": 2.29782772064209, "learning_rate": 9.5672229991816e-05, "loss": 1.0016, "step": 2917 }, { "epoch": 0.15953528105245174, "grad_norm": 2.612661600112915, "learning_rate": 9.566862620887288e-05, "loss": 1.2198, "step": 2918 }, { "epoch": 0.15958995386981034, "grad_norm": 2.135035514831543, "learning_rate": 9.566502099403026e-05, "loss": 1.2761, "step": 2919 }, { "epoch": 0.15964462668716897, "grad_norm": 2.3590126037597656, "learning_rate": 9.566141434740115e-05, "loss": 1.2974, "step": 2920 }, { "epoch": 0.1596992995045276, "grad_norm": 2.7101056575775146, "learning_rate": 9.565780626909864e-05, "loss": 0.9347, "step": 2921 }, { "epoch": 0.1597539723218862, "grad_norm": 2.3320934772491455, "learning_rate": 9.565419675923587e-05, "loss": 1.2, "step": 2922 }, { "epoch": 0.15980864513924484, "grad_norm": 3.813153028488159, "learning_rate": 9.565058581792601e-05, "loss": 1.1212, "step": 2923 }, { "epoch": 0.15986331795660344, "grad_norm": 2.743525743484497, "learning_rate": 9.564697344528227e-05, "loss": 1.3415, "step": 2924 }, { "epoch": 0.15991799077396207, "grad_norm": 2.508960485458374, "learning_rate": 9.564335964141793e-05, "loss": 1.0155, "step": 2925 }, { "epoch": 0.1599726635913207, "grad_norm": 2.5125977993011475, "learning_rate": 9.563974440644627e-05, "loss": 0.8846, "step": 2926 }, { "epoch": 0.1600273364086793, "grad_norm": 2.979623794555664, "learning_rate": 9.563612774048067e-05, "loss": 1.2676, "step": 2927 }, { "epoch": 0.16008200922603794, "grad_norm": 3.2631161212921143, "learning_rate": 9.563250964363453e-05, "loss": 1.0046, "step": 2928 }, { "epoch": 0.16013668204339654, "grad_norm": 2.940981388092041, "learning_rate": 9.562889011602125e-05, "loss": 1.2035, "step": 2929 }, { "epoch": 0.16019135486075517, "grad_norm": 2.2076690196990967, "learning_rate": 9.562526915775437e-05, "loss": 1.0521, "step": 2930 }, { "epoch": 0.1602460276781138, "grad_norm": 2.350555181503296, "learning_rate": 9.562164676894738e-05, "loss": 1.2629, "step": 2931 }, { "epoch": 0.1603007004954724, "grad_norm": 2.3219480514526367, "learning_rate": 9.56180229497139e-05, "loss": 1.221, "step": 2932 }, { "epoch": 0.16035537331283103, "grad_norm": 4.480883598327637, "learning_rate": 9.561439770016749e-05, "loss": 1.3272, "step": 2933 }, { "epoch": 0.16041004613018964, "grad_norm": 4.439670085906982, "learning_rate": 9.561077102042188e-05, "loss": 1.3616, "step": 2934 }, { "epoch": 0.16046471894754827, "grad_norm": 3.873460292816162, "learning_rate": 9.560714291059075e-05, "loss": 1.3436, "step": 2935 }, { "epoch": 0.1605193917649069, "grad_norm": 2.349055290222168, "learning_rate": 9.560351337078783e-05, "loss": 0.9973, "step": 2936 }, { "epoch": 0.1605740645822655, "grad_norm": 2.0931625366210938, "learning_rate": 9.559988240112698e-05, "loss": 1.0718, "step": 2937 }, { "epoch": 0.16062873739962413, "grad_norm": 2.551778554916382, "learning_rate": 9.559625000172201e-05, "loss": 1.1897, "step": 2938 }, { "epoch": 0.16068341021698274, "grad_norm": 2.190216541290283, "learning_rate": 9.559261617268682e-05, "loss": 1.0924, "step": 2939 }, { "epoch": 0.16073808303434137, "grad_norm": 2.813568592071533, "learning_rate": 9.558898091413534e-05, "loss": 1.3394, "step": 2940 }, { "epoch": 0.16079275585169997, "grad_norm": 2.4034554958343506, "learning_rate": 9.558534422618155e-05, "loss": 1.1994, "step": 2941 }, { "epoch": 0.1608474286690586, "grad_norm": 3.816429853439331, "learning_rate": 9.558170610893949e-05, "loss": 1.1705, "step": 2942 }, { "epoch": 0.16090210148641723, "grad_norm": 2.690136432647705, "learning_rate": 9.557806656252322e-05, "loss": 0.9591, "step": 2943 }, { "epoch": 0.16095677430377583, "grad_norm": 2.5779225826263428, "learning_rate": 9.557442558704684e-05, "loss": 1.2076, "step": 2944 }, { "epoch": 0.16101144712113447, "grad_norm": 3.3285562992095947, "learning_rate": 9.557078318262451e-05, "loss": 1.4176, "step": 2945 }, { "epoch": 0.16106611993849307, "grad_norm": 2.3379786014556885, "learning_rate": 9.556713934937048e-05, "loss": 0.9937, "step": 2946 }, { "epoch": 0.1611207927558517, "grad_norm": 2.6290407180786133, "learning_rate": 9.556349408739894e-05, "loss": 1.2307, "step": 2947 }, { "epoch": 0.16117546557321033, "grad_norm": 2.498955488204956, "learning_rate": 9.555984739682422e-05, "loss": 1.1295, "step": 2948 }, { "epoch": 0.16123013839056893, "grad_norm": 2.1627957820892334, "learning_rate": 9.555619927776065e-05, "loss": 1.1567, "step": 2949 }, { "epoch": 0.16128481120792756, "grad_norm": 3.142394781112671, "learning_rate": 9.555254973032262e-05, "loss": 1.036, "step": 2950 }, { "epoch": 0.16133948402528617, "grad_norm": 3.062927484512329, "learning_rate": 9.554889875462454e-05, "loss": 1.2119, "step": 2951 }, { "epoch": 0.1613941568426448, "grad_norm": 2.318851947784424, "learning_rate": 9.554524635078089e-05, "loss": 1.0973, "step": 2952 }, { "epoch": 0.16144882966000343, "grad_norm": 2.1991071701049805, "learning_rate": 9.55415925189062e-05, "loss": 0.9891, "step": 2953 }, { "epoch": 0.16150350247736203, "grad_norm": 2.816460609436035, "learning_rate": 9.553793725911502e-05, "loss": 1.2388, "step": 2954 }, { "epoch": 0.16155817529472066, "grad_norm": 2.5116171836853027, "learning_rate": 9.553428057152197e-05, "loss": 1.2493, "step": 2955 }, { "epoch": 0.16161284811207927, "grad_norm": 2.5989151000976562, "learning_rate": 9.553062245624169e-05, "loss": 1.2429, "step": 2956 }, { "epoch": 0.1616675209294379, "grad_norm": 2.562157154083252, "learning_rate": 9.552696291338887e-05, "loss": 1.2636, "step": 2957 }, { "epoch": 0.16172219374679653, "grad_norm": 2.4234354496002197, "learning_rate": 9.552330194307827e-05, "loss": 1.1653, "step": 2958 }, { "epoch": 0.16177686656415513, "grad_norm": 3.7624738216400146, "learning_rate": 9.55196395454247e-05, "loss": 1.0923, "step": 2959 }, { "epoch": 0.16183153938151376, "grad_norm": 3.0354342460632324, "learning_rate": 9.551597572054292e-05, "loss": 1.3987, "step": 2960 }, { "epoch": 0.16188621219887236, "grad_norm": 2.5003397464752197, "learning_rate": 9.551231046854786e-05, "loss": 1.327, "step": 2961 }, { "epoch": 0.161940885016231, "grad_norm": 2.6333675384521484, "learning_rate": 9.550864378955443e-05, "loss": 1.2474, "step": 2962 }, { "epoch": 0.1619955578335896, "grad_norm": 2.944610834121704, "learning_rate": 9.55049756836776e-05, "loss": 1.3343, "step": 2963 }, { "epoch": 0.16205023065094823, "grad_norm": 2.453984260559082, "learning_rate": 9.550130615103236e-05, "loss": 1.1825, "step": 2964 }, { "epoch": 0.16210490346830686, "grad_norm": 2.7330353260040283, "learning_rate": 9.549763519173378e-05, "loss": 1.1878, "step": 2965 }, { "epoch": 0.16215957628566546, "grad_norm": 2.8894970417022705, "learning_rate": 9.549396280589696e-05, "loss": 1.2609, "step": 2966 }, { "epoch": 0.1622142491030241, "grad_norm": 2.639289617538452, "learning_rate": 9.549028899363704e-05, "loss": 1.0495, "step": 2967 }, { "epoch": 0.1622689219203827, "grad_norm": 2.5375454425811768, "learning_rate": 9.548661375506922e-05, "loss": 1.2851, "step": 2968 }, { "epoch": 0.16232359473774133, "grad_norm": 2.708749771118164, "learning_rate": 9.548293709030872e-05, "loss": 1.0748, "step": 2969 }, { "epoch": 0.16237826755509996, "grad_norm": 3.1223795413970947, "learning_rate": 9.547925899947081e-05, "loss": 1.1014, "step": 2970 }, { "epoch": 0.16243294037245856, "grad_norm": 2.991558790206909, "learning_rate": 9.547557948267085e-05, "loss": 1.0965, "step": 2971 }, { "epoch": 0.1624876131898172, "grad_norm": 2.84368634223938, "learning_rate": 9.547189854002417e-05, "loss": 1.163, "step": 2972 }, { "epoch": 0.1625422860071758, "grad_norm": 2.4397943019866943, "learning_rate": 9.54682161716462e-05, "loss": 1.1309, "step": 2973 }, { "epoch": 0.16259695882453443, "grad_norm": 2.6895971298217773, "learning_rate": 9.54645323776524e-05, "loss": 1.468, "step": 2974 }, { "epoch": 0.16265163164189306, "grad_norm": 2.626260995864868, "learning_rate": 9.546084715815828e-05, "loss": 0.8912, "step": 2975 }, { "epoch": 0.16270630445925166, "grad_norm": 2.1087818145751953, "learning_rate": 9.545716051327935e-05, "loss": 1.1104, "step": 2976 }, { "epoch": 0.1627609772766103, "grad_norm": 2.082279920578003, "learning_rate": 9.545347244313123e-05, "loss": 1.0762, "step": 2977 }, { "epoch": 0.1628156500939689, "grad_norm": 2.6400437355041504, "learning_rate": 9.544978294782956e-05, "loss": 1.2703, "step": 2978 }, { "epoch": 0.16287032291132753, "grad_norm": 2.3295609951019287, "learning_rate": 9.544609202749002e-05, "loss": 1.0868, "step": 2979 }, { "epoch": 0.16292499572868616, "grad_norm": 2.3952553272247314, "learning_rate": 9.544239968222831e-05, "loss": 1.2323, "step": 2980 }, { "epoch": 0.16297966854604476, "grad_norm": 3.2981550693511963, "learning_rate": 9.543870591216023e-05, "loss": 1.0212, "step": 2981 }, { "epoch": 0.1630343413634034, "grad_norm": 2.6118621826171875, "learning_rate": 9.543501071740159e-05, "loss": 1.2508, "step": 2982 }, { "epoch": 0.163089014180762, "grad_norm": 2.4742183685302734, "learning_rate": 9.543131409806822e-05, "loss": 1.2419, "step": 2983 }, { "epoch": 0.16314368699812062, "grad_norm": 2.5274813175201416, "learning_rate": 9.542761605427607e-05, "loss": 1.2475, "step": 2984 }, { "epoch": 0.16319835981547925, "grad_norm": 2.5104994773864746, "learning_rate": 9.542391658614105e-05, "loss": 1.123, "step": 2985 }, { "epoch": 0.16325303263283786, "grad_norm": 3.080789566040039, "learning_rate": 9.54202156937792e-05, "loss": 1.0873, "step": 2986 }, { "epoch": 0.1633077054501965, "grad_norm": 2.252235174179077, "learning_rate": 9.541651337730648e-05, "loss": 0.969, "step": 2987 }, { "epoch": 0.1633623782675551, "grad_norm": 2.4278664588928223, "learning_rate": 9.541280963683905e-05, "loss": 1.3193, "step": 2988 }, { "epoch": 0.16341705108491372, "grad_norm": 2.5096304416656494, "learning_rate": 9.5409104472493e-05, "loss": 1.2029, "step": 2989 }, { "epoch": 0.16347172390227233, "grad_norm": 2.892822742462158, "learning_rate": 9.540539788438452e-05, "loss": 1.0378, "step": 2990 }, { "epoch": 0.16352639671963096, "grad_norm": 2.425661087036133, "learning_rate": 9.540168987262982e-05, "loss": 1.0797, "step": 2991 }, { "epoch": 0.1635810695369896, "grad_norm": 2.6153008937835693, "learning_rate": 9.539798043734516e-05, "loss": 1.1626, "step": 2992 }, { "epoch": 0.1636357423543482, "grad_norm": 2.8548972606658936, "learning_rate": 9.539426957864683e-05, "loss": 1.2241, "step": 2993 }, { "epoch": 0.16369041517170682, "grad_norm": 3.545565366744995, "learning_rate": 9.539055729665119e-05, "loss": 1.0228, "step": 2994 }, { "epoch": 0.16374508798906542, "grad_norm": 2.6115798950195312, "learning_rate": 9.538684359147465e-05, "loss": 1.0726, "step": 2995 }, { "epoch": 0.16379976080642406, "grad_norm": 1.9550384283065796, "learning_rate": 9.538312846323365e-05, "loss": 1.0546, "step": 2996 }, { "epoch": 0.16385443362378269, "grad_norm": 2.381143093109131, "learning_rate": 9.537941191204466e-05, "loss": 1.2254, "step": 2997 }, { "epoch": 0.1639091064411413, "grad_norm": 3.1580569744110107, "learning_rate": 9.537569393802422e-05, "loss": 1.1928, "step": 2998 }, { "epoch": 0.16396377925849992, "grad_norm": 2.3739442825317383, "learning_rate": 9.537197454128887e-05, "loss": 1.2377, "step": 2999 }, { "epoch": 0.16401845207585852, "grad_norm": 2.901752471923828, "learning_rate": 9.53682537219553e-05, "loss": 1.1862, "step": 3000 }, { "epoch": 0.16407312489321715, "grad_norm": 2.8818960189819336, "learning_rate": 9.536453148014011e-05, "loss": 1.2991, "step": 3001 }, { "epoch": 0.16412779771057578, "grad_norm": 2.3555679321289062, "learning_rate": 9.536080781596002e-05, "loss": 1.1885, "step": 3002 }, { "epoch": 0.1641824705279344, "grad_norm": 2.954136371612549, "learning_rate": 9.535708272953179e-05, "loss": 1.2409, "step": 3003 }, { "epoch": 0.16423714334529302, "grad_norm": 2.9767050743103027, "learning_rate": 9.535335622097223e-05, "loss": 1.2732, "step": 3004 }, { "epoch": 0.16429181616265162, "grad_norm": 2.7439017295837402, "learning_rate": 9.534962829039815e-05, "loss": 1.0701, "step": 3005 }, { "epoch": 0.16434648898001025, "grad_norm": 2.5139806270599365, "learning_rate": 9.534589893792647e-05, "loss": 1.3062, "step": 3006 }, { "epoch": 0.16440116179736888, "grad_norm": 2.576802968978882, "learning_rate": 9.534216816367409e-05, "loss": 1.1287, "step": 3007 }, { "epoch": 0.1644558346147275, "grad_norm": 2.9597322940826416, "learning_rate": 9.5338435967758e-05, "loss": 1.0401, "step": 3008 }, { "epoch": 0.16451050743208612, "grad_norm": 2.470269203186035, "learning_rate": 9.533470235029524e-05, "loss": 0.958, "step": 3009 }, { "epoch": 0.16456518024944472, "grad_norm": 2.6655571460723877, "learning_rate": 9.533096731140284e-05, "loss": 1.3443, "step": 3010 }, { "epoch": 0.16461985306680335, "grad_norm": 3.107404947280884, "learning_rate": 9.532723085119792e-05, "loss": 1.2279, "step": 3011 }, { "epoch": 0.16467452588416198, "grad_norm": 2.9844601154327393, "learning_rate": 9.532349296979763e-05, "loss": 1.1539, "step": 3012 }, { "epoch": 0.16472919870152058, "grad_norm": 2.959636926651001, "learning_rate": 9.531975366731917e-05, "loss": 1.1938, "step": 3013 }, { "epoch": 0.16478387151887922, "grad_norm": 2.888230323791504, "learning_rate": 9.531601294387981e-05, "loss": 1.2701, "step": 3014 }, { "epoch": 0.16483854433623782, "grad_norm": 3.214224100112915, "learning_rate": 9.531227079959679e-05, "loss": 0.9654, "step": 3015 }, { "epoch": 0.16489321715359645, "grad_norm": 2.8176522254943848, "learning_rate": 9.530852723458748e-05, "loss": 1.1245, "step": 3016 }, { "epoch": 0.16494788997095505, "grad_norm": 2.83024263381958, "learning_rate": 9.530478224896923e-05, "loss": 1.2547, "step": 3017 }, { "epoch": 0.16500256278831368, "grad_norm": 2.556307792663574, "learning_rate": 9.53010358428595e-05, "loss": 1.1091, "step": 3018 }, { "epoch": 0.16505723560567231, "grad_norm": 2.6292107105255127, "learning_rate": 9.52972880163757e-05, "loss": 1.1808, "step": 3019 }, { "epoch": 0.16511190842303092, "grad_norm": 3.4352288246154785, "learning_rate": 9.529353876963536e-05, "loss": 1.509, "step": 3020 }, { "epoch": 0.16516658124038955, "grad_norm": 3.281785249710083, "learning_rate": 9.528978810275606e-05, "loss": 1.0848, "step": 3021 }, { "epoch": 0.16522125405774815, "grad_norm": 3.0023629665374756, "learning_rate": 9.528603601585537e-05, "loss": 1.2853, "step": 3022 }, { "epoch": 0.16527592687510678, "grad_norm": 2.6605567932128906, "learning_rate": 9.528228250905096e-05, "loss": 1.0177, "step": 3023 }, { "epoch": 0.1653305996924654, "grad_norm": 2.2797815799713135, "learning_rate": 9.527852758246047e-05, "loss": 1.0824, "step": 3024 }, { "epoch": 0.16538527250982402, "grad_norm": 2.4903981685638428, "learning_rate": 9.52747712362017e-05, "loss": 1.0615, "step": 3025 }, { "epoch": 0.16543994532718265, "grad_norm": 2.5680668354034424, "learning_rate": 9.527101347039237e-05, "loss": 1.172, "step": 3026 }, { "epoch": 0.16549461814454125, "grad_norm": 3.2500815391540527, "learning_rate": 9.526725428515032e-05, "loss": 1.1323, "step": 3027 }, { "epoch": 0.16554929096189988, "grad_norm": 2.9504830837249756, "learning_rate": 9.526349368059342e-05, "loss": 1.0102, "step": 3028 }, { "epoch": 0.1656039637792585, "grad_norm": 4.014622688293457, "learning_rate": 9.52597316568396e-05, "loss": 1.3402, "step": 3029 }, { "epoch": 0.16565863659661711, "grad_norm": 2.8878543376922607, "learning_rate": 9.525596821400677e-05, "loss": 1.1287, "step": 3030 }, { "epoch": 0.16571330941397575, "grad_norm": 2.351233720779419, "learning_rate": 9.525220335221296e-05, "loss": 1.167, "step": 3031 }, { "epoch": 0.16576798223133435, "grad_norm": 2.2696330547332764, "learning_rate": 9.52484370715762e-05, "loss": 0.9395, "step": 3032 }, { "epoch": 0.16582265504869298, "grad_norm": 2.607051134109497, "learning_rate": 9.52446693722146e-05, "loss": 1.2561, "step": 3033 }, { "epoch": 0.1658773278660516, "grad_norm": 3.1412086486816406, "learning_rate": 9.524090025424626e-05, "loss": 1.2406, "step": 3034 }, { "epoch": 0.1659320006834102, "grad_norm": 2.538892984390259, "learning_rate": 9.523712971778938e-05, "loss": 1.4057, "step": 3035 }, { "epoch": 0.16598667350076884, "grad_norm": 2.323441743850708, "learning_rate": 9.523335776296219e-05, "loss": 1.1418, "step": 3036 }, { "epoch": 0.16604134631812745, "grad_norm": 2.3157050609588623, "learning_rate": 9.522958438988293e-05, "loss": 1.0028, "step": 3037 }, { "epoch": 0.16609601913548608, "grad_norm": 2.4919066429138184, "learning_rate": 9.522580959866993e-05, "loss": 1.2928, "step": 3038 }, { "epoch": 0.16615069195284468, "grad_norm": 2.4361231327056885, "learning_rate": 9.522203338944154e-05, "loss": 1.1958, "step": 3039 }, { "epoch": 0.1662053647702033, "grad_norm": 2.3055837154388428, "learning_rate": 9.521825576231616e-05, "loss": 1.1055, "step": 3040 }, { "epoch": 0.16626003758756194, "grad_norm": 2.2226309776306152, "learning_rate": 9.521447671741222e-05, "loss": 1.1435, "step": 3041 }, { "epoch": 0.16631471040492055, "grad_norm": 2.643049478530884, "learning_rate": 9.521069625484824e-05, "loss": 1.0314, "step": 3042 }, { "epoch": 0.16636938322227918, "grad_norm": 2.9784038066864014, "learning_rate": 9.520691437474273e-05, "loss": 1.0665, "step": 3043 }, { "epoch": 0.16642405603963778, "grad_norm": 2.938831329345703, "learning_rate": 9.520313107721427e-05, "loss": 1.0648, "step": 3044 }, { "epoch": 0.1664787288569964, "grad_norm": 3.5556421279907227, "learning_rate": 9.519934636238148e-05, "loss": 1.1985, "step": 3045 }, { "epoch": 0.16653340167435504, "grad_norm": 3.030141830444336, "learning_rate": 9.519556023036305e-05, "loss": 1.3943, "step": 3046 }, { "epoch": 0.16658807449171364, "grad_norm": 2.400775194168091, "learning_rate": 9.519177268127766e-05, "loss": 0.9797, "step": 3047 }, { "epoch": 0.16664274730907228, "grad_norm": 2.7827377319335938, "learning_rate": 9.518798371524406e-05, "loss": 0.9995, "step": 3048 }, { "epoch": 0.16669742012643088, "grad_norm": 4.260008335113525, "learning_rate": 9.51841933323811e-05, "loss": 1.4463, "step": 3049 }, { "epoch": 0.1667520929437895, "grad_norm": 2.9963419437408447, "learning_rate": 9.518040153280757e-05, "loss": 1.2216, "step": 3050 }, { "epoch": 0.16680676576114814, "grad_norm": 2.2761034965515137, "learning_rate": 9.517660831664239e-05, "loss": 1.2864, "step": 3051 }, { "epoch": 0.16686143857850674, "grad_norm": 3.645437479019165, "learning_rate": 9.517281368400448e-05, "loss": 1.2578, "step": 3052 }, { "epoch": 0.16691611139586537, "grad_norm": 3.8928794860839844, "learning_rate": 9.516901763501282e-05, "loss": 1.1753, "step": 3053 }, { "epoch": 0.16697078421322398, "grad_norm": 3.932962656021118, "learning_rate": 9.516522016978642e-05, "loss": 0.7894, "step": 3054 }, { "epoch": 0.1670254570305826, "grad_norm": 2.4920928478240967, "learning_rate": 9.516142128844436e-05, "loss": 1.3369, "step": 3055 }, { "epoch": 0.16708012984794124, "grad_norm": 2.426837205886841, "learning_rate": 9.515762099110577e-05, "loss": 1.308, "step": 3056 }, { "epoch": 0.16713480266529984, "grad_norm": 2.71586537361145, "learning_rate": 9.515381927788975e-05, "loss": 1.2273, "step": 3057 }, { "epoch": 0.16718947548265847, "grad_norm": 2.5763940811157227, "learning_rate": 9.515001614891556e-05, "loss": 1.2183, "step": 3058 }, { "epoch": 0.16724414830001708, "grad_norm": 2.45330810546875, "learning_rate": 9.514621160430241e-05, "loss": 1.3108, "step": 3059 }, { "epoch": 0.1672988211173757, "grad_norm": 3.650352954864502, "learning_rate": 9.51424056441696e-05, "loss": 1.1732, "step": 3060 }, { "epoch": 0.16735349393473434, "grad_norm": 3.1716485023498535, "learning_rate": 9.513859826863645e-05, "loss": 1.1081, "step": 3061 }, { "epoch": 0.16740816675209294, "grad_norm": 2.1136295795440674, "learning_rate": 9.513478947782234e-05, "loss": 1.1287, "step": 3062 }, { "epoch": 0.16746283956945157, "grad_norm": 2.3991892337799072, "learning_rate": 9.51309792718467e-05, "loss": 1.1565, "step": 3063 }, { "epoch": 0.16751751238681017, "grad_norm": 2.4276082515716553, "learning_rate": 9.512716765082898e-05, "loss": 1.1943, "step": 3064 }, { "epoch": 0.1675721852041688, "grad_norm": 2.064312219619751, "learning_rate": 9.512335461488871e-05, "loss": 1.2923, "step": 3065 }, { "epoch": 0.1676268580215274, "grad_norm": 3.295665740966797, "learning_rate": 9.511954016414544e-05, "loss": 1.2317, "step": 3066 }, { "epoch": 0.16768153083888604, "grad_norm": 2.19266414642334, "learning_rate": 9.511572429871875e-05, "loss": 0.9531, "step": 3067 }, { "epoch": 0.16773620365624467, "grad_norm": 3.8191401958465576, "learning_rate": 9.511190701872832e-05, "loss": 1.4292, "step": 3068 }, { "epoch": 0.16779087647360327, "grad_norm": 2.0209667682647705, "learning_rate": 9.510808832429381e-05, "loss": 1.06, "step": 3069 }, { "epoch": 0.1678455492909619, "grad_norm": 3.6884586811065674, "learning_rate": 9.510426821553494e-05, "loss": 1.4266, "step": 3070 }, { "epoch": 0.1679002221083205, "grad_norm": 2.799793004989624, "learning_rate": 9.510044669257152e-05, "loss": 1.0646, "step": 3071 }, { "epoch": 0.16795489492567914, "grad_norm": 2.8278541564941406, "learning_rate": 9.509662375552335e-05, "loss": 1.1406, "step": 3072 }, { "epoch": 0.16800956774303777, "grad_norm": 2.9892122745513916, "learning_rate": 9.509279940451028e-05, "loss": 1.1507, "step": 3073 }, { "epoch": 0.16806424056039637, "grad_norm": 2.5852346420288086, "learning_rate": 9.508897363965225e-05, "loss": 1.1431, "step": 3074 }, { "epoch": 0.168118913377755, "grad_norm": 2.601228713989258, "learning_rate": 9.508514646106921e-05, "loss": 1.3733, "step": 3075 }, { "epoch": 0.1681735861951136, "grad_norm": 2.7457847595214844, "learning_rate": 9.508131786888113e-05, "loss": 1.0866, "step": 3076 }, { "epoch": 0.16822825901247224, "grad_norm": 2.9128470420837402, "learning_rate": 9.507748786320807e-05, "loss": 1.139, "step": 3077 }, { "epoch": 0.16828293182983087, "grad_norm": 2.1348750591278076, "learning_rate": 9.507365644417013e-05, "loss": 1.0323, "step": 3078 }, { "epoch": 0.16833760464718947, "grad_norm": 2.5389623641967773, "learning_rate": 9.506982361188744e-05, "loss": 1.0115, "step": 3079 }, { "epoch": 0.1683922774645481, "grad_norm": 3.086195945739746, "learning_rate": 9.506598936648014e-05, "loss": 1.3515, "step": 3080 }, { "epoch": 0.1684469502819067, "grad_norm": 3.065070629119873, "learning_rate": 9.506215370806847e-05, "loss": 1.3755, "step": 3081 }, { "epoch": 0.16850162309926534, "grad_norm": 2.962810754776001, "learning_rate": 9.50583166367727e-05, "loss": 1.0986, "step": 3082 }, { "epoch": 0.16855629591662397, "grad_norm": 2.447221279144287, "learning_rate": 9.505447815271314e-05, "loss": 1.1975, "step": 3083 }, { "epoch": 0.16861096873398257, "grad_norm": 3.355092763900757, "learning_rate": 9.505063825601014e-05, "loss": 1.0118, "step": 3084 }, { "epoch": 0.1686656415513412, "grad_norm": 2.6417665481567383, "learning_rate": 9.504679694678409e-05, "loss": 1.1102, "step": 3085 }, { "epoch": 0.1687203143686998, "grad_norm": 3.1882946491241455, "learning_rate": 9.504295422515544e-05, "loss": 1.17, "step": 3086 }, { "epoch": 0.16877498718605843, "grad_norm": 2.9339330196380615, "learning_rate": 9.503911009124464e-05, "loss": 1.2529, "step": 3087 }, { "epoch": 0.16882966000341706, "grad_norm": 4.37533712387085, "learning_rate": 9.503526454517227e-05, "loss": 1.2928, "step": 3088 }, { "epoch": 0.16888433282077567, "grad_norm": 2.089677572250366, "learning_rate": 9.503141758705888e-05, "loss": 1.0509, "step": 3089 }, { "epoch": 0.1689390056381343, "grad_norm": 2.491631507873535, "learning_rate": 9.502756921702509e-05, "loss": 1.1441, "step": 3090 }, { "epoch": 0.1689936784554929, "grad_norm": 2.9039881229400635, "learning_rate": 9.502371943519156e-05, "loss": 1.1869, "step": 3091 }, { "epoch": 0.16904835127285153, "grad_norm": 2.7314133644104004, "learning_rate": 9.501986824167901e-05, "loss": 1.2699, "step": 3092 }, { "epoch": 0.16910302409021014, "grad_norm": 3.1398420333862305, "learning_rate": 9.501601563660815e-05, "loss": 1.3369, "step": 3093 }, { "epoch": 0.16915769690756877, "grad_norm": 4.365324020385742, "learning_rate": 9.501216162009984e-05, "loss": 1.0736, "step": 3094 }, { "epoch": 0.1692123697249274, "grad_norm": 2.294283390045166, "learning_rate": 9.500830619227486e-05, "loss": 1.2362, "step": 3095 }, { "epoch": 0.169267042542286, "grad_norm": 2.1168696880340576, "learning_rate": 9.500444935325412e-05, "loss": 1.0544, "step": 3096 }, { "epoch": 0.16932171535964463, "grad_norm": 2.775923252105713, "learning_rate": 9.500059110315856e-05, "loss": 1.0787, "step": 3097 }, { "epoch": 0.16937638817700323, "grad_norm": 3.8075859546661377, "learning_rate": 9.499673144210912e-05, "loss": 1.198, "step": 3098 }, { "epoch": 0.16943106099436187, "grad_norm": 2.4144034385681152, "learning_rate": 9.499287037022683e-05, "loss": 1.2003, "step": 3099 }, { "epoch": 0.1694857338117205, "grad_norm": 2.4005417823791504, "learning_rate": 9.498900788763279e-05, "loss": 1.0645, "step": 3100 }, { "epoch": 0.1695404066290791, "grad_norm": 3.0701522827148438, "learning_rate": 9.498514399444804e-05, "loss": 1.2247, "step": 3101 }, { "epoch": 0.16959507944643773, "grad_norm": 2.5826759338378906, "learning_rate": 9.498127869079375e-05, "loss": 1.2202, "step": 3102 }, { "epoch": 0.16964975226379633, "grad_norm": 2.261727809906006, "learning_rate": 9.497741197679114e-05, "loss": 1.1498, "step": 3103 }, { "epoch": 0.16970442508115496, "grad_norm": 2.3602042198181152, "learning_rate": 9.497354385256142e-05, "loss": 1.1536, "step": 3104 }, { "epoch": 0.1697590978985136, "grad_norm": 2.697176218032837, "learning_rate": 9.496967431822588e-05, "loss": 1.1848, "step": 3105 }, { "epoch": 0.1698137707158722, "grad_norm": 3.3121497631073, "learning_rate": 9.496580337390583e-05, "loss": 1.1155, "step": 3106 }, { "epoch": 0.16986844353323083, "grad_norm": 2.492323875427246, "learning_rate": 9.496193101972269e-05, "loss": 1.1759, "step": 3107 }, { "epoch": 0.16992311635058943, "grad_norm": 3.5242919921875, "learning_rate": 9.495805725579781e-05, "loss": 1.3679, "step": 3108 }, { "epoch": 0.16997778916794806, "grad_norm": 3.1552140712738037, "learning_rate": 9.495418208225269e-05, "loss": 1.2832, "step": 3109 }, { "epoch": 0.1700324619853067, "grad_norm": 2.2093870639801025, "learning_rate": 9.495030549920882e-05, "loss": 1.3658, "step": 3110 }, { "epoch": 0.1700871348026653, "grad_norm": 8.25866413116455, "learning_rate": 9.494642750678774e-05, "loss": 1.6069, "step": 3111 }, { "epoch": 0.17014180762002393, "grad_norm": 2.4929847717285156, "learning_rate": 9.494254810511105e-05, "loss": 1.2093, "step": 3112 }, { "epoch": 0.17019648043738253, "grad_norm": 2.4574055671691895, "learning_rate": 9.49386672943004e-05, "loss": 1.2741, "step": 3113 }, { "epoch": 0.17025115325474116, "grad_norm": 2.762195587158203, "learning_rate": 9.493478507447744e-05, "loss": 1.0974, "step": 3114 }, { "epoch": 0.17030582607209976, "grad_norm": 2.335946559906006, "learning_rate": 9.493090144576391e-05, "loss": 1.2309, "step": 3115 }, { "epoch": 0.1703604988894584, "grad_norm": 3.0032894611358643, "learning_rate": 9.492701640828157e-05, "loss": 1.2284, "step": 3116 }, { "epoch": 0.17041517170681703, "grad_norm": 2.5921735763549805, "learning_rate": 9.492312996215224e-05, "loss": 1.202, "step": 3117 }, { "epoch": 0.17046984452417563, "grad_norm": 5.386680603027344, "learning_rate": 9.491924210749779e-05, "loss": 1.1352, "step": 3118 }, { "epoch": 0.17052451734153426, "grad_norm": 2.2814090251922607, "learning_rate": 9.491535284444009e-05, "loss": 0.9794, "step": 3119 }, { "epoch": 0.17057919015889286, "grad_norm": 3.0097577571868896, "learning_rate": 9.49114621731011e-05, "loss": 1.2063, "step": 3120 }, { "epoch": 0.1706338629762515, "grad_norm": 2.517380952835083, "learning_rate": 9.490757009360278e-05, "loss": 1.2931, "step": 3121 }, { "epoch": 0.17068853579361012, "grad_norm": 5.115128993988037, "learning_rate": 9.490367660606723e-05, "loss": 1.3408, "step": 3122 }, { "epoch": 0.17074320861096873, "grad_norm": 2.3972368240356445, "learning_rate": 9.489978171061646e-05, "loss": 1.2348, "step": 3123 }, { "epoch": 0.17079788142832736, "grad_norm": 2.3315021991729736, "learning_rate": 9.489588540737261e-05, "loss": 1.3122, "step": 3124 }, { "epoch": 0.17085255424568596, "grad_norm": 2.177610397338867, "learning_rate": 9.489198769645788e-05, "loss": 0.9998, "step": 3125 }, { "epoch": 0.1709072270630446, "grad_norm": 3.8203020095825195, "learning_rate": 9.488808857799443e-05, "loss": 1.0403, "step": 3126 }, { "epoch": 0.17096189988040322, "grad_norm": 2.8827853202819824, "learning_rate": 9.488418805210455e-05, "loss": 1.3269, "step": 3127 }, { "epoch": 0.17101657269776183, "grad_norm": 3.2110471725463867, "learning_rate": 9.48802861189105e-05, "loss": 1.3029, "step": 3128 }, { "epoch": 0.17107124551512046, "grad_norm": 2.506287097930908, "learning_rate": 9.487638277853466e-05, "loss": 1.1668, "step": 3129 }, { "epoch": 0.17112591833247906, "grad_norm": 2.8359882831573486, "learning_rate": 9.48724780310994e-05, "loss": 1.2974, "step": 3130 }, { "epoch": 0.1711805911498377, "grad_norm": 2.0537655353546143, "learning_rate": 9.486857187672715e-05, "loss": 1.0237, "step": 3131 }, { "epoch": 0.17123526396719632, "grad_norm": 2.9696226119995117, "learning_rate": 9.486466431554038e-05, "loss": 1.4609, "step": 3132 }, { "epoch": 0.17128993678455492, "grad_norm": 2.992600440979004, "learning_rate": 9.486075534766161e-05, "loss": 1.2824, "step": 3133 }, { "epoch": 0.17134460960191356, "grad_norm": 2.485802412033081, "learning_rate": 9.48568449732134e-05, "loss": 1.1384, "step": 3134 }, { "epoch": 0.17139928241927216, "grad_norm": 4.905906677246094, "learning_rate": 9.485293319231836e-05, "loss": 1.1438, "step": 3135 }, { "epoch": 0.1714539552366308, "grad_norm": 2.1532182693481445, "learning_rate": 9.484902000509915e-05, "loss": 0.9649, "step": 3136 }, { "epoch": 0.17150862805398942, "grad_norm": 3.343085289001465, "learning_rate": 9.484510541167845e-05, "loss": 1.121, "step": 3137 }, { "epoch": 0.17156330087134802, "grad_norm": 2.680293083190918, "learning_rate": 9.484118941217901e-05, "loss": 1.2517, "step": 3138 }, { "epoch": 0.17161797368870665, "grad_norm": 3.1376054286956787, "learning_rate": 9.48372720067236e-05, "loss": 1.0405, "step": 3139 }, { "epoch": 0.17167264650606526, "grad_norm": 5.197237968444824, "learning_rate": 9.483335319543505e-05, "loss": 1.4676, "step": 3140 }, { "epoch": 0.1717273193234239, "grad_norm": 2.294264793395996, "learning_rate": 9.482943297843625e-05, "loss": 1.0534, "step": 3141 }, { "epoch": 0.1717819921407825, "grad_norm": 2.466923952102661, "learning_rate": 9.482551135585008e-05, "loss": 1.2741, "step": 3142 }, { "epoch": 0.17183666495814112, "grad_norm": 2.596616268157959, "learning_rate": 9.482158832779953e-05, "loss": 1.1466, "step": 3143 }, { "epoch": 0.17189133777549975, "grad_norm": 3.2436201572418213, "learning_rate": 9.481766389440759e-05, "loss": 1.1936, "step": 3144 }, { "epoch": 0.17194601059285836, "grad_norm": 2.617035150527954, "learning_rate": 9.481373805579729e-05, "loss": 1.1256, "step": 3145 }, { "epoch": 0.172000683410217, "grad_norm": 2.3738274574279785, "learning_rate": 9.480981081209178e-05, "loss": 0.9776, "step": 3146 }, { "epoch": 0.1720553562275756, "grad_norm": 2.8781614303588867, "learning_rate": 9.480588216341412e-05, "loss": 1.0144, "step": 3147 }, { "epoch": 0.17211002904493422, "grad_norm": 2.3174655437469482, "learning_rate": 9.480195210988754e-05, "loss": 1.1985, "step": 3148 }, { "epoch": 0.17216470186229285, "grad_norm": 3.373155117034912, "learning_rate": 9.479802065163524e-05, "loss": 1.03, "step": 3149 }, { "epoch": 0.17221937467965145, "grad_norm": 2.343677282333374, "learning_rate": 9.479408778878049e-05, "loss": 1.1569, "step": 3150 }, { "epoch": 0.17227404749701009, "grad_norm": 2.436638116836548, "learning_rate": 9.479015352144662e-05, "loss": 1.1063, "step": 3151 }, { "epoch": 0.1723287203143687, "grad_norm": 2.1385512351989746, "learning_rate": 9.478621784975696e-05, "loss": 1.1554, "step": 3152 }, { "epoch": 0.17238339313172732, "grad_norm": 2.775768756866455, "learning_rate": 9.478228077383493e-05, "loss": 0.9785, "step": 3153 }, { "epoch": 0.17243806594908595, "grad_norm": 2.916093349456787, "learning_rate": 9.477834229380397e-05, "loss": 1.2095, "step": 3154 }, { "epoch": 0.17249273876644455, "grad_norm": 2.718777894973755, "learning_rate": 9.477440240978754e-05, "loss": 1.1868, "step": 3155 }, { "epoch": 0.17254741158380318, "grad_norm": 2.693132162094116, "learning_rate": 9.477046112190921e-05, "loss": 1.1486, "step": 3156 }, { "epoch": 0.1726020844011618, "grad_norm": 2.2237892150878906, "learning_rate": 9.476651843029254e-05, "loss": 1.1627, "step": 3157 }, { "epoch": 0.17265675721852042, "grad_norm": 2.486419916152954, "learning_rate": 9.476257433506114e-05, "loss": 1.2553, "step": 3158 }, { "epoch": 0.17271143003587905, "grad_norm": 2.9892027378082275, "learning_rate": 9.47586288363387e-05, "loss": 1.1602, "step": 3159 }, { "epoch": 0.17276610285323765, "grad_norm": 3.051382541656494, "learning_rate": 9.47546819342489e-05, "loss": 1.1598, "step": 3160 }, { "epoch": 0.17282077567059628, "grad_norm": 2.635793685913086, "learning_rate": 9.475073362891551e-05, "loss": 1.1784, "step": 3161 }, { "epoch": 0.17287544848795489, "grad_norm": 2.573596477508545, "learning_rate": 9.474678392046231e-05, "loss": 1.1669, "step": 3162 }, { "epoch": 0.17293012130531352, "grad_norm": 3.1586837768554688, "learning_rate": 9.474283280901315e-05, "loss": 1.3175, "step": 3163 }, { "epoch": 0.17298479412267215, "grad_norm": 2.256115436553955, "learning_rate": 9.473888029469192e-05, "loss": 1.2575, "step": 3164 }, { "epoch": 0.17303946694003075, "grad_norm": 3.6150290966033936, "learning_rate": 9.473492637762253e-05, "loss": 1.2792, "step": 3165 }, { "epoch": 0.17309413975738938, "grad_norm": 2.33221173286438, "learning_rate": 9.473097105792897e-05, "loss": 1.2709, "step": 3166 }, { "epoch": 0.17314881257474798, "grad_norm": 2.631254196166992, "learning_rate": 9.472701433573523e-05, "loss": 1.2116, "step": 3167 }, { "epoch": 0.17320348539210662, "grad_norm": 2.3023993968963623, "learning_rate": 9.472305621116538e-05, "loss": 1.1777, "step": 3168 }, { "epoch": 0.17325815820946522, "grad_norm": 3.2163748741149902, "learning_rate": 9.471909668434354e-05, "loss": 1.2511, "step": 3169 }, { "epoch": 0.17331283102682385, "grad_norm": 2.8078114986419678, "learning_rate": 9.471513575539384e-05, "loss": 1.3661, "step": 3170 }, { "epoch": 0.17336750384418248, "grad_norm": 2.461378335952759, "learning_rate": 9.47111734244405e-05, "loss": 1.3982, "step": 3171 }, { "epoch": 0.17342217666154108, "grad_norm": 2.3670194149017334, "learning_rate": 9.470720969160772e-05, "loss": 1.2152, "step": 3172 }, { "epoch": 0.17347684947889971, "grad_norm": 2.6587910652160645, "learning_rate": 9.470324455701978e-05, "loss": 1.1884, "step": 3173 }, { "epoch": 0.17353152229625832, "grad_norm": 2.5301475524902344, "learning_rate": 9.469927802080102e-05, "loss": 0.9955, "step": 3174 }, { "epoch": 0.17358619511361695, "grad_norm": 2.4687106609344482, "learning_rate": 9.469531008307582e-05, "loss": 1.1001, "step": 3175 }, { "epoch": 0.17364086793097558, "grad_norm": 3.4619216918945312, "learning_rate": 9.469134074396856e-05, "loss": 0.9473, "step": 3176 }, { "epoch": 0.17369554074833418, "grad_norm": 2.5569562911987305, "learning_rate": 9.468737000360372e-05, "loss": 0.9599, "step": 3177 }, { "epoch": 0.1737502135656928, "grad_norm": 2.8251285552978516, "learning_rate": 9.468339786210578e-05, "loss": 1.075, "step": 3178 }, { "epoch": 0.17380488638305142, "grad_norm": 3.082033157348633, "learning_rate": 9.467942431959928e-05, "loss": 1.2088, "step": 3179 }, { "epoch": 0.17385955920041005, "grad_norm": 3.1233949661254883, "learning_rate": 9.467544937620885e-05, "loss": 1.2906, "step": 3180 }, { "epoch": 0.17391423201776868, "grad_norm": 2.852672576904297, "learning_rate": 9.467147303205905e-05, "loss": 1.1619, "step": 3181 }, { "epoch": 0.17396890483512728, "grad_norm": 2.9458343982696533, "learning_rate": 9.466749528727463e-05, "loss": 1.2007, "step": 3182 }, { "epoch": 0.1740235776524859, "grad_norm": 2.470313310623169, "learning_rate": 9.466351614198026e-05, "loss": 0.9477, "step": 3183 }, { "epoch": 0.17407825046984451, "grad_norm": 2.1653811931610107, "learning_rate": 9.465953559630071e-05, "loss": 1.1757, "step": 3184 }, { "epoch": 0.17413292328720315, "grad_norm": 3.230191230773926, "learning_rate": 9.465555365036078e-05, "loss": 1.154, "step": 3185 }, { "epoch": 0.17418759610456178, "grad_norm": 3.01529860496521, "learning_rate": 9.465157030428535e-05, "loss": 1.3341, "step": 3186 }, { "epoch": 0.17424226892192038, "grad_norm": 2.347074031829834, "learning_rate": 9.46475855581993e-05, "loss": 1.1362, "step": 3187 }, { "epoch": 0.174296941739279, "grad_norm": 3.3560259342193604, "learning_rate": 9.464359941222756e-05, "loss": 1.255, "step": 3188 }, { "epoch": 0.1743516145566376, "grad_norm": 2.768390417098999, "learning_rate": 9.463961186649512e-05, "loss": 1.259, "step": 3189 }, { "epoch": 0.17440628737399624, "grad_norm": 2.380225419998169, "learning_rate": 9.4635622921127e-05, "loss": 1.2475, "step": 3190 }, { "epoch": 0.17446096019135485, "grad_norm": 2.8013720512390137, "learning_rate": 9.463163257624827e-05, "loss": 1.1163, "step": 3191 }, { "epoch": 0.17451563300871348, "grad_norm": 2.300274133682251, "learning_rate": 9.462764083198405e-05, "loss": 0.9795, "step": 3192 }, { "epoch": 0.1745703058260721, "grad_norm": 2.301286458969116, "learning_rate": 9.462364768845948e-05, "loss": 0.9474, "step": 3193 }, { "epoch": 0.1746249786434307, "grad_norm": 2.79075026512146, "learning_rate": 9.46196531457998e-05, "loss": 1.3112, "step": 3194 }, { "epoch": 0.17467965146078934, "grad_norm": 2.3839337825775146, "learning_rate": 9.461565720413022e-05, "loss": 1.2272, "step": 3195 }, { "epoch": 0.17473432427814795, "grad_norm": 4.367537975311279, "learning_rate": 9.461165986357603e-05, "loss": 1.2455, "step": 3196 }, { "epoch": 0.17478899709550658, "grad_norm": 3.3555586338043213, "learning_rate": 9.460766112426258e-05, "loss": 1.29, "step": 3197 }, { "epoch": 0.1748436699128652, "grad_norm": 2.1022605895996094, "learning_rate": 9.460366098631523e-05, "loss": 1.1305, "step": 3198 }, { "epoch": 0.1748983427302238, "grad_norm": 2.156777858734131, "learning_rate": 9.459965944985942e-05, "loss": 1.1615, "step": 3199 }, { "epoch": 0.17495301554758244, "grad_norm": 3.116281747817993, "learning_rate": 9.459565651502061e-05, "loss": 1.1378, "step": 3200 }, { "epoch": 0.17500768836494104, "grad_norm": 2.786068916320801, "learning_rate": 9.45916521819243e-05, "loss": 1.1548, "step": 3201 }, { "epoch": 0.17506236118229968, "grad_norm": 3.149932384490967, "learning_rate": 9.458764645069605e-05, "loss": 1.2447, "step": 3202 }, { "epoch": 0.1751170339996583, "grad_norm": 3.4209136962890625, "learning_rate": 9.458363932146147e-05, "loss": 1.3045, "step": 3203 }, { "epoch": 0.1751717068170169, "grad_norm": 3.0424015522003174, "learning_rate": 9.457963079434615e-05, "loss": 1.2366, "step": 3204 }, { "epoch": 0.17522637963437554, "grad_norm": 2.99100399017334, "learning_rate": 9.457562086947582e-05, "loss": 1.1753, "step": 3205 }, { "epoch": 0.17528105245173414, "grad_norm": 3.258470296859741, "learning_rate": 9.45716095469762e-05, "loss": 1.3472, "step": 3206 }, { "epoch": 0.17533572526909277, "grad_norm": 2.8187150955200195, "learning_rate": 9.456759682697305e-05, "loss": 1.2759, "step": 3207 }, { "epoch": 0.1753903980864514, "grad_norm": 2.6988108158111572, "learning_rate": 9.456358270959218e-05, "loss": 1.1987, "step": 3208 }, { "epoch": 0.17544507090381, "grad_norm": 3.029217481613159, "learning_rate": 9.455956719495947e-05, "loss": 1.1488, "step": 3209 }, { "epoch": 0.17549974372116864, "grad_norm": 2.280675172805786, "learning_rate": 9.455555028320082e-05, "loss": 1.0902, "step": 3210 }, { "epoch": 0.17555441653852724, "grad_norm": 3.186025857925415, "learning_rate": 9.455153197444215e-05, "loss": 1.0525, "step": 3211 }, { "epoch": 0.17560908935588587, "grad_norm": 3.1766231060028076, "learning_rate": 9.454751226880949e-05, "loss": 1.3112, "step": 3212 }, { "epoch": 0.1756637621732445, "grad_norm": 2.4409360885620117, "learning_rate": 9.454349116642885e-05, "loss": 1.171, "step": 3213 }, { "epoch": 0.1757184349906031, "grad_norm": 3.18888783454895, "learning_rate": 9.453946866742632e-05, "loss": 1.3264, "step": 3214 }, { "epoch": 0.17577310780796174, "grad_norm": 2.9366157054901123, "learning_rate": 9.453544477192799e-05, "loss": 1.2625, "step": 3215 }, { "epoch": 0.17582778062532034, "grad_norm": 2.306110143661499, "learning_rate": 9.453141948006008e-05, "loss": 1.1864, "step": 3216 }, { "epoch": 0.17588245344267897, "grad_norm": 2.7899744510650635, "learning_rate": 9.452739279194876e-05, "loss": 1.1028, "step": 3217 }, { "epoch": 0.17593712626003757, "grad_norm": 2.6768712997436523, "learning_rate": 9.452336470772027e-05, "loss": 1.0842, "step": 3218 }, { "epoch": 0.1759917990773962, "grad_norm": 2.7894535064697266, "learning_rate": 9.451933522750096e-05, "loss": 1.2687, "step": 3219 }, { "epoch": 0.17604647189475484, "grad_norm": 2.843968391418457, "learning_rate": 9.451530435141713e-05, "loss": 1.4273, "step": 3220 }, { "epoch": 0.17610114471211344, "grad_norm": 3.6054699420928955, "learning_rate": 9.451127207959516e-05, "loss": 0.9493, "step": 3221 }, { "epoch": 0.17615581752947207, "grad_norm": 2.7355451583862305, "learning_rate": 9.450723841216151e-05, "loss": 1.1345, "step": 3222 }, { "epoch": 0.17621049034683067, "grad_norm": 2.552727699279785, "learning_rate": 9.450320334924264e-05, "loss": 1.0691, "step": 3223 }, { "epoch": 0.1762651631641893, "grad_norm": 2.2425150871276855, "learning_rate": 9.449916689096505e-05, "loss": 1.2217, "step": 3224 }, { "epoch": 0.17631983598154793, "grad_norm": 2.4626271724700928, "learning_rate": 9.449512903745532e-05, "loss": 1.2306, "step": 3225 }, { "epoch": 0.17637450879890654, "grad_norm": 2.6591079235076904, "learning_rate": 9.449108978884003e-05, "loss": 1.1006, "step": 3226 }, { "epoch": 0.17642918161626517, "grad_norm": 2.4703562259674072, "learning_rate": 9.448704914524586e-05, "loss": 1.2226, "step": 3227 }, { "epoch": 0.17648385443362377, "grad_norm": 2.2021281719207764, "learning_rate": 9.448300710679947e-05, "loss": 1.214, "step": 3228 }, { "epoch": 0.1765385272509824, "grad_norm": 2.6572539806365967, "learning_rate": 9.447896367362762e-05, "loss": 1.3404, "step": 3229 }, { "epoch": 0.17659320006834103, "grad_norm": 2.5361897945404053, "learning_rate": 9.447491884585706e-05, "loss": 1.2566, "step": 3230 }, { "epoch": 0.17664787288569964, "grad_norm": 2.1677422523498535, "learning_rate": 9.447087262361464e-05, "loss": 1.0027, "step": 3231 }, { "epoch": 0.17670254570305827, "grad_norm": 2.993016004562378, "learning_rate": 9.44668250070272e-05, "loss": 1.2951, "step": 3232 }, { "epoch": 0.17675721852041687, "grad_norm": 2.645932197570801, "learning_rate": 9.446277599622167e-05, "loss": 1.0941, "step": 3233 }, { "epoch": 0.1768118913377755, "grad_norm": 3.5866143703460693, "learning_rate": 9.4458725591325e-05, "loss": 1.1606, "step": 3234 }, { "epoch": 0.17686656415513413, "grad_norm": 2.3287086486816406, "learning_rate": 9.445467379246418e-05, "loss": 1.238, "step": 3235 }, { "epoch": 0.17692123697249273, "grad_norm": 2.5985074043273926, "learning_rate": 9.445062059976624e-05, "loss": 1.0857, "step": 3236 }, { "epoch": 0.17697590978985137, "grad_norm": 2.472299098968506, "learning_rate": 9.444656601335829e-05, "loss": 1.1286, "step": 3237 }, { "epoch": 0.17703058260720997, "grad_norm": 2.1222314834594727, "learning_rate": 9.444251003336744e-05, "loss": 1.2171, "step": 3238 }, { "epoch": 0.1770852554245686, "grad_norm": 2.4045140743255615, "learning_rate": 9.443845265992088e-05, "loss": 1.1776, "step": 3239 }, { "epoch": 0.17713992824192723, "grad_norm": 3.153996706008911, "learning_rate": 9.443439389314581e-05, "loss": 1.1591, "step": 3240 }, { "epoch": 0.17719460105928583, "grad_norm": 2.7562272548675537, "learning_rate": 9.443033373316948e-05, "loss": 1.2661, "step": 3241 }, { "epoch": 0.17724927387664446, "grad_norm": 2.543975830078125, "learning_rate": 9.442627218011922e-05, "loss": 1.2485, "step": 3242 }, { "epoch": 0.17730394669400307, "grad_norm": 2.2361507415771484, "learning_rate": 9.442220923412234e-05, "loss": 1.1536, "step": 3243 }, { "epoch": 0.1773586195113617, "grad_norm": 2.597398281097412, "learning_rate": 9.441814489530626e-05, "loss": 1.199, "step": 3244 }, { "epoch": 0.1774132923287203, "grad_norm": 2.4685497283935547, "learning_rate": 9.441407916379841e-05, "loss": 1.2747, "step": 3245 }, { "epoch": 0.17746796514607893, "grad_norm": 2.744285821914673, "learning_rate": 9.441001203972624e-05, "loss": 1.4093, "step": 3246 }, { "epoch": 0.17752263796343756, "grad_norm": 2.7199792861938477, "learning_rate": 9.440594352321732e-05, "loss": 1.1384, "step": 3247 }, { "epoch": 0.17757731078079617, "grad_norm": 2.262204647064209, "learning_rate": 9.440187361439917e-05, "loss": 1.1442, "step": 3248 }, { "epoch": 0.1776319835981548, "grad_norm": 2.430962324142456, "learning_rate": 9.439780231339943e-05, "loss": 1.0488, "step": 3249 }, { "epoch": 0.1776866564155134, "grad_norm": 2.2968192100524902, "learning_rate": 9.439372962034572e-05, "loss": 1.2007, "step": 3250 }, { "epoch": 0.17774132923287203, "grad_norm": 2.870173454284668, "learning_rate": 9.438965553536577e-05, "loss": 0.9478, "step": 3251 }, { "epoch": 0.17779600205023066, "grad_norm": 2.0916478633880615, "learning_rate": 9.43855800585873e-05, "loss": 1.0474, "step": 3252 }, { "epoch": 0.17785067486758926, "grad_norm": 2.8872733116149902, "learning_rate": 9.438150319013809e-05, "loss": 1.3235, "step": 3253 }, { "epoch": 0.1779053476849479, "grad_norm": 3.1116015911102295, "learning_rate": 9.437742493014598e-05, "loss": 1.3334, "step": 3254 }, { "epoch": 0.1779600205023065, "grad_norm": 3.0507688522338867, "learning_rate": 9.437334527873884e-05, "loss": 1.3024, "step": 3255 }, { "epoch": 0.17801469331966513, "grad_norm": 2.86324143409729, "learning_rate": 9.436926423604456e-05, "loss": 1.4441, "step": 3256 }, { "epoch": 0.17806936613702376, "grad_norm": 2.2057607173919678, "learning_rate": 9.436518180219112e-05, "loss": 1.1484, "step": 3257 }, { "epoch": 0.17812403895438236, "grad_norm": 2.7711894512176514, "learning_rate": 9.436109797730653e-05, "loss": 1.0974, "step": 3258 }, { "epoch": 0.178178711771741, "grad_norm": 2.431110382080078, "learning_rate": 9.43570127615188e-05, "loss": 1.028, "step": 3259 }, { "epoch": 0.1782333845890996, "grad_norm": 2.409475326538086, "learning_rate": 9.435292615495604e-05, "loss": 1.1384, "step": 3260 }, { "epoch": 0.17828805740645823, "grad_norm": 2.4152281284332275, "learning_rate": 9.43488381577464e-05, "loss": 1.1715, "step": 3261 }, { "epoch": 0.17834273022381686, "grad_norm": 2.8702754974365234, "learning_rate": 9.434474877001802e-05, "loss": 1.0865, "step": 3262 }, { "epoch": 0.17839740304117546, "grad_norm": 2.3191521167755127, "learning_rate": 9.434065799189913e-05, "loss": 1.0354, "step": 3263 }, { "epoch": 0.1784520758585341, "grad_norm": 2.6960060596466064, "learning_rate": 9.433656582351802e-05, "loss": 1.3118, "step": 3264 }, { "epoch": 0.1785067486758927, "grad_norm": 2.171616315841675, "learning_rate": 9.433247226500295e-05, "loss": 1.1631, "step": 3265 }, { "epoch": 0.17856142149325133, "grad_norm": 2.7366509437561035, "learning_rate": 9.432837731648231e-05, "loss": 0.8339, "step": 3266 }, { "epoch": 0.17861609431060996, "grad_norm": 2.7880704402923584, "learning_rate": 9.432428097808447e-05, "loss": 1.0532, "step": 3267 }, { "epoch": 0.17867076712796856, "grad_norm": 2.703296184539795, "learning_rate": 9.432018324993788e-05, "loss": 1.3266, "step": 3268 }, { "epoch": 0.1787254399453272, "grad_norm": 2.1086184978485107, "learning_rate": 9.431608413217101e-05, "loss": 1.0521, "step": 3269 }, { "epoch": 0.1787801127626858, "grad_norm": 2.8605778217315674, "learning_rate": 9.43119836249124e-05, "loss": 1.2961, "step": 3270 }, { "epoch": 0.17883478558004443, "grad_norm": 3.5108699798583984, "learning_rate": 9.430788172829059e-05, "loss": 1.0659, "step": 3271 }, { "epoch": 0.17888945839740303, "grad_norm": 2.585390329360962, "learning_rate": 9.430377844243422e-05, "loss": 1.178, "step": 3272 }, { "epoch": 0.17894413121476166, "grad_norm": 2.3359978199005127, "learning_rate": 9.429967376747194e-05, "loss": 1.0794, "step": 3273 }, { "epoch": 0.1789988040321203, "grad_norm": 2.154733180999756, "learning_rate": 9.429556770353242e-05, "loss": 1.1805, "step": 3274 }, { "epoch": 0.1790534768494789, "grad_norm": 2.249802827835083, "learning_rate": 9.429146025074444e-05, "loss": 1.2061, "step": 3275 }, { "epoch": 0.17910814966683752, "grad_norm": 2.361093282699585, "learning_rate": 9.428735140923678e-05, "loss": 1.1957, "step": 3276 }, { "epoch": 0.17916282248419613, "grad_norm": 3.210597038269043, "learning_rate": 9.428324117913824e-05, "loss": 1.0875, "step": 3277 }, { "epoch": 0.17921749530155476, "grad_norm": 3.5239007472991943, "learning_rate": 9.427912956057772e-05, "loss": 1.2193, "step": 3278 }, { "epoch": 0.1792721681189134, "grad_norm": 2.8069961071014404, "learning_rate": 9.427501655368414e-05, "loss": 1.228, "step": 3279 }, { "epoch": 0.179326840936272, "grad_norm": 2.7926063537597656, "learning_rate": 9.427090215858643e-05, "loss": 1.1671, "step": 3280 }, { "epoch": 0.17938151375363062, "grad_norm": 3.360649585723877, "learning_rate": 9.426678637541362e-05, "loss": 1.2465, "step": 3281 }, { "epoch": 0.17943618657098923, "grad_norm": 2.5641281604766846, "learning_rate": 9.426266920429473e-05, "loss": 1.0958, "step": 3282 }, { "epoch": 0.17949085938834786, "grad_norm": 2.9353208541870117, "learning_rate": 9.425855064535889e-05, "loss": 1.1508, "step": 3283 }, { "epoch": 0.1795455322057065, "grad_norm": 2.62848162651062, "learning_rate": 9.425443069873519e-05, "loss": 1.1956, "step": 3284 }, { "epoch": 0.1796002050230651, "grad_norm": 3.8185927867889404, "learning_rate": 9.425030936455284e-05, "loss": 1.4291, "step": 3285 }, { "epoch": 0.17965487784042372, "grad_norm": 2.857917547225952, "learning_rate": 9.424618664294106e-05, "loss": 1.2752, "step": 3286 }, { "epoch": 0.17970955065778232, "grad_norm": 2.5346226692199707, "learning_rate": 9.42420625340291e-05, "loss": 1.0369, "step": 3287 }, { "epoch": 0.17976422347514096, "grad_norm": 2.783055543899536, "learning_rate": 9.423793703794626e-05, "loss": 1.0654, "step": 3288 }, { "epoch": 0.17981889629249959, "grad_norm": 3.508291006088257, "learning_rate": 9.423381015482191e-05, "loss": 1.2284, "step": 3289 }, { "epoch": 0.1798735691098582, "grad_norm": 2.876389265060425, "learning_rate": 9.422968188478542e-05, "loss": 1.1578, "step": 3290 }, { "epoch": 0.17992824192721682, "grad_norm": 2.174298048019409, "learning_rate": 9.422555222796628e-05, "loss": 1.1848, "step": 3291 }, { "epoch": 0.17998291474457542, "grad_norm": 2.191699743270874, "learning_rate": 9.42214211844939e-05, "loss": 1.2367, "step": 3292 }, { "epoch": 0.18003758756193405, "grad_norm": 2.486264705657959, "learning_rate": 9.421728875449787e-05, "loss": 1.2717, "step": 3293 }, { "epoch": 0.18009226037929266, "grad_norm": 2.35624623298645, "learning_rate": 9.421315493810774e-05, "loss": 0.931, "step": 3294 }, { "epoch": 0.1801469331966513, "grad_norm": 2.5119943618774414, "learning_rate": 9.420901973545309e-05, "loss": 1.1479, "step": 3295 }, { "epoch": 0.18020160601400992, "grad_norm": 2.3332622051239014, "learning_rate": 9.420488314666361e-05, "loss": 0.9435, "step": 3296 }, { "epoch": 0.18025627883136852, "grad_norm": 2.6883440017700195, "learning_rate": 9.420074517186899e-05, "loss": 1.0882, "step": 3297 }, { "epoch": 0.18031095164872715, "grad_norm": 2.770064353942871, "learning_rate": 9.419660581119895e-05, "loss": 1.2614, "step": 3298 }, { "epoch": 0.18036562446608576, "grad_norm": 2.1774189472198486, "learning_rate": 9.419246506478334e-05, "loss": 1.1619, "step": 3299 }, { "epoch": 0.1804202972834444, "grad_norm": 2.6091487407684326, "learning_rate": 9.418832293275191e-05, "loss": 1.2402, "step": 3300 }, { "epoch": 0.18047497010080302, "grad_norm": 2.350942850112915, "learning_rate": 9.418417941523459e-05, "loss": 0.9877, "step": 3301 }, { "epoch": 0.18052964291816162, "grad_norm": 2.308431386947632, "learning_rate": 9.418003451236125e-05, "loss": 1.1838, "step": 3302 }, { "epoch": 0.18058431573552025, "grad_norm": 2.1895790100097656, "learning_rate": 9.41758882242619e-05, "loss": 0.9289, "step": 3303 }, { "epoch": 0.18063898855287885, "grad_norm": 2.811534881591797, "learning_rate": 9.417174055106652e-05, "loss": 1.305, "step": 3304 }, { "epoch": 0.18069366137023748, "grad_norm": 3.1434247493743896, "learning_rate": 9.416759149290513e-05, "loss": 1.1992, "step": 3305 }, { "epoch": 0.18074833418759612, "grad_norm": 2.4969327449798584, "learning_rate": 9.416344104990787e-05, "loss": 1.2199, "step": 3306 }, { "epoch": 0.18080300700495472, "grad_norm": 2.4098117351531982, "learning_rate": 9.415928922220485e-05, "loss": 1.0997, "step": 3307 }, { "epoch": 0.18085767982231335, "grad_norm": 3.181250810623169, "learning_rate": 9.415513600992623e-05, "loss": 1.0293, "step": 3308 }, { "epoch": 0.18091235263967195, "grad_norm": 2.5383710861206055, "learning_rate": 9.415098141320225e-05, "loss": 1.1178, "step": 3309 }, { "epoch": 0.18096702545703058, "grad_norm": 2.7847161293029785, "learning_rate": 9.414682543216318e-05, "loss": 1.1693, "step": 3310 }, { "epoch": 0.18102169827438921, "grad_norm": 2.7835004329681396, "learning_rate": 9.41426680669393e-05, "loss": 1.1314, "step": 3311 }, { "epoch": 0.18107637109174782, "grad_norm": 2.890174627304077, "learning_rate": 9.413850931766099e-05, "loss": 1.1203, "step": 3312 }, { "epoch": 0.18113104390910645, "grad_norm": 2.067645311355591, "learning_rate": 9.413434918445863e-05, "loss": 1.1779, "step": 3313 }, { "epoch": 0.18118571672646505, "grad_norm": 2.1205430030822754, "learning_rate": 9.413018766746266e-05, "loss": 1.046, "step": 3314 }, { "epoch": 0.18124038954382368, "grad_norm": 2.9416701793670654, "learning_rate": 9.412602476680357e-05, "loss": 1.3679, "step": 3315 }, { "epoch": 0.1812950623611823, "grad_norm": 2.899562120437622, "learning_rate": 9.412186048261184e-05, "loss": 1.167, "step": 3316 }, { "epoch": 0.18134973517854092, "grad_norm": 2.5529046058654785, "learning_rate": 9.411769481501811e-05, "loss": 1.1452, "step": 3317 }, { "epoch": 0.18140440799589955, "grad_norm": 2.802694082260132, "learning_rate": 9.411352776415292e-05, "loss": 1.0317, "step": 3318 }, { "epoch": 0.18145908081325815, "grad_norm": 2.6332972049713135, "learning_rate": 9.410935933014698e-05, "loss": 1.1524, "step": 3319 }, { "epoch": 0.18151375363061678, "grad_norm": 2.8383421897888184, "learning_rate": 9.410518951313094e-05, "loss": 1.3053, "step": 3320 }, { "epoch": 0.18156842644797538, "grad_norm": 2.451789617538452, "learning_rate": 9.410101831323558e-05, "loss": 1.1121, "step": 3321 }, { "epoch": 0.18162309926533401, "grad_norm": 4.216357231140137, "learning_rate": 9.409684573059168e-05, "loss": 1.047, "step": 3322 }, { "epoch": 0.18167777208269265, "grad_norm": 2.3802647590637207, "learning_rate": 9.409267176533003e-05, "loss": 1.1111, "step": 3323 }, { "epoch": 0.18173244490005125, "grad_norm": 3.362421989440918, "learning_rate": 9.408849641758155e-05, "loss": 1.1552, "step": 3324 }, { "epoch": 0.18178711771740988, "grad_norm": 2.03151535987854, "learning_rate": 9.408431968747714e-05, "loss": 0.9248, "step": 3325 }, { "epoch": 0.18184179053476848, "grad_norm": 3.007324695587158, "learning_rate": 9.40801415751477e-05, "loss": 0.995, "step": 3326 }, { "epoch": 0.1818964633521271, "grad_norm": 2.739060640335083, "learning_rate": 9.407596208072433e-05, "loss": 1.0737, "step": 3327 }, { "epoch": 0.18195113616948574, "grad_norm": 10.118335723876953, "learning_rate": 9.407178120433801e-05, "loss": 1.1626, "step": 3328 }, { "epoch": 0.18200580898684435, "grad_norm": 2.4429738521575928, "learning_rate": 9.406759894611983e-05, "loss": 1.0631, "step": 3329 }, { "epoch": 0.18206048180420298, "grad_norm": 2.981522560119629, "learning_rate": 9.406341530620095e-05, "loss": 1.1303, "step": 3330 }, { "epoch": 0.18211515462156158, "grad_norm": 2.9693233966827393, "learning_rate": 9.405923028471252e-05, "loss": 1.1666, "step": 3331 }, { "epoch": 0.1821698274389202, "grad_norm": 3.0063815116882324, "learning_rate": 9.405504388178577e-05, "loss": 1.0195, "step": 3332 }, { "epoch": 0.18222450025627884, "grad_norm": 2.223527193069458, "learning_rate": 9.405085609755195e-05, "loss": 1.0338, "step": 3333 }, { "epoch": 0.18227917307363745, "grad_norm": 3.09635853767395, "learning_rate": 9.404666693214238e-05, "loss": 1.4122, "step": 3334 }, { "epoch": 0.18233384589099608, "grad_norm": 5.268616676330566, "learning_rate": 9.404247638568839e-05, "loss": 1.238, "step": 3335 }, { "epoch": 0.18238851870835468, "grad_norm": 2.2849814891815186, "learning_rate": 9.40382844583214e-05, "loss": 1.2402, "step": 3336 }, { "epoch": 0.1824431915257133, "grad_norm": 2.1077587604522705, "learning_rate": 9.403409115017279e-05, "loss": 0.9902, "step": 3337 }, { "epoch": 0.18249786434307194, "grad_norm": 2.4042556285858154, "learning_rate": 9.40298964613741e-05, "loss": 0.9551, "step": 3338 }, { "epoch": 0.18255253716043054, "grad_norm": 3.1469244956970215, "learning_rate": 9.40257003920568e-05, "loss": 1.2712, "step": 3339 }, { "epoch": 0.18260720997778918, "grad_norm": 2.89540433883667, "learning_rate": 9.402150294235249e-05, "loss": 1.2386, "step": 3340 }, { "epoch": 0.18266188279514778, "grad_norm": 3.3014893531799316, "learning_rate": 9.401730411239276e-05, "loss": 1.1965, "step": 3341 }, { "epoch": 0.1827165556125064, "grad_norm": 2.300569772720337, "learning_rate": 9.401310390230926e-05, "loss": 1.312, "step": 3342 }, { "epoch": 0.18277122842986504, "grad_norm": 3.07293701171875, "learning_rate": 9.400890231223369e-05, "loss": 1.2876, "step": 3343 }, { "epoch": 0.18282590124722364, "grad_norm": 2.869682788848877, "learning_rate": 9.400469934229778e-05, "loss": 1.2035, "step": 3344 }, { "epoch": 0.18288057406458227, "grad_norm": 2.441895008087158, "learning_rate": 9.400049499263333e-05, "loss": 1.3001, "step": 3345 }, { "epoch": 0.18293524688194088, "grad_norm": 2.351923704147339, "learning_rate": 9.399628926337214e-05, "loss": 1.1155, "step": 3346 }, { "epoch": 0.1829899196992995, "grad_norm": 1.8867982625961304, "learning_rate": 9.399208215464607e-05, "loss": 1.0933, "step": 3347 }, { "epoch": 0.1830445925166581, "grad_norm": 2.2394204139709473, "learning_rate": 9.398787366658708e-05, "loss": 1.1196, "step": 3348 }, { "epoch": 0.18309926533401674, "grad_norm": 2.606785774230957, "learning_rate": 9.398366379932705e-05, "loss": 1.1658, "step": 3349 }, { "epoch": 0.18315393815137537, "grad_norm": 2.8161699771881104, "learning_rate": 9.397945255299805e-05, "loss": 1.3079, "step": 3350 }, { "epoch": 0.18320861096873398, "grad_norm": 2.55672025680542, "learning_rate": 9.397523992773207e-05, "loss": 1.1445, "step": 3351 }, { "epoch": 0.1832632837860926, "grad_norm": 2.691633939743042, "learning_rate": 9.397102592366123e-05, "loss": 1.2573, "step": 3352 }, { "epoch": 0.1833179566034512, "grad_norm": 2.3272011280059814, "learning_rate": 9.39668105409176e-05, "loss": 1.271, "step": 3353 }, { "epoch": 0.18337262942080984, "grad_norm": 2.594379186630249, "learning_rate": 9.39625937796334e-05, "loss": 1.2683, "step": 3354 }, { "epoch": 0.18342730223816847, "grad_norm": 3.1318845748901367, "learning_rate": 9.395837563994085e-05, "loss": 1.4972, "step": 3355 }, { "epoch": 0.18348197505552707, "grad_norm": 2.488172769546509, "learning_rate": 9.395415612197216e-05, "loss": 1.167, "step": 3356 }, { "epoch": 0.1835366478728857, "grad_norm": 2.8879148960113525, "learning_rate": 9.394993522585966e-05, "loss": 1.3068, "step": 3357 }, { "epoch": 0.1835913206902443, "grad_norm": 2.997746229171753, "learning_rate": 9.394571295173569e-05, "loss": 1.182, "step": 3358 }, { "epoch": 0.18364599350760294, "grad_norm": 2.5340514183044434, "learning_rate": 9.394148929973262e-05, "loss": 1.0603, "step": 3359 }, { "epoch": 0.18370066632496157, "grad_norm": 2.3911855220794678, "learning_rate": 9.39372642699829e-05, "loss": 1.0672, "step": 3360 }, { "epoch": 0.18375533914232017, "grad_norm": 3.0592124462127686, "learning_rate": 9.393303786261897e-05, "loss": 1.4049, "step": 3361 }, { "epoch": 0.1838100119596788, "grad_norm": 2.2085278034210205, "learning_rate": 9.392881007777341e-05, "loss": 1.0434, "step": 3362 }, { "epoch": 0.1838646847770374, "grad_norm": 2.3640058040618896, "learning_rate": 9.39245809155787e-05, "loss": 1.2377, "step": 3363 }, { "epoch": 0.18391935759439604, "grad_norm": 2.078669309616089, "learning_rate": 9.39203503761675e-05, "loss": 1.1893, "step": 3364 }, { "epoch": 0.18397403041175467, "grad_norm": 2.577765941619873, "learning_rate": 9.391611845967244e-05, "loss": 1.0986, "step": 3365 }, { "epoch": 0.18402870322911327, "grad_norm": 2.1617136001586914, "learning_rate": 9.391188516622617e-05, "loss": 1.1069, "step": 3366 }, { "epoch": 0.1840833760464719, "grad_norm": 2.587409257888794, "learning_rate": 9.390765049596147e-05, "loss": 1.1247, "step": 3367 }, { "epoch": 0.1841380488638305, "grad_norm": 2.789665699005127, "learning_rate": 9.390341444901109e-05, "loss": 1.4123, "step": 3368 }, { "epoch": 0.18419272168118914, "grad_norm": 2.718796730041504, "learning_rate": 9.389917702550786e-05, "loss": 1.1123, "step": 3369 }, { "epoch": 0.18424739449854774, "grad_norm": 4.224709510803223, "learning_rate": 9.389493822558463e-05, "loss": 1.152, "step": 3370 }, { "epoch": 0.18430206731590637, "grad_norm": 4.020953178405762, "learning_rate": 9.389069804937431e-05, "loss": 1.0972, "step": 3371 }, { "epoch": 0.184356740133265, "grad_norm": 3.6084961891174316, "learning_rate": 9.388645649700985e-05, "loss": 1.1067, "step": 3372 }, { "epoch": 0.1844114129506236, "grad_norm": 2.9537675380706787, "learning_rate": 9.388221356862422e-05, "loss": 1.1429, "step": 3373 }, { "epoch": 0.18446608576798224, "grad_norm": 3.023952007293701, "learning_rate": 9.387796926435049e-05, "loss": 1.1994, "step": 3374 }, { "epoch": 0.18452075858534084, "grad_norm": 2.669551372528076, "learning_rate": 9.387372358432169e-05, "loss": 1.3685, "step": 3375 }, { "epoch": 0.18457543140269947, "grad_norm": 2.14147686958313, "learning_rate": 9.386947652867098e-05, "loss": 1.2132, "step": 3376 }, { "epoch": 0.1846301042200581, "grad_norm": 2.704049587249756, "learning_rate": 9.386522809753151e-05, "loss": 1.2923, "step": 3377 }, { "epoch": 0.1846847770374167, "grad_norm": 3.012895345687866, "learning_rate": 9.386097829103648e-05, "loss": 1.3864, "step": 3378 }, { "epoch": 0.18473944985477533, "grad_norm": 2.155993700027466, "learning_rate": 9.385672710931914e-05, "loss": 1.0195, "step": 3379 }, { "epoch": 0.18479412267213394, "grad_norm": 2.162893772125244, "learning_rate": 9.385247455251279e-05, "loss": 1.2227, "step": 3380 }, { "epoch": 0.18484879548949257, "grad_norm": 2.371933698654175, "learning_rate": 9.384822062075075e-05, "loss": 1.1194, "step": 3381 }, { "epoch": 0.1849034683068512, "grad_norm": 2.9482109546661377, "learning_rate": 9.384396531416643e-05, "loss": 0.9119, "step": 3382 }, { "epoch": 0.1849581411242098, "grad_norm": 2.384021043777466, "learning_rate": 9.38397086328932e-05, "loss": 1.0479, "step": 3383 }, { "epoch": 0.18501281394156843, "grad_norm": 2.678468942642212, "learning_rate": 9.383545057706458e-05, "loss": 1.2517, "step": 3384 }, { "epoch": 0.18506748675892704, "grad_norm": 2.133734703063965, "learning_rate": 9.383119114681402e-05, "loss": 0.879, "step": 3385 }, { "epoch": 0.18512215957628567, "grad_norm": 2.2086262702941895, "learning_rate": 9.382693034227512e-05, "loss": 1.1583, "step": 3386 }, { "epoch": 0.1851768323936443, "grad_norm": 2.314211845397949, "learning_rate": 9.382266816358147e-05, "loss": 1.1637, "step": 3387 }, { "epoch": 0.1852315052110029, "grad_norm": 2.3569176197052, "learning_rate": 9.381840461086666e-05, "loss": 1.2031, "step": 3388 }, { "epoch": 0.18528617802836153, "grad_norm": 2.42075514793396, "learning_rate": 9.381413968426442e-05, "loss": 1.2204, "step": 3389 }, { "epoch": 0.18534085084572013, "grad_norm": 2.6111104488372803, "learning_rate": 9.380987338390846e-05, "loss": 1.1416, "step": 3390 }, { "epoch": 0.18539552366307877, "grad_norm": 1.9383550882339478, "learning_rate": 9.380560570993253e-05, "loss": 1.0538, "step": 3391 }, { "epoch": 0.1854501964804374, "grad_norm": 2.5393009185791016, "learning_rate": 9.380133666247046e-05, "loss": 1.1825, "step": 3392 }, { "epoch": 0.185504869297796, "grad_norm": 2.4218637943267822, "learning_rate": 9.379706624165609e-05, "loss": 1.1477, "step": 3393 }, { "epoch": 0.18555954211515463, "grad_norm": 2.2830333709716797, "learning_rate": 9.379279444762333e-05, "loss": 1.2049, "step": 3394 }, { "epoch": 0.18561421493251323, "grad_norm": 2.9498648643493652, "learning_rate": 9.378852128050608e-05, "loss": 1.167, "step": 3395 }, { "epoch": 0.18566888774987186, "grad_norm": 2.6098527908325195, "learning_rate": 9.378424674043838e-05, "loss": 1.1108, "step": 3396 }, { "epoch": 0.18572356056723047, "grad_norm": 2.551426887512207, "learning_rate": 9.37799708275542e-05, "loss": 1.1613, "step": 3397 }, { "epoch": 0.1857782333845891, "grad_norm": 2.9057867527008057, "learning_rate": 9.377569354198764e-05, "loss": 1.1152, "step": 3398 }, { "epoch": 0.18583290620194773, "grad_norm": 2.672557830810547, "learning_rate": 9.377141488387279e-05, "loss": 1.1409, "step": 3399 }, { "epoch": 0.18588757901930633, "grad_norm": 4.309108257293701, "learning_rate": 9.376713485334381e-05, "loss": 1.3384, "step": 3400 }, { "epoch": 0.18594225183666496, "grad_norm": 3.5303235054016113, "learning_rate": 9.376285345053491e-05, "loss": 1.2795, "step": 3401 }, { "epoch": 0.18599692465402357, "grad_norm": 2.643083095550537, "learning_rate": 9.375857067558031e-05, "loss": 1.1759, "step": 3402 }, { "epoch": 0.1860515974713822, "grad_norm": 2.0731093883514404, "learning_rate": 9.375428652861432e-05, "loss": 1.148, "step": 3403 }, { "epoch": 0.18610627028874083, "grad_norm": 2.838914632797241, "learning_rate": 9.375000100977125e-05, "loss": 1.0955, "step": 3404 }, { "epoch": 0.18616094310609943, "grad_norm": 2.703752279281616, "learning_rate": 9.374571411918545e-05, "loss": 1.1783, "step": 3405 }, { "epoch": 0.18621561592345806, "grad_norm": 2.325361728668213, "learning_rate": 9.374142585699135e-05, "loss": 0.967, "step": 3406 }, { "epoch": 0.18627028874081666, "grad_norm": 2.409684896469116, "learning_rate": 9.373713622332341e-05, "loss": 1.0616, "step": 3407 }, { "epoch": 0.1863249615581753, "grad_norm": 3.106468915939331, "learning_rate": 9.373284521831612e-05, "loss": 1.2036, "step": 3408 }, { "epoch": 0.18637963437553393, "grad_norm": 2.227322578430176, "learning_rate": 9.372855284210403e-05, "loss": 1.1036, "step": 3409 }, { "epoch": 0.18643430719289253, "grad_norm": 2.9674947261810303, "learning_rate": 9.37242590948217e-05, "loss": 1.14, "step": 3410 }, { "epoch": 0.18648898001025116, "grad_norm": 2.2721450328826904, "learning_rate": 9.371996397660377e-05, "loss": 1.1949, "step": 3411 }, { "epoch": 0.18654365282760976, "grad_norm": 2.5109238624572754, "learning_rate": 9.371566748758492e-05, "loss": 1.2101, "step": 3412 }, { "epoch": 0.1865983256449684, "grad_norm": 3.5781564712524414, "learning_rate": 9.371136962789986e-05, "loss": 1.2729, "step": 3413 }, { "epoch": 0.18665299846232702, "grad_norm": 2.137138605117798, "learning_rate": 9.370707039768334e-05, "loss": 1.1312, "step": 3414 }, { "epoch": 0.18670767127968563, "grad_norm": 3.0052261352539062, "learning_rate": 9.370276979707014e-05, "loss": 1.4615, "step": 3415 }, { "epoch": 0.18676234409704426, "grad_norm": 2.2895684242248535, "learning_rate": 9.369846782619514e-05, "loss": 0.9258, "step": 3416 }, { "epoch": 0.18681701691440286, "grad_norm": 2.039607286453247, "learning_rate": 9.36941644851932e-05, "loss": 0.7851, "step": 3417 }, { "epoch": 0.1868716897317615, "grad_norm": 2.1735525131225586, "learning_rate": 9.368985977419924e-05, "loss": 1.101, "step": 3418 }, { "epoch": 0.18692636254912012, "grad_norm": 2.3898394107818604, "learning_rate": 9.368555369334826e-05, "loss": 1.1672, "step": 3419 }, { "epoch": 0.18698103536647873, "grad_norm": 2.3510420322418213, "learning_rate": 9.368124624277525e-05, "loss": 1.1776, "step": 3420 }, { "epoch": 0.18703570818383736, "grad_norm": 2.365121364593506, "learning_rate": 9.367693742261526e-05, "loss": 1.2134, "step": 3421 }, { "epoch": 0.18709038100119596, "grad_norm": 2.7198777198791504, "learning_rate": 9.36726272330034e-05, "loss": 1.0181, "step": 3422 }, { "epoch": 0.1871450538185546, "grad_norm": 2.6806142330169678, "learning_rate": 9.366831567407484e-05, "loss": 1.2842, "step": 3423 }, { "epoch": 0.1871997266359132, "grad_norm": 2.764009952545166, "learning_rate": 9.366400274596471e-05, "loss": 1.1456, "step": 3424 }, { "epoch": 0.18725439945327182, "grad_norm": 2.8116955757141113, "learning_rate": 9.365968844880829e-05, "loss": 1.1922, "step": 3425 }, { "epoch": 0.18730907227063046, "grad_norm": 2.649278163909912, "learning_rate": 9.365537278274082e-05, "loss": 1.3068, "step": 3426 }, { "epoch": 0.18736374508798906, "grad_norm": 2.481985569000244, "learning_rate": 9.365105574789762e-05, "loss": 1.152, "step": 3427 }, { "epoch": 0.1874184179053477, "grad_norm": 2.3233845233917236, "learning_rate": 9.364673734441405e-05, "loss": 1.0421, "step": 3428 }, { "epoch": 0.1874730907227063, "grad_norm": 4.117557048797607, "learning_rate": 9.36424175724255e-05, "loss": 1.2441, "step": 3429 }, { "epoch": 0.18752776354006492, "grad_norm": 2.732780933380127, "learning_rate": 9.363809643206742e-05, "loss": 1.1866, "step": 3430 }, { "epoch": 0.18758243635742355, "grad_norm": 3.9872167110443115, "learning_rate": 9.363377392347532e-05, "loss": 1.3527, "step": 3431 }, { "epoch": 0.18763710917478216, "grad_norm": 4.441727161407471, "learning_rate": 9.362945004678468e-05, "loss": 1.197, "step": 3432 }, { "epoch": 0.1876917819921408, "grad_norm": 2.3602852821350098, "learning_rate": 9.36251248021311e-05, "loss": 1.1691, "step": 3433 }, { "epoch": 0.1877464548094994, "grad_norm": 2.8048031330108643, "learning_rate": 9.36207981896502e-05, "loss": 1.3576, "step": 3434 }, { "epoch": 0.18780112762685802, "grad_norm": 2.1036882400512695, "learning_rate": 9.361647020947762e-05, "loss": 0.8772, "step": 3435 }, { "epoch": 0.18785580044421665, "grad_norm": 2.2333617210388184, "learning_rate": 9.361214086174907e-05, "loss": 1.2175, "step": 3436 }, { "epoch": 0.18791047326157526, "grad_norm": 2.327442169189453, "learning_rate": 9.360781014660029e-05, "loss": 1.1194, "step": 3437 }, { "epoch": 0.1879651460789339, "grad_norm": 2.277517080307007, "learning_rate": 9.360347806416707e-05, "loss": 1.1302, "step": 3438 }, { "epoch": 0.1880198188962925, "grad_norm": 2.5843002796173096, "learning_rate": 9.359914461458524e-05, "loss": 1.1072, "step": 3439 }, { "epoch": 0.18807449171365112, "grad_norm": 2.2756567001342773, "learning_rate": 9.359480979799064e-05, "loss": 0.9838, "step": 3440 }, { "epoch": 0.18812916453100975, "grad_norm": 5.147974491119385, "learning_rate": 9.359047361451923e-05, "loss": 1.4562, "step": 3441 }, { "epoch": 0.18818383734836835, "grad_norm": 2.8638672828674316, "learning_rate": 9.358613606430695e-05, "loss": 1.0826, "step": 3442 }, { "epoch": 0.18823851016572699, "grad_norm": 2.3177807331085205, "learning_rate": 9.358179714748978e-05, "loss": 1.1154, "step": 3443 }, { "epoch": 0.1882931829830856, "grad_norm": 2.789649486541748, "learning_rate": 9.35774568642038e-05, "loss": 1.1279, "step": 3444 }, { "epoch": 0.18834785580044422, "grad_norm": 2.9279844760894775, "learning_rate": 9.357311521458507e-05, "loss": 1.2697, "step": 3445 }, { "epoch": 0.18840252861780282, "grad_norm": 2.617962121963501, "learning_rate": 9.356877219876973e-05, "loss": 1.2859, "step": 3446 }, { "epoch": 0.18845720143516145, "grad_norm": 2.508312702178955, "learning_rate": 9.356442781689394e-05, "loss": 1.102, "step": 3447 }, { "epoch": 0.18851187425252008, "grad_norm": 2.486316204071045, "learning_rate": 9.356008206909393e-05, "loss": 1.0236, "step": 3448 }, { "epoch": 0.1885665470698787, "grad_norm": 3.449399471282959, "learning_rate": 9.355573495550594e-05, "loss": 1.085, "step": 3449 }, { "epoch": 0.18862121988723732, "grad_norm": 4.249879837036133, "learning_rate": 9.355138647626627e-05, "loss": 1.3637, "step": 3450 }, { "epoch": 0.18867589270459592, "grad_norm": 2.096219539642334, "learning_rate": 9.354703663151128e-05, "loss": 1.1301, "step": 3451 }, { "epoch": 0.18873056552195455, "grad_norm": 2.937873363494873, "learning_rate": 9.354268542137734e-05, "loss": 1.3949, "step": 3452 }, { "epoch": 0.18878523833931318, "grad_norm": 1.890399694442749, "learning_rate": 9.35383328460009e-05, "loss": 0.9529, "step": 3453 }, { "epoch": 0.18883991115667179, "grad_norm": 2.462122917175293, "learning_rate": 9.35339789055184e-05, "loss": 1.1973, "step": 3454 }, { "epoch": 0.18889458397403042, "grad_norm": 3.3336596488952637, "learning_rate": 9.352962360006638e-05, "loss": 1.2111, "step": 3455 }, { "epoch": 0.18894925679138902, "grad_norm": 2.755384683609009, "learning_rate": 9.352526692978138e-05, "loss": 0.9197, "step": 3456 }, { "epoch": 0.18900392960874765, "grad_norm": 2.740859031677246, "learning_rate": 9.352090889480001e-05, "loss": 1.2064, "step": 3457 }, { "epoch": 0.18905860242610628, "grad_norm": 2.272148370742798, "learning_rate": 9.35165494952589e-05, "loss": 1.1427, "step": 3458 }, { "epoch": 0.18911327524346488, "grad_norm": 2.1819584369659424, "learning_rate": 9.351218873129475e-05, "loss": 1.1871, "step": 3459 }, { "epoch": 0.18916794806082352, "grad_norm": 2.926227331161499, "learning_rate": 9.350782660304428e-05, "loss": 1.2332, "step": 3460 }, { "epoch": 0.18922262087818212, "grad_norm": 2.004223108291626, "learning_rate": 9.350346311064426e-05, "loss": 0.9952, "step": 3461 }, { "epoch": 0.18927729369554075, "grad_norm": 3.789658308029175, "learning_rate": 9.349909825423151e-05, "loss": 1.1217, "step": 3462 }, { "epoch": 0.18933196651289938, "grad_norm": 2.9797606468200684, "learning_rate": 9.349473203394287e-05, "loss": 1.3586, "step": 3463 }, { "epoch": 0.18938663933025798, "grad_norm": 2.340933322906494, "learning_rate": 9.349036444991528e-05, "loss": 0.9914, "step": 3464 }, { "epoch": 0.18944131214761661, "grad_norm": 2.8888468742370605, "learning_rate": 9.348599550228563e-05, "loss": 1.3097, "step": 3465 }, { "epoch": 0.18949598496497522, "grad_norm": 2.9601500034332275, "learning_rate": 9.348162519119093e-05, "loss": 1.047, "step": 3466 }, { "epoch": 0.18955065778233385, "grad_norm": 2.1682844161987305, "learning_rate": 9.347725351676819e-05, "loss": 1.2432, "step": 3467 }, { "epoch": 0.18960533059969248, "grad_norm": 2.41062068939209, "learning_rate": 9.347288047915451e-05, "loss": 1.1707, "step": 3468 }, { "epoch": 0.18966000341705108, "grad_norm": 2.1397714614868164, "learning_rate": 9.346850607848699e-05, "loss": 1.0837, "step": 3469 }, { "epoch": 0.1897146762344097, "grad_norm": 2.8099076747894287, "learning_rate": 9.346413031490277e-05, "loss": 1.3197, "step": 3470 }, { "epoch": 0.18976934905176832, "grad_norm": 2.2621073722839355, "learning_rate": 9.345975318853907e-05, "loss": 0.9352, "step": 3471 }, { "epoch": 0.18982402186912695, "grad_norm": 2.4932861328125, "learning_rate": 9.345537469953311e-05, "loss": 1.0734, "step": 3472 }, { "epoch": 0.18987869468648555, "grad_norm": 2.552738904953003, "learning_rate": 9.34509948480222e-05, "loss": 1.1846, "step": 3473 }, { "epoch": 0.18993336750384418, "grad_norm": 2.932523488998413, "learning_rate": 9.344661363414365e-05, "loss": 1.1284, "step": 3474 }, { "epoch": 0.1899880403212028, "grad_norm": 2.405933380126953, "learning_rate": 9.344223105803482e-05, "loss": 1.1142, "step": 3475 }, { "epoch": 0.19004271313856141, "grad_norm": 2.28953218460083, "learning_rate": 9.343784711983315e-05, "loss": 1.031, "step": 3476 }, { "epoch": 0.19009738595592005, "grad_norm": 1.7789857387542725, "learning_rate": 9.343346181967606e-05, "loss": 0.8832, "step": 3477 }, { "epoch": 0.19015205877327865, "grad_norm": 2.221287965774536, "learning_rate": 9.342907515770107e-05, "loss": 0.9957, "step": 3478 }, { "epoch": 0.19020673159063728, "grad_norm": 2.2931933403015137, "learning_rate": 9.342468713404571e-05, "loss": 1.1548, "step": 3479 }, { "epoch": 0.1902614044079959, "grad_norm": 2.036424398422241, "learning_rate": 9.342029774884757e-05, "loss": 1.0392, "step": 3480 }, { "epoch": 0.1903160772253545, "grad_norm": 2.136265516281128, "learning_rate": 9.341590700224428e-05, "loss": 1.018, "step": 3481 }, { "epoch": 0.19037075004271314, "grad_norm": 2.061121940612793, "learning_rate": 9.34115148943735e-05, "loss": 0.9687, "step": 3482 }, { "epoch": 0.19042542286007175, "grad_norm": 3.2450411319732666, "learning_rate": 9.340712142537294e-05, "loss": 1.2431, "step": 3483 }, { "epoch": 0.19048009567743038, "grad_norm": 2.477970838546753, "learning_rate": 9.340272659538034e-05, "loss": 1.0309, "step": 3484 }, { "epoch": 0.190534768494789, "grad_norm": 3.9893665313720703, "learning_rate": 9.339833040453352e-05, "loss": 1.0568, "step": 3485 }, { "epoch": 0.1905894413121476, "grad_norm": 3.150599241256714, "learning_rate": 9.33939328529703e-05, "loss": 1.3314, "step": 3486 }, { "epoch": 0.19064411412950624, "grad_norm": 2.814253568649292, "learning_rate": 9.338953394082859e-05, "loss": 1.374, "step": 3487 }, { "epoch": 0.19069878694686485, "grad_norm": 2.7940404415130615, "learning_rate": 9.338513366824627e-05, "loss": 1.1945, "step": 3488 }, { "epoch": 0.19075345976422348, "grad_norm": 2.9624202251434326, "learning_rate": 9.338073203536135e-05, "loss": 1.3171, "step": 3489 }, { "epoch": 0.1908081325815821, "grad_norm": 2.6092333793640137, "learning_rate": 9.337632904231181e-05, "loss": 1.2621, "step": 3490 }, { "epoch": 0.1908628053989407, "grad_norm": 2.7541134357452393, "learning_rate": 9.33719246892357e-05, "loss": 0.9601, "step": 3491 }, { "epoch": 0.19091747821629934, "grad_norm": 2.9983484745025635, "learning_rate": 9.336751897627115e-05, "loss": 1.0037, "step": 3492 }, { "epoch": 0.19097215103365794, "grad_norm": 1.9914119243621826, "learning_rate": 9.336311190355627e-05, "loss": 1.0601, "step": 3493 }, { "epoch": 0.19102682385101658, "grad_norm": 2.947563409805298, "learning_rate": 9.335870347122924e-05, "loss": 1.0515, "step": 3494 }, { "epoch": 0.1910814966683752, "grad_norm": 2.01751446723938, "learning_rate": 9.335429367942827e-05, "loss": 0.9873, "step": 3495 }, { "epoch": 0.1911361694857338, "grad_norm": 2.5320773124694824, "learning_rate": 9.334988252829166e-05, "loss": 1.0426, "step": 3496 }, { "epoch": 0.19119084230309244, "grad_norm": 2.841069221496582, "learning_rate": 9.334547001795771e-05, "loss": 1.0786, "step": 3497 }, { "epoch": 0.19124551512045104, "grad_norm": 4.324984073638916, "learning_rate": 9.334105614856475e-05, "loss": 1.176, "step": 3498 }, { "epoch": 0.19130018793780967, "grad_norm": 3.6539597511291504, "learning_rate": 9.333664092025116e-05, "loss": 1.2771, "step": 3499 }, { "epoch": 0.19135486075516828, "grad_norm": 2.6763558387756348, "learning_rate": 9.333222433315543e-05, "loss": 1.1208, "step": 3500 }, { "epoch": 0.1914095335725269, "grad_norm": 2.79237699508667, "learning_rate": 9.332780638741598e-05, "loss": 1.2731, "step": 3501 }, { "epoch": 0.19146420638988554, "grad_norm": 3.0586259365081787, "learning_rate": 9.332338708317137e-05, "loss": 1.316, "step": 3502 }, { "epoch": 0.19151887920724414, "grad_norm": 2.9388115406036377, "learning_rate": 9.331896642056014e-05, "loss": 1.0976, "step": 3503 }, { "epoch": 0.19157355202460277, "grad_norm": 2.648592948913574, "learning_rate": 9.331454439972094e-05, "loss": 1.1697, "step": 3504 }, { "epoch": 0.19162822484196138, "grad_norm": 3.597165822982788, "learning_rate": 9.331012102079235e-05, "loss": 1.3785, "step": 3505 }, { "epoch": 0.19168289765932, "grad_norm": 3.6790754795074463, "learning_rate": 9.33056962839131e-05, "loss": 1.1686, "step": 3506 }, { "epoch": 0.19173757047667864, "grad_norm": 2.7285029888153076, "learning_rate": 9.330127018922194e-05, "loss": 1.2576, "step": 3507 }, { "epoch": 0.19179224329403724, "grad_norm": 5.490627765655518, "learning_rate": 9.329684273685762e-05, "loss": 1.1934, "step": 3508 }, { "epoch": 0.19184691611139587, "grad_norm": 1.993061900138855, "learning_rate": 9.329241392695895e-05, "loss": 1.1293, "step": 3509 }, { "epoch": 0.19190158892875447, "grad_norm": 3.1159112453460693, "learning_rate": 9.328798375966481e-05, "loss": 1.3091, "step": 3510 }, { "epoch": 0.1919562617461131, "grad_norm": 2.5439226627349854, "learning_rate": 9.328355223511412e-05, "loss": 1.2713, "step": 3511 }, { "epoch": 0.19201093456347174, "grad_norm": 4.073310375213623, "learning_rate": 9.327911935344579e-05, "loss": 1.1002, "step": 3512 }, { "epoch": 0.19206560738083034, "grad_norm": 2.489574432373047, "learning_rate": 9.327468511479882e-05, "loss": 1.0259, "step": 3513 }, { "epoch": 0.19212028019818897, "grad_norm": 3.6262032985687256, "learning_rate": 9.327024951931227e-05, "loss": 1.1137, "step": 3514 }, { "epoch": 0.19217495301554757, "grad_norm": 2.758805274963379, "learning_rate": 9.326581256712517e-05, "loss": 1.1382, "step": 3515 }, { "epoch": 0.1922296258329062, "grad_norm": 2.4332313537597656, "learning_rate": 9.326137425837666e-05, "loss": 1.2366, "step": 3516 }, { "epoch": 0.19228429865026483, "grad_norm": 2.9033007621765137, "learning_rate": 9.325693459320593e-05, "loss": 1.2829, "step": 3517 }, { "epoch": 0.19233897146762344, "grad_norm": 2.104248046875, "learning_rate": 9.325249357175212e-05, "loss": 1.045, "step": 3518 }, { "epoch": 0.19239364428498207, "grad_norm": 3.269805669784546, "learning_rate": 9.32480511941545e-05, "loss": 1.4614, "step": 3519 }, { "epoch": 0.19244831710234067, "grad_norm": 2.5263431072235107, "learning_rate": 9.324360746055237e-05, "loss": 1.15, "step": 3520 }, { "epoch": 0.1925029899196993, "grad_norm": 2.3207850456237793, "learning_rate": 9.323916237108505e-05, "loss": 1.185, "step": 3521 }, { "epoch": 0.1925576627370579, "grad_norm": 2.156888484954834, "learning_rate": 9.323471592589193e-05, "loss": 1.2315, "step": 3522 }, { "epoch": 0.19261233555441654, "grad_norm": 2.5571277141571045, "learning_rate": 9.323026812511238e-05, "loss": 1.1698, "step": 3523 }, { "epoch": 0.19266700837177517, "grad_norm": 2.5515005588531494, "learning_rate": 9.322581896888589e-05, "loss": 1.2261, "step": 3524 }, { "epoch": 0.19272168118913377, "grad_norm": 2.7866671085357666, "learning_rate": 9.322136845735197e-05, "loss": 1.2036, "step": 3525 }, { "epoch": 0.1927763540064924, "grad_norm": 2.7385969161987305, "learning_rate": 9.321691659065012e-05, "loss": 1.3641, "step": 3526 }, { "epoch": 0.192831026823851, "grad_norm": 2.190192937850952, "learning_rate": 9.321246336891995e-05, "loss": 0.9584, "step": 3527 }, { "epoch": 0.19288569964120963, "grad_norm": 2.369765281677246, "learning_rate": 9.320800879230111e-05, "loss": 1.0226, "step": 3528 }, { "epoch": 0.19294037245856827, "grad_norm": 2.350224494934082, "learning_rate": 9.320355286093323e-05, "loss": 1.2043, "step": 3529 }, { "epoch": 0.19299504527592687, "grad_norm": 2.609131097793579, "learning_rate": 9.319909557495603e-05, "loss": 1.0431, "step": 3530 }, { "epoch": 0.1930497180932855, "grad_norm": 2.918195962905884, "learning_rate": 9.319463693450929e-05, "loss": 1.0909, "step": 3531 }, { "epoch": 0.1931043909106441, "grad_norm": 2.3846981525421143, "learning_rate": 9.319017693973277e-05, "loss": 1.2067, "step": 3532 }, { "epoch": 0.19315906372800273, "grad_norm": 1.8857123851776123, "learning_rate": 9.318571559076634e-05, "loss": 0.9662, "step": 3533 }, { "epoch": 0.19321373654536136, "grad_norm": 2.5464394092559814, "learning_rate": 9.318125288774986e-05, "loss": 1.4117, "step": 3534 }, { "epoch": 0.19326840936271997, "grad_norm": 3.4634921550750732, "learning_rate": 9.317678883082326e-05, "loss": 1.377, "step": 3535 }, { "epoch": 0.1933230821800786, "grad_norm": 2.4088222980499268, "learning_rate": 9.317232342012652e-05, "loss": 1.1945, "step": 3536 }, { "epoch": 0.1933777549974372, "grad_norm": 2.9339191913604736, "learning_rate": 9.316785665579964e-05, "loss": 1.3292, "step": 3537 }, { "epoch": 0.19343242781479583, "grad_norm": 2.5418474674224854, "learning_rate": 9.316338853798266e-05, "loss": 1.2539, "step": 3538 }, { "epoch": 0.19348710063215446, "grad_norm": 3.998948335647583, "learning_rate": 9.315891906681569e-05, "loss": 1.1695, "step": 3539 }, { "epoch": 0.19354177344951307, "grad_norm": 2.4159250259399414, "learning_rate": 9.315444824243885e-05, "loss": 1.0005, "step": 3540 }, { "epoch": 0.1935964462668717, "grad_norm": 2.761298894882202, "learning_rate": 9.314997606499234e-05, "loss": 1.1242, "step": 3541 }, { "epoch": 0.1936511190842303, "grad_norm": 2.7033944129943848, "learning_rate": 9.314550253461637e-05, "loss": 1.2197, "step": 3542 }, { "epoch": 0.19370579190158893, "grad_norm": 3.0824711322784424, "learning_rate": 9.31410276514512e-05, "loss": 1.105, "step": 3543 }, { "epoch": 0.19376046471894756, "grad_norm": 2.7253496646881104, "learning_rate": 9.313655141563715e-05, "loss": 1.2111, "step": 3544 }, { "epoch": 0.19381513753630616, "grad_norm": 2.6803548336029053, "learning_rate": 9.313207382731453e-05, "loss": 0.8702, "step": 3545 }, { "epoch": 0.1938698103536648, "grad_norm": 3.80761456489563, "learning_rate": 9.31275948866238e-05, "loss": 1.0956, "step": 3546 }, { "epoch": 0.1939244831710234, "grad_norm": 3.6228644847869873, "learning_rate": 9.312311459370532e-05, "loss": 1.1389, "step": 3547 }, { "epoch": 0.19397915598838203, "grad_norm": 2.2854411602020264, "learning_rate": 9.311863294869961e-05, "loss": 1.1033, "step": 3548 }, { "epoch": 0.19403382880574063, "grad_norm": 2.5128557682037354, "learning_rate": 9.311414995174716e-05, "loss": 1.1137, "step": 3549 }, { "epoch": 0.19408850162309926, "grad_norm": 2.570345878601074, "learning_rate": 9.310966560298857e-05, "loss": 1.1739, "step": 3550 }, { "epoch": 0.1941431744404579, "grad_norm": 3.2202067375183105, "learning_rate": 9.310517990256441e-05, "loss": 1.0478, "step": 3551 }, { "epoch": 0.1941978472578165, "grad_norm": 2.1858456134796143, "learning_rate": 9.310069285061534e-05, "loss": 1.2209, "step": 3552 }, { "epoch": 0.19425252007517513, "grad_norm": 2.1702194213867188, "learning_rate": 9.309620444728203e-05, "loss": 1.0266, "step": 3553 }, { "epoch": 0.19430719289253373, "grad_norm": 3.362088918685913, "learning_rate": 9.309171469270524e-05, "loss": 1.0579, "step": 3554 }, { "epoch": 0.19436186570989236, "grad_norm": 2.9648587703704834, "learning_rate": 9.30872235870257e-05, "loss": 1.2831, "step": 3555 }, { "epoch": 0.194416538527251, "grad_norm": 2.44887638092041, "learning_rate": 9.308273113038426e-05, "loss": 1.3322, "step": 3556 }, { "epoch": 0.1944712113446096, "grad_norm": 2.4106204509735107, "learning_rate": 9.307823732292176e-05, "loss": 1.095, "step": 3557 }, { "epoch": 0.19452588416196823, "grad_norm": 3.0234053134918213, "learning_rate": 9.30737421647791e-05, "loss": 1.3422, "step": 3558 }, { "epoch": 0.19458055697932683, "grad_norm": 2.3060150146484375, "learning_rate": 9.306924565609724e-05, "loss": 1.2463, "step": 3559 }, { "epoch": 0.19463522979668546, "grad_norm": 2.2591655254364014, "learning_rate": 9.306474779701715e-05, "loss": 1.0495, "step": 3560 }, { "epoch": 0.1946899026140441, "grad_norm": 3.0992558002471924, "learning_rate": 9.306024858767988e-05, "loss": 1.2458, "step": 3561 }, { "epoch": 0.1947445754314027, "grad_norm": 2.871849536895752, "learning_rate": 9.305574802822645e-05, "loss": 1.353, "step": 3562 }, { "epoch": 0.19479924824876133, "grad_norm": 2.104519844055176, "learning_rate": 9.305124611879799e-05, "loss": 1.2334, "step": 3563 }, { "epoch": 0.19485392106611993, "grad_norm": 3.792517900466919, "learning_rate": 9.304674285953567e-05, "loss": 1.1991, "step": 3564 }, { "epoch": 0.19490859388347856, "grad_norm": 2.72444748878479, "learning_rate": 9.304223825058068e-05, "loss": 1.2098, "step": 3565 }, { "epoch": 0.1949632667008372, "grad_norm": 2.5619661808013916, "learning_rate": 9.303773229207424e-05, "loss": 1.2265, "step": 3566 }, { "epoch": 0.1950179395181958, "grad_norm": 2.4699783325195312, "learning_rate": 9.303322498415766e-05, "loss": 1.2112, "step": 3567 }, { "epoch": 0.19507261233555442, "grad_norm": 3.3314130306243896, "learning_rate": 9.302871632697226e-05, "loss": 1.3126, "step": 3568 }, { "epoch": 0.19512728515291303, "grad_norm": 2.4526207447052, "learning_rate": 9.302420632065935e-05, "loss": 1.1344, "step": 3569 }, { "epoch": 0.19518195797027166, "grad_norm": 2.9060094356536865, "learning_rate": 9.301969496536042e-05, "loss": 1.2473, "step": 3570 }, { "epoch": 0.1952366307876303, "grad_norm": 2.5874152183532715, "learning_rate": 9.301518226121686e-05, "loss": 1.2961, "step": 3571 }, { "epoch": 0.1952913036049889, "grad_norm": 2.301215648651123, "learning_rate": 9.301066820837019e-05, "loss": 1.2334, "step": 3572 }, { "epoch": 0.19534597642234752, "grad_norm": 2.700266122817993, "learning_rate": 9.300615280696192e-05, "loss": 1.0897, "step": 3573 }, { "epoch": 0.19540064923970613, "grad_norm": 2.629185438156128, "learning_rate": 9.300163605713365e-05, "loss": 1.2537, "step": 3574 }, { "epoch": 0.19545532205706476, "grad_norm": 2.86556077003479, "learning_rate": 9.2997117959027e-05, "loss": 1.2046, "step": 3575 }, { "epoch": 0.19550999487442336, "grad_norm": 2.751682996749878, "learning_rate": 9.299259851278361e-05, "loss": 1.3793, "step": 3576 }, { "epoch": 0.195564667691782, "grad_norm": 2.357335090637207, "learning_rate": 9.298807771854521e-05, "loss": 1.0428, "step": 3577 }, { "epoch": 0.19561934050914062, "grad_norm": 3.2287235260009766, "learning_rate": 9.298355557645351e-05, "loss": 1.0253, "step": 3578 }, { "epoch": 0.19567401332649922, "grad_norm": 2.312267780303955, "learning_rate": 9.297903208665033e-05, "loss": 1.0884, "step": 3579 }, { "epoch": 0.19572868614385786, "grad_norm": 1.94718599319458, "learning_rate": 9.297450724927749e-05, "loss": 1.0139, "step": 3580 }, { "epoch": 0.19578335896121646, "grad_norm": 2.5511815547943115, "learning_rate": 9.296998106447685e-05, "loss": 1.1628, "step": 3581 }, { "epoch": 0.1958380317785751, "grad_norm": 2.0192172527313232, "learning_rate": 9.296545353239034e-05, "loss": 1.122, "step": 3582 }, { "epoch": 0.19589270459593372, "grad_norm": 2.7307987213134766, "learning_rate": 9.296092465315991e-05, "loss": 1.0835, "step": 3583 }, { "epoch": 0.19594737741329232, "grad_norm": 3.025787353515625, "learning_rate": 9.295639442692756e-05, "loss": 0.9049, "step": 3584 }, { "epoch": 0.19600205023065095, "grad_norm": 2.322737693786621, "learning_rate": 9.295186285383532e-05, "loss": 0.9491, "step": 3585 }, { "epoch": 0.19605672304800956, "grad_norm": 2.4403350353240967, "learning_rate": 9.294732993402531e-05, "loss": 1.1282, "step": 3586 }, { "epoch": 0.1961113958653682, "grad_norm": 2.587533473968506, "learning_rate": 9.294279566763961e-05, "loss": 1.2588, "step": 3587 }, { "epoch": 0.19616606868272682, "grad_norm": 2.097510576248169, "learning_rate": 9.293826005482042e-05, "loss": 1.0289, "step": 3588 }, { "epoch": 0.19622074150008542, "grad_norm": 2.422316312789917, "learning_rate": 9.293372309570994e-05, "loss": 1.0658, "step": 3589 }, { "epoch": 0.19627541431744405, "grad_norm": 2.233574390411377, "learning_rate": 9.292918479045043e-05, "loss": 1.0372, "step": 3590 }, { "epoch": 0.19633008713480266, "grad_norm": 2.732529401779175, "learning_rate": 9.292464513918415e-05, "loss": 1.1229, "step": 3591 }, { "epoch": 0.1963847599521613, "grad_norm": 2.5927698612213135, "learning_rate": 9.292010414205347e-05, "loss": 1.3773, "step": 3592 }, { "epoch": 0.19643943276951992, "grad_norm": 2.37621808052063, "learning_rate": 9.291556179920078e-05, "loss": 0.8745, "step": 3593 }, { "epoch": 0.19649410558687852, "grad_norm": 3.135000228881836, "learning_rate": 9.291101811076848e-05, "loss": 1.3356, "step": 3594 }, { "epoch": 0.19654877840423715, "grad_norm": 2.285656213760376, "learning_rate": 9.290647307689902e-05, "loss": 1.1932, "step": 3595 }, { "epoch": 0.19660345122159575, "grad_norm": 2.9266998767852783, "learning_rate": 9.290192669773492e-05, "loss": 1.0553, "step": 3596 }, { "epoch": 0.19665812403895438, "grad_norm": 2.8263256549835205, "learning_rate": 9.289737897341874e-05, "loss": 1.1066, "step": 3597 }, { "epoch": 0.196712796856313, "grad_norm": 2.4837982654571533, "learning_rate": 9.289282990409307e-05, "loss": 1.0676, "step": 3598 }, { "epoch": 0.19676746967367162, "grad_norm": 2.462019920349121, "learning_rate": 9.288827948990051e-05, "loss": 1.1343, "step": 3599 }, { "epoch": 0.19682214249103025, "grad_norm": 2.76407790184021, "learning_rate": 9.288372773098378e-05, "loss": 1.1024, "step": 3600 }, { "epoch": 0.19687681530838885, "grad_norm": 2.6721107959747314, "learning_rate": 9.287917462748554e-05, "loss": 1.2031, "step": 3601 }, { "epoch": 0.19693148812574748, "grad_norm": 3.586555004119873, "learning_rate": 9.28746201795486e-05, "loss": 0.9521, "step": 3602 }, { "epoch": 0.1969861609431061, "grad_norm": 2.9003312587738037, "learning_rate": 9.287006438731573e-05, "loss": 1.383, "step": 3603 }, { "epoch": 0.19704083376046472, "grad_norm": 2.0397751331329346, "learning_rate": 9.286550725092979e-05, "loss": 1.2101, "step": 3604 }, { "epoch": 0.19709550657782335, "grad_norm": 2.709071159362793, "learning_rate": 9.286094877053367e-05, "loss": 1.2476, "step": 3605 }, { "epoch": 0.19715017939518195, "grad_norm": 2.5708463191986084, "learning_rate": 9.285638894627029e-05, "loss": 1.0366, "step": 3606 }, { "epoch": 0.19720485221254058, "grad_norm": 2.890993118286133, "learning_rate": 9.285182777828259e-05, "loss": 1.3337, "step": 3607 }, { "epoch": 0.19725952502989919, "grad_norm": 2.1964597702026367, "learning_rate": 9.284726526671361e-05, "loss": 0.9715, "step": 3608 }, { "epoch": 0.19731419784725782, "grad_norm": 2.299325704574585, "learning_rate": 9.284270141170643e-05, "loss": 1.2078, "step": 3609 }, { "epoch": 0.19736887066461645, "grad_norm": 2.3169798851013184, "learning_rate": 9.283813621340409e-05, "loss": 1.1439, "step": 3610 }, { "epoch": 0.19742354348197505, "grad_norm": 2.117680549621582, "learning_rate": 9.283356967194976e-05, "loss": 1.045, "step": 3611 }, { "epoch": 0.19747821629933368, "grad_norm": 3.0794036388397217, "learning_rate": 9.282900178748661e-05, "loss": 1.3658, "step": 3612 }, { "epoch": 0.19753288911669228, "grad_norm": 3.063852310180664, "learning_rate": 9.282443256015788e-05, "loss": 1.1553, "step": 3613 }, { "epoch": 0.19758756193405091, "grad_norm": 2.681260585784912, "learning_rate": 9.28198619901068e-05, "loss": 1.1878, "step": 3614 }, { "epoch": 0.19764223475140955, "grad_norm": 2.814160108566284, "learning_rate": 9.28152900774767e-05, "loss": 1.2417, "step": 3615 }, { "epoch": 0.19769690756876815, "grad_norm": 2.567589044570923, "learning_rate": 9.281071682241093e-05, "loss": 1.1525, "step": 3616 }, { "epoch": 0.19775158038612678, "grad_norm": 2.9607250690460205, "learning_rate": 9.280614222505288e-05, "loss": 1.22, "step": 3617 }, { "epoch": 0.19780625320348538, "grad_norm": 2.362502098083496, "learning_rate": 9.280156628554597e-05, "loss": 1.197, "step": 3618 }, { "epoch": 0.197860926020844, "grad_norm": 3.9105677604675293, "learning_rate": 9.279698900403368e-05, "loss": 1.1753, "step": 3619 }, { "epoch": 0.19791559883820264, "grad_norm": 2.7247135639190674, "learning_rate": 9.279241038065954e-05, "loss": 1.0239, "step": 3620 }, { "epoch": 0.19797027165556125, "grad_norm": 2.955185890197754, "learning_rate": 9.278783041556708e-05, "loss": 1.2256, "step": 3621 }, { "epoch": 0.19802494447291988, "grad_norm": 3.1357898712158203, "learning_rate": 9.278324910889993e-05, "loss": 1.1737, "step": 3622 }, { "epoch": 0.19807961729027848, "grad_norm": 2.5134665966033936, "learning_rate": 9.27786664608017e-05, "loss": 1.3009, "step": 3623 }, { "epoch": 0.1981342901076371, "grad_norm": 2.857691526412964, "learning_rate": 9.277408247141612e-05, "loss": 1.2603, "step": 3624 }, { "epoch": 0.19818896292499572, "grad_norm": 2.01303768157959, "learning_rate": 9.276949714088688e-05, "loss": 0.8944, "step": 3625 }, { "epoch": 0.19824363574235435, "grad_norm": 3.275505304336548, "learning_rate": 9.276491046935777e-05, "loss": 1.0828, "step": 3626 }, { "epoch": 0.19829830855971298, "grad_norm": 2.8190994262695312, "learning_rate": 9.27603224569726e-05, "loss": 1.1879, "step": 3627 }, { "epoch": 0.19835298137707158, "grad_norm": 2.076843500137329, "learning_rate": 9.27557331038752e-05, "loss": 1.0941, "step": 3628 }, { "epoch": 0.1984076541944302, "grad_norm": 2.405646562576294, "learning_rate": 9.275114241020947e-05, "loss": 1.2637, "step": 3629 }, { "epoch": 0.1984623270117888, "grad_norm": 2.0796539783477783, "learning_rate": 9.274655037611938e-05, "loss": 1.0571, "step": 3630 }, { "epoch": 0.19851699982914744, "grad_norm": 2.5366268157958984, "learning_rate": 9.274195700174888e-05, "loss": 1.0205, "step": 3631 }, { "epoch": 0.19857167264650608, "grad_norm": 2.7510390281677246, "learning_rate": 9.273736228724198e-05, "loss": 1.0075, "step": 3632 }, { "epoch": 0.19862634546386468, "grad_norm": 2.501173496246338, "learning_rate": 9.273276623274279e-05, "loss": 1.3208, "step": 3633 }, { "epoch": 0.1986810182812233, "grad_norm": 2.7698118686676025, "learning_rate": 9.272816883839537e-05, "loss": 1.1548, "step": 3634 }, { "epoch": 0.1987356910985819, "grad_norm": 2.719989538192749, "learning_rate": 9.272357010434389e-05, "loss": 1.1245, "step": 3635 }, { "epoch": 0.19879036391594054, "grad_norm": 2.557290554046631, "learning_rate": 9.271897003073253e-05, "loss": 0.9419, "step": 3636 }, { "epoch": 0.19884503673329917, "grad_norm": 4.361799240112305, "learning_rate": 9.271436861770553e-05, "loss": 1.1154, "step": 3637 }, { "epoch": 0.19889970955065778, "grad_norm": 2.4188225269317627, "learning_rate": 9.270976586540717e-05, "loss": 1.1166, "step": 3638 }, { "epoch": 0.1989543823680164, "grad_norm": 2.643892526626587, "learning_rate": 9.270516177398172e-05, "loss": 1.2395, "step": 3639 }, { "epoch": 0.199009055185375, "grad_norm": 2.8083386421203613, "learning_rate": 9.270055634357359e-05, "loss": 1.1687, "step": 3640 }, { "epoch": 0.19906372800273364, "grad_norm": 3.0705795288085938, "learning_rate": 9.269594957432716e-05, "loss": 1.1018, "step": 3641 }, { "epoch": 0.19911840082009227, "grad_norm": 2.3255467414855957, "learning_rate": 9.269134146638687e-05, "loss": 1.1411, "step": 3642 }, { "epoch": 0.19917307363745088, "grad_norm": 2.453803300857544, "learning_rate": 9.26867320198972e-05, "loss": 1.2672, "step": 3643 }, { "epoch": 0.1992277464548095, "grad_norm": 2.703878879547119, "learning_rate": 9.268212123500267e-05, "loss": 1.0888, "step": 3644 }, { "epoch": 0.1992824192721681, "grad_norm": 2.309033155441284, "learning_rate": 9.267750911184787e-05, "loss": 1.1236, "step": 3645 }, { "epoch": 0.19933709208952674, "grad_norm": 2.7637550830841064, "learning_rate": 9.267289565057738e-05, "loss": 1.0982, "step": 3646 }, { "epoch": 0.19939176490688537, "grad_norm": 2.4992446899414062, "learning_rate": 9.266828085133588e-05, "loss": 1.231, "step": 3647 }, { "epoch": 0.19944643772424397, "grad_norm": 2.6119964122772217, "learning_rate": 9.266366471426803e-05, "loss": 1.1359, "step": 3648 }, { "epoch": 0.1995011105416026, "grad_norm": 3.1604161262512207, "learning_rate": 9.265904723951862e-05, "loss": 1.0349, "step": 3649 }, { "epoch": 0.1995557833589612, "grad_norm": 2.274348020553589, "learning_rate": 9.265442842723237e-05, "loss": 1.0805, "step": 3650 }, { "epoch": 0.19961045617631984, "grad_norm": 2.318635940551758, "learning_rate": 9.264980827755411e-05, "loss": 1.1561, "step": 3651 }, { "epoch": 0.19966512899367844, "grad_norm": 2.262268304824829, "learning_rate": 9.264518679062872e-05, "loss": 1.0345, "step": 3652 }, { "epoch": 0.19971980181103707, "grad_norm": 2.0888853073120117, "learning_rate": 9.26405639666011e-05, "loss": 0.9936, "step": 3653 }, { "epoch": 0.1997744746283957, "grad_norm": 3.0320584774017334, "learning_rate": 9.263593980561618e-05, "loss": 0.9719, "step": 3654 }, { "epoch": 0.1998291474457543, "grad_norm": 2.6796212196350098, "learning_rate": 9.263131430781895e-05, "loss": 0.9872, "step": 3655 }, { "epoch": 0.19988382026311294, "grad_norm": 2.8022453784942627, "learning_rate": 9.262668747335445e-05, "loss": 1.0398, "step": 3656 }, { "epoch": 0.19993849308047154, "grad_norm": 2.9884748458862305, "learning_rate": 9.262205930236774e-05, "loss": 1.2715, "step": 3657 }, { "epoch": 0.19999316589783017, "grad_norm": 2.300130844116211, "learning_rate": 9.261742979500392e-05, "loss": 0.8225, "step": 3658 }, { "epoch": 0.2000478387151888, "grad_norm": 2.7471373081207275, "learning_rate": 9.261279895140818e-05, "loss": 1.1734, "step": 3659 }, { "epoch": 0.2001025115325474, "grad_norm": 2.6634669303894043, "learning_rate": 9.260816677172568e-05, "loss": 0.9822, "step": 3660 }, { "epoch": 0.20015718434990604, "grad_norm": 2.7075085639953613, "learning_rate": 9.260353325610168e-05, "loss": 1.0509, "step": 3661 }, { "epoch": 0.20021185716726464, "grad_norm": 3.4704790115356445, "learning_rate": 9.259889840468146e-05, "loss": 1.0849, "step": 3662 }, { "epoch": 0.20026652998462327, "grad_norm": 3.132061004638672, "learning_rate": 9.259426221761031e-05, "loss": 0.994, "step": 3663 }, { "epoch": 0.2003212028019819, "grad_norm": 3.4366073608398438, "learning_rate": 9.258962469503365e-05, "loss": 1.0651, "step": 3664 }, { "epoch": 0.2003758756193405, "grad_norm": 2.5111567974090576, "learning_rate": 9.258498583709683e-05, "loss": 1.1905, "step": 3665 }, { "epoch": 0.20043054843669914, "grad_norm": 2.845653533935547, "learning_rate": 9.258034564394533e-05, "loss": 1.2008, "step": 3666 }, { "epoch": 0.20048522125405774, "grad_norm": 2.770784854888916, "learning_rate": 9.257570411572464e-05, "loss": 1.3386, "step": 3667 }, { "epoch": 0.20053989407141637, "grad_norm": 2.8999147415161133, "learning_rate": 9.257106125258026e-05, "loss": 1.115, "step": 3668 }, { "epoch": 0.200594566888775, "grad_norm": 2.707642078399658, "learning_rate": 9.25664170546578e-05, "loss": 1.3048, "step": 3669 }, { "epoch": 0.2006492397061336, "grad_norm": 2.371029853820801, "learning_rate": 9.256177152210286e-05, "loss": 1.3732, "step": 3670 }, { "epoch": 0.20070391252349223, "grad_norm": 3.1617062091827393, "learning_rate": 9.255712465506108e-05, "loss": 1.0002, "step": 3671 }, { "epoch": 0.20075858534085084, "grad_norm": 2.762044668197632, "learning_rate": 9.255247645367818e-05, "loss": 1.32, "step": 3672 }, { "epoch": 0.20081325815820947, "grad_norm": 3.312391996383667, "learning_rate": 9.254782691809989e-05, "loss": 1.0327, "step": 3673 }, { "epoch": 0.2008679309755681, "grad_norm": 2.3162319660186768, "learning_rate": 9.254317604847201e-05, "loss": 1.1401, "step": 3674 }, { "epoch": 0.2009226037929267, "grad_norm": 2.2980799674987793, "learning_rate": 9.253852384494033e-05, "loss": 1.2202, "step": 3675 }, { "epoch": 0.20097727661028533, "grad_norm": 2.9239697456359863, "learning_rate": 9.253387030765075e-05, "loss": 1.095, "step": 3676 }, { "epoch": 0.20103194942764394, "grad_norm": 3.747875213623047, "learning_rate": 9.252921543674915e-05, "loss": 1.1858, "step": 3677 }, { "epoch": 0.20108662224500257, "grad_norm": 2.6539206504821777, "learning_rate": 9.25245592323815e-05, "loss": 1.1985, "step": 3678 }, { "epoch": 0.20114129506236117, "grad_norm": 2.4523515701293945, "learning_rate": 9.251990169469379e-05, "loss": 1.2783, "step": 3679 }, { "epoch": 0.2011959678797198, "grad_norm": 2.6118502616882324, "learning_rate": 9.251524282383204e-05, "loss": 0.8547, "step": 3680 }, { "epoch": 0.20125064069707843, "grad_norm": 2.2507355213165283, "learning_rate": 9.251058261994233e-05, "loss": 1.2606, "step": 3681 }, { "epoch": 0.20130531351443703, "grad_norm": 2.5160298347473145, "learning_rate": 9.250592108317078e-05, "loss": 1.1368, "step": 3682 }, { "epoch": 0.20135998633179567, "grad_norm": 2.9124133586883545, "learning_rate": 9.250125821366356e-05, "loss": 1.3017, "step": 3683 }, { "epoch": 0.20141465914915427, "grad_norm": 2.6599037647247314, "learning_rate": 9.249659401156683e-05, "loss": 1.2631, "step": 3684 }, { "epoch": 0.2014693319665129, "grad_norm": 2.464402914047241, "learning_rate": 9.249192847702688e-05, "loss": 1.0077, "step": 3685 }, { "epoch": 0.20152400478387153, "grad_norm": 2.581664562225342, "learning_rate": 9.248726161018996e-05, "loss": 1.0457, "step": 3686 }, { "epoch": 0.20157867760123013, "grad_norm": 2.4170267581939697, "learning_rate": 9.24825934112024e-05, "loss": 0.992, "step": 3687 }, { "epoch": 0.20163335041858876, "grad_norm": 3.5657315254211426, "learning_rate": 9.247792388021059e-05, "loss": 1.3193, "step": 3688 }, { "epoch": 0.20168802323594737, "grad_norm": 2.9119317531585693, "learning_rate": 9.247325301736092e-05, "loss": 0.9877, "step": 3689 }, { "epoch": 0.201742696053306, "grad_norm": 2.9141087532043457, "learning_rate": 9.246858082279985e-05, "loss": 1.213, "step": 3690 }, { "epoch": 0.20179736887066463, "grad_norm": 2.730804920196533, "learning_rate": 9.246390729667385e-05, "loss": 1.0964, "step": 3691 }, { "epoch": 0.20185204168802323, "grad_norm": 3.1051747798919678, "learning_rate": 9.245923243912948e-05, "loss": 1.2309, "step": 3692 }, { "epoch": 0.20190671450538186, "grad_norm": 3.060168504714966, "learning_rate": 9.245455625031331e-05, "loss": 1.2084, "step": 3693 }, { "epoch": 0.20196138732274047, "grad_norm": 2.0853304862976074, "learning_rate": 9.244987873037196e-05, "loss": 1.0492, "step": 3694 }, { "epoch": 0.2020160601400991, "grad_norm": 2.055974245071411, "learning_rate": 9.244519987945209e-05, "loss": 1.1675, "step": 3695 }, { "epoch": 0.20207073295745773, "grad_norm": 3.335947036743164, "learning_rate": 9.244051969770039e-05, "loss": 1.1266, "step": 3696 }, { "epoch": 0.20212540577481633, "grad_norm": 2.4198668003082275, "learning_rate": 9.24358381852636e-05, "loss": 1.1522, "step": 3697 }, { "epoch": 0.20218007859217496, "grad_norm": 2.3841733932495117, "learning_rate": 9.243115534228852e-05, "loss": 1.2792, "step": 3698 }, { "epoch": 0.20223475140953356, "grad_norm": 3.3355138301849365, "learning_rate": 9.242647116892198e-05, "loss": 1.2691, "step": 3699 }, { "epoch": 0.2022894242268922, "grad_norm": 2.5939998626708984, "learning_rate": 9.242178566531082e-05, "loss": 1.1714, "step": 3700 }, { "epoch": 0.2023440970442508, "grad_norm": 2.3425745964050293, "learning_rate": 9.2417098831602e-05, "loss": 1.1311, "step": 3701 }, { "epoch": 0.20239876986160943, "grad_norm": 2.7266907691955566, "learning_rate": 9.24124106679424e-05, "loss": 1.2326, "step": 3702 }, { "epoch": 0.20245344267896806, "grad_norm": 2.7993693351745605, "learning_rate": 9.240772117447907e-05, "loss": 1.0074, "step": 3703 }, { "epoch": 0.20250811549632666, "grad_norm": 2.454728126525879, "learning_rate": 9.240303035135902e-05, "loss": 1.2254, "step": 3704 }, { "epoch": 0.2025627883136853, "grad_norm": 3.1021065711975098, "learning_rate": 9.239833819872934e-05, "loss": 1.1629, "step": 3705 }, { "epoch": 0.2026174611310439, "grad_norm": 2.6664605140686035, "learning_rate": 9.239364471673714e-05, "loss": 1.2066, "step": 3706 }, { "epoch": 0.20267213394840253, "grad_norm": 2.152850866317749, "learning_rate": 9.23889499055296e-05, "loss": 1.2171, "step": 3707 }, { "epoch": 0.20272680676576116, "grad_norm": 8.595810890197754, "learning_rate": 9.238425376525389e-05, "loss": 1.2274, "step": 3708 }, { "epoch": 0.20278147958311976, "grad_norm": 2.6020870208740234, "learning_rate": 9.237955629605728e-05, "loss": 0.9741, "step": 3709 }, { "epoch": 0.2028361524004784, "grad_norm": 3.1367828845977783, "learning_rate": 9.237485749808703e-05, "loss": 1.3643, "step": 3710 }, { "epoch": 0.202890825217837, "grad_norm": 3.2158544063568115, "learning_rate": 9.237015737149048e-05, "loss": 1.199, "step": 3711 }, { "epoch": 0.20294549803519563, "grad_norm": 3.5623950958251953, "learning_rate": 9.2365455916415e-05, "loss": 1.089, "step": 3712 }, { "epoch": 0.20300017085255426, "grad_norm": 2.412140369415283, "learning_rate": 9.2360753133008e-05, "loss": 1.0592, "step": 3713 }, { "epoch": 0.20305484366991286, "grad_norm": 2.700807809829712, "learning_rate": 9.235604902141693e-05, "loss": 1.3147, "step": 3714 }, { "epoch": 0.2031095164872715, "grad_norm": 3.237218141555786, "learning_rate": 9.235134358178928e-05, "loss": 1.2499, "step": 3715 }, { "epoch": 0.2031641893046301, "grad_norm": 2.376507043838501, "learning_rate": 9.234663681427258e-05, "loss": 1.017, "step": 3716 }, { "epoch": 0.20321886212198872, "grad_norm": 3.678269386291504, "learning_rate": 9.234192871901443e-05, "loss": 1.1117, "step": 3717 }, { "epoch": 0.20327353493934736, "grad_norm": 1.9435425996780396, "learning_rate": 9.233721929616241e-05, "loss": 0.919, "step": 3718 }, { "epoch": 0.20332820775670596, "grad_norm": 2.7178595066070557, "learning_rate": 9.233250854586423e-05, "loss": 1.2301, "step": 3719 }, { "epoch": 0.2033828805740646, "grad_norm": 2.374443292617798, "learning_rate": 9.232779646826754e-05, "loss": 1.0198, "step": 3720 }, { "epoch": 0.2034375533914232, "grad_norm": 2.5272140502929688, "learning_rate": 9.232308306352012e-05, "loss": 0.9575, "step": 3721 }, { "epoch": 0.20349222620878182, "grad_norm": 2.4804723262786865, "learning_rate": 9.231836833176974e-05, "loss": 1.1032, "step": 3722 }, { "epoch": 0.20354689902614045, "grad_norm": 2.4994895458221436, "learning_rate": 9.231365227316421e-05, "loss": 1.2371, "step": 3723 }, { "epoch": 0.20360157184349906, "grad_norm": 2.2698848247528076, "learning_rate": 9.230893488785144e-05, "loss": 1.1089, "step": 3724 }, { "epoch": 0.2036562446608577, "grad_norm": 2.8565149307250977, "learning_rate": 9.230421617597931e-05, "loss": 1.1923, "step": 3725 }, { "epoch": 0.2037109174782163, "grad_norm": 2.372194528579712, "learning_rate": 9.229949613769578e-05, "loss": 1.1623, "step": 3726 }, { "epoch": 0.20376559029557492, "grad_norm": 1.9456982612609863, "learning_rate": 9.229477477314883e-05, "loss": 1.0305, "step": 3727 }, { "epoch": 0.20382026311293353, "grad_norm": 2.705298900604248, "learning_rate": 9.22900520824865e-05, "loss": 1.1946, "step": 3728 }, { "epoch": 0.20387493593029216, "grad_norm": 2.185023307800293, "learning_rate": 9.228532806585687e-05, "loss": 1.1776, "step": 3729 }, { "epoch": 0.2039296087476508, "grad_norm": 2.3674564361572266, "learning_rate": 9.228060272340807e-05, "loss": 1.1327, "step": 3730 }, { "epoch": 0.2039842815650094, "grad_norm": 2.693855047225952, "learning_rate": 9.227587605528823e-05, "loss": 1.0168, "step": 3731 }, { "epoch": 0.20403895438236802, "grad_norm": 2.6618993282318115, "learning_rate": 9.227114806164556e-05, "loss": 1.2177, "step": 3732 }, { "epoch": 0.20409362719972662, "grad_norm": 2.814269781112671, "learning_rate": 9.226641874262831e-05, "loss": 1.3401, "step": 3733 }, { "epoch": 0.20414830001708525, "grad_norm": 2.9019248485565186, "learning_rate": 9.226168809838475e-05, "loss": 1.0031, "step": 3734 }, { "epoch": 0.20420297283444389, "grad_norm": 3.856419324874878, "learning_rate": 9.225695612906324e-05, "loss": 1.3314, "step": 3735 }, { "epoch": 0.2042576456518025, "grad_norm": 2.45831298828125, "learning_rate": 9.225222283481212e-05, "loss": 1.0908, "step": 3736 }, { "epoch": 0.20431231846916112, "grad_norm": 2.4829795360565186, "learning_rate": 9.22474882157798e-05, "loss": 1.1337, "step": 3737 }, { "epoch": 0.20436699128651972, "grad_norm": 3.2175400257110596, "learning_rate": 9.224275227211473e-05, "loss": 1.2224, "step": 3738 }, { "epoch": 0.20442166410387835, "grad_norm": 2.6441116333007812, "learning_rate": 9.223801500396539e-05, "loss": 1.1201, "step": 3739 }, { "epoch": 0.20447633692123698, "grad_norm": 4.039104461669922, "learning_rate": 9.223327641148034e-05, "loss": 1.0445, "step": 3740 }, { "epoch": 0.2045310097385956, "grad_norm": 2.8933677673339844, "learning_rate": 9.222853649480813e-05, "loss": 1.0439, "step": 3741 }, { "epoch": 0.20458568255595422, "grad_norm": 2.8733649253845215, "learning_rate": 9.222379525409738e-05, "loss": 1.1587, "step": 3742 }, { "epoch": 0.20464035537331282, "grad_norm": 2.696244239807129, "learning_rate": 9.221905268949677e-05, "loss": 1.2565, "step": 3743 }, { "epoch": 0.20469502819067145, "grad_norm": 3.3909173011779785, "learning_rate": 9.221430880115498e-05, "loss": 1.097, "step": 3744 }, { "epoch": 0.20474970100803008, "grad_norm": 2.0524799823760986, "learning_rate": 9.220956358922075e-05, "loss": 1.1131, "step": 3745 }, { "epoch": 0.20480437382538869, "grad_norm": 2.633513927459717, "learning_rate": 9.220481705384286e-05, "loss": 1.306, "step": 3746 }, { "epoch": 0.20485904664274732, "grad_norm": 2.3865115642547607, "learning_rate": 9.220006919517015e-05, "loss": 1.052, "step": 3747 }, { "epoch": 0.20491371946010592, "grad_norm": 2.19777512550354, "learning_rate": 9.219532001335145e-05, "loss": 1.0548, "step": 3748 }, { "epoch": 0.20496839227746455, "grad_norm": 1.9926756620407104, "learning_rate": 9.21905695085357e-05, "loss": 1.1617, "step": 3749 }, { "epoch": 0.20502306509482318, "grad_norm": 3.08695387840271, "learning_rate": 9.218581768087185e-05, "loss": 1.2976, "step": 3750 }, { "epoch": 0.20507773791218178, "grad_norm": 2.9662513732910156, "learning_rate": 9.218106453050886e-05, "loss": 1.2754, "step": 3751 }, { "epoch": 0.20513241072954042, "grad_norm": 3.1882853507995605, "learning_rate": 9.217631005759579e-05, "loss": 1.2588, "step": 3752 }, { "epoch": 0.20518708354689902, "grad_norm": 2.476179838180542, "learning_rate": 9.217155426228168e-05, "loss": 1.0166, "step": 3753 }, { "epoch": 0.20524175636425765, "grad_norm": 2.1229751110076904, "learning_rate": 9.216679714471567e-05, "loss": 1.0305, "step": 3754 }, { "epoch": 0.20529642918161625, "grad_norm": 2.1776158809661865, "learning_rate": 9.216203870504692e-05, "loss": 1.0999, "step": 3755 }, { "epoch": 0.20535110199897488, "grad_norm": 1.9697456359863281, "learning_rate": 9.215727894342461e-05, "loss": 1.2309, "step": 3756 }, { "epoch": 0.20540577481633351, "grad_norm": 2.6191065311431885, "learning_rate": 9.215251785999797e-05, "loss": 1.2088, "step": 3757 }, { "epoch": 0.20546044763369212, "grad_norm": 2.266411066055298, "learning_rate": 9.214775545491631e-05, "loss": 1.1838, "step": 3758 }, { "epoch": 0.20551512045105075, "grad_norm": 2.270995616912842, "learning_rate": 9.214299172832893e-05, "loss": 1.0489, "step": 3759 }, { "epoch": 0.20556979326840935, "grad_norm": 2.4500787258148193, "learning_rate": 9.213822668038519e-05, "loss": 1.2825, "step": 3760 }, { "epoch": 0.20562446608576798, "grad_norm": 1.9930862188339233, "learning_rate": 9.21334603112345e-05, "loss": 1.0733, "step": 3761 }, { "epoch": 0.2056791389031266, "grad_norm": 2.597238302230835, "learning_rate": 9.212869262102632e-05, "loss": 1.2315, "step": 3762 }, { "epoch": 0.20573381172048522, "grad_norm": 3.0221059322357178, "learning_rate": 9.212392360991011e-05, "loss": 1.1615, "step": 3763 }, { "epoch": 0.20578848453784385, "grad_norm": 5.876741409301758, "learning_rate": 9.211915327803542e-05, "loss": 0.8383, "step": 3764 }, { "epoch": 0.20584315735520245, "grad_norm": 2.3910953998565674, "learning_rate": 9.211438162555179e-05, "loss": 1.1193, "step": 3765 }, { "epoch": 0.20589783017256108, "grad_norm": 2.15112042427063, "learning_rate": 9.210960865260887e-05, "loss": 1.0283, "step": 3766 }, { "epoch": 0.2059525029899197, "grad_norm": 2.297300100326538, "learning_rate": 9.210483435935629e-05, "loss": 1.1006, "step": 3767 }, { "epoch": 0.20600717580727831, "grad_norm": 2.4762864112854004, "learning_rate": 9.210005874594374e-05, "loss": 1.1148, "step": 3768 }, { "epoch": 0.20606184862463695, "grad_norm": 2.570971965789795, "learning_rate": 9.209528181252096e-05, "loss": 1.1389, "step": 3769 }, { "epoch": 0.20611652144199555, "grad_norm": 2.6513400077819824, "learning_rate": 9.209050355923775e-05, "loss": 1.0278, "step": 3770 }, { "epoch": 0.20617119425935418, "grad_norm": 4.685550212860107, "learning_rate": 9.208572398624388e-05, "loss": 1.0482, "step": 3771 }, { "epoch": 0.2062258670767128, "grad_norm": 2.4266273975372314, "learning_rate": 9.208094309368924e-05, "loss": 1.2309, "step": 3772 }, { "epoch": 0.2062805398940714, "grad_norm": 2.190337896347046, "learning_rate": 9.207616088172373e-05, "loss": 1.0182, "step": 3773 }, { "epoch": 0.20633521271143004, "grad_norm": 2.6904819011688232, "learning_rate": 9.20713773504973e-05, "loss": 1.125, "step": 3774 }, { "epoch": 0.20638988552878865, "grad_norm": 2.5228312015533447, "learning_rate": 9.206659250015992e-05, "loss": 0.9491, "step": 3775 }, { "epoch": 0.20644455834614728, "grad_norm": 2.0819478034973145, "learning_rate": 9.206180633086162e-05, "loss": 1.1321, "step": 3776 }, { "epoch": 0.20649923116350588, "grad_norm": 2.786273241043091, "learning_rate": 9.205701884275243e-05, "loss": 1.1279, "step": 3777 }, { "epoch": 0.2065539039808645, "grad_norm": 2.572127342224121, "learning_rate": 9.205223003598252e-05, "loss": 1.1216, "step": 3778 }, { "epoch": 0.20660857679822314, "grad_norm": 2.026944160461426, "learning_rate": 9.2047439910702e-05, "loss": 1.0141, "step": 3779 }, { "epoch": 0.20666324961558175, "grad_norm": 3.559365749359131, "learning_rate": 9.204264846706108e-05, "loss": 1.2249, "step": 3780 }, { "epoch": 0.20671792243294038, "grad_norm": 2.419243574142456, "learning_rate": 9.203785570520998e-05, "loss": 1.0989, "step": 3781 }, { "epoch": 0.20677259525029898, "grad_norm": 2.5999388694763184, "learning_rate": 9.203306162529896e-05, "loss": 1.1275, "step": 3782 }, { "epoch": 0.2068272680676576, "grad_norm": 3.078291893005371, "learning_rate": 9.202826622747836e-05, "loss": 1.1384, "step": 3783 }, { "epoch": 0.20688194088501624, "grad_norm": 2.228713274002075, "learning_rate": 9.202346951189851e-05, "loss": 0.9981, "step": 3784 }, { "epoch": 0.20693661370237484, "grad_norm": 2.4031529426574707, "learning_rate": 9.201867147870982e-05, "loss": 0.8354, "step": 3785 }, { "epoch": 0.20699128651973348, "grad_norm": 2.9036121368408203, "learning_rate": 9.201387212806274e-05, "loss": 1.0754, "step": 3786 }, { "epoch": 0.20704595933709208, "grad_norm": 2.307716131210327, "learning_rate": 9.200907146010773e-05, "loss": 1.1909, "step": 3787 }, { "epoch": 0.2071006321544507, "grad_norm": 3.2411258220672607, "learning_rate": 9.200426947499532e-05, "loss": 0.912, "step": 3788 }, { "epoch": 0.20715530497180934, "grad_norm": 2.5053906440734863, "learning_rate": 9.199946617287607e-05, "loss": 1.2947, "step": 3789 }, { "epoch": 0.20720997778916794, "grad_norm": 2.6391093730926514, "learning_rate": 9.19946615539006e-05, "loss": 1.1944, "step": 3790 }, { "epoch": 0.20726465060652657, "grad_norm": 3.0880234241485596, "learning_rate": 9.198985561821951e-05, "loss": 1.011, "step": 3791 }, { "epoch": 0.20731932342388518, "grad_norm": 2.8218421936035156, "learning_rate": 9.198504836598352e-05, "loss": 1.2072, "step": 3792 }, { "epoch": 0.2073739962412438, "grad_norm": 2.391223669052124, "learning_rate": 9.198023979734337e-05, "loss": 1.0953, "step": 3793 }, { "epoch": 0.20742866905860244, "grad_norm": 2.904653549194336, "learning_rate": 9.197542991244981e-05, "loss": 1.1358, "step": 3794 }, { "epoch": 0.20748334187596104, "grad_norm": 2.42214298248291, "learning_rate": 9.197061871145363e-05, "loss": 1.0578, "step": 3795 }, { "epoch": 0.20753801469331967, "grad_norm": 2.521857261657715, "learning_rate": 9.19658061945057e-05, "loss": 1.0993, "step": 3796 }, { "epoch": 0.20759268751067828, "grad_norm": 2.9266557693481445, "learning_rate": 9.196099236175693e-05, "loss": 0.9258, "step": 3797 }, { "epoch": 0.2076473603280369, "grad_norm": 2.299187421798706, "learning_rate": 9.195617721335822e-05, "loss": 0.9758, "step": 3798 }, { "epoch": 0.20770203314539554, "grad_norm": 3.096755027770996, "learning_rate": 9.195136074946056e-05, "loss": 1.2916, "step": 3799 }, { "epoch": 0.20775670596275414, "grad_norm": 2.62614369392395, "learning_rate": 9.194654297021498e-05, "loss": 1.1051, "step": 3800 }, { "epoch": 0.20781137878011277, "grad_norm": 2.5080320835113525, "learning_rate": 9.194172387577251e-05, "loss": 1.3988, "step": 3801 }, { "epoch": 0.20786605159747137, "grad_norm": 2.312797784805298, "learning_rate": 9.193690346628427e-05, "loss": 1.0194, "step": 3802 }, { "epoch": 0.20792072441483, "grad_norm": 2.859682559967041, "learning_rate": 9.19320817419014e-05, "loss": 1.0526, "step": 3803 }, { "epoch": 0.2079753972321886, "grad_norm": 2.5110156536102295, "learning_rate": 9.192725870277507e-05, "loss": 1.1247, "step": 3804 }, { "epoch": 0.20803007004954724, "grad_norm": 1.947365164756775, "learning_rate": 9.19224343490565e-05, "loss": 0.866, "step": 3805 }, { "epoch": 0.20808474286690587, "grad_norm": 2.191589832305908, "learning_rate": 9.191760868089697e-05, "loss": 1.3018, "step": 3806 }, { "epoch": 0.20813941568426447, "grad_norm": 3.177480697631836, "learning_rate": 9.191278169844775e-05, "loss": 1.2672, "step": 3807 }, { "epoch": 0.2081940885016231, "grad_norm": 2.2375614643096924, "learning_rate": 9.190795340186023e-05, "loss": 1.1829, "step": 3808 }, { "epoch": 0.2082487613189817, "grad_norm": 2.584212064743042, "learning_rate": 9.190312379128577e-05, "loss": 1.2628, "step": 3809 }, { "epoch": 0.20830343413634034, "grad_norm": 2.183652400970459, "learning_rate": 9.189829286687579e-05, "loss": 1.1101, "step": 3810 }, { "epoch": 0.20835810695369897, "grad_norm": 2.7866828441619873, "learning_rate": 9.189346062878178e-05, "loss": 1.0394, "step": 3811 }, { "epoch": 0.20841277977105757, "grad_norm": 4.495517730712891, "learning_rate": 9.188862707715524e-05, "loss": 1.1455, "step": 3812 }, { "epoch": 0.2084674525884162, "grad_norm": 2.5201025009155273, "learning_rate": 9.188379221214773e-05, "loss": 1.0346, "step": 3813 }, { "epoch": 0.2085221254057748, "grad_norm": 2.3699026107788086, "learning_rate": 9.187895603391085e-05, "loss": 0.9396, "step": 3814 }, { "epoch": 0.20857679822313344, "grad_norm": 1.769492268562317, "learning_rate": 9.187411854259623e-05, "loss": 0.9402, "step": 3815 }, { "epoch": 0.20863147104049207, "grad_norm": 2.9478557109832764, "learning_rate": 9.186927973835551e-05, "loss": 0.9998, "step": 3816 }, { "epoch": 0.20868614385785067, "grad_norm": 2.3174655437469482, "learning_rate": 9.186443962134044e-05, "loss": 1.0894, "step": 3817 }, { "epoch": 0.2087408166752093, "grad_norm": 2.360816717147827, "learning_rate": 9.185959819170279e-05, "loss": 1.1681, "step": 3818 }, { "epoch": 0.2087954894925679, "grad_norm": 2.8729584217071533, "learning_rate": 9.185475544959432e-05, "loss": 1.0774, "step": 3819 }, { "epoch": 0.20885016230992653, "grad_norm": 2.4704360961914062, "learning_rate": 9.18499113951669e-05, "loss": 1.2353, "step": 3820 }, { "epoch": 0.20890483512728517, "grad_norm": 2.531982660293579, "learning_rate": 9.18450660285724e-05, "loss": 1.2549, "step": 3821 }, { "epoch": 0.20895950794464377, "grad_norm": 2.457792043685913, "learning_rate": 9.184021934996277e-05, "loss": 1.0942, "step": 3822 }, { "epoch": 0.2090141807620024, "grad_norm": 2.7872345447540283, "learning_rate": 9.183537135948992e-05, "loss": 0.9979, "step": 3823 }, { "epoch": 0.209068853579361, "grad_norm": 2.679636001586914, "learning_rate": 9.183052205730587e-05, "loss": 0.8966, "step": 3824 }, { "epoch": 0.20912352639671963, "grad_norm": 2.9307544231414795, "learning_rate": 9.18256714435627e-05, "loss": 1.3401, "step": 3825 }, { "epoch": 0.20917819921407826, "grad_norm": 3.1942224502563477, "learning_rate": 9.182081951841245e-05, "loss": 1.1639, "step": 3826 }, { "epoch": 0.20923287203143687, "grad_norm": 2.3483283519744873, "learning_rate": 9.18159662820073e-05, "loss": 1.1234, "step": 3827 }, { "epoch": 0.2092875448487955, "grad_norm": 2.9563522338867188, "learning_rate": 9.181111173449938e-05, "loss": 1.1599, "step": 3828 }, { "epoch": 0.2093422176661541, "grad_norm": 3.290963649749756, "learning_rate": 9.180625587604092e-05, "loss": 1.0495, "step": 3829 }, { "epoch": 0.20939689048351273, "grad_norm": 2.8172414302825928, "learning_rate": 9.180139870678415e-05, "loss": 1.1691, "step": 3830 }, { "epoch": 0.20945156330087134, "grad_norm": 2.5547406673431396, "learning_rate": 9.179654022688138e-05, "loss": 1.0865, "step": 3831 }, { "epoch": 0.20950623611822997, "grad_norm": 3.1606497764587402, "learning_rate": 9.179168043648492e-05, "loss": 1.3136, "step": 3832 }, { "epoch": 0.2095609089355886, "grad_norm": 2.5904412269592285, "learning_rate": 9.178681933574719e-05, "loss": 1.3403, "step": 3833 }, { "epoch": 0.2096155817529472, "grad_norm": 2.419889450073242, "learning_rate": 9.178195692482057e-05, "loss": 1.2434, "step": 3834 }, { "epoch": 0.20967025457030583, "grad_norm": 2.528716802597046, "learning_rate": 9.177709320385751e-05, "loss": 1.2298, "step": 3835 }, { "epoch": 0.20972492738766443, "grad_norm": 3.7256107330322266, "learning_rate": 9.177222817301053e-05, "loss": 1.0496, "step": 3836 }, { "epoch": 0.20977960020502306, "grad_norm": 2.6465795040130615, "learning_rate": 9.176736183243216e-05, "loss": 1.0303, "step": 3837 }, { "epoch": 0.2098342730223817, "grad_norm": 2.8479573726654053, "learning_rate": 9.176249418227498e-05, "loss": 1.2731, "step": 3838 }, { "epoch": 0.2098889458397403, "grad_norm": 2.7077741622924805, "learning_rate": 9.175762522269162e-05, "loss": 1.1242, "step": 3839 }, { "epoch": 0.20994361865709893, "grad_norm": 4.2641682624816895, "learning_rate": 9.175275495383473e-05, "loss": 1.1831, "step": 3840 }, { "epoch": 0.20999829147445753, "grad_norm": 2.4928126335144043, "learning_rate": 9.174788337585702e-05, "loss": 1.2725, "step": 3841 }, { "epoch": 0.21005296429181616, "grad_norm": 2.2307496070861816, "learning_rate": 9.17430104889112e-05, "loss": 1.1806, "step": 3842 }, { "epoch": 0.2101076371091748, "grad_norm": 3.0009145736694336, "learning_rate": 9.173813629315013e-05, "loss": 1.1768, "step": 3843 }, { "epoch": 0.2101623099265334, "grad_norm": 3.2193286418914795, "learning_rate": 9.173326078872658e-05, "loss": 1.3102, "step": 3844 }, { "epoch": 0.21021698274389203, "grad_norm": 3.0924127101898193, "learning_rate": 9.172838397579341e-05, "loss": 1.2195, "step": 3845 }, { "epoch": 0.21027165556125063, "grad_norm": 1.988905906677246, "learning_rate": 9.172350585450355e-05, "loss": 0.8928, "step": 3846 }, { "epoch": 0.21032632837860926, "grad_norm": 2.881089925765991, "learning_rate": 9.171862642500996e-05, "loss": 1.24, "step": 3847 }, { "epoch": 0.2103810011959679, "grad_norm": 2.3738601207733154, "learning_rate": 9.17137456874656e-05, "loss": 1.1304, "step": 3848 }, { "epoch": 0.2104356740133265, "grad_norm": 2.5676445960998535, "learning_rate": 9.170886364202353e-05, "loss": 1.1366, "step": 3849 }, { "epoch": 0.21049034683068513, "grad_norm": 2.142751693725586, "learning_rate": 9.17039802888368e-05, "loss": 1.0459, "step": 3850 }, { "epoch": 0.21054501964804373, "grad_norm": 2.8430378437042236, "learning_rate": 9.169909562805854e-05, "loss": 1.0916, "step": 3851 }, { "epoch": 0.21059969246540236, "grad_norm": 2.9631974697113037, "learning_rate": 9.16942096598419e-05, "loss": 1.3871, "step": 3852 }, { "epoch": 0.21065436528276096, "grad_norm": 2.453429937362671, "learning_rate": 9.168932238434007e-05, "loss": 1.033, "step": 3853 }, { "epoch": 0.2107090381001196, "grad_norm": 2.6806440353393555, "learning_rate": 9.168443380170628e-05, "loss": 1.0512, "step": 3854 }, { "epoch": 0.21076371091747823, "grad_norm": 2.8256266117095947, "learning_rate": 9.167954391209383e-05, "loss": 1.1107, "step": 3855 }, { "epoch": 0.21081838373483683, "grad_norm": 2.5940804481506348, "learning_rate": 9.167465271565602e-05, "loss": 0.9958, "step": 3856 }, { "epoch": 0.21087305655219546, "grad_norm": 3.0017223358154297, "learning_rate": 9.166976021254621e-05, "loss": 1.1186, "step": 3857 }, { "epoch": 0.21092772936955406, "grad_norm": 3.1718194484710693, "learning_rate": 9.16648664029178e-05, "loss": 1.0542, "step": 3858 }, { "epoch": 0.2109824021869127, "grad_norm": 3.600881576538086, "learning_rate": 9.165997128692425e-05, "loss": 1.0858, "step": 3859 }, { "epoch": 0.21103707500427132, "grad_norm": 4.975048542022705, "learning_rate": 9.1655074864719e-05, "loss": 0.9704, "step": 3860 }, { "epoch": 0.21109174782162993, "grad_norm": 2.925037384033203, "learning_rate": 9.165017713645561e-05, "loss": 1.1826, "step": 3861 }, { "epoch": 0.21114642063898856, "grad_norm": 2.5262227058410645, "learning_rate": 9.164527810228765e-05, "loss": 1.1018, "step": 3862 }, { "epoch": 0.21120109345634716, "grad_norm": 3.3481009006500244, "learning_rate": 9.164037776236869e-05, "loss": 1.0741, "step": 3863 }, { "epoch": 0.2112557662737058, "grad_norm": 2.4204609394073486, "learning_rate": 9.16354761168524e-05, "loss": 1.3251, "step": 3864 }, { "epoch": 0.21131043909106442, "grad_norm": 2.685319662094116, "learning_rate": 9.163057316589246e-05, "loss": 1.2281, "step": 3865 }, { "epoch": 0.21136511190842303, "grad_norm": 2.264885425567627, "learning_rate": 9.162566890964259e-05, "loss": 1.2184, "step": 3866 }, { "epoch": 0.21141978472578166, "grad_norm": 2.8373677730560303, "learning_rate": 9.162076334825659e-05, "loss": 1.1219, "step": 3867 }, { "epoch": 0.21147445754314026, "grad_norm": 2.4314017295837402, "learning_rate": 9.161585648188823e-05, "loss": 1.2134, "step": 3868 }, { "epoch": 0.2115291303604989, "grad_norm": 2.0442819595336914, "learning_rate": 9.161094831069138e-05, "loss": 0.8552, "step": 3869 }, { "epoch": 0.21158380317785752, "grad_norm": 2.559964895248413, "learning_rate": 9.160603883481993e-05, "loss": 1.0945, "step": 3870 }, { "epoch": 0.21163847599521612, "grad_norm": 2.0049524307250977, "learning_rate": 9.160112805442781e-05, "loss": 1.0171, "step": 3871 }, { "epoch": 0.21169314881257476, "grad_norm": 2.5492889881134033, "learning_rate": 9.159621596966898e-05, "loss": 1.1464, "step": 3872 }, { "epoch": 0.21174782162993336, "grad_norm": 2.6391007900238037, "learning_rate": 9.15913025806975e-05, "loss": 1.1163, "step": 3873 }, { "epoch": 0.211802494447292, "grad_norm": 2.151974678039551, "learning_rate": 9.158638788766737e-05, "loss": 1.0484, "step": 3874 }, { "epoch": 0.21185716726465062, "grad_norm": 2.734179735183716, "learning_rate": 9.158147189073272e-05, "loss": 1.2514, "step": 3875 }, { "epoch": 0.21191184008200922, "grad_norm": 2.6368050575256348, "learning_rate": 9.157655459004766e-05, "loss": 1.3264, "step": 3876 }, { "epoch": 0.21196651289936785, "grad_norm": 2.615919828414917, "learning_rate": 9.15716359857664e-05, "loss": 1.3127, "step": 3877 }, { "epoch": 0.21202118571672646, "grad_norm": 2.7982139587402344, "learning_rate": 9.156671607804313e-05, "loss": 1.0841, "step": 3878 }, { "epoch": 0.2120758585340851, "grad_norm": 2.3100459575653076, "learning_rate": 9.156179486703214e-05, "loss": 1.0787, "step": 3879 }, { "epoch": 0.2121305313514437, "grad_norm": 2.3354501724243164, "learning_rate": 9.15568723528877e-05, "loss": 1.2084, "step": 3880 }, { "epoch": 0.21218520416880232, "grad_norm": 2.815859794616699, "learning_rate": 9.155194853576414e-05, "loss": 1.0157, "step": 3881 }, { "epoch": 0.21223987698616095, "grad_norm": 2.748612880706787, "learning_rate": 9.154702341581589e-05, "loss": 1.1251, "step": 3882 }, { "epoch": 0.21229454980351956, "grad_norm": 2.8357746601104736, "learning_rate": 9.154209699319734e-05, "loss": 1.1661, "step": 3883 }, { "epoch": 0.2123492226208782, "grad_norm": 3.2410976886749268, "learning_rate": 9.153716926806297e-05, "loss": 0.9883, "step": 3884 }, { "epoch": 0.2124038954382368, "grad_norm": 2.4468884468078613, "learning_rate": 9.153224024056728e-05, "loss": 1.0482, "step": 3885 }, { "epoch": 0.21245856825559542, "grad_norm": 2.1086745262145996, "learning_rate": 9.152730991086479e-05, "loss": 1.1859, "step": 3886 }, { "epoch": 0.21251324107295405, "grad_norm": 2.242708444595337, "learning_rate": 9.152237827911013e-05, "loss": 1.0395, "step": 3887 }, { "epoch": 0.21256791389031265, "grad_norm": 2.704124927520752, "learning_rate": 9.151744534545787e-05, "loss": 1.2904, "step": 3888 }, { "epoch": 0.21262258670767128, "grad_norm": 2.632599115371704, "learning_rate": 9.151251111006273e-05, "loss": 1.2923, "step": 3889 }, { "epoch": 0.2126772595250299, "grad_norm": 2.402358055114746, "learning_rate": 9.150757557307942e-05, "loss": 0.9931, "step": 3890 }, { "epoch": 0.21273193234238852, "grad_norm": 2.167285203933716, "learning_rate": 9.150263873466265e-05, "loss": 1.1451, "step": 3891 }, { "epoch": 0.21278660515974715, "grad_norm": 2.358114719390869, "learning_rate": 9.149770059496723e-05, "loss": 1.0551, "step": 3892 }, { "epoch": 0.21284127797710575, "grad_norm": 3.4046096801757812, "learning_rate": 9.1492761154148e-05, "loss": 1.0565, "step": 3893 }, { "epoch": 0.21289595079446438, "grad_norm": 2.266345262527466, "learning_rate": 9.148782041235982e-05, "loss": 1.2103, "step": 3894 }, { "epoch": 0.212950623611823, "grad_norm": 2.4933393001556396, "learning_rate": 9.14828783697576e-05, "loss": 1.1553, "step": 3895 }, { "epoch": 0.21300529642918162, "grad_norm": 2.6418652534484863, "learning_rate": 9.147793502649628e-05, "loss": 1.1321, "step": 3896 }, { "epoch": 0.21305996924654025, "grad_norm": 2.2604312896728516, "learning_rate": 9.147299038273091e-05, "loss": 1.0899, "step": 3897 }, { "epoch": 0.21311464206389885, "grad_norm": 2.039379119873047, "learning_rate": 9.146804443861647e-05, "loss": 1.1203, "step": 3898 }, { "epoch": 0.21316931488125748, "grad_norm": 2.8098948001861572, "learning_rate": 9.146309719430805e-05, "loss": 1.3061, "step": 3899 }, { "epoch": 0.21322398769861609, "grad_norm": 2.223304271697998, "learning_rate": 9.145814864996077e-05, "loss": 1.0341, "step": 3900 }, { "epoch": 0.21327866051597472, "grad_norm": 2.6309666633605957, "learning_rate": 9.14531988057298e-05, "loss": 1.1231, "step": 3901 }, { "epoch": 0.21333333333333335, "grad_norm": 2.284734010696411, "learning_rate": 9.144824766177032e-05, "loss": 1.3219, "step": 3902 }, { "epoch": 0.21338800615069195, "grad_norm": 2.262666940689087, "learning_rate": 9.144329521823756e-05, "loss": 1.0681, "step": 3903 }, { "epoch": 0.21344267896805058, "grad_norm": 2.7029831409454346, "learning_rate": 9.143834147528682e-05, "loss": 1.1011, "step": 3904 }, { "epoch": 0.21349735178540918, "grad_norm": 3.058392286300659, "learning_rate": 9.143338643307342e-05, "loss": 1.0779, "step": 3905 }, { "epoch": 0.21355202460276781, "grad_norm": 1.9948043823242188, "learning_rate": 9.142843009175273e-05, "loss": 0.9678, "step": 3906 }, { "epoch": 0.21360669742012642, "grad_norm": 2.425776720046997, "learning_rate": 9.142347245148011e-05, "loss": 1.1242, "step": 3907 }, { "epoch": 0.21366137023748505, "grad_norm": 2.3159499168395996, "learning_rate": 9.141851351241104e-05, "loss": 1.1671, "step": 3908 }, { "epoch": 0.21371604305484368, "grad_norm": 2.441922426223755, "learning_rate": 9.1413553274701e-05, "loss": 1.1882, "step": 3909 }, { "epoch": 0.21377071587220228, "grad_norm": 2.5610544681549072, "learning_rate": 9.140859173850549e-05, "loss": 1.1126, "step": 3910 }, { "epoch": 0.2138253886895609, "grad_norm": 2.072512626647949, "learning_rate": 9.140362890398009e-05, "loss": 1.0212, "step": 3911 }, { "epoch": 0.21388006150691952, "grad_norm": 4.235448837280273, "learning_rate": 9.139866477128042e-05, "loss": 1.1983, "step": 3912 }, { "epoch": 0.21393473432427815, "grad_norm": 2.3555920124053955, "learning_rate": 9.13936993405621e-05, "loss": 1.08, "step": 3913 }, { "epoch": 0.21398940714163678, "grad_norm": 2.5174477100372314, "learning_rate": 9.138873261198083e-05, "loss": 1.0163, "step": 3914 }, { "epoch": 0.21404407995899538, "grad_norm": 2.945992946624756, "learning_rate": 9.138376458569234e-05, "loss": 1.1526, "step": 3915 }, { "epoch": 0.214098752776354, "grad_norm": 2.2430977821350098, "learning_rate": 9.13787952618524e-05, "loss": 1.1533, "step": 3916 }, { "epoch": 0.21415342559371262, "grad_norm": 2.819422483444214, "learning_rate": 9.137382464061681e-05, "loss": 1.1805, "step": 3917 }, { "epoch": 0.21420809841107125, "grad_norm": 2.6214520931243896, "learning_rate": 9.136885272214142e-05, "loss": 1.3094, "step": 3918 }, { "epoch": 0.21426277122842988, "grad_norm": 3.100865125656128, "learning_rate": 9.136387950658212e-05, "loss": 1.1744, "step": 3919 }, { "epoch": 0.21431744404578848, "grad_norm": 3.207742214202881, "learning_rate": 9.135890499409483e-05, "loss": 1.3743, "step": 3920 }, { "epoch": 0.2143721168631471, "grad_norm": 2.8066020011901855, "learning_rate": 9.135392918483556e-05, "loss": 1.2809, "step": 3921 }, { "epoch": 0.2144267896805057, "grad_norm": 2.1302998065948486, "learning_rate": 9.134895207896029e-05, "loss": 1.1579, "step": 3922 }, { "epoch": 0.21448146249786434, "grad_norm": 2.5081238746643066, "learning_rate": 9.134397367662505e-05, "loss": 1.2752, "step": 3923 }, { "epoch": 0.21453613531522298, "grad_norm": 2.160933017730713, "learning_rate": 9.1338993977986e-05, "loss": 1.0859, "step": 3924 }, { "epoch": 0.21459080813258158, "grad_norm": 2.27182936668396, "learning_rate": 9.133401298319922e-05, "loss": 1.0645, "step": 3925 }, { "epoch": 0.2146454809499402, "grad_norm": 3.0893754959106445, "learning_rate": 9.132903069242091e-05, "loss": 1.3327, "step": 3926 }, { "epoch": 0.2147001537672988, "grad_norm": 5.085695266723633, "learning_rate": 9.132404710580727e-05, "loss": 0.9018, "step": 3927 }, { "epoch": 0.21475482658465744, "grad_norm": 2.8494086265563965, "learning_rate": 9.131906222351457e-05, "loss": 0.9569, "step": 3928 }, { "epoch": 0.21480949940201605, "grad_norm": 2.6620049476623535, "learning_rate": 9.13140760456991e-05, "loss": 1.0574, "step": 3929 }, { "epoch": 0.21486417221937468, "grad_norm": 3.398831844329834, "learning_rate": 9.130908857251719e-05, "loss": 1.1329, "step": 3930 }, { "epoch": 0.2149188450367333, "grad_norm": 2.4219937324523926, "learning_rate": 9.130409980412523e-05, "loss": 1.062, "step": 3931 }, { "epoch": 0.2149735178540919, "grad_norm": 2.1815145015716553, "learning_rate": 9.129910974067963e-05, "loss": 1.0819, "step": 3932 }, { "epoch": 0.21502819067145054, "grad_norm": 2.5069339275360107, "learning_rate": 9.129411838233686e-05, "loss": 1.0022, "step": 3933 }, { "epoch": 0.21508286348880915, "grad_norm": 2.809112071990967, "learning_rate": 9.12891257292534e-05, "loss": 1.2193, "step": 3934 }, { "epoch": 0.21513753630616778, "grad_norm": 2.5507376194000244, "learning_rate": 9.128413178158581e-05, "loss": 1.1517, "step": 3935 }, { "epoch": 0.2151922091235264, "grad_norm": 2.2182772159576416, "learning_rate": 9.127913653949066e-05, "loss": 1.1381, "step": 3936 }, { "epoch": 0.215246881940885, "grad_norm": 3.593859910964966, "learning_rate": 9.127414000312457e-05, "loss": 1.3347, "step": 3937 }, { "epoch": 0.21530155475824364, "grad_norm": 2.5560247898101807, "learning_rate": 9.12691421726442e-05, "loss": 1.0613, "step": 3938 }, { "epoch": 0.21535622757560224, "grad_norm": 2.7682676315307617, "learning_rate": 9.126414304820627e-05, "loss": 1.1569, "step": 3939 }, { "epoch": 0.21541090039296087, "grad_norm": 2.4749436378479004, "learning_rate": 9.12591426299675e-05, "loss": 1.1683, "step": 3940 }, { "epoch": 0.2154655732103195, "grad_norm": 2.428950071334839, "learning_rate": 9.125414091808471e-05, "loss": 1.1105, "step": 3941 }, { "epoch": 0.2155202460276781, "grad_norm": 2.4544477462768555, "learning_rate": 9.124913791271468e-05, "loss": 1.1689, "step": 3942 }, { "epoch": 0.21557491884503674, "grad_norm": 2.5192902088165283, "learning_rate": 9.12441336140143e-05, "loss": 1.1211, "step": 3943 }, { "epoch": 0.21562959166239534, "grad_norm": 2.4798927307128906, "learning_rate": 9.123912802214048e-05, "loss": 1.3037, "step": 3944 }, { "epoch": 0.21568426447975397, "grad_norm": 2.203411340713501, "learning_rate": 9.123412113725013e-05, "loss": 1.1231, "step": 3945 }, { "epoch": 0.2157389372971126, "grad_norm": 2.7026240825653076, "learning_rate": 9.122911295950029e-05, "loss": 1.1705, "step": 3946 }, { "epoch": 0.2157936101144712, "grad_norm": 2.233142137527466, "learning_rate": 9.122410348904796e-05, "loss": 1.1207, "step": 3947 }, { "epoch": 0.21584828293182984, "grad_norm": 2.401310682296753, "learning_rate": 9.121909272605018e-05, "loss": 1.1717, "step": 3948 }, { "epoch": 0.21590295574918844, "grad_norm": 3.3275787830352783, "learning_rate": 9.12140806706641e-05, "loss": 1.2933, "step": 3949 }, { "epoch": 0.21595762856654707, "grad_norm": 2.7938170433044434, "learning_rate": 9.120906732304686e-05, "loss": 1.1967, "step": 3950 }, { "epoch": 0.2160123013839057, "grad_norm": 2.7079262733459473, "learning_rate": 9.120405268335563e-05, "loss": 1.2334, "step": 3951 }, { "epoch": 0.2160669742012643, "grad_norm": 2.2335219383239746, "learning_rate": 9.119903675174766e-05, "loss": 1.0427, "step": 3952 }, { "epoch": 0.21612164701862294, "grad_norm": 2.1728122234344482, "learning_rate": 9.119401952838021e-05, "loss": 1.1061, "step": 3953 }, { "epoch": 0.21617631983598154, "grad_norm": 2.5333683490753174, "learning_rate": 9.118900101341058e-05, "loss": 0.9863, "step": 3954 }, { "epoch": 0.21623099265334017, "grad_norm": 3.0137529373168945, "learning_rate": 9.118398120699616e-05, "loss": 1.2353, "step": 3955 }, { "epoch": 0.21628566547069877, "grad_norm": 2.5271496772766113, "learning_rate": 9.117896010929431e-05, "loss": 1.1831, "step": 3956 }, { "epoch": 0.2163403382880574, "grad_norm": 4.527108192443848, "learning_rate": 9.117393772046247e-05, "loss": 1.1984, "step": 3957 }, { "epoch": 0.21639501110541604, "grad_norm": 2.9946584701538086, "learning_rate": 9.116891404065811e-05, "loss": 1.2676, "step": 3958 }, { "epoch": 0.21644968392277464, "grad_norm": 2.841756582260132, "learning_rate": 9.116388907003872e-05, "loss": 1.0254, "step": 3959 }, { "epoch": 0.21650435674013327, "grad_norm": 2.6818723678588867, "learning_rate": 9.115886280876189e-05, "loss": 1.0848, "step": 3960 }, { "epoch": 0.21655902955749187, "grad_norm": 2.768251895904541, "learning_rate": 9.115383525698521e-05, "loss": 0.9978, "step": 3961 }, { "epoch": 0.2166137023748505, "grad_norm": 2.7508270740509033, "learning_rate": 9.11488064148663e-05, "loss": 1.1599, "step": 3962 }, { "epoch": 0.21666837519220913, "grad_norm": 2.5709903240203857, "learning_rate": 9.114377628256284e-05, "loss": 1.2424, "step": 3963 }, { "epoch": 0.21672304800956774, "grad_norm": 2.336280345916748, "learning_rate": 9.113874486023256e-05, "loss": 1.1872, "step": 3964 }, { "epoch": 0.21677772082692637, "grad_norm": 2.248084545135498, "learning_rate": 9.113371214803317e-05, "loss": 1.3338, "step": 3965 }, { "epoch": 0.21683239364428497, "grad_norm": 2.351069927215576, "learning_rate": 9.112867814612252e-05, "loss": 1.2397, "step": 3966 }, { "epoch": 0.2168870664616436, "grad_norm": 2.0085973739624023, "learning_rate": 9.112364285465842e-05, "loss": 1.0031, "step": 3967 }, { "epoch": 0.21694173927900223, "grad_norm": 2.7548835277557373, "learning_rate": 9.111860627379875e-05, "loss": 0.8994, "step": 3968 }, { "epoch": 0.21699641209636084, "grad_norm": 2.7057976722717285, "learning_rate": 9.111356840370142e-05, "loss": 1.1675, "step": 3969 }, { "epoch": 0.21705108491371947, "grad_norm": 2.6244776248931885, "learning_rate": 9.110852924452442e-05, "loss": 1.0969, "step": 3970 }, { "epoch": 0.21710575773107807, "grad_norm": 2.2361361980438232, "learning_rate": 9.110348879642571e-05, "loss": 1.0966, "step": 3971 }, { "epoch": 0.2171604305484367, "grad_norm": 2.446627140045166, "learning_rate": 9.109844705956335e-05, "loss": 1.2097, "step": 3972 }, { "epoch": 0.21721510336579533, "grad_norm": 2.269636392593384, "learning_rate": 9.109340403409541e-05, "loss": 0.9746, "step": 3973 }, { "epoch": 0.21726977618315393, "grad_norm": 2.84134840965271, "learning_rate": 9.108835972018e-05, "loss": 1.31, "step": 3974 }, { "epoch": 0.21732444900051257, "grad_norm": 2.2546098232269287, "learning_rate": 9.108331411797532e-05, "loss": 0.9257, "step": 3975 }, { "epoch": 0.21737912181787117, "grad_norm": 2.971484661102295, "learning_rate": 9.107826722763952e-05, "loss": 1.1124, "step": 3976 }, { "epoch": 0.2174337946352298, "grad_norm": 2.2155072689056396, "learning_rate": 9.107321904933088e-05, "loss": 1.0981, "step": 3977 }, { "epoch": 0.21748846745258843, "grad_norm": 2.41479229927063, "learning_rate": 9.106816958320767e-05, "loss": 1.1181, "step": 3978 }, { "epoch": 0.21754314026994703, "grad_norm": 2.921841621398926, "learning_rate": 9.10631188294282e-05, "loss": 1.3001, "step": 3979 }, { "epoch": 0.21759781308730566, "grad_norm": 2.7282321453094482, "learning_rate": 9.105806678815084e-05, "loss": 1.1447, "step": 3980 }, { "epoch": 0.21765248590466427, "grad_norm": 3.0905516147613525, "learning_rate": 9.105301345953397e-05, "loss": 1.2751, "step": 3981 }, { "epoch": 0.2177071587220229, "grad_norm": 2.66951060295105, "learning_rate": 9.104795884373607e-05, "loss": 0.9899, "step": 3982 }, { "epoch": 0.2177618315393815, "grad_norm": 2.2129921913146973, "learning_rate": 9.104290294091561e-05, "loss": 1.0734, "step": 3983 }, { "epoch": 0.21781650435674013, "grad_norm": 2.6070148944854736, "learning_rate": 9.103784575123111e-05, "loss": 1.2407, "step": 3984 }, { "epoch": 0.21787117717409876, "grad_norm": 2.391934394836426, "learning_rate": 9.103278727484115e-05, "loss": 1.1472, "step": 3985 }, { "epoch": 0.21792584999145737, "grad_norm": 2.5229010581970215, "learning_rate": 9.10277275119043e-05, "loss": 1.1561, "step": 3986 }, { "epoch": 0.217980522808816, "grad_norm": 2.4866960048675537, "learning_rate": 9.102266646257923e-05, "loss": 1.1537, "step": 3987 }, { "epoch": 0.2180351956261746, "grad_norm": 2.3593406677246094, "learning_rate": 9.10176041270246e-05, "loss": 0.932, "step": 3988 }, { "epoch": 0.21808986844353323, "grad_norm": 2.836228609085083, "learning_rate": 9.101254050539916e-05, "loss": 1.2591, "step": 3989 }, { "epoch": 0.21814454126089186, "grad_norm": 2.7423341274261475, "learning_rate": 9.100747559786166e-05, "loss": 1.2022, "step": 3990 }, { "epoch": 0.21819921407825046, "grad_norm": 2.7922797203063965, "learning_rate": 9.100240940457095e-05, "loss": 1.2837, "step": 3991 }, { "epoch": 0.2182538868956091, "grad_norm": 2.2381553649902344, "learning_rate": 9.099734192568581e-05, "loss": 1.0863, "step": 3992 }, { "epoch": 0.2183085597129677, "grad_norm": 3.1066088676452637, "learning_rate": 9.099227316136516e-05, "loss": 1.1806, "step": 3993 }, { "epoch": 0.21836323253032633, "grad_norm": 3.412792205810547, "learning_rate": 9.098720311176791e-05, "loss": 1.263, "step": 3994 }, { "epoch": 0.21841790534768496, "grad_norm": 2.4531006813049316, "learning_rate": 9.098213177705306e-05, "loss": 1.0387, "step": 3995 }, { "epoch": 0.21847257816504356, "grad_norm": 2.560724973678589, "learning_rate": 9.097705915737959e-05, "loss": 1.2272, "step": 3996 }, { "epoch": 0.2185272509824022, "grad_norm": 2.7990336418151855, "learning_rate": 9.097198525290656e-05, "loss": 1.1485, "step": 3997 }, { "epoch": 0.2185819237997608, "grad_norm": 3.147130012512207, "learning_rate": 9.096691006379305e-05, "loss": 1.021, "step": 3998 }, { "epoch": 0.21863659661711943, "grad_norm": 2.0537538528442383, "learning_rate": 9.096183359019818e-05, "loss": 1.097, "step": 3999 }, { "epoch": 0.21869126943447806, "grad_norm": 2.2555713653564453, "learning_rate": 9.095675583228114e-05, "loss": 1.1601, "step": 4000 }, { "epoch": 0.21874594225183666, "grad_norm": 2.890263557434082, "learning_rate": 9.095167679020112e-05, "loss": 1.2263, "step": 4001 }, { "epoch": 0.2188006150691953, "grad_norm": 2.2587740421295166, "learning_rate": 9.094659646411739e-05, "loss": 1.2717, "step": 4002 }, { "epoch": 0.2188552878865539, "grad_norm": 3.3304035663604736, "learning_rate": 9.09415148541892e-05, "loss": 0.9756, "step": 4003 }, { "epoch": 0.21890996070391253, "grad_norm": 2.5888354778289795, "learning_rate": 9.093643196057592e-05, "loss": 1.1136, "step": 4004 }, { "epoch": 0.21896463352127113, "grad_norm": 2.717730760574341, "learning_rate": 9.093134778343691e-05, "loss": 0.8822, "step": 4005 }, { "epoch": 0.21901930633862976, "grad_norm": 2.6876368522644043, "learning_rate": 9.092626232293155e-05, "loss": 1.2221, "step": 4006 }, { "epoch": 0.2190739791559884, "grad_norm": 2.130554437637329, "learning_rate": 9.092117557921933e-05, "loss": 1.0934, "step": 4007 }, { "epoch": 0.219128651973347, "grad_norm": 4.029627323150635, "learning_rate": 9.091608755245973e-05, "loss": 1.0231, "step": 4008 }, { "epoch": 0.21918332479070562, "grad_norm": 2.4660003185272217, "learning_rate": 9.091099824281226e-05, "loss": 0.9144, "step": 4009 }, { "epoch": 0.21923799760806423, "grad_norm": 2.879373073577881, "learning_rate": 9.090590765043651e-05, "loss": 1.07, "step": 4010 }, { "epoch": 0.21929267042542286, "grad_norm": 2.6722004413604736, "learning_rate": 9.09008157754921e-05, "loss": 1.362, "step": 4011 }, { "epoch": 0.2193473432427815, "grad_norm": 2.188882827758789, "learning_rate": 9.089572261813866e-05, "loss": 0.9889, "step": 4012 }, { "epoch": 0.2194020160601401, "grad_norm": 2.5800323486328125, "learning_rate": 9.089062817853589e-05, "loss": 1.3466, "step": 4013 }, { "epoch": 0.21945668887749872, "grad_norm": 2.5135626792907715, "learning_rate": 9.088553245684353e-05, "loss": 0.9624, "step": 4014 }, { "epoch": 0.21951136169485733, "grad_norm": 2.07863712310791, "learning_rate": 9.088043545322133e-05, "loss": 1.0653, "step": 4015 }, { "epoch": 0.21956603451221596, "grad_norm": 2.4683549404144287, "learning_rate": 9.087533716782912e-05, "loss": 1.2213, "step": 4016 }, { "epoch": 0.2196207073295746, "grad_norm": 2.419905662536621, "learning_rate": 9.087023760082675e-05, "loss": 0.9478, "step": 4017 }, { "epoch": 0.2196753801469332, "grad_norm": 3.016303539276123, "learning_rate": 9.08651367523741e-05, "loss": 1.2834, "step": 4018 }, { "epoch": 0.21973005296429182, "grad_norm": 2.5271267890930176, "learning_rate": 9.086003462263113e-05, "loss": 1.0764, "step": 4019 }, { "epoch": 0.21978472578165043, "grad_norm": 2.3917694091796875, "learning_rate": 9.085493121175779e-05, "loss": 1.1777, "step": 4020 }, { "epoch": 0.21983939859900906, "grad_norm": 2.6135597229003906, "learning_rate": 9.084982651991408e-05, "loss": 1.1566, "step": 4021 }, { "epoch": 0.2198940714163677, "grad_norm": 2.654291868209839, "learning_rate": 9.08447205472601e-05, "loss": 1.348, "step": 4022 }, { "epoch": 0.2199487442337263, "grad_norm": 2.94380784034729, "learning_rate": 9.083961329395589e-05, "loss": 1.3182, "step": 4023 }, { "epoch": 0.22000341705108492, "grad_norm": 3.786005973815918, "learning_rate": 9.083450476016162e-05, "loss": 1.233, "step": 4024 }, { "epoch": 0.22005808986844352, "grad_norm": 2.9475314617156982, "learning_rate": 9.082939494603744e-05, "loss": 1.2482, "step": 4025 }, { "epoch": 0.22011276268580215, "grad_norm": 1.9602689743041992, "learning_rate": 9.082428385174359e-05, "loss": 0.927, "step": 4026 }, { "epoch": 0.22016743550316079, "grad_norm": 2.7589216232299805, "learning_rate": 9.08191714774403e-05, "loss": 1.1736, "step": 4027 }, { "epoch": 0.2202221083205194, "grad_norm": 2.9497082233428955, "learning_rate": 9.08140578232879e-05, "loss": 1.0182, "step": 4028 }, { "epoch": 0.22027678113787802, "grad_norm": 2.4142298698425293, "learning_rate": 9.080894288944666e-05, "loss": 1.1381, "step": 4029 }, { "epoch": 0.22033145395523662, "grad_norm": 2.759251832962036, "learning_rate": 9.0803826676077e-05, "loss": 1.3244, "step": 4030 }, { "epoch": 0.22038612677259525, "grad_norm": 2.8264923095703125, "learning_rate": 9.079870918333934e-05, "loss": 1.1305, "step": 4031 }, { "epoch": 0.22044079958995386, "grad_norm": 2.5777244567871094, "learning_rate": 9.07935904113941e-05, "loss": 1.1529, "step": 4032 }, { "epoch": 0.2204954724073125, "grad_norm": 2.239030361175537, "learning_rate": 9.078847036040182e-05, "loss": 1.1032, "step": 4033 }, { "epoch": 0.22055014522467112, "grad_norm": 3.0839476585388184, "learning_rate": 9.078334903052299e-05, "loss": 1.1929, "step": 4034 }, { "epoch": 0.22060481804202972, "grad_norm": 2.644684314727783, "learning_rate": 9.077822642191822e-05, "loss": 0.9988, "step": 4035 }, { "epoch": 0.22065949085938835, "grad_norm": 2.410769462585449, "learning_rate": 9.077310253474809e-05, "loss": 1.1461, "step": 4036 }, { "epoch": 0.22071416367674696, "grad_norm": 2.3144938945770264, "learning_rate": 9.07679773691733e-05, "loss": 1.1063, "step": 4037 }, { "epoch": 0.22076883649410559, "grad_norm": 3.6248371601104736, "learning_rate": 9.076285092535451e-05, "loss": 1.1306, "step": 4038 }, { "epoch": 0.22082350931146422, "grad_norm": 2.5182175636291504, "learning_rate": 9.075772320345244e-05, "loss": 1.1458, "step": 4039 }, { "epoch": 0.22087818212882282, "grad_norm": 2.8175673484802246, "learning_rate": 9.075259420362791e-05, "loss": 1.2274, "step": 4040 }, { "epoch": 0.22093285494618145, "grad_norm": 3.6326358318328857, "learning_rate": 9.074746392604172e-05, "loss": 1.0897, "step": 4041 }, { "epoch": 0.22098752776354005, "grad_norm": 2.7856903076171875, "learning_rate": 9.074233237085472e-05, "loss": 1.2938, "step": 4042 }, { "epoch": 0.22104220058089868, "grad_norm": 3.0790762901306152, "learning_rate": 9.073719953822779e-05, "loss": 1.2561, "step": 4043 }, { "epoch": 0.22109687339825732, "grad_norm": 3.1817150115966797, "learning_rate": 9.07320654283219e-05, "loss": 1.0428, "step": 4044 }, { "epoch": 0.22115154621561592, "grad_norm": 2.152343988418579, "learning_rate": 9.0726930041298e-05, "loss": 1.2381, "step": 4045 }, { "epoch": 0.22120621903297455, "grad_norm": 2.463982105255127, "learning_rate": 9.07217933773171e-05, "loss": 1.016, "step": 4046 }, { "epoch": 0.22126089185033315, "grad_norm": 2.986452102661133, "learning_rate": 9.071665543654029e-05, "loss": 1.2036, "step": 4047 }, { "epoch": 0.22131556466769178, "grad_norm": 6.760281562805176, "learning_rate": 9.071151621912862e-05, "loss": 1.2424, "step": 4048 }, { "epoch": 0.22137023748505041, "grad_norm": 3.1748580932617188, "learning_rate": 9.070637572524326e-05, "loss": 1.1814, "step": 4049 }, { "epoch": 0.22142491030240902, "grad_norm": 1.9933710098266602, "learning_rate": 9.070123395504537e-05, "loss": 0.907, "step": 4050 }, { "epoch": 0.22147958311976765, "grad_norm": 2.69828724861145, "learning_rate": 9.069609090869618e-05, "loss": 1.1914, "step": 4051 }, { "epoch": 0.22153425593712625, "grad_norm": 2.5334463119506836, "learning_rate": 9.069094658635693e-05, "loss": 1.1135, "step": 4052 }, { "epoch": 0.22158892875448488, "grad_norm": 2.9102184772491455, "learning_rate": 9.068580098818893e-05, "loss": 1.1839, "step": 4053 }, { "epoch": 0.2216436015718435, "grad_norm": 2.779332160949707, "learning_rate": 9.06806541143535e-05, "loss": 1.3231, "step": 4054 }, { "epoch": 0.22169827438920212, "grad_norm": 2.933954954147339, "learning_rate": 9.067550596501202e-05, "loss": 1.2944, "step": 4055 }, { "epoch": 0.22175294720656075, "grad_norm": 2.3605270385742188, "learning_rate": 9.06703565403259e-05, "loss": 1.1975, "step": 4056 }, { "epoch": 0.22180762002391935, "grad_norm": 5.1020073890686035, "learning_rate": 9.066520584045662e-05, "loss": 1.4119, "step": 4057 }, { "epoch": 0.22186229284127798, "grad_norm": 2.63849139213562, "learning_rate": 9.066005386556567e-05, "loss": 1.1519, "step": 4058 }, { "epoch": 0.22191696565863658, "grad_norm": 2.3872406482696533, "learning_rate": 9.065490061581455e-05, "loss": 1.0995, "step": 4059 }, { "epoch": 0.22197163847599521, "grad_norm": 2.3125808238983154, "learning_rate": 9.064974609136487e-05, "loss": 1.2811, "step": 4060 }, { "epoch": 0.22202631129335385, "grad_norm": 2.8977224826812744, "learning_rate": 9.064459029237825e-05, "loss": 1.1074, "step": 4061 }, { "epoch": 0.22208098411071245, "grad_norm": 2.5224382877349854, "learning_rate": 9.063943321901631e-05, "loss": 1.0952, "step": 4062 }, { "epoch": 0.22213565692807108, "grad_norm": 5.007063865661621, "learning_rate": 9.063427487144078e-05, "loss": 1.0717, "step": 4063 }, { "epoch": 0.22219032974542968, "grad_norm": 2.385443687438965, "learning_rate": 9.062911524981338e-05, "loss": 1.0756, "step": 4064 }, { "epoch": 0.2222450025627883, "grad_norm": 2.369429111480713, "learning_rate": 9.06239543542959e-05, "loss": 1.2266, "step": 4065 }, { "epoch": 0.22229967538014694, "grad_norm": 2.9237070083618164, "learning_rate": 9.061879218505013e-05, "loss": 1.2251, "step": 4066 }, { "epoch": 0.22235434819750555, "grad_norm": 1.974146842956543, "learning_rate": 9.061362874223796e-05, "loss": 1.078, "step": 4067 }, { "epoch": 0.22240902101486418, "grad_norm": 2.8489394187927246, "learning_rate": 9.060846402602123e-05, "loss": 1.2533, "step": 4068 }, { "epoch": 0.22246369383222278, "grad_norm": 2.393552541732788, "learning_rate": 9.060329803656193e-05, "loss": 1.209, "step": 4069 }, { "epoch": 0.2225183666495814, "grad_norm": 2.765106678009033, "learning_rate": 9.059813077402201e-05, "loss": 1.0633, "step": 4070 }, { "epoch": 0.22257303946694004, "grad_norm": 2.155557155609131, "learning_rate": 9.05929622385635e-05, "loss": 1.0939, "step": 4071 }, { "epoch": 0.22262771228429865, "grad_norm": 2.8775393962860107, "learning_rate": 9.058779243034845e-05, "loss": 1.0272, "step": 4072 }, { "epoch": 0.22268238510165728, "grad_norm": 2.7384819984436035, "learning_rate": 9.058262134953893e-05, "loss": 1.2497, "step": 4073 }, { "epoch": 0.22273705791901588, "grad_norm": 2.7942726612091064, "learning_rate": 9.05774489962971e-05, "loss": 1.2039, "step": 4074 }, { "epoch": 0.2227917307363745, "grad_norm": 2.398376941680908, "learning_rate": 9.057227537078513e-05, "loss": 1.1822, "step": 4075 }, { "epoch": 0.22284640355373314, "grad_norm": 2.820984363555908, "learning_rate": 9.056710047316523e-05, "loss": 1.258, "step": 4076 }, { "epoch": 0.22290107637109174, "grad_norm": 2.570708751678467, "learning_rate": 9.056192430359967e-05, "loss": 1.2064, "step": 4077 }, { "epoch": 0.22295574918845038, "grad_norm": 2.193843364715576, "learning_rate": 9.055674686225072e-05, "loss": 1.0524, "step": 4078 }, { "epoch": 0.22301042200580898, "grad_norm": 2.778367519378662, "learning_rate": 9.055156814928074e-05, "loss": 1.0831, "step": 4079 }, { "epoch": 0.2230650948231676, "grad_norm": 1.836267352104187, "learning_rate": 9.054638816485206e-05, "loss": 0.9877, "step": 4080 }, { "epoch": 0.2231197676405262, "grad_norm": 2.4320895671844482, "learning_rate": 9.054120690912715e-05, "loss": 0.9948, "step": 4081 }, { "epoch": 0.22317444045788484, "grad_norm": 2.1685092449188232, "learning_rate": 9.053602438226842e-05, "loss": 1.1179, "step": 4082 }, { "epoch": 0.22322911327524347, "grad_norm": 3.1495039463043213, "learning_rate": 9.053084058443839e-05, "loss": 1.2495, "step": 4083 }, { "epoch": 0.22328378609260208, "grad_norm": 2.1710774898529053, "learning_rate": 9.052565551579959e-05, "loss": 1.1022, "step": 4084 }, { "epoch": 0.2233384589099607, "grad_norm": 2.822847604751587, "learning_rate": 9.052046917651458e-05, "loss": 1.1729, "step": 4085 }, { "epoch": 0.2233931317273193, "grad_norm": 2.687964916229248, "learning_rate": 9.051528156674598e-05, "loss": 1.0158, "step": 4086 }, { "epoch": 0.22344780454467794, "grad_norm": 2.9048104286193848, "learning_rate": 9.051009268665644e-05, "loss": 1.2487, "step": 4087 }, { "epoch": 0.22350247736203657, "grad_norm": 2.462851047515869, "learning_rate": 9.050490253640866e-05, "loss": 1.0177, "step": 4088 }, { "epoch": 0.22355715017939518, "grad_norm": 2.803220510482788, "learning_rate": 9.049971111616537e-05, "loss": 1.2663, "step": 4089 }, { "epoch": 0.2236118229967538, "grad_norm": 3.21006178855896, "learning_rate": 9.049451842608933e-05, "loss": 1.2892, "step": 4090 }, { "epoch": 0.2236664958141124, "grad_norm": 2.5338428020477295, "learning_rate": 9.04893244663434e-05, "loss": 1.2323, "step": 4091 }, { "epoch": 0.22372116863147104, "grad_norm": 2.563284397125244, "learning_rate": 9.048412923709036e-05, "loss": 1.0525, "step": 4092 }, { "epoch": 0.22377584144882967, "grad_norm": 2.345466136932373, "learning_rate": 9.047893273849316e-05, "loss": 1.042, "step": 4093 }, { "epoch": 0.22383051426618827, "grad_norm": 2.527167797088623, "learning_rate": 9.047373497071467e-05, "loss": 1.0545, "step": 4094 }, { "epoch": 0.2238851870835469, "grad_norm": 2.581366777420044, "learning_rate": 9.046853593391793e-05, "loss": 1.0729, "step": 4095 }, { "epoch": 0.2239398599009055, "grad_norm": 2.4302468299865723, "learning_rate": 9.046333562826592e-05, "loss": 1.1352, "step": 4096 }, { "epoch": 0.22399453271826414, "grad_norm": 2.406973123550415, "learning_rate": 9.04581340539217e-05, "loss": 0.9235, "step": 4097 }, { "epoch": 0.22404920553562277, "grad_norm": 2.5898959636688232, "learning_rate": 9.045293121104834e-05, "loss": 0.928, "step": 4098 }, { "epoch": 0.22410387835298137, "grad_norm": 2.7660105228424072, "learning_rate": 9.044772709980897e-05, "loss": 1.0299, "step": 4099 }, { "epoch": 0.22415855117034, "grad_norm": 2.7124316692352295, "learning_rate": 9.04425217203668e-05, "loss": 1.1578, "step": 4100 }, { "epoch": 0.2242132239876986, "grad_norm": 3.64587140083313, "learning_rate": 9.0437315072885e-05, "loss": 1.1426, "step": 4101 }, { "epoch": 0.22426789680505724, "grad_norm": 2.1725146770477295, "learning_rate": 9.043210715752686e-05, "loss": 1.1445, "step": 4102 }, { "epoch": 0.22432256962241587, "grad_norm": 2.574531316757202, "learning_rate": 9.042689797445562e-05, "loss": 1.0988, "step": 4103 }, { "epoch": 0.22437724243977447, "grad_norm": 2.3091511726379395, "learning_rate": 9.042168752383462e-05, "loss": 1.1202, "step": 4104 }, { "epoch": 0.2244319152571331, "grad_norm": 2.690544605255127, "learning_rate": 9.041647580582727e-05, "loss": 1.2829, "step": 4105 }, { "epoch": 0.2244865880744917, "grad_norm": 2.269911289215088, "learning_rate": 9.041126282059694e-05, "loss": 1.1062, "step": 4106 }, { "epoch": 0.22454126089185034, "grad_norm": 2.823566198348999, "learning_rate": 9.040604856830709e-05, "loss": 1.0712, "step": 4107 }, { "epoch": 0.22459593370920894, "grad_norm": 2.484529733657837, "learning_rate": 9.040083304912121e-05, "loss": 1.1868, "step": 4108 }, { "epoch": 0.22465060652656757, "grad_norm": 4.757461071014404, "learning_rate": 9.039561626320283e-05, "loss": 1.059, "step": 4109 }, { "epoch": 0.2247052793439262, "grad_norm": 2.6347532272338867, "learning_rate": 9.03903982107155e-05, "loss": 1.2851, "step": 4110 }, { "epoch": 0.2247599521612848, "grad_norm": 3.329270362854004, "learning_rate": 9.038517889182285e-05, "loss": 1.332, "step": 4111 }, { "epoch": 0.22481462497864343, "grad_norm": 2.545297622680664, "learning_rate": 9.03799583066885e-05, "loss": 1.1688, "step": 4112 }, { "epoch": 0.22486929779600204, "grad_norm": 2.5350213050842285, "learning_rate": 9.037473645547618e-05, "loss": 1.0658, "step": 4113 }, { "epoch": 0.22492397061336067, "grad_norm": 2.0562808513641357, "learning_rate": 9.036951333834959e-05, "loss": 1.0746, "step": 4114 }, { "epoch": 0.2249786434307193, "grad_norm": 2.1732747554779053, "learning_rate": 9.036428895547248e-05, "loss": 1.0954, "step": 4115 }, { "epoch": 0.2250333162480779, "grad_norm": 3.0582005977630615, "learning_rate": 9.035906330700869e-05, "loss": 1.3862, "step": 4116 }, { "epoch": 0.22508798906543653, "grad_norm": 2.01223087310791, "learning_rate": 9.035383639312205e-05, "loss": 1.1138, "step": 4117 }, { "epoch": 0.22514266188279514, "grad_norm": 2.7717721462249756, "learning_rate": 9.034860821397644e-05, "loss": 1.271, "step": 4118 }, { "epoch": 0.22519733470015377, "grad_norm": 2.494223117828369, "learning_rate": 9.034337876973578e-05, "loss": 1.2342, "step": 4119 }, { "epoch": 0.2252520075175124, "grad_norm": 2.553981065750122, "learning_rate": 9.033814806056405e-05, "loss": 1.2218, "step": 4120 }, { "epoch": 0.225306680334871, "grad_norm": 2.4329030513763428, "learning_rate": 9.033291608662525e-05, "loss": 1.2651, "step": 4121 }, { "epoch": 0.22536135315222963, "grad_norm": 3.292189359664917, "learning_rate": 9.032768284808343e-05, "loss": 1.4154, "step": 4122 }, { "epoch": 0.22541602596958824, "grad_norm": 2.412090301513672, "learning_rate": 9.032244834510266e-05, "loss": 1.0117, "step": 4123 }, { "epoch": 0.22547069878694687, "grad_norm": 2.202472448348999, "learning_rate": 9.031721257784707e-05, "loss": 0.991, "step": 4124 }, { "epoch": 0.2255253716043055, "grad_norm": 1.8337795734405518, "learning_rate": 9.03119755464808e-05, "loss": 0.9464, "step": 4125 }, { "epoch": 0.2255800444216641, "grad_norm": 2.6778647899627686, "learning_rate": 9.03067372511681e-05, "loss": 1.2532, "step": 4126 }, { "epoch": 0.22563471723902273, "grad_norm": 2.4821391105651855, "learning_rate": 9.030149769207318e-05, "loss": 1.1585, "step": 4127 }, { "epoch": 0.22568939005638133, "grad_norm": 2.3203670978546143, "learning_rate": 9.029625686936034e-05, "loss": 0.9255, "step": 4128 }, { "epoch": 0.22574406287373996, "grad_norm": 2.729766607284546, "learning_rate": 9.029101478319387e-05, "loss": 1.2287, "step": 4129 }, { "epoch": 0.2257987356910986, "grad_norm": 2.5795581340789795, "learning_rate": 9.028577143373816e-05, "loss": 1.0683, "step": 4130 }, { "epoch": 0.2258534085084572, "grad_norm": 2.6903884410858154, "learning_rate": 9.02805268211576e-05, "loss": 1.3344, "step": 4131 }, { "epoch": 0.22590808132581583, "grad_norm": 2.627617835998535, "learning_rate": 9.027528094561664e-05, "loss": 1.1018, "step": 4132 }, { "epoch": 0.22596275414317443, "grad_norm": 2.3029279708862305, "learning_rate": 9.027003380727974e-05, "loss": 1.2248, "step": 4133 }, { "epoch": 0.22601742696053306, "grad_norm": 2.1988983154296875, "learning_rate": 9.026478540631144e-05, "loss": 1.1563, "step": 4134 }, { "epoch": 0.22607209977789167, "grad_norm": 3.0192716121673584, "learning_rate": 9.02595357428763e-05, "loss": 1.3654, "step": 4135 }, { "epoch": 0.2261267725952503, "grad_norm": 2.073377847671509, "learning_rate": 9.025428481713887e-05, "loss": 1.0458, "step": 4136 }, { "epoch": 0.22618144541260893, "grad_norm": 2.135209560394287, "learning_rate": 9.024903262926386e-05, "loss": 1.0798, "step": 4137 }, { "epoch": 0.22623611822996753, "grad_norm": 3.0700061321258545, "learning_rate": 9.02437791794159e-05, "loss": 1.3182, "step": 4138 }, { "epoch": 0.22629079104732616, "grad_norm": 2.4953830242156982, "learning_rate": 9.023852446775973e-05, "loss": 1.1635, "step": 4139 }, { "epoch": 0.22634546386468476, "grad_norm": 2.6940178871154785, "learning_rate": 9.02332684944601e-05, "loss": 1.1885, "step": 4140 }, { "epoch": 0.2264001366820434, "grad_norm": 5.088781356811523, "learning_rate": 9.022801125968179e-05, "loss": 1.3043, "step": 4141 }, { "epoch": 0.22645480949940203, "grad_norm": 4.539536476135254, "learning_rate": 9.022275276358965e-05, "loss": 1.0175, "step": 4142 }, { "epoch": 0.22650948231676063, "grad_norm": 2.1585159301757812, "learning_rate": 9.021749300634856e-05, "loss": 0.975, "step": 4143 }, { "epoch": 0.22656415513411926, "grad_norm": 2.60402512550354, "learning_rate": 9.021223198812345e-05, "loss": 1.016, "step": 4144 }, { "epoch": 0.22661882795147786, "grad_norm": 7.260556697845459, "learning_rate": 9.020696970907925e-05, "loss": 1.3087, "step": 4145 }, { "epoch": 0.2266735007688365, "grad_norm": 2.690110921859741, "learning_rate": 9.020170616938095e-05, "loss": 1.1077, "step": 4146 }, { "epoch": 0.22672817358619513, "grad_norm": 2.354524612426758, "learning_rate": 9.019644136919358e-05, "loss": 1.1907, "step": 4147 }, { "epoch": 0.22678284640355373, "grad_norm": 2.240708351135254, "learning_rate": 9.019117530868225e-05, "loss": 1.0782, "step": 4148 }, { "epoch": 0.22683751922091236, "grad_norm": 2.6522059440612793, "learning_rate": 9.018590798801204e-05, "loss": 1.2461, "step": 4149 }, { "epoch": 0.22689219203827096, "grad_norm": 2.3471996784210205, "learning_rate": 9.018063940734811e-05, "loss": 0.9936, "step": 4150 }, { "epoch": 0.2269468648556296, "grad_norm": 3.9063987731933594, "learning_rate": 9.017536956685566e-05, "loss": 1.1377, "step": 4151 }, { "epoch": 0.22700153767298822, "grad_norm": 2.7535529136657715, "learning_rate": 9.017009846669992e-05, "loss": 1.0603, "step": 4152 }, { "epoch": 0.22705621049034683, "grad_norm": 2.4054555892944336, "learning_rate": 9.016482610704615e-05, "loss": 1.0169, "step": 4153 }, { "epoch": 0.22711088330770546, "grad_norm": 2.2736635208129883, "learning_rate": 9.015955248805966e-05, "loss": 1.1701, "step": 4154 }, { "epoch": 0.22716555612506406, "grad_norm": 2.3083527088165283, "learning_rate": 9.01542776099058e-05, "loss": 1.0249, "step": 4155 }, { "epoch": 0.2272202289424227, "grad_norm": 2.5008552074432373, "learning_rate": 9.014900147274998e-05, "loss": 1.3608, "step": 4156 }, { "epoch": 0.22727490175978132, "grad_norm": 2.6494178771972656, "learning_rate": 9.01437240767576e-05, "loss": 0.9939, "step": 4157 }, { "epoch": 0.22732957457713993, "grad_norm": 2.3947649002075195, "learning_rate": 9.013844542209414e-05, "loss": 1.3291, "step": 4158 }, { "epoch": 0.22738424739449856, "grad_norm": 2.6258022785186768, "learning_rate": 9.013316550892513e-05, "loss": 1.2697, "step": 4159 }, { "epoch": 0.22743892021185716, "grad_norm": 3.4943912029266357, "learning_rate": 9.012788433741607e-05, "loss": 1.2056, "step": 4160 }, { "epoch": 0.2274935930292158, "grad_norm": 2.909872531890869, "learning_rate": 9.012260190773259e-05, "loss": 0.9188, "step": 4161 }, { "epoch": 0.2275482658465744, "grad_norm": 2.1982908248901367, "learning_rate": 9.011731822004028e-05, "loss": 0.8417, "step": 4162 }, { "epoch": 0.22760293866393302, "grad_norm": 2.7200849056243896, "learning_rate": 9.011203327450484e-05, "loss": 0.8403, "step": 4163 }, { "epoch": 0.22765761148129166, "grad_norm": 2.6142232418060303, "learning_rate": 9.010674707129194e-05, "loss": 1.0444, "step": 4164 }, { "epoch": 0.22771228429865026, "grad_norm": 2.16957950592041, "learning_rate": 9.010145961056736e-05, "loss": 1.1803, "step": 4165 }, { "epoch": 0.2277669571160089, "grad_norm": 2.430880308151245, "learning_rate": 9.009617089249686e-05, "loss": 1.2357, "step": 4166 }, { "epoch": 0.2278216299333675, "grad_norm": 2.4328277111053467, "learning_rate": 9.009088091724627e-05, "loss": 1.0391, "step": 4167 }, { "epoch": 0.22787630275072612, "grad_norm": 4.222201347351074, "learning_rate": 9.008558968498146e-05, "loss": 1.1481, "step": 4168 }, { "epoch": 0.22793097556808475, "grad_norm": 2.792951822280884, "learning_rate": 9.00802971958683e-05, "loss": 1.2843, "step": 4169 }, { "epoch": 0.22798564838544336, "grad_norm": 2.3235585689544678, "learning_rate": 9.007500345007278e-05, "loss": 1.1959, "step": 4170 }, { "epoch": 0.228040321202802, "grad_norm": 2.680835247039795, "learning_rate": 9.006970844776083e-05, "loss": 1.199, "step": 4171 }, { "epoch": 0.2280949940201606, "grad_norm": 2.441218137741089, "learning_rate": 9.006441218909852e-05, "loss": 1.0984, "step": 4172 }, { "epoch": 0.22814966683751922, "grad_norm": 2.361264705657959, "learning_rate": 9.005911467425188e-05, "loss": 1.1058, "step": 4173 }, { "epoch": 0.22820433965487785, "grad_norm": 2.477938175201416, "learning_rate": 9.005381590338702e-05, "loss": 1.2888, "step": 4174 }, { "epoch": 0.22825901247223646, "grad_norm": 2.5901601314544678, "learning_rate": 9.004851587667005e-05, "loss": 1.1313, "step": 4175 }, { "epoch": 0.2283136852895951, "grad_norm": 2.870009422302246, "learning_rate": 9.004321459426719e-05, "loss": 1.1094, "step": 4176 }, { "epoch": 0.2283683581069537, "grad_norm": 2.453070878982544, "learning_rate": 9.003791205634463e-05, "loss": 1.1572, "step": 4177 }, { "epoch": 0.22842303092431232, "grad_norm": 4.1056365966796875, "learning_rate": 9.003260826306862e-05, "loss": 1.2494, "step": 4178 }, { "epoch": 0.22847770374167095, "grad_norm": 2.4994356632232666, "learning_rate": 9.00273032146055e-05, "loss": 1.1549, "step": 4179 }, { "epoch": 0.22853237655902955, "grad_norm": 2.7218713760375977, "learning_rate": 9.002199691112156e-05, "loss": 1.2208, "step": 4180 }, { "epoch": 0.22858704937638818, "grad_norm": 2.0714516639709473, "learning_rate": 9.001668935278318e-05, "loss": 1.2019, "step": 4181 }, { "epoch": 0.2286417221937468, "grad_norm": 2.125405788421631, "learning_rate": 9.00113805397568e-05, "loss": 0.9899, "step": 4182 }, { "epoch": 0.22869639501110542, "grad_norm": 2.4239001274108887, "learning_rate": 9.000607047220883e-05, "loss": 1.1249, "step": 4183 }, { "epoch": 0.22875106782846402, "grad_norm": 2.196591854095459, "learning_rate": 9.000075915030582e-05, "loss": 1.0816, "step": 4184 }, { "epoch": 0.22880574064582265, "grad_norm": 2.16316294670105, "learning_rate": 8.999544657421425e-05, "loss": 1.0297, "step": 4185 }, { "epoch": 0.22886041346318128, "grad_norm": 1.9318920373916626, "learning_rate": 8.999013274410072e-05, "loss": 1.1364, "step": 4186 }, { "epoch": 0.2289150862805399, "grad_norm": 2.7106332778930664, "learning_rate": 8.998481766013182e-05, "loss": 1.0176, "step": 4187 }, { "epoch": 0.22896975909789852, "grad_norm": 2.706834316253662, "learning_rate": 8.997950132247423e-05, "loss": 1.186, "step": 4188 }, { "epoch": 0.22902443191525712, "grad_norm": 4.109928607940674, "learning_rate": 8.99741837312946e-05, "loss": 1.3221, "step": 4189 }, { "epoch": 0.22907910473261575, "grad_norm": 2.598205804824829, "learning_rate": 8.99688648867597e-05, "loss": 1.2993, "step": 4190 }, { "epoch": 0.22913377754997438, "grad_norm": 2.4561727046966553, "learning_rate": 8.996354478903626e-05, "loss": 1.2857, "step": 4191 }, { "epoch": 0.22918845036733299, "grad_norm": 2.3667778968811035, "learning_rate": 8.995822343829111e-05, "loss": 1.0943, "step": 4192 }, { "epoch": 0.22924312318469162, "grad_norm": 2.6839284896850586, "learning_rate": 8.995290083469108e-05, "loss": 1.1625, "step": 4193 }, { "epoch": 0.22929779600205022, "grad_norm": 2.3928017616271973, "learning_rate": 8.994757697840308e-05, "loss": 1.1144, "step": 4194 }, { "epoch": 0.22935246881940885, "grad_norm": 2.3423004150390625, "learning_rate": 8.994225186959402e-05, "loss": 1.1258, "step": 4195 }, { "epoch": 0.22940714163676748, "grad_norm": 2.2332310676574707, "learning_rate": 8.993692550843087e-05, "loss": 1.1948, "step": 4196 }, { "epoch": 0.22946181445412608, "grad_norm": 3.046227216720581, "learning_rate": 8.993159789508062e-05, "loss": 1.3654, "step": 4197 }, { "epoch": 0.22951648727148471, "grad_norm": 4.398423194885254, "learning_rate": 8.992626902971031e-05, "loss": 1.3959, "step": 4198 }, { "epoch": 0.22957116008884332, "grad_norm": 3.1394238471984863, "learning_rate": 8.992093891248704e-05, "loss": 1.1933, "step": 4199 }, { "epoch": 0.22962583290620195, "grad_norm": 1.9710586071014404, "learning_rate": 8.991560754357793e-05, "loss": 1.0285, "step": 4200 }, { "epoch": 0.22968050572356058, "grad_norm": 2.6752572059631348, "learning_rate": 8.991027492315012e-05, "loss": 1.2103, "step": 4201 }, { "epoch": 0.22973517854091918, "grad_norm": 2.593446969985962, "learning_rate": 8.990494105137083e-05, "loss": 1.2441, "step": 4202 }, { "epoch": 0.2297898513582778, "grad_norm": 2.860847234725952, "learning_rate": 8.989960592840729e-05, "loss": 1.0855, "step": 4203 }, { "epoch": 0.22984452417563642, "grad_norm": 2.6360318660736084, "learning_rate": 8.98942695544268e-05, "loss": 1.2358, "step": 4204 }, { "epoch": 0.22989919699299505, "grad_norm": 2.418131113052368, "learning_rate": 8.988893192959665e-05, "loss": 1.0918, "step": 4205 }, { "epoch": 0.22995386981035368, "grad_norm": 3.448103189468384, "learning_rate": 8.988359305408419e-05, "loss": 0.9936, "step": 4206 }, { "epoch": 0.23000854262771228, "grad_norm": 2.554392099380493, "learning_rate": 8.987825292805683e-05, "loss": 1.1801, "step": 4207 }, { "epoch": 0.2300632154450709, "grad_norm": 3.072615385055542, "learning_rate": 8.9872911551682e-05, "loss": 0.9763, "step": 4208 }, { "epoch": 0.23011788826242952, "grad_norm": 3.9481186866760254, "learning_rate": 8.98675689251272e-05, "loss": 1.2058, "step": 4209 }, { "epoch": 0.23017256107978815, "grad_norm": 2.6309595108032227, "learning_rate": 8.986222504855991e-05, "loss": 1.2992, "step": 4210 }, { "epoch": 0.23022723389714675, "grad_norm": 2.4530317783355713, "learning_rate": 8.98568799221477e-05, "loss": 1.3124, "step": 4211 }, { "epoch": 0.23028190671450538, "grad_norm": 2.380441904067993, "learning_rate": 8.985153354605816e-05, "loss": 1.1993, "step": 4212 }, { "epoch": 0.230336579531864, "grad_norm": 2.9765851497650146, "learning_rate": 8.98461859204589e-05, "loss": 1.475, "step": 4213 }, { "epoch": 0.2303912523492226, "grad_norm": 2.3889379501342773, "learning_rate": 8.984083704551762e-05, "loss": 1.1442, "step": 4214 }, { "epoch": 0.23044592516658124, "grad_norm": 2.497520923614502, "learning_rate": 8.983548692140203e-05, "loss": 1.0197, "step": 4215 }, { "epoch": 0.23050059798393985, "grad_norm": 4.142690658569336, "learning_rate": 8.983013554827983e-05, "loss": 1.2126, "step": 4216 }, { "epoch": 0.23055527080129848, "grad_norm": 2.4898300170898438, "learning_rate": 8.982478292631887e-05, "loss": 1.1409, "step": 4217 }, { "epoch": 0.2306099436186571, "grad_norm": 2.5510053634643555, "learning_rate": 8.981942905568695e-05, "loss": 1.0022, "step": 4218 }, { "epoch": 0.2306646164360157, "grad_norm": 2.609814405441284, "learning_rate": 8.981407393655193e-05, "loss": 1.1647, "step": 4219 }, { "epoch": 0.23071928925337434, "grad_norm": 3.816800117492676, "learning_rate": 8.980871756908171e-05, "loss": 1.0839, "step": 4220 }, { "epoch": 0.23077396207073295, "grad_norm": 2.1468193531036377, "learning_rate": 8.980335995344427e-05, "loss": 1.1502, "step": 4221 }, { "epoch": 0.23082863488809158, "grad_norm": 3.9228718280792236, "learning_rate": 8.979800108980753e-05, "loss": 1.137, "step": 4222 }, { "epoch": 0.2308833077054502, "grad_norm": 4.192899703979492, "learning_rate": 8.979264097833959e-05, "loss": 1.3673, "step": 4223 }, { "epoch": 0.2309379805228088, "grad_norm": 2.7017719745635986, "learning_rate": 8.978727961920846e-05, "loss": 0.9505, "step": 4224 }, { "epoch": 0.23099265334016744, "grad_norm": 2.942239284515381, "learning_rate": 8.978191701258224e-05, "loss": 1.0451, "step": 4225 }, { "epoch": 0.23104732615752605, "grad_norm": 2.6310224533081055, "learning_rate": 8.977655315862909e-05, "loss": 0.9366, "step": 4226 }, { "epoch": 0.23110199897488468, "grad_norm": 2.6022157669067383, "learning_rate": 8.977118805751718e-05, "loss": 1.1769, "step": 4227 }, { "epoch": 0.2311566717922433, "grad_norm": 2.006481170654297, "learning_rate": 8.976582170941475e-05, "loss": 1.0699, "step": 4228 }, { "epoch": 0.2312113446096019, "grad_norm": 2.5383522510528564, "learning_rate": 8.976045411449e-05, "loss": 1.2386, "step": 4229 }, { "epoch": 0.23126601742696054, "grad_norm": 2.2314810752868652, "learning_rate": 8.975508527291127e-05, "loss": 1.0668, "step": 4230 }, { "epoch": 0.23132069024431914, "grad_norm": 2.5900182723999023, "learning_rate": 8.974971518484692e-05, "loss": 1.0504, "step": 4231 }, { "epoch": 0.23137536306167777, "grad_norm": 2.0954642295837402, "learning_rate": 8.974434385046526e-05, "loss": 1.1501, "step": 4232 }, { "epoch": 0.2314300358790364, "grad_norm": 6.160410404205322, "learning_rate": 8.973897126993476e-05, "loss": 1.2049, "step": 4233 }, { "epoch": 0.231484708696395, "grad_norm": 2.7347710132598877, "learning_rate": 8.973359744342382e-05, "loss": 1.2302, "step": 4234 }, { "epoch": 0.23153938151375364, "grad_norm": 2.394456386566162, "learning_rate": 8.972822237110099e-05, "loss": 1.0855, "step": 4235 }, { "epoch": 0.23159405433111224, "grad_norm": 2.2728335857391357, "learning_rate": 8.972284605313474e-05, "loss": 1.2468, "step": 4236 }, { "epoch": 0.23164872714847087, "grad_norm": 2.6393487453460693, "learning_rate": 8.971746848969369e-05, "loss": 1.1069, "step": 4237 }, { "epoch": 0.23170339996582948, "grad_norm": 2.152897834777832, "learning_rate": 8.971208968094644e-05, "loss": 0.9124, "step": 4238 }, { "epoch": 0.2317580727831881, "grad_norm": 2.7432918548583984, "learning_rate": 8.97067096270616e-05, "loss": 1.195, "step": 4239 }, { "epoch": 0.23181274560054674, "grad_norm": 2.7273306846618652, "learning_rate": 8.97013283282079e-05, "loss": 1.0895, "step": 4240 }, { "epoch": 0.23186741841790534, "grad_norm": 2.587459087371826, "learning_rate": 8.969594578455404e-05, "loss": 1.2346, "step": 4241 }, { "epoch": 0.23192209123526397, "grad_norm": 2.996654510498047, "learning_rate": 8.969056199626882e-05, "loss": 1.1437, "step": 4242 }, { "epoch": 0.23197676405262257, "grad_norm": 2.3707833290100098, "learning_rate": 8.968517696352099e-05, "loss": 0.9214, "step": 4243 }, { "epoch": 0.2320314368699812, "grad_norm": 3.0189602375030518, "learning_rate": 8.967979068647943e-05, "loss": 1.0257, "step": 4244 }, { "epoch": 0.23208610968733984, "grad_norm": 2.298938035964966, "learning_rate": 8.967440316531302e-05, "loss": 1.0912, "step": 4245 }, { "epoch": 0.23214078250469844, "grad_norm": 2.7701706886291504, "learning_rate": 8.966901440019066e-05, "loss": 1.2846, "step": 4246 }, { "epoch": 0.23219545532205707, "grad_norm": 2.2512073516845703, "learning_rate": 8.966362439128134e-05, "loss": 1.2321, "step": 4247 }, { "epoch": 0.23225012813941567, "grad_norm": 2.8509559631347656, "learning_rate": 8.965823313875403e-05, "loss": 0.9685, "step": 4248 }, { "epoch": 0.2323048009567743, "grad_norm": 3.4435884952545166, "learning_rate": 8.965284064277779e-05, "loss": 1.0029, "step": 4249 }, { "epoch": 0.23235947377413294, "grad_norm": 2.5197689533233643, "learning_rate": 8.96474469035217e-05, "loss": 1.123, "step": 4250 }, { "epoch": 0.23241414659149154, "grad_norm": 2.4921271800994873, "learning_rate": 8.964205192115484e-05, "loss": 1.219, "step": 4251 }, { "epoch": 0.23246881940885017, "grad_norm": 2.3359827995300293, "learning_rate": 8.963665569584641e-05, "loss": 1.2071, "step": 4252 }, { "epoch": 0.23252349222620877, "grad_norm": 3.720906972885132, "learning_rate": 8.963125822776557e-05, "loss": 1.0214, "step": 4253 }, { "epoch": 0.2325781650435674, "grad_norm": 2.308029890060425, "learning_rate": 8.962585951708157e-05, "loss": 1.1536, "step": 4254 }, { "epoch": 0.23263283786092603, "grad_norm": 3.126085042953491, "learning_rate": 8.962045956396368e-05, "loss": 1.1797, "step": 4255 }, { "epoch": 0.23268751067828464, "grad_norm": 2.493311643600464, "learning_rate": 8.96150583685812e-05, "loss": 1.1623, "step": 4256 }, { "epoch": 0.23274218349564327, "grad_norm": 3.6503210067749023, "learning_rate": 8.960965593110349e-05, "loss": 1.1249, "step": 4257 }, { "epoch": 0.23279685631300187, "grad_norm": 2.137456178665161, "learning_rate": 8.960425225169995e-05, "loss": 0.9805, "step": 4258 }, { "epoch": 0.2328515291303605, "grad_norm": 2.3328542709350586, "learning_rate": 8.959884733053998e-05, "loss": 1.1729, "step": 4259 }, { "epoch": 0.2329062019477191, "grad_norm": 2.2466530799865723, "learning_rate": 8.959344116779307e-05, "loss": 0.9843, "step": 4260 }, { "epoch": 0.23296087476507774, "grad_norm": 3.072500467300415, "learning_rate": 8.95880337636287e-05, "loss": 1.3763, "step": 4261 }, { "epoch": 0.23301554758243637, "grad_norm": 2.414917469024658, "learning_rate": 8.958262511821645e-05, "loss": 1.1548, "step": 4262 }, { "epoch": 0.23307022039979497, "grad_norm": 2.27494740486145, "learning_rate": 8.957721523172589e-05, "loss": 1.0672, "step": 4263 }, { "epoch": 0.2331248932171536, "grad_norm": 3.119671106338501, "learning_rate": 8.957180410432662e-05, "loss": 1.3756, "step": 4264 }, { "epoch": 0.2331795660345122, "grad_norm": 2.4319491386413574, "learning_rate": 8.956639173618833e-05, "loss": 1.1079, "step": 4265 }, { "epoch": 0.23323423885187083, "grad_norm": 2.7501983642578125, "learning_rate": 8.956097812748069e-05, "loss": 1.1349, "step": 4266 }, { "epoch": 0.23328891166922947, "grad_norm": 2.3602559566497803, "learning_rate": 8.955556327837347e-05, "loss": 1.179, "step": 4267 }, { "epoch": 0.23334358448658807, "grad_norm": 2.3303565979003906, "learning_rate": 8.955014718903643e-05, "loss": 1.053, "step": 4268 }, { "epoch": 0.2333982573039467, "grad_norm": 3.1923611164093018, "learning_rate": 8.95447298596394e-05, "loss": 1.0262, "step": 4269 }, { "epoch": 0.2334529301213053, "grad_norm": 2.1273069381713867, "learning_rate": 8.95393112903522e-05, "loss": 1.1297, "step": 4270 }, { "epoch": 0.23350760293866393, "grad_norm": 2.03975248336792, "learning_rate": 8.953389148134478e-05, "loss": 1.077, "step": 4271 }, { "epoch": 0.23356227575602256, "grad_norm": 2.0339908599853516, "learning_rate": 8.952847043278703e-05, "loss": 0.9962, "step": 4272 }, { "epoch": 0.23361694857338117, "grad_norm": 4.293134689331055, "learning_rate": 8.952304814484894e-05, "loss": 1.2511, "step": 4273 }, { "epoch": 0.2336716213907398, "grad_norm": 2.745722770690918, "learning_rate": 8.951762461770053e-05, "loss": 1.3531, "step": 4274 }, { "epoch": 0.2337262942080984, "grad_norm": 2.888118267059326, "learning_rate": 8.951219985151182e-05, "loss": 1.1107, "step": 4275 }, { "epoch": 0.23378096702545703, "grad_norm": 3.1205809116363525, "learning_rate": 8.950677384645292e-05, "loss": 1.0398, "step": 4276 }, { "epoch": 0.23383563984281566, "grad_norm": 3.538604259490967, "learning_rate": 8.950134660269396e-05, "loss": 1.192, "step": 4277 }, { "epoch": 0.23389031266017427, "grad_norm": 2.12473464012146, "learning_rate": 8.94959181204051e-05, "loss": 1.0002, "step": 4278 }, { "epoch": 0.2339449854775329, "grad_norm": 2.5219457149505615, "learning_rate": 8.949048839975654e-05, "loss": 1.2918, "step": 4279 }, { "epoch": 0.2339996582948915, "grad_norm": 2.7378718852996826, "learning_rate": 8.948505744091853e-05, "loss": 0.9187, "step": 4280 }, { "epoch": 0.23405433111225013, "grad_norm": 4.047329425811768, "learning_rate": 8.947962524406135e-05, "loss": 1.2988, "step": 4281 }, { "epoch": 0.23410900392960876, "grad_norm": 2.306605815887451, "learning_rate": 8.947419180935532e-05, "loss": 1.1149, "step": 4282 }, { "epoch": 0.23416367674696736, "grad_norm": 2.5869815349578857, "learning_rate": 8.946875713697083e-05, "loss": 1.2394, "step": 4283 }, { "epoch": 0.234218349564326, "grad_norm": 3.0518195629119873, "learning_rate": 8.946332122707823e-05, "loss": 1.1446, "step": 4284 }, { "epoch": 0.2342730223816846, "grad_norm": 2.475139617919922, "learning_rate": 8.945788407984799e-05, "loss": 1.2613, "step": 4285 }, { "epoch": 0.23432769519904323, "grad_norm": 4.435600757598877, "learning_rate": 8.94524456954506e-05, "loss": 1.5757, "step": 4286 }, { "epoch": 0.23438236801640183, "grad_norm": 2.979572296142578, "learning_rate": 8.944700607405651e-05, "loss": 1.0847, "step": 4287 }, { "epoch": 0.23443704083376046, "grad_norm": 2.3593640327453613, "learning_rate": 8.944156521583636e-05, "loss": 1.1463, "step": 4288 }, { "epoch": 0.2344917136511191, "grad_norm": 2.9592838287353516, "learning_rate": 8.943612312096068e-05, "loss": 0.892, "step": 4289 }, { "epoch": 0.2345463864684777, "grad_norm": 2.5239250659942627, "learning_rate": 8.943067978960014e-05, "loss": 1.2546, "step": 4290 }, { "epoch": 0.23460105928583633, "grad_norm": 2.5146615505218506, "learning_rate": 8.942523522192538e-05, "loss": 1.3571, "step": 4291 }, { "epoch": 0.23465573210319493, "grad_norm": 2.7996582984924316, "learning_rate": 8.941978941810714e-05, "loss": 1.2267, "step": 4292 }, { "epoch": 0.23471040492055356, "grad_norm": 3.5421364307403564, "learning_rate": 8.941434237831616e-05, "loss": 1.2212, "step": 4293 }, { "epoch": 0.2347650777379122, "grad_norm": 3.0196001529693604, "learning_rate": 8.940889410272321e-05, "loss": 1.2289, "step": 4294 }, { "epoch": 0.2348197505552708, "grad_norm": 2.6477489471435547, "learning_rate": 8.940344459149913e-05, "loss": 1.1745, "step": 4295 }, { "epoch": 0.23487442337262943, "grad_norm": 2.871243476867676, "learning_rate": 8.939799384481478e-05, "loss": 1.1653, "step": 4296 }, { "epoch": 0.23492909618998803, "grad_norm": 2.532175064086914, "learning_rate": 8.939254186284106e-05, "loss": 1.2962, "step": 4297 }, { "epoch": 0.23498376900734666, "grad_norm": 2.9628164768218994, "learning_rate": 8.938708864574892e-05, "loss": 1.3277, "step": 4298 }, { "epoch": 0.2350384418247053, "grad_norm": 2.4618687629699707, "learning_rate": 8.938163419370934e-05, "loss": 1.1549, "step": 4299 }, { "epoch": 0.2350931146420639, "grad_norm": 2.511340618133545, "learning_rate": 8.937617850689334e-05, "loss": 1.1975, "step": 4300 }, { "epoch": 0.23514778745942252, "grad_norm": 2.5666332244873047, "learning_rate": 8.937072158547198e-05, "loss": 1.0403, "step": 4301 }, { "epoch": 0.23520246027678113, "grad_norm": 2.303586006164551, "learning_rate": 8.936526342961635e-05, "loss": 0.9721, "step": 4302 }, { "epoch": 0.23525713309413976, "grad_norm": 2.7827694416046143, "learning_rate": 8.935980403949758e-05, "loss": 1.1752, "step": 4303 }, { "epoch": 0.2353118059114984, "grad_norm": 2.050879716873169, "learning_rate": 8.935434341528686e-05, "loss": 0.8873, "step": 4304 }, { "epoch": 0.235366478728857, "grad_norm": 2.5539798736572266, "learning_rate": 8.934888155715537e-05, "loss": 1.168, "step": 4305 }, { "epoch": 0.23542115154621562, "grad_norm": 1.9890198707580566, "learning_rate": 8.934341846527442e-05, "loss": 1.0114, "step": 4306 }, { "epoch": 0.23547582436357423, "grad_norm": 3.0028727054595947, "learning_rate": 8.933795413981525e-05, "loss": 1.0704, "step": 4307 }, { "epoch": 0.23553049718093286, "grad_norm": 2.5799765586853027, "learning_rate": 8.933248858094922e-05, "loss": 1.1392, "step": 4308 }, { "epoch": 0.2355851699982915, "grad_norm": 2.840627431869507, "learning_rate": 8.932702178884768e-05, "loss": 1.1283, "step": 4309 }, { "epoch": 0.2356398428156501, "grad_norm": 2.4200661182403564, "learning_rate": 8.932155376368204e-05, "loss": 1.1507, "step": 4310 }, { "epoch": 0.23569451563300872, "grad_norm": 2.5223805904388428, "learning_rate": 8.931608450562375e-05, "loss": 0.9763, "step": 4311 }, { "epoch": 0.23574918845036733, "grad_norm": 2.352609395980835, "learning_rate": 8.931061401484428e-05, "loss": 1.1436, "step": 4312 }, { "epoch": 0.23580386126772596, "grad_norm": 2.60688853263855, "learning_rate": 8.930514229151519e-05, "loss": 1.0496, "step": 4313 }, { "epoch": 0.23585853408508456, "grad_norm": 1.7835441827774048, "learning_rate": 8.929966933580798e-05, "loss": 0.8948, "step": 4314 }, { "epoch": 0.2359132069024432, "grad_norm": 2.750875949859619, "learning_rate": 8.929419514789429e-05, "loss": 1.2988, "step": 4315 }, { "epoch": 0.23596787971980182, "grad_norm": 1.9837164878845215, "learning_rate": 8.928871972794577e-05, "loss": 0.9875, "step": 4316 }, { "epoch": 0.23602255253716042, "grad_norm": 1.9164059162139893, "learning_rate": 8.928324307613407e-05, "loss": 1.1264, "step": 4317 }, { "epoch": 0.23607722535451905, "grad_norm": 13.126774787902832, "learning_rate": 8.927776519263092e-05, "loss": 1.0567, "step": 4318 }, { "epoch": 0.23613189817187766, "grad_norm": 2.9557013511657715, "learning_rate": 8.927228607760806e-05, "loss": 1.3337, "step": 4319 }, { "epoch": 0.2361865709892363, "grad_norm": 3.0505335330963135, "learning_rate": 8.926680573123729e-05, "loss": 1.1094, "step": 4320 }, { "epoch": 0.23624124380659492, "grad_norm": 3.180701971054077, "learning_rate": 8.926132415369045e-05, "loss": 1.0922, "step": 4321 }, { "epoch": 0.23629591662395352, "grad_norm": 2.825103759765625, "learning_rate": 8.925584134513938e-05, "loss": 1.0891, "step": 4322 }, { "epoch": 0.23635058944131215, "grad_norm": 2.3827264308929443, "learning_rate": 8.925035730575604e-05, "loss": 1.0878, "step": 4323 }, { "epoch": 0.23640526225867076, "grad_norm": 3.000988483428955, "learning_rate": 8.924487203571233e-05, "loss": 1.2728, "step": 4324 }, { "epoch": 0.2364599350760294, "grad_norm": 2.2232940196990967, "learning_rate": 8.923938553518027e-05, "loss": 1.0538, "step": 4325 }, { "epoch": 0.23651460789338802, "grad_norm": 4.178905487060547, "learning_rate": 8.923389780433186e-05, "loss": 1.1288, "step": 4326 }, { "epoch": 0.23656928071074662, "grad_norm": 2.1097607612609863, "learning_rate": 8.922840884333917e-05, "loss": 1.0821, "step": 4327 }, { "epoch": 0.23662395352810525, "grad_norm": 2.4159271717071533, "learning_rate": 8.92229186523743e-05, "loss": 1.0328, "step": 4328 }, { "epoch": 0.23667862634546386, "grad_norm": 2.4636874198913574, "learning_rate": 8.92174272316094e-05, "loss": 1.3352, "step": 4329 }, { "epoch": 0.23673329916282249, "grad_norm": 2.5839040279388428, "learning_rate": 8.921193458121664e-05, "loss": 1.1366, "step": 4330 }, { "epoch": 0.23678797198018112, "grad_norm": 2.7724761962890625, "learning_rate": 8.920644070136823e-05, "loss": 0.9481, "step": 4331 }, { "epoch": 0.23684264479753972, "grad_norm": 2.327785015106201, "learning_rate": 8.920094559223646e-05, "loss": 1.1508, "step": 4332 }, { "epoch": 0.23689731761489835, "grad_norm": 2.4596338272094727, "learning_rate": 8.919544925399357e-05, "loss": 1.275, "step": 4333 }, { "epoch": 0.23695199043225695, "grad_norm": 2.6074910163879395, "learning_rate": 8.918995168681195e-05, "loss": 1.2006, "step": 4334 }, { "epoch": 0.23700666324961558, "grad_norm": 2.97043776512146, "learning_rate": 8.918445289086392e-05, "loss": 1.0033, "step": 4335 }, { "epoch": 0.2370613360669742, "grad_norm": 2.2442798614501953, "learning_rate": 8.917895286632192e-05, "loss": 1.0232, "step": 4336 }, { "epoch": 0.23711600888433282, "grad_norm": 2.502570390701294, "learning_rate": 8.91734516133584e-05, "loss": 1.0489, "step": 4337 }, { "epoch": 0.23717068170169145, "grad_norm": 2.213341474533081, "learning_rate": 8.916794913214584e-05, "loss": 1.0158, "step": 4338 }, { "epoch": 0.23722535451905005, "grad_norm": 4.132869720458984, "learning_rate": 8.916244542285675e-05, "loss": 1.2112, "step": 4339 }, { "epoch": 0.23728002733640868, "grad_norm": 2.496229410171509, "learning_rate": 8.915694048566372e-05, "loss": 1.1087, "step": 4340 }, { "epoch": 0.2373347001537673, "grad_norm": 2.5243780612945557, "learning_rate": 8.915143432073934e-05, "loss": 1.2624, "step": 4341 }, { "epoch": 0.23738937297112592, "grad_norm": 2.7313740253448486, "learning_rate": 8.914592692825624e-05, "loss": 1.0482, "step": 4342 }, { "epoch": 0.23744404578848455, "grad_norm": 3.09403395652771, "learning_rate": 8.914041830838712e-05, "loss": 1.3071, "step": 4343 }, { "epoch": 0.23749871860584315, "grad_norm": 3.0702409744262695, "learning_rate": 8.913490846130468e-05, "loss": 1.251, "step": 4344 }, { "epoch": 0.23755339142320178, "grad_norm": 2.399954080581665, "learning_rate": 8.912939738718171e-05, "loss": 1.1748, "step": 4345 }, { "epoch": 0.23760806424056038, "grad_norm": 3.434053659439087, "learning_rate": 8.912388508619096e-05, "loss": 1.0619, "step": 4346 }, { "epoch": 0.23766273705791902, "grad_norm": 3.2228944301605225, "learning_rate": 8.911837155850527e-05, "loss": 1.3493, "step": 4347 }, { "epoch": 0.23771740987527765, "grad_norm": 2.2112650871276855, "learning_rate": 8.911285680429755e-05, "loss": 0.9966, "step": 4348 }, { "epoch": 0.23777208269263625, "grad_norm": 2.349454641342163, "learning_rate": 8.910734082374068e-05, "loss": 1.0732, "step": 4349 }, { "epoch": 0.23782675550999488, "grad_norm": 2.685075283050537, "learning_rate": 8.91018236170076e-05, "loss": 1.0415, "step": 4350 }, { "epoch": 0.23788142832735348, "grad_norm": 2.902071952819824, "learning_rate": 8.909630518427133e-05, "loss": 1.0196, "step": 4351 }, { "epoch": 0.23793610114471211, "grad_norm": 2.493654727935791, "learning_rate": 8.909078552570487e-05, "loss": 1.0835, "step": 4352 }, { "epoch": 0.23799077396207075, "grad_norm": 2.4592971801757812, "learning_rate": 8.90852646414813e-05, "loss": 1.2044, "step": 4353 }, { "epoch": 0.23804544677942935, "grad_norm": 3.1013896465301514, "learning_rate": 8.907974253177369e-05, "loss": 1.2068, "step": 4354 }, { "epoch": 0.23810011959678798, "grad_norm": 2.361605405807495, "learning_rate": 8.907421919675522e-05, "loss": 1.2207, "step": 4355 }, { "epoch": 0.23815479241414658, "grad_norm": 2.6298203468322754, "learning_rate": 8.906869463659906e-05, "loss": 0.9617, "step": 4356 }, { "epoch": 0.2382094652315052, "grad_norm": 1.772775411605835, "learning_rate": 8.906316885147842e-05, "loss": 0.9952, "step": 4357 }, { "epoch": 0.23826413804886384, "grad_norm": 2.391292095184326, "learning_rate": 8.905764184156655e-05, "loss": 1.0861, "step": 4358 }, { "epoch": 0.23831881086622245, "grad_norm": 4.964305400848389, "learning_rate": 8.905211360703676e-05, "loss": 1.2526, "step": 4359 }, { "epoch": 0.23837348368358108, "grad_norm": 2.561720371246338, "learning_rate": 8.904658414806236e-05, "loss": 1.0427, "step": 4360 }, { "epoch": 0.23842815650093968, "grad_norm": 3.805756092071533, "learning_rate": 8.904105346481675e-05, "loss": 1.134, "step": 4361 }, { "epoch": 0.2384828293182983, "grad_norm": 2.474339485168457, "learning_rate": 8.903552155747332e-05, "loss": 1.3702, "step": 4362 }, { "epoch": 0.23853750213565691, "grad_norm": 2.133983850479126, "learning_rate": 8.902998842620553e-05, "loss": 1.1142, "step": 4363 }, { "epoch": 0.23859217495301555, "grad_norm": 3.426671028137207, "learning_rate": 8.902445407118685e-05, "loss": 1.0366, "step": 4364 }, { "epoch": 0.23864684777037418, "grad_norm": 2.5233752727508545, "learning_rate": 8.901891849259083e-05, "loss": 1.139, "step": 4365 }, { "epoch": 0.23870152058773278, "grad_norm": 2.4591970443725586, "learning_rate": 8.901338169059101e-05, "loss": 1.202, "step": 4366 }, { "epoch": 0.2387561934050914, "grad_norm": 2.590068817138672, "learning_rate": 8.900784366536098e-05, "loss": 1.2667, "step": 4367 }, { "epoch": 0.23881086622245, "grad_norm": 1.8964637517929077, "learning_rate": 8.900230441707443e-05, "loss": 1.0672, "step": 4368 }, { "epoch": 0.23886553903980864, "grad_norm": 2.480724334716797, "learning_rate": 8.899676394590499e-05, "loss": 1.1417, "step": 4369 }, { "epoch": 0.23892021185716728, "grad_norm": 2.865682601928711, "learning_rate": 8.899122225202641e-05, "loss": 1.3032, "step": 4370 }, { "epoch": 0.23897488467452588, "grad_norm": 2.2783710956573486, "learning_rate": 8.898567933561242e-05, "loss": 1.0502, "step": 4371 }, { "epoch": 0.2390295574918845, "grad_norm": 2.7493526935577393, "learning_rate": 8.898013519683683e-05, "loss": 1.266, "step": 4372 }, { "epoch": 0.2390842303092431, "grad_norm": 2.0236756801605225, "learning_rate": 8.897458983587345e-05, "loss": 1.0743, "step": 4373 }, { "epoch": 0.23913890312660174, "grad_norm": 3.463625431060791, "learning_rate": 8.896904325289619e-05, "loss": 1.1886, "step": 4374 }, { "epoch": 0.23919357594396037, "grad_norm": 2.1364567279815674, "learning_rate": 8.896349544807892e-05, "loss": 1.2119, "step": 4375 }, { "epoch": 0.23924824876131898, "grad_norm": 2.063063144683838, "learning_rate": 8.895794642159559e-05, "loss": 1.014, "step": 4376 }, { "epoch": 0.2393029215786776, "grad_norm": 2.3687801361083984, "learning_rate": 8.895239617362021e-05, "loss": 1.1226, "step": 4377 }, { "epoch": 0.2393575943960362, "grad_norm": 2.4513437747955322, "learning_rate": 8.894684470432677e-05, "loss": 1.1168, "step": 4378 }, { "epoch": 0.23941226721339484, "grad_norm": 2.460286855697632, "learning_rate": 8.894129201388935e-05, "loss": 1.2134, "step": 4379 }, { "epoch": 0.23946694003075347, "grad_norm": 2.4946084022521973, "learning_rate": 8.893573810248206e-05, "loss": 1.2402, "step": 4380 }, { "epoch": 0.23952161284811208, "grad_norm": 2.9392828941345215, "learning_rate": 8.893018297027901e-05, "loss": 1.1634, "step": 4381 }, { "epoch": 0.2395762856654707, "grad_norm": 2.999772071838379, "learning_rate": 8.892462661745441e-05, "loss": 1.2802, "step": 4382 }, { "epoch": 0.2396309584828293, "grad_norm": 2.1513006687164307, "learning_rate": 8.891906904418246e-05, "loss": 0.8803, "step": 4383 }, { "epoch": 0.23968563130018794, "grad_norm": 2.366856336593628, "learning_rate": 8.891351025063739e-05, "loss": 1.1894, "step": 4384 }, { "epoch": 0.23974030411754657, "grad_norm": 2.2782304286956787, "learning_rate": 8.890795023699352e-05, "loss": 1.1609, "step": 4385 }, { "epoch": 0.23979497693490517, "grad_norm": 2.404846668243408, "learning_rate": 8.890238900342519e-05, "loss": 1.1373, "step": 4386 }, { "epoch": 0.2398496497522638, "grad_norm": 2.5481531620025635, "learning_rate": 8.889682655010672e-05, "loss": 1.1206, "step": 4387 }, { "epoch": 0.2399043225696224, "grad_norm": 2.495734214782715, "learning_rate": 8.889126287721254e-05, "loss": 1.1385, "step": 4388 }, { "epoch": 0.23995899538698104, "grad_norm": 2.740259885787964, "learning_rate": 8.888569798491712e-05, "loss": 1.3681, "step": 4389 }, { "epoch": 0.24001366820433964, "grad_norm": 2.3821604251861572, "learning_rate": 8.888013187339491e-05, "loss": 1.2365, "step": 4390 }, { "epoch": 0.24006834102169827, "grad_norm": 2.4102957248687744, "learning_rate": 8.887456454282044e-05, "loss": 1.1281, "step": 4391 }, { "epoch": 0.2401230138390569, "grad_norm": 2.185032367706299, "learning_rate": 8.886899599336828e-05, "loss": 1.0735, "step": 4392 }, { "epoch": 0.2401776866564155, "grad_norm": 2.518214702606201, "learning_rate": 8.8863426225213e-05, "loss": 1.037, "step": 4393 }, { "epoch": 0.24023235947377414, "grad_norm": 2.7707533836364746, "learning_rate": 8.885785523852927e-05, "loss": 1.1661, "step": 4394 }, { "epoch": 0.24028703229113274, "grad_norm": 2.928694725036621, "learning_rate": 8.885228303349174e-05, "loss": 1.3007, "step": 4395 }, { "epoch": 0.24034170510849137, "grad_norm": 3.033644676208496, "learning_rate": 8.88467096102751e-05, "loss": 1.0233, "step": 4396 }, { "epoch": 0.24039637792585, "grad_norm": 2.343471050262451, "learning_rate": 8.884113496905415e-05, "loss": 0.931, "step": 4397 }, { "epoch": 0.2404510507432086, "grad_norm": 1.8905994892120361, "learning_rate": 8.883555911000366e-05, "loss": 1.0921, "step": 4398 }, { "epoch": 0.24050572356056724, "grad_norm": 2.192504644393921, "learning_rate": 8.882998203329844e-05, "loss": 1.0869, "step": 4399 }, { "epoch": 0.24056039637792584, "grad_norm": 2.2899913787841797, "learning_rate": 8.882440373911336e-05, "loss": 0.9806, "step": 4400 }, { "epoch": 0.24061506919528447, "grad_norm": 2.1591835021972656, "learning_rate": 8.881882422762333e-05, "loss": 1.0396, "step": 4401 }, { "epoch": 0.2406697420126431, "grad_norm": 2.4500789642333984, "learning_rate": 8.88132434990033e-05, "loss": 1.0433, "step": 4402 }, { "epoch": 0.2407244148300017, "grad_norm": 2.624508857727051, "learning_rate": 8.880766155342823e-05, "loss": 1.1659, "step": 4403 }, { "epoch": 0.24077908764736033, "grad_norm": 2.9176814556121826, "learning_rate": 8.880207839107313e-05, "loss": 0.8745, "step": 4404 }, { "epoch": 0.24083376046471894, "grad_norm": 2.5973293781280518, "learning_rate": 8.879649401211309e-05, "loss": 1.2049, "step": 4405 }, { "epoch": 0.24088843328207757, "grad_norm": 3.17814040184021, "learning_rate": 8.879090841672317e-05, "loss": 1.1628, "step": 4406 }, { "epoch": 0.2409431060994362, "grad_norm": 3.45273494720459, "learning_rate": 8.87853216050785e-05, "loss": 1.1483, "step": 4407 }, { "epoch": 0.2409977789167948, "grad_norm": 2.0630745887756348, "learning_rate": 8.87797335773543e-05, "loss": 1.2461, "step": 4408 }, { "epoch": 0.24105245173415343, "grad_norm": 3.0685229301452637, "learning_rate": 8.87741443337257e-05, "loss": 1.3599, "step": 4409 }, { "epoch": 0.24110712455151204, "grad_norm": 2.521392583847046, "learning_rate": 8.876855387436802e-05, "loss": 1.118, "step": 4410 }, { "epoch": 0.24116179736887067, "grad_norm": 2.9504752159118652, "learning_rate": 8.87629621994565e-05, "loss": 1.1113, "step": 4411 }, { "epoch": 0.24121647018622927, "grad_norm": 2.477386951446533, "learning_rate": 8.875736930916648e-05, "loss": 1.1647, "step": 4412 }, { "epoch": 0.2412711430035879, "grad_norm": 2.1082956790924072, "learning_rate": 8.875177520367328e-05, "loss": 0.9034, "step": 4413 }, { "epoch": 0.24132581582094653, "grad_norm": 3.2379162311553955, "learning_rate": 8.874617988315235e-05, "loss": 1.218, "step": 4414 }, { "epoch": 0.24138048863830514, "grad_norm": 2.2667617797851562, "learning_rate": 8.874058334777912e-05, "loss": 1.201, "step": 4415 }, { "epoch": 0.24143516145566377, "grad_norm": 2.3678648471832275, "learning_rate": 8.873498559772904e-05, "loss": 1.1189, "step": 4416 }, { "epoch": 0.24148983427302237, "grad_norm": 2.383946657180786, "learning_rate": 8.872938663317762e-05, "loss": 1.015, "step": 4417 }, { "epoch": 0.241544507090381, "grad_norm": 2.859792470932007, "learning_rate": 8.872378645430046e-05, "loss": 1.0957, "step": 4418 }, { "epoch": 0.24159917990773963, "grad_norm": 2.1619439125061035, "learning_rate": 8.871818506127308e-05, "loss": 1.1411, "step": 4419 }, { "epoch": 0.24165385272509823, "grad_norm": 3.066096305847168, "learning_rate": 8.871258245427116e-05, "loss": 0.872, "step": 4420 }, { "epoch": 0.24170852554245686, "grad_norm": 2.505875825881958, "learning_rate": 8.870697863347032e-05, "loss": 1.222, "step": 4421 }, { "epoch": 0.24176319835981547, "grad_norm": 2.670769691467285, "learning_rate": 8.870137359904632e-05, "loss": 1.2066, "step": 4422 }, { "epoch": 0.2418178711771741, "grad_norm": 3.062786102294922, "learning_rate": 8.869576735117485e-05, "loss": 1.0583, "step": 4423 }, { "epoch": 0.24187254399453273, "grad_norm": 2.3296024799346924, "learning_rate": 8.869015989003171e-05, "loss": 1.124, "step": 4424 }, { "epoch": 0.24192721681189133, "grad_norm": 4.484513759613037, "learning_rate": 8.868455121579272e-05, "loss": 1.4281, "step": 4425 }, { "epoch": 0.24198188962924996, "grad_norm": 2.0197458267211914, "learning_rate": 8.867894132863373e-05, "loss": 0.9841, "step": 4426 }, { "epoch": 0.24203656244660857, "grad_norm": 2.5678844451904297, "learning_rate": 8.867333022873063e-05, "loss": 0.8885, "step": 4427 }, { "epoch": 0.2420912352639672, "grad_norm": 4.325313568115234, "learning_rate": 8.866771791625936e-05, "loss": 1.0974, "step": 4428 }, { "epoch": 0.24214590808132583, "grad_norm": 2.7511961460113525, "learning_rate": 8.866210439139586e-05, "loss": 1.0135, "step": 4429 }, { "epoch": 0.24220058089868443, "grad_norm": 2.6341476440429688, "learning_rate": 8.865648965431618e-05, "loss": 1.2564, "step": 4430 }, { "epoch": 0.24225525371604306, "grad_norm": 2.945953130722046, "learning_rate": 8.865087370519635e-05, "loss": 1.1579, "step": 4431 }, { "epoch": 0.24230992653340166, "grad_norm": 2.8494794368743896, "learning_rate": 8.864525654421243e-05, "loss": 1.1865, "step": 4432 }, { "epoch": 0.2423645993507603, "grad_norm": 2.575040578842163, "learning_rate": 8.863963817154057e-05, "loss": 1.1081, "step": 4433 }, { "epoch": 0.24241927216811893, "grad_norm": 2.6710171699523926, "learning_rate": 8.863401858735692e-05, "loss": 1.1945, "step": 4434 }, { "epoch": 0.24247394498547753, "grad_norm": 4.759150505065918, "learning_rate": 8.862839779183767e-05, "loss": 0.915, "step": 4435 }, { "epoch": 0.24252861780283616, "grad_norm": 3.9315340518951416, "learning_rate": 8.862277578515907e-05, "loss": 1.0645, "step": 4436 }, { "epoch": 0.24258329062019476, "grad_norm": 3.008735179901123, "learning_rate": 8.861715256749738e-05, "loss": 1.2881, "step": 4437 }, { "epoch": 0.2426379634375534, "grad_norm": 2.780085802078247, "learning_rate": 8.861152813902891e-05, "loss": 1.4467, "step": 4438 }, { "epoch": 0.242692636254912, "grad_norm": 2.814199209213257, "learning_rate": 8.860590249993001e-05, "loss": 1.0606, "step": 4439 }, { "epoch": 0.24274730907227063, "grad_norm": 2.150730848312378, "learning_rate": 8.860027565037709e-05, "loss": 1.0332, "step": 4440 }, { "epoch": 0.24280198188962926, "grad_norm": 3.7418692111968994, "learning_rate": 8.859464759054655e-05, "loss": 1.0858, "step": 4441 }, { "epoch": 0.24285665470698786, "grad_norm": 2.5535502433776855, "learning_rate": 8.858901832061484e-05, "loss": 1.2525, "step": 4442 }, { "epoch": 0.2429113275243465, "grad_norm": 2.255906820297241, "learning_rate": 8.858338784075851e-05, "loss": 1.0547, "step": 4443 }, { "epoch": 0.2429660003417051, "grad_norm": 2.712702751159668, "learning_rate": 8.857775615115404e-05, "loss": 1.1291, "step": 4444 }, { "epoch": 0.24302067315906373, "grad_norm": 3.0481574535369873, "learning_rate": 8.857212325197803e-05, "loss": 1.0294, "step": 4445 }, { "epoch": 0.24307534597642236, "grad_norm": 2.7939975261688232, "learning_rate": 8.856648914340713e-05, "loss": 1.1518, "step": 4446 }, { "epoch": 0.24313001879378096, "grad_norm": 2.5847580432891846, "learning_rate": 8.856085382561793e-05, "loss": 1.2634, "step": 4447 }, { "epoch": 0.2431846916111396, "grad_norm": 3.1999313831329346, "learning_rate": 8.855521729878717e-05, "loss": 1.0154, "step": 4448 }, { "epoch": 0.2432393644284982, "grad_norm": 2.2470250129699707, "learning_rate": 8.854957956309158e-05, "loss": 1.0127, "step": 4449 }, { "epoch": 0.24329403724585683, "grad_norm": 3.1023080348968506, "learning_rate": 8.854394061870788e-05, "loss": 1.2069, "step": 4450 }, { "epoch": 0.24334871006321546, "grad_norm": 3.036090850830078, "learning_rate": 8.85383004658129e-05, "loss": 1.4265, "step": 4451 }, { "epoch": 0.24340338288057406, "grad_norm": 2.724102258682251, "learning_rate": 8.853265910458349e-05, "loss": 1.0742, "step": 4452 }, { "epoch": 0.2434580556979327, "grad_norm": 2.7204267978668213, "learning_rate": 8.852701653519653e-05, "loss": 1.0523, "step": 4453 }, { "epoch": 0.2435127285152913, "grad_norm": 2.5668270587921143, "learning_rate": 8.852137275782892e-05, "loss": 1.1757, "step": 4454 }, { "epoch": 0.24356740133264992, "grad_norm": 2.999910354614258, "learning_rate": 8.851572777265762e-05, "loss": 1.2437, "step": 4455 }, { "epoch": 0.24362207415000856, "grad_norm": 2.4109339714050293, "learning_rate": 8.851008157985965e-05, "loss": 1.148, "step": 4456 }, { "epoch": 0.24367674696736716, "grad_norm": 3.090773344039917, "learning_rate": 8.850443417961201e-05, "loss": 1.429, "step": 4457 }, { "epoch": 0.2437314197847258, "grad_norm": 2.491152286529541, "learning_rate": 8.849878557209178e-05, "loss": 1.0076, "step": 4458 }, { "epoch": 0.2437860926020844, "grad_norm": 2.275891065597534, "learning_rate": 8.849313575747608e-05, "loss": 1.0375, "step": 4459 }, { "epoch": 0.24384076541944302, "grad_norm": 2.286142110824585, "learning_rate": 8.848748473594203e-05, "loss": 1.0219, "step": 4460 }, { "epoch": 0.24389543823680165, "grad_norm": 2.7410480976104736, "learning_rate": 8.848183250766683e-05, "loss": 1.2481, "step": 4461 }, { "epoch": 0.24395011105416026, "grad_norm": 2.006693124771118, "learning_rate": 8.847617907282769e-05, "loss": 1.0225, "step": 4462 }, { "epoch": 0.2440047838715189, "grad_norm": 2.3101861476898193, "learning_rate": 8.847052443160189e-05, "loss": 1.2296, "step": 4463 }, { "epoch": 0.2440594566888775, "grad_norm": 2.928706645965576, "learning_rate": 8.84648685841667e-05, "loss": 1.1911, "step": 4464 }, { "epoch": 0.24411412950623612, "grad_norm": 2.3982834815979004, "learning_rate": 8.845921153069945e-05, "loss": 1.039, "step": 4465 }, { "epoch": 0.24416880232359472, "grad_norm": 2.5688953399658203, "learning_rate": 8.845355327137754e-05, "loss": 1.1649, "step": 4466 }, { "epoch": 0.24422347514095336, "grad_norm": 3.4183149337768555, "learning_rate": 8.844789380637837e-05, "loss": 1.3494, "step": 4467 }, { "epoch": 0.244278147958312, "grad_norm": 2.738833427429199, "learning_rate": 8.844223313587938e-05, "loss": 1.3327, "step": 4468 }, { "epoch": 0.2443328207756706, "grad_norm": 3.1151320934295654, "learning_rate": 8.843657126005806e-05, "loss": 0.9479, "step": 4469 }, { "epoch": 0.24438749359302922, "grad_norm": 1.9985381364822388, "learning_rate": 8.843090817909194e-05, "loss": 1.1372, "step": 4470 }, { "epoch": 0.24444216641038782, "grad_norm": 2.914905071258545, "learning_rate": 8.842524389315857e-05, "loss": 1.1264, "step": 4471 }, { "epoch": 0.24449683922774645, "grad_norm": 2.6742589473724365, "learning_rate": 8.841957840243556e-05, "loss": 1.1825, "step": 4472 }, { "epoch": 0.24455151204510509, "grad_norm": 3.2105953693389893, "learning_rate": 8.841391170710052e-05, "loss": 1.1944, "step": 4473 }, { "epoch": 0.2446061848624637, "grad_norm": 2.067922353744507, "learning_rate": 8.840824380733115e-05, "loss": 0.9814, "step": 4474 }, { "epoch": 0.24466085767982232, "grad_norm": 2.111748695373535, "learning_rate": 8.840257470330515e-05, "loss": 1.1142, "step": 4475 }, { "epoch": 0.24471553049718092, "grad_norm": 2.4615113735198975, "learning_rate": 8.83969043952003e-05, "loss": 0.9183, "step": 4476 }, { "epoch": 0.24477020331453955, "grad_norm": 2.7303810119628906, "learning_rate": 8.839123288319432e-05, "loss": 1.0537, "step": 4477 }, { "epoch": 0.24482487613189818, "grad_norm": 2.389291286468506, "learning_rate": 8.838556016746511e-05, "loss": 1.0229, "step": 4478 }, { "epoch": 0.2448795489492568, "grad_norm": 2.3359878063201904, "learning_rate": 8.837988624819049e-05, "loss": 1.0439, "step": 4479 }, { "epoch": 0.24493422176661542, "grad_norm": 3.5443859100341797, "learning_rate": 8.837421112554838e-05, "loss": 0.9505, "step": 4480 }, { "epoch": 0.24498889458397402, "grad_norm": 3.0523555278778076, "learning_rate": 8.83685347997167e-05, "loss": 1.3658, "step": 4481 }, { "epoch": 0.24504356740133265, "grad_norm": 1.9326629638671875, "learning_rate": 8.836285727087343e-05, "loss": 1.0711, "step": 4482 }, { "epoch": 0.24509824021869128, "grad_norm": 3.0090646743774414, "learning_rate": 8.83571785391966e-05, "loss": 1.1473, "step": 4483 }, { "epoch": 0.24515291303604989, "grad_norm": 3.743873357772827, "learning_rate": 8.835149860486426e-05, "loss": 1.1975, "step": 4484 }, { "epoch": 0.24520758585340852, "grad_norm": 2.3572499752044678, "learning_rate": 8.834581746805448e-05, "loss": 1.2546, "step": 4485 }, { "epoch": 0.24526225867076712, "grad_norm": 2.2676002979278564, "learning_rate": 8.834013512894538e-05, "loss": 1.0409, "step": 4486 }, { "epoch": 0.24531693148812575, "grad_norm": 2.172577381134033, "learning_rate": 8.833445158771518e-05, "loss": 1.1091, "step": 4487 }, { "epoch": 0.24537160430548435, "grad_norm": 2.880988836288452, "learning_rate": 8.832876684454202e-05, "loss": 1.2558, "step": 4488 }, { "epoch": 0.24542627712284298, "grad_norm": 3.1807262897491455, "learning_rate": 8.832308089960417e-05, "loss": 1.1667, "step": 4489 }, { "epoch": 0.24548094994020161, "grad_norm": 3.3351056575775146, "learning_rate": 8.831739375307991e-05, "loss": 1.3891, "step": 4490 }, { "epoch": 0.24553562275756022, "grad_norm": 2.4615678787231445, "learning_rate": 8.831170540514753e-05, "loss": 1.2254, "step": 4491 }, { "epoch": 0.24559029557491885, "grad_norm": 2.5862836837768555, "learning_rate": 8.83060158559854e-05, "loss": 1.1048, "step": 4492 }, { "epoch": 0.24564496839227745, "grad_norm": 2.059732675552368, "learning_rate": 8.830032510577194e-05, "loss": 1.094, "step": 4493 }, { "epoch": 0.24569964120963608, "grad_norm": 2.070364236831665, "learning_rate": 8.829463315468553e-05, "loss": 0.9366, "step": 4494 }, { "epoch": 0.2457543140269947, "grad_norm": 2.0613455772399902, "learning_rate": 8.828894000290468e-05, "loss": 1.0097, "step": 4495 }, { "epoch": 0.24580898684435332, "grad_norm": 3.2595388889312744, "learning_rate": 8.828324565060786e-05, "loss": 0.9986, "step": 4496 }, { "epoch": 0.24586365966171195, "grad_norm": 3.061671257019043, "learning_rate": 8.827755009797361e-05, "loss": 1.285, "step": 4497 }, { "epoch": 0.24591833247907055, "grad_norm": 3.0086309909820557, "learning_rate": 8.827185334518051e-05, "loss": 1.2402, "step": 4498 }, { "epoch": 0.24597300529642918, "grad_norm": 3.6849000453948975, "learning_rate": 8.826615539240722e-05, "loss": 1.1977, "step": 4499 }, { "epoch": 0.2460276781137878, "grad_norm": 2.6346547603607178, "learning_rate": 8.826045623983233e-05, "loss": 1.1739, "step": 4500 }, { "epoch": 0.24608235093114642, "grad_norm": 2.2024106979370117, "learning_rate": 8.825475588763459e-05, "loss": 1.1153, "step": 4501 }, { "epoch": 0.24613702374850505, "grad_norm": 2.4523978233337402, "learning_rate": 8.824905433599268e-05, "loss": 1.1345, "step": 4502 }, { "epoch": 0.24619169656586365, "grad_norm": 4.506684303283691, "learning_rate": 8.824335158508542e-05, "loss": 0.9216, "step": 4503 }, { "epoch": 0.24624636938322228, "grad_norm": 3.101349115371704, "learning_rate": 8.823764763509155e-05, "loss": 1.2062, "step": 4504 }, { "epoch": 0.2463010422005809, "grad_norm": 2.2113871574401855, "learning_rate": 8.823194248618998e-05, "loss": 1.0175, "step": 4505 }, { "epoch": 0.24635571501793951, "grad_norm": 2.3325815200805664, "learning_rate": 8.822623613855953e-05, "loss": 1.0376, "step": 4506 }, { "epoch": 0.24641038783529814, "grad_norm": 2.0296595096588135, "learning_rate": 8.822052859237917e-05, "loss": 0.9668, "step": 4507 }, { "epoch": 0.24646506065265675, "grad_norm": 2.987159013748169, "learning_rate": 8.821481984782783e-05, "loss": 1.114, "step": 4508 }, { "epoch": 0.24651973347001538, "grad_norm": 3.4815266132354736, "learning_rate": 8.820910990508447e-05, "loss": 1.2585, "step": 4509 }, { "epoch": 0.246574406287374, "grad_norm": 2.8727457523345947, "learning_rate": 8.820339876432818e-05, "loss": 1.1768, "step": 4510 }, { "epoch": 0.2466290791047326, "grad_norm": 3.038494348526001, "learning_rate": 8.8197686425738e-05, "loss": 0.8524, "step": 4511 }, { "epoch": 0.24668375192209124, "grad_norm": 2.0757102966308594, "learning_rate": 8.819197288949303e-05, "loss": 0.8165, "step": 4512 }, { "epoch": 0.24673842473944985, "grad_norm": 2.3602850437164307, "learning_rate": 8.818625815577242e-05, "loss": 1.1141, "step": 4513 }, { "epoch": 0.24679309755680848, "grad_norm": 3.069427728652954, "learning_rate": 8.818054222475533e-05, "loss": 1.327, "step": 4514 }, { "epoch": 0.24684777037416708, "grad_norm": 2.273632049560547, "learning_rate": 8.817482509662103e-05, "loss": 1.0357, "step": 4515 }, { "epoch": 0.2469024431915257, "grad_norm": 2.063781976699829, "learning_rate": 8.816910677154873e-05, "loss": 1.0388, "step": 4516 }, { "epoch": 0.24695711600888434, "grad_norm": 2.0145504474639893, "learning_rate": 8.816338724971773e-05, "loss": 1.1059, "step": 4517 }, { "epoch": 0.24701178882624295, "grad_norm": 2.745779514312744, "learning_rate": 8.815766653130736e-05, "loss": 1.2012, "step": 4518 }, { "epoch": 0.24706646164360158, "grad_norm": 3.101057291030884, "learning_rate": 8.815194461649702e-05, "loss": 1.0039, "step": 4519 }, { "epoch": 0.24712113446096018, "grad_norm": 2.096745729446411, "learning_rate": 8.814622150546607e-05, "loss": 1.0775, "step": 4520 }, { "epoch": 0.2471758072783188, "grad_norm": 2.0781397819519043, "learning_rate": 8.8140497198394e-05, "loss": 0.9649, "step": 4521 }, { "epoch": 0.24723048009567744, "grad_norm": 4.212640762329102, "learning_rate": 8.813477169546023e-05, "loss": 0.8582, "step": 4522 }, { "epoch": 0.24728515291303604, "grad_norm": 2.762282371520996, "learning_rate": 8.812904499684433e-05, "loss": 1.1482, "step": 4523 }, { "epoch": 0.24733982573039467, "grad_norm": 2.707958221435547, "learning_rate": 8.812331710272583e-05, "loss": 1.1276, "step": 4524 }, { "epoch": 0.24739449854775328, "grad_norm": 2.5876052379608154, "learning_rate": 8.811758801328433e-05, "loss": 0.9768, "step": 4525 }, { "epoch": 0.2474491713651119, "grad_norm": 2.524644136428833, "learning_rate": 8.811185772869945e-05, "loss": 1.2733, "step": 4526 }, { "epoch": 0.24750384418247054, "grad_norm": 2.2885797023773193, "learning_rate": 8.810612624915089e-05, "loss": 0.9416, "step": 4527 }, { "epoch": 0.24755851699982914, "grad_norm": 2.300630569458008, "learning_rate": 8.810039357481833e-05, "loss": 1.1005, "step": 4528 }, { "epoch": 0.24761318981718777, "grad_norm": 2.519078493118286, "learning_rate": 8.809465970588152e-05, "loss": 1.1546, "step": 4529 }, { "epoch": 0.24766786263454638, "grad_norm": 2.4449355602264404, "learning_rate": 8.808892464252023e-05, "loss": 1.2003, "step": 4530 }, { "epoch": 0.247722535451905, "grad_norm": 2.715668201446533, "learning_rate": 8.808318838491428e-05, "loss": 1.2875, "step": 4531 }, { "epoch": 0.24777720826926364, "grad_norm": 3.0384044647216797, "learning_rate": 8.807745093324355e-05, "loss": 1.2264, "step": 4532 }, { "epoch": 0.24783188108662224, "grad_norm": 3.4178998470306396, "learning_rate": 8.807171228768789e-05, "loss": 1.0078, "step": 4533 }, { "epoch": 0.24788655390398087, "grad_norm": 2.26186203956604, "learning_rate": 8.806597244842728e-05, "loss": 1.053, "step": 4534 }, { "epoch": 0.24794122672133947, "grad_norm": 2.088878631591797, "learning_rate": 8.806023141564165e-05, "loss": 1.0118, "step": 4535 }, { "epoch": 0.2479958995386981, "grad_norm": 2.1154842376708984, "learning_rate": 8.805448918951101e-05, "loss": 1.0772, "step": 4536 }, { "epoch": 0.24805057235605674, "grad_norm": 3.5485594272613525, "learning_rate": 8.804874577021542e-05, "loss": 1.2437, "step": 4537 }, { "epoch": 0.24810524517341534, "grad_norm": 3.2297861576080322, "learning_rate": 8.804300115793494e-05, "loss": 1.1248, "step": 4538 }, { "epoch": 0.24815991799077397, "grad_norm": 3.1695375442504883, "learning_rate": 8.80372553528497e-05, "loss": 1.4744, "step": 4539 }, { "epoch": 0.24821459080813257, "grad_norm": 2.608772039413452, "learning_rate": 8.803150835513986e-05, "loss": 0.9612, "step": 4540 }, { "epoch": 0.2482692636254912, "grad_norm": 3.147369146347046, "learning_rate": 8.802576016498558e-05, "loss": 1.0845, "step": 4541 }, { "epoch": 0.2483239364428498, "grad_norm": 2.321181058883667, "learning_rate": 8.802001078256714e-05, "loss": 1.1083, "step": 4542 }, { "epoch": 0.24837860926020844, "grad_norm": 2.799440860748291, "learning_rate": 8.801426020806476e-05, "loss": 1.2414, "step": 4543 }, { "epoch": 0.24843328207756707, "grad_norm": 3.0284976959228516, "learning_rate": 8.800850844165877e-05, "loss": 1.1876, "step": 4544 }, { "epoch": 0.24848795489492567, "grad_norm": 2.6749191284179688, "learning_rate": 8.800275548352951e-05, "loss": 1.1991, "step": 4545 }, { "epoch": 0.2485426277122843, "grad_norm": 3.7760941982269287, "learning_rate": 8.799700133385736e-05, "loss": 1.1237, "step": 4546 }, { "epoch": 0.2485973005296429, "grad_norm": 4.240449905395508, "learning_rate": 8.79912459928227e-05, "loss": 1.1197, "step": 4547 }, { "epoch": 0.24865197334700154, "grad_norm": 2.480266809463501, "learning_rate": 8.798548946060603e-05, "loss": 1.3189, "step": 4548 }, { "epoch": 0.24870664616436017, "grad_norm": 3.43937349319458, "learning_rate": 8.797973173738782e-05, "loss": 1.2226, "step": 4549 }, { "epoch": 0.24876131898171877, "grad_norm": 2.8054609298706055, "learning_rate": 8.797397282334863e-05, "loss": 1.2486, "step": 4550 }, { "epoch": 0.2488159917990774, "grad_norm": 2.5491020679473877, "learning_rate": 8.796821271866897e-05, "loss": 1.1146, "step": 4551 }, { "epoch": 0.248870664616436, "grad_norm": 2.510408878326416, "learning_rate": 8.796245142352948e-05, "loss": 1.3088, "step": 4552 }, { "epoch": 0.24892533743379464, "grad_norm": 3.2641549110412598, "learning_rate": 8.79566889381108e-05, "loss": 1.0784, "step": 4553 }, { "epoch": 0.24898001025115327, "grad_norm": 2.195216417312622, "learning_rate": 8.795092526259359e-05, "loss": 1.0762, "step": 4554 }, { "epoch": 0.24903468306851187, "grad_norm": 3.477185010910034, "learning_rate": 8.794516039715857e-05, "loss": 1.2009, "step": 4555 }, { "epoch": 0.2490893558858705, "grad_norm": 2.8580636978149414, "learning_rate": 8.79393943419865e-05, "loss": 1.2284, "step": 4556 }, { "epoch": 0.2491440287032291, "grad_norm": 2.0177054405212402, "learning_rate": 8.793362709725818e-05, "loss": 0.9176, "step": 4557 }, { "epoch": 0.24919870152058773, "grad_norm": 2.511371374130249, "learning_rate": 8.79278586631544e-05, "loss": 1.1011, "step": 4558 }, { "epoch": 0.24925337433794637, "grad_norm": 3.4674172401428223, "learning_rate": 8.792208903985608e-05, "loss": 1.248, "step": 4559 }, { "epoch": 0.24930804715530497, "grad_norm": 2.181452989578247, "learning_rate": 8.791631822754406e-05, "loss": 0.9646, "step": 4560 }, { "epoch": 0.2493627199726636, "grad_norm": 4.016112804412842, "learning_rate": 8.791054622639932e-05, "loss": 1.2536, "step": 4561 }, { "epoch": 0.2494173927900222, "grad_norm": 2.664233922958374, "learning_rate": 8.790477303660283e-05, "loss": 1.1335, "step": 4562 }, { "epoch": 0.24947206560738083, "grad_norm": 2.822629928588867, "learning_rate": 8.789899865833558e-05, "loss": 1.228, "step": 4563 }, { "epoch": 0.24952673842473944, "grad_norm": 3.354461669921875, "learning_rate": 8.789322309177866e-05, "loss": 1.1148, "step": 4564 }, { "epoch": 0.24958141124209807, "grad_norm": 1.9468382596969604, "learning_rate": 8.788744633711312e-05, "loss": 0.9867, "step": 4565 }, { "epoch": 0.2496360840594567, "grad_norm": 3.188194513320923, "learning_rate": 8.78816683945201e-05, "loss": 1.2201, "step": 4566 }, { "epoch": 0.2496907568768153, "grad_norm": 2.7036685943603516, "learning_rate": 8.787588926418076e-05, "loss": 1.0483, "step": 4567 }, { "epoch": 0.24974542969417393, "grad_norm": 1.9802840948104858, "learning_rate": 8.787010894627631e-05, "loss": 0.8076, "step": 4568 }, { "epoch": 0.24980010251153253, "grad_norm": 3.117859363555908, "learning_rate": 8.786432744098798e-05, "loss": 1.1335, "step": 4569 }, { "epoch": 0.24985477532889117, "grad_norm": 2.2257299423217773, "learning_rate": 8.785854474849704e-05, "loss": 0.8835, "step": 4570 }, { "epoch": 0.2499094481462498, "grad_norm": 2.7616758346557617, "learning_rate": 8.785276086898481e-05, "loss": 1.2157, "step": 4571 }, { "epoch": 0.2499641209636084, "grad_norm": 2.523160934448242, "learning_rate": 8.784697580263262e-05, "loss": 0.9877, "step": 4572 }, { "epoch": 0.25001879378096703, "grad_norm": 2.376749038696289, "learning_rate": 8.784118954962188e-05, "loss": 1.0747, "step": 4573 }, { "epoch": 0.25007346659832563, "grad_norm": 3.403372287750244, "learning_rate": 8.7835402110134e-05, "loss": 1.1993, "step": 4574 }, { "epoch": 0.2501281394156843, "grad_norm": 2.685655117034912, "learning_rate": 8.782961348435044e-05, "loss": 1.0901, "step": 4575 }, { "epoch": 0.2501828122330429, "grad_norm": 2.1776766777038574, "learning_rate": 8.78238236724527e-05, "loss": 1.0923, "step": 4576 }, { "epoch": 0.2502374850504015, "grad_norm": 2.936042070388794, "learning_rate": 8.781803267462229e-05, "loss": 1.072, "step": 4577 }, { "epoch": 0.2502921578677601, "grad_norm": 1.9095638990402222, "learning_rate": 8.781224049104084e-05, "loss": 1.0463, "step": 4578 }, { "epoch": 0.25034683068511876, "grad_norm": 2.0968286991119385, "learning_rate": 8.78064471218899e-05, "loss": 1.1034, "step": 4579 }, { "epoch": 0.25040150350247736, "grad_norm": 2.5521316528320312, "learning_rate": 8.780065256735116e-05, "loss": 1.2113, "step": 4580 }, { "epoch": 0.25045617631983597, "grad_norm": 2.2292516231536865, "learning_rate": 8.779485682760627e-05, "loss": 1.2385, "step": 4581 }, { "epoch": 0.2505108491371946, "grad_norm": 2.269784927368164, "learning_rate": 8.778905990283695e-05, "loss": 0.7845, "step": 4582 }, { "epoch": 0.2505655219545532, "grad_norm": 2.148944139480591, "learning_rate": 8.778326179322498e-05, "loss": 1.0034, "step": 4583 }, { "epoch": 0.25062019477191183, "grad_norm": 2.2077383995056152, "learning_rate": 8.777746249895215e-05, "loss": 1.0844, "step": 4584 }, { "epoch": 0.25067486758927043, "grad_norm": 4.396316051483154, "learning_rate": 8.777166202020028e-05, "loss": 1.2825, "step": 4585 }, { "epoch": 0.2507295404066291, "grad_norm": 2.4410274028778076, "learning_rate": 8.776586035715127e-05, "loss": 1.3252, "step": 4586 }, { "epoch": 0.2507842132239877, "grad_norm": 2.75748348236084, "learning_rate": 8.776005750998697e-05, "loss": 1.1294, "step": 4587 }, { "epoch": 0.2508388860413463, "grad_norm": 2.1775519847869873, "learning_rate": 8.775425347888937e-05, "loss": 0.9405, "step": 4588 }, { "epoch": 0.25089355885870496, "grad_norm": 2.15152907371521, "learning_rate": 8.774844826404044e-05, "loss": 1.0128, "step": 4589 }, { "epoch": 0.25094823167606356, "grad_norm": 2.083224058151245, "learning_rate": 8.774264186562218e-05, "loss": 1.0548, "step": 4590 }, { "epoch": 0.25100290449342216, "grad_norm": 2.661198139190674, "learning_rate": 8.773683428381667e-05, "loss": 1.3225, "step": 4591 }, { "epoch": 0.2510575773107808, "grad_norm": 2.2783195972442627, "learning_rate": 8.773102551880597e-05, "loss": 1.0912, "step": 4592 }, { "epoch": 0.2511122501281394, "grad_norm": 2.391599416732788, "learning_rate": 8.772521557077224e-05, "loss": 1.3074, "step": 4593 }, { "epoch": 0.25116692294549803, "grad_norm": 4.32239294052124, "learning_rate": 8.771940443989763e-05, "loss": 1.0829, "step": 4594 }, { "epoch": 0.25122159576285663, "grad_norm": 2.215606212615967, "learning_rate": 8.771359212636436e-05, "loss": 0.8971, "step": 4595 }, { "epoch": 0.2512762685802153, "grad_norm": 2.8214478492736816, "learning_rate": 8.770777863035464e-05, "loss": 1.0252, "step": 4596 }, { "epoch": 0.2513309413975739, "grad_norm": 2.6269819736480713, "learning_rate": 8.770196395205077e-05, "loss": 1.1971, "step": 4597 }, { "epoch": 0.2513856142149325, "grad_norm": 2.6685538291931152, "learning_rate": 8.769614809163505e-05, "loss": 1.2658, "step": 4598 }, { "epoch": 0.25144028703229115, "grad_norm": 2.8146073818206787, "learning_rate": 8.769033104928984e-05, "loss": 1.2868, "step": 4599 }, { "epoch": 0.25149495984964976, "grad_norm": 3.08992862701416, "learning_rate": 8.768451282519753e-05, "loss": 1.3193, "step": 4600 }, { "epoch": 0.25154963266700836, "grad_norm": 2.549863576889038, "learning_rate": 8.767869341954053e-05, "loss": 1.2849, "step": 4601 }, { "epoch": 0.251604305484367, "grad_norm": 2.9483983516693115, "learning_rate": 8.767287283250134e-05, "loss": 1.0685, "step": 4602 }, { "epoch": 0.2516589783017256, "grad_norm": 2.818784475326538, "learning_rate": 8.766705106426242e-05, "loss": 1.0134, "step": 4603 }, { "epoch": 0.2517136511190842, "grad_norm": 2.1054229736328125, "learning_rate": 8.766122811500632e-05, "loss": 1.1263, "step": 4604 }, { "epoch": 0.25176832393644283, "grad_norm": 3.4669177532196045, "learning_rate": 8.76554039849156e-05, "loss": 1.0075, "step": 4605 }, { "epoch": 0.2518229967538015, "grad_norm": 3.104369640350342, "learning_rate": 8.76495786741729e-05, "loss": 0.8612, "step": 4606 }, { "epoch": 0.2518776695711601, "grad_norm": 3.5590503215789795, "learning_rate": 8.764375218296084e-05, "loss": 0.9758, "step": 4607 }, { "epoch": 0.2519323423885187, "grad_norm": 2.5256898403167725, "learning_rate": 8.763792451146214e-05, "loss": 1.0815, "step": 4608 }, { "epoch": 0.25198701520587735, "grad_norm": 3.427295207977295, "learning_rate": 8.763209565985947e-05, "loss": 0.9277, "step": 4609 }, { "epoch": 0.25204168802323595, "grad_norm": 2.4689395427703857, "learning_rate": 8.762626562833563e-05, "loss": 1.0846, "step": 4610 }, { "epoch": 0.25209636084059456, "grad_norm": 2.458068609237671, "learning_rate": 8.762043441707339e-05, "loss": 1.1448, "step": 4611 }, { "epoch": 0.25215103365795316, "grad_norm": 2.8189899921417236, "learning_rate": 8.76146020262556e-05, "loss": 1.0292, "step": 4612 }, { "epoch": 0.2522057064753118, "grad_norm": 2.2957236766815186, "learning_rate": 8.760876845606514e-05, "loss": 1.1159, "step": 4613 }, { "epoch": 0.2522603792926704, "grad_norm": 4.307215213775635, "learning_rate": 8.760293370668486e-05, "loss": 1.2113, "step": 4614 }, { "epoch": 0.252315052110029, "grad_norm": 2.8219940662384033, "learning_rate": 8.759709777829778e-05, "loss": 1.1215, "step": 4615 }, { "epoch": 0.2523697249273877, "grad_norm": 2.426138401031494, "learning_rate": 8.759126067108683e-05, "loss": 1.0982, "step": 4616 }, { "epoch": 0.2524243977447463, "grad_norm": 2.4478657245635986, "learning_rate": 8.758542238523503e-05, "loss": 1.1251, "step": 4617 }, { "epoch": 0.2524790705621049, "grad_norm": 2.528169870376587, "learning_rate": 8.757958292092547e-05, "loss": 0.9734, "step": 4618 }, { "epoch": 0.25253374337946355, "grad_norm": 2.73205828666687, "learning_rate": 8.75737422783412e-05, "loss": 1.0348, "step": 4619 }, { "epoch": 0.25258841619682215, "grad_norm": 1.9292371273040771, "learning_rate": 8.756790045766538e-05, "loss": 0.933, "step": 4620 }, { "epoch": 0.25264308901418076, "grad_norm": 3.756704568862915, "learning_rate": 8.756205745908115e-05, "loss": 1.2708, "step": 4621 }, { "epoch": 0.25269776183153936, "grad_norm": 2.5524818897247314, "learning_rate": 8.75562132827717e-05, "loss": 0.9641, "step": 4622 }, { "epoch": 0.252752434648898, "grad_norm": 3.2040531635284424, "learning_rate": 8.755036792892034e-05, "loss": 1.1711, "step": 4623 }, { "epoch": 0.2528071074662566, "grad_norm": 2.6696884632110596, "learning_rate": 8.754452139771026e-05, "loss": 1.1844, "step": 4624 }, { "epoch": 0.2528617802836152, "grad_norm": 3.460848808288574, "learning_rate": 8.75386736893248e-05, "loss": 1.2154, "step": 4625 }, { "epoch": 0.2529164531009739, "grad_norm": 2.947659492492676, "learning_rate": 8.753282480394734e-05, "loss": 0.9798, "step": 4626 }, { "epoch": 0.2529711259183325, "grad_norm": 2.575939655303955, "learning_rate": 8.752697474176125e-05, "loss": 1.1754, "step": 4627 }, { "epoch": 0.2530257987356911, "grad_norm": 3.4654479026794434, "learning_rate": 8.752112350294994e-05, "loss": 1.2114, "step": 4628 }, { "epoch": 0.2530804715530497, "grad_norm": 2.6841859817504883, "learning_rate": 8.751527108769688e-05, "loss": 1.0829, "step": 4629 }, { "epoch": 0.25313514437040835, "grad_norm": 1.955093264579773, "learning_rate": 8.750941749618558e-05, "loss": 0.9979, "step": 4630 }, { "epoch": 0.25318981718776695, "grad_norm": 2.962542772293091, "learning_rate": 8.750356272859954e-05, "loss": 1.0437, "step": 4631 }, { "epoch": 0.25324449000512556, "grad_norm": 3.444182872772217, "learning_rate": 8.749770678512236e-05, "loss": 1.2848, "step": 4632 }, { "epoch": 0.2532991628224842, "grad_norm": 2.4558138847351074, "learning_rate": 8.749184966593766e-05, "loss": 1.1091, "step": 4633 }, { "epoch": 0.2533538356398428, "grad_norm": 2.3408117294311523, "learning_rate": 8.748599137122904e-05, "loss": 1.2751, "step": 4634 }, { "epoch": 0.2534085084572014, "grad_norm": 2.603543996810913, "learning_rate": 8.748013190118021e-05, "loss": 1.219, "step": 4635 }, { "epoch": 0.2534631812745601, "grad_norm": 3.03895902633667, "learning_rate": 8.74742712559749e-05, "loss": 1.0687, "step": 4636 }, { "epoch": 0.2535178540919187, "grad_norm": 2.535778522491455, "learning_rate": 8.746840943579684e-05, "loss": 1.2649, "step": 4637 }, { "epoch": 0.2535725269092773, "grad_norm": 2.029210090637207, "learning_rate": 8.746254644082985e-05, "loss": 1.1301, "step": 4638 }, { "epoch": 0.2536271997266359, "grad_norm": 2.2949657440185547, "learning_rate": 8.745668227125772e-05, "loss": 1.0939, "step": 4639 }, { "epoch": 0.25368187254399455, "grad_norm": 2.455850124359131, "learning_rate": 8.745081692726435e-05, "loss": 1.1942, "step": 4640 }, { "epoch": 0.25373654536135315, "grad_norm": 2.449883460998535, "learning_rate": 8.744495040903362e-05, "loss": 1.2103, "step": 4641 }, { "epoch": 0.25379121817871175, "grad_norm": 2.149604082107544, "learning_rate": 8.74390827167495e-05, "loss": 1.0104, "step": 4642 }, { "epoch": 0.2538458909960704, "grad_norm": 2.0451765060424805, "learning_rate": 8.743321385059592e-05, "loss": 1.0297, "step": 4643 }, { "epoch": 0.253900563813429, "grad_norm": 2.3407845497131348, "learning_rate": 8.742734381075695e-05, "loss": 1.2261, "step": 4644 }, { "epoch": 0.2539552366307876, "grad_norm": 2.4586408138275146, "learning_rate": 8.742147259741659e-05, "loss": 1.1902, "step": 4645 }, { "epoch": 0.2540099094481463, "grad_norm": 3.1016266345977783, "learning_rate": 8.741560021075895e-05, "loss": 1.1336, "step": 4646 }, { "epoch": 0.2540645822655049, "grad_norm": 2.837789535522461, "learning_rate": 8.740972665096815e-05, "loss": 1.38, "step": 4647 }, { "epoch": 0.2541192550828635, "grad_norm": 3.0713605880737305, "learning_rate": 8.740385191822835e-05, "loss": 1.2554, "step": 4648 }, { "epoch": 0.2541739279002221, "grad_norm": 2.688307046890259, "learning_rate": 8.739797601272374e-05, "loss": 1.1715, "step": 4649 }, { "epoch": 0.25422860071758074, "grad_norm": 2.9235849380493164, "learning_rate": 8.739209893463858e-05, "loss": 0.984, "step": 4650 }, { "epoch": 0.25428327353493935, "grad_norm": 1.9622910022735596, "learning_rate": 8.73862206841571e-05, "loss": 1.0309, "step": 4651 }, { "epoch": 0.25433794635229795, "grad_norm": 3.0972554683685303, "learning_rate": 8.738034126146363e-05, "loss": 1.0641, "step": 4652 }, { "epoch": 0.2543926191696566, "grad_norm": 2.4951488971710205, "learning_rate": 8.737446066674253e-05, "loss": 1.1298, "step": 4653 }, { "epoch": 0.2544472919870152, "grad_norm": 2.5781610012054443, "learning_rate": 8.736857890017815e-05, "loss": 1.1306, "step": 4654 }, { "epoch": 0.2545019648043738, "grad_norm": 2.2634387016296387, "learning_rate": 8.736269596195493e-05, "loss": 1.1971, "step": 4655 }, { "epoch": 0.2545566376217324, "grad_norm": 2.952100992202759, "learning_rate": 8.735681185225732e-05, "loss": 1.1935, "step": 4656 }, { "epoch": 0.2546113104390911, "grad_norm": 2.510779619216919, "learning_rate": 8.735092657126979e-05, "loss": 1.1234, "step": 4657 }, { "epoch": 0.2546659832564497, "grad_norm": 2.414435863494873, "learning_rate": 8.73450401191769e-05, "loss": 1.102, "step": 4658 }, { "epoch": 0.2547206560738083, "grad_norm": 2.5265796184539795, "learning_rate": 8.73391524961632e-05, "loss": 1.1811, "step": 4659 }, { "epoch": 0.25477532889116694, "grad_norm": 2.4909207820892334, "learning_rate": 8.733326370241328e-05, "loss": 1.0382, "step": 4660 }, { "epoch": 0.25483000170852554, "grad_norm": 3.0015087127685547, "learning_rate": 8.73273737381118e-05, "loss": 1.3576, "step": 4661 }, { "epoch": 0.25488467452588415, "grad_norm": 3.04079270362854, "learning_rate": 8.73214826034434e-05, "loss": 1.17, "step": 4662 }, { "epoch": 0.2549393473432428, "grad_norm": 2.5976502895355225, "learning_rate": 8.731559029859284e-05, "loss": 1.0502, "step": 4663 }, { "epoch": 0.2549940201606014, "grad_norm": 2.5872409343719482, "learning_rate": 8.730969682374484e-05, "loss": 1.1376, "step": 4664 }, { "epoch": 0.25504869297796, "grad_norm": 2.3557212352752686, "learning_rate": 8.730380217908417e-05, "loss": 0.8929, "step": 4665 }, { "epoch": 0.2551033657953186, "grad_norm": 2.754955768585205, "learning_rate": 8.729790636479568e-05, "loss": 1.4183, "step": 4666 }, { "epoch": 0.2551580386126773, "grad_norm": 2.200683832168579, "learning_rate": 8.729200938106421e-05, "loss": 1.023, "step": 4667 }, { "epoch": 0.2552127114300359, "grad_norm": 3.377048969268799, "learning_rate": 8.728611122807466e-05, "loss": 1.2117, "step": 4668 }, { "epoch": 0.2552673842473945, "grad_norm": 3.321593761444092, "learning_rate": 8.728021190601198e-05, "loss": 1.3396, "step": 4669 }, { "epoch": 0.25532205706475314, "grad_norm": 2.6494972705841064, "learning_rate": 8.72743114150611e-05, "loss": 1.043, "step": 4670 }, { "epoch": 0.25537672988211174, "grad_norm": 2.5587854385375977, "learning_rate": 8.726840975540706e-05, "loss": 1.1703, "step": 4671 }, { "epoch": 0.25543140269947034, "grad_norm": 2.6212081909179688, "learning_rate": 8.726250692723488e-05, "loss": 1.2258, "step": 4672 }, { "epoch": 0.255486075516829, "grad_norm": 2.6700122356414795, "learning_rate": 8.725660293072965e-05, "loss": 1.0833, "step": 4673 }, { "epoch": 0.2555407483341876, "grad_norm": 2.1130154132843018, "learning_rate": 8.725069776607648e-05, "loss": 1.0899, "step": 4674 }, { "epoch": 0.2555954211515462, "grad_norm": 2.0234475135803223, "learning_rate": 8.724479143346051e-05, "loss": 0.9313, "step": 4675 }, { "epoch": 0.2556500939689048, "grad_norm": 2.180229425430298, "learning_rate": 8.723888393306695e-05, "loss": 1.081, "step": 4676 }, { "epoch": 0.25570476678626347, "grad_norm": 2.3861467838287354, "learning_rate": 8.723297526508101e-05, "loss": 0.8919, "step": 4677 }, { "epoch": 0.2557594396036221, "grad_norm": 3.336700677871704, "learning_rate": 8.722706542968795e-05, "loss": 0.9993, "step": 4678 }, { "epoch": 0.2558141124209807, "grad_norm": 2.3351356983184814, "learning_rate": 8.722115442707308e-05, "loss": 1.1635, "step": 4679 }, { "epoch": 0.25586878523833934, "grad_norm": 2.9977540969848633, "learning_rate": 8.721524225742171e-05, "loss": 1.1142, "step": 4680 }, { "epoch": 0.25592345805569794, "grad_norm": 4.554276466369629, "learning_rate": 8.720932892091924e-05, "loss": 1.1499, "step": 4681 }, { "epoch": 0.25597813087305654, "grad_norm": 2.55271315574646, "learning_rate": 8.720341441775106e-05, "loss": 1.0541, "step": 4682 }, { "epoch": 0.25603280369041514, "grad_norm": 2.388214349746704, "learning_rate": 8.719749874810263e-05, "loss": 1.2742, "step": 4683 }, { "epoch": 0.2560874765077738, "grad_norm": 2.6073453426361084, "learning_rate": 8.71915819121594e-05, "loss": 1.0905, "step": 4684 }, { "epoch": 0.2561421493251324, "grad_norm": 2.088421583175659, "learning_rate": 8.718566391010692e-05, "loss": 1.0232, "step": 4685 }, { "epoch": 0.256196822142491, "grad_norm": 2.406717300415039, "learning_rate": 8.717974474213072e-05, "loss": 0.8964, "step": 4686 }, { "epoch": 0.25625149495984967, "grad_norm": 2.420252799987793, "learning_rate": 8.71738244084164e-05, "loss": 1.1332, "step": 4687 }, { "epoch": 0.25630616777720827, "grad_norm": 2.9695024490356445, "learning_rate": 8.71679029091496e-05, "loss": 1.3484, "step": 4688 }, { "epoch": 0.2563608405945669, "grad_norm": 3.159543037414551, "learning_rate": 8.716198024451596e-05, "loss": 0.9607, "step": 4689 }, { "epoch": 0.25641551341192553, "grad_norm": 2.3826239109039307, "learning_rate": 8.715605641470119e-05, "loss": 1.117, "step": 4690 }, { "epoch": 0.25647018622928414, "grad_norm": 2.5369694232940674, "learning_rate": 8.715013141989103e-05, "loss": 1.0427, "step": 4691 }, { "epoch": 0.25652485904664274, "grad_norm": 3.5404164791107178, "learning_rate": 8.714420526027125e-05, "loss": 1.2494, "step": 4692 }, { "epoch": 0.25657953186400134, "grad_norm": 2.597566843032837, "learning_rate": 8.713827793602765e-05, "loss": 1.0864, "step": 4693 }, { "epoch": 0.25663420468136, "grad_norm": 2.1627283096313477, "learning_rate": 8.713234944734609e-05, "loss": 1.2145, "step": 4694 }, { "epoch": 0.2566888774987186, "grad_norm": 2.9443137645721436, "learning_rate": 8.712641979441245e-05, "loss": 1.0258, "step": 4695 }, { "epoch": 0.2567435503160772, "grad_norm": 2.6571764945983887, "learning_rate": 8.712048897741266e-05, "loss": 1.1009, "step": 4696 }, { "epoch": 0.25679822313343587, "grad_norm": 2.6367621421813965, "learning_rate": 8.711455699653264e-05, "loss": 1.1049, "step": 4697 }, { "epoch": 0.25685289595079447, "grad_norm": 5.001741886138916, "learning_rate": 8.710862385195842e-05, "loss": 1.0482, "step": 4698 }, { "epoch": 0.25690756876815307, "grad_norm": 3.086398124694824, "learning_rate": 8.7102689543876e-05, "loss": 1.1635, "step": 4699 }, { "epoch": 0.25696224158551173, "grad_norm": 2.7783544063568115, "learning_rate": 8.709675407247146e-05, "loss": 0.9102, "step": 4700 }, { "epoch": 0.25701691440287033, "grad_norm": 2.6095030307769775, "learning_rate": 8.709081743793091e-05, "loss": 1.2194, "step": 4701 }, { "epoch": 0.25707158722022894, "grad_norm": 3.0715529918670654, "learning_rate": 8.708487964044048e-05, "loss": 1.1368, "step": 4702 }, { "epoch": 0.25712626003758754, "grad_norm": 3.9043192863464355, "learning_rate": 8.707894068018633e-05, "loss": 1.2277, "step": 4703 }, { "epoch": 0.2571809328549462, "grad_norm": 2.711636543273926, "learning_rate": 8.707300055735468e-05, "loss": 1.0696, "step": 4704 }, { "epoch": 0.2572356056723048, "grad_norm": 3.079261541366577, "learning_rate": 8.706705927213178e-05, "loss": 1.1493, "step": 4705 }, { "epoch": 0.2572902784896634, "grad_norm": 4.42392110824585, "learning_rate": 8.706111682470392e-05, "loss": 1.0788, "step": 4706 }, { "epoch": 0.25734495130702206, "grad_norm": 2.4117484092712402, "learning_rate": 8.705517321525743e-05, "loss": 1.0532, "step": 4707 }, { "epoch": 0.25739962412438067, "grad_norm": 2.3559396266937256, "learning_rate": 8.704922844397863e-05, "loss": 1.1361, "step": 4708 }, { "epoch": 0.25745429694173927, "grad_norm": 2.0240859985351562, "learning_rate": 8.704328251105394e-05, "loss": 0.964, "step": 4709 }, { "epoch": 0.25750896975909787, "grad_norm": 2.38390851020813, "learning_rate": 8.703733541666977e-05, "loss": 1.118, "step": 4710 }, { "epoch": 0.25756364257645653, "grad_norm": 3.3615212440490723, "learning_rate": 8.703138716101261e-05, "loss": 1.0973, "step": 4711 }, { "epoch": 0.25761831539381513, "grad_norm": 4.623227119445801, "learning_rate": 8.702543774426895e-05, "loss": 0.9898, "step": 4712 }, { "epoch": 0.25767298821117374, "grad_norm": 2.8308217525482178, "learning_rate": 8.701948716662533e-05, "loss": 1.2636, "step": 4713 }, { "epoch": 0.2577276610285324, "grad_norm": 2.532311201095581, "learning_rate": 8.701353542826833e-05, "loss": 1.2668, "step": 4714 }, { "epoch": 0.257782333845891, "grad_norm": 2.2736706733703613, "learning_rate": 8.700758252938454e-05, "loss": 0.957, "step": 4715 }, { "epoch": 0.2578370066632496, "grad_norm": 4.32968282699585, "learning_rate": 8.700162847016064e-05, "loss": 1.0924, "step": 4716 }, { "epoch": 0.25789167948060826, "grad_norm": 2.4768261909484863, "learning_rate": 8.69956732507833e-05, "loss": 1.0872, "step": 4717 }, { "epoch": 0.25794635229796686, "grad_norm": 2.5125279426574707, "learning_rate": 8.698971687143925e-05, "loss": 0.9797, "step": 4718 }, { "epoch": 0.25800102511532547, "grad_norm": 2.053914785385132, "learning_rate": 8.698375933231522e-05, "loss": 0.9853, "step": 4719 }, { "epoch": 0.25805569793268407, "grad_norm": 2.9088919162750244, "learning_rate": 8.697780063359801e-05, "loss": 0.88, "step": 4720 }, { "epoch": 0.25811037075004273, "grad_norm": 3.264195680618286, "learning_rate": 8.697184077547446e-05, "loss": 0.8574, "step": 4721 }, { "epoch": 0.25816504356740133, "grad_norm": 2.9216318130493164, "learning_rate": 8.696587975813146e-05, "loss": 1.2628, "step": 4722 }, { "epoch": 0.25821971638475993, "grad_norm": 2.240877389907837, "learning_rate": 8.695991758175588e-05, "loss": 1.1148, "step": 4723 }, { "epoch": 0.2582743892021186, "grad_norm": 2.4923603534698486, "learning_rate": 8.695395424653465e-05, "loss": 1.0753, "step": 4724 }, { "epoch": 0.2583290620194772, "grad_norm": 2.852191209793091, "learning_rate": 8.694798975265477e-05, "loss": 1.2487, "step": 4725 }, { "epoch": 0.2583837348368358, "grad_norm": 2.7798304557800293, "learning_rate": 8.694202410030325e-05, "loss": 1.2689, "step": 4726 }, { "epoch": 0.25843840765419446, "grad_norm": 2.7285561561584473, "learning_rate": 8.693605728966713e-05, "loss": 1.0235, "step": 4727 }, { "epoch": 0.25849308047155306, "grad_norm": 4.177070617675781, "learning_rate": 8.69300893209335e-05, "loss": 1.3848, "step": 4728 }, { "epoch": 0.25854775328891166, "grad_norm": 2.3101389408111572, "learning_rate": 8.692412019428947e-05, "loss": 1.1672, "step": 4729 }, { "epoch": 0.25860242610627027, "grad_norm": 2.75808048248291, "learning_rate": 8.691814990992221e-05, "loss": 1.0215, "step": 4730 }, { "epoch": 0.2586570989236289, "grad_norm": 2.730698347091675, "learning_rate": 8.691217846801888e-05, "loss": 1.2413, "step": 4731 }, { "epoch": 0.25871177174098753, "grad_norm": 2.386795997619629, "learning_rate": 8.690620586876676e-05, "loss": 1.0882, "step": 4732 }, { "epoch": 0.25876644455834613, "grad_norm": 2.4248321056365967, "learning_rate": 8.69002321123531e-05, "loss": 1.2121, "step": 4733 }, { "epoch": 0.2588211173757048, "grad_norm": 3.064619779586792, "learning_rate": 8.689425719896515e-05, "loss": 1.2269, "step": 4734 }, { "epoch": 0.2588757901930634, "grad_norm": 2.716953754425049, "learning_rate": 8.688828112879033e-05, "loss": 1.1923, "step": 4735 }, { "epoch": 0.258930463010422, "grad_norm": 3.344369411468506, "learning_rate": 8.688230390201596e-05, "loss": 1.2364, "step": 4736 }, { "epoch": 0.2589851358277806, "grad_norm": 2.374382734298706, "learning_rate": 8.687632551882947e-05, "loss": 1.1863, "step": 4737 }, { "epoch": 0.25903980864513926, "grad_norm": 2.532400369644165, "learning_rate": 8.68703459794183e-05, "loss": 1.0501, "step": 4738 }, { "epoch": 0.25909448146249786, "grad_norm": 3.4568817615509033, "learning_rate": 8.686436528396993e-05, "loss": 1.3504, "step": 4739 }, { "epoch": 0.25914915427985646, "grad_norm": 3.92995023727417, "learning_rate": 8.685838343267189e-05, "loss": 1.2492, "step": 4740 }, { "epoch": 0.2592038270972151, "grad_norm": 2.6108949184417725, "learning_rate": 8.685240042571173e-05, "loss": 1.1997, "step": 4741 }, { "epoch": 0.2592584999145737, "grad_norm": 2.347477436065674, "learning_rate": 8.684641626327704e-05, "loss": 1.1913, "step": 4742 }, { "epoch": 0.25931317273193233, "grad_norm": 1.878000020980835, "learning_rate": 8.684043094555545e-05, "loss": 0.9007, "step": 4743 }, { "epoch": 0.259367845549291, "grad_norm": 2.438400983810425, "learning_rate": 8.683444447273463e-05, "loss": 0.9854, "step": 4744 }, { "epoch": 0.2594225183666496, "grad_norm": 3.049480438232422, "learning_rate": 8.682845684500227e-05, "loss": 1.0603, "step": 4745 }, { "epoch": 0.2594771911840082, "grad_norm": 2.0690419673919678, "learning_rate": 8.682246806254612e-05, "loss": 0.9109, "step": 4746 }, { "epoch": 0.2595318640013668, "grad_norm": 2.3885574340820312, "learning_rate": 8.681647812555394e-05, "loss": 1.2733, "step": 4747 }, { "epoch": 0.25958653681872546, "grad_norm": 2.444132089614868, "learning_rate": 8.681048703421355e-05, "loss": 1.1188, "step": 4748 }, { "epoch": 0.25964120963608406, "grad_norm": 2.101095676422119, "learning_rate": 8.680449478871277e-05, "loss": 1.2526, "step": 4749 }, { "epoch": 0.25969588245344266, "grad_norm": 3.9962921142578125, "learning_rate": 8.679850138923953e-05, "loss": 0.8812, "step": 4750 }, { "epoch": 0.2597505552708013, "grad_norm": 2.365673780441284, "learning_rate": 8.67925068359817e-05, "loss": 1.1641, "step": 4751 }, { "epoch": 0.2598052280881599, "grad_norm": 2.467491626739502, "learning_rate": 8.678651112912726e-05, "loss": 0.9986, "step": 4752 }, { "epoch": 0.2598599009055185, "grad_norm": 3.055972099304199, "learning_rate": 8.67805142688642e-05, "loss": 1.1728, "step": 4753 }, { "epoch": 0.2599145737228772, "grad_norm": 2.8496437072753906, "learning_rate": 8.677451625538053e-05, "loss": 1.1037, "step": 4754 }, { "epoch": 0.2599692465402358, "grad_norm": 2.97517466545105, "learning_rate": 8.676851708886433e-05, "loss": 1.2567, "step": 4755 }, { "epoch": 0.2600239193575944, "grad_norm": 3.165517807006836, "learning_rate": 8.676251676950369e-05, "loss": 1.3171, "step": 4756 }, { "epoch": 0.260078592174953, "grad_norm": 2.3910739421844482, "learning_rate": 8.675651529748674e-05, "loss": 1.2989, "step": 4757 }, { "epoch": 0.26013326499231165, "grad_norm": 2.5433034896850586, "learning_rate": 8.675051267300165e-05, "loss": 0.9521, "step": 4758 }, { "epoch": 0.26018793780967026, "grad_norm": 2.4929561614990234, "learning_rate": 8.674450889623664e-05, "loss": 1.2314, "step": 4759 }, { "epoch": 0.26024261062702886, "grad_norm": 2.2547786235809326, "learning_rate": 8.673850396737995e-05, "loss": 0.9032, "step": 4760 }, { "epoch": 0.2602972834443875, "grad_norm": 2.613579750061035, "learning_rate": 8.673249788661985e-05, "loss": 1.134, "step": 4761 }, { "epoch": 0.2603519562617461, "grad_norm": 2.834744691848755, "learning_rate": 8.672649065414467e-05, "loss": 0.952, "step": 4762 }, { "epoch": 0.2604066290791047, "grad_norm": 2.778120517730713, "learning_rate": 8.672048227014274e-05, "loss": 1.4411, "step": 4763 }, { "epoch": 0.2604613018964633, "grad_norm": 2.3460843563079834, "learning_rate": 8.671447273480247e-05, "loss": 1.065, "step": 4764 }, { "epoch": 0.260515974713822, "grad_norm": 2.4598500728607178, "learning_rate": 8.670846204831227e-05, "loss": 1.1765, "step": 4765 }, { "epoch": 0.2605706475311806, "grad_norm": 2.850914716720581, "learning_rate": 8.67024502108606e-05, "loss": 1.3257, "step": 4766 }, { "epoch": 0.2606253203485392, "grad_norm": 2.6123969554901123, "learning_rate": 8.669643722263596e-05, "loss": 1.1277, "step": 4767 }, { "epoch": 0.26067999316589785, "grad_norm": 2.551015853881836, "learning_rate": 8.669042308382688e-05, "loss": 1.1476, "step": 4768 }, { "epoch": 0.26073466598325645, "grad_norm": 3.1886744499206543, "learning_rate": 8.668440779462194e-05, "loss": 1.0073, "step": 4769 }, { "epoch": 0.26078933880061506, "grad_norm": 2.3754189014434814, "learning_rate": 8.667839135520973e-05, "loss": 0.9429, "step": 4770 }, { "epoch": 0.2608440116179737, "grad_norm": 2.892897605895996, "learning_rate": 8.667237376577888e-05, "loss": 1.2132, "step": 4771 }, { "epoch": 0.2608986844353323, "grad_norm": 3.4669113159179688, "learning_rate": 8.66663550265181e-05, "loss": 1.1939, "step": 4772 }, { "epoch": 0.2609533572526909, "grad_norm": 2.1760284900665283, "learning_rate": 8.666033513761606e-05, "loss": 1.1074, "step": 4773 }, { "epoch": 0.2610080300700495, "grad_norm": 2.9632315635681152, "learning_rate": 8.665431409926155e-05, "loss": 1.2971, "step": 4774 }, { "epoch": 0.2610627028874082, "grad_norm": 2.259577751159668, "learning_rate": 8.664829191164332e-05, "loss": 1.1406, "step": 4775 }, { "epoch": 0.2611173757047668, "grad_norm": 3.2921361923217773, "learning_rate": 8.664226857495022e-05, "loss": 1.1924, "step": 4776 }, { "epoch": 0.2611720485221254, "grad_norm": 2.773210287094116, "learning_rate": 8.663624408937107e-05, "loss": 1.1731, "step": 4777 }, { "epoch": 0.26122672133948405, "grad_norm": 3.259991407394409, "learning_rate": 8.663021845509481e-05, "loss": 1.1053, "step": 4778 }, { "epoch": 0.26128139415684265, "grad_norm": 2.269176483154297, "learning_rate": 8.662419167231032e-05, "loss": 0.9764, "step": 4779 }, { "epoch": 0.26133606697420125, "grad_norm": 2.3109395503997803, "learning_rate": 8.661816374120662e-05, "loss": 1.0352, "step": 4780 }, { "epoch": 0.26139073979155986, "grad_norm": 2.744475841522217, "learning_rate": 8.661213466197264e-05, "loss": 1.3233, "step": 4781 }, { "epoch": 0.2614454126089185, "grad_norm": 3.936436414718628, "learning_rate": 8.660610443479747e-05, "loss": 1.2193, "step": 4782 }, { "epoch": 0.2615000854262771, "grad_norm": 2.5750880241394043, "learning_rate": 8.660007305987017e-05, "loss": 1.2163, "step": 4783 }, { "epoch": 0.2615547582436357, "grad_norm": 2.6583149433135986, "learning_rate": 8.659404053737983e-05, "loss": 1.2556, "step": 4784 }, { "epoch": 0.2616094310609944, "grad_norm": 3.198551893234253, "learning_rate": 8.658800686751562e-05, "loss": 0.9658, "step": 4785 }, { "epoch": 0.261664103878353, "grad_norm": 2.5588090419769287, "learning_rate": 8.65819720504667e-05, "loss": 1.0535, "step": 4786 }, { "epoch": 0.2617187766957116, "grad_norm": 2.096055030822754, "learning_rate": 8.657593608642231e-05, "loss": 1.0388, "step": 4787 }, { "epoch": 0.26177344951307024, "grad_norm": 4.068143367767334, "learning_rate": 8.656989897557168e-05, "loss": 1.0624, "step": 4788 }, { "epoch": 0.26182812233042885, "grad_norm": 2.502150297164917, "learning_rate": 8.656386071810412e-05, "loss": 1.0918, "step": 4789 }, { "epoch": 0.26188279514778745, "grad_norm": 2.7843377590179443, "learning_rate": 8.655782131420894e-05, "loss": 1.0896, "step": 4790 }, { "epoch": 0.26193746796514605, "grad_norm": 2.856260061264038, "learning_rate": 8.655178076407547e-05, "loss": 1.3241, "step": 4791 }, { "epoch": 0.2619921407825047, "grad_norm": 2.8116495609283447, "learning_rate": 8.654573906789317e-05, "loss": 1.2252, "step": 4792 }, { "epoch": 0.2620468135998633, "grad_norm": 2.5499815940856934, "learning_rate": 8.65396962258514e-05, "loss": 1.0632, "step": 4793 }, { "epoch": 0.2621014864172219, "grad_norm": 2.402711868286133, "learning_rate": 8.653365223813971e-05, "loss": 1.2388, "step": 4794 }, { "epoch": 0.2621561592345806, "grad_norm": 4.496379852294922, "learning_rate": 8.652760710494754e-05, "loss": 1.1412, "step": 4795 }, { "epoch": 0.2622108320519392, "grad_norm": 2.515131711959839, "learning_rate": 8.652156082646446e-05, "loss": 1.1995, "step": 4796 }, { "epoch": 0.2622655048692978, "grad_norm": 2.912287473678589, "learning_rate": 8.651551340288003e-05, "loss": 0.8697, "step": 4797 }, { "epoch": 0.26232017768665644, "grad_norm": 2.193572759628296, "learning_rate": 8.650946483438387e-05, "loss": 0.9906, "step": 4798 }, { "epoch": 0.26237485050401504, "grad_norm": 2.383287191390991, "learning_rate": 8.650341512116563e-05, "loss": 1.0729, "step": 4799 }, { "epoch": 0.26242952332137365, "grad_norm": 1.9736003875732422, "learning_rate": 8.649736426341499e-05, "loss": 1.0799, "step": 4800 }, { "epoch": 0.26248419613873225, "grad_norm": 2.2091612815856934, "learning_rate": 8.649131226132165e-05, "loss": 1.0332, "step": 4801 }, { "epoch": 0.2625388689560909, "grad_norm": 2.792975664138794, "learning_rate": 8.648525911507541e-05, "loss": 1.3489, "step": 4802 }, { "epoch": 0.2625935417734495, "grad_norm": 2.103972911834717, "learning_rate": 8.6479204824866e-05, "loss": 1.0131, "step": 4803 }, { "epoch": 0.2626482145908081, "grad_norm": 2.2924535274505615, "learning_rate": 8.647314939088331e-05, "loss": 1.1688, "step": 4804 }, { "epoch": 0.2627028874081668, "grad_norm": 2.692267656326294, "learning_rate": 8.646709281331717e-05, "loss": 1.1528, "step": 4805 }, { "epoch": 0.2627575602255254, "grad_norm": 2.4132328033447266, "learning_rate": 8.646103509235748e-05, "loss": 1.0166, "step": 4806 }, { "epoch": 0.262812233042884, "grad_norm": 2.0850155353546143, "learning_rate": 8.645497622819419e-05, "loss": 0.8828, "step": 4807 }, { "epoch": 0.2628669058602426, "grad_norm": 2.0474605560302734, "learning_rate": 8.644891622101722e-05, "loss": 1.0186, "step": 4808 }, { "epoch": 0.26292157867760124, "grad_norm": 2.7574572563171387, "learning_rate": 8.644285507101666e-05, "loss": 0.9205, "step": 4809 }, { "epoch": 0.26297625149495985, "grad_norm": 3.123232126235962, "learning_rate": 8.643679277838248e-05, "loss": 1.1292, "step": 4810 }, { "epoch": 0.26303092431231845, "grad_norm": 2.5597317218780518, "learning_rate": 8.643072934330478e-05, "loss": 1.1123, "step": 4811 }, { "epoch": 0.2630855971296771, "grad_norm": 2.6104955673217773, "learning_rate": 8.642466476597371e-05, "loss": 1.1336, "step": 4812 }, { "epoch": 0.2631402699470357, "grad_norm": 2.3022124767303467, "learning_rate": 8.641859904657935e-05, "loss": 0.9099, "step": 4813 }, { "epoch": 0.2631949427643943, "grad_norm": 2.976877212524414, "learning_rate": 8.641253218531193e-05, "loss": 1.2895, "step": 4814 }, { "epoch": 0.26324961558175297, "grad_norm": 2.422119140625, "learning_rate": 8.640646418236168e-05, "loss": 1.0765, "step": 4815 }, { "epoch": 0.2633042883991116, "grad_norm": 2.0034468173980713, "learning_rate": 8.640039503791884e-05, "loss": 1.1476, "step": 4816 }, { "epoch": 0.2633589612164702, "grad_norm": 2.2552809715270996, "learning_rate": 8.639432475217368e-05, "loss": 1.0909, "step": 4817 }, { "epoch": 0.2634136340338288, "grad_norm": 2.128939628601074, "learning_rate": 8.638825332531658e-05, "loss": 0.8964, "step": 4818 }, { "epoch": 0.26346830685118744, "grad_norm": 2.7650091648101807, "learning_rate": 8.638218075753786e-05, "loss": 1.3254, "step": 4819 }, { "epoch": 0.26352297966854604, "grad_norm": 1.882422685623169, "learning_rate": 8.637610704902793e-05, "loss": 1.0287, "step": 4820 }, { "epoch": 0.26357765248590465, "grad_norm": 2.382272481918335, "learning_rate": 8.637003219997724e-05, "loss": 1.0762, "step": 4821 }, { "epoch": 0.2636323253032633, "grad_norm": 3.6669394969940186, "learning_rate": 8.636395621057624e-05, "loss": 1.1307, "step": 4822 }, { "epoch": 0.2636869981206219, "grad_norm": 2.816072940826416, "learning_rate": 8.635787908101547e-05, "loss": 1.0161, "step": 4823 }, { "epoch": 0.2637416709379805, "grad_norm": 2.9144439697265625, "learning_rate": 8.635180081148546e-05, "loss": 1.2386, "step": 4824 }, { "epoch": 0.26379634375533917, "grad_norm": 2.6523516178131104, "learning_rate": 8.634572140217677e-05, "loss": 1.1453, "step": 4825 }, { "epoch": 0.26385101657269777, "grad_norm": 2.1414756774902344, "learning_rate": 8.633964085328002e-05, "loss": 1.1339, "step": 4826 }, { "epoch": 0.2639056893900564, "grad_norm": 3.343689203262329, "learning_rate": 8.633355916498587e-05, "loss": 1.1667, "step": 4827 }, { "epoch": 0.263960362207415, "grad_norm": 3.0701258182525635, "learning_rate": 8.632747633748499e-05, "loss": 1.2276, "step": 4828 }, { "epoch": 0.26401503502477364, "grad_norm": 2.781015634536743, "learning_rate": 8.632139237096814e-05, "loss": 1.1414, "step": 4829 }, { "epoch": 0.26406970784213224, "grad_norm": 2.5419435501098633, "learning_rate": 8.631530726562605e-05, "loss": 1.2382, "step": 4830 }, { "epoch": 0.26412438065949084, "grad_norm": 3.915184259414673, "learning_rate": 8.630922102164949e-05, "loss": 1.1852, "step": 4831 }, { "epoch": 0.2641790534768495, "grad_norm": 2.7238786220550537, "learning_rate": 8.630313363922934e-05, "loss": 1.0951, "step": 4832 }, { "epoch": 0.2642337262942081, "grad_norm": 2.5967373847961426, "learning_rate": 8.629704511855642e-05, "loss": 1.2794, "step": 4833 }, { "epoch": 0.2642883991115667, "grad_norm": 2.753618001937866, "learning_rate": 8.629095545982167e-05, "loss": 1.0818, "step": 4834 }, { "epoch": 0.2643430719289253, "grad_norm": 2.1578991413116455, "learning_rate": 8.628486466321598e-05, "loss": 1.2103, "step": 4835 }, { "epoch": 0.26439774474628397, "grad_norm": 2.4160056114196777, "learning_rate": 8.627877272893035e-05, "loss": 0.9957, "step": 4836 }, { "epoch": 0.26445241756364257, "grad_norm": 3.5809433460235596, "learning_rate": 8.62726796571558e-05, "loss": 0.7911, "step": 4837 }, { "epoch": 0.2645070903810012, "grad_norm": 1.7592062950134277, "learning_rate": 8.626658544808335e-05, "loss": 0.9357, "step": 4838 }, { "epoch": 0.26456176319835983, "grad_norm": 2.916625738143921, "learning_rate": 8.626049010190408e-05, "loss": 1.1455, "step": 4839 }, { "epoch": 0.26461643601571844, "grad_norm": 2.1249635219573975, "learning_rate": 8.625439361880911e-05, "loss": 1.0368, "step": 4840 }, { "epoch": 0.26467110883307704, "grad_norm": 2.4031598567962646, "learning_rate": 8.624829599898959e-05, "loss": 1.3636, "step": 4841 }, { "epoch": 0.2647257816504357, "grad_norm": 2.284968852996826, "learning_rate": 8.62421972426367e-05, "loss": 0.802, "step": 4842 }, { "epoch": 0.2647804544677943, "grad_norm": 2.684509038925171, "learning_rate": 8.623609734994167e-05, "loss": 1.2522, "step": 4843 }, { "epoch": 0.2648351272851529, "grad_norm": 2.2790775299072266, "learning_rate": 8.622999632109577e-05, "loss": 1.2028, "step": 4844 }, { "epoch": 0.2648898001025115, "grad_norm": 2.7944090366363525, "learning_rate": 8.622389415629025e-05, "loss": 1.1161, "step": 4845 }, { "epoch": 0.26494447291987017, "grad_norm": 2.242100715637207, "learning_rate": 8.621779085571646e-05, "loss": 1.0177, "step": 4846 }, { "epoch": 0.26499914573722877, "grad_norm": 2.4578166007995605, "learning_rate": 8.621168641956578e-05, "loss": 1.0244, "step": 4847 }, { "epoch": 0.2650538185545874, "grad_norm": 2.8140597343444824, "learning_rate": 8.620558084802959e-05, "loss": 1.2171, "step": 4848 }, { "epoch": 0.26510849137194603, "grad_norm": 2.5107059478759766, "learning_rate": 8.619947414129932e-05, "loss": 0.9874, "step": 4849 }, { "epoch": 0.26516316418930463, "grad_norm": 2.1246695518493652, "learning_rate": 8.619336629956646e-05, "loss": 1.1129, "step": 4850 }, { "epoch": 0.26521783700666324, "grad_norm": 2.287259101867676, "learning_rate": 8.61872573230225e-05, "loss": 1.1541, "step": 4851 }, { "epoch": 0.2652725098240219, "grad_norm": 2.329347610473633, "learning_rate": 8.618114721185902e-05, "loss": 1.0692, "step": 4852 }, { "epoch": 0.2653271826413805, "grad_norm": 4.070623874664307, "learning_rate": 8.617503596626753e-05, "loss": 1.3691, "step": 4853 }, { "epoch": 0.2653818554587391, "grad_norm": 3.179680109024048, "learning_rate": 8.616892358643969e-05, "loss": 1.2636, "step": 4854 }, { "epoch": 0.2654365282760977, "grad_norm": 2.3689022064208984, "learning_rate": 8.616281007256714e-05, "loss": 1.0426, "step": 4855 }, { "epoch": 0.26549120109345636, "grad_norm": 2.121309280395508, "learning_rate": 8.615669542484155e-05, "loss": 1.0513, "step": 4856 }, { "epoch": 0.26554587391081497, "grad_norm": 2.6612026691436768, "learning_rate": 8.615057964345466e-05, "loss": 1.0976, "step": 4857 }, { "epoch": 0.26560054672817357, "grad_norm": 2.1469881534576416, "learning_rate": 8.61444627285982e-05, "loss": 1.0881, "step": 4858 }, { "epoch": 0.26565521954553223, "grad_norm": 2.4695351123809814, "learning_rate": 8.6138344680464e-05, "loss": 1.2228, "step": 4859 }, { "epoch": 0.26570989236289083, "grad_norm": 3.179823160171509, "learning_rate": 8.613222549924384e-05, "loss": 1.1734, "step": 4860 }, { "epoch": 0.26576456518024943, "grad_norm": 2.021984100341797, "learning_rate": 8.61261051851296e-05, "loss": 0.9721, "step": 4861 }, { "epoch": 0.26581923799760804, "grad_norm": 2.4241178035736084, "learning_rate": 8.611998373831319e-05, "loss": 1.1111, "step": 4862 }, { "epoch": 0.2658739108149667, "grad_norm": 2.3480911254882812, "learning_rate": 8.611386115898655e-05, "loss": 1.2917, "step": 4863 }, { "epoch": 0.2659285836323253, "grad_norm": 2.3460021018981934, "learning_rate": 8.61077374473416e-05, "loss": 1.0115, "step": 4864 }, { "epoch": 0.2659832564496839, "grad_norm": 2.7500014305114746, "learning_rate": 8.610161260357036e-05, "loss": 1.1864, "step": 4865 }, { "epoch": 0.26603792926704256, "grad_norm": 2.442931652069092, "learning_rate": 8.609548662786492e-05, "loss": 1.3006, "step": 4866 }, { "epoch": 0.26609260208440116, "grad_norm": 2.885589599609375, "learning_rate": 8.608935952041731e-05, "loss": 1.2775, "step": 4867 }, { "epoch": 0.26614727490175977, "grad_norm": 2.4653937816619873, "learning_rate": 8.608323128141964e-05, "loss": 0.865, "step": 4868 }, { "epoch": 0.2662019477191184, "grad_norm": 2.1731700897216797, "learning_rate": 8.607710191106406e-05, "loss": 1.1106, "step": 4869 }, { "epoch": 0.26625662053647703, "grad_norm": 2.6047332286834717, "learning_rate": 8.607097140954276e-05, "loss": 1.1214, "step": 4870 }, { "epoch": 0.26631129335383563, "grad_norm": 2.8050737380981445, "learning_rate": 8.606483977704796e-05, "loss": 1.2561, "step": 4871 }, { "epoch": 0.26636596617119424, "grad_norm": 2.299934148788452, "learning_rate": 8.605870701377189e-05, "loss": 1.0757, "step": 4872 }, { "epoch": 0.2664206389885529, "grad_norm": 2.725156307220459, "learning_rate": 8.605257311990685e-05, "loss": 0.9318, "step": 4873 }, { "epoch": 0.2664753118059115, "grad_norm": 2.2023136615753174, "learning_rate": 8.604643809564517e-05, "loss": 0.8554, "step": 4874 }, { "epoch": 0.2665299846232701, "grad_norm": 2.8095436096191406, "learning_rate": 8.60403019411792e-05, "loss": 1.1661, "step": 4875 }, { "epoch": 0.26658465744062876, "grad_norm": 2.2082979679107666, "learning_rate": 8.603416465670132e-05, "loss": 1.1303, "step": 4876 }, { "epoch": 0.26663933025798736, "grad_norm": 2.8039536476135254, "learning_rate": 8.602802624240399e-05, "loss": 1.1669, "step": 4877 }, { "epoch": 0.26669400307534596, "grad_norm": 3.2147152423858643, "learning_rate": 8.602188669847965e-05, "loss": 1.2658, "step": 4878 }, { "epoch": 0.2667486758927046, "grad_norm": 2.2357985973358154, "learning_rate": 8.60157460251208e-05, "loss": 1.1155, "step": 4879 }, { "epoch": 0.2668033487100632, "grad_norm": 2.3143234252929688, "learning_rate": 8.600960422252e-05, "loss": 1.2581, "step": 4880 }, { "epoch": 0.26685802152742183, "grad_norm": 2.1987340450286865, "learning_rate": 8.60034612908698e-05, "loss": 1.088, "step": 4881 }, { "epoch": 0.26691269434478043, "grad_norm": 3.0616519451141357, "learning_rate": 8.599731723036281e-05, "loss": 1.2093, "step": 4882 }, { "epoch": 0.2669673671621391, "grad_norm": 2.704657554626465, "learning_rate": 8.599117204119167e-05, "loss": 1.0509, "step": 4883 }, { "epoch": 0.2670220399794977, "grad_norm": 2.852086067199707, "learning_rate": 8.598502572354905e-05, "loss": 0.8922, "step": 4884 }, { "epoch": 0.2670767127968563, "grad_norm": 3.501574754714966, "learning_rate": 8.597887827762769e-05, "loss": 1.1624, "step": 4885 }, { "epoch": 0.26713138561421496, "grad_norm": 2.6141374111175537, "learning_rate": 8.597272970362032e-05, "loss": 1.21, "step": 4886 }, { "epoch": 0.26718605843157356, "grad_norm": 2.0859458446502686, "learning_rate": 8.59665800017197e-05, "loss": 0.9181, "step": 4887 }, { "epoch": 0.26724073124893216, "grad_norm": 2.5633018016815186, "learning_rate": 8.59604291721187e-05, "loss": 1.1037, "step": 4888 }, { "epoch": 0.26729540406629076, "grad_norm": 2.8661084175109863, "learning_rate": 8.595427721501013e-05, "loss": 0.9165, "step": 4889 }, { "epoch": 0.2673500768836494, "grad_norm": 2.4943480491638184, "learning_rate": 8.59481241305869e-05, "loss": 0.9278, "step": 4890 }, { "epoch": 0.267404749701008, "grad_norm": 2.907508611679077, "learning_rate": 8.594196991904192e-05, "loss": 1.2525, "step": 4891 }, { "epoch": 0.26745942251836663, "grad_norm": 2.1521477699279785, "learning_rate": 8.593581458056817e-05, "loss": 1.0486, "step": 4892 }, { "epoch": 0.2675140953357253, "grad_norm": 2.680081605911255, "learning_rate": 8.592965811535862e-05, "loss": 1.1147, "step": 4893 }, { "epoch": 0.2675687681530839, "grad_norm": 2.8167335987091064, "learning_rate": 8.592350052360631e-05, "loss": 1.0746, "step": 4894 }, { "epoch": 0.2676234409704425, "grad_norm": 2.445202112197876, "learning_rate": 8.591734180550432e-05, "loss": 0.8557, "step": 4895 }, { "epoch": 0.26767811378780115, "grad_norm": 2.5345869064331055, "learning_rate": 8.591118196124575e-05, "loss": 0.9273, "step": 4896 }, { "epoch": 0.26773278660515976, "grad_norm": 2.7590696811676025, "learning_rate": 8.590502099102371e-05, "loss": 1.2893, "step": 4897 }, { "epoch": 0.26778745942251836, "grad_norm": 2.503619909286499, "learning_rate": 8.58988588950314e-05, "loss": 1.2125, "step": 4898 }, { "epoch": 0.26784213223987696, "grad_norm": 2.9224812984466553, "learning_rate": 8.5892695673462e-05, "loss": 1.2367, "step": 4899 }, { "epoch": 0.2678968050572356, "grad_norm": 3.3259222507476807, "learning_rate": 8.58865313265088e-05, "loss": 1.2233, "step": 4900 }, { "epoch": 0.2679514778745942, "grad_norm": 5.109480857849121, "learning_rate": 8.588036585436503e-05, "loss": 1.3748, "step": 4901 }, { "epoch": 0.2680061506919528, "grad_norm": 2.7799785137176514, "learning_rate": 8.587419925722401e-05, "loss": 1.2979, "step": 4902 }, { "epoch": 0.2680608235093115, "grad_norm": 2.477943181991577, "learning_rate": 8.586803153527912e-05, "loss": 0.9861, "step": 4903 }, { "epoch": 0.2681154963266701, "grad_norm": 2.4380314350128174, "learning_rate": 8.586186268872372e-05, "loss": 1.0638, "step": 4904 }, { "epoch": 0.2681701691440287, "grad_norm": 2.561185121536255, "learning_rate": 8.585569271775121e-05, "loss": 1.4093, "step": 4905 }, { "epoch": 0.26822484196138735, "grad_norm": 2.419861078262329, "learning_rate": 8.584952162255507e-05, "loss": 1.1296, "step": 4906 }, { "epoch": 0.26827951477874595, "grad_norm": 2.375491142272949, "learning_rate": 8.584334940332879e-05, "loss": 1.2633, "step": 4907 }, { "epoch": 0.26833418759610456, "grad_norm": 4.827086925506592, "learning_rate": 8.583717606026589e-05, "loss": 1.014, "step": 4908 }, { "epoch": 0.26838886041346316, "grad_norm": 2.6261308193206787, "learning_rate": 8.583100159355992e-05, "loss": 1.1892, "step": 4909 }, { "epoch": 0.2684435332308218, "grad_norm": 3.834834098815918, "learning_rate": 8.582482600340449e-05, "loss": 1.1443, "step": 4910 }, { "epoch": 0.2684982060481804, "grad_norm": 2.113067388534546, "learning_rate": 8.581864928999321e-05, "loss": 0.9916, "step": 4911 }, { "epoch": 0.268552878865539, "grad_norm": 2.6329081058502197, "learning_rate": 8.581247145351976e-05, "loss": 1.222, "step": 4912 }, { "epoch": 0.2686075516828977, "grad_norm": 1.7913426160812378, "learning_rate": 8.580629249417786e-05, "loss": 0.726, "step": 4913 }, { "epoch": 0.2686622245002563, "grad_norm": 2.4280052185058594, "learning_rate": 8.58001124121612e-05, "loss": 1.0672, "step": 4914 }, { "epoch": 0.2687168973176149, "grad_norm": 2.6406829357147217, "learning_rate": 8.579393120766359e-05, "loss": 1.2722, "step": 4915 }, { "epoch": 0.2687715701349735, "grad_norm": 4.069700241088867, "learning_rate": 8.578774888087882e-05, "loss": 1.1188, "step": 4916 }, { "epoch": 0.26882624295233215, "grad_norm": 2.3824334144592285, "learning_rate": 8.578156543200074e-05, "loss": 1.0716, "step": 4917 }, { "epoch": 0.26888091576969075, "grad_norm": 2.2029690742492676, "learning_rate": 8.57753808612232e-05, "loss": 1.0431, "step": 4918 }, { "epoch": 0.26893558858704936, "grad_norm": 1.8629356622695923, "learning_rate": 8.576919516874014e-05, "loss": 0.892, "step": 4919 }, { "epoch": 0.268990261404408, "grad_norm": 2.464081287384033, "learning_rate": 8.57630083547455e-05, "loss": 1.1816, "step": 4920 }, { "epoch": 0.2690449342217666, "grad_norm": 3.190437078475952, "learning_rate": 8.575682041943326e-05, "loss": 0.9384, "step": 4921 }, { "epoch": 0.2690996070391252, "grad_norm": 3.2642858028411865, "learning_rate": 8.575063136299743e-05, "loss": 0.9344, "step": 4922 }, { "epoch": 0.2691542798564839, "grad_norm": 2.2124502658843994, "learning_rate": 8.574444118563208e-05, "loss": 1.0563, "step": 4923 }, { "epoch": 0.2692089526738425, "grad_norm": 3.6030685901641846, "learning_rate": 8.573824988753129e-05, "loss": 0.972, "step": 4924 }, { "epoch": 0.2692636254912011, "grad_norm": 3.0003576278686523, "learning_rate": 8.573205746888918e-05, "loss": 1.2203, "step": 4925 }, { "epoch": 0.2693182983085597, "grad_norm": 2.617865562438965, "learning_rate": 8.572586392989989e-05, "loss": 1.1645, "step": 4926 }, { "epoch": 0.26937297112591835, "grad_norm": 2.213059902191162, "learning_rate": 8.571966927075765e-05, "loss": 1.1326, "step": 4927 }, { "epoch": 0.26942764394327695, "grad_norm": 2.4064834117889404, "learning_rate": 8.571347349165667e-05, "loss": 1.0442, "step": 4928 }, { "epoch": 0.26948231676063555, "grad_norm": 2.157672882080078, "learning_rate": 8.57072765927912e-05, "loss": 1.0379, "step": 4929 }, { "epoch": 0.2695369895779942, "grad_norm": 2.8528761863708496, "learning_rate": 8.570107857435557e-05, "loss": 0.8604, "step": 4930 }, { "epoch": 0.2695916623953528, "grad_norm": 2.6096973419189453, "learning_rate": 8.569487943654408e-05, "loss": 1.1231, "step": 4931 }, { "epoch": 0.2696463352127114, "grad_norm": 3.214632511138916, "learning_rate": 8.568867917955112e-05, "loss": 1.1937, "step": 4932 }, { "epoch": 0.26970100803007, "grad_norm": 2.2159066200256348, "learning_rate": 8.568247780357108e-05, "loss": 1.1844, "step": 4933 }, { "epoch": 0.2697556808474287, "grad_norm": 2.4512500762939453, "learning_rate": 8.567627530879841e-05, "loss": 1.22, "step": 4934 }, { "epoch": 0.2698103536647873, "grad_norm": 2.0852882862091064, "learning_rate": 8.567007169542757e-05, "loss": 0.9128, "step": 4935 }, { "epoch": 0.2698650264821459, "grad_norm": 2.2235090732574463, "learning_rate": 8.56638669636531e-05, "loss": 0.885, "step": 4936 }, { "epoch": 0.26991969929950455, "grad_norm": 2.607785701751709, "learning_rate": 8.56576611136695e-05, "loss": 1.1149, "step": 4937 }, { "epoch": 0.26997437211686315, "grad_norm": 2.518770933151245, "learning_rate": 8.565145414567137e-05, "loss": 1.087, "step": 4938 }, { "epoch": 0.27002904493422175, "grad_norm": 2.354022264480591, "learning_rate": 8.564524605985333e-05, "loss": 0.9918, "step": 4939 }, { "epoch": 0.2700837177515804, "grad_norm": 2.578049659729004, "learning_rate": 8.563903685641003e-05, "loss": 1.1034, "step": 4940 }, { "epoch": 0.270138390568939, "grad_norm": 2.248769998550415, "learning_rate": 8.563282653553614e-05, "loss": 1.0978, "step": 4941 }, { "epoch": 0.2701930633862976, "grad_norm": 2.2214839458465576, "learning_rate": 8.562661509742639e-05, "loss": 0.9385, "step": 4942 }, { "epoch": 0.2702477362036562, "grad_norm": 2.4983091354370117, "learning_rate": 8.562040254227552e-05, "loss": 1.1796, "step": 4943 }, { "epoch": 0.2703024090210149, "grad_norm": 3.550532579421997, "learning_rate": 8.561418887027834e-05, "loss": 1.2013, "step": 4944 }, { "epoch": 0.2703570818383735, "grad_norm": 3.3570756912231445, "learning_rate": 8.560797408162967e-05, "loss": 1.241, "step": 4945 }, { "epoch": 0.2704117546557321, "grad_norm": 3.602910280227661, "learning_rate": 8.560175817652437e-05, "loss": 1.1366, "step": 4946 }, { "epoch": 0.27046642747309074, "grad_norm": 3.8107006549835205, "learning_rate": 8.55955411551573e-05, "loss": 1.1122, "step": 4947 }, { "epoch": 0.27052110029044935, "grad_norm": 2.7245702743530273, "learning_rate": 8.558932301772343e-05, "loss": 1.1638, "step": 4948 }, { "epoch": 0.27057577310780795, "grad_norm": 2.8918607234954834, "learning_rate": 8.558310376441771e-05, "loss": 1.1508, "step": 4949 }, { "epoch": 0.2706304459251666, "grad_norm": 2.552473545074463, "learning_rate": 8.557688339543515e-05, "loss": 1.1193, "step": 4950 }, { "epoch": 0.2706851187425252, "grad_norm": 3.3683388233184814, "learning_rate": 8.557066191097076e-05, "loss": 1.192, "step": 4951 }, { "epoch": 0.2707397915598838, "grad_norm": 2.8496696949005127, "learning_rate": 8.556443931121964e-05, "loss": 1.0599, "step": 4952 }, { "epoch": 0.2707944643772424, "grad_norm": 3.7512340545654297, "learning_rate": 8.555821559637686e-05, "loss": 1.1152, "step": 4953 }, { "epoch": 0.2708491371946011, "grad_norm": 2.2857003211975098, "learning_rate": 8.55519907666376e-05, "loss": 1.2133, "step": 4954 }, { "epoch": 0.2709038100119597, "grad_norm": 2.5314650535583496, "learning_rate": 8.554576482219698e-05, "loss": 1.1937, "step": 4955 }, { "epoch": 0.2709584828293183, "grad_norm": 2.946117401123047, "learning_rate": 8.553953776325028e-05, "loss": 1.3587, "step": 4956 }, { "epoch": 0.27101315564667694, "grad_norm": 2.258286476135254, "learning_rate": 8.553330958999268e-05, "loss": 0.9513, "step": 4957 }, { "epoch": 0.27106782846403554, "grad_norm": 2.3390614986419678, "learning_rate": 8.552708030261948e-05, "loss": 1.1319, "step": 4958 }, { "epoch": 0.27112250128139415, "grad_norm": 2.254732131958008, "learning_rate": 8.5520849901326e-05, "loss": 0.9775, "step": 4959 }, { "epoch": 0.27117717409875275, "grad_norm": 3.018521785736084, "learning_rate": 8.551461838630758e-05, "loss": 0.9023, "step": 4960 }, { "epoch": 0.2712318469161114, "grad_norm": 2.4507482051849365, "learning_rate": 8.55083857577596e-05, "loss": 1.1882, "step": 4961 }, { "epoch": 0.27128651973347, "grad_norm": 3.197524309158325, "learning_rate": 8.550215201587753e-05, "loss": 1.1168, "step": 4962 }, { "epoch": 0.2713411925508286, "grad_norm": 3.1499879360198975, "learning_rate": 8.549591716085675e-05, "loss": 1.0019, "step": 4963 }, { "epoch": 0.2713958653681873, "grad_norm": 2.093060255050659, "learning_rate": 8.548968119289278e-05, "loss": 1.1561, "step": 4964 }, { "epoch": 0.2714505381855459, "grad_norm": 3.2134103775024414, "learning_rate": 8.548344411218116e-05, "loss": 1.0987, "step": 4965 }, { "epoch": 0.2715052110029045, "grad_norm": 2.634953022003174, "learning_rate": 8.547720591891741e-05, "loss": 1.127, "step": 4966 }, { "epoch": 0.27155988382026314, "grad_norm": 2.420088291168213, "learning_rate": 8.547096661329716e-05, "loss": 1.0082, "step": 4967 }, { "epoch": 0.27161455663762174, "grad_norm": 2.533932685852051, "learning_rate": 8.5464726195516e-05, "loss": 1.2282, "step": 4968 }, { "epoch": 0.27166922945498034, "grad_norm": 3.179155111312866, "learning_rate": 8.545848466576963e-05, "loss": 1.085, "step": 4969 }, { "epoch": 0.27172390227233895, "grad_norm": 3.5480806827545166, "learning_rate": 8.545224202425374e-05, "loss": 0.8821, "step": 4970 }, { "epoch": 0.2717785750896976, "grad_norm": 2.4523820877075195, "learning_rate": 8.544599827116403e-05, "loss": 1.2327, "step": 4971 }, { "epoch": 0.2718332479070562, "grad_norm": 2.7862637042999268, "learning_rate": 8.543975340669632e-05, "loss": 1.1727, "step": 4972 }, { "epoch": 0.2718879207244148, "grad_norm": 3.1471874713897705, "learning_rate": 8.543350743104637e-05, "loss": 1.2635, "step": 4973 }, { "epoch": 0.27194259354177347, "grad_norm": 2.7543599605560303, "learning_rate": 8.542726034441005e-05, "loss": 1.0428, "step": 4974 }, { "epoch": 0.2719972663591321, "grad_norm": 2.6654698848724365, "learning_rate": 8.542101214698317e-05, "loss": 1.0781, "step": 4975 }, { "epoch": 0.2720519391764907, "grad_norm": 2.8363797664642334, "learning_rate": 8.541476283896172e-05, "loss": 1.0946, "step": 4976 }, { "epoch": 0.27210661199384933, "grad_norm": 3.214137077331543, "learning_rate": 8.540851242054159e-05, "loss": 1.2262, "step": 4977 }, { "epoch": 0.27216128481120794, "grad_norm": 2.3304927349090576, "learning_rate": 8.540226089191877e-05, "loss": 0.9062, "step": 4978 }, { "epoch": 0.27221595762856654, "grad_norm": 3.8352463245391846, "learning_rate": 8.539600825328927e-05, "loss": 1.0865, "step": 4979 }, { "epoch": 0.27227063044592514, "grad_norm": 2.802373170852661, "learning_rate": 8.538975450484913e-05, "loss": 1.0244, "step": 4980 }, { "epoch": 0.2723253032632838, "grad_norm": 2.919755220413208, "learning_rate": 8.538349964679444e-05, "loss": 1.2039, "step": 4981 }, { "epoch": 0.2723799760806424, "grad_norm": 4.177722454071045, "learning_rate": 8.53772436793213e-05, "loss": 1.0322, "step": 4982 }, { "epoch": 0.272434648898001, "grad_norm": 2.631150484085083, "learning_rate": 8.537098660262588e-05, "loss": 1.1449, "step": 4983 }, { "epoch": 0.27248932171535967, "grad_norm": 2.920163869857788, "learning_rate": 8.536472841690437e-05, "loss": 1.0794, "step": 4984 }, { "epoch": 0.27254399453271827, "grad_norm": 3.634644031524658, "learning_rate": 8.535846912235298e-05, "loss": 0.9004, "step": 4985 }, { "epoch": 0.2725986673500769, "grad_norm": 2.244631052017212, "learning_rate": 8.535220871916793e-05, "loss": 1.1329, "step": 4986 }, { "epoch": 0.2726533401674355, "grad_norm": 2.57407808303833, "learning_rate": 8.534594720754556e-05, "loss": 1.2079, "step": 4987 }, { "epoch": 0.27270801298479413, "grad_norm": 3.0484354496002197, "learning_rate": 8.533968458768217e-05, "loss": 1.0929, "step": 4988 }, { "epoch": 0.27276268580215274, "grad_norm": 2.723180055618286, "learning_rate": 8.533342085977413e-05, "loss": 0.9815, "step": 4989 }, { "epoch": 0.27281735861951134, "grad_norm": 2.165677785873413, "learning_rate": 8.532715602401782e-05, "loss": 1.0906, "step": 4990 }, { "epoch": 0.27287203143687, "grad_norm": 2.5426623821258545, "learning_rate": 8.532089008060968e-05, "loss": 0.9746, "step": 4991 }, { "epoch": 0.2729267042542286, "grad_norm": 2.408754587173462, "learning_rate": 8.531462302974618e-05, "loss": 1.1745, "step": 4992 }, { "epoch": 0.2729813770715872, "grad_norm": 2.782229423522949, "learning_rate": 8.530835487162379e-05, "loss": 1.243, "step": 4993 }, { "epoch": 0.27303604988894586, "grad_norm": 2.3909761905670166, "learning_rate": 8.530208560643907e-05, "loss": 1.1856, "step": 4994 }, { "epoch": 0.27309072270630447, "grad_norm": 2.639514923095703, "learning_rate": 8.529581523438857e-05, "loss": 1.0585, "step": 4995 }, { "epoch": 0.27314539552366307, "grad_norm": 2.694016695022583, "learning_rate": 8.528954375566891e-05, "loss": 0.9239, "step": 4996 }, { "epoch": 0.2732000683410217, "grad_norm": 2.8254311084747314, "learning_rate": 8.528327117047672e-05, "loss": 1.3396, "step": 4997 }, { "epoch": 0.27325474115838033, "grad_norm": 2.501142740249634, "learning_rate": 8.527699747900864e-05, "loss": 1.1053, "step": 4998 }, { "epoch": 0.27330941397573894, "grad_norm": 3.404266834259033, "learning_rate": 8.527072268146143e-05, "loss": 1.1508, "step": 4999 }, { "epoch": 0.27336408679309754, "grad_norm": 3.501143455505371, "learning_rate": 8.526444677803178e-05, "loss": 1.2368, "step": 5000 }, { "epoch": 0.2734187596104562, "grad_norm": 2.6162986755371094, "learning_rate": 8.525816976891652e-05, "loss": 1.2356, "step": 5001 }, { "epoch": 0.2734734324278148, "grad_norm": 2.328873872756958, "learning_rate": 8.52518916543124e-05, "loss": 1.0956, "step": 5002 }, { "epoch": 0.2735281052451734, "grad_norm": 2.1861319541931152, "learning_rate": 8.52456124344163e-05, "loss": 0.981, "step": 5003 }, { "epoch": 0.27358277806253206, "grad_norm": 2.725292682647705, "learning_rate": 8.523933210942511e-05, "loss": 1.0148, "step": 5004 }, { "epoch": 0.27363745087989066, "grad_norm": 2.450976848602295, "learning_rate": 8.523305067953571e-05, "loss": 1.0878, "step": 5005 }, { "epoch": 0.27369212369724927, "grad_norm": 2.2666714191436768, "learning_rate": 8.522676814494509e-05, "loss": 0.9245, "step": 5006 }, { "epoch": 0.27374679651460787, "grad_norm": 2.4305601119995117, "learning_rate": 8.522048450585018e-05, "loss": 1.2666, "step": 5007 }, { "epoch": 0.27380146933196653, "grad_norm": 2.5321080684661865, "learning_rate": 8.521419976244804e-05, "loss": 1.1752, "step": 5008 }, { "epoch": 0.27385614214932513, "grad_norm": 2.532597303390503, "learning_rate": 8.520791391493573e-05, "loss": 1.0532, "step": 5009 }, { "epoch": 0.27391081496668374, "grad_norm": 2.68082857131958, "learning_rate": 8.520162696351028e-05, "loss": 1.1837, "step": 5010 }, { "epoch": 0.2739654877840424, "grad_norm": 2.6800637245178223, "learning_rate": 8.519533890836887e-05, "loss": 1.0124, "step": 5011 }, { "epoch": 0.274020160601401, "grad_norm": 2.4261558055877686, "learning_rate": 8.518904974970864e-05, "loss": 1.2121, "step": 5012 }, { "epoch": 0.2740748334187596, "grad_norm": 2.5011730194091797, "learning_rate": 8.518275948772676e-05, "loss": 0.9923, "step": 5013 }, { "epoch": 0.2741295062361182, "grad_norm": 2.5352518558502197, "learning_rate": 8.517646812262049e-05, "loss": 1.3001, "step": 5014 }, { "epoch": 0.27418417905347686, "grad_norm": 2.361722946166992, "learning_rate": 8.517017565458707e-05, "loss": 1.0065, "step": 5015 }, { "epoch": 0.27423885187083546, "grad_norm": 2.702282190322876, "learning_rate": 8.516388208382379e-05, "loss": 1.2043, "step": 5016 }, { "epoch": 0.27429352468819407, "grad_norm": 2.118973970413208, "learning_rate": 8.5157587410528e-05, "loss": 1.0197, "step": 5017 }, { "epoch": 0.2743481975055527, "grad_norm": 3.0408427715301514, "learning_rate": 8.515129163489703e-05, "loss": 0.9808, "step": 5018 }, { "epoch": 0.27440287032291133, "grad_norm": 2.230955123901367, "learning_rate": 8.514499475712831e-05, "loss": 1.1518, "step": 5019 }, { "epoch": 0.27445754314026993, "grad_norm": 2.2050764560699463, "learning_rate": 8.513869677741926e-05, "loss": 1.0338, "step": 5020 }, { "epoch": 0.2745122159576286, "grad_norm": 2.7416157722473145, "learning_rate": 8.513239769596734e-05, "loss": 1.2213, "step": 5021 }, { "epoch": 0.2745668887749872, "grad_norm": 2.7076256275177, "learning_rate": 8.512609751297008e-05, "loss": 0.9805, "step": 5022 }, { "epoch": 0.2746215615923458, "grad_norm": 2.374079465866089, "learning_rate": 8.511979622862498e-05, "loss": 1.0658, "step": 5023 }, { "epoch": 0.2746762344097044, "grad_norm": 2.4802863597869873, "learning_rate": 8.511349384312965e-05, "loss": 1.2381, "step": 5024 }, { "epoch": 0.27473090722706306, "grad_norm": 2.399275302886963, "learning_rate": 8.510719035668167e-05, "loss": 1.1788, "step": 5025 }, { "epoch": 0.27478558004442166, "grad_norm": 2.8338353633880615, "learning_rate": 8.510088576947867e-05, "loss": 1.2295, "step": 5026 }, { "epoch": 0.27484025286178027, "grad_norm": 2.2954187393188477, "learning_rate": 8.509458008171836e-05, "loss": 1.2238, "step": 5027 }, { "epoch": 0.2748949256791389, "grad_norm": 2.172905921936035, "learning_rate": 8.508827329359841e-05, "loss": 1.0187, "step": 5028 }, { "epoch": 0.2749495984964975, "grad_norm": 2.501469373703003, "learning_rate": 8.508196540531661e-05, "loss": 1.1878, "step": 5029 }, { "epoch": 0.27500427131385613, "grad_norm": 2.763991117477417, "learning_rate": 8.507565641707069e-05, "loss": 1.1122, "step": 5030 }, { "epoch": 0.2750589441312148, "grad_norm": 3.0261495113372803, "learning_rate": 8.50693463290585e-05, "loss": 1.0841, "step": 5031 }, { "epoch": 0.2751136169485734, "grad_norm": 2.4906818866729736, "learning_rate": 8.506303514147787e-05, "loss": 1.142, "step": 5032 }, { "epoch": 0.275168289765932, "grad_norm": 2.6361756324768066, "learning_rate": 8.505672285452666e-05, "loss": 1.2487, "step": 5033 }, { "epoch": 0.2752229625832906, "grad_norm": 2.7286152839660645, "learning_rate": 8.505040946840284e-05, "loss": 1.1269, "step": 5034 }, { "epoch": 0.27527763540064926, "grad_norm": 2.6119446754455566, "learning_rate": 8.504409498330431e-05, "loss": 1.3175, "step": 5035 }, { "epoch": 0.27533230821800786, "grad_norm": 2.583099842071533, "learning_rate": 8.503777939942909e-05, "loss": 1.1281, "step": 5036 }, { "epoch": 0.27538698103536646, "grad_norm": 2.867318868637085, "learning_rate": 8.503146271697518e-05, "loss": 0.9939, "step": 5037 }, { "epoch": 0.2754416538527251, "grad_norm": 2.8472299575805664, "learning_rate": 8.502514493614062e-05, "loss": 0.9067, "step": 5038 }, { "epoch": 0.2754963266700837, "grad_norm": 2.6429152488708496, "learning_rate": 8.501882605712355e-05, "loss": 0.9424, "step": 5039 }, { "epoch": 0.2755509994874423, "grad_norm": 2.220569133758545, "learning_rate": 8.501250608012203e-05, "loss": 1.2461, "step": 5040 }, { "epoch": 0.27560567230480093, "grad_norm": 2.699000835418701, "learning_rate": 8.500618500533429e-05, "loss": 1.1103, "step": 5041 }, { "epoch": 0.2756603451221596, "grad_norm": 2.644914150238037, "learning_rate": 8.499986283295843e-05, "loss": 1.0867, "step": 5042 }, { "epoch": 0.2757150179395182, "grad_norm": 2.891110897064209, "learning_rate": 8.499353956319275e-05, "loss": 0.9998, "step": 5043 }, { "epoch": 0.2757696907568768, "grad_norm": 2.3852062225341797, "learning_rate": 8.49872151962355e-05, "loss": 1.1841, "step": 5044 }, { "epoch": 0.27582436357423545, "grad_norm": 2.7190215587615967, "learning_rate": 8.498088973228493e-05, "loss": 1.0248, "step": 5045 }, { "epoch": 0.27587903639159406, "grad_norm": 2.8456954956054688, "learning_rate": 8.497456317153942e-05, "loss": 1.3409, "step": 5046 }, { "epoch": 0.27593370920895266, "grad_norm": 2.8916990756988525, "learning_rate": 8.496823551419731e-05, "loss": 1.1893, "step": 5047 }, { "epoch": 0.2759883820263113, "grad_norm": 2.7914414405822754, "learning_rate": 8.4961906760457e-05, "loss": 1.4601, "step": 5048 }, { "epoch": 0.2760430548436699, "grad_norm": 2.864013195037842, "learning_rate": 8.495557691051695e-05, "loss": 1.1537, "step": 5049 }, { "epoch": 0.2760977276610285, "grad_norm": 2.4817347526550293, "learning_rate": 8.494924596457556e-05, "loss": 1.1448, "step": 5050 }, { "epoch": 0.27615240047838713, "grad_norm": 2.93524432182312, "learning_rate": 8.49429139228314e-05, "loss": 1.2245, "step": 5051 }, { "epoch": 0.2762070732957458, "grad_norm": 2.4682300090789795, "learning_rate": 8.493658078548297e-05, "loss": 1.3333, "step": 5052 }, { "epoch": 0.2762617461131044, "grad_norm": 2.6878373622894287, "learning_rate": 8.493024655272885e-05, "loss": 1.0583, "step": 5053 }, { "epoch": 0.276316418930463, "grad_norm": 2.958660840988159, "learning_rate": 8.492391122476764e-05, "loss": 1.2672, "step": 5054 }, { "epoch": 0.27637109174782165, "grad_norm": 2.664010524749756, "learning_rate": 8.491757480179798e-05, "loss": 1.0695, "step": 5055 }, { "epoch": 0.27642576456518025, "grad_norm": 2.550835609436035, "learning_rate": 8.491123728401855e-05, "loss": 1.2885, "step": 5056 }, { "epoch": 0.27648043738253886, "grad_norm": 2.195934534072876, "learning_rate": 8.490489867162805e-05, "loss": 1.1755, "step": 5057 }, { "epoch": 0.2765351101998975, "grad_norm": 2.3720335960388184, "learning_rate": 8.489855896482523e-05, "loss": 1.1274, "step": 5058 }, { "epoch": 0.2765897830172561, "grad_norm": 6.020603656768799, "learning_rate": 8.489221816380886e-05, "loss": 1.4126, "step": 5059 }, { "epoch": 0.2766444558346147, "grad_norm": 2.752396583557129, "learning_rate": 8.488587626877772e-05, "loss": 1.1555, "step": 5060 }, { "epoch": 0.2766991286519733, "grad_norm": 4.32509183883667, "learning_rate": 8.487953327993072e-05, "loss": 1.3684, "step": 5061 }, { "epoch": 0.276753801469332, "grad_norm": 2.395890235900879, "learning_rate": 8.487318919746668e-05, "loss": 1.1856, "step": 5062 }, { "epoch": 0.2768084742866906, "grad_norm": 4.65580415725708, "learning_rate": 8.486684402158455e-05, "loss": 0.928, "step": 5063 }, { "epoch": 0.2768631471040492, "grad_norm": 2.555112361907959, "learning_rate": 8.486049775248326e-05, "loss": 1.3294, "step": 5064 }, { "epoch": 0.27691781992140785, "grad_norm": 2.9054102897644043, "learning_rate": 8.48541503903618e-05, "loss": 1.0173, "step": 5065 }, { "epoch": 0.27697249273876645, "grad_norm": 2.3449976444244385, "learning_rate": 8.484780193541918e-05, "loss": 1.1762, "step": 5066 }, { "epoch": 0.27702716555612505, "grad_norm": 2.3496086597442627, "learning_rate": 8.484145238785443e-05, "loss": 1.1068, "step": 5067 }, { "epoch": 0.27708183837348366, "grad_norm": 2.3337554931640625, "learning_rate": 8.483510174786667e-05, "loss": 1.0834, "step": 5068 }, { "epoch": 0.2771365111908423, "grad_norm": 2.3054258823394775, "learning_rate": 8.4828750015655e-05, "loss": 1.0887, "step": 5069 }, { "epoch": 0.2771911840082009, "grad_norm": 3.6761555671691895, "learning_rate": 8.482239719141859e-05, "loss": 0.9069, "step": 5070 }, { "epoch": 0.2772458568255595, "grad_norm": 2.3712806701660156, "learning_rate": 8.481604327535659e-05, "loss": 1.2438, "step": 5071 }, { "epoch": 0.2773005296429182, "grad_norm": 2.4491374492645264, "learning_rate": 8.480968826766826e-05, "loss": 1.1228, "step": 5072 }, { "epoch": 0.2773552024602768, "grad_norm": 2.9201576709747314, "learning_rate": 8.480333216855286e-05, "loss": 1.2356, "step": 5073 }, { "epoch": 0.2774098752776354, "grad_norm": 2.500805139541626, "learning_rate": 8.479697497820964e-05, "loss": 1.0721, "step": 5074 }, { "epoch": 0.27746454809499405, "grad_norm": 4.7744364738464355, "learning_rate": 8.479061669683794e-05, "loss": 1.0431, "step": 5075 }, { "epoch": 0.27751922091235265, "grad_norm": 2.637723684310913, "learning_rate": 8.478425732463714e-05, "loss": 1.1077, "step": 5076 }, { "epoch": 0.27757389372971125, "grad_norm": 2.6556150913238525, "learning_rate": 8.47778968618066e-05, "loss": 1.1163, "step": 5077 }, { "epoch": 0.27762856654706985, "grad_norm": 2.7894856929779053, "learning_rate": 8.477153530854577e-05, "loss": 1.0947, "step": 5078 }, { "epoch": 0.2776832393644285, "grad_norm": 2.124701976776123, "learning_rate": 8.476517266505412e-05, "loss": 0.9509, "step": 5079 }, { "epoch": 0.2777379121817871, "grad_norm": 2.7635931968688965, "learning_rate": 8.475880893153113e-05, "loss": 0.8125, "step": 5080 }, { "epoch": 0.2777925849991457, "grad_norm": 2.1673507690429688, "learning_rate": 8.47524441081763e-05, "loss": 1.1185, "step": 5081 }, { "epoch": 0.2778472578165044, "grad_norm": 4.1646809577941895, "learning_rate": 8.474607819518922e-05, "loss": 0.9456, "step": 5082 }, { "epoch": 0.277901930633863, "grad_norm": 2.527855634689331, "learning_rate": 8.473971119276951e-05, "loss": 0.8754, "step": 5083 }, { "epoch": 0.2779566034512216, "grad_norm": 2.4250710010528564, "learning_rate": 8.473334310111678e-05, "loss": 0.9438, "step": 5084 }, { "epoch": 0.27801127626858024, "grad_norm": 2.9421534538269043, "learning_rate": 8.47269739204307e-05, "loss": 0.9971, "step": 5085 }, { "epoch": 0.27806594908593885, "grad_norm": 3.331083297729492, "learning_rate": 8.472060365091096e-05, "loss": 1.3052, "step": 5086 }, { "epoch": 0.27812062190329745, "grad_norm": 2.365077018737793, "learning_rate": 8.471423229275728e-05, "loss": 0.9689, "step": 5087 }, { "epoch": 0.27817529472065605, "grad_norm": 2.148465871810913, "learning_rate": 8.470785984616949e-05, "loss": 1.1306, "step": 5088 }, { "epoch": 0.2782299675380147, "grad_norm": 2.728649616241455, "learning_rate": 8.470148631134733e-05, "loss": 1.1836, "step": 5089 }, { "epoch": 0.2782846403553733, "grad_norm": 2.9314863681793213, "learning_rate": 8.469511168849065e-05, "loss": 1.2541, "step": 5090 }, { "epoch": 0.2783393131727319, "grad_norm": 2.6225695610046387, "learning_rate": 8.468873597779933e-05, "loss": 1.2158, "step": 5091 }, { "epoch": 0.2783939859900906, "grad_norm": 2.1524295806884766, "learning_rate": 8.468235917947329e-05, "loss": 1.0728, "step": 5092 }, { "epoch": 0.2784486588074492, "grad_norm": 2.435016393661499, "learning_rate": 8.467598129371246e-05, "loss": 1.1148, "step": 5093 }, { "epoch": 0.2785033316248078, "grad_norm": 2.5244758129119873, "learning_rate": 8.466960232071679e-05, "loss": 0.9859, "step": 5094 }, { "epoch": 0.2785580044421664, "grad_norm": 3.0673232078552246, "learning_rate": 8.466322226068631e-05, "loss": 1.2287, "step": 5095 }, { "epoch": 0.27861267725952504, "grad_norm": 2.23364520072937, "learning_rate": 8.465684111382103e-05, "loss": 1.0155, "step": 5096 }, { "epoch": 0.27866735007688365, "grad_norm": 1.8428107500076294, "learning_rate": 8.465045888032108e-05, "loss": 0.8844, "step": 5097 }, { "epoch": 0.27872202289424225, "grad_norm": 2.858121395111084, "learning_rate": 8.464407556038652e-05, "loss": 1.3217, "step": 5098 }, { "epoch": 0.2787766957116009, "grad_norm": 2.597019672393799, "learning_rate": 8.463769115421751e-05, "loss": 0.8853, "step": 5099 }, { "epoch": 0.2788313685289595, "grad_norm": 2.3040199279785156, "learning_rate": 8.463130566201425e-05, "loss": 1.0189, "step": 5100 }, { "epoch": 0.2788860413463181, "grad_norm": 2.6220147609710693, "learning_rate": 8.462491908397692e-05, "loss": 1.298, "step": 5101 }, { "epoch": 0.2789407141636768, "grad_norm": 2.7186777591705322, "learning_rate": 8.461853142030579e-05, "loss": 1.0639, "step": 5102 }, { "epoch": 0.2789953869810354, "grad_norm": 2.0502047538757324, "learning_rate": 8.46121426712011e-05, "loss": 0.9211, "step": 5103 }, { "epoch": 0.279050059798394, "grad_norm": 2.3583571910858154, "learning_rate": 8.46057528368632e-05, "loss": 1.0797, "step": 5104 }, { "epoch": 0.2791047326157526, "grad_norm": 2.130281686782837, "learning_rate": 8.459936191749243e-05, "loss": 0.9557, "step": 5105 }, { "epoch": 0.27915940543311124, "grad_norm": 2.6379270553588867, "learning_rate": 8.459296991328915e-05, "loss": 1.198, "step": 5106 }, { "epoch": 0.27921407825046984, "grad_norm": 3.732069253921509, "learning_rate": 8.458657682445382e-05, "loss": 1.2423, "step": 5107 }, { "epoch": 0.27926875106782845, "grad_norm": 2.3671557903289795, "learning_rate": 8.458018265118685e-05, "loss": 1.1066, "step": 5108 }, { "epoch": 0.2793234238851871, "grad_norm": 2.8071062564849854, "learning_rate": 8.457378739368875e-05, "loss": 1.2221, "step": 5109 }, { "epoch": 0.2793780967025457, "grad_norm": 2.8447494506835938, "learning_rate": 8.456739105216003e-05, "loss": 1.1555, "step": 5110 }, { "epoch": 0.2794327695199043, "grad_norm": 3.0282158851623535, "learning_rate": 8.456099362680122e-05, "loss": 1.0615, "step": 5111 }, { "epoch": 0.2794874423372629, "grad_norm": 2.2433602809906006, "learning_rate": 8.455459511781292e-05, "loss": 1.1048, "step": 5112 }, { "epoch": 0.2795421151546216, "grad_norm": 2.9509499073028564, "learning_rate": 8.454819552539576e-05, "loss": 1.077, "step": 5113 }, { "epoch": 0.2795967879719802, "grad_norm": 2.1848111152648926, "learning_rate": 8.454179484975039e-05, "loss": 1.1481, "step": 5114 }, { "epoch": 0.2796514607893388, "grad_norm": 3.103022336959839, "learning_rate": 8.45353930910775e-05, "loss": 1.2321, "step": 5115 }, { "epoch": 0.27970613360669744, "grad_norm": 2.842398166656494, "learning_rate": 8.452899024957779e-05, "loss": 1.1195, "step": 5116 }, { "epoch": 0.27976080642405604, "grad_norm": 2.6293206214904785, "learning_rate": 8.452258632545202e-05, "loss": 1.1079, "step": 5117 }, { "epoch": 0.27981547924141464, "grad_norm": 2.660728693008423, "learning_rate": 8.451618131890102e-05, "loss": 1.0685, "step": 5118 }, { "epoch": 0.2798701520587733, "grad_norm": 3.5090417861938477, "learning_rate": 8.450977523012556e-05, "loss": 1.067, "step": 5119 }, { "epoch": 0.2799248248761319, "grad_norm": 2.3419008255004883, "learning_rate": 8.450336805932652e-05, "loss": 1.1706, "step": 5120 }, { "epoch": 0.2799794976934905, "grad_norm": 4.337882041931152, "learning_rate": 8.44969598067048e-05, "loss": 1.2499, "step": 5121 }, { "epoch": 0.2800341705108491, "grad_norm": 2.1792430877685547, "learning_rate": 8.449055047246133e-05, "loss": 0.9313, "step": 5122 }, { "epoch": 0.28008884332820777, "grad_norm": 4.166155815124512, "learning_rate": 8.448414005679704e-05, "loss": 1.1685, "step": 5123 }, { "epoch": 0.2801435161455664, "grad_norm": 2.082028865814209, "learning_rate": 8.447772855991294e-05, "loss": 1.0972, "step": 5124 }, { "epoch": 0.280198188962925, "grad_norm": 2.229287624359131, "learning_rate": 8.447131598201006e-05, "loss": 1.0973, "step": 5125 }, { "epoch": 0.28025286178028364, "grad_norm": 2.193939447402954, "learning_rate": 8.446490232328945e-05, "loss": 0.8307, "step": 5126 }, { "epoch": 0.28030753459764224, "grad_norm": 2.7116174697875977, "learning_rate": 8.44584875839522e-05, "loss": 1.0538, "step": 5127 }, { "epoch": 0.28036220741500084, "grad_norm": 2.6155810356140137, "learning_rate": 8.445207176419947e-05, "loss": 1.2045, "step": 5128 }, { "epoch": 0.2804168802323595, "grad_norm": 5.4033050537109375, "learning_rate": 8.44456548642324e-05, "loss": 0.975, "step": 5129 }, { "epoch": 0.2804715530497181, "grad_norm": 2.56773042678833, "learning_rate": 8.44392368842522e-05, "loss": 1.2799, "step": 5130 }, { "epoch": 0.2805262258670767, "grad_norm": 2.787919282913208, "learning_rate": 8.443281782446006e-05, "loss": 1.3427, "step": 5131 }, { "epoch": 0.2805808986844353, "grad_norm": 3.4435088634490967, "learning_rate": 8.442639768505727e-05, "loss": 1.2418, "step": 5132 }, { "epoch": 0.28063557150179397, "grad_norm": 2.4338207244873047, "learning_rate": 8.441997646624515e-05, "loss": 1.0138, "step": 5133 }, { "epoch": 0.28069024431915257, "grad_norm": 2.2592012882232666, "learning_rate": 8.4413554168225e-05, "loss": 0.9734, "step": 5134 }, { "epoch": 0.2807449171365112, "grad_norm": 3.582221746444702, "learning_rate": 8.44071307911982e-05, "loss": 1.2245, "step": 5135 }, { "epoch": 0.28079958995386983, "grad_norm": 2.352402687072754, "learning_rate": 8.440070633536614e-05, "loss": 1.1399, "step": 5136 }, { "epoch": 0.28085426277122844, "grad_norm": 2.2099502086639404, "learning_rate": 8.439428080093028e-05, "loss": 1.1821, "step": 5137 }, { "epoch": 0.28090893558858704, "grad_norm": 2.689732551574707, "learning_rate": 8.438785418809205e-05, "loss": 1.1203, "step": 5138 }, { "epoch": 0.28096360840594564, "grad_norm": 2.257779598236084, "learning_rate": 8.438142649705297e-05, "loss": 1.1508, "step": 5139 }, { "epoch": 0.2810182812233043, "grad_norm": 2.789076328277588, "learning_rate": 8.437499772801458e-05, "loss": 1.1112, "step": 5140 }, { "epoch": 0.2810729540406629, "grad_norm": 2.5146842002868652, "learning_rate": 8.436856788117842e-05, "loss": 1.1777, "step": 5141 }, { "epoch": 0.2811276268580215, "grad_norm": 2.493098258972168, "learning_rate": 8.436213695674613e-05, "loss": 1.0581, "step": 5142 }, { "epoch": 0.28118229967538017, "grad_norm": 2.0107407569885254, "learning_rate": 8.435570495491932e-05, "loss": 0.9589, "step": 5143 }, { "epoch": 0.28123697249273877, "grad_norm": 2.8750977516174316, "learning_rate": 8.434927187589967e-05, "loss": 1.3509, "step": 5144 }, { "epoch": 0.28129164531009737, "grad_norm": 3.1033105850219727, "learning_rate": 8.434283771988889e-05, "loss": 1.1819, "step": 5145 }, { "epoch": 0.28134631812745603, "grad_norm": 2.1956348419189453, "learning_rate": 8.433640248708869e-05, "loss": 1.1542, "step": 5146 }, { "epoch": 0.28140099094481463, "grad_norm": 2.6131954193115234, "learning_rate": 8.432996617770089e-05, "loss": 0.9691, "step": 5147 }, { "epoch": 0.28145566376217324, "grad_norm": 3.0640170574188232, "learning_rate": 8.432352879192724e-05, "loss": 1.3533, "step": 5148 }, { "epoch": 0.28151033657953184, "grad_norm": 2.193330764770508, "learning_rate": 8.43170903299696e-05, "loss": 0.9837, "step": 5149 }, { "epoch": 0.2815650093968905, "grad_norm": 2.1313321590423584, "learning_rate": 8.431065079202987e-05, "loss": 1.0857, "step": 5150 }, { "epoch": 0.2816196822142491, "grad_norm": 2.4758431911468506, "learning_rate": 8.430421017830991e-05, "loss": 1.137, "step": 5151 }, { "epoch": 0.2816743550316077, "grad_norm": 2.7016685009002686, "learning_rate": 8.429776848901168e-05, "loss": 1.0408, "step": 5152 }, { "epoch": 0.28172902784896636, "grad_norm": 2.9435107707977295, "learning_rate": 8.429132572433717e-05, "loss": 1.0028, "step": 5153 }, { "epoch": 0.28178370066632497, "grad_norm": 2.367995262145996, "learning_rate": 8.428488188448836e-05, "loss": 1.117, "step": 5154 }, { "epoch": 0.28183837348368357, "grad_norm": 2.689401626586914, "learning_rate": 8.427843696966731e-05, "loss": 1.2441, "step": 5155 }, { "epoch": 0.2818930463010422, "grad_norm": 2.58204984664917, "learning_rate": 8.427199098007608e-05, "loss": 0.9163, "step": 5156 }, { "epoch": 0.28194771911840083, "grad_norm": 2.21705961227417, "learning_rate": 8.42655439159168e-05, "loss": 1.2097, "step": 5157 }, { "epoch": 0.28200239193575943, "grad_norm": 2.103057384490967, "learning_rate": 8.42590957773916e-05, "loss": 1.1989, "step": 5158 }, { "epoch": 0.28205706475311804, "grad_norm": 3.0787465572357178, "learning_rate": 8.425264656470264e-05, "loss": 1.0609, "step": 5159 }, { "epoch": 0.2821117375704767, "grad_norm": 2.89937162399292, "learning_rate": 8.424619627805213e-05, "loss": 1.2668, "step": 5160 }, { "epoch": 0.2821664103878353, "grad_norm": 2.21540904045105, "learning_rate": 8.423974491764235e-05, "loss": 1.1657, "step": 5161 }, { "epoch": 0.2822210832051939, "grad_norm": 3.131870985031128, "learning_rate": 8.423329248367554e-05, "loss": 1.157, "step": 5162 }, { "epoch": 0.28227575602255256, "grad_norm": 2.281013250350952, "learning_rate": 8.422683897635404e-05, "loss": 1.1099, "step": 5163 }, { "epoch": 0.28233042883991116, "grad_norm": 2.103410005569458, "learning_rate": 8.422038439588016e-05, "loss": 0.8759, "step": 5164 }, { "epoch": 0.28238510165726977, "grad_norm": 2.378037452697754, "learning_rate": 8.421392874245629e-05, "loss": 1.1978, "step": 5165 }, { "epoch": 0.28243977447462837, "grad_norm": 2.191105365753174, "learning_rate": 8.420747201628487e-05, "loss": 0.9528, "step": 5166 }, { "epoch": 0.282494447291987, "grad_norm": 3.9646806716918945, "learning_rate": 8.42010142175683e-05, "loss": 1.0897, "step": 5167 }, { "epoch": 0.28254912010934563, "grad_norm": 2.2995259761810303, "learning_rate": 8.419455534650908e-05, "loss": 0.8262, "step": 5168 }, { "epoch": 0.28260379292670423, "grad_norm": 2.409073829650879, "learning_rate": 8.418809540330974e-05, "loss": 0.9227, "step": 5169 }, { "epoch": 0.2826584657440629, "grad_norm": 2.5460071563720703, "learning_rate": 8.41816343881728e-05, "loss": 1.2961, "step": 5170 }, { "epoch": 0.2827131385614215, "grad_norm": 1.873321533203125, "learning_rate": 8.417517230130083e-05, "loss": 0.9281, "step": 5171 }, { "epoch": 0.2827678113787801, "grad_norm": 3.2767174243927, "learning_rate": 8.416870914289647e-05, "loss": 0.9748, "step": 5172 }, { "epoch": 0.28282248419613876, "grad_norm": 2.427783489227295, "learning_rate": 8.416224491316238e-05, "loss": 1.1287, "step": 5173 }, { "epoch": 0.28287715701349736, "grad_norm": 2.348073720932007, "learning_rate": 8.415577961230119e-05, "loss": 1.2376, "step": 5174 }, { "epoch": 0.28293182983085596, "grad_norm": 2.396773338317871, "learning_rate": 8.414931324051565e-05, "loss": 0.8871, "step": 5175 }, { "epoch": 0.28298650264821457, "grad_norm": 2.5120511054992676, "learning_rate": 8.414284579800849e-05, "loss": 1.1728, "step": 5176 }, { "epoch": 0.2830411754655732, "grad_norm": 3.1105799674987793, "learning_rate": 8.413637728498252e-05, "loss": 0.8891, "step": 5177 }, { "epoch": 0.28309584828293183, "grad_norm": 2.796635627746582, "learning_rate": 8.41299077016405e-05, "loss": 1.2817, "step": 5178 }, { "epoch": 0.28315052110029043, "grad_norm": 4.320777416229248, "learning_rate": 8.412343704818536e-05, "loss": 1.3692, "step": 5179 }, { "epoch": 0.2832051939176491, "grad_norm": 2.699566125869751, "learning_rate": 8.41169653248199e-05, "loss": 1.1045, "step": 5180 }, { "epoch": 0.2832598667350077, "grad_norm": 2.139476776123047, "learning_rate": 8.411049253174707e-05, "loss": 0.8937, "step": 5181 }, { "epoch": 0.2833145395523663, "grad_norm": 2.4423370361328125, "learning_rate": 8.410401866916981e-05, "loss": 1.0526, "step": 5182 }, { "epoch": 0.28336921236972495, "grad_norm": 2.2680845260620117, "learning_rate": 8.409754373729113e-05, "loss": 1.184, "step": 5183 }, { "epoch": 0.28342388518708356, "grad_norm": 2.265536069869995, "learning_rate": 8.409106773631403e-05, "loss": 1.1775, "step": 5184 }, { "epoch": 0.28347855800444216, "grad_norm": 2.6922645568847656, "learning_rate": 8.408459066644152e-05, "loss": 1.2426, "step": 5185 }, { "epoch": 0.28353323082180076, "grad_norm": 3.3551597595214844, "learning_rate": 8.407811252787675e-05, "loss": 1.1568, "step": 5186 }, { "epoch": 0.2835879036391594, "grad_norm": 3.17944598197937, "learning_rate": 8.40716333208228e-05, "loss": 1.2523, "step": 5187 }, { "epoch": 0.283642576456518, "grad_norm": 3.551523208618164, "learning_rate": 8.406515304548281e-05, "loss": 1.1773, "step": 5188 }, { "epoch": 0.28369724927387663, "grad_norm": 2.2144556045532227, "learning_rate": 8.405867170205998e-05, "loss": 1.0163, "step": 5189 }, { "epoch": 0.2837519220912353, "grad_norm": 2.1207234859466553, "learning_rate": 8.405218929075754e-05, "loss": 1.0805, "step": 5190 }, { "epoch": 0.2838065949085939, "grad_norm": 2.3739564418792725, "learning_rate": 8.40457058117787e-05, "loss": 1.1743, "step": 5191 }, { "epoch": 0.2838612677259525, "grad_norm": 3.0141053199768066, "learning_rate": 8.403922126532678e-05, "loss": 1.1516, "step": 5192 }, { "epoch": 0.2839159405433111, "grad_norm": 3.0440573692321777, "learning_rate": 8.40327356516051e-05, "loss": 1.3574, "step": 5193 }, { "epoch": 0.28397061336066975, "grad_norm": 3.194547414779663, "learning_rate": 8.402624897081697e-05, "loss": 1.2138, "step": 5194 }, { "epoch": 0.28402528617802836, "grad_norm": 3.010207414627075, "learning_rate": 8.401976122316581e-05, "loss": 1.3333, "step": 5195 }, { "epoch": 0.28407995899538696, "grad_norm": 2.6590118408203125, "learning_rate": 8.401327240885503e-05, "loss": 1.2175, "step": 5196 }, { "epoch": 0.2841346318127456, "grad_norm": 2.265758514404297, "learning_rate": 8.400678252808809e-05, "loss": 0.8764, "step": 5197 }, { "epoch": 0.2841893046301042, "grad_norm": 2.881092071533203, "learning_rate": 8.400029158106844e-05, "loss": 1.0306, "step": 5198 }, { "epoch": 0.2842439774474628, "grad_norm": 2.489093065261841, "learning_rate": 8.399379956799963e-05, "loss": 1.0633, "step": 5199 }, { "epoch": 0.2842986502648215, "grad_norm": 3.2921993732452393, "learning_rate": 8.39873064890852e-05, "loss": 1.2466, "step": 5200 }, { "epoch": 0.2843533230821801, "grad_norm": 2.8564376831054688, "learning_rate": 8.398081234452875e-05, "loss": 1.09, "step": 5201 }, { "epoch": 0.2844079958995387, "grad_norm": 2.350032091140747, "learning_rate": 8.397431713453388e-05, "loss": 0.9364, "step": 5202 }, { "epoch": 0.2844626687168973, "grad_norm": 2.634772539138794, "learning_rate": 8.396782085930424e-05, "loss": 1.2177, "step": 5203 }, { "epoch": 0.28451734153425595, "grad_norm": 2.40794038772583, "learning_rate": 8.396132351904352e-05, "loss": 0.8673, "step": 5204 }, { "epoch": 0.28457201435161456, "grad_norm": 2.7848868370056152, "learning_rate": 8.395482511395545e-05, "loss": 1.0863, "step": 5205 }, { "epoch": 0.28462668716897316, "grad_norm": 3.0151143074035645, "learning_rate": 8.394832564424377e-05, "loss": 1.1724, "step": 5206 }, { "epoch": 0.2846813599863318, "grad_norm": 2.5012173652648926, "learning_rate": 8.394182511011226e-05, "loss": 1.1174, "step": 5207 }, { "epoch": 0.2847360328036904, "grad_norm": 3.14284610748291, "learning_rate": 8.393532351176477e-05, "loss": 0.964, "step": 5208 }, { "epoch": 0.284790705621049, "grad_norm": 2.4738259315490723, "learning_rate": 8.392882084940509e-05, "loss": 0.9907, "step": 5209 }, { "epoch": 0.2848453784384077, "grad_norm": 2.7212815284729004, "learning_rate": 8.392231712323716e-05, "loss": 1.2968, "step": 5210 }, { "epoch": 0.2849000512557663, "grad_norm": 2.506307601928711, "learning_rate": 8.391581233346488e-05, "loss": 1.1032, "step": 5211 }, { "epoch": 0.2849547240731249, "grad_norm": 1.9373711347579956, "learning_rate": 8.390930648029221e-05, "loss": 1.0013, "step": 5212 }, { "epoch": 0.2850093968904835, "grad_norm": 2.3904058933258057, "learning_rate": 8.390279956392312e-05, "loss": 1.1501, "step": 5213 }, { "epoch": 0.28506406970784215, "grad_norm": 2.4516191482543945, "learning_rate": 8.389629158456164e-05, "loss": 0.9893, "step": 5214 }, { "epoch": 0.28511874252520075, "grad_norm": 2.2828643321990967, "learning_rate": 8.388978254241182e-05, "loss": 1.1123, "step": 5215 }, { "epoch": 0.28517341534255936, "grad_norm": 2.109281301498413, "learning_rate": 8.388327243767775e-05, "loss": 1.0782, "step": 5216 }, { "epoch": 0.285228088159918, "grad_norm": 2.9303321838378906, "learning_rate": 8.387676127056354e-05, "loss": 0.9415, "step": 5217 }, { "epoch": 0.2852827609772766, "grad_norm": 2.827918529510498, "learning_rate": 8.387024904127334e-05, "loss": 1.1223, "step": 5218 }, { "epoch": 0.2853374337946352, "grad_norm": 2.576017379760742, "learning_rate": 8.386373575001134e-05, "loss": 1.1776, "step": 5219 }, { "epoch": 0.2853921066119938, "grad_norm": 2.0014731884002686, "learning_rate": 8.385722139698178e-05, "loss": 1.1279, "step": 5220 }, { "epoch": 0.2854467794293525, "grad_norm": 2.7928590774536133, "learning_rate": 8.385070598238886e-05, "loss": 0.9593, "step": 5221 }, { "epoch": 0.2855014522467111, "grad_norm": 2.9638583660125732, "learning_rate": 8.384418950643692e-05, "loss": 1.2012, "step": 5222 }, { "epoch": 0.2855561250640697, "grad_norm": 2.502074956893921, "learning_rate": 8.383767196933024e-05, "loss": 1.2539, "step": 5223 }, { "epoch": 0.28561079788142835, "grad_norm": 2.6914288997650146, "learning_rate": 8.383115337127319e-05, "loss": 1.0895, "step": 5224 }, { "epoch": 0.28566547069878695, "grad_norm": 2.49763560295105, "learning_rate": 8.382463371247014e-05, "loss": 1.2849, "step": 5225 }, { "epoch": 0.28572014351614555, "grad_norm": 2.4348556995391846, "learning_rate": 8.381811299312555e-05, "loss": 1.3452, "step": 5226 }, { "epoch": 0.2857748163335042, "grad_norm": 3.2745261192321777, "learning_rate": 8.38115912134438e-05, "loss": 1.0962, "step": 5227 }, { "epoch": 0.2858294891508628, "grad_norm": 2.1190242767333984, "learning_rate": 8.380506837362943e-05, "loss": 1.0589, "step": 5228 }, { "epoch": 0.2858841619682214, "grad_norm": 2.2104432582855225, "learning_rate": 8.379854447388696e-05, "loss": 1.1607, "step": 5229 }, { "epoch": 0.28593883478558, "grad_norm": 2.2497479915618896, "learning_rate": 8.379201951442091e-05, "loss": 0.9605, "step": 5230 }, { "epoch": 0.2859935076029387, "grad_norm": 2.0738770961761475, "learning_rate": 8.378549349543588e-05, "loss": 0.8789, "step": 5231 }, { "epoch": 0.2860481804202973, "grad_norm": 2.6751370429992676, "learning_rate": 8.377896641713647e-05, "loss": 1.1484, "step": 5232 }, { "epoch": 0.2861028532376559, "grad_norm": 2.41291880607605, "learning_rate": 8.377243827972737e-05, "loss": 1.1065, "step": 5233 }, { "epoch": 0.28615752605501454, "grad_norm": 1.9093513488769531, "learning_rate": 8.376590908341322e-05, "loss": 0.9473, "step": 5234 }, { "epoch": 0.28621219887237315, "grad_norm": 3.2789270877838135, "learning_rate": 8.375937882839877e-05, "loss": 1.3025, "step": 5235 }, { "epoch": 0.28626687168973175, "grad_norm": 2.5652496814727783, "learning_rate": 8.375284751488876e-05, "loss": 1.0785, "step": 5236 }, { "epoch": 0.2863215445070904, "grad_norm": 2.351511240005493, "learning_rate": 8.374631514308796e-05, "loss": 1.1249, "step": 5237 }, { "epoch": 0.286376217324449, "grad_norm": 2.2916646003723145, "learning_rate": 8.37397817132012e-05, "loss": 1.1439, "step": 5238 }, { "epoch": 0.2864308901418076, "grad_norm": 2.1854279041290283, "learning_rate": 8.373324722543334e-05, "loss": 1.0632, "step": 5239 }, { "epoch": 0.2864855629591662, "grad_norm": 3.212433099746704, "learning_rate": 8.372671167998925e-05, "loss": 1.1102, "step": 5240 }, { "epoch": 0.2865402357765249, "grad_norm": 3.0547537803649902, "learning_rate": 8.372017507707384e-05, "loss": 0.8694, "step": 5241 }, { "epoch": 0.2865949085938835, "grad_norm": 2.4799535274505615, "learning_rate": 8.371363741689207e-05, "loss": 1.1896, "step": 5242 }, { "epoch": 0.2866495814112421, "grad_norm": 2.5727009773254395, "learning_rate": 8.370709869964892e-05, "loss": 1.0903, "step": 5243 }, { "epoch": 0.28670425422860074, "grad_norm": 2.684492349624634, "learning_rate": 8.37005589255494e-05, "loss": 1.2565, "step": 5244 }, { "epoch": 0.28675892704595934, "grad_norm": 3.3883371353149414, "learning_rate": 8.369401809479857e-05, "loss": 1.1852, "step": 5245 }, { "epoch": 0.28681359986331795, "grad_norm": 2.5409040451049805, "learning_rate": 8.368747620760151e-05, "loss": 1.0751, "step": 5246 }, { "epoch": 0.28686827268067655, "grad_norm": 2.385312557220459, "learning_rate": 8.368093326416334e-05, "loss": 1.2728, "step": 5247 }, { "epoch": 0.2869229454980352, "grad_norm": 2.7969038486480713, "learning_rate": 8.367438926468918e-05, "loss": 1.1929, "step": 5248 }, { "epoch": 0.2869776183153938, "grad_norm": 2.4447836875915527, "learning_rate": 8.366784420938423e-05, "loss": 1.1666, "step": 5249 }, { "epoch": 0.2870322911327524, "grad_norm": 2.3023808002471924, "learning_rate": 8.366129809845372e-05, "loss": 0.975, "step": 5250 }, { "epoch": 0.2870869639501111, "grad_norm": 2.3287034034729004, "learning_rate": 8.365475093210286e-05, "loss": 1.1971, "step": 5251 }, { "epoch": 0.2871416367674697, "grad_norm": 2.366878032684326, "learning_rate": 8.364820271053698e-05, "loss": 0.913, "step": 5252 }, { "epoch": 0.2871963095848283, "grad_norm": 2.3403408527374268, "learning_rate": 8.364165343396135e-05, "loss": 1.2479, "step": 5253 }, { "epoch": 0.28725098240218694, "grad_norm": 2.1392123699188232, "learning_rate": 8.363510310258134e-05, "loss": 1.0284, "step": 5254 }, { "epoch": 0.28730565521954554, "grad_norm": 2.5286004543304443, "learning_rate": 8.362855171660233e-05, "loss": 0.763, "step": 5255 }, { "epoch": 0.28736032803690414, "grad_norm": 2.2663590908050537, "learning_rate": 8.362199927622972e-05, "loss": 1.0847, "step": 5256 }, { "epoch": 0.28741500085426275, "grad_norm": 2.9264516830444336, "learning_rate": 8.361544578166898e-05, "loss": 1.052, "step": 5257 }, { "epoch": 0.2874696736716214, "grad_norm": 2.8588919639587402, "learning_rate": 8.360889123312554e-05, "loss": 1.0865, "step": 5258 }, { "epoch": 0.28752434648898, "grad_norm": 3.3576724529266357, "learning_rate": 8.360233563080496e-05, "loss": 1.2307, "step": 5259 }, { "epoch": 0.2875790193063386, "grad_norm": 2.181886911392212, "learning_rate": 8.359577897491277e-05, "loss": 1.1619, "step": 5260 }, { "epoch": 0.28763369212369727, "grad_norm": 2.5593008995056152, "learning_rate": 8.358922126565455e-05, "loss": 1.0949, "step": 5261 }, { "epoch": 0.2876883649410559, "grad_norm": 2.3792049884796143, "learning_rate": 8.358266250323589e-05, "loss": 0.8912, "step": 5262 }, { "epoch": 0.2877430377584145, "grad_norm": 2.6123390197753906, "learning_rate": 8.357610268786247e-05, "loss": 1.0283, "step": 5263 }, { "epoch": 0.2877977105757731, "grad_norm": 2.3426003456115723, "learning_rate": 8.356954181973995e-05, "loss": 1.1381, "step": 5264 }, { "epoch": 0.28785238339313174, "grad_norm": 2.7070627212524414, "learning_rate": 8.356297989907404e-05, "loss": 1.079, "step": 5265 }, { "epoch": 0.28790705621049034, "grad_norm": 2.2185771465301514, "learning_rate": 8.355641692607047e-05, "loss": 1.0494, "step": 5266 }, { "epoch": 0.28796172902784894, "grad_norm": 2.463094711303711, "learning_rate": 8.354985290093505e-05, "loss": 1.0586, "step": 5267 }, { "epoch": 0.2880164018452076, "grad_norm": 2.3829524517059326, "learning_rate": 8.354328782387355e-05, "loss": 1.0592, "step": 5268 }, { "epoch": 0.2880710746625662, "grad_norm": 2.9655730724334717, "learning_rate": 8.353672169509185e-05, "loss": 1.1445, "step": 5269 }, { "epoch": 0.2881257474799248, "grad_norm": 2.131852388381958, "learning_rate": 8.35301545147958e-05, "loss": 0.9746, "step": 5270 }, { "epoch": 0.28818042029728347, "grad_norm": 2.325986385345459, "learning_rate": 8.35235862831913e-05, "loss": 1.0272, "step": 5271 }, { "epoch": 0.28823509311464207, "grad_norm": 2.1663711071014404, "learning_rate": 8.351701700048433e-05, "loss": 0.9828, "step": 5272 }, { "epoch": 0.2882897659320007, "grad_norm": 2.5125341415405273, "learning_rate": 8.351044666688081e-05, "loss": 1.148, "step": 5273 }, { "epoch": 0.2883444387493593, "grad_norm": 4.116685390472412, "learning_rate": 8.35038752825868e-05, "loss": 1.1989, "step": 5274 }, { "epoch": 0.28839911156671794, "grad_norm": 2.652294874191284, "learning_rate": 8.34973028478083e-05, "loss": 1.1931, "step": 5275 }, { "epoch": 0.28845378438407654, "grad_norm": 3.1073830127716064, "learning_rate": 8.349072936275142e-05, "loss": 1.1085, "step": 5276 }, { "epoch": 0.28850845720143514, "grad_norm": 4.436819553375244, "learning_rate": 8.348415482762223e-05, "loss": 1.3516, "step": 5277 }, { "epoch": 0.2885631300187938, "grad_norm": 2.3073220252990723, "learning_rate": 8.347757924262689e-05, "loss": 1.0096, "step": 5278 }, { "epoch": 0.2886178028361524, "grad_norm": 2.2284040451049805, "learning_rate": 8.347100260797157e-05, "loss": 1.1286, "step": 5279 }, { "epoch": 0.288672475653511, "grad_norm": 2.844322443008423, "learning_rate": 8.346442492386245e-05, "loss": 1.2603, "step": 5280 }, { "epoch": 0.28872714847086967, "grad_norm": 2.7568931579589844, "learning_rate": 8.34578461905058e-05, "loss": 0.9711, "step": 5281 }, { "epoch": 0.28878182128822827, "grad_norm": 1.9000803232192993, "learning_rate": 8.345126640810788e-05, "loss": 1.0924, "step": 5282 }, { "epoch": 0.28883649410558687, "grad_norm": 2.633620500564575, "learning_rate": 8.3444685576875e-05, "loss": 1.1692, "step": 5283 }, { "epoch": 0.2888911669229455, "grad_norm": 3.4660515785217285, "learning_rate": 8.343810369701346e-05, "loss": 1.193, "step": 5284 }, { "epoch": 0.28894583974030413, "grad_norm": 3.470543146133423, "learning_rate": 8.343152076872967e-05, "loss": 0.9778, "step": 5285 }, { "epoch": 0.28900051255766274, "grad_norm": 2.60246205329895, "learning_rate": 8.342493679223003e-05, "loss": 1.1419, "step": 5286 }, { "epoch": 0.28905518537502134, "grad_norm": 2.266869068145752, "learning_rate": 8.341835176772096e-05, "loss": 1.0962, "step": 5287 }, { "epoch": 0.28910985819238, "grad_norm": 2.9197235107421875, "learning_rate": 8.341176569540891e-05, "loss": 0.9961, "step": 5288 }, { "epoch": 0.2891645310097386, "grad_norm": 2.5003726482391357, "learning_rate": 8.340517857550043e-05, "loss": 1.2011, "step": 5289 }, { "epoch": 0.2892192038270972, "grad_norm": 2.5147085189819336, "learning_rate": 8.339859040820201e-05, "loss": 1.0597, "step": 5290 }, { "epoch": 0.2892738766444558, "grad_norm": 2.9094903469085693, "learning_rate": 8.339200119372024e-05, "loss": 1.2323, "step": 5291 }, { "epoch": 0.28932854946181447, "grad_norm": 2.5332679748535156, "learning_rate": 8.33854109322617e-05, "loss": 1.0671, "step": 5292 }, { "epoch": 0.28938322227917307, "grad_norm": 2.3858885765075684, "learning_rate": 8.337881962403303e-05, "loss": 1.1241, "step": 5293 }, { "epoch": 0.28943789509653167, "grad_norm": 2.2454001903533936, "learning_rate": 8.33722272692409e-05, "loss": 0.9598, "step": 5294 }, { "epoch": 0.28949256791389033, "grad_norm": 2.352137804031372, "learning_rate": 8.336563386809202e-05, "loss": 1.1948, "step": 5295 }, { "epoch": 0.28954724073124893, "grad_norm": 2.2279632091522217, "learning_rate": 8.335903942079309e-05, "loss": 1.0031, "step": 5296 }, { "epoch": 0.28960191354860754, "grad_norm": 2.883979320526123, "learning_rate": 8.335244392755089e-05, "loss": 1.0869, "step": 5297 }, { "epoch": 0.2896565863659662, "grad_norm": 2.502250909805298, "learning_rate": 8.334584738857219e-05, "loss": 0.9861, "step": 5298 }, { "epoch": 0.2897112591833248, "grad_norm": 2.8255391120910645, "learning_rate": 8.333924980406386e-05, "loss": 1.1469, "step": 5299 }, { "epoch": 0.2897659320006834, "grad_norm": 2.6992228031158447, "learning_rate": 8.333265117423276e-05, "loss": 1.1006, "step": 5300 }, { "epoch": 0.289820604818042, "grad_norm": 3.5998127460479736, "learning_rate": 8.332605149928575e-05, "loss": 1.3077, "step": 5301 }, { "epoch": 0.28987527763540066, "grad_norm": 2.7308461666107178, "learning_rate": 8.331945077942978e-05, "loss": 1.1634, "step": 5302 }, { "epoch": 0.28992995045275927, "grad_norm": 2.4512860774993896, "learning_rate": 8.33128490148718e-05, "loss": 1.0356, "step": 5303 }, { "epoch": 0.28998462327011787, "grad_norm": 2.7488105297088623, "learning_rate": 8.33062462058188e-05, "loss": 1.0026, "step": 5304 }, { "epoch": 0.29003929608747653, "grad_norm": 2.5840353965759277, "learning_rate": 8.329964235247783e-05, "loss": 1.0526, "step": 5305 }, { "epoch": 0.29009396890483513, "grad_norm": 2.6095685958862305, "learning_rate": 8.329303745505592e-05, "loss": 1.2342, "step": 5306 }, { "epoch": 0.29014864172219373, "grad_norm": 2.2483458518981934, "learning_rate": 8.328643151376016e-05, "loss": 0.8871, "step": 5307 }, { "epoch": 0.2902033145395524, "grad_norm": 3.3505072593688965, "learning_rate": 8.32798245287977e-05, "loss": 1.1117, "step": 5308 }, { "epoch": 0.290257987356911, "grad_norm": 2.738696336746216, "learning_rate": 8.327321650037568e-05, "loss": 1.2401, "step": 5309 }, { "epoch": 0.2903126601742696, "grad_norm": 2.47977614402771, "learning_rate": 8.326660742870128e-05, "loss": 0.9179, "step": 5310 }, { "epoch": 0.2903673329916282, "grad_norm": 2.556018352508545, "learning_rate": 8.325999731398173e-05, "loss": 0.9651, "step": 5311 }, { "epoch": 0.29042200580898686, "grad_norm": 2.3346269130706787, "learning_rate": 8.325338615642428e-05, "loss": 1.2126, "step": 5312 }, { "epoch": 0.29047667862634546, "grad_norm": 2.0679659843444824, "learning_rate": 8.324677395623624e-05, "loss": 0.9977, "step": 5313 }, { "epoch": 0.29053135144370407, "grad_norm": 2.6086626052856445, "learning_rate": 8.32401607136249e-05, "loss": 1.0192, "step": 5314 }, { "epoch": 0.2905860242610627, "grad_norm": 2.1766304969787598, "learning_rate": 8.323354642879764e-05, "loss": 1.0773, "step": 5315 }, { "epoch": 0.29064069707842133, "grad_norm": 2.2625362873077393, "learning_rate": 8.322693110196183e-05, "loss": 1.104, "step": 5316 }, { "epoch": 0.29069536989577993, "grad_norm": 2.1076529026031494, "learning_rate": 8.322031473332486e-05, "loss": 1.0383, "step": 5317 }, { "epoch": 0.29075004271313853, "grad_norm": 1.8660372495651245, "learning_rate": 8.321369732309422e-05, "loss": 1.0325, "step": 5318 }, { "epoch": 0.2908047155304972, "grad_norm": 2.1647491455078125, "learning_rate": 8.320707887147739e-05, "loss": 0.9795, "step": 5319 }, { "epoch": 0.2908593883478558, "grad_norm": 2.1186633110046387, "learning_rate": 8.320045937868187e-05, "loss": 0.9744, "step": 5320 }, { "epoch": 0.2909140611652144, "grad_norm": 2.6444458961486816, "learning_rate": 8.31938388449152e-05, "loss": 1.1709, "step": 5321 }, { "epoch": 0.29096873398257306, "grad_norm": 4.789309024810791, "learning_rate": 8.3187217270385e-05, "loss": 1.2934, "step": 5322 }, { "epoch": 0.29102340679993166, "grad_norm": 2.212252378463745, "learning_rate": 8.318059465529884e-05, "loss": 1.0488, "step": 5323 }, { "epoch": 0.29107807961729026, "grad_norm": 2.639481782913208, "learning_rate": 8.31739709998644e-05, "loss": 0.9285, "step": 5324 }, { "epoch": 0.2911327524346489, "grad_norm": 3.0466582775115967, "learning_rate": 8.316734630428933e-05, "loss": 1.2989, "step": 5325 }, { "epoch": 0.2911874252520075, "grad_norm": 3.763951539993286, "learning_rate": 8.316072056878138e-05, "loss": 1.0917, "step": 5326 }, { "epoch": 0.29124209806936613, "grad_norm": 3.226252794265747, "learning_rate": 8.315409379354824e-05, "loss": 0.9418, "step": 5327 }, { "epoch": 0.29129677088672473, "grad_norm": 2.8670926094055176, "learning_rate": 8.314746597879774e-05, "loss": 1.0813, "step": 5328 }, { "epoch": 0.2913514437040834, "grad_norm": 2.4465548992156982, "learning_rate": 8.314083712473766e-05, "loss": 1.11, "step": 5329 }, { "epoch": 0.291406116521442, "grad_norm": 2.8672757148742676, "learning_rate": 8.313420723157585e-05, "loss": 1.2864, "step": 5330 }, { "epoch": 0.2914607893388006, "grad_norm": 2.7283425331115723, "learning_rate": 8.312757629952017e-05, "loss": 1.1055, "step": 5331 }, { "epoch": 0.29151546215615926, "grad_norm": 2.2181267738342285, "learning_rate": 8.312094432877855e-05, "loss": 0.9938, "step": 5332 }, { "epoch": 0.29157013497351786, "grad_norm": 2.7772421836853027, "learning_rate": 8.311431131955891e-05, "loss": 1.1057, "step": 5333 }, { "epoch": 0.29162480779087646, "grad_norm": 2.6743228435516357, "learning_rate": 8.310767727206925e-05, "loss": 1.1676, "step": 5334 }, { "epoch": 0.2916794806082351, "grad_norm": 2.5623724460601807, "learning_rate": 8.310104218651755e-05, "loss": 1.2062, "step": 5335 }, { "epoch": 0.2917341534255937, "grad_norm": 2.5208470821380615, "learning_rate": 8.309440606311183e-05, "loss": 1.1938, "step": 5336 }, { "epoch": 0.2917888262429523, "grad_norm": 2.6524791717529297, "learning_rate": 8.30877689020602e-05, "loss": 1.3863, "step": 5337 }, { "epoch": 0.29184349906031093, "grad_norm": 2.1480765342712402, "learning_rate": 8.308113070357076e-05, "loss": 1.1437, "step": 5338 }, { "epoch": 0.2918981718776696, "grad_norm": 2.841419219970703, "learning_rate": 8.30744914678516e-05, "loss": 1.11, "step": 5339 }, { "epoch": 0.2919528446950282, "grad_norm": 4.89113712310791, "learning_rate": 8.306785119511093e-05, "loss": 1.2261, "step": 5340 }, { "epoch": 0.2920075175123868, "grad_norm": 2.041743755340576, "learning_rate": 8.306120988555694e-05, "loss": 0.873, "step": 5341 }, { "epoch": 0.29206219032974545, "grad_norm": 2.4011106491088867, "learning_rate": 8.305456753939786e-05, "loss": 1.1298, "step": 5342 }, { "epoch": 0.29211686314710406, "grad_norm": 3.5679690837860107, "learning_rate": 8.304792415684196e-05, "loss": 1.371, "step": 5343 }, { "epoch": 0.29217153596446266, "grad_norm": 2.7609596252441406, "learning_rate": 8.304127973809752e-05, "loss": 0.9368, "step": 5344 }, { "epoch": 0.29222620878182126, "grad_norm": 2.7777931690216064, "learning_rate": 8.30346342833729e-05, "loss": 1.0067, "step": 5345 }, { "epoch": 0.2922808815991799, "grad_norm": 2.1474690437316895, "learning_rate": 8.302798779287643e-05, "loss": 1.0946, "step": 5346 }, { "epoch": 0.2923355544165385, "grad_norm": 2.3972058296203613, "learning_rate": 8.302134026681652e-05, "loss": 1.1281, "step": 5347 }, { "epoch": 0.2923902272338971, "grad_norm": 2.3340437412261963, "learning_rate": 8.301469170540159e-05, "loss": 1.2055, "step": 5348 }, { "epoch": 0.2924449000512558, "grad_norm": 2.179368019104004, "learning_rate": 8.300804210884013e-05, "loss": 1.0853, "step": 5349 }, { "epoch": 0.2924995728686144, "grad_norm": 2.5083839893341064, "learning_rate": 8.300139147734059e-05, "loss": 1.2826, "step": 5350 }, { "epoch": 0.292554245685973, "grad_norm": 2.142219305038452, "learning_rate": 8.299473981111151e-05, "loss": 1.0556, "step": 5351 }, { "epoch": 0.29260891850333165, "grad_norm": 2.735271453857422, "learning_rate": 8.298808711036146e-05, "loss": 1.1836, "step": 5352 }, { "epoch": 0.29266359132069025, "grad_norm": 2.514885663986206, "learning_rate": 8.2981433375299e-05, "loss": 0.9971, "step": 5353 }, { "epoch": 0.29271826413804886, "grad_norm": 2.4359402656555176, "learning_rate": 8.29747786061328e-05, "loss": 0.9802, "step": 5354 }, { "epoch": 0.29277293695540746, "grad_norm": 2.705156087875366, "learning_rate": 8.296812280307147e-05, "loss": 1.1733, "step": 5355 }, { "epoch": 0.2928276097727661, "grad_norm": 2.922072649002075, "learning_rate": 8.296146596632372e-05, "loss": 1.0069, "step": 5356 }, { "epoch": 0.2928822825901247, "grad_norm": 2.320787191390991, "learning_rate": 8.295480809609826e-05, "loss": 0.9865, "step": 5357 }, { "epoch": 0.2929369554074833, "grad_norm": 2.9072999954223633, "learning_rate": 8.294814919260385e-05, "loss": 1.346, "step": 5358 }, { "epoch": 0.292991628224842, "grad_norm": 3.634955883026123, "learning_rate": 8.294148925604925e-05, "loss": 1.1746, "step": 5359 }, { "epoch": 0.2930463010422006, "grad_norm": 2.12058162689209, "learning_rate": 8.293482828664332e-05, "loss": 1.0664, "step": 5360 }, { "epoch": 0.2931009738595592, "grad_norm": 2.375264883041382, "learning_rate": 8.292816628459486e-05, "loss": 1.0935, "step": 5361 }, { "epoch": 0.29315564667691785, "grad_norm": 2.8566086292266846, "learning_rate": 8.292150325011278e-05, "loss": 1.1613, "step": 5362 }, { "epoch": 0.29321031949427645, "grad_norm": 2.5499274730682373, "learning_rate": 8.2914839183406e-05, "loss": 1.2144, "step": 5363 }, { "epoch": 0.29326499231163505, "grad_norm": 2.5137133598327637, "learning_rate": 8.290817408468345e-05, "loss": 1.0637, "step": 5364 }, { "epoch": 0.29331966512899366, "grad_norm": 2.1087496280670166, "learning_rate": 8.29015079541541e-05, "loss": 1.0058, "step": 5365 }, { "epoch": 0.2933743379463523, "grad_norm": 1.927573323249817, "learning_rate": 8.289484079202698e-05, "loss": 0.8396, "step": 5366 }, { "epoch": 0.2934290107637109, "grad_norm": 1.9109240770339966, "learning_rate": 8.288817259851114e-05, "loss": 0.9425, "step": 5367 }, { "epoch": 0.2934836835810695, "grad_norm": 2.92189884185791, "learning_rate": 8.288150337381563e-05, "loss": 0.9532, "step": 5368 }, { "epoch": 0.2935383563984282, "grad_norm": 2.6065077781677246, "learning_rate": 8.287483311814956e-05, "loss": 1.0636, "step": 5369 }, { "epoch": 0.2935930292157868, "grad_norm": 2.549055814743042, "learning_rate": 8.28681618317221e-05, "loss": 1.11, "step": 5370 }, { "epoch": 0.2936477020331454, "grad_norm": 2.931652545928955, "learning_rate": 8.286148951474237e-05, "loss": 1.271, "step": 5371 }, { "epoch": 0.293702374850504, "grad_norm": 2.448570489883423, "learning_rate": 8.285481616741964e-05, "loss": 1.0441, "step": 5372 }, { "epoch": 0.29375704766786265, "grad_norm": 2.2901532649993896, "learning_rate": 8.28481417899631e-05, "loss": 1.1375, "step": 5373 }, { "epoch": 0.29381172048522125, "grad_norm": 2.3788774013519287, "learning_rate": 8.284146638258204e-05, "loss": 0.7232, "step": 5374 }, { "epoch": 0.29386639330257985, "grad_norm": 2.51639986038208, "learning_rate": 8.283478994548572e-05, "loss": 0.8677, "step": 5375 }, { "epoch": 0.2939210661199385, "grad_norm": 2.4102771282196045, "learning_rate": 8.282811247888353e-05, "loss": 1.2565, "step": 5376 }, { "epoch": 0.2939757389372971, "grad_norm": 3.1734378337860107, "learning_rate": 8.282143398298483e-05, "loss": 1.2161, "step": 5377 }, { "epoch": 0.2940304117546557, "grad_norm": 2.707972288131714, "learning_rate": 8.281475445799897e-05, "loss": 1.2227, "step": 5378 }, { "epoch": 0.2940850845720144, "grad_norm": 2.7800703048706055, "learning_rate": 8.280807390413544e-05, "loss": 1.2287, "step": 5379 }, { "epoch": 0.294139757389373, "grad_norm": 2.6885783672332764, "learning_rate": 8.280139232160367e-05, "loss": 1.0969, "step": 5380 }, { "epoch": 0.2941944302067316, "grad_norm": 2.51796817779541, "learning_rate": 8.279470971061313e-05, "loss": 1.3325, "step": 5381 }, { "epoch": 0.2942491030240902, "grad_norm": 2.2303566932678223, "learning_rate": 8.278802607137342e-05, "loss": 1.0356, "step": 5382 }, { "epoch": 0.29430377584144884, "grad_norm": 2.5721685886383057, "learning_rate": 8.278134140409403e-05, "loss": 1.0795, "step": 5383 }, { "epoch": 0.29435844865880745, "grad_norm": 2.8639540672302246, "learning_rate": 8.277465570898459e-05, "loss": 1.1573, "step": 5384 }, { "epoch": 0.29441312147616605, "grad_norm": 2.959137439727783, "learning_rate": 8.276796898625472e-05, "loss": 1.0184, "step": 5385 }, { "epoch": 0.2944677942935247, "grad_norm": 2.4106385707855225, "learning_rate": 8.276128123611406e-05, "loss": 1.1711, "step": 5386 }, { "epoch": 0.2945224671108833, "grad_norm": 2.2988336086273193, "learning_rate": 8.275459245877231e-05, "loss": 1.2055, "step": 5387 }, { "epoch": 0.2945771399282419, "grad_norm": 2.4551620483398438, "learning_rate": 8.274790265443919e-05, "loss": 1.1509, "step": 5388 }, { "epoch": 0.2946318127456006, "grad_norm": 2.7942631244659424, "learning_rate": 8.274121182332446e-05, "loss": 1.1298, "step": 5389 }, { "epoch": 0.2946864855629592, "grad_norm": 2.9609110355377197, "learning_rate": 8.273451996563789e-05, "loss": 0.9429, "step": 5390 }, { "epoch": 0.2947411583803178, "grad_norm": 2.0923895835876465, "learning_rate": 8.272782708158929e-05, "loss": 0.9937, "step": 5391 }, { "epoch": 0.2947958311976764, "grad_norm": 4.951343536376953, "learning_rate": 8.272113317138855e-05, "loss": 1.2361, "step": 5392 }, { "epoch": 0.29485050401503504, "grad_norm": 2.907949686050415, "learning_rate": 8.271443823524549e-05, "loss": 1.1473, "step": 5393 }, { "epoch": 0.29490517683239365, "grad_norm": 2.201982259750366, "learning_rate": 8.27077422733701e-05, "loss": 1.0797, "step": 5394 }, { "epoch": 0.29495984964975225, "grad_norm": 2.6418635845184326, "learning_rate": 8.270104528597226e-05, "loss": 1.0303, "step": 5395 }, { "epoch": 0.2950145224671109, "grad_norm": 1.8953806161880493, "learning_rate": 8.269434727326198e-05, "loss": 0.7497, "step": 5396 }, { "epoch": 0.2950691952844695, "grad_norm": 3.576709508895874, "learning_rate": 8.268764823544925e-05, "loss": 0.9762, "step": 5397 }, { "epoch": 0.2951238681018281, "grad_norm": 2.7265498638153076, "learning_rate": 8.268094817274414e-05, "loss": 1.2916, "step": 5398 }, { "epoch": 0.2951785409191867, "grad_norm": 2.388320207595825, "learning_rate": 8.267424708535672e-05, "loss": 0.8942, "step": 5399 }, { "epoch": 0.2952332137365454, "grad_norm": 2.618640184402466, "learning_rate": 8.266754497349707e-05, "loss": 0.9052, "step": 5400 }, { "epoch": 0.295287886553904, "grad_norm": 3.5636043548583984, "learning_rate": 8.266084183737535e-05, "loss": 0.9887, "step": 5401 }, { "epoch": 0.2953425593712626, "grad_norm": 2.279994010925293, "learning_rate": 8.265413767720172e-05, "loss": 1.037, "step": 5402 }, { "epoch": 0.29539723218862124, "grad_norm": 2.4447925090789795, "learning_rate": 8.26474324931864e-05, "loss": 1.1621, "step": 5403 }, { "epoch": 0.29545190500597984, "grad_norm": 2.7091686725616455, "learning_rate": 8.264072628553963e-05, "loss": 1.2573, "step": 5404 }, { "epoch": 0.29550657782333845, "grad_norm": 2.179581880569458, "learning_rate": 8.263401905447163e-05, "loss": 1.0912, "step": 5405 }, { "epoch": 0.2955612506406971, "grad_norm": 2.6110167503356934, "learning_rate": 8.262731080019275e-05, "loss": 1.1705, "step": 5406 }, { "epoch": 0.2956159234580557, "grad_norm": 2.391965389251709, "learning_rate": 8.262060152291331e-05, "loss": 1.0242, "step": 5407 }, { "epoch": 0.2956705962754143, "grad_norm": 2.354264736175537, "learning_rate": 8.261389122284366e-05, "loss": 1.1533, "step": 5408 }, { "epoch": 0.2957252690927729, "grad_norm": 3.3182735443115234, "learning_rate": 8.260717990019419e-05, "loss": 0.8955, "step": 5409 }, { "epoch": 0.29577994191013157, "grad_norm": 2.1924993991851807, "learning_rate": 8.260046755517534e-05, "loss": 1.0843, "step": 5410 }, { "epoch": 0.2958346147274902, "grad_norm": 2.7985153198242188, "learning_rate": 8.259375418799759e-05, "loss": 0.8402, "step": 5411 }, { "epoch": 0.2958892875448488, "grad_norm": 2.0941176414489746, "learning_rate": 8.258703979887139e-05, "loss": 0.996, "step": 5412 }, { "epoch": 0.29594396036220744, "grad_norm": 2.1724472045898438, "learning_rate": 8.258032438800731e-05, "loss": 1.1891, "step": 5413 }, { "epoch": 0.29599863317956604, "grad_norm": 2.332150459289551, "learning_rate": 8.257360795561586e-05, "loss": 1.1553, "step": 5414 }, { "epoch": 0.29605330599692464, "grad_norm": 2.1438369750976562, "learning_rate": 8.256689050190764e-05, "loss": 1.1607, "step": 5415 }, { "epoch": 0.29610797881428325, "grad_norm": 2.157554864883423, "learning_rate": 8.256017202709329e-05, "loss": 0.9686, "step": 5416 }, { "epoch": 0.2961626516316419, "grad_norm": 2.949413299560547, "learning_rate": 8.255345253138347e-05, "loss": 1.1925, "step": 5417 }, { "epoch": 0.2962173244490005, "grad_norm": 2.8812482357025146, "learning_rate": 8.254673201498883e-05, "loss": 1.0842, "step": 5418 }, { "epoch": 0.2962719972663591, "grad_norm": 2.2825934886932373, "learning_rate": 8.254001047812009e-05, "loss": 1.1039, "step": 5419 }, { "epoch": 0.29632667008371777, "grad_norm": 2.5987424850463867, "learning_rate": 8.253328792098801e-05, "loss": 1.2688, "step": 5420 }, { "epoch": 0.2963813429010764, "grad_norm": 2.0548369884490967, "learning_rate": 8.252656434380337e-05, "loss": 0.932, "step": 5421 }, { "epoch": 0.296436015718435, "grad_norm": 2.945551633834839, "learning_rate": 8.251983974677698e-05, "loss": 1.1176, "step": 5422 }, { "epoch": 0.29649068853579363, "grad_norm": 2.6172759532928467, "learning_rate": 8.251311413011969e-05, "loss": 1.1946, "step": 5423 }, { "epoch": 0.29654536135315224, "grad_norm": 2.321641683578491, "learning_rate": 8.250638749404236e-05, "loss": 1.0267, "step": 5424 }, { "epoch": 0.29660003417051084, "grad_norm": 2.1987922191619873, "learning_rate": 8.249965983875591e-05, "loss": 1.1818, "step": 5425 }, { "epoch": 0.29665470698786944, "grad_norm": 2.425839424133301, "learning_rate": 8.249293116447128e-05, "loss": 0.9409, "step": 5426 }, { "epoch": 0.2967093798052281, "grad_norm": 2.293192148208618, "learning_rate": 8.248620147139943e-05, "loss": 1.1266, "step": 5427 }, { "epoch": 0.2967640526225867, "grad_norm": 3.2447240352630615, "learning_rate": 8.247947075975138e-05, "loss": 1.2006, "step": 5428 }, { "epoch": 0.2968187254399453, "grad_norm": 2.6530239582061768, "learning_rate": 8.247273902973816e-05, "loss": 1.22, "step": 5429 }, { "epoch": 0.29687339825730397, "grad_norm": 3.5130178928375244, "learning_rate": 8.246600628157082e-05, "loss": 1.167, "step": 5430 }, { "epoch": 0.29692807107466257, "grad_norm": 2.529244899749756, "learning_rate": 8.245927251546048e-05, "loss": 1.0036, "step": 5431 }, { "epoch": 0.2969827438920212, "grad_norm": 2.434563398361206, "learning_rate": 8.245253773161827e-05, "loss": 0.9734, "step": 5432 }, { "epoch": 0.29703741670937983, "grad_norm": 2.5392608642578125, "learning_rate": 8.244580193025536e-05, "loss": 1.0527, "step": 5433 }, { "epoch": 0.29709208952673843, "grad_norm": 2.127354145050049, "learning_rate": 8.24390651115829e-05, "loss": 1.0506, "step": 5434 }, { "epoch": 0.29714676234409704, "grad_norm": 3.901355028152466, "learning_rate": 8.243232727581216e-05, "loss": 1.3027, "step": 5435 }, { "epoch": 0.29720143516145564, "grad_norm": 2.801431894302368, "learning_rate": 8.242558842315441e-05, "loss": 0.9861, "step": 5436 }, { "epoch": 0.2972561079788143, "grad_norm": 2.6904706954956055, "learning_rate": 8.241884855382091e-05, "loss": 1.1444, "step": 5437 }, { "epoch": 0.2973107807961729, "grad_norm": 2.4878737926483154, "learning_rate": 8.2412107668023e-05, "loss": 1.0257, "step": 5438 }, { "epoch": 0.2973654536135315, "grad_norm": 3.0219802856445312, "learning_rate": 8.240536576597202e-05, "loss": 0.8848, "step": 5439 }, { "epoch": 0.29742012643089016, "grad_norm": 2.5234484672546387, "learning_rate": 8.239862284787936e-05, "loss": 1.1986, "step": 5440 }, { "epoch": 0.29747479924824877, "grad_norm": 2.431448459625244, "learning_rate": 8.239187891395644e-05, "loss": 1.1494, "step": 5441 }, { "epoch": 0.29752947206560737, "grad_norm": 3.68475604057312, "learning_rate": 8.238513396441472e-05, "loss": 1.1008, "step": 5442 }, { "epoch": 0.297584144882966, "grad_norm": 2.5822436809539795, "learning_rate": 8.237838799946568e-05, "loss": 1.0445, "step": 5443 }, { "epoch": 0.29763881770032463, "grad_norm": 2.5035247802734375, "learning_rate": 8.237164101932082e-05, "loss": 1.1347, "step": 5444 }, { "epoch": 0.29769349051768323, "grad_norm": 3.204543113708496, "learning_rate": 8.236489302419169e-05, "loss": 1.0665, "step": 5445 }, { "epoch": 0.29774816333504184, "grad_norm": 2.719640016555786, "learning_rate": 8.235814401428987e-05, "loss": 1.1248, "step": 5446 }, { "epoch": 0.2978028361524005, "grad_norm": 2.7010157108306885, "learning_rate": 8.235139398982698e-05, "loss": 1.3264, "step": 5447 }, { "epoch": 0.2978575089697591, "grad_norm": 3.0403175354003906, "learning_rate": 8.234464295101465e-05, "loss": 1.0576, "step": 5448 }, { "epoch": 0.2979121817871177, "grad_norm": 3.9188225269317627, "learning_rate": 8.233789089806456e-05, "loss": 0.9005, "step": 5449 }, { "epoch": 0.29796685460447636, "grad_norm": 2.597421884536743, "learning_rate": 8.233113783118839e-05, "loss": 1.2253, "step": 5450 }, { "epoch": 0.29802152742183496, "grad_norm": 2.755080461502075, "learning_rate": 8.232438375059792e-05, "loss": 1.0722, "step": 5451 }, { "epoch": 0.29807620023919357, "grad_norm": 2.304797410964966, "learning_rate": 8.231762865650487e-05, "loss": 0.9201, "step": 5452 }, { "epoch": 0.29813087305655217, "grad_norm": 2.5094406604766846, "learning_rate": 8.231087254912108e-05, "loss": 1.1085, "step": 5453 }, { "epoch": 0.29818554587391083, "grad_norm": 3.545452833175659, "learning_rate": 8.230411542865836e-05, "loss": 1.0945, "step": 5454 }, { "epoch": 0.29824021869126943, "grad_norm": 5.229420185089111, "learning_rate": 8.229735729532857e-05, "loss": 1.0225, "step": 5455 }, { "epoch": 0.29829489150862804, "grad_norm": 2.3200466632843018, "learning_rate": 8.229059814934363e-05, "loss": 0.9731, "step": 5456 }, { "epoch": 0.2983495643259867, "grad_norm": 2.91410493850708, "learning_rate": 8.228383799091544e-05, "loss": 0.9031, "step": 5457 }, { "epoch": 0.2984042371433453, "grad_norm": 2.7916059494018555, "learning_rate": 8.227707682025598e-05, "loss": 1.3087, "step": 5458 }, { "epoch": 0.2984589099607039, "grad_norm": 2.8882675170898438, "learning_rate": 8.227031463757722e-05, "loss": 1.2488, "step": 5459 }, { "epoch": 0.29851358277806256, "grad_norm": 2.292570114135742, "learning_rate": 8.226355144309119e-05, "loss": 0.9236, "step": 5460 }, { "epoch": 0.29856825559542116, "grad_norm": 2.6122257709503174, "learning_rate": 8.225678723700996e-05, "loss": 1.2001, "step": 5461 }, { "epoch": 0.29862292841277976, "grad_norm": 2.473686695098877, "learning_rate": 8.22500220195456e-05, "loss": 1.1601, "step": 5462 }, { "epoch": 0.29867760123013837, "grad_norm": 2.2023677825927734, "learning_rate": 8.224325579091023e-05, "loss": 1.0523, "step": 5463 }, { "epoch": 0.298732274047497, "grad_norm": 2.2368359565734863, "learning_rate": 8.2236488551316e-05, "loss": 1.0247, "step": 5464 }, { "epoch": 0.29878694686485563, "grad_norm": 2.617884397506714, "learning_rate": 8.222972030097509e-05, "loss": 0.9063, "step": 5465 }, { "epoch": 0.29884161968221423, "grad_norm": 2.52091908454895, "learning_rate": 8.22229510400997e-05, "loss": 1.1442, "step": 5466 }, { "epoch": 0.2988962924995729, "grad_norm": 2.70395565032959, "learning_rate": 8.22161807689021e-05, "loss": 1.0203, "step": 5467 }, { "epoch": 0.2989509653169315, "grad_norm": 2.2192466259002686, "learning_rate": 8.220940948759455e-05, "loss": 0.9611, "step": 5468 }, { "epoch": 0.2990056381342901, "grad_norm": 2.3226332664489746, "learning_rate": 8.220263719638936e-05, "loss": 1.0696, "step": 5469 }, { "epoch": 0.2990603109516487, "grad_norm": 2.4536781311035156, "learning_rate": 8.219586389549887e-05, "loss": 1.1835, "step": 5470 }, { "epoch": 0.29911498376900736, "grad_norm": 2.153822660446167, "learning_rate": 8.218908958513545e-05, "loss": 0.972, "step": 5471 }, { "epoch": 0.29916965658636596, "grad_norm": 3.0533437728881836, "learning_rate": 8.21823142655115e-05, "loss": 1.1595, "step": 5472 }, { "epoch": 0.29922432940372456, "grad_norm": 3.1291024684906006, "learning_rate": 8.217553793683946e-05, "loss": 1.1063, "step": 5473 }, { "epoch": 0.2992790022210832, "grad_norm": 2.5788469314575195, "learning_rate": 8.21687605993318e-05, "loss": 1.2169, "step": 5474 }, { "epoch": 0.2993336750384418, "grad_norm": 2.0108089447021484, "learning_rate": 8.216198225320099e-05, "loss": 1.1408, "step": 5475 }, { "epoch": 0.29938834785580043, "grad_norm": 2.833594799041748, "learning_rate": 8.215520289865961e-05, "loss": 1.2703, "step": 5476 }, { "epoch": 0.2994430206731591, "grad_norm": 3.3393962383270264, "learning_rate": 8.214842253592017e-05, "loss": 1.2428, "step": 5477 }, { "epoch": 0.2994976934905177, "grad_norm": 2.5312397480010986, "learning_rate": 8.214164116519528e-05, "loss": 1.0775, "step": 5478 }, { "epoch": 0.2995523663078763, "grad_norm": 5.54673433303833, "learning_rate": 8.213485878669758e-05, "loss": 1.3668, "step": 5479 }, { "epoch": 0.2996070391252349, "grad_norm": 3.067096471786499, "learning_rate": 8.21280754006397e-05, "loss": 1.2764, "step": 5480 }, { "epoch": 0.29966171194259356, "grad_norm": 2.1751558780670166, "learning_rate": 8.212129100723434e-05, "loss": 1.1194, "step": 5481 }, { "epoch": 0.29971638475995216, "grad_norm": 2.8590567111968994, "learning_rate": 8.211450560669423e-05, "loss": 1.0164, "step": 5482 }, { "epoch": 0.29977105757731076, "grad_norm": 2.827608823776245, "learning_rate": 8.21077191992321e-05, "loss": 1.1745, "step": 5483 }, { "epoch": 0.2998257303946694, "grad_norm": 2.4755332469940186, "learning_rate": 8.210093178506073e-05, "loss": 0.9904, "step": 5484 }, { "epoch": 0.299880403212028, "grad_norm": 2.2283411026000977, "learning_rate": 8.209414336439295e-05, "loss": 0.9833, "step": 5485 }, { "epoch": 0.2999350760293866, "grad_norm": 2.480569839477539, "learning_rate": 8.20873539374416e-05, "loss": 1.1731, "step": 5486 }, { "epoch": 0.2999897488467453, "grad_norm": 2.2696163654327393, "learning_rate": 8.208056350441955e-05, "loss": 1.1981, "step": 5487 }, { "epoch": 0.3000444216641039, "grad_norm": 2.8502161502838135, "learning_rate": 8.207377206553973e-05, "loss": 1.268, "step": 5488 }, { "epoch": 0.3000990944814625, "grad_norm": 3.9623444080352783, "learning_rate": 8.206697962101504e-05, "loss": 1.143, "step": 5489 }, { "epoch": 0.3001537672988211, "grad_norm": 2.699122667312622, "learning_rate": 8.206018617105848e-05, "loss": 0.9693, "step": 5490 }, { "epoch": 0.30020844011617975, "grad_norm": 2.8039491176605225, "learning_rate": 8.205339171588305e-05, "loss": 1.213, "step": 5491 }, { "epoch": 0.30026311293353836, "grad_norm": 3.316230058670044, "learning_rate": 8.204659625570177e-05, "loss": 1.3162, "step": 5492 }, { "epoch": 0.30031778575089696, "grad_norm": 2.5928051471710205, "learning_rate": 8.203979979072774e-05, "loss": 1.0475, "step": 5493 }, { "epoch": 0.3003724585682556, "grad_norm": 2.742213010787964, "learning_rate": 8.203300232117399e-05, "loss": 1.1913, "step": 5494 }, { "epoch": 0.3004271313856142, "grad_norm": 2.7829301357269287, "learning_rate": 8.202620384725372e-05, "loss": 1.0573, "step": 5495 }, { "epoch": 0.3004818042029728, "grad_norm": 2.972517490386963, "learning_rate": 8.201940436918007e-05, "loss": 1.1565, "step": 5496 }, { "epoch": 0.3005364770203314, "grad_norm": 2.2645537853240967, "learning_rate": 8.201260388716621e-05, "loss": 1.019, "step": 5497 }, { "epoch": 0.3005911498376901, "grad_norm": 2.251880168914795, "learning_rate": 8.200580240142539e-05, "loss": 1.0734, "step": 5498 }, { "epoch": 0.3006458226550487, "grad_norm": 2.210420608520508, "learning_rate": 8.199899991217081e-05, "loss": 0.9385, "step": 5499 }, { "epoch": 0.3007004954724073, "grad_norm": 2.2950522899627686, "learning_rate": 8.199219641961584e-05, "loss": 0.798, "step": 5500 }, { "epoch": 0.30075516828976595, "grad_norm": 2.261699676513672, "learning_rate": 8.198539192397374e-05, "loss": 1.0925, "step": 5501 }, { "epoch": 0.30080984110712455, "grad_norm": 2.548182725906372, "learning_rate": 8.197858642545788e-05, "loss": 1.1748, "step": 5502 }, { "epoch": 0.30086451392448316, "grad_norm": 3.594449520111084, "learning_rate": 8.197177992428162e-05, "loss": 1.1763, "step": 5503 }, { "epoch": 0.3009191867418418, "grad_norm": 2.447432518005371, "learning_rate": 8.196497242065839e-05, "loss": 1.1273, "step": 5504 }, { "epoch": 0.3009738595592004, "grad_norm": 3.151245594024658, "learning_rate": 8.195816391480164e-05, "loss": 1.1019, "step": 5505 }, { "epoch": 0.301028532376559, "grad_norm": 2.8932790756225586, "learning_rate": 8.195135440692483e-05, "loss": 1.1652, "step": 5506 }, { "epoch": 0.3010832051939176, "grad_norm": 3.324066638946533, "learning_rate": 8.194454389724147e-05, "loss": 1.0957, "step": 5507 }, { "epoch": 0.3011378780112763, "grad_norm": 2.946506977081299, "learning_rate": 8.193773238596509e-05, "loss": 1.0824, "step": 5508 }, { "epoch": 0.3011925508286349, "grad_norm": 2.2208778858184814, "learning_rate": 8.193091987330928e-05, "loss": 1.0175, "step": 5509 }, { "epoch": 0.3012472236459935, "grad_norm": 2.565840244293213, "learning_rate": 8.192410635948761e-05, "loss": 0.9684, "step": 5510 }, { "epoch": 0.30130189646335215, "grad_norm": 2.6344988346099854, "learning_rate": 8.191729184471373e-05, "loss": 1.2097, "step": 5511 }, { "epoch": 0.30135656928071075, "grad_norm": 2.2860753536224365, "learning_rate": 8.191047632920131e-05, "loss": 0.9104, "step": 5512 }, { "epoch": 0.30141124209806935, "grad_norm": 2.4920997619628906, "learning_rate": 8.190365981316403e-05, "loss": 1.2137, "step": 5513 }, { "epoch": 0.301465914915428, "grad_norm": 3.401093006134033, "learning_rate": 8.189684229681563e-05, "loss": 1.0657, "step": 5514 }, { "epoch": 0.3015205877327866, "grad_norm": 2.7678048610687256, "learning_rate": 8.189002378036985e-05, "loss": 1.1507, "step": 5515 }, { "epoch": 0.3015752605501452, "grad_norm": 3.8216464519500732, "learning_rate": 8.18832042640405e-05, "loss": 1.1754, "step": 5516 }, { "epoch": 0.3016299333675038, "grad_norm": 2.940016031265259, "learning_rate": 8.187638374804139e-05, "loss": 1.0933, "step": 5517 }, { "epoch": 0.3016846061848625, "grad_norm": 2.671403646469116, "learning_rate": 8.186956223258635e-05, "loss": 1.0896, "step": 5518 }, { "epoch": 0.3017392790022211, "grad_norm": 4.569914817810059, "learning_rate": 8.186273971788929e-05, "loss": 1.1885, "step": 5519 }, { "epoch": 0.3017939518195797, "grad_norm": 4.521412372589111, "learning_rate": 8.185591620416411e-05, "loss": 1.4406, "step": 5520 }, { "epoch": 0.30184862463693835, "grad_norm": 2.455228328704834, "learning_rate": 8.184909169162477e-05, "loss": 1.1953, "step": 5521 }, { "epoch": 0.30190329745429695, "grad_norm": 2.909575939178467, "learning_rate": 8.184226618048523e-05, "loss": 1.1601, "step": 5522 }, { "epoch": 0.30195797027165555, "grad_norm": 2.258596420288086, "learning_rate": 8.18354396709595e-05, "loss": 1.1872, "step": 5523 }, { "epoch": 0.30201264308901415, "grad_norm": 2.9365110397338867, "learning_rate": 8.182861216326164e-05, "loss": 1.2802, "step": 5524 }, { "epoch": 0.3020673159063728, "grad_norm": 2.628769636154175, "learning_rate": 8.18217836576057e-05, "loss": 1.1418, "step": 5525 }, { "epoch": 0.3021219887237314, "grad_norm": 2.9639577865600586, "learning_rate": 8.181495415420579e-05, "loss": 1.2928, "step": 5526 }, { "epoch": 0.30217666154109, "grad_norm": 2.376673698425293, "learning_rate": 8.180812365327603e-05, "loss": 1.003, "step": 5527 }, { "epoch": 0.3022313343584487, "grad_norm": 2.7482926845550537, "learning_rate": 8.180129215503058e-05, "loss": 1.176, "step": 5528 }, { "epoch": 0.3022860071758073, "grad_norm": 1.9515233039855957, "learning_rate": 8.179445965968367e-05, "loss": 0.9938, "step": 5529 }, { "epoch": 0.3023406799931659, "grad_norm": 2.3038902282714844, "learning_rate": 8.178762616744951e-05, "loss": 1.0481, "step": 5530 }, { "epoch": 0.30239535281052454, "grad_norm": 2.0885770320892334, "learning_rate": 8.178079167854235e-05, "loss": 0.9981, "step": 5531 }, { "epoch": 0.30245002562788315, "grad_norm": 2.6176230907440186, "learning_rate": 8.177395619317648e-05, "loss": 1.0472, "step": 5532 }, { "epoch": 0.30250469844524175, "grad_norm": 2.856905698776245, "learning_rate": 8.176711971156623e-05, "loss": 1.0266, "step": 5533 }, { "epoch": 0.30255937126260035, "grad_norm": 2.504556179046631, "learning_rate": 8.176028223392593e-05, "loss": 1.094, "step": 5534 }, { "epoch": 0.302614044079959, "grad_norm": 2.89947509765625, "learning_rate": 8.175344376047e-05, "loss": 1.1472, "step": 5535 }, { "epoch": 0.3026687168973176, "grad_norm": 2.4711899757385254, "learning_rate": 8.174660429141282e-05, "loss": 1.0907, "step": 5536 }, { "epoch": 0.3027233897146762, "grad_norm": 2.39835786819458, "learning_rate": 8.173976382696886e-05, "loss": 1.0649, "step": 5537 }, { "epoch": 0.3027780625320349, "grad_norm": 2.460127830505371, "learning_rate": 8.173292236735258e-05, "loss": 1.0704, "step": 5538 }, { "epoch": 0.3028327353493935, "grad_norm": 2.33976674079895, "learning_rate": 8.172607991277849e-05, "loss": 1.1838, "step": 5539 }, { "epoch": 0.3028874081667521, "grad_norm": 2.331787109375, "learning_rate": 8.171923646346114e-05, "loss": 0.8924, "step": 5540 }, { "epoch": 0.30294208098411074, "grad_norm": 2.5377960205078125, "learning_rate": 8.171239201961509e-05, "loss": 1.259, "step": 5541 }, { "epoch": 0.30299675380146934, "grad_norm": 2.9900546073913574, "learning_rate": 8.170554658145495e-05, "loss": 0.9207, "step": 5542 }, { "epoch": 0.30305142661882795, "grad_norm": 3.2518649101257324, "learning_rate": 8.169870014919534e-05, "loss": 1.0652, "step": 5543 }, { "epoch": 0.30310609943618655, "grad_norm": 2.355306386947632, "learning_rate": 8.169185272305093e-05, "loss": 0.9339, "step": 5544 }, { "epoch": 0.3031607722535452, "grad_norm": 2.722754716873169, "learning_rate": 8.168500430323643e-05, "loss": 0.9332, "step": 5545 }, { "epoch": 0.3032154450709038, "grad_norm": 2.539705753326416, "learning_rate": 8.167815488996653e-05, "loss": 1.0503, "step": 5546 }, { "epoch": 0.3032701178882624, "grad_norm": 2.6053290367126465, "learning_rate": 8.167130448345604e-05, "loss": 0.9814, "step": 5547 }, { "epoch": 0.3033247907056211, "grad_norm": 2.5736641883850098, "learning_rate": 8.166445308391968e-05, "loss": 1.1307, "step": 5548 }, { "epoch": 0.3033794635229797, "grad_norm": 2.296408176422119, "learning_rate": 8.165760069157234e-05, "loss": 1.0431, "step": 5549 }, { "epoch": 0.3034341363403383, "grad_norm": 2.186596155166626, "learning_rate": 8.165074730662883e-05, "loss": 1.1097, "step": 5550 }, { "epoch": 0.3034888091576969, "grad_norm": 2.2980597019195557, "learning_rate": 8.164389292930403e-05, "loss": 0.983, "step": 5551 }, { "epoch": 0.30354348197505554, "grad_norm": 2.3572771549224854, "learning_rate": 8.163703755981288e-05, "loss": 1.2497, "step": 5552 }, { "epoch": 0.30359815479241414, "grad_norm": 2.7414073944091797, "learning_rate": 8.163018119837029e-05, "loss": 1.2092, "step": 5553 }, { "epoch": 0.30365282760977275, "grad_norm": 3.0077579021453857, "learning_rate": 8.162332384519127e-05, "loss": 0.9557, "step": 5554 }, { "epoch": 0.3037075004271314, "grad_norm": 2.8735132217407227, "learning_rate": 8.16164655004908e-05, "loss": 1.0098, "step": 5555 }, { "epoch": 0.30376217324449, "grad_norm": 2.753343105316162, "learning_rate": 8.160960616448393e-05, "loss": 1.1641, "step": 5556 }, { "epoch": 0.3038168460618486, "grad_norm": 3.2940332889556885, "learning_rate": 8.160274583738572e-05, "loss": 1.1664, "step": 5557 }, { "epoch": 0.30387151887920727, "grad_norm": 3.565124273300171, "learning_rate": 8.159588451941127e-05, "loss": 0.979, "step": 5558 }, { "epoch": 0.3039261916965659, "grad_norm": 2.452030658721924, "learning_rate": 8.158902221077573e-05, "loss": 1.122, "step": 5559 }, { "epoch": 0.3039808645139245, "grad_norm": 1.84891676902771, "learning_rate": 8.158215891169423e-05, "loss": 0.9263, "step": 5560 }, { "epoch": 0.3040355373312831, "grad_norm": 2.9836807250976562, "learning_rate": 8.157529462238201e-05, "loss": 1.1604, "step": 5561 }, { "epoch": 0.30409021014864174, "grad_norm": 2.8770806789398193, "learning_rate": 8.156842934305422e-05, "loss": 1.2067, "step": 5562 }, { "epoch": 0.30414488296600034, "grad_norm": 3.176462173461914, "learning_rate": 8.156156307392619e-05, "loss": 1.2308, "step": 5563 }, { "epoch": 0.30419955578335894, "grad_norm": 2.791815757751465, "learning_rate": 8.155469581521316e-05, "loss": 1.1129, "step": 5564 }, { "epoch": 0.3042542286007176, "grad_norm": 2.7499239444732666, "learning_rate": 8.154782756713045e-05, "loss": 1.1489, "step": 5565 }, { "epoch": 0.3043089014180762, "grad_norm": 2.24825119972229, "learning_rate": 8.154095832989344e-05, "loss": 0.9391, "step": 5566 }, { "epoch": 0.3043635742354348, "grad_norm": 2.44392991065979, "learning_rate": 8.153408810371747e-05, "loss": 1.0814, "step": 5567 }, { "epoch": 0.30441824705279347, "grad_norm": 3.382427930831909, "learning_rate": 8.152721688881798e-05, "loss": 1.0051, "step": 5568 }, { "epoch": 0.30447291987015207, "grad_norm": 2.9477384090423584, "learning_rate": 8.152034468541039e-05, "loss": 1.2711, "step": 5569 }, { "epoch": 0.3045275926875107, "grad_norm": 1.9593627452850342, "learning_rate": 8.151347149371018e-05, "loss": 1.0608, "step": 5570 }, { "epoch": 0.3045822655048693, "grad_norm": 2.8937606811523438, "learning_rate": 8.150659731393287e-05, "loss": 1.1238, "step": 5571 }, { "epoch": 0.30463693832222793, "grad_norm": 1.9768176078796387, "learning_rate": 8.149972214629395e-05, "loss": 0.7701, "step": 5572 }, { "epoch": 0.30469161113958654, "grad_norm": 2.9783108234405518, "learning_rate": 8.149284599100902e-05, "loss": 1.0992, "step": 5573 }, { "epoch": 0.30474628395694514, "grad_norm": 2.54339861869812, "learning_rate": 8.148596884829368e-05, "loss": 1.0546, "step": 5574 }, { "epoch": 0.3048009567743038, "grad_norm": 4.978541374206543, "learning_rate": 8.147909071836352e-05, "loss": 1.3017, "step": 5575 }, { "epoch": 0.3048556295916624, "grad_norm": 2.054985523223877, "learning_rate": 8.147221160143423e-05, "loss": 0.9101, "step": 5576 }, { "epoch": 0.304910302409021, "grad_norm": 3.0084919929504395, "learning_rate": 8.146533149772149e-05, "loss": 1.1776, "step": 5577 }, { "epoch": 0.3049649752263796, "grad_norm": 2.599043369293213, "learning_rate": 8.145845040744102e-05, "loss": 0.9597, "step": 5578 }, { "epoch": 0.30501964804373827, "grad_norm": 2.5956735610961914, "learning_rate": 8.145156833080858e-05, "loss": 1.007, "step": 5579 }, { "epoch": 0.30507432086109687, "grad_norm": 3.014415979385376, "learning_rate": 8.144468526803995e-05, "loss": 1.0434, "step": 5580 }, { "epoch": 0.3051289936784555, "grad_norm": 2.6551339626312256, "learning_rate": 8.143780121935092e-05, "loss": 0.9014, "step": 5581 }, { "epoch": 0.30518366649581413, "grad_norm": 3.6671509742736816, "learning_rate": 8.143091618495733e-05, "loss": 1.1184, "step": 5582 }, { "epoch": 0.30523833931317274, "grad_norm": 1.8798435926437378, "learning_rate": 8.14240301650751e-05, "loss": 1.0212, "step": 5583 }, { "epoch": 0.30529301213053134, "grad_norm": 2.5791540145874023, "learning_rate": 8.14171431599201e-05, "loss": 0.8746, "step": 5584 }, { "epoch": 0.30534768494789, "grad_norm": 2.4809553623199463, "learning_rate": 8.141025516970826e-05, "loss": 1.0651, "step": 5585 }, { "epoch": 0.3054023577652486, "grad_norm": 2.7080483436584473, "learning_rate": 8.140336619465558e-05, "loss": 1.0277, "step": 5586 }, { "epoch": 0.3054570305826072, "grad_norm": 3.09222149848938, "learning_rate": 8.139647623497801e-05, "loss": 1.0061, "step": 5587 }, { "epoch": 0.3055117033999658, "grad_norm": 2.624699592590332, "learning_rate": 8.138958529089163e-05, "loss": 1.0662, "step": 5588 }, { "epoch": 0.30556637621732446, "grad_norm": 2.9057228565216064, "learning_rate": 8.138269336261246e-05, "loss": 1.2854, "step": 5589 }, { "epoch": 0.30562104903468307, "grad_norm": 2.19492506980896, "learning_rate": 8.137580045035662e-05, "loss": 1.2303, "step": 5590 }, { "epoch": 0.30567572185204167, "grad_norm": 2.9655935764312744, "learning_rate": 8.136890655434019e-05, "loss": 1.2175, "step": 5591 }, { "epoch": 0.30573039466940033, "grad_norm": 2.537946939468384, "learning_rate": 8.136201167477937e-05, "loss": 1.029, "step": 5592 }, { "epoch": 0.30578506748675893, "grad_norm": 2.2298662662506104, "learning_rate": 8.135511581189032e-05, "loss": 0.9988, "step": 5593 }, { "epoch": 0.30583974030411754, "grad_norm": 2.5018491744995117, "learning_rate": 8.134821896588927e-05, "loss": 1.2538, "step": 5594 }, { "epoch": 0.30589441312147614, "grad_norm": 2.5142717361450195, "learning_rate": 8.134132113699242e-05, "loss": 1.1152, "step": 5595 }, { "epoch": 0.3059490859388348, "grad_norm": 1.8729709386825562, "learning_rate": 8.13344223254161e-05, "loss": 0.9635, "step": 5596 }, { "epoch": 0.3060037587561934, "grad_norm": 2.116687297821045, "learning_rate": 8.132752253137657e-05, "loss": 1.1438, "step": 5597 }, { "epoch": 0.306058431573552, "grad_norm": 2.413270950317383, "learning_rate": 8.13206217550902e-05, "loss": 1.1689, "step": 5598 }, { "epoch": 0.30611310439091066, "grad_norm": 2.698509931564331, "learning_rate": 8.131371999677336e-05, "loss": 1.1591, "step": 5599 }, { "epoch": 0.30616777720826927, "grad_norm": 2.258450508117676, "learning_rate": 8.130681725664242e-05, "loss": 1.0634, "step": 5600 }, { "epoch": 0.30622245002562787, "grad_norm": 2.3849925994873047, "learning_rate": 8.129991353491382e-05, "loss": 0.8971, "step": 5601 }, { "epoch": 0.3062771228429865, "grad_norm": 2.4136245250701904, "learning_rate": 8.129300883180402e-05, "loss": 1.0576, "step": 5602 }, { "epoch": 0.30633179566034513, "grad_norm": 2.5404834747314453, "learning_rate": 8.128610314752952e-05, "loss": 0.9177, "step": 5603 }, { "epoch": 0.30638646847770373, "grad_norm": 2.506701946258545, "learning_rate": 8.127919648230684e-05, "loss": 1.1021, "step": 5604 }, { "epoch": 0.30644114129506234, "grad_norm": 2.4717719554901123, "learning_rate": 8.127228883635254e-05, "loss": 0.8025, "step": 5605 }, { "epoch": 0.306495814112421, "grad_norm": 2.315634250640869, "learning_rate": 8.126538020988318e-05, "loss": 1.2631, "step": 5606 }, { "epoch": 0.3065504869297796, "grad_norm": 2.145359992980957, "learning_rate": 8.125847060311538e-05, "loss": 1.0176, "step": 5607 }, { "epoch": 0.3066051597471382, "grad_norm": 2.501589298248291, "learning_rate": 8.125156001626581e-05, "loss": 1.1898, "step": 5608 }, { "epoch": 0.30665983256449686, "grad_norm": 2.3399810791015625, "learning_rate": 8.12446484495511e-05, "loss": 0.7448, "step": 5609 }, { "epoch": 0.30671450538185546, "grad_norm": 2.975837469100952, "learning_rate": 8.1237735903188e-05, "loss": 1.2087, "step": 5610 }, { "epoch": 0.30676917819921407, "grad_norm": 2.5467135906219482, "learning_rate": 8.123082237739323e-05, "loss": 0.9763, "step": 5611 }, { "epoch": 0.3068238510165727, "grad_norm": 4.251797199249268, "learning_rate": 8.122390787238354e-05, "loss": 1.0063, "step": 5612 }, { "epoch": 0.3068785238339313, "grad_norm": 3.0010015964508057, "learning_rate": 8.121699238837577e-05, "loss": 1.0019, "step": 5613 }, { "epoch": 0.30693319665128993, "grad_norm": 2.6563761234283447, "learning_rate": 8.121007592558672e-05, "loss": 1.1357, "step": 5614 }, { "epoch": 0.30698786946864853, "grad_norm": 2.354778528213501, "learning_rate": 8.120315848423324e-05, "loss": 1.0442, "step": 5615 }, { "epoch": 0.3070425422860072, "grad_norm": 2.233729124069214, "learning_rate": 8.119624006453223e-05, "loss": 1.025, "step": 5616 }, { "epoch": 0.3070972151033658, "grad_norm": 3.3359017372131348, "learning_rate": 8.118932066670062e-05, "loss": 1.1376, "step": 5617 }, { "epoch": 0.3071518879207244, "grad_norm": 2.9414522647857666, "learning_rate": 8.118240029095537e-05, "loss": 1.1387, "step": 5618 }, { "epoch": 0.30720656073808306, "grad_norm": 2.6866822242736816, "learning_rate": 8.117547893751342e-05, "loss": 0.9752, "step": 5619 }, { "epoch": 0.30726123355544166, "grad_norm": 2.0321576595306396, "learning_rate": 8.116855660659184e-05, "loss": 1.1701, "step": 5620 }, { "epoch": 0.30731590637280026, "grad_norm": 2.3816139698028564, "learning_rate": 8.116163329840762e-05, "loss": 1.0078, "step": 5621 }, { "epoch": 0.30737057919015887, "grad_norm": 2.4473400115966797, "learning_rate": 8.115470901317787e-05, "loss": 1.0514, "step": 5622 }, { "epoch": 0.3074252520075175, "grad_norm": 12.552775382995605, "learning_rate": 8.114778375111968e-05, "loss": 1.1023, "step": 5623 }, { "epoch": 0.3074799248248761, "grad_norm": 2.3265445232391357, "learning_rate": 8.114085751245019e-05, "loss": 1.2966, "step": 5624 }, { "epoch": 0.30753459764223473, "grad_norm": 2.6067211627960205, "learning_rate": 8.113393029738658e-05, "loss": 1.1792, "step": 5625 }, { "epoch": 0.3075892704595934, "grad_norm": 2.115067481994629, "learning_rate": 8.112700210614601e-05, "loss": 1.0677, "step": 5626 }, { "epoch": 0.307643943276952, "grad_norm": 1.9524188041687012, "learning_rate": 8.112007293894575e-05, "loss": 0.9771, "step": 5627 }, { "epoch": 0.3076986160943106, "grad_norm": 3.040748357772827, "learning_rate": 8.111314279600303e-05, "loss": 1.0088, "step": 5628 }, { "epoch": 0.30775328891166925, "grad_norm": 2.323065757751465, "learning_rate": 8.110621167753514e-05, "loss": 1.0225, "step": 5629 }, { "epoch": 0.30780796172902786, "grad_norm": 2.2181239128112793, "learning_rate": 8.109927958375941e-05, "loss": 0.931, "step": 5630 }, { "epoch": 0.30786263454638646, "grad_norm": 3.8029372692108154, "learning_rate": 8.10923465148932e-05, "loss": 1.3408, "step": 5631 }, { "epoch": 0.30791730736374506, "grad_norm": 4.432315826416016, "learning_rate": 8.108541247115384e-05, "loss": 1.0237, "step": 5632 }, { "epoch": 0.3079719801811037, "grad_norm": 2.7399909496307373, "learning_rate": 8.10784774527588e-05, "loss": 1.2118, "step": 5633 }, { "epoch": 0.3080266529984623, "grad_norm": 2.708724021911621, "learning_rate": 8.10715414599255e-05, "loss": 1.1516, "step": 5634 }, { "epoch": 0.30808132581582093, "grad_norm": 3.473062038421631, "learning_rate": 8.10646044928714e-05, "loss": 1.0813, "step": 5635 }, { "epoch": 0.3081359986331796, "grad_norm": 2.081655263900757, "learning_rate": 8.105766655181401e-05, "loss": 1.0001, "step": 5636 }, { "epoch": 0.3081906714505382, "grad_norm": 3.333782911300659, "learning_rate": 8.105072763697086e-05, "loss": 1.2548, "step": 5637 }, { "epoch": 0.3082453442678968, "grad_norm": 2.8884708881378174, "learning_rate": 8.104378774855954e-05, "loss": 1.1057, "step": 5638 }, { "epoch": 0.30830001708525545, "grad_norm": 2.310274362564087, "learning_rate": 8.10368468867976e-05, "loss": 1.1202, "step": 5639 }, { "epoch": 0.30835468990261405, "grad_norm": 2.308290958404541, "learning_rate": 8.102990505190271e-05, "loss": 1.0397, "step": 5640 }, { "epoch": 0.30840936271997266, "grad_norm": 2.9051454067230225, "learning_rate": 8.102296224409247e-05, "loss": 1.2006, "step": 5641 }, { "epoch": 0.30846403553733126, "grad_norm": 2.8572566509246826, "learning_rate": 8.101601846358462e-05, "loss": 1.0792, "step": 5642 }, { "epoch": 0.3085187083546899, "grad_norm": 2.3134031295776367, "learning_rate": 8.100907371059685e-05, "loss": 0.8614, "step": 5643 }, { "epoch": 0.3085733811720485, "grad_norm": 2.3432650566101074, "learning_rate": 8.100212798534692e-05, "loss": 1.0021, "step": 5644 }, { "epoch": 0.3086280539894071, "grad_norm": 2.5271129608154297, "learning_rate": 8.09951812880526e-05, "loss": 1.2915, "step": 5645 }, { "epoch": 0.3086827268067658, "grad_norm": 1.9755853414535522, "learning_rate": 8.098823361893166e-05, "loss": 1.117, "step": 5646 }, { "epoch": 0.3087373996241244, "grad_norm": 2.7751386165618896, "learning_rate": 8.0981284978202e-05, "loss": 1.1572, "step": 5647 }, { "epoch": 0.308792072441483, "grad_norm": 2.531886339187622, "learning_rate": 8.097433536608145e-05, "loss": 1.1796, "step": 5648 }, { "epoch": 0.3088467452588416, "grad_norm": 2.4384565353393555, "learning_rate": 8.096738478278793e-05, "loss": 1.1729, "step": 5649 }, { "epoch": 0.30890141807620025, "grad_norm": 2.223937511444092, "learning_rate": 8.096043322853937e-05, "loss": 1.1795, "step": 5650 }, { "epoch": 0.30895609089355885, "grad_norm": 5.5180463790893555, "learning_rate": 8.095348070355371e-05, "loss": 1.0141, "step": 5651 }, { "epoch": 0.30901076371091746, "grad_norm": 2.4299302101135254, "learning_rate": 8.094652720804894e-05, "loss": 0.9074, "step": 5652 }, { "epoch": 0.3090654365282761, "grad_norm": 2.156005859375, "learning_rate": 8.09395727422431e-05, "loss": 0.9679, "step": 5653 }, { "epoch": 0.3091201093456347, "grad_norm": 2.5181314945220947, "learning_rate": 8.093261730635423e-05, "loss": 1.1035, "step": 5654 }, { "epoch": 0.3091747821629933, "grad_norm": 2.2429721355438232, "learning_rate": 8.092566090060042e-05, "loss": 1.1376, "step": 5655 }, { "epoch": 0.309229454980352, "grad_norm": 2.2647581100463867, "learning_rate": 8.091870352519977e-05, "loss": 0.8141, "step": 5656 }, { "epoch": 0.3092841277977106, "grad_norm": 2.3464162349700928, "learning_rate": 8.091174518037042e-05, "loss": 0.9782, "step": 5657 }, { "epoch": 0.3093388006150692, "grad_norm": 2.369344472885132, "learning_rate": 8.090478586633057e-05, "loss": 1.1829, "step": 5658 }, { "epoch": 0.3093934734324278, "grad_norm": 2.303116798400879, "learning_rate": 8.089782558329839e-05, "loss": 1.0488, "step": 5659 }, { "epoch": 0.30944814624978645, "grad_norm": 2.4417548179626465, "learning_rate": 8.089086433149213e-05, "loss": 1.1846, "step": 5660 }, { "epoch": 0.30950281906714505, "grad_norm": 2.5464887619018555, "learning_rate": 8.088390211113004e-05, "loss": 1.3778, "step": 5661 }, { "epoch": 0.30955749188450365, "grad_norm": 2.9545485973358154, "learning_rate": 8.087693892243045e-05, "loss": 1.2054, "step": 5662 }, { "epoch": 0.3096121647018623, "grad_norm": 2.514331579208374, "learning_rate": 8.086997476561164e-05, "loss": 1.1359, "step": 5663 }, { "epoch": 0.3096668375192209, "grad_norm": 3.33760404586792, "learning_rate": 8.0863009640892e-05, "loss": 0.8795, "step": 5664 }, { "epoch": 0.3097215103365795, "grad_norm": 3.4414734840393066, "learning_rate": 8.085604354848987e-05, "loss": 1.1943, "step": 5665 }, { "epoch": 0.3097761831539382, "grad_norm": 2.903306245803833, "learning_rate": 8.084907648862373e-05, "loss": 1.0661, "step": 5666 }, { "epoch": 0.3098308559712968, "grad_norm": 2.5910837650299072, "learning_rate": 8.084210846151198e-05, "loss": 1.0746, "step": 5667 }, { "epoch": 0.3098855287886554, "grad_norm": 3.2182528972625732, "learning_rate": 8.083513946737311e-05, "loss": 0.9364, "step": 5668 }, { "epoch": 0.309940201606014, "grad_norm": 2.616889238357544, "learning_rate": 8.082816950642564e-05, "loss": 1.2112, "step": 5669 }, { "epoch": 0.30999487442337265, "grad_norm": 3.8859646320343018, "learning_rate": 8.082119857888807e-05, "loss": 0.9748, "step": 5670 }, { "epoch": 0.31004954724073125, "grad_norm": 2.4399144649505615, "learning_rate": 8.0814226684979e-05, "loss": 1.0655, "step": 5671 }, { "epoch": 0.31010422005808985, "grad_norm": 2.7441515922546387, "learning_rate": 8.0807253824917e-05, "loss": 1.1678, "step": 5672 }, { "epoch": 0.3101588928754485, "grad_norm": 2.9372785091400146, "learning_rate": 8.080027999892075e-05, "loss": 1.0886, "step": 5673 }, { "epoch": 0.3102135656928071, "grad_norm": 2.438455581665039, "learning_rate": 8.079330520720884e-05, "loss": 1.1622, "step": 5674 }, { "epoch": 0.3102682385101657, "grad_norm": 2.9434611797332764, "learning_rate": 8.078632945e-05, "loss": 1.0318, "step": 5675 }, { "epoch": 0.3103229113275243, "grad_norm": 2.417584180831909, "learning_rate": 8.077935272751296e-05, "loss": 1.2369, "step": 5676 }, { "epoch": 0.310377584144883, "grad_norm": 2.410001277923584, "learning_rate": 8.077237503996641e-05, "loss": 1.0614, "step": 5677 }, { "epoch": 0.3104322569622416, "grad_norm": 3.048522710800171, "learning_rate": 8.07653963875792e-05, "loss": 1.0513, "step": 5678 }, { "epoch": 0.3104869297796002, "grad_norm": 2.3921642303466797, "learning_rate": 8.075841677057011e-05, "loss": 1.1462, "step": 5679 }, { "epoch": 0.31054160259695884, "grad_norm": 3.1970622539520264, "learning_rate": 8.075143618915797e-05, "loss": 0.9151, "step": 5680 }, { "epoch": 0.31059627541431745, "grad_norm": 2.8330626487731934, "learning_rate": 8.074445464356165e-05, "loss": 1.1508, "step": 5681 }, { "epoch": 0.31065094823167605, "grad_norm": 2.3502750396728516, "learning_rate": 8.073747213400006e-05, "loss": 1.2538, "step": 5682 }, { "epoch": 0.3107056210490347, "grad_norm": 3.0077123641967773, "learning_rate": 8.073048866069215e-05, "loss": 1.1443, "step": 5683 }, { "epoch": 0.3107602938663933, "grad_norm": 3.0558693408966064, "learning_rate": 8.072350422385683e-05, "loss": 1.3228, "step": 5684 }, { "epoch": 0.3108149666837519, "grad_norm": 2.2094812393188477, "learning_rate": 8.071651882371312e-05, "loss": 0.9765, "step": 5685 }, { "epoch": 0.3108696395011105, "grad_norm": 2.4413771629333496, "learning_rate": 8.070953246048006e-05, "loss": 1.2091, "step": 5686 }, { "epoch": 0.3109243123184692, "grad_norm": 2.8083643913269043, "learning_rate": 8.070254513437669e-05, "loss": 1.0743, "step": 5687 }, { "epoch": 0.3109789851358278, "grad_norm": 2.003206491470337, "learning_rate": 8.069555684562206e-05, "loss": 0.8997, "step": 5688 }, { "epoch": 0.3110336579531864, "grad_norm": 2.1767807006835938, "learning_rate": 8.068856759443532e-05, "loss": 1.0021, "step": 5689 }, { "epoch": 0.31108833077054504, "grad_norm": 2.8880908489227295, "learning_rate": 8.068157738103558e-05, "loss": 1.1319, "step": 5690 }, { "epoch": 0.31114300358790364, "grad_norm": 2.3088572025299072, "learning_rate": 8.067458620564205e-05, "loss": 1.0604, "step": 5691 }, { "epoch": 0.31119767640526225, "grad_norm": 2.639939785003662, "learning_rate": 8.066759406847389e-05, "loss": 1.2029, "step": 5692 }, { "epoch": 0.3112523492226209, "grad_norm": 2.809502124786377, "learning_rate": 8.066060096975037e-05, "loss": 1.1362, "step": 5693 }, { "epoch": 0.3113070220399795, "grad_norm": 4.955379486083984, "learning_rate": 8.065360690969073e-05, "loss": 1.2027, "step": 5694 }, { "epoch": 0.3113616948573381, "grad_norm": 2.1435482501983643, "learning_rate": 8.064661188851428e-05, "loss": 1.0057, "step": 5695 }, { "epoch": 0.3114163676746967, "grad_norm": 2.4127180576324463, "learning_rate": 8.063961590644031e-05, "loss": 1.0715, "step": 5696 }, { "epoch": 0.3114710404920554, "grad_norm": 2.4647974967956543, "learning_rate": 8.063261896368822e-05, "loss": 1.1426, "step": 5697 }, { "epoch": 0.311525713309414, "grad_norm": 2.3097951412200928, "learning_rate": 8.062562106047735e-05, "loss": 0.9425, "step": 5698 }, { "epoch": 0.3115803861267726, "grad_norm": 2.398888111114502, "learning_rate": 8.061862219702713e-05, "loss": 1.1463, "step": 5699 }, { "epoch": 0.31163505894413124, "grad_norm": 2.53005051612854, "learning_rate": 8.061162237355699e-05, "loss": 1.1406, "step": 5700 }, { "epoch": 0.31168973176148984, "grad_norm": 2.3770625591278076, "learning_rate": 8.060462159028645e-05, "loss": 1.1605, "step": 5701 }, { "epoch": 0.31174440457884844, "grad_norm": 2.7635202407836914, "learning_rate": 8.059761984743496e-05, "loss": 1.2384, "step": 5702 }, { "epoch": 0.31179907739620705, "grad_norm": 2.352020025253296, "learning_rate": 8.059061714522206e-05, "loss": 1.0751, "step": 5703 }, { "epoch": 0.3118537502135657, "grad_norm": 1.9978338479995728, "learning_rate": 8.058361348386736e-05, "loss": 1.0295, "step": 5704 }, { "epoch": 0.3119084230309243, "grad_norm": 2.3311357498168945, "learning_rate": 8.05766088635904e-05, "loss": 1.0389, "step": 5705 }, { "epoch": 0.3119630958482829, "grad_norm": 2.6653575897216797, "learning_rate": 8.056960328461083e-05, "loss": 1.1208, "step": 5706 }, { "epoch": 0.31201776866564157, "grad_norm": 2.004424571990967, "learning_rate": 8.05625967471483e-05, "loss": 0.953, "step": 5707 }, { "epoch": 0.3120724414830002, "grad_norm": 2.828975200653076, "learning_rate": 8.05555892514225e-05, "loss": 1.0335, "step": 5708 }, { "epoch": 0.3121271143003588, "grad_norm": 2.959826707839966, "learning_rate": 8.054858079765311e-05, "loss": 1.2265, "step": 5709 }, { "epoch": 0.31218178711771744, "grad_norm": 2.543036937713623, "learning_rate": 8.054157138605991e-05, "loss": 1.0721, "step": 5710 }, { "epoch": 0.31223645993507604, "grad_norm": 2.6112911701202393, "learning_rate": 8.053456101686267e-05, "loss": 1.1207, "step": 5711 }, { "epoch": 0.31229113275243464, "grad_norm": 2.487666606903076, "learning_rate": 8.05275496902812e-05, "loss": 1.0791, "step": 5712 }, { "epoch": 0.31234580556979324, "grad_norm": 2.26375412940979, "learning_rate": 8.05205374065353e-05, "loss": 1.1417, "step": 5713 }, { "epoch": 0.3124004783871519, "grad_norm": 3.597132921218872, "learning_rate": 8.051352416584486e-05, "loss": 1.3713, "step": 5714 }, { "epoch": 0.3124551512045105, "grad_norm": 2.0420539379119873, "learning_rate": 8.050650996842977e-05, "loss": 1.041, "step": 5715 }, { "epoch": 0.3125098240218691, "grad_norm": 2.7276124954223633, "learning_rate": 8.049949481450995e-05, "loss": 1.2332, "step": 5716 }, { "epoch": 0.31256449683922777, "grad_norm": 1.9527802467346191, "learning_rate": 8.049247870430538e-05, "loss": 0.9471, "step": 5717 }, { "epoch": 0.31261916965658637, "grad_norm": 2.9710681438446045, "learning_rate": 8.048546163803601e-05, "loss": 1.1909, "step": 5718 }, { "epoch": 0.312673842473945, "grad_norm": 2.700986623764038, "learning_rate": 8.047844361592185e-05, "loss": 1.1755, "step": 5719 }, { "epoch": 0.31272851529130363, "grad_norm": 2.6659765243530273, "learning_rate": 8.047142463818297e-05, "loss": 1.1431, "step": 5720 }, { "epoch": 0.31278318810866224, "grad_norm": 3.2562992572784424, "learning_rate": 8.046440470503943e-05, "loss": 1.0233, "step": 5721 }, { "epoch": 0.31283786092602084, "grad_norm": 2.778897285461426, "learning_rate": 8.045738381671136e-05, "loss": 1.1692, "step": 5722 }, { "epoch": 0.31289253374337944, "grad_norm": 2.3730742931365967, "learning_rate": 8.045036197341884e-05, "loss": 1.0843, "step": 5723 }, { "epoch": 0.3129472065607381, "grad_norm": 2.320852041244507, "learning_rate": 8.044333917538206e-05, "loss": 1.0601, "step": 5724 }, { "epoch": 0.3130018793780967, "grad_norm": 3.021451473236084, "learning_rate": 8.043631542282124e-05, "loss": 1.057, "step": 5725 }, { "epoch": 0.3130565521954553, "grad_norm": 2.3945066928863525, "learning_rate": 8.042929071595657e-05, "loss": 1.1112, "step": 5726 }, { "epoch": 0.31311122501281397, "grad_norm": 2.729372262954712, "learning_rate": 8.042226505500833e-05, "loss": 1.2723, "step": 5727 }, { "epoch": 0.31316589783017257, "grad_norm": 3.1517131328582764, "learning_rate": 8.041523844019678e-05, "loss": 1.3087, "step": 5728 }, { "epoch": 0.31322057064753117, "grad_norm": 3.6017849445343018, "learning_rate": 8.040821087174223e-05, "loss": 1.2613, "step": 5729 }, { "epoch": 0.3132752434648898, "grad_norm": 2.6208691596984863, "learning_rate": 8.040118234986504e-05, "loss": 1.1821, "step": 5730 }, { "epoch": 0.31332991628224843, "grad_norm": 2.205925464630127, "learning_rate": 8.03941528747856e-05, "loss": 1.1297, "step": 5731 }, { "epoch": 0.31338458909960704, "grad_norm": 2.475349187850952, "learning_rate": 8.038712244672426e-05, "loss": 0.9037, "step": 5732 }, { "epoch": 0.31343926191696564, "grad_norm": 4.900537490844727, "learning_rate": 8.038009106590151e-05, "loss": 1.1445, "step": 5733 }, { "epoch": 0.3134939347343243, "grad_norm": 2.163043737411499, "learning_rate": 8.037305873253778e-05, "loss": 1.1837, "step": 5734 }, { "epoch": 0.3135486075516829, "grad_norm": 2.0040178298950195, "learning_rate": 8.036602544685355e-05, "loss": 0.8548, "step": 5735 }, { "epoch": 0.3136032803690415, "grad_norm": 3.977526903152466, "learning_rate": 8.035899120906938e-05, "loss": 1.1694, "step": 5736 }, { "epoch": 0.31365795318640016, "grad_norm": 3.1097676753997803, "learning_rate": 8.03519560194058e-05, "loss": 1.0291, "step": 5737 }, { "epoch": 0.31371262600375877, "grad_norm": 2.171961784362793, "learning_rate": 8.03449198780834e-05, "loss": 1.0626, "step": 5738 }, { "epoch": 0.31376729882111737, "grad_norm": 2.127586841583252, "learning_rate": 8.033788278532279e-05, "loss": 1.0574, "step": 5739 }, { "epoch": 0.31382197163847597, "grad_norm": 2.3006153106689453, "learning_rate": 8.033084474134461e-05, "loss": 1.3211, "step": 5740 }, { "epoch": 0.31387664445583463, "grad_norm": 2.548530101776123, "learning_rate": 8.032380574636952e-05, "loss": 1.0775, "step": 5741 }, { "epoch": 0.31393131727319323, "grad_norm": 2.9228951930999756, "learning_rate": 8.031676580061824e-05, "loss": 0.982, "step": 5742 }, { "epoch": 0.31398599009055184, "grad_norm": 2.650207281112671, "learning_rate": 8.03097249043115e-05, "loss": 1.0379, "step": 5743 }, { "epoch": 0.3140406629079105, "grad_norm": 2.574291706085205, "learning_rate": 8.030268305767004e-05, "loss": 1.0544, "step": 5744 }, { "epoch": 0.3140953357252691, "grad_norm": 2.4289169311523438, "learning_rate": 8.029564026091468e-05, "loss": 1.006, "step": 5745 }, { "epoch": 0.3141500085426277, "grad_norm": 2.4022910594940186, "learning_rate": 8.028859651426623e-05, "loss": 1.061, "step": 5746 }, { "epoch": 0.3142046813599863, "grad_norm": 3.1832845211029053, "learning_rate": 8.028155181794553e-05, "loss": 1.0126, "step": 5747 }, { "epoch": 0.31425935417734496, "grad_norm": 2.0832276344299316, "learning_rate": 8.027450617217347e-05, "loss": 1.0238, "step": 5748 }, { "epoch": 0.31431402699470357, "grad_norm": 2.0122296810150146, "learning_rate": 8.026745957717097e-05, "loss": 0.9611, "step": 5749 }, { "epoch": 0.31436869981206217, "grad_norm": 2.61332106590271, "learning_rate": 8.026041203315894e-05, "loss": 1.0311, "step": 5750 }, { "epoch": 0.3144233726294208, "grad_norm": 2.5955963134765625, "learning_rate": 8.025336354035837e-05, "loss": 1.0919, "step": 5751 }, { "epoch": 0.31447804544677943, "grad_norm": 2.4532556533813477, "learning_rate": 8.024631409899026e-05, "loss": 1.0751, "step": 5752 }, { "epoch": 0.31453271826413803, "grad_norm": 2.114304780960083, "learning_rate": 8.023926370927564e-05, "loss": 1.0477, "step": 5753 }, { "epoch": 0.3145873910814967, "grad_norm": 2.085880756378174, "learning_rate": 8.023221237143557e-05, "loss": 1.0745, "step": 5754 }, { "epoch": 0.3146420638988553, "grad_norm": 4.637014389038086, "learning_rate": 8.022516008569112e-05, "loss": 1.0688, "step": 5755 }, { "epoch": 0.3146967367162139, "grad_norm": 2.966643810272217, "learning_rate": 8.021810685226342e-05, "loss": 1.3842, "step": 5756 }, { "epoch": 0.3147514095335725, "grad_norm": 2.6438446044921875, "learning_rate": 8.021105267137363e-05, "loss": 1.2207, "step": 5757 }, { "epoch": 0.31480608235093116, "grad_norm": 4.398162364959717, "learning_rate": 8.02039975432429e-05, "loss": 1.2715, "step": 5758 }, { "epoch": 0.31486075516828976, "grad_norm": 2.0401217937469482, "learning_rate": 8.019694146809247e-05, "loss": 0.813, "step": 5759 }, { "epoch": 0.31491542798564837, "grad_norm": 2.63362455368042, "learning_rate": 8.018988444614355e-05, "loss": 1.1563, "step": 5760 }, { "epoch": 0.314970100803007, "grad_norm": 2.795360565185547, "learning_rate": 8.018282647761742e-05, "loss": 1.052, "step": 5761 }, { "epoch": 0.31502477362036563, "grad_norm": 2.1154181957244873, "learning_rate": 8.017576756273539e-05, "loss": 1.0781, "step": 5762 }, { "epoch": 0.31507944643772423, "grad_norm": 2.2095370292663574, "learning_rate": 8.016870770171876e-05, "loss": 1.003, "step": 5763 }, { "epoch": 0.3151341192550829, "grad_norm": 2.8515748977661133, "learning_rate": 8.016164689478888e-05, "loss": 1.1131, "step": 5764 }, { "epoch": 0.3151887920724415, "grad_norm": 2.4327094554901123, "learning_rate": 8.015458514216716e-05, "loss": 1.0535, "step": 5765 }, { "epoch": 0.3152434648898001, "grad_norm": 2.433443307876587, "learning_rate": 8.014752244407501e-05, "loss": 1.1841, "step": 5766 }, { "epoch": 0.3152981377071587, "grad_norm": 2.711571455001831, "learning_rate": 8.014045880073387e-05, "loss": 1.2838, "step": 5767 }, { "epoch": 0.31535281052451736, "grad_norm": 2.1470253467559814, "learning_rate": 8.013339421236523e-05, "loss": 0.9945, "step": 5768 }, { "epoch": 0.31540748334187596, "grad_norm": 2.6554553508758545, "learning_rate": 8.012632867919055e-05, "loss": 1.0009, "step": 5769 }, { "epoch": 0.31546215615923456, "grad_norm": 3.2765579223632812, "learning_rate": 8.011926220143141e-05, "loss": 1.1884, "step": 5770 }, { "epoch": 0.3155168289765932, "grad_norm": 3.361206531524658, "learning_rate": 8.011219477930936e-05, "loss": 1.09, "step": 5771 }, { "epoch": 0.3155715017939518, "grad_norm": 2.323240041732788, "learning_rate": 8.010512641304599e-05, "loss": 1.04, "step": 5772 }, { "epoch": 0.31562617461131043, "grad_norm": 2.089718818664551, "learning_rate": 8.00980571028629e-05, "loss": 1.0457, "step": 5773 }, { "epoch": 0.31568084742866903, "grad_norm": 2.9567983150482178, "learning_rate": 8.009098684898178e-05, "loss": 1.1699, "step": 5774 }, { "epoch": 0.3157355202460277, "grad_norm": 2.8665125370025635, "learning_rate": 8.008391565162429e-05, "loss": 1.138, "step": 5775 }, { "epoch": 0.3157901930633863, "grad_norm": 3.11425518989563, "learning_rate": 8.007684351101215e-05, "loss": 1.0883, "step": 5776 }, { "epoch": 0.3158448658807449, "grad_norm": 2.2605433464050293, "learning_rate": 8.00697704273671e-05, "loss": 1.0444, "step": 5777 }, { "epoch": 0.31589953869810355, "grad_norm": 2.441035270690918, "learning_rate": 8.006269640091089e-05, "loss": 1.1493, "step": 5778 }, { "epoch": 0.31595421151546216, "grad_norm": 2.179877996444702, "learning_rate": 8.005562143186535e-05, "loss": 1.1579, "step": 5779 }, { "epoch": 0.31600888433282076, "grad_norm": 6.57317590713501, "learning_rate": 8.004854552045229e-05, "loss": 1.0786, "step": 5780 }, { "epoch": 0.3160635571501794, "grad_norm": 2.7383973598480225, "learning_rate": 8.004146866689358e-05, "loss": 0.957, "step": 5781 }, { "epoch": 0.316118229967538, "grad_norm": 2.241480827331543, "learning_rate": 8.00343908714111e-05, "loss": 0.8816, "step": 5782 }, { "epoch": 0.3161729027848966, "grad_norm": 2.574453353881836, "learning_rate": 8.002731213422676e-05, "loss": 1.0202, "step": 5783 }, { "epoch": 0.31622757560225523, "grad_norm": 2.565643310546875, "learning_rate": 8.002023245556254e-05, "loss": 1.1866, "step": 5784 }, { "epoch": 0.3162822484196139, "grad_norm": 2.149096727371216, "learning_rate": 8.00131518356404e-05, "loss": 1.1056, "step": 5785 }, { "epoch": 0.3163369212369725, "grad_norm": 2.3773608207702637, "learning_rate": 8.000607027468232e-05, "loss": 1.1605, "step": 5786 }, { "epoch": 0.3163915940543311, "grad_norm": 2.753726005554199, "learning_rate": 7.999898777291037e-05, "loss": 1.1536, "step": 5787 }, { "epoch": 0.31644626687168975, "grad_norm": 2.077867031097412, "learning_rate": 7.999190433054662e-05, "loss": 0.9468, "step": 5788 }, { "epoch": 0.31650093968904836, "grad_norm": 2.682657241821289, "learning_rate": 7.998481994781312e-05, "loss": 1.174, "step": 5789 }, { "epoch": 0.31655561250640696, "grad_norm": 2.3492002487182617, "learning_rate": 7.997773462493205e-05, "loss": 0.9838, "step": 5790 }, { "epoch": 0.3166102853237656, "grad_norm": 2.3812954425811768, "learning_rate": 7.997064836212553e-05, "loss": 1.1634, "step": 5791 }, { "epoch": 0.3166649581411242, "grad_norm": 2.8682148456573486, "learning_rate": 7.996356115961574e-05, "loss": 1.1228, "step": 5792 }, { "epoch": 0.3167196309584828, "grad_norm": 2.8360602855682373, "learning_rate": 7.995647301762492e-05, "loss": 1.2365, "step": 5793 }, { "epoch": 0.3167743037758414, "grad_norm": 2.119966506958008, "learning_rate": 7.994938393637529e-05, "loss": 0.9979, "step": 5794 }, { "epoch": 0.3168289765932001, "grad_norm": 2.1920006275177, "learning_rate": 7.994229391608913e-05, "loss": 1.0575, "step": 5795 }, { "epoch": 0.3168836494105587, "grad_norm": 2.9249205589294434, "learning_rate": 7.993520295698873e-05, "loss": 1.1998, "step": 5796 }, { "epoch": 0.3169383222279173, "grad_norm": 2.9174399375915527, "learning_rate": 7.992811105929645e-05, "loss": 1.0992, "step": 5797 }, { "epoch": 0.31699299504527595, "grad_norm": 2.7572178840637207, "learning_rate": 7.992101822323462e-05, "loss": 1.2195, "step": 5798 }, { "epoch": 0.31704766786263455, "grad_norm": 3.0956389904022217, "learning_rate": 7.991392444902565e-05, "loss": 1.0213, "step": 5799 }, { "epoch": 0.31710234067999316, "grad_norm": 2.213860511779785, "learning_rate": 7.990682973689194e-05, "loss": 1.214, "step": 5800 }, { "epoch": 0.31715701349735176, "grad_norm": 2.5443480014801025, "learning_rate": 7.989973408705596e-05, "loss": 1.2643, "step": 5801 }, { "epoch": 0.3172116863147104, "grad_norm": 2.502204418182373, "learning_rate": 7.989263749974016e-05, "loss": 1.1206, "step": 5802 }, { "epoch": 0.317266359132069, "grad_norm": 2.3536536693573, "learning_rate": 7.988553997516708e-05, "loss": 1.1697, "step": 5803 }, { "epoch": 0.3173210319494276, "grad_norm": 2.02205753326416, "learning_rate": 7.987844151355923e-05, "loss": 0.8958, "step": 5804 }, { "epoch": 0.3173757047667863, "grad_norm": 3.377023220062256, "learning_rate": 7.987134211513918e-05, "loss": 1.3125, "step": 5805 }, { "epoch": 0.3174303775841449, "grad_norm": 2.7468810081481934, "learning_rate": 7.986424178012955e-05, "loss": 0.9833, "step": 5806 }, { "epoch": 0.3174850504015035, "grad_norm": 2.69297456741333, "learning_rate": 7.985714050875295e-05, "loss": 1.0907, "step": 5807 }, { "epoch": 0.31753972321886215, "grad_norm": 2.584500551223755, "learning_rate": 7.9850038301232e-05, "loss": 0.9713, "step": 5808 }, { "epoch": 0.31759439603622075, "grad_norm": 2.4802942276000977, "learning_rate": 7.984293515778943e-05, "loss": 1.116, "step": 5809 }, { "epoch": 0.31764906885357935, "grad_norm": 2.582505226135254, "learning_rate": 7.983583107864794e-05, "loss": 1.2737, "step": 5810 }, { "epoch": 0.31770374167093796, "grad_norm": 2.3764078617095947, "learning_rate": 7.982872606403026e-05, "loss": 1.0817, "step": 5811 }, { "epoch": 0.3177584144882966, "grad_norm": 2.7209086418151855, "learning_rate": 7.98216201141592e-05, "loss": 1.3001, "step": 5812 }, { "epoch": 0.3178130873056552, "grad_norm": 2.57706618309021, "learning_rate": 7.981451322925749e-05, "loss": 1.121, "step": 5813 }, { "epoch": 0.3178677601230138, "grad_norm": 2.8013341426849365, "learning_rate": 7.980740540954803e-05, "loss": 1.0376, "step": 5814 }, { "epoch": 0.3179224329403725, "grad_norm": 3.224172592163086, "learning_rate": 7.980029665525364e-05, "loss": 0.9628, "step": 5815 }, { "epoch": 0.3179771057577311, "grad_norm": 2.558784008026123, "learning_rate": 7.97931869665972e-05, "loss": 1.2021, "step": 5816 }, { "epoch": 0.3180317785750897, "grad_norm": 2.6086974143981934, "learning_rate": 7.978607634380168e-05, "loss": 1.1691, "step": 5817 }, { "epoch": 0.31808645139244834, "grad_norm": 2.9324262142181396, "learning_rate": 7.977896478708999e-05, "loss": 1.2052, "step": 5818 }, { "epoch": 0.31814112420980695, "grad_norm": 2.3079288005828857, "learning_rate": 7.977185229668508e-05, "loss": 1.118, "step": 5819 }, { "epoch": 0.31819579702716555, "grad_norm": 1.5545698404312134, "learning_rate": 7.976473887281003e-05, "loss": 0.6425, "step": 5820 }, { "epoch": 0.31825046984452415, "grad_norm": 2.461635112762451, "learning_rate": 7.975762451568781e-05, "loss": 1.0064, "step": 5821 }, { "epoch": 0.3183051426618828, "grad_norm": 2.468047618865967, "learning_rate": 7.975050922554151e-05, "loss": 1.1637, "step": 5822 }, { "epoch": 0.3183598154792414, "grad_norm": 2.9828567504882812, "learning_rate": 7.974339300259421e-05, "loss": 1.1349, "step": 5823 }, { "epoch": 0.3184144882966, "grad_norm": 2.7969791889190674, "learning_rate": 7.973627584706906e-05, "loss": 1.1541, "step": 5824 }, { "epoch": 0.3184691611139587, "grad_norm": 2.3513848781585693, "learning_rate": 7.972915775918918e-05, "loss": 0.913, "step": 5825 }, { "epoch": 0.3185238339313173, "grad_norm": 2.889375925064087, "learning_rate": 7.972203873917778e-05, "loss": 1.1408, "step": 5826 }, { "epoch": 0.3185785067486759, "grad_norm": 2.6508328914642334, "learning_rate": 7.971491878725806e-05, "loss": 1.361, "step": 5827 }, { "epoch": 0.3186331795660345, "grad_norm": 3.5798516273498535, "learning_rate": 7.970779790365325e-05, "loss": 1.2721, "step": 5828 }, { "epoch": 0.31868785238339314, "grad_norm": 2.281782388687134, "learning_rate": 7.970067608858662e-05, "loss": 1.0715, "step": 5829 }, { "epoch": 0.31874252520075175, "grad_norm": 2.604450225830078, "learning_rate": 7.969355334228148e-05, "loss": 1.1737, "step": 5830 }, { "epoch": 0.31879719801811035, "grad_norm": 2.280341386795044, "learning_rate": 7.968642966496116e-05, "loss": 0.9609, "step": 5831 }, { "epoch": 0.318851870835469, "grad_norm": 3.352757453918457, "learning_rate": 7.9679305056849e-05, "loss": 0.9332, "step": 5832 }, { "epoch": 0.3189065436528276, "grad_norm": 2.623612403869629, "learning_rate": 7.967217951816839e-05, "loss": 1.2203, "step": 5833 }, { "epoch": 0.3189612164701862, "grad_norm": 2.0906245708465576, "learning_rate": 7.966505304914276e-05, "loss": 1.1135, "step": 5834 }, { "epoch": 0.3190158892875449, "grad_norm": 2.2762811183929443, "learning_rate": 7.965792564999554e-05, "loss": 1.2512, "step": 5835 }, { "epoch": 0.3190705621049035, "grad_norm": 1.7884734869003296, "learning_rate": 7.96507973209502e-05, "loss": 0.8479, "step": 5836 }, { "epoch": 0.3191252349222621, "grad_norm": 2.418576955795288, "learning_rate": 7.964366806223025e-05, "loss": 0.9756, "step": 5837 }, { "epoch": 0.3191799077396207, "grad_norm": 3.845339059829712, "learning_rate": 7.963653787405922e-05, "loss": 1.0375, "step": 5838 }, { "epoch": 0.31923458055697934, "grad_norm": 2.442208766937256, "learning_rate": 7.962940675666068e-05, "loss": 1.0956, "step": 5839 }, { "epoch": 0.31928925337433794, "grad_norm": 3.473886013031006, "learning_rate": 7.962227471025821e-05, "loss": 0.9438, "step": 5840 }, { "epoch": 0.31934392619169655, "grad_norm": 3.1281754970550537, "learning_rate": 7.961514173507542e-05, "loss": 1.1175, "step": 5841 }, { "epoch": 0.3193985990090552, "grad_norm": 3.3897056579589844, "learning_rate": 7.960800783133599e-05, "loss": 1.2176, "step": 5842 }, { "epoch": 0.3194532718264138, "grad_norm": 2.5148205757141113, "learning_rate": 7.960087299926355e-05, "loss": 1.0215, "step": 5843 }, { "epoch": 0.3195079446437724, "grad_norm": 2.321197271347046, "learning_rate": 7.959373723908186e-05, "loss": 1.0896, "step": 5844 }, { "epoch": 0.31956261746113107, "grad_norm": 2.183973789215088, "learning_rate": 7.95866005510146e-05, "loss": 0.8874, "step": 5845 }, { "epoch": 0.3196172902784897, "grad_norm": 2.4613728523254395, "learning_rate": 7.957946293528557e-05, "loss": 1.0764, "step": 5846 }, { "epoch": 0.3196719630958483, "grad_norm": 2.8994181156158447, "learning_rate": 7.957232439211857e-05, "loss": 1.1556, "step": 5847 }, { "epoch": 0.3197266359132069, "grad_norm": 2.0591702461242676, "learning_rate": 7.956518492173742e-05, "loss": 1.1546, "step": 5848 }, { "epoch": 0.31978130873056554, "grad_norm": 3.9153366088867188, "learning_rate": 7.955804452436592e-05, "loss": 1.1988, "step": 5849 }, { "epoch": 0.31983598154792414, "grad_norm": 2.6895413398742676, "learning_rate": 7.955090320022802e-05, "loss": 1.1258, "step": 5850 }, { "epoch": 0.31989065436528274, "grad_norm": 2.2951762676239014, "learning_rate": 7.95437609495476e-05, "loss": 0.9992, "step": 5851 }, { "epoch": 0.3199453271826414, "grad_norm": 2.6772820949554443, "learning_rate": 7.953661777254858e-05, "loss": 0.9768, "step": 5852 }, { "epoch": 0.32, "grad_norm": 3.5161142349243164, "learning_rate": 7.952947366945495e-05, "loss": 0.8725, "step": 5853 }, { "epoch": 0.3200546728173586, "grad_norm": 2.1373066902160645, "learning_rate": 7.952232864049075e-05, "loss": 0.9923, "step": 5854 }, { "epoch": 0.3201093456347172, "grad_norm": 4.539252281188965, "learning_rate": 7.951518268587992e-05, "loss": 1.043, "step": 5855 }, { "epoch": 0.32016401845207587, "grad_norm": 2.410313844680786, "learning_rate": 7.950803580584655e-05, "loss": 1.0957, "step": 5856 }, { "epoch": 0.3202186912694345, "grad_norm": 2.494316816329956, "learning_rate": 7.950088800061475e-05, "loss": 1.1751, "step": 5857 }, { "epoch": 0.3202733640867931, "grad_norm": 1.9755929708480835, "learning_rate": 7.949373927040861e-05, "loss": 0.9484, "step": 5858 }, { "epoch": 0.32032803690415174, "grad_norm": 2.953920841217041, "learning_rate": 7.948658961545228e-05, "loss": 1.1448, "step": 5859 }, { "epoch": 0.32038270972151034, "grad_norm": 5.70904016494751, "learning_rate": 7.947943903596992e-05, "loss": 1.005, "step": 5860 }, { "epoch": 0.32043738253886894, "grad_norm": 3.329857349395752, "learning_rate": 7.947228753218574e-05, "loss": 1.0345, "step": 5861 }, { "epoch": 0.3204920553562276, "grad_norm": 2.328744649887085, "learning_rate": 7.946513510432397e-05, "loss": 1.2049, "step": 5862 }, { "epoch": 0.3205467281735862, "grad_norm": 2.716299533843994, "learning_rate": 7.945798175260885e-05, "loss": 1.0969, "step": 5863 }, { "epoch": 0.3206014009909448, "grad_norm": 2.0893752574920654, "learning_rate": 7.94508274772647e-05, "loss": 0.9235, "step": 5864 }, { "epoch": 0.3206560738083034, "grad_norm": 2.2083778381347656, "learning_rate": 7.944367227851581e-05, "loss": 1.2766, "step": 5865 }, { "epoch": 0.32071074662566207, "grad_norm": 4.24208927154541, "learning_rate": 7.943651615658654e-05, "loss": 1.2379, "step": 5866 }, { "epoch": 0.32076541944302067, "grad_norm": 2.5345780849456787, "learning_rate": 7.942935911170123e-05, "loss": 0.8916, "step": 5867 }, { "epoch": 0.3208200922603793, "grad_norm": 3.8370232582092285, "learning_rate": 7.942220114408433e-05, "loss": 0.9966, "step": 5868 }, { "epoch": 0.32087476507773793, "grad_norm": 2.470829963684082, "learning_rate": 7.941504225396024e-05, "loss": 1.1038, "step": 5869 }, { "epoch": 0.32092943789509654, "grad_norm": 2.610509157180786, "learning_rate": 7.940788244155344e-05, "loss": 1.029, "step": 5870 }, { "epoch": 0.32098411071245514, "grad_norm": 1.920748233795166, "learning_rate": 7.940072170708842e-05, "loss": 1.0182, "step": 5871 }, { "epoch": 0.3210387835298138, "grad_norm": 2.430056095123291, "learning_rate": 7.939356005078967e-05, "loss": 0.9384, "step": 5872 }, { "epoch": 0.3210934563471724, "grad_norm": 2.1015403270721436, "learning_rate": 7.938639747288177e-05, "loss": 1.0072, "step": 5873 }, { "epoch": 0.321148129164531, "grad_norm": 2.902498245239258, "learning_rate": 7.937923397358928e-05, "loss": 1.1411, "step": 5874 }, { "epoch": 0.3212028019818896, "grad_norm": 2.4137957096099854, "learning_rate": 7.937206955313681e-05, "loss": 1.3338, "step": 5875 }, { "epoch": 0.32125747479924827, "grad_norm": 2.4957685470581055, "learning_rate": 7.936490421174901e-05, "loss": 1.2724, "step": 5876 }, { "epoch": 0.32131214761660687, "grad_norm": 2.576184034347534, "learning_rate": 7.935773794965049e-05, "loss": 1.2466, "step": 5877 }, { "epoch": 0.32136682043396547, "grad_norm": 2.6554806232452393, "learning_rate": 7.9350570767066e-05, "loss": 1.1277, "step": 5878 }, { "epoch": 0.32142149325132413, "grad_norm": 2.509488821029663, "learning_rate": 7.934340266422022e-05, "loss": 1.1098, "step": 5879 }, { "epoch": 0.32147616606868273, "grad_norm": 2.694582462310791, "learning_rate": 7.933623364133793e-05, "loss": 1.2474, "step": 5880 }, { "epoch": 0.32153083888604134, "grad_norm": 2.142352342605591, "learning_rate": 7.93290636986439e-05, "loss": 1.0541, "step": 5881 }, { "epoch": 0.32158551170339994, "grad_norm": 2.5921154022216797, "learning_rate": 7.932189283636293e-05, "loss": 1.1296, "step": 5882 }, { "epoch": 0.3216401845207586, "grad_norm": 2.1979379653930664, "learning_rate": 7.931472105471986e-05, "loss": 1.1363, "step": 5883 }, { "epoch": 0.3216948573381172, "grad_norm": 2.9512765407562256, "learning_rate": 7.930754835393956e-05, "loss": 1.3462, "step": 5884 }, { "epoch": 0.3217495301554758, "grad_norm": 2.292696714401245, "learning_rate": 7.93003747342469e-05, "loss": 1.2722, "step": 5885 }, { "epoch": 0.32180420297283446, "grad_norm": 2.631542444229126, "learning_rate": 7.929320019586683e-05, "loss": 1.2008, "step": 5886 }, { "epoch": 0.32185887579019307, "grad_norm": 2.1114885807037354, "learning_rate": 7.92860247390243e-05, "loss": 1.0869, "step": 5887 }, { "epoch": 0.32191354860755167, "grad_norm": 2.8122875690460205, "learning_rate": 7.927884836394428e-05, "loss": 0.9554, "step": 5888 }, { "epoch": 0.32196822142491033, "grad_norm": 3.0726327896118164, "learning_rate": 7.927167107085177e-05, "loss": 1.0581, "step": 5889 }, { "epoch": 0.32202289424226893, "grad_norm": 2.2587037086486816, "learning_rate": 7.926449285997183e-05, "loss": 1.0972, "step": 5890 }, { "epoch": 0.32207756705962753, "grad_norm": 3.227198362350464, "learning_rate": 7.925731373152952e-05, "loss": 1.0795, "step": 5891 }, { "epoch": 0.32213223987698614, "grad_norm": 3.314692974090576, "learning_rate": 7.925013368574992e-05, "loss": 1.1786, "step": 5892 }, { "epoch": 0.3221869126943448, "grad_norm": 3.106321096420288, "learning_rate": 7.924295272285815e-05, "loss": 1.3567, "step": 5893 }, { "epoch": 0.3222415855117034, "grad_norm": 2.384752035140991, "learning_rate": 7.92357708430794e-05, "loss": 1.1004, "step": 5894 }, { "epoch": 0.322296258329062, "grad_norm": 2.373267650604248, "learning_rate": 7.922858804663882e-05, "loss": 1.2875, "step": 5895 }, { "epoch": 0.32235093114642066, "grad_norm": 2.3895137310028076, "learning_rate": 7.922140433376161e-05, "loss": 1.2128, "step": 5896 }, { "epoch": 0.32240560396377926, "grad_norm": 1.861809253692627, "learning_rate": 7.921421970467307e-05, "loss": 0.9105, "step": 5897 }, { "epoch": 0.32246027678113787, "grad_norm": 2.2437734603881836, "learning_rate": 7.92070341595984e-05, "loss": 1.1278, "step": 5898 }, { "epoch": 0.32251494959849647, "grad_norm": 3.1202149391174316, "learning_rate": 7.919984769876292e-05, "loss": 1.043, "step": 5899 }, { "epoch": 0.32256962241585513, "grad_norm": 3.08528733253479, "learning_rate": 7.919266032239196e-05, "loss": 1.1914, "step": 5900 }, { "epoch": 0.32262429523321373, "grad_norm": 2.472496747970581, "learning_rate": 7.918547203071087e-05, "loss": 0.9581, "step": 5901 }, { "epoch": 0.32267896805057233, "grad_norm": 2.5176801681518555, "learning_rate": 7.917828282394504e-05, "loss": 1.2726, "step": 5902 }, { "epoch": 0.322733640867931, "grad_norm": 2.6854918003082275, "learning_rate": 7.917109270231987e-05, "loss": 1.1622, "step": 5903 }, { "epoch": 0.3227883136852896, "grad_norm": 2.9358179569244385, "learning_rate": 7.91639016660608e-05, "loss": 1.1894, "step": 5904 }, { "epoch": 0.3228429865026482, "grad_norm": 2.2081618309020996, "learning_rate": 7.91567097153933e-05, "loss": 1.04, "step": 5905 }, { "epoch": 0.32289765932000686, "grad_norm": 2.6619248390197754, "learning_rate": 7.914951685054288e-05, "loss": 0.9991, "step": 5906 }, { "epoch": 0.32295233213736546, "grad_norm": 2.713846445083618, "learning_rate": 7.914232307173506e-05, "loss": 1.2748, "step": 5907 }, { "epoch": 0.32300700495472406, "grad_norm": 1.9295566082000732, "learning_rate": 7.913512837919538e-05, "loss": 0.8606, "step": 5908 }, { "epoch": 0.32306167777208267, "grad_norm": 2.799034357070923, "learning_rate": 7.912793277314945e-05, "loss": 1.2206, "step": 5909 }, { "epoch": 0.3231163505894413, "grad_norm": 2.728132724761963, "learning_rate": 7.912073625382286e-05, "loss": 1.1961, "step": 5910 }, { "epoch": 0.32317102340679993, "grad_norm": 2.9032249450683594, "learning_rate": 7.911353882144124e-05, "loss": 1.2275, "step": 5911 }, { "epoch": 0.32322569622415853, "grad_norm": 2.1082398891448975, "learning_rate": 7.91063404762303e-05, "loss": 1.0959, "step": 5912 }, { "epoch": 0.3232803690415172, "grad_norm": 2.0619661808013916, "learning_rate": 7.90991412184157e-05, "loss": 1.1658, "step": 5913 }, { "epoch": 0.3233350418588758, "grad_norm": 2.2652323246002197, "learning_rate": 7.90919410482232e-05, "loss": 1.1463, "step": 5914 }, { "epoch": 0.3233897146762344, "grad_norm": 2.3976356983184814, "learning_rate": 7.90847399658785e-05, "loss": 1.0281, "step": 5915 }, { "epoch": 0.32344438749359306, "grad_norm": 2.6139888763427734, "learning_rate": 7.907753797160744e-05, "loss": 0.9423, "step": 5916 }, { "epoch": 0.32349906031095166, "grad_norm": 2.7932894229888916, "learning_rate": 7.90703350656358e-05, "loss": 1.0273, "step": 5917 }, { "epoch": 0.32355373312831026, "grad_norm": 2.6634485721588135, "learning_rate": 7.906313124818945e-05, "loss": 1.3252, "step": 5918 }, { "epoch": 0.32360840594566886, "grad_norm": 2.894843578338623, "learning_rate": 7.905592651949423e-05, "loss": 1.117, "step": 5919 }, { "epoch": 0.3236630787630275, "grad_norm": 2.233476400375366, "learning_rate": 7.904872087977604e-05, "loss": 1.1517, "step": 5920 }, { "epoch": 0.3237177515803861, "grad_norm": 2.2658932209014893, "learning_rate": 7.904151432926083e-05, "loss": 1.0365, "step": 5921 }, { "epoch": 0.32377242439774473, "grad_norm": 2.1707403659820557, "learning_rate": 7.903430686817452e-05, "loss": 0.7732, "step": 5922 }, { "epoch": 0.3238270972151034, "grad_norm": 2.2374801635742188, "learning_rate": 7.902709849674315e-05, "loss": 1.2572, "step": 5923 }, { "epoch": 0.323881770032462, "grad_norm": 2.3942601680755615, "learning_rate": 7.901988921519267e-05, "loss": 0.9679, "step": 5924 }, { "epoch": 0.3239364428498206, "grad_norm": 2.49094295501709, "learning_rate": 7.901267902374914e-05, "loss": 1.0328, "step": 5925 }, { "epoch": 0.3239911156671792, "grad_norm": 2.6408162117004395, "learning_rate": 7.900546792263864e-05, "loss": 1.2151, "step": 5926 }, { "epoch": 0.32404578848453786, "grad_norm": 2.0900793075561523, "learning_rate": 7.899825591208728e-05, "loss": 1.0559, "step": 5927 }, { "epoch": 0.32410046130189646, "grad_norm": 2.511892557144165, "learning_rate": 7.899104299232116e-05, "loss": 1.0746, "step": 5928 }, { "epoch": 0.32415513411925506, "grad_norm": 4.300947189331055, "learning_rate": 7.898382916356643e-05, "loss": 1.1172, "step": 5929 }, { "epoch": 0.3242098069366137, "grad_norm": 2.173466682434082, "learning_rate": 7.897661442604932e-05, "loss": 1.0134, "step": 5930 }, { "epoch": 0.3242644797539723, "grad_norm": 2.684448003768921, "learning_rate": 7.896939877999599e-05, "loss": 1.1558, "step": 5931 }, { "epoch": 0.3243191525713309, "grad_norm": 2.3558101654052734, "learning_rate": 7.89621822256327e-05, "loss": 1.1943, "step": 5932 }, { "epoch": 0.3243738253886896, "grad_norm": 3.2023394107818604, "learning_rate": 7.895496476318571e-05, "loss": 1.3382, "step": 5933 }, { "epoch": 0.3244284982060482, "grad_norm": 2.168214797973633, "learning_rate": 7.894774639288134e-05, "loss": 0.6646, "step": 5934 }, { "epoch": 0.3244831710234068, "grad_norm": 2.640223741531372, "learning_rate": 7.89405271149459e-05, "loss": 0.8679, "step": 5935 }, { "epoch": 0.3245378438407654, "grad_norm": 2.4702773094177246, "learning_rate": 7.893330692960574e-05, "loss": 1.0426, "step": 5936 }, { "epoch": 0.32459251665812405, "grad_norm": 2.3834047317504883, "learning_rate": 7.892608583708724e-05, "loss": 1.0881, "step": 5937 }, { "epoch": 0.32464718947548266, "grad_norm": 4.393484592437744, "learning_rate": 7.891886383761684e-05, "loss": 0.9886, "step": 5938 }, { "epoch": 0.32470186229284126, "grad_norm": 2.6088268756866455, "learning_rate": 7.891164093142095e-05, "loss": 0.9214, "step": 5939 }, { "epoch": 0.3247565351101999, "grad_norm": 2.3399670124053955, "learning_rate": 7.890441711872604e-05, "loss": 0.9799, "step": 5940 }, { "epoch": 0.3248112079275585, "grad_norm": 2.420706272125244, "learning_rate": 7.889719239975861e-05, "loss": 1.0071, "step": 5941 }, { "epoch": 0.3248658807449171, "grad_norm": 2.5961570739746094, "learning_rate": 7.88899667747452e-05, "loss": 1.0025, "step": 5942 }, { "epoch": 0.3249205535622758, "grad_norm": 3.6119070053100586, "learning_rate": 7.888274024391234e-05, "loss": 1.1357, "step": 5943 }, { "epoch": 0.3249752263796344, "grad_norm": 2.7473678588867188, "learning_rate": 7.887551280748664e-05, "loss": 1.1543, "step": 5944 }, { "epoch": 0.325029899196993, "grad_norm": 4.1389689445495605, "learning_rate": 7.886828446569467e-05, "loss": 1.3443, "step": 5945 }, { "epoch": 0.3250845720143516, "grad_norm": 1.8889883756637573, "learning_rate": 7.886105521876309e-05, "loss": 0.9308, "step": 5946 }, { "epoch": 0.32513924483171025, "grad_norm": 2.532900094985962, "learning_rate": 7.885382506691858e-05, "loss": 0.9223, "step": 5947 }, { "epoch": 0.32519391764906885, "grad_norm": 2.3233606815338135, "learning_rate": 7.88465940103878e-05, "loss": 1.0487, "step": 5948 }, { "epoch": 0.32524859046642746, "grad_norm": 3.1202566623687744, "learning_rate": 7.883936204939752e-05, "loss": 1.3104, "step": 5949 }, { "epoch": 0.3253032632837861, "grad_norm": 2.8740956783294678, "learning_rate": 7.883212918417446e-05, "loss": 1.1617, "step": 5950 }, { "epoch": 0.3253579361011447, "grad_norm": 2.8106276988983154, "learning_rate": 7.88248954149454e-05, "loss": 1.07, "step": 5951 }, { "epoch": 0.3254126089185033, "grad_norm": 2.917902946472168, "learning_rate": 7.881766074193716e-05, "loss": 1.2141, "step": 5952 }, { "epoch": 0.3254672817358619, "grad_norm": 2.9323201179504395, "learning_rate": 7.881042516537658e-05, "loss": 1.1746, "step": 5953 }, { "epoch": 0.3255219545532206, "grad_norm": 2.806117534637451, "learning_rate": 7.88031886854905e-05, "loss": 1.1497, "step": 5954 }, { "epoch": 0.3255766273705792, "grad_norm": 2.7369751930236816, "learning_rate": 7.879595130250584e-05, "loss": 1.0951, "step": 5955 }, { "epoch": 0.3256313001879378, "grad_norm": 3.251248359680176, "learning_rate": 7.878871301664951e-05, "loss": 1.0024, "step": 5956 }, { "epoch": 0.32568597300529645, "grad_norm": 2.1002285480499268, "learning_rate": 7.878147382814846e-05, "loss": 1.01, "step": 5957 }, { "epoch": 0.32574064582265505, "grad_norm": 2.6365795135498047, "learning_rate": 7.877423373722969e-05, "loss": 1.0267, "step": 5958 }, { "epoch": 0.32579531864001365, "grad_norm": 2.61112642288208, "learning_rate": 7.876699274412017e-05, "loss": 1.0951, "step": 5959 }, { "epoch": 0.3258499914573723, "grad_norm": 1.9146528244018555, "learning_rate": 7.875975084904694e-05, "loss": 1.1025, "step": 5960 }, { "epoch": 0.3259046642747309, "grad_norm": 2.3053832054138184, "learning_rate": 7.87525080522371e-05, "loss": 1.2146, "step": 5961 }, { "epoch": 0.3259593370920895, "grad_norm": 2.8376898765563965, "learning_rate": 7.874526435391771e-05, "loss": 1.191, "step": 5962 }, { "epoch": 0.3260140099094481, "grad_norm": 3.904877185821533, "learning_rate": 7.873801975431589e-05, "loss": 1.1087, "step": 5963 }, { "epoch": 0.3260686827268068, "grad_norm": 2.4172091484069824, "learning_rate": 7.873077425365881e-05, "loss": 1.2495, "step": 5964 }, { "epoch": 0.3261233555441654, "grad_norm": 2.563579797744751, "learning_rate": 7.872352785217362e-05, "loss": 0.8975, "step": 5965 }, { "epoch": 0.326178028361524, "grad_norm": 3.017725706100464, "learning_rate": 7.871628055008754e-05, "loss": 0.9294, "step": 5966 }, { "epoch": 0.32623270117888264, "grad_norm": 2.9510498046875, "learning_rate": 7.87090323476278e-05, "loss": 1.1028, "step": 5967 }, { "epoch": 0.32628737399624125, "grad_norm": 2.296053647994995, "learning_rate": 7.870178324502166e-05, "loss": 1.2122, "step": 5968 }, { "epoch": 0.32634204681359985, "grad_norm": 2.2399330139160156, "learning_rate": 7.86945332424964e-05, "loss": 1.181, "step": 5969 }, { "epoch": 0.3263967196309585, "grad_norm": 2.409343719482422, "learning_rate": 7.868728234027936e-05, "loss": 1.201, "step": 5970 }, { "epoch": 0.3264513924483171, "grad_norm": 2.401675224304199, "learning_rate": 7.868003053859785e-05, "loss": 1.1986, "step": 5971 }, { "epoch": 0.3265060652656757, "grad_norm": 2.2434961795806885, "learning_rate": 7.867277783767928e-05, "loss": 0.9133, "step": 5972 }, { "epoch": 0.3265607380830343, "grad_norm": 2.2069432735443115, "learning_rate": 7.866552423775105e-05, "loss": 1.0631, "step": 5973 }, { "epoch": 0.326615410900393, "grad_norm": 3.2066569328308105, "learning_rate": 7.865826973904057e-05, "loss": 1.0665, "step": 5974 }, { "epoch": 0.3266700837177516, "grad_norm": 2.4137496948242188, "learning_rate": 7.86510143417753e-05, "loss": 1.0123, "step": 5975 }, { "epoch": 0.3267247565351102, "grad_norm": 2.406158447265625, "learning_rate": 7.864375804618274e-05, "loss": 1.2497, "step": 5976 }, { "epoch": 0.32677942935246884, "grad_norm": 2.315488338470459, "learning_rate": 7.863650085249039e-05, "loss": 0.9955, "step": 5977 }, { "epoch": 0.32683410216982745, "grad_norm": 2.5691354274749756, "learning_rate": 7.86292427609258e-05, "loss": 1.1694, "step": 5978 }, { "epoch": 0.32688877498718605, "grad_norm": 2.177870988845825, "learning_rate": 7.862198377171655e-05, "loss": 0.9181, "step": 5979 }, { "epoch": 0.32694344780454465, "grad_norm": 2.5005033016204834, "learning_rate": 7.861472388509022e-05, "loss": 1.1651, "step": 5980 }, { "epoch": 0.3269981206219033, "grad_norm": 2.7041056156158447, "learning_rate": 7.860746310127447e-05, "loss": 1.3466, "step": 5981 }, { "epoch": 0.3270527934392619, "grad_norm": 2.5508782863616943, "learning_rate": 7.860020142049691e-05, "loss": 1.1044, "step": 5982 }, { "epoch": 0.3271074662566205, "grad_norm": 2.1708791255950928, "learning_rate": 7.859293884298527e-05, "loss": 1.0006, "step": 5983 }, { "epoch": 0.3271621390739792, "grad_norm": 2.20939302444458, "learning_rate": 7.858567536896722e-05, "loss": 1.3076, "step": 5984 }, { "epoch": 0.3272168118913378, "grad_norm": 1.9584665298461914, "learning_rate": 7.857841099867051e-05, "loss": 1.13, "step": 5985 }, { "epoch": 0.3272714847086964, "grad_norm": 3.167515993118286, "learning_rate": 7.857114573232294e-05, "loss": 0.9857, "step": 5986 }, { "epoch": 0.32732615752605504, "grad_norm": 3.075277090072632, "learning_rate": 7.856387957015228e-05, "loss": 1.213, "step": 5987 }, { "epoch": 0.32738083034341364, "grad_norm": 2.6073453426361084, "learning_rate": 7.855661251238635e-05, "loss": 1.1871, "step": 5988 }, { "epoch": 0.32743550316077225, "grad_norm": 2.4954285621643066, "learning_rate": 7.854934455925302e-05, "loss": 1.1219, "step": 5989 }, { "epoch": 0.32749017597813085, "grad_norm": 2.571702480316162, "learning_rate": 7.854207571098015e-05, "loss": 1.1278, "step": 5990 }, { "epoch": 0.3275448487954895, "grad_norm": 2.7797396183013916, "learning_rate": 7.853480596779565e-05, "loss": 1.0555, "step": 5991 }, { "epoch": 0.3275995216128481, "grad_norm": 2.0889503955841064, "learning_rate": 7.85275353299275e-05, "loss": 1.095, "step": 5992 }, { "epoch": 0.3276541944302067, "grad_norm": 2.2886152267456055, "learning_rate": 7.85202637976036e-05, "loss": 1.1543, "step": 5993 }, { "epoch": 0.32770886724756537, "grad_norm": 3.45562481880188, "learning_rate": 7.851299137105195e-05, "loss": 1.1479, "step": 5994 }, { "epoch": 0.327763540064924, "grad_norm": 3.0316691398620605, "learning_rate": 7.850571805050062e-05, "loss": 1.0443, "step": 5995 }, { "epoch": 0.3278182128822826, "grad_norm": 1.8794705867767334, "learning_rate": 7.849844383617764e-05, "loss": 0.895, "step": 5996 }, { "epoch": 0.32787288569964124, "grad_norm": 3.035585641860962, "learning_rate": 7.849116872831106e-05, "loss": 1.0216, "step": 5997 }, { "epoch": 0.32792755851699984, "grad_norm": 3.086665630340576, "learning_rate": 7.8483892727129e-05, "loss": 1.0105, "step": 5998 }, { "epoch": 0.32798223133435844, "grad_norm": 2.149017095565796, "learning_rate": 7.847661583285959e-05, "loss": 1.0831, "step": 5999 }, { "epoch": 0.32803690415171705, "grad_norm": 2.8337972164154053, "learning_rate": 7.8469338045731e-05, "loss": 1.0942, "step": 6000 }, { "epoch": 0.3280915769690757, "grad_norm": 2.129328727722168, "learning_rate": 7.846205936597142e-05, "loss": 1.066, "step": 6001 }, { "epoch": 0.3281462497864343, "grad_norm": 2.9846255779266357, "learning_rate": 7.845477979380907e-05, "loss": 1.1208, "step": 6002 }, { "epoch": 0.3282009226037929, "grad_norm": 2.630842447280884, "learning_rate": 7.844749932947217e-05, "loss": 1.0566, "step": 6003 }, { "epoch": 0.32825559542115157, "grad_norm": 2.8215954303741455, "learning_rate": 7.844021797318899e-05, "loss": 1.2999, "step": 6004 }, { "epoch": 0.3283102682385102, "grad_norm": 3.0393052101135254, "learning_rate": 7.843293572518787e-05, "loss": 1.0856, "step": 6005 }, { "epoch": 0.3283649410558688, "grad_norm": 2.107428550720215, "learning_rate": 7.842565258569712e-05, "loss": 1.084, "step": 6006 }, { "epoch": 0.3284196138732274, "grad_norm": 2.5372581481933594, "learning_rate": 7.841836855494507e-05, "loss": 1.2749, "step": 6007 }, { "epoch": 0.32847428669058604, "grad_norm": 2.3950982093811035, "learning_rate": 7.841108363316015e-05, "loss": 0.9418, "step": 6008 }, { "epoch": 0.32852895950794464, "grad_norm": 2.8205137252807617, "learning_rate": 7.840379782057072e-05, "loss": 1.2011, "step": 6009 }, { "epoch": 0.32858363232530324, "grad_norm": 2.4707581996917725, "learning_rate": 7.839651111740528e-05, "loss": 1.0697, "step": 6010 }, { "epoch": 0.3286383051426619, "grad_norm": 3.4816887378692627, "learning_rate": 7.838922352389226e-05, "loss": 1.1049, "step": 6011 }, { "epoch": 0.3286929779600205, "grad_norm": 2.508023500442505, "learning_rate": 7.838193504026015e-05, "loss": 1.0612, "step": 6012 }, { "epoch": 0.3287476507773791, "grad_norm": 2.997469902038574, "learning_rate": 7.837464566673752e-05, "loss": 1.0838, "step": 6013 }, { "epoch": 0.32880232359473777, "grad_norm": 2.2805914878845215, "learning_rate": 7.836735540355285e-05, "loss": 0.9993, "step": 6014 }, { "epoch": 0.32885699641209637, "grad_norm": 1.8537694215774536, "learning_rate": 7.836006425093476e-05, "loss": 0.8716, "step": 6015 }, { "epoch": 0.328911669229455, "grad_norm": 2.5326783657073975, "learning_rate": 7.835277220911188e-05, "loss": 1.1337, "step": 6016 }, { "epoch": 0.3289663420468136, "grad_norm": 2.2602782249450684, "learning_rate": 7.834547927831282e-05, "loss": 0.986, "step": 6017 }, { "epoch": 0.32902101486417223, "grad_norm": 2.097794771194458, "learning_rate": 7.833818545876623e-05, "loss": 1.056, "step": 6018 }, { "epoch": 0.32907568768153084, "grad_norm": 4.116666316986084, "learning_rate": 7.833089075070084e-05, "loss": 1.3083, "step": 6019 }, { "epoch": 0.32913036049888944, "grad_norm": 2.3136305809020996, "learning_rate": 7.832359515434534e-05, "loss": 1.0462, "step": 6020 }, { "epoch": 0.3291850333162481, "grad_norm": 4.168988227844238, "learning_rate": 7.831629866992847e-05, "loss": 1.091, "step": 6021 }, { "epoch": 0.3292397061336067, "grad_norm": 2.55478835105896, "learning_rate": 7.830900129767902e-05, "loss": 0.9332, "step": 6022 }, { "epoch": 0.3292943789509653, "grad_norm": 2.5272533893585205, "learning_rate": 7.830170303782579e-05, "loss": 1.0483, "step": 6023 }, { "epoch": 0.32934905176832396, "grad_norm": 2.9051337242126465, "learning_rate": 7.829440389059761e-05, "loss": 1.2087, "step": 6024 }, { "epoch": 0.32940372458568257, "grad_norm": 2.451237916946411, "learning_rate": 7.828710385622335e-05, "loss": 1.0048, "step": 6025 }, { "epoch": 0.32945839740304117, "grad_norm": 3.5511786937713623, "learning_rate": 7.827980293493188e-05, "loss": 1.0405, "step": 6026 }, { "epoch": 0.3295130702203998, "grad_norm": 2.4287383556365967, "learning_rate": 7.827250112695212e-05, "loss": 1.1133, "step": 6027 }, { "epoch": 0.32956774303775843, "grad_norm": 2.668030023574829, "learning_rate": 7.826519843251301e-05, "loss": 0.8079, "step": 6028 }, { "epoch": 0.32962241585511703, "grad_norm": 2.4557886123657227, "learning_rate": 7.825789485184351e-05, "loss": 1.26, "step": 6029 }, { "epoch": 0.32967708867247564, "grad_norm": 2.6564409732818604, "learning_rate": 7.825059038517267e-05, "loss": 1.1908, "step": 6030 }, { "epoch": 0.3297317614898343, "grad_norm": 2.1857810020446777, "learning_rate": 7.824328503272942e-05, "loss": 0.8303, "step": 6031 }, { "epoch": 0.3297864343071929, "grad_norm": 2.887897491455078, "learning_rate": 7.82359787947429e-05, "loss": 1.2843, "step": 6032 }, { "epoch": 0.3298411071245515, "grad_norm": 2.6153371334075928, "learning_rate": 7.822867167144215e-05, "loss": 0.8937, "step": 6033 }, { "epoch": 0.3298957799419101, "grad_norm": 2.8806159496307373, "learning_rate": 7.822136366305627e-05, "loss": 1.0251, "step": 6034 }, { "epoch": 0.32995045275926876, "grad_norm": 3.25361704826355, "learning_rate": 7.821405476981442e-05, "loss": 1.3217, "step": 6035 }, { "epoch": 0.33000512557662737, "grad_norm": 2.2416539192199707, "learning_rate": 7.820674499194577e-05, "loss": 0.9784, "step": 6036 }, { "epoch": 0.33005979839398597, "grad_norm": 2.2778735160827637, "learning_rate": 7.819943432967948e-05, "loss": 0.9977, "step": 6037 }, { "epoch": 0.33011447121134463, "grad_norm": 2.4914636611938477, "learning_rate": 7.819212278324479e-05, "loss": 1.181, "step": 6038 }, { "epoch": 0.33016914402870323, "grad_norm": 2.3943421840667725, "learning_rate": 7.818481035287096e-05, "loss": 1.1617, "step": 6039 }, { "epoch": 0.33022381684606184, "grad_norm": 2.7372803688049316, "learning_rate": 7.817749703878722e-05, "loss": 1.1132, "step": 6040 }, { "epoch": 0.3302784896634205, "grad_norm": 2.5527572631835938, "learning_rate": 7.817018284122292e-05, "loss": 1.0313, "step": 6041 }, { "epoch": 0.3303331624807791, "grad_norm": 2.539090156555176, "learning_rate": 7.816286776040738e-05, "loss": 1.0425, "step": 6042 }, { "epoch": 0.3303878352981377, "grad_norm": 2.778017997741699, "learning_rate": 7.815555179656992e-05, "loss": 1.191, "step": 6043 }, { "epoch": 0.3304425081154963, "grad_norm": 2.3398306369781494, "learning_rate": 7.814823494993997e-05, "loss": 1.0725, "step": 6044 }, { "epoch": 0.33049718093285496, "grad_norm": 2.4510433673858643, "learning_rate": 7.814091722074693e-05, "loss": 1.1571, "step": 6045 }, { "epoch": 0.33055185375021356, "grad_norm": 2.7996506690979004, "learning_rate": 7.813359860922022e-05, "loss": 1.088, "step": 6046 }, { "epoch": 0.33060652656757217, "grad_norm": 2.6141488552093506, "learning_rate": 7.812627911558937e-05, "loss": 1.0389, "step": 6047 }, { "epoch": 0.3306611993849308, "grad_norm": 2.63191819190979, "learning_rate": 7.81189587400838e-05, "loss": 1.0547, "step": 6048 }, { "epoch": 0.33071587220228943, "grad_norm": 2.7750906944274902, "learning_rate": 7.811163748293307e-05, "loss": 1.0288, "step": 6049 }, { "epoch": 0.33077054501964803, "grad_norm": 2.5728299617767334, "learning_rate": 7.810431534436673e-05, "loss": 1.0084, "step": 6050 }, { "epoch": 0.3308252178370067, "grad_norm": 2.8347716331481934, "learning_rate": 7.809699232461436e-05, "loss": 1.1388, "step": 6051 }, { "epoch": 0.3308798906543653, "grad_norm": 3.308589220046997, "learning_rate": 7.808966842390557e-05, "loss": 1.1506, "step": 6052 }, { "epoch": 0.3309345634717239, "grad_norm": 2.8055500984191895, "learning_rate": 7.808234364246998e-05, "loss": 1.266, "step": 6053 }, { "epoch": 0.3309892362890825, "grad_norm": 3.0550811290740967, "learning_rate": 7.807501798053727e-05, "loss": 1.0754, "step": 6054 }, { "epoch": 0.33104390910644116, "grad_norm": 2.5360753536224365, "learning_rate": 7.806769143833711e-05, "loss": 1.1543, "step": 6055 }, { "epoch": 0.33109858192379976, "grad_norm": 2.138502597808838, "learning_rate": 7.806036401609924e-05, "loss": 1.0771, "step": 6056 }, { "epoch": 0.33115325474115836, "grad_norm": 2.754603862762451, "learning_rate": 7.805303571405338e-05, "loss": 1.1381, "step": 6057 }, { "epoch": 0.331207927558517, "grad_norm": 2.480982542037964, "learning_rate": 7.804570653242933e-05, "loss": 1.0134, "step": 6058 }, { "epoch": 0.3312626003758756, "grad_norm": 2.1875572204589844, "learning_rate": 7.803837647145687e-05, "loss": 0.9918, "step": 6059 }, { "epoch": 0.33131727319323423, "grad_norm": 2.032667398452759, "learning_rate": 7.803104553136584e-05, "loss": 1.1004, "step": 6060 }, { "epoch": 0.33137194601059283, "grad_norm": 2.361433982849121, "learning_rate": 7.802371371238609e-05, "loss": 0.798, "step": 6061 }, { "epoch": 0.3314266188279515, "grad_norm": 2.112571954727173, "learning_rate": 7.80163810147475e-05, "loss": 1.0462, "step": 6062 }, { "epoch": 0.3314812916453101, "grad_norm": 2.9269185066223145, "learning_rate": 7.800904743867996e-05, "loss": 0.9843, "step": 6063 }, { "epoch": 0.3315359644626687, "grad_norm": 2.3587288856506348, "learning_rate": 7.800171298441345e-05, "loss": 1.0183, "step": 6064 }, { "epoch": 0.33159063728002736, "grad_norm": 2.245286464691162, "learning_rate": 7.799437765217792e-05, "loss": 0.8646, "step": 6065 }, { "epoch": 0.33164531009738596, "grad_norm": 2.5010735988616943, "learning_rate": 7.798704144220334e-05, "loss": 0.9075, "step": 6066 }, { "epoch": 0.33169998291474456, "grad_norm": 4.570713520050049, "learning_rate": 7.797970435471978e-05, "loss": 1.1285, "step": 6067 }, { "epoch": 0.3317546557321032, "grad_norm": 2.4819283485412598, "learning_rate": 7.797236638995722e-05, "loss": 0.9574, "step": 6068 }, { "epoch": 0.3318093285494618, "grad_norm": 2.4527742862701416, "learning_rate": 7.796502754814579e-05, "loss": 1.1668, "step": 6069 }, { "epoch": 0.3318640013668204, "grad_norm": 2.2610089778900146, "learning_rate": 7.795768782951555e-05, "loss": 0.9181, "step": 6070 }, { "epoch": 0.33191867418417903, "grad_norm": 2.3408868312835693, "learning_rate": 7.795034723429668e-05, "loss": 1.1132, "step": 6071 }, { "epoch": 0.3319733470015377, "grad_norm": 2.519352436065674, "learning_rate": 7.794300576271932e-05, "loss": 1.171, "step": 6072 }, { "epoch": 0.3320280198188963, "grad_norm": 2.3667986392974854, "learning_rate": 7.793566341501363e-05, "loss": 0.9916, "step": 6073 }, { "epoch": 0.3320826926362549, "grad_norm": 2.499725341796875, "learning_rate": 7.792832019140985e-05, "loss": 1.0677, "step": 6074 }, { "epoch": 0.33213736545361355, "grad_norm": 2.5153708457946777, "learning_rate": 7.79209760921382e-05, "loss": 1.1479, "step": 6075 }, { "epoch": 0.33219203827097216, "grad_norm": 2.4907033443450928, "learning_rate": 7.791363111742896e-05, "loss": 1.1936, "step": 6076 }, { "epoch": 0.33224671108833076, "grad_norm": 2.552812337875366, "learning_rate": 7.790628526751243e-05, "loss": 1.1205, "step": 6077 }, { "epoch": 0.33230138390568936, "grad_norm": 2.967461347579956, "learning_rate": 7.789893854261893e-05, "loss": 1.1678, "step": 6078 }, { "epoch": 0.332356056723048, "grad_norm": 2.759533166885376, "learning_rate": 7.78915909429788e-05, "loss": 1.2225, "step": 6079 }, { "epoch": 0.3324107295404066, "grad_norm": 3.4134161472320557, "learning_rate": 7.788424246882243e-05, "loss": 0.9327, "step": 6080 }, { "epoch": 0.3324654023577652, "grad_norm": 2.6646509170532227, "learning_rate": 7.787689312038022e-05, "loss": 1.2198, "step": 6081 }, { "epoch": 0.3325200751751239, "grad_norm": 2.9271557331085205, "learning_rate": 7.78695428978826e-05, "loss": 1.158, "step": 6082 }, { "epoch": 0.3325747479924825, "grad_norm": 2.466998338699341, "learning_rate": 7.786219180156002e-05, "loss": 0.9399, "step": 6083 }, { "epoch": 0.3326294208098411, "grad_norm": 4.933682441711426, "learning_rate": 7.7854839831643e-05, "loss": 1.0128, "step": 6084 }, { "epoch": 0.33268409362719975, "grad_norm": 3.0858840942382812, "learning_rate": 7.784748698836202e-05, "loss": 1.2532, "step": 6085 }, { "epoch": 0.33273876644455835, "grad_norm": 2.7565197944641113, "learning_rate": 7.784013327194764e-05, "loss": 1.0772, "step": 6086 }, { "epoch": 0.33279343926191696, "grad_norm": 2.4866602420806885, "learning_rate": 7.783277868263042e-05, "loss": 1.2037, "step": 6087 }, { "epoch": 0.33284811207927556, "grad_norm": 2.0396649837493896, "learning_rate": 7.782542322064094e-05, "loss": 0.8723, "step": 6088 }, { "epoch": 0.3329027848966342, "grad_norm": 2.5612902641296387, "learning_rate": 7.781806688620987e-05, "loss": 1.1492, "step": 6089 }, { "epoch": 0.3329574577139928, "grad_norm": 3.2172434329986572, "learning_rate": 7.781070967956784e-05, "loss": 1.3131, "step": 6090 }, { "epoch": 0.3330121305313514, "grad_norm": 2.065702199935913, "learning_rate": 7.780335160094552e-05, "loss": 1.009, "step": 6091 }, { "epoch": 0.3330668033487101, "grad_norm": 1.9989022016525269, "learning_rate": 7.77959926505736e-05, "loss": 1.0261, "step": 6092 }, { "epoch": 0.3331214761660687, "grad_norm": 2.214984655380249, "learning_rate": 7.778863282868286e-05, "loss": 0.9872, "step": 6093 }, { "epoch": 0.3331761489834273, "grad_norm": 2.2467334270477295, "learning_rate": 7.778127213550404e-05, "loss": 1.004, "step": 6094 }, { "epoch": 0.33323082180078595, "grad_norm": 2.3965439796447754, "learning_rate": 7.777391057126791e-05, "loss": 1.189, "step": 6095 }, { "epoch": 0.33328549461814455, "grad_norm": 2.9555320739746094, "learning_rate": 7.77665481362053e-05, "loss": 1.0058, "step": 6096 }, { "epoch": 0.33334016743550315, "grad_norm": 2.4095842838287354, "learning_rate": 7.775918483054705e-05, "loss": 1.0315, "step": 6097 }, { "epoch": 0.33339484025286176, "grad_norm": 2.5494003295898438, "learning_rate": 7.775182065452403e-05, "loss": 1.0957, "step": 6098 }, { "epoch": 0.3334495130702204, "grad_norm": 2.890263795852661, "learning_rate": 7.774445560836713e-05, "loss": 1.0485, "step": 6099 }, { "epoch": 0.333504185887579, "grad_norm": 2.505995273590088, "learning_rate": 7.773708969230731e-05, "loss": 1.041, "step": 6100 }, { "epoch": 0.3335588587049376, "grad_norm": 2.367187976837158, "learning_rate": 7.772972290657548e-05, "loss": 1.0722, "step": 6101 }, { "epoch": 0.3336135315222963, "grad_norm": 2.6529128551483154, "learning_rate": 7.772235525140262e-05, "loss": 0.9943, "step": 6102 }, { "epoch": 0.3336682043396549, "grad_norm": 2.3109681606292725, "learning_rate": 7.771498672701976e-05, "loss": 1.0897, "step": 6103 }, { "epoch": 0.3337228771570135, "grad_norm": 2.3394763469696045, "learning_rate": 7.770761733365794e-05, "loss": 0.9959, "step": 6104 }, { "epoch": 0.3337775499743721, "grad_norm": 2.9051342010498047, "learning_rate": 7.770024707154819e-05, "loss": 1.0132, "step": 6105 }, { "epoch": 0.33383222279173075, "grad_norm": 3.2194578647613525, "learning_rate": 7.769287594092162e-05, "loss": 1.0665, "step": 6106 }, { "epoch": 0.33388689560908935, "grad_norm": 2.2352967262268066, "learning_rate": 7.768550394200932e-05, "loss": 1.0234, "step": 6107 }, { "epoch": 0.33394156842644795, "grad_norm": 2.668916702270508, "learning_rate": 7.767813107504247e-05, "loss": 0.8734, "step": 6108 }, { "epoch": 0.3339962412438066, "grad_norm": 2.7868361473083496, "learning_rate": 7.767075734025222e-05, "loss": 1.1266, "step": 6109 }, { "epoch": 0.3340509140611652, "grad_norm": 2.539565324783325, "learning_rate": 7.766338273786975e-05, "loss": 1.1865, "step": 6110 }, { "epoch": 0.3341055868785238, "grad_norm": 2.6968460083007812, "learning_rate": 7.765600726812632e-05, "loss": 1.1514, "step": 6111 }, { "epoch": 0.3341602596958825, "grad_norm": 2.677281379699707, "learning_rate": 7.764863093125315e-05, "loss": 1.2651, "step": 6112 }, { "epoch": 0.3342149325132411, "grad_norm": 2.8837480545043945, "learning_rate": 7.764125372748153e-05, "loss": 1.1731, "step": 6113 }, { "epoch": 0.3342696053305997, "grad_norm": 4.24222993850708, "learning_rate": 7.763387565704279e-05, "loss": 1.1439, "step": 6114 }, { "epoch": 0.3343242781479583, "grad_norm": 3.013446807861328, "learning_rate": 7.762649672016822e-05, "loss": 1.1507, "step": 6115 }, { "epoch": 0.33437895096531695, "grad_norm": 2.8495140075683594, "learning_rate": 7.761911691708921e-05, "loss": 1.1989, "step": 6116 }, { "epoch": 0.33443362378267555, "grad_norm": 3.5397772789001465, "learning_rate": 7.761173624803713e-05, "loss": 1.0715, "step": 6117 }, { "epoch": 0.33448829660003415, "grad_norm": 3.08736252784729, "learning_rate": 7.76043547132434e-05, "loss": 1.2804, "step": 6118 }, { "epoch": 0.3345429694173928, "grad_norm": 2.1951255798339844, "learning_rate": 7.759697231293945e-05, "loss": 1.0925, "step": 6119 }, { "epoch": 0.3345976422347514, "grad_norm": 2.15459942817688, "learning_rate": 7.758958904735678e-05, "loss": 1.1901, "step": 6120 }, { "epoch": 0.33465231505211, "grad_norm": 2.5566511154174805, "learning_rate": 7.758220491672687e-05, "loss": 1.0502, "step": 6121 }, { "epoch": 0.3347069878694687, "grad_norm": 1.9917150735855103, "learning_rate": 7.757481992128123e-05, "loss": 0.9453, "step": 6122 }, { "epoch": 0.3347616606868273, "grad_norm": 2.17447829246521, "learning_rate": 7.756743406125142e-05, "loss": 1.1154, "step": 6123 }, { "epoch": 0.3348163335041859, "grad_norm": 2.5268657207489014, "learning_rate": 7.756004733686904e-05, "loss": 1.0201, "step": 6124 }, { "epoch": 0.3348710063215445, "grad_norm": 3.3054134845733643, "learning_rate": 7.755265974836566e-05, "loss": 1.278, "step": 6125 }, { "epoch": 0.33492567913890314, "grad_norm": 2.4034268856048584, "learning_rate": 7.754527129597291e-05, "loss": 0.9567, "step": 6126 }, { "epoch": 0.33498035195626175, "grad_norm": 2.1756317615509033, "learning_rate": 7.753788197992247e-05, "loss": 1.1782, "step": 6127 }, { "epoch": 0.33503502477362035, "grad_norm": 2.1875360012054443, "learning_rate": 7.7530491800446e-05, "loss": 0.9949, "step": 6128 }, { "epoch": 0.335089697590979, "grad_norm": 2.5108821392059326, "learning_rate": 7.752310075777526e-05, "loss": 0.9942, "step": 6129 }, { "epoch": 0.3351443704083376, "grad_norm": 2.1305668354034424, "learning_rate": 7.751570885214195e-05, "loss": 1.03, "step": 6130 }, { "epoch": 0.3351990432256962, "grad_norm": 2.68982195854187, "learning_rate": 7.750831608377785e-05, "loss": 1.1139, "step": 6131 }, { "epoch": 0.3352537160430548, "grad_norm": 2.205026149749756, "learning_rate": 7.750092245291471e-05, "loss": 1.2609, "step": 6132 }, { "epoch": 0.3353083888604135, "grad_norm": 2.3984363079071045, "learning_rate": 7.749352795978444e-05, "loss": 1.0965, "step": 6133 }, { "epoch": 0.3353630616777721, "grad_norm": 3.049804449081421, "learning_rate": 7.748613260461881e-05, "loss": 1.0252, "step": 6134 }, { "epoch": 0.3354177344951307, "grad_norm": 3.759406328201294, "learning_rate": 7.747873638764974e-05, "loss": 0.9669, "step": 6135 }, { "epoch": 0.33547240731248934, "grad_norm": 2.5760700702667236, "learning_rate": 7.747133930910911e-05, "loss": 1.2759, "step": 6136 }, { "epoch": 0.33552708012984794, "grad_norm": 2.1585988998413086, "learning_rate": 7.746394136922884e-05, "loss": 0.7136, "step": 6137 }, { "epoch": 0.33558175294720655, "grad_norm": 2.194445848464966, "learning_rate": 7.745654256824092e-05, "loss": 1.03, "step": 6138 }, { "epoch": 0.3356364257645652, "grad_norm": 3.618783473968506, "learning_rate": 7.744914290637731e-05, "loss": 1.0053, "step": 6139 }, { "epoch": 0.3356910985819238, "grad_norm": 2.46378755569458, "learning_rate": 7.744174238387001e-05, "loss": 1.0258, "step": 6140 }, { "epoch": 0.3357457713992824, "grad_norm": 2.1358790397644043, "learning_rate": 7.743434100095107e-05, "loss": 1.0434, "step": 6141 }, { "epoch": 0.335800444216641, "grad_norm": 2.09999942779541, "learning_rate": 7.742693875785257e-05, "loss": 1.0214, "step": 6142 }, { "epoch": 0.3358551170339997, "grad_norm": 2.423689365386963, "learning_rate": 7.741953565480656e-05, "loss": 1.0844, "step": 6143 }, { "epoch": 0.3359097898513583, "grad_norm": 3.5055832862854004, "learning_rate": 7.741213169204519e-05, "loss": 1.2676, "step": 6144 }, { "epoch": 0.3359644626687169, "grad_norm": 3.057616949081421, "learning_rate": 7.740472686980062e-05, "loss": 1.131, "step": 6145 }, { "epoch": 0.33601913548607554, "grad_norm": 3.7572178840637207, "learning_rate": 7.739732118830496e-05, "loss": 1.0716, "step": 6146 }, { "epoch": 0.33607380830343414, "grad_norm": 2.8833837509155273, "learning_rate": 7.738991464779048e-05, "loss": 1.1431, "step": 6147 }, { "epoch": 0.33612848112079274, "grad_norm": 2.5746099948883057, "learning_rate": 7.738250724848936e-05, "loss": 1.1277, "step": 6148 }, { "epoch": 0.3361831539381514, "grad_norm": 2.714658737182617, "learning_rate": 7.737509899063387e-05, "loss": 1.1557, "step": 6149 }, { "epoch": 0.33623782675551, "grad_norm": 2.0390982627868652, "learning_rate": 7.736768987445626e-05, "loss": 0.8982, "step": 6150 }, { "epoch": 0.3362924995728686, "grad_norm": 3.309520959854126, "learning_rate": 7.736027990018889e-05, "loss": 1.2506, "step": 6151 }, { "epoch": 0.3363471723902272, "grad_norm": 2.732736587524414, "learning_rate": 7.735286906806406e-05, "loss": 1.0702, "step": 6152 }, { "epoch": 0.33640184520758587, "grad_norm": 2.393296241760254, "learning_rate": 7.734545737831411e-05, "loss": 1.1364, "step": 6153 }, { "epoch": 0.3364565180249445, "grad_norm": 3.1360552310943604, "learning_rate": 7.733804483117146e-05, "loss": 1.2902, "step": 6154 }, { "epoch": 0.3365111908423031, "grad_norm": 2.560319662094116, "learning_rate": 7.733063142686852e-05, "loss": 1.0311, "step": 6155 }, { "epoch": 0.33656586365966173, "grad_norm": 2.5442349910736084, "learning_rate": 7.732321716563773e-05, "loss": 1.1373, "step": 6156 }, { "epoch": 0.33662053647702034, "grad_norm": 3.262986183166504, "learning_rate": 7.731580204771154e-05, "loss": 1.2873, "step": 6157 }, { "epoch": 0.33667520929437894, "grad_norm": 2.707566261291504, "learning_rate": 7.730838607332247e-05, "loss": 1.2367, "step": 6158 }, { "epoch": 0.33672988211173754, "grad_norm": 2.347890615463257, "learning_rate": 7.730096924270303e-05, "loss": 1.1112, "step": 6159 }, { "epoch": 0.3367845549290962, "grad_norm": 2.1962249279022217, "learning_rate": 7.729355155608578e-05, "loss": 1.2097, "step": 6160 }, { "epoch": 0.3368392277464548, "grad_norm": 2.788358449935913, "learning_rate": 7.728613301370325e-05, "loss": 1.054, "step": 6161 }, { "epoch": 0.3368939005638134, "grad_norm": 2.8446590900421143, "learning_rate": 7.727871361578809e-05, "loss": 1.0336, "step": 6162 }, { "epoch": 0.33694857338117207, "grad_norm": 2.070451498031616, "learning_rate": 7.727129336257291e-05, "loss": 1.0492, "step": 6163 }, { "epoch": 0.33700324619853067, "grad_norm": 1.8453853130340576, "learning_rate": 7.726387225429037e-05, "loss": 0.8798, "step": 6164 }, { "epoch": 0.3370579190158893, "grad_norm": 2.976041555404663, "learning_rate": 7.725645029117316e-05, "loss": 1.0809, "step": 6165 }, { "epoch": 0.33711259183324793, "grad_norm": 2.156663656234741, "learning_rate": 7.724902747345396e-05, "loss": 1.0842, "step": 6166 }, { "epoch": 0.33716726465060654, "grad_norm": 2.789058208465576, "learning_rate": 7.724160380136554e-05, "loss": 0.9528, "step": 6167 }, { "epoch": 0.33722193746796514, "grad_norm": 2.5672359466552734, "learning_rate": 7.723417927514064e-05, "loss": 1.1098, "step": 6168 }, { "epoch": 0.33727661028532374, "grad_norm": 2.744828939437866, "learning_rate": 7.722675389501206e-05, "loss": 0.8633, "step": 6169 }, { "epoch": 0.3373312831026824, "grad_norm": 2.6263043880462646, "learning_rate": 7.721932766121261e-05, "loss": 1.0923, "step": 6170 }, { "epoch": 0.337385955920041, "grad_norm": 2.757185220718384, "learning_rate": 7.721190057397514e-05, "loss": 0.7777, "step": 6171 }, { "epoch": 0.3374406287373996, "grad_norm": 2.3839895725250244, "learning_rate": 7.720447263353252e-05, "loss": 0.9788, "step": 6172 }, { "epoch": 0.33749530155475826, "grad_norm": 2.4644203186035156, "learning_rate": 7.719704384011765e-05, "loss": 1.0202, "step": 6173 }, { "epoch": 0.33754997437211687, "grad_norm": 3.0680410861968994, "learning_rate": 7.718961419396344e-05, "loss": 1.124, "step": 6174 }, { "epoch": 0.33760464718947547, "grad_norm": 2.4963932037353516, "learning_rate": 7.718218369530285e-05, "loss": 1.1806, "step": 6175 }, { "epoch": 0.33765932000683413, "grad_norm": 2.8311266899108887, "learning_rate": 7.717475234436884e-05, "loss": 1.1803, "step": 6176 }, { "epoch": 0.33771399282419273, "grad_norm": 2.650468349456787, "learning_rate": 7.716732014139443e-05, "loss": 1.122, "step": 6177 }, { "epoch": 0.33776866564155134, "grad_norm": 2.67561674118042, "learning_rate": 7.715988708661266e-05, "loss": 1.2366, "step": 6178 }, { "epoch": 0.33782333845890994, "grad_norm": 2.6924402713775635, "learning_rate": 7.715245318025655e-05, "loss": 1.0943, "step": 6179 }, { "epoch": 0.3378780112762686, "grad_norm": 1.974732756614685, "learning_rate": 7.714501842255923e-05, "loss": 1.0757, "step": 6180 }, { "epoch": 0.3379326840936272, "grad_norm": 2.74100923538208, "learning_rate": 7.713758281375378e-05, "loss": 1.3266, "step": 6181 }, { "epoch": 0.3379873569109858, "grad_norm": 1.98850417137146, "learning_rate": 7.713014635407334e-05, "loss": 1.0042, "step": 6182 }, { "epoch": 0.33804202972834446, "grad_norm": 2.7054309844970703, "learning_rate": 7.712270904375108e-05, "loss": 1.0563, "step": 6183 }, { "epoch": 0.33809670254570307, "grad_norm": 4.531088352203369, "learning_rate": 7.71152708830202e-05, "loss": 1.0505, "step": 6184 }, { "epoch": 0.33815137536306167, "grad_norm": 1.9935076236724854, "learning_rate": 7.71078318721139e-05, "loss": 0.9762, "step": 6185 }, { "epoch": 0.33820604818042027, "grad_norm": 1.9208946228027344, "learning_rate": 7.710039201126541e-05, "loss": 0.9284, "step": 6186 }, { "epoch": 0.33826072099777893, "grad_norm": 2.7012786865234375, "learning_rate": 7.709295130070803e-05, "loss": 0.9396, "step": 6187 }, { "epoch": 0.33831539381513753, "grad_norm": 2.225761890411377, "learning_rate": 7.708550974067506e-05, "loss": 0.9411, "step": 6188 }, { "epoch": 0.33837006663249614, "grad_norm": 2.240584373474121, "learning_rate": 7.707806733139981e-05, "loss": 0.9311, "step": 6189 }, { "epoch": 0.3384247394498548, "grad_norm": 3.2955424785614014, "learning_rate": 7.707062407311562e-05, "loss": 1.2486, "step": 6190 }, { "epoch": 0.3384794122672134, "grad_norm": 2.6738531589508057, "learning_rate": 7.706317996605587e-05, "loss": 1.123, "step": 6191 }, { "epoch": 0.338534085084572, "grad_norm": 2.3452811241149902, "learning_rate": 7.705573501045398e-05, "loss": 1.0386, "step": 6192 }, { "epoch": 0.33858875790193066, "grad_norm": 2.0041890144348145, "learning_rate": 7.704828920654337e-05, "loss": 1.0899, "step": 6193 }, { "epoch": 0.33864343071928926, "grad_norm": 2.3875539302825928, "learning_rate": 7.704084255455749e-05, "loss": 1.1251, "step": 6194 }, { "epoch": 0.33869810353664787, "grad_norm": 2.3665812015533447, "learning_rate": 7.703339505472983e-05, "loss": 1.2089, "step": 6195 }, { "epoch": 0.33875277635400647, "grad_norm": 3.229663372039795, "learning_rate": 7.70259467072939e-05, "loss": 1.0992, "step": 6196 }, { "epoch": 0.3388074491713651, "grad_norm": 2.2909116744995117, "learning_rate": 7.701849751248325e-05, "loss": 1.0582, "step": 6197 }, { "epoch": 0.33886212198872373, "grad_norm": 2.4920718669891357, "learning_rate": 7.701104747053141e-05, "loss": 1.2212, "step": 6198 }, { "epoch": 0.33891679480608233, "grad_norm": 2.7429757118225098, "learning_rate": 7.700359658167201e-05, "loss": 0.9987, "step": 6199 }, { "epoch": 0.338971467623441, "grad_norm": 2.2580971717834473, "learning_rate": 7.699614484613862e-05, "loss": 0.9618, "step": 6200 }, { "epoch": 0.3390261404407996, "grad_norm": 2.2365903854370117, "learning_rate": 7.698869226416493e-05, "loss": 1.0001, "step": 6201 }, { "epoch": 0.3390808132581582, "grad_norm": 2.161210775375366, "learning_rate": 7.698123883598459e-05, "loss": 0.9423, "step": 6202 }, { "epoch": 0.33913548607551686, "grad_norm": 3.315354824066162, "learning_rate": 7.697378456183127e-05, "loss": 1.3178, "step": 6203 }, { "epoch": 0.33919015889287546, "grad_norm": 2.7172982692718506, "learning_rate": 7.696632944193872e-05, "loss": 1.0492, "step": 6204 }, { "epoch": 0.33924483171023406, "grad_norm": 2.245361328125, "learning_rate": 7.695887347654068e-05, "loss": 0.9933, "step": 6205 }, { "epoch": 0.33929950452759267, "grad_norm": 4.0923051834106445, "learning_rate": 7.695141666587093e-05, "loss": 1.0426, "step": 6206 }, { "epoch": 0.3393541773449513, "grad_norm": 2.8061113357543945, "learning_rate": 7.694395901016329e-05, "loss": 1.0906, "step": 6207 }, { "epoch": 0.3394088501623099, "grad_norm": 2.808952808380127, "learning_rate": 7.693650050965156e-05, "loss": 1.2131, "step": 6208 }, { "epoch": 0.33946352297966853, "grad_norm": 2.335256576538086, "learning_rate": 7.692904116456958e-05, "loss": 0.9629, "step": 6209 }, { "epoch": 0.3395181957970272, "grad_norm": 2.0234882831573486, "learning_rate": 7.692158097515128e-05, "loss": 1.042, "step": 6210 }, { "epoch": 0.3395728686143858, "grad_norm": 1.9464832544326782, "learning_rate": 7.691411994163052e-05, "loss": 0.8075, "step": 6211 }, { "epoch": 0.3396275414317444, "grad_norm": 3.5535547733306885, "learning_rate": 7.690665806424127e-05, "loss": 1.097, "step": 6212 }, { "epoch": 0.339682214249103, "grad_norm": 2.409367322921753, "learning_rate": 7.689919534321748e-05, "loss": 1.0323, "step": 6213 }, { "epoch": 0.33973688706646166, "grad_norm": 2.4656548500061035, "learning_rate": 7.689173177879313e-05, "loss": 1.1137, "step": 6214 }, { "epoch": 0.33979155988382026, "grad_norm": 3.1210317611694336, "learning_rate": 7.688426737120222e-05, "loss": 0.9795, "step": 6215 }, { "epoch": 0.33984623270117886, "grad_norm": 2.4193613529205322, "learning_rate": 7.687680212067882e-05, "loss": 0.9648, "step": 6216 }, { "epoch": 0.3399009055185375, "grad_norm": 2.4431686401367188, "learning_rate": 7.6869336027457e-05, "loss": 1.1689, "step": 6217 }, { "epoch": 0.3399555783358961, "grad_norm": 2.5367026329040527, "learning_rate": 7.686186909177082e-05, "loss": 1.2183, "step": 6218 }, { "epoch": 0.34001025115325473, "grad_norm": 2.2130801677703857, "learning_rate": 7.685440131385441e-05, "loss": 0.928, "step": 6219 }, { "epoch": 0.3400649239706134, "grad_norm": 3.0652682781219482, "learning_rate": 7.684693269394193e-05, "loss": 1.2149, "step": 6220 }, { "epoch": 0.340119596787972, "grad_norm": 3.567680835723877, "learning_rate": 7.683946323226754e-05, "loss": 0.9568, "step": 6221 }, { "epoch": 0.3401742696053306, "grad_norm": 2.34362530708313, "learning_rate": 7.683199292906545e-05, "loss": 1.2034, "step": 6222 }, { "epoch": 0.3402289424226892, "grad_norm": 2.697194814682007, "learning_rate": 7.682452178456986e-05, "loss": 0.9509, "step": 6223 }, { "epoch": 0.34028361524004785, "grad_norm": 2.6577560901641846, "learning_rate": 7.681704979901504e-05, "loss": 1.1465, "step": 6224 }, { "epoch": 0.34033828805740646, "grad_norm": 2.1171984672546387, "learning_rate": 7.680957697263527e-05, "loss": 1.0894, "step": 6225 }, { "epoch": 0.34039296087476506, "grad_norm": 2.065040349960327, "learning_rate": 7.680210330566485e-05, "loss": 0.7742, "step": 6226 }, { "epoch": 0.3404476336921237, "grad_norm": 2.3544628620147705, "learning_rate": 7.67946287983381e-05, "loss": 1.0121, "step": 6227 }, { "epoch": 0.3405023065094823, "grad_norm": 2.7815656661987305, "learning_rate": 7.678715345088939e-05, "loss": 1.28, "step": 6228 }, { "epoch": 0.3405569793268409, "grad_norm": 3.2321901321411133, "learning_rate": 7.67796772635531e-05, "loss": 1.2055, "step": 6229 }, { "epoch": 0.34061165214419953, "grad_norm": 2.378528118133545, "learning_rate": 7.677220023656363e-05, "loss": 1.0504, "step": 6230 }, { "epoch": 0.3406663249615582, "grad_norm": 2.8960323333740234, "learning_rate": 7.676472237015545e-05, "loss": 1.0956, "step": 6231 }, { "epoch": 0.3407209977789168, "grad_norm": 2.5688955783843994, "learning_rate": 7.675724366456296e-05, "loss": 1.0556, "step": 6232 }, { "epoch": 0.3407756705962754, "grad_norm": 3.9071011543273926, "learning_rate": 7.674976412002071e-05, "loss": 1.261, "step": 6233 }, { "epoch": 0.34083034341363405, "grad_norm": 2.6402089595794678, "learning_rate": 7.674228373676316e-05, "loss": 1.2814, "step": 6234 }, { "epoch": 0.34088501623099265, "grad_norm": 2.5063037872314453, "learning_rate": 7.67348025150249e-05, "loss": 1.1206, "step": 6235 }, { "epoch": 0.34093968904835126, "grad_norm": 2.0253241062164307, "learning_rate": 7.672732045504047e-05, "loss": 0.8819, "step": 6236 }, { "epoch": 0.3409943618657099, "grad_norm": 2.248079299926758, "learning_rate": 7.671983755704448e-05, "loss": 1.0978, "step": 6237 }, { "epoch": 0.3410490346830685, "grad_norm": 2.5950796604156494, "learning_rate": 7.671235382127151e-05, "loss": 1.0728, "step": 6238 }, { "epoch": 0.3411037075004271, "grad_norm": 2.696824550628662, "learning_rate": 7.670486924795625e-05, "loss": 1.306, "step": 6239 }, { "epoch": 0.3411583803177857, "grad_norm": 2.7069923877716064, "learning_rate": 7.669738383733338e-05, "loss": 0.8444, "step": 6240 }, { "epoch": 0.3412130531351444, "grad_norm": 2.48752760887146, "learning_rate": 7.668989758963756e-05, "loss": 1.2123, "step": 6241 }, { "epoch": 0.341267725952503, "grad_norm": 2.2629239559173584, "learning_rate": 7.668241050510352e-05, "loss": 1.108, "step": 6242 }, { "epoch": 0.3413223987698616, "grad_norm": 2.432595729827881, "learning_rate": 7.667492258396603e-05, "loss": 1.0497, "step": 6243 }, { "epoch": 0.34137707158722025, "grad_norm": 2.3466544151306152, "learning_rate": 7.666743382645984e-05, "loss": 1.1179, "step": 6244 }, { "epoch": 0.34143174440457885, "grad_norm": 2.943005323410034, "learning_rate": 7.66599442328198e-05, "loss": 1.0376, "step": 6245 }, { "epoch": 0.34148641722193745, "grad_norm": 2.4096782207489014, "learning_rate": 7.665245380328069e-05, "loss": 1.0533, "step": 6246 }, { "epoch": 0.3415410900392961, "grad_norm": 2.215907573699951, "learning_rate": 7.66449625380774e-05, "loss": 1.0195, "step": 6247 }, { "epoch": 0.3415957628566547, "grad_norm": 2.559983491897583, "learning_rate": 7.663747043744478e-05, "loss": 1.1723, "step": 6248 }, { "epoch": 0.3416504356740133, "grad_norm": 2.3716259002685547, "learning_rate": 7.662997750161778e-05, "loss": 1.1304, "step": 6249 }, { "epoch": 0.3417051084913719, "grad_norm": 2.7599804401397705, "learning_rate": 7.66224837308313e-05, "loss": 1.1114, "step": 6250 }, { "epoch": 0.3417597813087306, "grad_norm": 2.8200643062591553, "learning_rate": 7.66149891253203e-05, "loss": 1.1482, "step": 6251 }, { "epoch": 0.3418144541260892, "grad_norm": 2.141252279281616, "learning_rate": 7.66074936853198e-05, "loss": 1.1472, "step": 6252 }, { "epoch": 0.3418691269434478, "grad_norm": 3.4910635948181152, "learning_rate": 7.659999741106478e-05, "loss": 0.9358, "step": 6253 }, { "epoch": 0.34192379976080645, "grad_norm": 2.6350862979888916, "learning_rate": 7.65925003027903e-05, "loss": 1.117, "step": 6254 }, { "epoch": 0.34197847257816505, "grad_norm": 2.71030592918396, "learning_rate": 7.65850023607314e-05, "loss": 1.0482, "step": 6255 }, { "epoch": 0.34203314539552365, "grad_norm": 2.086031436920166, "learning_rate": 7.657750358512321e-05, "loss": 0.9777, "step": 6256 }, { "epoch": 0.34208781821288226, "grad_norm": 2.1856560707092285, "learning_rate": 7.657000397620082e-05, "loss": 0.8317, "step": 6257 }, { "epoch": 0.3421424910302409, "grad_norm": 2.6462745666503906, "learning_rate": 7.656250353419937e-05, "loss": 1.0978, "step": 6258 }, { "epoch": 0.3421971638475995, "grad_norm": 2.403195858001709, "learning_rate": 7.655500225935404e-05, "loss": 1.0463, "step": 6259 }, { "epoch": 0.3422518366649581, "grad_norm": 2.9845008850097656, "learning_rate": 7.654750015190002e-05, "loss": 1.0289, "step": 6260 }, { "epoch": 0.3423065094823168, "grad_norm": 2.6535494327545166, "learning_rate": 7.653999721207254e-05, "loss": 1.1796, "step": 6261 }, { "epoch": 0.3423611822996754, "grad_norm": 2.4584662914276123, "learning_rate": 7.653249344010685e-05, "loss": 1.0736, "step": 6262 }, { "epoch": 0.342415855117034, "grad_norm": 2.2888941764831543, "learning_rate": 7.652498883623822e-05, "loss": 1.016, "step": 6263 }, { "epoch": 0.34247052793439264, "grad_norm": 3.0566914081573486, "learning_rate": 7.651748340070193e-05, "loss": 1.2799, "step": 6264 }, { "epoch": 0.34252520075175125, "grad_norm": 2.1490800380706787, "learning_rate": 7.650997713373335e-05, "loss": 1.0181, "step": 6265 }, { "epoch": 0.34257987356910985, "grad_norm": 2.602118968963623, "learning_rate": 7.650247003556778e-05, "loss": 0.967, "step": 6266 }, { "epoch": 0.34263454638646845, "grad_norm": 2.3291120529174805, "learning_rate": 7.649496210644065e-05, "loss": 1.1333, "step": 6267 }, { "epoch": 0.3426892192038271, "grad_norm": 2.7604074478149414, "learning_rate": 7.648745334658734e-05, "loss": 1.1785, "step": 6268 }, { "epoch": 0.3427438920211857, "grad_norm": 2.4908878803253174, "learning_rate": 7.647994375624325e-05, "loss": 1.0829, "step": 6269 }, { "epoch": 0.3427985648385443, "grad_norm": 2.5732710361480713, "learning_rate": 7.647243333564391e-05, "loss": 1.2005, "step": 6270 }, { "epoch": 0.342853237655903, "grad_norm": 3.1863481998443604, "learning_rate": 7.646492208502474e-05, "loss": 1.1879, "step": 6271 }, { "epoch": 0.3429079104732616, "grad_norm": 2.4810402393341064, "learning_rate": 7.645741000462125e-05, "loss": 1.0961, "step": 6272 }, { "epoch": 0.3429625832906202, "grad_norm": 2.4252445697784424, "learning_rate": 7.644989709466903e-05, "loss": 1.3532, "step": 6273 }, { "epoch": 0.34301725610797884, "grad_norm": 1.8396227359771729, "learning_rate": 7.644238335540357e-05, "loss": 0.9926, "step": 6274 }, { "epoch": 0.34307192892533744, "grad_norm": 1.8984886407852173, "learning_rate": 7.643486878706052e-05, "loss": 1.0052, "step": 6275 }, { "epoch": 0.34312660174269605, "grad_norm": 1.9970351457595825, "learning_rate": 7.642735338987545e-05, "loss": 0.955, "step": 6276 }, { "epoch": 0.34318127456005465, "grad_norm": 2.2457447052001953, "learning_rate": 7.6419837164084e-05, "loss": 1.1284, "step": 6277 }, { "epoch": 0.3432359473774133, "grad_norm": 2.0090508460998535, "learning_rate": 7.641232010992186e-05, "loss": 1.0261, "step": 6278 }, { "epoch": 0.3432906201947719, "grad_norm": 2.6440505981445312, "learning_rate": 7.64048022276247e-05, "loss": 0.9521, "step": 6279 }, { "epoch": 0.3433452930121305, "grad_norm": 2.174097776412964, "learning_rate": 7.639728351742825e-05, "loss": 0.9658, "step": 6280 }, { "epoch": 0.3433999658294892, "grad_norm": 2.9920196533203125, "learning_rate": 7.638976397956825e-05, "loss": 1.3745, "step": 6281 }, { "epoch": 0.3434546386468478, "grad_norm": 3.6568963527679443, "learning_rate": 7.638224361428046e-05, "loss": 0.8826, "step": 6282 }, { "epoch": 0.3435093114642064, "grad_norm": 2.4074761867523193, "learning_rate": 7.637472242180068e-05, "loss": 1.0815, "step": 6283 }, { "epoch": 0.343563984281565, "grad_norm": 3.017244577407837, "learning_rate": 7.636720040236473e-05, "loss": 1.1629, "step": 6284 }, { "epoch": 0.34361865709892364, "grad_norm": 2.847255229949951, "learning_rate": 7.635967755620845e-05, "loss": 1.2235, "step": 6285 }, { "epoch": 0.34367332991628224, "grad_norm": 2.5938258171081543, "learning_rate": 7.635215388356772e-05, "loss": 1.1351, "step": 6286 }, { "epoch": 0.34372800273364085, "grad_norm": 2.835627317428589, "learning_rate": 7.634462938467845e-05, "loss": 1.2565, "step": 6287 }, { "epoch": 0.3437826755509995, "grad_norm": 2.736673593521118, "learning_rate": 7.633710405977654e-05, "loss": 1.2457, "step": 6288 }, { "epoch": 0.3438373483683581, "grad_norm": 2.905533790588379, "learning_rate": 7.632957790909794e-05, "loss": 1.0574, "step": 6289 }, { "epoch": 0.3438920211857167, "grad_norm": 2.730623722076416, "learning_rate": 7.632205093287865e-05, "loss": 0.8804, "step": 6290 }, { "epoch": 0.34394669400307537, "grad_norm": 2.340388536453247, "learning_rate": 7.631452313135466e-05, "loss": 1.1821, "step": 6291 }, { "epoch": 0.344001366820434, "grad_norm": 2.293456792831421, "learning_rate": 7.630699450476197e-05, "loss": 1.0097, "step": 6292 }, { "epoch": 0.3440560396377926, "grad_norm": 3.6727895736694336, "learning_rate": 7.62994650533367e-05, "loss": 1.168, "step": 6293 }, { "epoch": 0.3441107124551512, "grad_norm": 2.2052974700927734, "learning_rate": 7.629193477731484e-05, "loss": 1.0751, "step": 6294 }, { "epoch": 0.34416538527250984, "grad_norm": 2.893028497695923, "learning_rate": 7.628440367693258e-05, "loss": 1.3731, "step": 6295 }, { "epoch": 0.34422005808986844, "grad_norm": 3.1300108432769775, "learning_rate": 7.627687175242601e-05, "loss": 0.9615, "step": 6296 }, { "epoch": 0.34427473090722704, "grad_norm": 2.7278482913970947, "learning_rate": 7.626933900403128e-05, "loss": 1.0358, "step": 6297 }, { "epoch": 0.3443294037245857, "grad_norm": 2.644686698913574, "learning_rate": 7.626180543198458e-05, "loss": 1.1111, "step": 6298 }, { "epoch": 0.3443840765419443, "grad_norm": 3.074289083480835, "learning_rate": 7.625427103652213e-05, "loss": 1.0419, "step": 6299 }, { "epoch": 0.3444387493593029, "grad_norm": 2.0922915935516357, "learning_rate": 7.624673581788015e-05, "loss": 0.8645, "step": 6300 }, { "epoch": 0.34449342217666157, "grad_norm": 2.166749954223633, "learning_rate": 7.623919977629493e-05, "loss": 1.1284, "step": 6301 }, { "epoch": 0.34454809499402017, "grad_norm": 3.9618284702301025, "learning_rate": 7.623166291200271e-05, "loss": 1.2539, "step": 6302 }, { "epoch": 0.3446027678113788, "grad_norm": 1.9836127758026123, "learning_rate": 7.622412522523983e-05, "loss": 1.0863, "step": 6303 }, { "epoch": 0.3446574406287374, "grad_norm": 3.8729307651519775, "learning_rate": 7.621658671624261e-05, "loss": 1.1442, "step": 6304 }, { "epoch": 0.34471211344609604, "grad_norm": 2.736520767211914, "learning_rate": 7.620904738524745e-05, "loss": 1.257, "step": 6305 }, { "epoch": 0.34476678626345464, "grad_norm": 2.518461227416992, "learning_rate": 7.62015072324907e-05, "loss": 0.8665, "step": 6306 }, { "epoch": 0.34482145908081324, "grad_norm": 2.010028123855591, "learning_rate": 7.619396625820879e-05, "loss": 1.1586, "step": 6307 }, { "epoch": 0.3448761318981719, "grad_norm": 2.6690235137939453, "learning_rate": 7.618642446263815e-05, "loss": 1.0475, "step": 6308 }, { "epoch": 0.3449308047155305, "grad_norm": 2.718905448913574, "learning_rate": 7.617888184601527e-05, "loss": 1.0064, "step": 6309 }, { "epoch": 0.3449854775328891, "grad_norm": 2.4657814502716064, "learning_rate": 7.617133840857663e-05, "loss": 1.0761, "step": 6310 }, { "epoch": 0.3450401503502477, "grad_norm": 2.2117347717285156, "learning_rate": 7.616379415055875e-05, "loss": 1.0203, "step": 6311 }, { "epoch": 0.34509482316760637, "grad_norm": 3.682121992111206, "learning_rate": 7.615624907219816e-05, "loss": 1.1298, "step": 6312 }, { "epoch": 0.34514949598496497, "grad_norm": 2.447213888168335, "learning_rate": 7.614870317373143e-05, "loss": 1.0998, "step": 6313 }, { "epoch": 0.3452041688023236, "grad_norm": 2.146390438079834, "learning_rate": 7.614115645539516e-05, "loss": 1.0322, "step": 6314 }, { "epoch": 0.34525884161968223, "grad_norm": 2.5989298820495605, "learning_rate": 7.6133608917426e-05, "loss": 1.1991, "step": 6315 }, { "epoch": 0.34531351443704084, "grad_norm": 2.358443021774292, "learning_rate": 7.612606056006057e-05, "loss": 1.0331, "step": 6316 }, { "epoch": 0.34536818725439944, "grad_norm": 2.5797393321990967, "learning_rate": 7.611851138353551e-05, "loss": 1.1409, "step": 6317 }, { "epoch": 0.3454228600717581, "grad_norm": 2.7121431827545166, "learning_rate": 7.611096138808759e-05, "loss": 1.0053, "step": 6318 }, { "epoch": 0.3454775328891167, "grad_norm": 4.830761909484863, "learning_rate": 7.610341057395347e-05, "loss": 1.1354, "step": 6319 }, { "epoch": 0.3455322057064753, "grad_norm": 2.848870277404785, "learning_rate": 7.609585894136993e-05, "loss": 1.0242, "step": 6320 }, { "epoch": 0.3455868785238339, "grad_norm": 2.264307737350464, "learning_rate": 7.608830649057375e-05, "loss": 1.1049, "step": 6321 }, { "epoch": 0.34564155134119257, "grad_norm": 2.288895606994629, "learning_rate": 7.60807532218017e-05, "loss": 1.2199, "step": 6322 }, { "epoch": 0.34569622415855117, "grad_norm": 2.6467766761779785, "learning_rate": 7.607319913529063e-05, "loss": 1.2256, "step": 6323 }, { "epoch": 0.34575089697590977, "grad_norm": 2.8008980751037598, "learning_rate": 7.60656442312774e-05, "loss": 1.0475, "step": 6324 }, { "epoch": 0.34580556979326843, "grad_norm": 3.880554437637329, "learning_rate": 7.605808850999885e-05, "loss": 1.1449, "step": 6325 }, { "epoch": 0.34586024261062703, "grad_norm": 2.6703078746795654, "learning_rate": 7.605053197169192e-05, "loss": 1.3286, "step": 6326 }, { "epoch": 0.34591491542798564, "grad_norm": 2.494485378265381, "learning_rate": 7.604297461659353e-05, "loss": 1.112, "step": 6327 }, { "epoch": 0.3459695882453443, "grad_norm": 2.1836369037628174, "learning_rate": 7.603541644494062e-05, "loss": 1.0196, "step": 6328 }, { "epoch": 0.3460242610627029, "grad_norm": 2.1500518321990967, "learning_rate": 7.602785745697018e-05, "loss": 0.9373, "step": 6329 }, { "epoch": 0.3460789338800615, "grad_norm": 3.3440871238708496, "learning_rate": 7.602029765291922e-05, "loss": 1.1279, "step": 6330 }, { "epoch": 0.3461336066974201, "grad_norm": 3.718305826187134, "learning_rate": 7.601273703302477e-05, "loss": 1.0936, "step": 6331 }, { "epoch": 0.34618827951477876, "grad_norm": 3.609757661819458, "learning_rate": 7.600517559752387e-05, "loss": 1.1022, "step": 6332 }, { "epoch": 0.34624295233213737, "grad_norm": 3.114757776260376, "learning_rate": 7.599761334665363e-05, "loss": 1.2405, "step": 6333 }, { "epoch": 0.34629762514949597, "grad_norm": 2.3429219722747803, "learning_rate": 7.599005028065113e-05, "loss": 1.1114, "step": 6334 }, { "epoch": 0.3463522979668546, "grad_norm": 2.9227285385131836, "learning_rate": 7.598248639975351e-05, "loss": 1.1185, "step": 6335 }, { "epoch": 0.34640697078421323, "grad_norm": 2.758880853652954, "learning_rate": 7.597492170419795e-05, "loss": 1.1501, "step": 6336 }, { "epoch": 0.34646164360157183, "grad_norm": 2.8217597007751465, "learning_rate": 7.596735619422162e-05, "loss": 1.3087, "step": 6337 }, { "epoch": 0.34651631641893044, "grad_norm": 2.577141046524048, "learning_rate": 7.59597898700617e-05, "loss": 1.0928, "step": 6338 }, { "epoch": 0.3465709892362891, "grad_norm": 2.3916468620300293, "learning_rate": 7.595222273195549e-05, "loss": 1.2088, "step": 6339 }, { "epoch": 0.3466256620536477, "grad_norm": 2.901026725769043, "learning_rate": 7.594465478014019e-05, "loss": 1.0959, "step": 6340 }, { "epoch": 0.3466803348710063, "grad_norm": 1.6447875499725342, "learning_rate": 7.593708601485312e-05, "loss": 0.7798, "step": 6341 }, { "epoch": 0.34673500768836496, "grad_norm": 2.399055004119873, "learning_rate": 7.592951643633159e-05, "loss": 1.1182, "step": 6342 }, { "epoch": 0.34678968050572356, "grad_norm": 2.530914306640625, "learning_rate": 7.59219460448129e-05, "loss": 1.1368, "step": 6343 }, { "epoch": 0.34684435332308217, "grad_norm": 2.351588487625122, "learning_rate": 7.591437484053447e-05, "loss": 0.9557, "step": 6344 }, { "epoch": 0.3468990261404408, "grad_norm": 2.7785873413085938, "learning_rate": 7.590680282373368e-05, "loss": 1.2281, "step": 6345 }, { "epoch": 0.34695369895779943, "grad_norm": 2.591620922088623, "learning_rate": 7.58992299946479e-05, "loss": 1.0245, "step": 6346 }, { "epoch": 0.34700837177515803, "grad_norm": 3.0922744274139404, "learning_rate": 7.589165635351461e-05, "loss": 1.2721, "step": 6347 }, { "epoch": 0.34706304459251663, "grad_norm": 2.7023708820343018, "learning_rate": 7.588408190057124e-05, "loss": 1.1131, "step": 6348 }, { "epoch": 0.3471177174098753, "grad_norm": 2.679668664932251, "learning_rate": 7.587650663605531e-05, "loss": 1.0664, "step": 6349 }, { "epoch": 0.3471723902272339, "grad_norm": 2.9446582794189453, "learning_rate": 7.586893056020433e-05, "loss": 1.0471, "step": 6350 }, { "epoch": 0.3472270630445925, "grad_norm": 2.4450790882110596, "learning_rate": 7.586135367325584e-05, "loss": 1.1662, "step": 6351 }, { "epoch": 0.34728173586195116, "grad_norm": 2.606086254119873, "learning_rate": 7.58537759754474e-05, "loss": 0.8717, "step": 6352 }, { "epoch": 0.34733640867930976, "grad_norm": 2.9788787364959717, "learning_rate": 7.58461974670166e-05, "loss": 1.2759, "step": 6353 }, { "epoch": 0.34739108149666836, "grad_norm": 2.3983490467071533, "learning_rate": 7.583861814820108e-05, "loss": 1.0271, "step": 6354 }, { "epoch": 0.347445754314027, "grad_norm": 2.365996837615967, "learning_rate": 7.583103801923846e-05, "loss": 0.944, "step": 6355 }, { "epoch": 0.3475004271313856, "grad_norm": 3.6394171714782715, "learning_rate": 7.58234570803664e-05, "loss": 1.4052, "step": 6356 }, { "epoch": 0.34755509994874423, "grad_norm": 2.959017276763916, "learning_rate": 7.581587533182261e-05, "loss": 0.7773, "step": 6357 }, { "epoch": 0.34760977276610283, "grad_norm": 1.980675458908081, "learning_rate": 7.580829277384483e-05, "loss": 0.9956, "step": 6358 }, { "epoch": 0.3476644455834615, "grad_norm": 2.2544093132019043, "learning_rate": 7.580070940667076e-05, "loss": 1.0933, "step": 6359 }, { "epoch": 0.3477191184008201, "grad_norm": 2.7071022987365723, "learning_rate": 7.57931252305382e-05, "loss": 1.1776, "step": 6360 }, { "epoch": 0.3477737912181787, "grad_norm": 2.2837061882019043, "learning_rate": 7.578554024568495e-05, "loss": 1.0989, "step": 6361 }, { "epoch": 0.34782846403553735, "grad_norm": 2.5648865699768066, "learning_rate": 7.57779544523488e-05, "loss": 1.0266, "step": 6362 }, { "epoch": 0.34788313685289596, "grad_norm": 2.989129066467285, "learning_rate": 7.577036785076762e-05, "loss": 1.1182, "step": 6363 }, { "epoch": 0.34793780967025456, "grad_norm": 2.1061367988586426, "learning_rate": 7.576278044117928e-05, "loss": 0.8988, "step": 6364 }, { "epoch": 0.34799248248761316, "grad_norm": 2.6359751224517822, "learning_rate": 7.575519222382165e-05, "loss": 0.9179, "step": 6365 }, { "epoch": 0.3480471553049718, "grad_norm": 2.2912118434906006, "learning_rate": 7.574760319893269e-05, "loss": 1.048, "step": 6366 }, { "epoch": 0.3481018281223304, "grad_norm": 2.4664502143859863, "learning_rate": 7.574001336675032e-05, "loss": 0.9957, "step": 6367 }, { "epoch": 0.34815650093968903, "grad_norm": 2.713562250137329, "learning_rate": 7.573242272751253e-05, "loss": 0.9045, "step": 6368 }, { "epoch": 0.3482111737570477, "grad_norm": 2.6124191284179688, "learning_rate": 7.572483128145731e-05, "loss": 1.1274, "step": 6369 }, { "epoch": 0.3482658465744063, "grad_norm": 2.3842968940734863, "learning_rate": 7.571723902882269e-05, "loss": 0.8964, "step": 6370 }, { "epoch": 0.3483205193917649, "grad_norm": 2.026535987854004, "learning_rate": 7.570964596984671e-05, "loss": 0.835, "step": 6371 }, { "epoch": 0.34837519220912355, "grad_norm": 2.576462745666504, "learning_rate": 7.570205210476741e-05, "loss": 1.0981, "step": 6372 }, { "epoch": 0.34842986502648216, "grad_norm": 2.7413995265960693, "learning_rate": 7.569445743382297e-05, "loss": 0.9027, "step": 6373 }, { "epoch": 0.34848453784384076, "grad_norm": 3.1568217277526855, "learning_rate": 7.568686195725146e-05, "loss": 1.1188, "step": 6374 }, { "epoch": 0.34853921066119936, "grad_norm": 2.1014819145202637, "learning_rate": 7.567926567529102e-05, "loss": 0.8015, "step": 6375 }, { "epoch": 0.348593883478558, "grad_norm": 3.0711259841918945, "learning_rate": 7.567166858817987e-05, "loss": 1.1573, "step": 6376 }, { "epoch": 0.3486485562959166, "grad_norm": 2.43168306350708, "learning_rate": 7.566407069615615e-05, "loss": 1.1007, "step": 6377 }, { "epoch": 0.3487032291132752, "grad_norm": 2.5632832050323486, "learning_rate": 7.565647199945814e-05, "loss": 1.0047, "step": 6378 }, { "epoch": 0.3487579019306339, "grad_norm": 2.3980295658111572, "learning_rate": 7.564887249832407e-05, "loss": 0.8162, "step": 6379 }, { "epoch": 0.3488125747479925, "grad_norm": 2.4219799041748047, "learning_rate": 7.56412721929922e-05, "loss": 1.145, "step": 6380 }, { "epoch": 0.3488672475653511, "grad_norm": 2.4350719451904297, "learning_rate": 7.563367108370086e-05, "loss": 1.1595, "step": 6381 }, { "epoch": 0.3489219203827097, "grad_norm": 2.616704225540161, "learning_rate": 7.562606917068833e-05, "loss": 1.0754, "step": 6382 }, { "epoch": 0.34897659320006835, "grad_norm": 2.3017427921295166, "learning_rate": 7.561846645419301e-05, "loss": 0.903, "step": 6383 }, { "epoch": 0.34903126601742696, "grad_norm": 2.1209192276000977, "learning_rate": 7.561086293445328e-05, "loss": 0.9925, "step": 6384 }, { "epoch": 0.34908593883478556, "grad_norm": 2.734069585800171, "learning_rate": 7.560325861170749e-05, "loss": 1.0247, "step": 6385 }, { "epoch": 0.3491406116521442, "grad_norm": 1.9325083494186401, "learning_rate": 7.559565348619412e-05, "loss": 1.0325, "step": 6386 }, { "epoch": 0.3491952844695028, "grad_norm": 2.4928033351898193, "learning_rate": 7.558804755815159e-05, "loss": 1.2529, "step": 6387 }, { "epoch": 0.3492499572868614, "grad_norm": 3.4500560760498047, "learning_rate": 7.558044082781839e-05, "loss": 1.2394, "step": 6388 }, { "epoch": 0.3493046301042201, "grad_norm": 2.948787212371826, "learning_rate": 7.557283329543301e-05, "loss": 0.8167, "step": 6389 }, { "epoch": 0.3493593029215787, "grad_norm": 2.188786506652832, "learning_rate": 7.5565224961234e-05, "loss": 1.1978, "step": 6390 }, { "epoch": 0.3494139757389373, "grad_norm": 2.6946756839752197, "learning_rate": 7.555761582545988e-05, "loss": 1.1446, "step": 6391 }, { "epoch": 0.3494686485562959, "grad_norm": 2.5053038597106934, "learning_rate": 7.555000588834926e-05, "loss": 1.2257, "step": 6392 }, { "epoch": 0.34952332137365455, "grad_norm": 2.1154232025146484, "learning_rate": 7.554239515014072e-05, "loss": 1.0286, "step": 6393 }, { "epoch": 0.34957799419101315, "grad_norm": 2.0339105129241943, "learning_rate": 7.55347836110729e-05, "loss": 0.9469, "step": 6394 }, { "epoch": 0.34963266700837176, "grad_norm": 2.894564628601074, "learning_rate": 7.552717127138447e-05, "loss": 0.9257, "step": 6395 }, { "epoch": 0.3496873398257304, "grad_norm": 2.341454029083252, "learning_rate": 7.551955813131408e-05, "loss": 1.1258, "step": 6396 }, { "epoch": 0.349742012643089, "grad_norm": 2.337233781814575, "learning_rate": 7.551194419110043e-05, "loss": 0.9192, "step": 6397 }, { "epoch": 0.3497966854604476, "grad_norm": 2.273251533508301, "learning_rate": 7.550432945098226e-05, "loss": 1.0729, "step": 6398 }, { "epoch": 0.3498513582778063, "grad_norm": 3.20784068107605, "learning_rate": 7.549671391119833e-05, "loss": 1.1395, "step": 6399 }, { "epoch": 0.3499060310951649, "grad_norm": 2.2555394172668457, "learning_rate": 7.54890975719874e-05, "loss": 0.8811, "step": 6400 }, { "epoch": 0.3499607039125235, "grad_norm": 2.108433485031128, "learning_rate": 7.548148043358832e-05, "loss": 1.0766, "step": 6401 }, { "epoch": 0.3500153767298821, "grad_norm": 2.255246162414551, "learning_rate": 7.547386249623985e-05, "loss": 1.1124, "step": 6402 }, { "epoch": 0.35007004954724075, "grad_norm": 2.616335153579712, "learning_rate": 7.54662437601809e-05, "loss": 0.8756, "step": 6403 }, { "epoch": 0.35012472236459935, "grad_norm": 2.063290596008301, "learning_rate": 7.54586242256503e-05, "loss": 1.1282, "step": 6404 }, { "epoch": 0.35017939518195795, "grad_norm": 2.037402629852295, "learning_rate": 7.545100389288702e-05, "loss": 1.0775, "step": 6405 }, { "epoch": 0.3502340679993166, "grad_norm": 2.2381200790405273, "learning_rate": 7.544338276212992e-05, "loss": 1.0319, "step": 6406 }, { "epoch": 0.3502887408166752, "grad_norm": 3.6234164237976074, "learning_rate": 7.543576083361799e-05, "loss": 1.2713, "step": 6407 }, { "epoch": 0.3503434136340338, "grad_norm": 2.688206434249878, "learning_rate": 7.542813810759021e-05, "loss": 1.2549, "step": 6408 }, { "epoch": 0.3503980864513924, "grad_norm": 2.3680694103240967, "learning_rate": 7.542051458428558e-05, "loss": 1.126, "step": 6409 }, { "epoch": 0.3504527592687511, "grad_norm": 1.687228798866272, "learning_rate": 7.541289026394312e-05, "loss": 0.8536, "step": 6410 }, { "epoch": 0.3505074320861097, "grad_norm": 2.009244680404663, "learning_rate": 7.540526514680188e-05, "loss": 0.9766, "step": 6411 }, { "epoch": 0.3505621049034683, "grad_norm": 2.1470706462860107, "learning_rate": 7.539763923310095e-05, "loss": 0.9295, "step": 6412 }, { "epoch": 0.35061677772082694, "grad_norm": 1.8363406658172607, "learning_rate": 7.539001252307942e-05, "loss": 0.9564, "step": 6413 }, { "epoch": 0.35067145053818555, "grad_norm": 2.4656529426574707, "learning_rate": 7.538238501697645e-05, "loss": 1.094, "step": 6414 }, { "epoch": 0.35072612335554415, "grad_norm": 3.6163768768310547, "learning_rate": 7.537475671503119e-05, "loss": 1.2727, "step": 6415 }, { "epoch": 0.3507807961729028, "grad_norm": 2.2894458770751953, "learning_rate": 7.536712761748277e-05, "loss": 1.1685, "step": 6416 }, { "epoch": 0.3508354689902614, "grad_norm": 2.8482987880706787, "learning_rate": 7.535949772457044e-05, "loss": 1.2262, "step": 6417 }, { "epoch": 0.35089014180762, "grad_norm": 2.851997137069702, "learning_rate": 7.535186703653342e-05, "loss": 1.1617, "step": 6418 }, { "epoch": 0.3509448146249786, "grad_norm": 2.3129541873931885, "learning_rate": 7.534423555361095e-05, "loss": 0.8849, "step": 6419 }, { "epoch": 0.3509994874423373, "grad_norm": 2.7737436294555664, "learning_rate": 7.53366032760423e-05, "loss": 1.0805, "step": 6420 }, { "epoch": 0.3510541602596959, "grad_norm": 2.570037364959717, "learning_rate": 7.532897020406682e-05, "loss": 1.0492, "step": 6421 }, { "epoch": 0.3511088330770545, "grad_norm": 2.5147898197174072, "learning_rate": 7.53213363379238e-05, "loss": 1.1524, "step": 6422 }, { "epoch": 0.35116350589441314, "grad_norm": 2.8314051628112793, "learning_rate": 7.531370167785261e-05, "loss": 1.1418, "step": 6423 }, { "epoch": 0.35121817871177174, "grad_norm": 2.3100740909576416, "learning_rate": 7.53060662240926e-05, "loss": 1.2316, "step": 6424 }, { "epoch": 0.35127285152913035, "grad_norm": 3.3247129917144775, "learning_rate": 7.52984299768832e-05, "loss": 1.0953, "step": 6425 }, { "epoch": 0.351327524346489, "grad_norm": 2.7032737731933594, "learning_rate": 7.529079293646384e-05, "loss": 1.0192, "step": 6426 }, { "epoch": 0.3513821971638476, "grad_norm": 2.6033670902252197, "learning_rate": 7.528315510307396e-05, "loss": 1.0803, "step": 6427 }, { "epoch": 0.3514368699812062, "grad_norm": 2.2963104248046875, "learning_rate": 7.527551647695303e-05, "loss": 1.0684, "step": 6428 }, { "epoch": 0.3514915427985648, "grad_norm": 3.069892168045044, "learning_rate": 7.526787705834057e-05, "loss": 1.1236, "step": 6429 }, { "epoch": 0.3515462156159235, "grad_norm": 2.163858413696289, "learning_rate": 7.52602368474761e-05, "loss": 0.9775, "step": 6430 }, { "epoch": 0.3516008884332821, "grad_norm": 2.1442668437957764, "learning_rate": 7.525259584459916e-05, "loss": 1.0228, "step": 6431 }, { "epoch": 0.3516555612506407, "grad_norm": 2.793093204498291, "learning_rate": 7.524495404994935e-05, "loss": 1.2607, "step": 6432 }, { "epoch": 0.35171023406799934, "grad_norm": 2.0358455181121826, "learning_rate": 7.523731146376628e-05, "loss": 1.0963, "step": 6433 }, { "epoch": 0.35176490688535794, "grad_norm": 4.166771411895752, "learning_rate": 7.522966808628953e-05, "loss": 1.3081, "step": 6434 }, { "epoch": 0.35181957970271655, "grad_norm": 2.7003402709960938, "learning_rate": 7.522202391775878e-05, "loss": 1.0478, "step": 6435 }, { "epoch": 0.35187425252007515, "grad_norm": 2.365429162979126, "learning_rate": 7.521437895841371e-05, "loss": 0.9488, "step": 6436 }, { "epoch": 0.3519289253374338, "grad_norm": 2.868694305419922, "learning_rate": 7.520673320849401e-05, "loss": 0.8429, "step": 6437 }, { "epoch": 0.3519835981547924, "grad_norm": 1.8662290573120117, "learning_rate": 7.519908666823942e-05, "loss": 0.9835, "step": 6438 }, { "epoch": 0.352038270972151, "grad_norm": 2.4554433822631836, "learning_rate": 7.51914393378897e-05, "loss": 1.0063, "step": 6439 }, { "epoch": 0.35209294378950967, "grad_norm": 2.758019208908081, "learning_rate": 7.518379121768458e-05, "loss": 1.1334, "step": 6440 }, { "epoch": 0.3521476166068683, "grad_norm": 2.744941234588623, "learning_rate": 7.51761423078639e-05, "loss": 1.0839, "step": 6441 }, { "epoch": 0.3522022894242269, "grad_norm": 2.1689915657043457, "learning_rate": 7.516849260866748e-05, "loss": 1.1554, "step": 6442 }, { "epoch": 0.35225696224158554, "grad_norm": 2.81284499168396, "learning_rate": 7.516084212033514e-05, "loss": 0.9892, "step": 6443 }, { "epoch": 0.35231163505894414, "grad_norm": 2.6384520530700684, "learning_rate": 7.51531908431068e-05, "loss": 1.0526, "step": 6444 }, { "epoch": 0.35236630787630274, "grad_norm": 3.6764578819274902, "learning_rate": 7.514553877722233e-05, "loss": 0.9705, "step": 6445 }, { "epoch": 0.35242098069366135, "grad_norm": 2.4540202617645264, "learning_rate": 7.513788592292163e-05, "loss": 1.25, "step": 6446 }, { "epoch": 0.35247565351102, "grad_norm": 2.9147865772247314, "learning_rate": 7.513023228044471e-05, "loss": 1.1044, "step": 6447 }, { "epoch": 0.3525303263283786, "grad_norm": 2.6635513305664062, "learning_rate": 7.51225778500315e-05, "loss": 1.235, "step": 6448 }, { "epoch": 0.3525849991457372, "grad_norm": 2.618597984313965, "learning_rate": 7.511492263192202e-05, "loss": 0.9838, "step": 6449 }, { "epoch": 0.35263967196309587, "grad_norm": 3.097266912460327, "learning_rate": 7.510726662635626e-05, "loss": 1.2536, "step": 6450 }, { "epoch": 0.35269434478045447, "grad_norm": 2.670652151107788, "learning_rate": 7.50996098335743e-05, "loss": 1.1783, "step": 6451 }, { "epoch": 0.3527490175978131, "grad_norm": 2.3899800777435303, "learning_rate": 7.50919522538162e-05, "loss": 1.2894, "step": 6452 }, { "epoch": 0.35280369041517173, "grad_norm": 2.408550500869751, "learning_rate": 7.508429388732206e-05, "loss": 1.0998, "step": 6453 }, { "epoch": 0.35285836323253034, "grad_norm": 1.9573527574539185, "learning_rate": 7.5076634734332e-05, "loss": 0.8242, "step": 6454 }, { "epoch": 0.35291303604988894, "grad_norm": 2.6271989345550537, "learning_rate": 7.506897479508617e-05, "loss": 0.9776, "step": 6455 }, { "epoch": 0.35296770886724754, "grad_norm": 2.5114760398864746, "learning_rate": 7.50613140698247e-05, "loss": 0.9696, "step": 6456 }, { "epoch": 0.3530223816846062, "grad_norm": 2.0640385150909424, "learning_rate": 7.505365255878785e-05, "loss": 1.0144, "step": 6457 }, { "epoch": 0.3530770545019648, "grad_norm": 2.6713216304779053, "learning_rate": 7.504599026221581e-05, "loss": 1.16, "step": 6458 }, { "epoch": 0.3531317273193234, "grad_norm": 2.4226772785186768, "learning_rate": 7.503832718034884e-05, "loss": 1.2225, "step": 6459 }, { "epoch": 0.35318640013668207, "grad_norm": 2.4748728275299072, "learning_rate": 7.503066331342717e-05, "loss": 1.039, "step": 6460 }, { "epoch": 0.35324107295404067, "grad_norm": 3.324205160140991, "learning_rate": 7.502299866169112e-05, "loss": 1.0743, "step": 6461 }, { "epoch": 0.35329574577139927, "grad_norm": 2.1019420623779297, "learning_rate": 7.501533322538102e-05, "loss": 1.0314, "step": 6462 }, { "epoch": 0.3533504185887579, "grad_norm": 2.1574246883392334, "learning_rate": 7.500766700473718e-05, "loss": 0.9356, "step": 6463 }, { "epoch": 0.35340509140611653, "grad_norm": 2.3344414234161377, "learning_rate": 7.500000000000001e-05, "loss": 1.1548, "step": 6464 }, { "epoch": 0.35345976422347514, "grad_norm": 2.8621935844421387, "learning_rate": 7.499233221140986e-05, "loss": 1.2874, "step": 6465 }, { "epoch": 0.35351443704083374, "grad_norm": 2.3429746627807617, "learning_rate": 7.498466363920717e-05, "loss": 0.8744, "step": 6466 }, { "epoch": 0.3535691098581924, "grad_norm": 2.5340957641601562, "learning_rate": 7.497699428363238e-05, "loss": 0.9366, "step": 6467 }, { "epoch": 0.353623782675551, "grad_norm": 2.8621318340301514, "learning_rate": 7.496932414492597e-05, "loss": 1.1101, "step": 6468 }, { "epoch": 0.3536784554929096, "grad_norm": 2.643761396408081, "learning_rate": 7.49616532233284e-05, "loss": 0.905, "step": 6469 }, { "epoch": 0.35373312831026826, "grad_norm": 2.2004880905151367, "learning_rate": 7.495398151908018e-05, "loss": 1.1196, "step": 6470 }, { "epoch": 0.35378780112762687, "grad_norm": 2.8659403324127197, "learning_rate": 7.49463090324219e-05, "loss": 1.2637, "step": 6471 }, { "epoch": 0.35384247394498547, "grad_norm": 2.6279876232147217, "learning_rate": 7.493863576359407e-05, "loss": 1.1185, "step": 6472 }, { "epoch": 0.3538971467623441, "grad_norm": 3.4399430751800537, "learning_rate": 7.493096171283731e-05, "loss": 1.0505, "step": 6473 }, { "epoch": 0.35395181957970273, "grad_norm": 2.6700029373168945, "learning_rate": 7.492328688039222e-05, "loss": 1.0107, "step": 6474 }, { "epoch": 0.35400649239706133, "grad_norm": 2.4431440830230713, "learning_rate": 7.491561126649944e-05, "loss": 1.1145, "step": 6475 }, { "epoch": 0.35406116521441994, "grad_norm": 2.873922348022461, "learning_rate": 7.490793487139963e-05, "loss": 0.9047, "step": 6476 }, { "epoch": 0.3541158380317786, "grad_norm": 2.7052736282348633, "learning_rate": 7.490025769533349e-05, "loss": 1.0865, "step": 6477 }, { "epoch": 0.3541705108491372, "grad_norm": 2.670832395553589, "learning_rate": 7.489257973854172e-05, "loss": 1.1361, "step": 6478 }, { "epoch": 0.3542251836664958, "grad_norm": 2.913699150085449, "learning_rate": 7.488490100126505e-05, "loss": 1.1316, "step": 6479 }, { "epoch": 0.35427985648385446, "grad_norm": 2.584498643875122, "learning_rate": 7.487722148374425e-05, "loss": 1.0309, "step": 6480 }, { "epoch": 0.35433452930121306, "grad_norm": 2.1856582164764404, "learning_rate": 7.486954118622011e-05, "loss": 0.8098, "step": 6481 }, { "epoch": 0.35438920211857167, "grad_norm": 2.583812713623047, "learning_rate": 7.486186010893342e-05, "loss": 1.0507, "step": 6482 }, { "epoch": 0.35444387493593027, "grad_norm": 2.6025233268737793, "learning_rate": 7.485417825212503e-05, "loss": 1.0558, "step": 6483 }, { "epoch": 0.35449854775328893, "grad_norm": 2.8266401290893555, "learning_rate": 7.484649561603578e-05, "loss": 0.9046, "step": 6484 }, { "epoch": 0.35455322057064753, "grad_norm": 2.819918155670166, "learning_rate": 7.483881220090658e-05, "loss": 1.2264, "step": 6485 }, { "epoch": 0.35460789338800613, "grad_norm": 2.532806158065796, "learning_rate": 7.48311280069783e-05, "loss": 1.0502, "step": 6486 }, { "epoch": 0.3546625662053648, "grad_norm": 2.5212154388427734, "learning_rate": 7.482344303449192e-05, "loss": 0.9457, "step": 6487 }, { "epoch": 0.3547172390227234, "grad_norm": 3.3644802570343018, "learning_rate": 7.481575728368835e-05, "loss": 1.2771, "step": 6488 }, { "epoch": 0.354771911840082, "grad_norm": 2.171780586242676, "learning_rate": 7.480807075480858e-05, "loss": 1.1087, "step": 6489 }, { "epoch": 0.3548265846574406, "grad_norm": 2.257398843765259, "learning_rate": 7.480038344809362e-05, "loss": 1.1998, "step": 6490 }, { "epoch": 0.35488125747479926, "grad_norm": 2.2444849014282227, "learning_rate": 7.479269536378452e-05, "loss": 1.2203, "step": 6491 }, { "epoch": 0.35493593029215786, "grad_norm": 4.5202531814575195, "learning_rate": 7.47850065021223e-05, "loss": 1.2086, "step": 6492 }, { "epoch": 0.35499060310951647, "grad_norm": 2.6806931495666504, "learning_rate": 7.477731686334805e-05, "loss": 1.1996, "step": 6493 }, { "epoch": 0.3550452759268751, "grad_norm": 3.1172053813934326, "learning_rate": 7.476962644770289e-05, "loss": 1.1191, "step": 6494 }, { "epoch": 0.35509994874423373, "grad_norm": 2.5091097354888916, "learning_rate": 7.476193525542791e-05, "loss": 1.1785, "step": 6495 }, { "epoch": 0.35515462156159233, "grad_norm": 2.329892873764038, "learning_rate": 7.475424328676428e-05, "loss": 1.0355, "step": 6496 }, { "epoch": 0.355209294378951, "grad_norm": 2.511399984359741, "learning_rate": 7.474655054195319e-05, "loss": 1.0219, "step": 6497 }, { "epoch": 0.3552639671963096, "grad_norm": 2.8235983848571777, "learning_rate": 7.473885702123581e-05, "loss": 1.1333, "step": 6498 }, { "epoch": 0.3553186400136682, "grad_norm": 2.4653499126434326, "learning_rate": 7.473116272485338e-05, "loss": 0.9974, "step": 6499 }, { "epoch": 0.3553733128310268, "grad_norm": 2.748420000076294, "learning_rate": 7.472346765304714e-05, "loss": 1.172, "step": 6500 }, { "epoch": 0.35542798564838546, "grad_norm": 2.6279678344726562, "learning_rate": 7.471577180605837e-05, "loss": 0.912, "step": 6501 }, { "epoch": 0.35548265846574406, "grad_norm": 2.5289864540100098, "learning_rate": 7.470807518412838e-05, "loss": 1.2443, "step": 6502 }, { "epoch": 0.35553733128310266, "grad_norm": 2.8103251457214355, "learning_rate": 7.470037778749845e-05, "loss": 1.2171, "step": 6503 }, { "epoch": 0.3555920041004613, "grad_norm": 2.981278419494629, "learning_rate": 7.469267961640998e-05, "loss": 0.928, "step": 6504 }, { "epoch": 0.3556466769178199, "grad_norm": 2.25, "learning_rate": 7.468498067110428e-05, "loss": 1.1424, "step": 6505 }, { "epoch": 0.35570134973517853, "grad_norm": 2.1637823581695557, "learning_rate": 7.467728095182278e-05, "loss": 1.0919, "step": 6506 }, { "epoch": 0.3557560225525372, "grad_norm": 2.4290239810943604, "learning_rate": 7.466958045880689e-05, "loss": 1.0792, "step": 6507 }, { "epoch": 0.3558106953698958, "grad_norm": 2.748135566711426, "learning_rate": 7.466187919229806e-05, "loss": 1.0617, "step": 6508 }, { "epoch": 0.3558653681872544, "grad_norm": 2.4338669776916504, "learning_rate": 7.465417715253774e-05, "loss": 1.2459, "step": 6509 }, { "epoch": 0.355920041004613, "grad_norm": 2.6740663051605225, "learning_rate": 7.464647433976743e-05, "loss": 1.1336, "step": 6510 }, { "epoch": 0.35597471382197166, "grad_norm": 2.3606977462768555, "learning_rate": 7.463877075422866e-05, "loss": 1.0613, "step": 6511 }, { "epoch": 0.35602938663933026, "grad_norm": 2.729600191116333, "learning_rate": 7.463106639616292e-05, "loss": 1.1246, "step": 6512 }, { "epoch": 0.35608405945668886, "grad_norm": 2.5873141288757324, "learning_rate": 7.462336126581184e-05, "loss": 1.1409, "step": 6513 }, { "epoch": 0.3561387322740475, "grad_norm": 3.1274819374084473, "learning_rate": 7.461565536341697e-05, "loss": 0.9801, "step": 6514 }, { "epoch": 0.3561934050914061, "grad_norm": 2.302715301513672, "learning_rate": 7.460794868921991e-05, "loss": 0.8438, "step": 6515 }, { "epoch": 0.3562480779087647, "grad_norm": 3.4056198596954346, "learning_rate": 7.460024124346234e-05, "loss": 1.2692, "step": 6516 }, { "epoch": 0.35630275072612333, "grad_norm": 2.4979708194732666, "learning_rate": 7.459253302638587e-05, "loss": 1.0078, "step": 6517 }, { "epoch": 0.356357423543482, "grad_norm": 2.460085153579712, "learning_rate": 7.458482403823221e-05, "loss": 1.0534, "step": 6518 }, { "epoch": 0.3564120963608406, "grad_norm": 2.1830079555511475, "learning_rate": 7.457711427924307e-05, "loss": 0.9788, "step": 6519 }, { "epoch": 0.3564667691781992, "grad_norm": 2.0360331535339355, "learning_rate": 7.456940374966017e-05, "loss": 0.9591, "step": 6520 }, { "epoch": 0.35652144199555785, "grad_norm": 3.860779285430908, "learning_rate": 7.456169244972528e-05, "loss": 1.0218, "step": 6521 }, { "epoch": 0.35657611481291646, "grad_norm": 2.2411060333251953, "learning_rate": 7.455398037968019e-05, "loss": 1.0607, "step": 6522 }, { "epoch": 0.35663078763027506, "grad_norm": 2.06976580619812, "learning_rate": 7.454626753976668e-05, "loss": 0.9634, "step": 6523 }, { "epoch": 0.3566854604476337, "grad_norm": 2.2969284057617188, "learning_rate": 7.453855393022657e-05, "loss": 0.9639, "step": 6524 }, { "epoch": 0.3567401332649923, "grad_norm": 2.8867108821868896, "learning_rate": 7.453083955130176e-05, "loss": 1.192, "step": 6525 }, { "epoch": 0.3567948060823509, "grad_norm": 2.6298136711120605, "learning_rate": 7.45231244032341e-05, "loss": 1.2707, "step": 6526 }, { "epoch": 0.3568494788997095, "grad_norm": 3.0081958770751953, "learning_rate": 7.45154084862655e-05, "loss": 1.0297, "step": 6527 }, { "epoch": 0.3569041517170682, "grad_norm": 3.011017084121704, "learning_rate": 7.450769180063786e-05, "loss": 1.2756, "step": 6528 }, { "epoch": 0.3569588245344268, "grad_norm": 2.161667585372925, "learning_rate": 7.449997434659315e-05, "loss": 1.0024, "step": 6529 }, { "epoch": 0.3570134973517854, "grad_norm": 2.2204737663269043, "learning_rate": 7.449225612437336e-05, "loss": 1.0045, "step": 6530 }, { "epoch": 0.35706817016914405, "grad_norm": 2.142345905303955, "learning_rate": 7.448453713422044e-05, "loss": 0.936, "step": 6531 }, { "epoch": 0.35712284298650265, "grad_norm": 2.611579179763794, "learning_rate": 7.447681737637647e-05, "loss": 1.2255, "step": 6532 }, { "epoch": 0.35717751580386126, "grad_norm": 2.286587953567505, "learning_rate": 7.446909685108346e-05, "loss": 0.8809, "step": 6533 }, { "epoch": 0.3572321886212199, "grad_norm": 2.444784641265869, "learning_rate": 7.446137555858348e-05, "loss": 1.0505, "step": 6534 }, { "epoch": 0.3572868614385785, "grad_norm": 2.2168691158294678, "learning_rate": 7.445365349911866e-05, "loss": 1.1311, "step": 6535 }, { "epoch": 0.3573415342559371, "grad_norm": 2.2190024852752686, "learning_rate": 7.444593067293106e-05, "loss": 1.0257, "step": 6536 }, { "epoch": 0.3573962070732957, "grad_norm": 2.328340530395508, "learning_rate": 7.443820708026288e-05, "loss": 1.0336, "step": 6537 }, { "epoch": 0.3574508798906544, "grad_norm": 2.1829216480255127, "learning_rate": 7.443048272135626e-05, "loss": 0.9597, "step": 6538 }, { "epoch": 0.357505552708013, "grad_norm": 3.3481829166412354, "learning_rate": 7.442275759645337e-05, "loss": 1.1793, "step": 6539 }, { "epoch": 0.3575602255253716, "grad_norm": 2.708878755569458, "learning_rate": 7.441503170579646e-05, "loss": 1.1978, "step": 6540 }, { "epoch": 0.35761489834273025, "grad_norm": 4.039490222930908, "learning_rate": 7.440730504962776e-05, "loss": 0.8288, "step": 6541 }, { "epoch": 0.35766957116008885, "grad_norm": 2.2335777282714844, "learning_rate": 7.439957762818952e-05, "loss": 1.0632, "step": 6542 }, { "epoch": 0.35772424397744745, "grad_norm": 4.514975070953369, "learning_rate": 7.439184944172403e-05, "loss": 1.1315, "step": 6543 }, { "epoch": 0.35777891679480606, "grad_norm": 2.6353373527526855, "learning_rate": 7.438412049047361e-05, "loss": 1.3165, "step": 6544 }, { "epoch": 0.3578335896121647, "grad_norm": 2.571676731109619, "learning_rate": 7.437639077468058e-05, "loss": 1.094, "step": 6545 }, { "epoch": 0.3578882624295233, "grad_norm": 2.7574496269226074, "learning_rate": 7.436866029458731e-05, "loss": 1.0851, "step": 6546 }, { "epoch": 0.3579429352468819, "grad_norm": 2.411902904510498, "learning_rate": 7.436092905043619e-05, "loss": 1.1401, "step": 6547 }, { "epoch": 0.3579976080642406, "grad_norm": 2.1024832725524902, "learning_rate": 7.435319704246962e-05, "loss": 1.0005, "step": 6548 }, { "epoch": 0.3580522808815992, "grad_norm": 2.4022672176361084, "learning_rate": 7.434546427093e-05, "loss": 1.186, "step": 6549 }, { "epoch": 0.3581069536989578, "grad_norm": 2.6477301120758057, "learning_rate": 7.433773073605981e-05, "loss": 1.1256, "step": 6550 }, { "epoch": 0.35816162651631644, "grad_norm": 3.0871431827545166, "learning_rate": 7.432999643810154e-05, "loss": 1.3069, "step": 6551 }, { "epoch": 0.35821629933367505, "grad_norm": 2.4362611770629883, "learning_rate": 7.432226137729769e-05, "loss": 1.1192, "step": 6552 }, { "epoch": 0.35827097215103365, "grad_norm": 2.0613303184509277, "learning_rate": 7.431452555389078e-05, "loss": 0.9275, "step": 6553 }, { "epoch": 0.35832564496839225, "grad_norm": 2.5004959106445312, "learning_rate": 7.430678896812333e-05, "loss": 1.1736, "step": 6554 }, { "epoch": 0.3583803177857509, "grad_norm": 2.6919631958007812, "learning_rate": 7.429905162023795e-05, "loss": 1.2449, "step": 6555 }, { "epoch": 0.3584349906031095, "grad_norm": 2.9600703716278076, "learning_rate": 7.429131351047725e-05, "loss": 0.8735, "step": 6556 }, { "epoch": 0.3584896634204681, "grad_norm": 2.427844285964966, "learning_rate": 7.42835746390838e-05, "loss": 1.2274, "step": 6557 }, { "epoch": 0.3585443362378268, "grad_norm": 2.942985773086548, "learning_rate": 7.427583500630029e-05, "loss": 1.0876, "step": 6558 }, { "epoch": 0.3585990090551854, "grad_norm": 3.558380365371704, "learning_rate": 7.426809461236936e-05, "loss": 1.219, "step": 6559 }, { "epoch": 0.358653681872544, "grad_norm": 3.144913911819458, "learning_rate": 7.426035345753373e-05, "loss": 0.8572, "step": 6560 }, { "epoch": 0.3587083546899026, "grad_norm": 2.561671495437622, "learning_rate": 7.42526115420361e-05, "loss": 1.0695, "step": 6561 }, { "epoch": 0.35876302750726125, "grad_norm": 2.618072509765625, "learning_rate": 7.424486886611922e-05, "loss": 1.0308, "step": 6562 }, { "epoch": 0.35881770032461985, "grad_norm": 2.4328055381774902, "learning_rate": 7.423712543002585e-05, "loss": 1.0957, "step": 6563 }, { "epoch": 0.35887237314197845, "grad_norm": 2.4784412384033203, "learning_rate": 7.422938123399878e-05, "loss": 1.2268, "step": 6564 }, { "epoch": 0.3589270459593371, "grad_norm": 2.3162992000579834, "learning_rate": 7.42216362782808e-05, "loss": 0.9338, "step": 6565 }, { "epoch": 0.3589817187766957, "grad_norm": 2.552971839904785, "learning_rate": 7.421389056311479e-05, "loss": 1.1597, "step": 6566 }, { "epoch": 0.3590363915940543, "grad_norm": 2.3909757137298584, "learning_rate": 7.42061440887436e-05, "loss": 0.9458, "step": 6567 }, { "epoch": 0.359091064411413, "grad_norm": 2.2476980686187744, "learning_rate": 7.419839685541006e-05, "loss": 1.0781, "step": 6568 }, { "epoch": 0.3591457372287716, "grad_norm": 2.0948901176452637, "learning_rate": 7.419064886335716e-05, "loss": 0.9889, "step": 6569 }, { "epoch": 0.3592004100461302, "grad_norm": 3.7298474311828613, "learning_rate": 7.418290011282777e-05, "loss": 1.0617, "step": 6570 }, { "epoch": 0.3592550828634888, "grad_norm": 2.738103151321411, "learning_rate": 7.417515060406486e-05, "loss": 1.0634, "step": 6571 }, { "epoch": 0.35930975568084744, "grad_norm": 2.328395366668701, "learning_rate": 7.416740033731145e-05, "loss": 1.071, "step": 6572 }, { "epoch": 0.35936442849820605, "grad_norm": 2.2751054763793945, "learning_rate": 7.415964931281046e-05, "loss": 0.95, "step": 6573 }, { "epoch": 0.35941910131556465, "grad_norm": 2.893911838531494, "learning_rate": 7.4151897530805e-05, "loss": 1.2284, "step": 6574 }, { "epoch": 0.3594737741329233, "grad_norm": 2.298661231994629, "learning_rate": 7.414414499153805e-05, "loss": 1.0578, "step": 6575 }, { "epoch": 0.3595284469502819, "grad_norm": 3.345885753631592, "learning_rate": 7.413639169525275e-05, "loss": 1.2849, "step": 6576 }, { "epoch": 0.3595831197676405, "grad_norm": 2.2306559085845947, "learning_rate": 7.412863764219216e-05, "loss": 1.0016, "step": 6577 }, { "epoch": 0.35963779258499917, "grad_norm": 2.68406343460083, "learning_rate": 7.41208828325994e-05, "loss": 1.1779, "step": 6578 }, { "epoch": 0.3596924654023578, "grad_norm": 2.0691163539886475, "learning_rate": 7.411312726671762e-05, "loss": 1.1569, "step": 6579 }, { "epoch": 0.3597471382197164, "grad_norm": 2.2115907669067383, "learning_rate": 7.410537094479e-05, "loss": 1.0019, "step": 6580 }, { "epoch": 0.359801811037075, "grad_norm": 2.4584286212921143, "learning_rate": 7.409761386705973e-05, "loss": 1.0746, "step": 6581 }, { "epoch": 0.35985648385443364, "grad_norm": 4.0645833015441895, "learning_rate": 7.408985603377001e-05, "loss": 0.9788, "step": 6582 }, { "epoch": 0.35991115667179224, "grad_norm": 3.0032310485839844, "learning_rate": 7.408209744516409e-05, "loss": 1.0408, "step": 6583 }, { "epoch": 0.35996582948915085, "grad_norm": 1.854418158531189, "learning_rate": 7.407433810148524e-05, "loss": 1.0139, "step": 6584 }, { "epoch": 0.3600205023065095, "grad_norm": 2.140336275100708, "learning_rate": 7.406657800297674e-05, "loss": 1.0084, "step": 6585 }, { "epoch": 0.3600751751238681, "grad_norm": 2.950986623764038, "learning_rate": 7.405881714988191e-05, "loss": 1.1639, "step": 6586 }, { "epoch": 0.3601298479412267, "grad_norm": 2.5889248847961426, "learning_rate": 7.405105554244408e-05, "loss": 1.0848, "step": 6587 }, { "epoch": 0.3601845207585853, "grad_norm": 2.641066074371338, "learning_rate": 7.404329318090659e-05, "loss": 1.0008, "step": 6588 }, { "epoch": 0.360239193575944, "grad_norm": 2.215651512145996, "learning_rate": 7.403553006551285e-05, "loss": 1.0822, "step": 6589 }, { "epoch": 0.3602938663933026, "grad_norm": 2.8131840229034424, "learning_rate": 7.402776619650624e-05, "loss": 1.061, "step": 6590 }, { "epoch": 0.3603485392106612, "grad_norm": 2.9243032932281494, "learning_rate": 7.402000157413023e-05, "loss": 1.183, "step": 6591 }, { "epoch": 0.36040321202801984, "grad_norm": 2.3492026329040527, "learning_rate": 7.401223619862822e-05, "loss": 1.0647, "step": 6592 }, { "epoch": 0.36045788484537844, "grad_norm": 4.598526954650879, "learning_rate": 7.400447007024371e-05, "loss": 1.1682, "step": 6593 }, { "epoch": 0.36051255766273704, "grad_norm": 3.3261051177978516, "learning_rate": 7.399670318922023e-05, "loss": 1.3322, "step": 6594 }, { "epoch": 0.3605672304800957, "grad_norm": 2.5069074630737305, "learning_rate": 7.398893555580126e-05, "loss": 1.2314, "step": 6595 }, { "epoch": 0.3606219032974543, "grad_norm": 2.533703327178955, "learning_rate": 7.398116717023036e-05, "loss": 1.25, "step": 6596 }, { "epoch": 0.3606765761148129, "grad_norm": 2.443821430206299, "learning_rate": 7.397339803275112e-05, "loss": 1.1409, "step": 6597 }, { "epoch": 0.3607312489321715, "grad_norm": 2.9846084117889404, "learning_rate": 7.39656281436071e-05, "loss": 1.1863, "step": 6598 }, { "epoch": 0.36078592174953017, "grad_norm": 2.2973806858062744, "learning_rate": 7.395785750304195e-05, "loss": 0.9387, "step": 6599 }, { "epoch": 0.3608405945668888, "grad_norm": 2.3036813735961914, "learning_rate": 7.395008611129928e-05, "loss": 1.1309, "step": 6600 }, { "epoch": 0.3608952673842474, "grad_norm": 1.9787919521331787, "learning_rate": 7.394231396862279e-05, "loss": 1.0049, "step": 6601 }, { "epoch": 0.36094994020160603, "grad_norm": 2.1070680618286133, "learning_rate": 7.393454107525615e-05, "loss": 0.9881, "step": 6602 }, { "epoch": 0.36100461301896464, "grad_norm": 2.526141881942749, "learning_rate": 7.392676743144308e-05, "loss": 0.9334, "step": 6603 }, { "epoch": 0.36105928583632324, "grad_norm": 2.590731143951416, "learning_rate": 7.391899303742729e-05, "loss": 0.9952, "step": 6604 }, { "epoch": 0.3611139586536819, "grad_norm": 3.019648790359497, "learning_rate": 7.39112178934526e-05, "loss": 1.2723, "step": 6605 }, { "epoch": 0.3611686314710405, "grad_norm": 2.881861686706543, "learning_rate": 7.39034419997627e-05, "loss": 1.1017, "step": 6606 }, { "epoch": 0.3612233042883991, "grad_norm": 4.597650051116943, "learning_rate": 7.389566535660149e-05, "loss": 0.9291, "step": 6607 }, { "epoch": 0.3612779771057577, "grad_norm": 2.6069846153259277, "learning_rate": 7.388788796421273e-05, "loss": 0.9865, "step": 6608 }, { "epoch": 0.36133264992311637, "grad_norm": 2.4405035972595215, "learning_rate": 7.388010982284032e-05, "loss": 1.1236, "step": 6609 }, { "epoch": 0.36138732274047497, "grad_norm": 3.1756856441497803, "learning_rate": 7.387233093272812e-05, "loss": 1.2195, "step": 6610 }, { "epoch": 0.3614419955578336, "grad_norm": 2.180987596511841, "learning_rate": 7.386455129412002e-05, "loss": 1.0943, "step": 6611 }, { "epoch": 0.36149666837519223, "grad_norm": 2.6056814193725586, "learning_rate": 7.385677090725994e-05, "loss": 0.8919, "step": 6612 }, { "epoch": 0.36155134119255083, "grad_norm": 3.012773275375366, "learning_rate": 7.384898977239186e-05, "loss": 1.1725, "step": 6613 }, { "epoch": 0.36160601400990944, "grad_norm": 2.4819390773773193, "learning_rate": 7.384120788975973e-05, "loss": 0.9968, "step": 6614 }, { "epoch": 0.36166068682726804, "grad_norm": 2.31449031829834, "learning_rate": 7.383342525960754e-05, "loss": 1.0313, "step": 6615 }, { "epoch": 0.3617153596446267, "grad_norm": 2.7580459117889404, "learning_rate": 7.38256418821793e-05, "loss": 1.0839, "step": 6616 }, { "epoch": 0.3617700324619853, "grad_norm": 2.2669456005096436, "learning_rate": 7.381785775771906e-05, "loss": 1.0021, "step": 6617 }, { "epoch": 0.3618247052793439, "grad_norm": 2.451197862625122, "learning_rate": 7.38100728864709e-05, "loss": 1.0509, "step": 6618 }, { "epoch": 0.36187937809670256, "grad_norm": 2.6995787620544434, "learning_rate": 7.38022872686789e-05, "loss": 1.1688, "step": 6619 }, { "epoch": 0.36193405091406117, "grad_norm": 2.628066062927246, "learning_rate": 7.379450090458717e-05, "loss": 1.2365, "step": 6620 }, { "epoch": 0.36198872373141977, "grad_norm": 2.1922237873077393, "learning_rate": 7.378671379443983e-05, "loss": 0.9827, "step": 6621 }, { "epoch": 0.36204339654877843, "grad_norm": 2.2103278636932373, "learning_rate": 7.377892593848104e-05, "loss": 1.1245, "step": 6622 }, { "epoch": 0.36209806936613703, "grad_norm": 3.967703342437744, "learning_rate": 7.3771137336955e-05, "loss": 1.1825, "step": 6623 }, { "epoch": 0.36215274218349564, "grad_norm": 2.8568129539489746, "learning_rate": 7.37633479901059e-05, "loss": 1.0705, "step": 6624 }, { "epoch": 0.36220741500085424, "grad_norm": 2.033892869949341, "learning_rate": 7.375555789817799e-05, "loss": 1.0651, "step": 6625 }, { "epoch": 0.3622620878182129, "grad_norm": 2.3802058696746826, "learning_rate": 7.374776706141548e-05, "loss": 0.9404, "step": 6626 }, { "epoch": 0.3623167606355715, "grad_norm": 2.14561128616333, "learning_rate": 7.373997548006269e-05, "loss": 0.8647, "step": 6627 }, { "epoch": 0.3623714334529301, "grad_norm": 2.4933278560638428, "learning_rate": 7.373218315436387e-05, "loss": 1.1812, "step": 6628 }, { "epoch": 0.36242610627028876, "grad_norm": 1.9806950092315674, "learning_rate": 7.372439008456339e-05, "loss": 1.0259, "step": 6629 }, { "epoch": 0.36248077908764736, "grad_norm": 4.321889877319336, "learning_rate": 7.371659627090559e-05, "loss": 1.1483, "step": 6630 }, { "epoch": 0.36253545190500597, "grad_norm": 2.2468583583831787, "learning_rate": 7.370880171363479e-05, "loss": 0.8592, "step": 6631 }, { "epoch": 0.3625901247223646, "grad_norm": 2.445862054824829, "learning_rate": 7.370100641299542e-05, "loss": 1.3111, "step": 6632 }, { "epoch": 0.36264479753972323, "grad_norm": 2.087153673171997, "learning_rate": 7.36932103692319e-05, "loss": 1.0909, "step": 6633 }, { "epoch": 0.36269947035708183, "grad_norm": 2.490954875946045, "learning_rate": 7.368541358258865e-05, "loss": 1.1362, "step": 6634 }, { "epoch": 0.36275414317444044, "grad_norm": 2.7477829456329346, "learning_rate": 7.367761605331014e-05, "loss": 1.1693, "step": 6635 }, { "epoch": 0.3628088159917991, "grad_norm": 2.8860232830047607, "learning_rate": 7.366981778164084e-05, "loss": 1.1198, "step": 6636 }, { "epoch": 0.3628634888091577, "grad_norm": 2.8416192531585693, "learning_rate": 7.366201876782528e-05, "loss": 1.2657, "step": 6637 }, { "epoch": 0.3629181616265163, "grad_norm": 2.887739896774292, "learning_rate": 7.365421901210797e-05, "loss": 0.9292, "step": 6638 }, { "epoch": 0.36297283444387496, "grad_norm": 5.239643096923828, "learning_rate": 7.36464185147335e-05, "loss": 1.3969, "step": 6639 }, { "epoch": 0.36302750726123356, "grad_norm": 3.282957077026367, "learning_rate": 7.363861727594641e-05, "loss": 1.2267, "step": 6640 }, { "epoch": 0.36308218007859216, "grad_norm": 2.5663981437683105, "learning_rate": 7.363081529599131e-05, "loss": 1.1381, "step": 6641 }, { "epoch": 0.36313685289595077, "grad_norm": 2.746608018875122, "learning_rate": 7.362301257511281e-05, "loss": 0.9064, "step": 6642 }, { "epoch": 0.3631915257133094, "grad_norm": 2.772047281265259, "learning_rate": 7.361520911355562e-05, "loss": 0.7721, "step": 6643 }, { "epoch": 0.36324619853066803, "grad_norm": 2.621253252029419, "learning_rate": 7.360740491156434e-05, "loss": 0.8485, "step": 6644 }, { "epoch": 0.36330087134802663, "grad_norm": 3.0210328102111816, "learning_rate": 7.359959996938369e-05, "loss": 1.2167, "step": 6645 }, { "epoch": 0.3633555441653853, "grad_norm": 2.552762746810913, "learning_rate": 7.35917942872584e-05, "loss": 0.99, "step": 6646 }, { "epoch": 0.3634102169827439, "grad_norm": 2.5591936111450195, "learning_rate": 7.358398786543318e-05, "loss": 1.066, "step": 6647 }, { "epoch": 0.3634648898001025, "grad_norm": 2.913602352142334, "learning_rate": 7.357618070415281e-05, "loss": 1.0016, "step": 6648 }, { "epoch": 0.36351956261746116, "grad_norm": 2.4748880863189697, "learning_rate": 7.356837280366211e-05, "loss": 0.9979, "step": 6649 }, { "epoch": 0.36357423543481976, "grad_norm": 2.5195295810699463, "learning_rate": 7.356056416420584e-05, "loss": 1.0645, "step": 6650 }, { "epoch": 0.36362890825217836, "grad_norm": 2.8725926876068115, "learning_rate": 7.355275478602885e-05, "loss": 1.1272, "step": 6651 }, { "epoch": 0.36368358106953697, "grad_norm": 2.2519187927246094, "learning_rate": 7.354494466937598e-05, "loss": 0.8497, "step": 6652 }, { "epoch": 0.3637382538868956, "grad_norm": 2.0514514446258545, "learning_rate": 7.353713381449215e-05, "loss": 0.9414, "step": 6653 }, { "epoch": 0.3637929267042542, "grad_norm": 2.555251121520996, "learning_rate": 7.352932222162223e-05, "loss": 1.1497, "step": 6654 }, { "epoch": 0.36384759952161283, "grad_norm": 2.517986536026001, "learning_rate": 7.352150989101116e-05, "loss": 1.209, "step": 6655 }, { "epoch": 0.3639022723389715, "grad_norm": 2.596930742263794, "learning_rate": 7.351369682290388e-05, "loss": 1.2488, "step": 6656 }, { "epoch": 0.3639569451563301, "grad_norm": 2.230388641357422, "learning_rate": 7.350588301754535e-05, "loss": 1.249, "step": 6657 }, { "epoch": 0.3640116179736887, "grad_norm": 2.8194563388824463, "learning_rate": 7.34980684751806e-05, "loss": 1.281, "step": 6658 }, { "epoch": 0.36406629079104735, "grad_norm": 3.1736249923706055, "learning_rate": 7.349025319605462e-05, "loss": 1.1519, "step": 6659 }, { "epoch": 0.36412096360840596, "grad_norm": 2.5902814865112305, "learning_rate": 7.348243718041246e-05, "loss": 1.181, "step": 6660 }, { "epoch": 0.36417563642576456, "grad_norm": 2.4093849658966064, "learning_rate": 7.347462042849918e-05, "loss": 0.87, "step": 6661 }, { "epoch": 0.36423030924312316, "grad_norm": 2.317909002304077, "learning_rate": 7.346680294055987e-05, "loss": 0.8866, "step": 6662 }, { "epoch": 0.3642849820604818, "grad_norm": 3.232320785522461, "learning_rate": 7.345898471683965e-05, "loss": 1.1348, "step": 6663 }, { "epoch": 0.3643396548778404, "grad_norm": 2.926481246948242, "learning_rate": 7.345116575758366e-05, "loss": 1.0978, "step": 6664 }, { "epoch": 0.364394327695199, "grad_norm": 2.1005570888519287, "learning_rate": 7.344334606303701e-05, "loss": 1.064, "step": 6665 }, { "epoch": 0.3644490005125577, "grad_norm": 2.2193498611450195, "learning_rate": 7.343552563344492e-05, "loss": 1.1515, "step": 6666 }, { "epoch": 0.3645036733299163, "grad_norm": 2.1982572078704834, "learning_rate": 7.342770446905259e-05, "loss": 1.2426, "step": 6667 }, { "epoch": 0.3645583461472749, "grad_norm": 2.638385057449341, "learning_rate": 7.341988257010524e-05, "loss": 1.3288, "step": 6668 }, { "epoch": 0.3646130189646335, "grad_norm": 2.5646588802337646, "learning_rate": 7.341205993684812e-05, "loss": 1.1363, "step": 6669 }, { "epoch": 0.36466769178199215, "grad_norm": 2.8586983680725098, "learning_rate": 7.340423656952649e-05, "loss": 1.0563, "step": 6670 }, { "epoch": 0.36472236459935076, "grad_norm": 3.321868896484375, "learning_rate": 7.339641246838566e-05, "loss": 1.2276, "step": 6671 }, { "epoch": 0.36477703741670936, "grad_norm": 2.1764049530029297, "learning_rate": 7.338858763367094e-05, "loss": 1.0309, "step": 6672 }, { "epoch": 0.364831710234068, "grad_norm": 2.918515682220459, "learning_rate": 7.338076206562769e-05, "loss": 1.2229, "step": 6673 }, { "epoch": 0.3648863830514266, "grad_norm": 2.8569693565368652, "learning_rate": 7.337293576450123e-05, "loss": 1.1724, "step": 6674 }, { "epoch": 0.3649410558687852, "grad_norm": 2.439283847808838, "learning_rate": 7.3365108730537e-05, "loss": 1.1645, "step": 6675 }, { "epoch": 0.3649957286861439, "grad_norm": 3.0261659622192383, "learning_rate": 7.335728096398036e-05, "loss": 1.0777, "step": 6676 }, { "epoch": 0.3650504015035025, "grad_norm": 2.5204787254333496, "learning_rate": 7.334945246507679e-05, "loss": 1.1653, "step": 6677 }, { "epoch": 0.3651050743208611, "grad_norm": 2.8449606895446777, "learning_rate": 7.334162323407169e-05, "loss": 1.2712, "step": 6678 }, { "epoch": 0.3651597471382197, "grad_norm": 2.544576406478882, "learning_rate": 7.33337932712106e-05, "loss": 1.0852, "step": 6679 }, { "epoch": 0.36521441995557835, "grad_norm": 2.239215850830078, "learning_rate": 7.3325962576739e-05, "loss": 1.0617, "step": 6680 }, { "epoch": 0.36526909277293695, "grad_norm": 2.2181344032287598, "learning_rate": 7.331813115090239e-05, "loss": 1.1425, "step": 6681 }, { "epoch": 0.36532376559029556, "grad_norm": 2.7783565521240234, "learning_rate": 7.331029899394633e-05, "loss": 1.2078, "step": 6682 }, { "epoch": 0.3653784384076542, "grad_norm": 2.098259210586548, "learning_rate": 7.33024661061164e-05, "loss": 1.0373, "step": 6683 }, { "epoch": 0.3654331112250128, "grad_norm": 2.0903573036193848, "learning_rate": 7.329463248765817e-05, "loss": 0.9191, "step": 6684 }, { "epoch": 0.3654877840423714, "grad_norm": 2.321406841278076, "learning_rate": 7.32867981388173e-05, "loss": 1.1308, "step": 6685 }, { "epoch": 0.3655424568597301, "grad_norm": 2.1442832946777344, "learning_rate": 7.32789630598394e-05, "loss": 1.0231, "step": 6686 }, { "epoch": 0.3655971296770887, "grad_norm": 3.103055000305176, "learning_rate": 7.327112725097012e-05, "loss": 0.9618, "step": 6687 }, { "epoch": 0.3656518024944473, "grad_norm": 2.3463828563690186, "learning_rate": 7.326329071245517e-05, "loss": 1.1328, "step": 6688 }, { "epoch": 0.3657064753118059, "grad_norm": 2.65324330329895, "learning_rate": 7.325545344454026e-05, "loss": 1.1602, "step": 6689 }, { "epoch": 0.36576114812916455, "grad_norm": 3.5304198265075684, "learning_rate": 7.32476154474711e-05, "loss": 1.316, "step": 6690 }, { "epoch": 0.36581582094652315, "grad_norm": 2.882190227508545, "learning_rate": 7.323977672149343e-05, "loss": 1.0973, "step": 6691 }, { "epoch": 0.36587049376388175, "grad_norm": 3.310725212097168, "learning_rate": 7.323193726685308e-05, "loss": 1.0449, "step": 6692 }, { "epoch": 0.3659251665812404, "grad_norm": 2.2431626319885254, "learning_rate": 7.32240970837958e-05, "loss": 0.9768, "step": 6693 }, { "epoch": 0.365979839398599, "grad_norm": 2.323638677597046, "learning_rate": 7.321625617256744e-05, "loss": 0.9646, "step": 6694 }, { "epoch": 0.3660345122159576, "grad_norm": 2.6751999855041504, "learning_rate": 7.320841453341383e-05, "loss": 1.0345, "step": 6695 }, { "epoch": 0.3660891850333162, "grad_norm": 2.9415745735168457, "learning_rate": 7.320057216658083e-05, "loss": 1.2167, "step": 6696 }, { "epoch": 0.3661438578506749, "grad_norm": 2.5154995918273926, "learning_rate": 7.319272907231436e-05, "loss": 0.9851, "step": 6697 }, { "epoch": 0.3661985306680335, "grad_norm": 2.0993494987487793, "learning_rate": 7.318488525086031e-05, "loss": 1.0443, "step": 6698 }, { "epoch": 0.3662532034853921, "grad_norm": 2.499478578567505, "learning_rate": 7.31770407024646e-05, "loss": 1.0679, "step": 6699 }, { "epoch": 0.36630787630275075, "grad_norm": 3.2795205116271973, "learning_rate": 7.316919542737324e-05, "loss": 1.2698, "step": 6700 }, { "epoch": 0.36636254912010935, "grad_norm": 2.356483221054077, "learning_rate": 7.316134942583218e-05, "loss": 1.0928, "step": 6701 }, { "epoch": 0.36641722193746795, "grad_norm": 1.985593557357788, "learning_rate": 7.315350269808743e-05, "loss": 0.8892, "step": 6702 }, { "epoch": 0.3664718947548266, "grad_norm": 2.171670436859131, "learning_rate": 7.3145655244385e-05, "loss": 1.1037, "step": 6703 }, { "epoch": 0.3665265675721852, "grad_norm": 2.1079249382019043, "learning_rate": 7.313780706497097e-05, "loss": 0.7978, "step": 6704 }, { "epoch": 0.3665812403895438, "grad_norm": 2.2980589866638184, "learning_rate": 7.312995816009139e-05, "loss": 0.9409, "step": 6705 }, { "epoch": 0.3666359132069024, "grad_norm": 2.4685168266296387, "learning_rate": 7.312210852999235e-05, "loss": 1.1453, "step": 6706 }, { "epoch": 0.3666905860242611, "grad_norm": 2.97578763961792, "learning_rate": 7.311425817491999e-05, "loss": 1.036, "step": 6707 }, { "epoch": 0.3667452588416197, "grad_norm": 2.132676601409912, "learning_rate": 7.310640709512045e-05, "loss": 1.1419, "step": 6708 }, { "epoch": 0.3667999316589783, "grad_norm": 2.482856512069702, "learning_rate": 7.309855529083986e-05, "loss": 1.2281, "step": 6709 }, { "epoch": 0.36685460447633694, "grad_norm": 2.836155414581299, "learning_rate": 7.309070276232446e-05, "loss": 0.9719, "step": 6710 }, { "epoch": 0.36690927729369555, "grad_norm": 2.4637439250946045, "learning_rate": 7.308284950982042e-05, "loss": 1.1577, "step": 6711 }, { "epoch": 0.36696395011105415, "grad_norm": 3.077817440032959, "learning_rate": 7.307499553357398e-05, "loss": 1.0518, "step": 6712 }, { "epoch": 0.36701862292841275, "grad_norm": 2.5651066303253174, "learning_rate": 7.30671408338314e-05, "loss": 1.1824, "step": 6713 }, { "epoch": 0.3670732957457714, "grad_norm": 2.5601556301116943, "learning_rate": 7.305928541083896e-05, "loss": 1.1054, "step": 6714 }, { "epoch": 0.36712796856313, "grad_norm": 2.2599470615386963, "learning_rate": 7.305142926484294e-05, "loss": 0.8915, "step": 6715 }, { "epoch": 0.3671826413804886, "grad_norm": 3.238893508911133, "learning_rate": 7.304357239608969e-05, "loss": 1.088, "step": 6716 }, { "epoch": 0.3672373141978473, "grad_norm": 2.422395706176758, "learning_rate": 7.303571480482554e-05, "loss": 0.7949, "step": 6717 }, { "epoch": 0.3672919870152059, "grad_norm": 2.385075092315674, "learning_rate": 7.302785649129685e-05, "loss": 1.1754, "step": 6718 }, { "epoch": 0.3673466598325645, "grad_norm": 2.084386110305786, "learning_rate": 7.301999745575004e-05, "loss": 1.0748, "step": 6719 }, { "epoch": 0.36740133264992314, "grad_norm": 2.855048656463623, "learning_rate": 7.301213769843147e-05, "loss": 1.2561, "step": 6720 }, { "epoch": 0.36745600546728174, "grad_norm": 2.2474119663238525, "learning_rate": 7.300427721958765e-05, "loss": 0.9717, "step": 6721 }, { "epoch": 0.36751067828464035, "grad_norm": 2.8762705326080322, "learning_rate": 7.299641601946496e-05, "loss": 1.2167, "step": 6722 }, { "epoch": 0.36756535110199895, "grad_norm": 3.2839250564575195, "learning_rate": 7.298855409830995e-05, "loss": 1.3056, "step": 6723 }, { "epoch": 0.3676200239193576, "grad_norm": 2.215752124786377, "learning_rate": 7.298069145636907e-05, "loss": 1.0256, "step": 6724 }, { "epoch": 0.3676746967367162, "grad_norm": 2.5279510021209717, "learning_rate": 7.297282809388888e-05, "loss": 0.9335, "step": 6725 }, { "epoch": 0.3677293695540748, "grad_norm": 2.552110195159912, "learning_rate": 7.296496401111592e-05, "loss": 1.1904, "step": 6726 }, { "epoch": 0.3677840423714335, "grad_norm": 2.701476573944092, "learning_rate": 7.295709920829676e-05, "loss": 1.0783, "step": 6727 }, { "epoch": 0.3678387151887921, "grad_norm": 2.1124184131622314, "learning_rate": 7.294923368567798e-05, "loss": 1.0385, "step": 6728 }, { "epoch": 0.3678933880061507, "grad_norm": 3.3980770111083984, "learning_rate": 7.294136744350621e-05, "loss": 1.0646, "step": 6729 }, { "epoch": 0.36794806082350934, "grad_norm": 4.317195415496826, "learning_rate": 7.29335004820281e-05, "loss": 1.3149, "step": 6730 }, { "epoch": 0.36800273364086794, "grad_norm": 2.40771746635437, "learning_rate": 7.292563280149028e-05, "loss": 1.3251, "step": 6731 }, { "epoch": 0.36805740645822654, "grad_norm": 2.412533760070801, "learning_rate": 7.291776440213948e-05, "loss": 1.1118, "step": 6732 }, { "epoch": 0.36811207927558515, "grad_norm": 3.1851885318756104, "learning_rate": 7.290989528422236e-05, "loss": 1.2483, "step": 6733 }, { "epoch": 0.3681667520929438, "grad_norm": 2.041167736053467, "learning_rate": 7.290202544798569e-05, "loss": 1.0559, "step": 6734 }, { "epoch": 0.3682214249103024, "grad_norm": 2.947535514831543, "learning_rate": 7.289415489367618e-05, "loss": 1.0803, "step": 6735 }, { "epoch": 0.368276097727661, "grad_norm": 3.075840950012207, "learning_rate": 7.288628362154063e-05, "loss": 0.9684, "step": 6736 }, { "epoch": 0.36833077054501967, "grad_norm": 2.9473443031311035, "learning_rate": 7.287841163182585e-05, "loss": 0.9722, "step": 6737 }, { "epoch": 0.3683854433623783, "grad_norm": 2.430302143096924, "learning_rate": 7.287053892477864e-05, "loss": 1.0311, "step": 6738 }, { "epoch": 0.3684401161797369, "grad_norm": 4.060256004333496, "learning_rate": 7.286266550064582e-05, "loss": 1.1084, "step": 6739 }, { "epoch": 0.3684947889970955, "grad_norm": 2.6754236221313477, "learning_rate": 7.285479135967429e-05, "loss": 1.0377, "step": 6740 }, { "epoch": 0.36854946181445414, "grad_norm": 2.389129877090454, "learning_rate": 7.284691650211093e-05, "loss": 0.9704, "step": 6741 }, { "epoch": 0.36860413463181274, "grad_norm": 3.2248775959014893, "learning_rate": 7.283904092820264e-05, "loss": 0.936, "step": 6742 }, { "epoch": 0.36865880744917134, "grad_norm": 2.2135188579559326, "learning_rate": 7.283116463819637e-05, "loss": 0.9498, "step": 6743 }, { "epoch": 0.36871348026653, "grad_norm": 2.7333364486694336, "learning_rate": 7.282328763233904e-05, "loss": 1.0178, "step": 6744 }, { "epoch": 0.3687681530838886, "grad_norm": 2.3463850021362305, "learning_rate": 7.281540991087765e-05, "loss": 0.8702, "step": 6745 }, { "epoch": 0.3688228259012472, "grad_norm": 2.0822699069976807, "learning_rate": 7.280753147405922e-05, "loss": 1.0463, "step": 6746 }, { "epoch": 0.36887749871860587, "grad_norm": 2.4675133228302, "learning_rate": 7.279965232213071e-05, "loss": 1.1908, "step": 6747 }, { "epoch": 0.36893217153596447, "grad_norm": 2.7171318531036377, "learning_rate": 7.279177245533922e-05, "loss": 1.1979, "step": 6748 }, { "epoch": 0.3689868443533231, "grad_norm": 2.5178816318511963, "learning_rate": 7.27838918739318e-05, "loss": 1.064, "step": 6749 }, { "epoch": 0.3690415171706817, "grad_norm": 2.8618438243865967, "learning_rate": 7.277601057815553e-05, "loss": 1.103, "step": 6750 }, { "epoch": 0.36909618998804034, "grad_norm": 3.1998276710510254, "learning_rate": 7.276812856825753e-05, "loss": 1.1888, "step": 6751 }, { "epoch": 0.36915086280539894, "grad_norm": 2.1714296340942383, "learning_rate": 7.276024584448493e-05, "loss": 0.9714, "step": 6752 }, { "epoch": 0.36920553562275754, "grad_norm": 3.45108699798584, "learning_rate": 7.275236240708489e-05, "loss": 1.0293, "step": 6753 }, { "epoch": 0.3692602084401162, "grad_norm": 2.9779958724975586, "learning_rate": 7.274447825630457e-05, "loss": 1.1293, "step": 6754 }, { "epoch": 0.3693148812574748, "grad_norm": 2.3672239780426025, "learning_rate": 7.273659339239119e-05, "loss": 1.1019, "step": 6755 }, { "epoch": 0.3693695540748334, "grad_norm": 3.2597694396972656, "learning_rate": 7.272870781559199e-05, "loss": 1.1176, "step": 6756 }, { "epoch": 0.36942422689219206, "grad_norm": 2.3545303344726562, "learning_rate": 7.272082152615416e-05, "loss": 0.8953, "step": 6757 }, { "epoch": 0.36947889970955067, "grad_norm": 2.917766809463501, "learning_rate": 7.271293452432502e-05, "loss": 1.1328, "step": 6758 }, { "epoch": 0.36953357252690927, "grad_norm": 2.806825876235962, "learning_rate": 7.270504681035183e-05, "loss": 1.0851, "step": 6759 }, { "epoch": 0.3695882453442679, "grad_norm": 2.416905403137207, "learning_rate": 7.269715838448192e-05, "loss": 0.9352, "step": 6760 }, { "epoch": 0.36964291816162653, "grad_norm": 2.6148762702941895, "learning_rate": 7.268926924696262e-05, "loss": 1.2829, "step": 6761 }, { "epoch": 0.36969759097898514, "grad_norm": 2.5102813243865967, "learning_rate": 7.26813793980413e-05, "loss": 1.0489, "step": 6762 }, { "epoch": 0.36975226379634374, "grad_norm": 2.341221332550049, "learning_rate": 7.267348883796529e-05, "loss": 1.1593, "step": 6763 }, { "epoch": 0.3698069366137024, "grad_norm": 3.7239158153533936, "learning_rate": 7.266559756698206e-05, "loss": 1.1193, "step": 6764 }, { "epoch": 0.369861609431061, "grad_norm": 2.7902843952178955, "learning_rate": 7.265770558533898e-05, "loss": 0.9805, "step": 6765 }, { "epoch": 0.3699162822484196, "grad_norm": 2.447948694229126, "learning_rate": 7.264981289328352e-05, "loss": 1.0707, "step": 6766 }, { "epoch": 0.3699709550657782, "grad_norm": 2.2337732315063477, "learning_rate": 7.264191949106313e-05, "loss": 1.0024, "step": 6767 }, { "epoch": 0.37002562788313687, "grad_norm": 2.395456552505493, "learning_rate": 7.263402537892534e-05, "loss": 1.069, "step": 6768 }, { "epoch": 0.37008030070049547, "grad_norm": 2.700162172317505, "learning_rate": 7.262613055711764e-05, "loss": 1.0354, "step": 6769 }, { "epoch": 0.37013497351785407, "grad_norm": 3.1416563987731934, "learning_rate": 7.261823502588753e-05, "loss": 1.041, "step": 6770 }, { "epoch": 0.37018964633521273, "grad_norm": 2.755506992340088, "learning_rate": 7.261033878548263e-05, "loss": 1.3966, "step": 6771 }, { "epoch": 0.37024431915257133, "grad_norm": 2.349987745285034, "learning_rate": 7.260244183615046e-05, "loss": 1.144, "step": 6772 }, { "epoch": 0.37029899196992994, "grad_norm": 3.2596678733825684, "learning_rate": 7.259454417813868e-05, "loss": 1.1433, "step": 6773 }, { "epoch": 0.3703536647872886, "grad_norm": 2.564451217651367, "learning_rate": 7.258664581169488e-05, "loss": 1.1582, "step": 6774 }, { "epoch": 0.3704083376046472, "grad_norm": 2.4133243560791016, "learning_rate": 7.257874673706671e-05, "loss": 0.8691, "step": 6775 }, { "epoch": 0.3704630104220058, "grad_norm": 2.830637216567993, "learning_rate": 7.257084695450183e-05, "loss": 1.2818, "step": 6776 }, { "epoch": 0.3705176832393644, "grad_norm": 3.4860405921936035, "learning_rate": 7.256294646424796e-05, "loss": 1.0939, "step": 6777 }, { "epoch": 0.37057235605672306, "grad_norm": 2.8145980834960938, "learning_rate": 7.25550452665528e-05, "loss": 1.1394, "step": 6778 }, { "epoch": 0.37062702887408167, "grad_norm": 2.3880131244659424, "learning_rate": 7.254714336166406e-05, "loss": 0.8708, "step": 6779 }, { "epoch": 0.37068170169144027, "grad_norm": 3.0285520553588867, "learning_rate": 7.25392407498295e-05, "loss": 0.9373, "step": 6780 }, { "epoch": 0.3707363745087989, "grad_norm": 2.3396949768066406, "learning_rate": 7.253133743129695e-05, "loss": 0.9715, "step": 6781 }, { "epoch": 0.37079104732615753, "grad_norm": 2.599379539489746, "learning_rate": 7.252343340631417e-05, "loss": 0.9215, "step": 6782 }, { "epoch": 0.37084572014351613, "grad_norm": 2.3481333255767822, "learning_rate": 7.251552867512899e-05, "loss": 1.173, "step": 6783 }, { "epoch": 0.3709003929608748, "grad_norm": 2.579578399658203, "learning_rate": 7.250762323798925e-05, "loss": 1.0919, "step": 6784 }, { "epoch": 0.3709550657782334, "grad_norm": 2.2007696628570557, "learning_rate": 7.249971709514284e-05, "loss": 0.8501, "step": 6785 }, { "epoch": 0.371009738595592, "grad_norm": 2.3473830223083496, "learning_rate": 7.249181024683761e-05, "loss": 1.1232, "step": 6786 }, { "epoch": 0.3710644114129506, "grad_norm": 2.6029531955718994, "learning_rate": 7.248390269332152e-05, "loss": 1.2968, "step": 6787 }, { "epoch": 0.37111908423030926, "grad_norm": 2.2013537883758545, "learning_rate": 7.247599443484248e-05, "loss": 0.942, "step": 6788 }, { "epoch": 0.37117375704766786, "grad_norm": 2.4715256690979004, "learning_rate": 7.246808547164843e-05, "loss": 1.2839, "step": 6789 }, { "epoch": 0.37122842986502647, "grad_norm": 3.514634370803833, "learning_rate": 7.24601758039874e-05, "loss": 1.019, "step": 6790 }, { "epoch": 0.3712831026823851, "grad_norm": 2.346130847930908, "learning_rate": 7.245226543210734e-05, "loss": 1.179, "step": 6791 }, { "epoch": 0.3713377754997437, "grad_norm": 3.451599359512329, "learning_rate": 7.244435435625629e-05, "loss": 1.0875, "step": 6792 }, { "epoch": 0.37139244831710233, "grad_norm": 2.7180750370025635, "learning_rate": 7.243644257668229e-05, "loss": 1.2311, "step": 6793 }, { "epoch": 0.37144712113446093, "grad_norm": 2.374612808227539, "learning_rate": 7.242853009363342e-05, "loss": 0.889, "step": 6794 }, { "epoch": 0.3715017939518196, "grad_norm": 2.4118616580963135, "learning_rate": 7.242061690735775e-05, "loss": 0.945, "step": 6795 }, { "epoch": 0.3715564667691782, "grad_norm": 2.607306957244873, "learning_rate": 7.24127030181034e-05, "loss": 1.1387, "step": 6796 }, { "epoch": 0.3716111395865368, "grad_norm": 2.2420973777770996, "learning_rate": 7.240478842611853e-05, "loss": 1.0383, "step": 6797 }, { "epoch": 0.37166581240389546, "grad_norm": 2.784369945526123, "learning_rate": 7.239687313165127e-05, "loss": 1.1622, "step": 6798 }, { "epoch": 0.37172048522125406, "grad_norm": 3.1756296157836914, "learning_rate": 7.238895713494977e-05, "loss": 1.303, "step": 6799 }, { "epoch": 0.37177515803861266, "grad_norm": 2.5948023796081543, "learning_rate": 7.238104043626227e-05, "loss": 1.2195, "step": 6800 }, { "epoch": 0.3718298308559713, "grad_norm": 2.2903428077697754, "learning_rate": 7.237312303583699e-05, "loss": 0.9002, "step": 6801 }, { "epoch": 0.3718845036733299, "grad_norm": 2.372014284133911, "learning_rate": 7.236520493392214e-05, "loss": 1.0572, "step": 6802 }, { "epoch": 0.37193917649068853, "grad_norm": 2.8462018966674805, "learning_rate": 7.235728613076602e-05, "loss": 1.3491, "step": 6803 }, { "epoch": 0.37199384930804713, "grad_norm": 2.6049532890319824, "learning_rate": 7.234936662661689e-05, "loss": 1.0014, "step": 6804 }, { "epoch": 0.3720485221254058, "grad_norm": 3.132877826690674, "learning_rate": 7.234144642172308e-05, "loss": 0.9135, "step": 6805 }, { "epoch": 0.3721031949427644, "grad_norm": 2.4191880226135254, "learning_rate": 7.233352551633291e-05, "loss": 1.1581, "step": 6806 }, { "epoch": 0.372157867760123, "grad_norm": 2.2783992290496826, "learning_rate": 7.232560391069474e-05, "loss": 1.1438, "step": 6807 }, { "epoch": 0.37221254057748165, "grad_norm": 2.3471972942352295, "learning_rate": 7.231768160505695e-05, "loss": 0.8974, "step": 6808 }, { "epoch": 0.37226721339484026, "grad_norm": 2.7783732414245605, "learning_rate": 7.23097585996679e-05, "loss": 0.8711, "step": 6809 }, { "epoch": 0.37232188621219886, "grad_norm": 2.3498153686523438, "learning_rate": 7.230183489477606e-05, "loss": 1.179, "step": 6810 }, { "epoch": 0.3723765590295575, "grad_norm": 3.749047040939331, "learning_rate": 7.229391049062984e-05, "loss": 1.1215, "step": 6811 }, { "epoch": 0.3724312318469161, "grad_norm": 2.693086862564087, "learning_rate": 7.22859853874777e-05, "loss": 0.9867, "step": 6812 }, { "epoch": 0.3724859046642747, "grad_norm": 2.947129487991333, "learning_rate": 7.227805958556816e-05, "loss": 1.0589, "step": 6813 }, { "epoch": 0.37254057748163333, "grad_norm": 2.4265024662017822, "learning_rate": 7.227013308514967e-05, "loss": 1.0782, "step": 6814 }, { "epoch": 0.372595250298992, "grad_norm": 2.744906187057495, "learning_rate": 7.226220588647082e-05, "loss": 1.1049, "step": 6815 }, { "epoch": 0.3726499231163506, "grad_norm": 2.9853811264038086, "learning_rate": 7.225427798978011e-05, "loss": 1.0106, "step": 6816 }, { "epoch": 0.3727045959337092, "grad_norm": 3.8300721645355225, "learning_rate": 7.224634939532615e-05, "loss": 1.0093, "step": 6817 }, { "epoch": 0.37275926875106785, "grad_norm": 2.281594753265381, "learning_rate": 7.22384201033575e-05, "loss": 0.9876, "step": 6818 }, { "epoch": 0.37281394156842645, "grad_norm": 2.2822844982147217, "learning_rate": 7.22304901141228e-05, "loss": 1.0548, "step": 6819 }, { "epoch": 0.37286861438578506, "grad_norm": 2.6668310165405273, "learning_rate": 7.222255942787067e-05, "loss": 1.143, "step": 6820 }, { "epoch": 0.37292328720314366, "grad_norm": 2.308687210083008, "learning_rate": 7.221462804484979e-05, "loss": 1.0048, "step": 6821 }, { "epoch": 0.3729779600205023, "grad_norm": 2.0523972511291504, "learning_rate": 7.220669596530884e-05, "loss": 0.9638, "step": 6822 }, { "epoch": 0.3730326328378609, "grad_norm": 2.499896287918091, "learning_rate": 7.219876318949649e-05, "loss": 1.1184, "step": 6823 }, { "epoch": 0.3730873056552195, "grad_norm": 2.4104599952697754, "learning_rate": 7.219082971766152e-05, "loss": 1.0769, "step": 6824 }, { "epoch": 0.3731419784725782, "grad_norm": 2.2412335872650146, "learning_rate": 7.218289555005262e-05, "loss": 1.2346, "step": 6825 }, { "epoch": 0.3731966512899368, "grad_norm": 2.1712090969085693, "learning_rate": 7.21749606869186e-05, "loss": 1.0711, "step": 6826 }, { "epoch": 0.3732513241072954, "grad_norm": 2.8156445026397705, "learning_rate": 7.216702512850823e-05, "loss": 0.9739, "step": 6827 }, { "epoch": 0.37330599692465405, "grad_norm": 5.1405558586120605, "learning_rate": 7.215908887507032e-05, "loss": 1.0227, "step": 6828 }, { "epoch": 0.37336066974201265, "grad_norm": 2.623852252960205, "learning_rate": 7.215115192685373e-05, "loss": 1.1775, "step": 6829 }, { "epoch": 0.37341534255937125, "grad_norm": 2.2149770259857178, "learning_rate": 7.214321428410731e-05, "loss": 0.9386, "step": 6830 }, { "epoch": 0.37347001537672986, "grad_norm": 2.7387502193450928, "learning_rate": 7.213527594707991e-05, "loss": 1.0897, "step": 6831 }, { "epoch": 0.3735246881940885, "grad_norm": 3.008357286453247, "learning_rate": 7.212733691602046e-05, "loss": 1.1865, "step": 6832 }, { "epoch": 0.3735793610114471, "grad_norm": 2.6150619983673096, "learning_rate": 7.211939719117783e-05, "loss": 1.1932, "step": 6833 }, { "epoch": 0.3736340338288057, "grad_norm": 2.425408363342285, "learning_rate": 7.211145677280102e-05, "loss": 0.7458, "step": 6834 }, { "epoch": 0.3736887066461644, "grad_norm": 2.799576997756958, "learning_rate": 7.2103515661139e-05, "loss": 0.8206, "step": 6835 }, { "epoch": 0.373743379463523, "grad_norm": 2.7218570709228516, "learning_rate": 7.209557385644071e-05, "loss": 1.0529, "step": 6836 }, { "epoch": 0.3737980522808816, "grad_norm": 2.615671157836914, "learning_rate": 7.208763135895519e-05, "loss": 1.1057, "step": 6837 }, { "epoch": 0.37385272509824025, "grad_norm": 2.4200551509857178, "learning_rate": 7.207968816893145e-05, "loss": 1.0391, "step": 6838 }, { "epoch": 0.37390739791559885, "grad_norm": 2.25901460647583, "learning_rate": 7.207174428661855e-05, "loss": 1.0489, "step": 6839 }, { "epoch": 0.37396207073295745, "grad_norm": 3.021305799484253, "learning_rate": 7.206379971226558e-05, "loss": 1.1484, "step": 6840 }, { "epoch": 0.37401674355031606, "grad_norm": 4.9125189781188965, "learning_rate": 7.205585444612162e-05, "loss": 1.1426, "step": 6841 }, { "epoch": 0.3740714163676747, "grad_norm": 2.42560076713562, "learning_rate": 7.204790848843578e-05, "loss": 1.0525, "step": 6842 }, { "epoch": 0.3741260891850333, "grad_norm": 2.829085350036621, "learning_rate": 7.20399618394572e-05, "loss": 0.9418, "step": 6843 }, { "epoch": 0.3741807620023919, "grad_norm": 2.3315718173980713, "learning_rate": 7.203201449943505e-05, "loss": 1.1703, "step": 6844 }, { "epoch": 0.3742354348197506, "grad_norm": 3.7574462890625, "learning_rate": 7.20240664686185e-05, "loss": 1.2293, "step": 6845 }, { "epoch": 0.3742901076371092, "grad_norm": 2.509514331817627, "learning_rate": 7.201611774725678e-05, "loss": 1.2379, "step": 6846 }, { "epoch": 0.3743447804544678, "grad_norm": 4.769797325134277, "learning_rate": 7.20081683355991e-05, "loss": 0.9973, "step": 6847 }, { "epoch": 0.3743994532718264, "grad_norm": 2.5430948734283447, "learning_rate": 7.200021823389469e-05, "loss": 1.2614, "step": 6848 }, { "epoch": 0.37445412608918505, "grad_norm": 2.418975591659546, "learning_rate": 7.199226744239284e-05, "loss": 1.2682, "step": 6849 }, { "epoch": 0.37450879890654365, "grad_norm": 10.696521759033203, "learning_rate": 7.198431596134283e-05, "loss": 0.8751, "step": 6850 }, { "epoch": 0.37456347172390225, "grad_norm": 2.025184392929077, "learning_rate": 7.197636379099397e-05, "loss": 0.9285, "step": 6851 }, { "epoch": 0.3746181445412609, "grad_norm": 2.0961925983428955, "learning_rate": 7.19684109315956e-05, "loss": 1.1545, "step": 6852 }, { "epoch": 0.3746728173586195, "grad_norm": 3.2169036865234375, "learning_rate": 7.196045738339706e-05, "loss": 0.8326, "step": 6853 }, { "epoch": 0.3747274901759781, "grad_norm": 3.641700506210327, "learning_rate": 7.195250314664775e-05, "loss": 1.0428, "step": 6854 }, { "epoch": 0.3747821629933368, "grad_norm": 2.5698788166046143, "learning_rate": 7.194454822159707e-05, "loss": 0.9762, "step": 6855 }, { "epoch": 0.3748368358106954, "grad_norm": 3.1027581691741943, "learning_rate": 7.19365926084944e-05, "loss": 1.0904, "step": 6856 }, { "epoch": 0.374891508628054, "grad_norm": 2.225200653076172, "learning_rate": 7.192863630758921e-05, "loss": 1.022, "step": 6857 }, { "epoch": 0.3749461814454126, "grad_norm": 2.569528102874756, "learning_rate": 7.192067931913097e-05, "loss": 1.2039, "step": 6858 }, { "epoch": 0.37500085426277124, "grad_norm": 2.6980602741241455, "learning_rate": 7.191272164336915e-05, "loss": 0.8878, "step": 6859 }, { "epoch": 0.37505552708012985, "grad_norm": 2.697085380554199, "learning_rate": 7.190476328055327e-05, "loss": 1.0676, "step": 6860 }, { "epoch": 0.37511019989748845, "grad_norm": 1.8356549739837646, "learning_rate": 7.189680423093284e-05, "loss": 0.9462, "step": 6861 }, { "epoch": 0.3751648727148471, "grad_norm": 2.549203395843506, "learning_rate": 7.188884449475742e-05, "loss": 1.1027, "step": 6862 }, { "epoch": 0.3752195455322057, "grad_norm": 2.34474778175354, "learning_rate": 7.188088407227658e-05, "loss": 1.0983, "step": 6863 }, { "epoch": 0.3752742183495643, "grad_norm": 2.40751576423645, "learning_rate": 7.18729229637399e-05, "loss": 1.0654, "step": 6864 }, { "epoch": 0.3753288911669229, "grad_norm": 2.1844284534454346, "learning_rate": 7.186496116939702e-05, "loss": 1.0489, "step": 6865 }, { "epoch": 0.3753835639842816, "grad_norm": 2.4896373748779297, "learning_rate": 7.185699868949754e-05, "loss": 1.1618, "step": 6866 }, { "epoch": 0.3754382368016402, "grad_norm": 2.457216739654541, "learning_rate": 7.184903552429115e-05, "loss": 1.1589, "step": 6867 }, { "epoch": 0.3754929096189988, "grad_norm": 2.110621452331543, "learning_rate": 7.184107167402749e-05, "loss": 0.9667, "step": 6868 }, { "epoch": 0.37554758243635744, "grad_norm": 2.989896535873413, "learning_rate": 7.18331071389563e-05, "loss": 1.1412, "step": 6869 }, { "epoch": 0.37560225525371604, "grad_norm": 3.1872997283935547, "learning_rate": 7.182514191932728e-05, "loss": 1.1567, "step": 6870 }, { "epoch": 0.37565692807107465, "grad_norm": 2.9263155460357666, "learning_rate": 7.181717601539018e-05, "loss": 1.2409, "step": 6871 }, { "epoch": 0.3757116008884333, "grad_norm": 2.333104372024536, "learning_rate": 7.180920942739475e-05, "loss": 1.1985, "step": 6872 }, { "epoch": 0.3757662737057919, "grad_norm": 2.082221269607544, "learning_rate": 7.180124215559077e-05, "loss": 0.8863, "step": 6873 }, { "epoch": 0.3758209465231505, "grad_norm": 2.3542652130126953, "learning_rate": 7.179327420022808e-05, "loss": 0.9983, "step": 6874 }, { "epoch": 0.3758756193405091, "grad_norm": 2.8656833171844482, "learning_rate": 7.17853055615565e-05, "loss": 0.9123, "step": 6875 }, { "epoch": 0.3759302921578678, "grad_norm": 2.6439969539642334, "learning_rate": 7.177733623982586e-05, "loss": 1.0987, "step": 6876 }, { "epoch": 0.3759849649752264, "grad_norm": 2.8301799297332764, "learning_rate": 7.176936623528605e-05, "loss": 1.0846, "step": 6877 }, { "epoch": 0.376039637792585, "grad_norm": 2.5808298587799072, "learning_rate": 7.176139554818694e-05, "loss": 1.0627, "step": 6878 }, { "epoch": 0.37609431060994364, "grad_norm": 2.0251238346099854, "learning_rate": 7.175342417877846e-05, "loss": 0.802, "step": 6879 }, { "epoch": 0.37614898342730224, "grad_norm": 2.7486307621002197, "learning_rate": 7.174545212731052e-05, "loss": 1.1086, "step": 6880 }, { "epoch": 0.37620365624466084, "grad_norm": 2.981074094772339, "learning_rate": 7.173747939403312e-05, "loss": 1.1365, "step": 6881 }, { "epoch": 0.3762583290620195, "grad_norm": 2.050058603286743, "learning_rate": 7.172950597919624e-05, "loss": 1.097, "step": 6882 }, { "epoch": 0.3763130018793781, "grad_norm": 2.327247142791748, "learning_rate": 7.172153188304982e-05, "loss": 1.1281, "step": 6883 }, { "epoch": 0.3763676746967367, "grad_norm": 2.9173994064331055, "learning_rate": 7.171355710584393e-05, "loss": 1.2114, "step": 6884 }, { "epoch": 0.3764223475140953, "grad_norm": 2.7081034183502197, "learning_rate": 7.170558164782861e-05, "loss": 1.0102, "step": 6885 }, { "epoch": 0.37647702033145397, "grad_norm": 2.2235677242279053, "learning_rate": 7.169760550925389e-05, "loss": 1.098, "step": 6886 }, { "epoch": 0.3765316931488126, "grad_norm": 3.015233278274536, "learning_rate": 7.168962869036988e-05, "loss": 0.9256, "step": 6887 }, { "epoch": 0.3765863659661712, "grad_norm": 2.22127628326416, "learning_rate": 7.16816511914267e-05, "loss": 0.9045, "step": 6888 }, { "epoch": 0.37664103878352984, "grad_norm": 1.9654409885406494, "learning_rate": 7.167367301267444e-05, "loss": 0.8408, "step": 6889 }, { "epoch": 0.37669571160088844, "grad_norm": 2.4079792499542236, "learning_rate": 7.166569415436329e-05, "loss": 1.0946, "step": 6890 }, { "epoch": 0.37675038441824704, "grad_norm": 2.3216681480407715, "learning_rate": 7.165771461674339e-05, "loss": 1.1661, "step": 6891 }, { "epoch": 0.37680505723560564, "grad_norm": 3.166485071182251, "learning_rate": 7.164973440006494e-05, "loss": 0.9174, "step": 6892 }, { "epoch": 0.3768597300529643, "grad_norm": 1.9571791887283325, "learning_rate": 7.164175350457815e-05, "loss": 0.9245, "step": 6893 }, { "epoch": 0.3769144028703229, "grad_norm": 2.310251235961914, "learning_rate": 7.163377193053327e-05, "loss": 1.0934, "step": 6894 }, { "epoch": 0.3769690756876815, "grad_norm": 2.388339042663574, "learning_rate": 7.162578967818055e-05, "loss": 1.16, "step": 6895 }, { "epoch": 0.37702374850504017, "grad_norm": 2.633798599243164, "learning_rate": 7.161780674777023e-05, "loss": 1.3348, "step": 6896 }, { "epoch": 0.37707842132239877, "grad_norm": 3.3328449726104736, "learning_rate": 7.160982313955265e-05, "loss": 1.0436, "step": 6897 }, { "epoch": 0.3771330941397574, "grad_norm": 2.1072661876678467, "learning_rate": 7.160183885377811e-05, "loss": 0.9532, "step": 6898 }, { "epoch": 0.37718776695711603, "grad_norm": 4.8098578453063965, "learning_rate": 7.159385389069698e-05, "loss": 1.2441, "step": 6899 }, { "epoch": 0.37724243977447464, "grad_norm": 2.3907623291015625, "learning_rate": 7.158586825055957e-05, "loss": 0.89, "step": 6900 }, { "epoch": 0.37729711259183324, "grad_norm": 3.0524232387542725, "learning_rate": 7.157788193361632e-05, "loss": 1.0978, "step": 6901 }, { "epoch": 0.37735178540919184, "grad_norm": 2.28222393989563, "learning_rate": 7.156989494011758e-05, "loss": 1.0638, "step": 6902 }, { "epoch": 0.3774064582265505, "grad_norm": 1.975269079208374, "learning_rate": 7.15619072703138e-05, "loss": 1.0358, "step": 6903 }, { "epoch": 0.3774611310439091, "grad_norm": 2.155078887939453, "learning_rate": 7.155391892445543e-05, "loss": 1.0177, "step": 6904 }, { "epoch": 0.3775158038612677, "grad_norm": 3.0025832653045654, "learning_rate": 7.154592990279294e-05, "loss": 1.2671, "step": 6905 }, { "epoch": 0.37757047667862637, "grad_norm": 3.2125279903411865, "learning_rate": 7.153794020557681e-05, "loss": 1.1296, "step": 6906 }, { "epoch": 0.37762514949598497, "grad_norm": 2.745521306991577, "learning_rate": 7.152994983305754e-05, "loss": 0.9374, "step": 6907 }, { "epoch": 0.37767982231334357, "grad_norm": 3.1566500663757324, "learning_rate": 7.152195878548569e-05, "loss": 0.9755, "step": 6908 }, { "epoch": 0.37773449513070223, "grad_norm": 2.9222915172576904, "learning_rate": 7.151396706311179e-05, "loss": 1.089, "step": 6909 }, { "epoch": 0.37778916794806083, "grad_norm": 2.8538095951080322, "learning_rate": 7.150597466618641e-05, "loss": 1.1119, "step": 6910 }, { "epoch": 0.37784384076541944, "grad_norm": 2.1019604206085205, "learning_rate": 7.149798159496018e-05, "loss": 1.0176, "step": 6911 }, { "epoch": 0.37789851358277804, "grad_norm": 2.9960217475891113, "learning_rate": 7.148998784968365e-05, "loss": 1.0913, "step": 6912 }, { "epoch": 0.3779531864001367, "grad_norm": 2.280535936355591, "learning_rate": 7.148199343060751e-05, "loss": 0.9671, "step": 6913 }, { "epoch": 0.3780078592174953, "grad_norm": 2.945976495742798, "learning_rate": 7.147399833798242e-05, "loss": 1.1398, "step": 6914 }, { "epoch": 0.3780625320348539, "grad_norm": 3.1778244972229004, "learning_rate": 7.146600257205903e-05, "loss": 0.8524, "step": 6915 }, { "epoch": 0.37811720485221256, "grad_norm": 2.755237340927124, "learning_rate": 7.145800613308806e-05, "loss": 1.1595, "step": 6916 }, { "epoch": 0.37817187766957117, "grad_norm": 3.270336151123047, "learning_rate": 7.14500090213202e-05, "loss": 1.3202, "step": 6917 }, { "epoch": 0.37822655048692977, "grad_norm": 2.8694913387298584, "learning_rate": 7.144201123700625e-05, "loss": 0.869, "step": 6918 }, { "epoch": 0.37828122330428837, "grad_norm": 2.6953063011169434, "learning_rate": 7.143401278039692e-05, "loss": 1.2735, "step": 6919 }, { "epoch": 0.37833589612164703, "grad_norm": 2.851602792739868, "learning_rate": 7.142601365174303e-05, "loss": 1.1211, "step": 6920 }, { "epoch": 0.37839056893900563, "grad_norm": 2.116245985031128, "learning_rate": 7.141801385129537e-05, "loss": 0.8664, "step": 6921 }, { "epoch": 0.37844524175636424, "grad_norm": 2.2790400981903076, "learning_rate": 7.141001337930474e-05, "loss": 1.1156, "step": 6922 }, { "epoch": 0.3784999145737229, "grad_norm": 2.245364189147949, "learning_rate": 7.140201223602203e-05, "loss": 0.8113, "step": 6923 }, { "epoch": 0.3785545873910815, "grad_norm": 2.162778615951538, "learning_rate": 7.13940104216981e-05, "loss": 0.9152, "step": 6924 }, { "epoch": 0.3786092602084401, "grad_norm": 2.6899571418762207, "learning_rate": 7.138600793658383e-05, "loss": 1.0913, "step": 6925 }, { "epoch": 0.37866393302579876, "grad_norm": 3.151838541030884, "learning_rate": 7.137800478093015e-05, "loss": 1.0713, "step": 6926 }, { "epoch": 0.37871860584315736, "grad_norm": 2.46376895904541, "learning_rate": 7.137000095498795e-05, "loss": 0.9914, "step": 6927 }, { "epoch": 0.37877327866051597, "grad_norm": 2.6144492626190186, "learning_rate": 7.136199645900821e-05, "loss": 0.7814, "step": 6928 }, { "epoch": 0.37882795147787457, "grad_norm": 2.4157047271728516, "learning_rate": 7.135399129324193e-05, "loss": 1.1402, "step": 6929 }, { "epoch": 0.37888262429523323, "grad_norm": 2.1686782836914062, "learning_rate": 7.134598545794007e-05, "loss": 0.89, "step": 6930 }, { "epoch": 0.37893729711259183, "grad_norm": 2.526596784591675, "learning_rate": 7.133797895335364e-05, "loss": 1.0569, "step": 6931 }, { "epoch": 0.37899196992995043, "grad_norm": 2.6253409385681152, "learning_rate": 7.132997177973369e-05, "loss": 1.1578, "step": 6932 }, { "epoch": 0.3790466427473091, "grad_norm": 2.1768617630004883, "learning_rate": 7.132196393733129e-05, "loss": 0.9896, "step": 6933 }, { "epoch": 0.3791013155646677, "grad_norm": 2.6652281284332275, "learning_rate": 7.131395542639749e-05, "loss": 1.0563, "step": 6934 }, { "epoch": 0.3791559883820263, "grad_norm": 3.8223254680633545, "learning_rate": 7.130594624718343e-05, "loss": 1.0958, "step": 6935 }, { "epoch": 0.37921066119938496, "grad_norm": 1.9847592115402222, "learning_rate": 7.129793639994019e-05, "loss": 0.9504, "step": 6936 }, { "epoch": 0.37926533401674356, "grad_norm": 2.4721479415893555, "learning_rate": 7.128992588491893e-05, "loss": 1.0983, "step": 6937 }, { "epoch": 0.37932000683410216, "grad_norm": 3.2711362838745117, "learning_rate": 7.128191470237084e-05, "loss": 1.0327, "step": 6938 }, { "epoch": 0.37937467965146077, "grad_norm": 2.1494858264923096, "learning_rate": 7.127390285254704e-05, "loss": 1.1545, "step": 6939 }, { "epoch": 0.3794293524688194, "grad_norm": 2.2135801315307617, "learning_rate": 7.126589033569879e-05, "loss": 1.0731, "step": 6940 }, { "epoch": 0.37948402528617803, "grad_norm": 1.9617531299591064, "learning_rate": 7.125787715207729e-05, "loss": 0.9823, "step": 6941 }, { "epoch": 0.37953869810353663, "grad_norm": 3.186880350112915, "learning_rate": 7.12498633019338e-05, "loss": 1.1589, "step": 6942 }, { "epoch": 0.3795933709208953, "grad_norm": 2.375107526779175, "learning_rate": 7.124184878551959e-05, "loss": 1.0624, "step": 6943 }, { "epoch": 0.3796480437382539, "grad_norm": 3.72408127784729, "learning_rate": 7.12338336030859e-05, "loss": 1.0854, "step": 6944 }, { "epoch": 0.3797027165556125, "grad_norm": 2.129363536834717, "learning_rate": 7.122581775488411e-05, "loss": 1.2054, "step": 6945 }, { "epoch": 0.3797573893729711, "grad_norm": 2.5863218307495117, "learning_rate": 7.121780124116549e-05, "loss": 1.0509, "step": 6946 }, { "epoch": 0.37981206219032976, "grad_norm": 3.2639389038085938, "learning_rate": 7.120978406218143e-05, "loss": 1.2359, "step": 6947 }, { "epoch": 0.37986673500768836, "grad_norm": 2.171111822128296, "learning_rate": 7.120176621818331e-05, "loss": 0.8768, "step": 6948 }, { "epoch": 0.37992140782504696, "grad_norm": 2.694671392440796, "learning_rate": 7.119374770942247e-05, "loss": 1.2378, "step": 6949 }, { "epoch": 0.3799760806424056, "grad_norm": 2.241452693939209, "learning_rate": 7.118572853615037e-05, "loss": 1.1813, "step": 6950 }, { "epoch": 0.3800307534597642, "grad_norm": 2.244110107421875, "learning_rate": 7.117770869861841e-05, "loss": 0.9811, "step": 6951 }, { "epoch": 0.38008542627712283, "grad_norm": 6.320304870605469, "learning_rate": 7.116968819707808e-05, "loss": 0.9525, "step": 6952 }, { "epoch": 0.3801400990944815, "grad_norm": 2.7353641986846924, "learning_rate": 7.116166703178085e-05, "loss": 0.9305, "step": 6953 }, { "epoch": 0.3801947719118401, "grad_norm": 3.637094736099243, "learning_rate": 7.115364520297819e-05, "loss": 0.8207, "step": 6954 }, { "epoch": 0.3802494447291987, "grad_norm": 2.2807374000549316, "learning_rate": 7.114562271092163e-05, "loss": 0.819, "step": 6955 }, { "epoch": 0.3803041175465573, "grad_norm": 2.5112671852111816, "learning_rate": 7.113759955586271e-05, "loss": 1.085, "step": 6956 }, { "epoch": 0.38035879036391596, "grad_norm": 1.8894011974334717, "learning_rate": 7.1129575738053e-05, "loss": 0.8154, "step": 6957 }, { "epoch": 0.38041346318127456, "grad_norm": 1.9221670627593994, "learning_rate": 7.112155125774407e-05, "loss": 1.0272, "step": 6958 }, { "epoch": 0.38046813599863316, "grad_norm": 2.37998366355896, "learning_rate": 7.111352611518752e-05, "loss": 1.0008, "step": 6959 }, { "epoch": 0.3805228088159918, "grad_norm": 2.394014596939087, "learning_rate": 7.110550031063497e-05, "loss": 1.0363, "step": 6960 }, { "epoch": 0.3805774816333504, "grad_norm": 2.2581405639648438, "learning_rate": 7.109747384433805e-05, "loss": 1.0138, "step": 6961 }, { "epoch": 0.380632154450709, "grad_norm": 2.102031946182251, "learning_rate": 7.108944671654845e-05, "loss": 1.1097, "step": 6962 }, { "epoch": 0.3806868272680677, "grad_norm": 3.648655891418457, "learning_rate": 7.108141892751784e-05, "loss": 1.0361, "step": 6963 }, { "epoch": 0.3807415000854263, "grad_norm": 2.7671382427215576, "learning_rate": 7.107339047749793e-05, "loss": 1.3413, "step": 6964 }, { "epoch": 0.3807961729027849, "grad_norm": 2.7090697288513184, "learning_rate": 7.106536136674043e-05, "loss": 1.2017, "step": 6965 }, { "epoch": 0.3808508457201435, "grad_norm": 2.4033966064453125, "learning_rate": 7.10573315954971e-05, "loss": 1.052, "step": 6966 }, { "epoch": 0.38090551853750215, "grad_norm": 4.452269554138184, "learning_rate": 7.104930116401968e-05, "loss": 0.9608, "step": 6967 }, { "epoch": 0.38096019135486076, "grad_norm": 2.486405611038208, "learning_rate": 7.104127007256e-05, "loss": 1.1766, "step": 6968 }, { "epoch": 0.38101486417221936, "grad_norm": 2.198685646057129, "learning_rate": 7.103323832136985e-05, "loss": 0.9266, "step": 6969 }, { "epoch": 0.381069536989578, "grad_norm": 2.578209638595581, "learning_rate": 7.102520591070105e-05, "loss": 0.8456, "step": 6970 }, { "epoch": 0.3811242098069366, "grad_norm": 2.744508743286133, "learning_rate": 7.101717284080546e-05, "loss": 1.1024, "step": 6971 }, { "epoch": 0.3811788826242952, "grad_norm": 2.509650945663452, "learning_rate": 7.100913911193493e-05, "loss": 1.2214, "step": 6972 }, { "epoch": 0.3812335554416538, "grad_norm": 4.115751266479492, "learning_rate": 7.100110472434136e-05, "loss": 1.0395, "step": 6973 }, { "epoch": 0.3812882282590125, "grad_norm": 2.5749990940093994, "learning_rate": 7.099306967827667e-05, "loss": 1.1572, "step": 6974 }, { "epoch": 0.3813429010763711, "grad_norm": 3.533268451690674, "learning_rate": 7.098503397399281e-05, "loss": 1.1705, "step": 6975 }, { "epoch": 0.3813975738937297, "grad_norm": 2.7553551197052, "learning_rate": 7.097699761174169e-05, "loss": 1.0085, "step": 6976 }, { "epoch": 0.38145224671108835, "grad_norm": 2.4726788997650146, "learning_rate": 7.09689605917753e-05, "loss": 1.1723, "step": 6977 }, { "epoch": 0.38150691952844695, "grad_norm": 2.408684492111206, "learning_rate": 7.096092291434564e-05, "loss": 1.1535, "step": 6978 }, { "epoch": 0.38156159234580556, "grad_norm": 2.5139071941375732, "learning_rate": 7.095288457970473e-05, "loss": 0.9868, "step": 6979 }, { "epoch": 0.3816162651631642, "grad_norm": 2.474159002304077, "learning_rate": 7.094484558810457e-05, "loss": 0.9486, "step": 6980 }, { "epoch": 0.3816709379805228, "grad_norm": 2.4177987575531006, "learning_rate": 7.093680593979725e-05, "loss": 0.9527, "step": 6981 }, { "epoch": 0.3817256107978814, "grad_norm": 2.8097517490386963, "learning_rate": 7.092876563503486e-05, "loss": 1.0989, "step": 6982 }, { "epoch": 0.38178028361524, "grad_norm": 2.694502592086792, "learning_rate": 7.092072467406946e-05, "loss": 1.0804, "step": 6983 }, { "epoch": 0.3818349564325987, "grad_norm": 2.6722679138183594, "learning_rate": 7.091268305715317e-05, "loss": 1.2283, "step": 6984 }, { "epoch": 0.3818896292499573, "grad_norm": 2.9065427780151367, "learning_rate": 7.090464078453814e-05, "loss": 1.1854, "step": 6985 }, { "epoch": 0.3819443020673159, "grad_norm": 2.2317261695861816, "learning_rate": 7.089659785647654e-05, "loss": 0.8859, "step": 6986 }, { "epoch": 0.38199897488467455, "grad_norm": 2.451502561569214, "learning_rate": 7.088855427322053e-05, "loss": 1.133, "step": 6987 }, { "epoch": 0.38205364770203315, "grad_norm": 2.472071886062622, "learning_rate": 7.088051003502231e-05, "loss": 0.9319, "step": 6988 }, { "epoch": 0.38210832051939175, "grad_norm": 2.4722440242767334, "learning_rate": 7.087246514213413e-05, "loss": 1.0952, "step": 6989 }, { "epoch": 0.3821629933367504, "grad_norm": 2.5344700813293457, "learning_rate": 7.086441959480818e-05, "loss": 1.0222, "step": 6990 }, { "epoch": 0.382217666154109, "grad_norm": 2.840728759765625, "learning_rate": 7.085637339329675e-05, "loss": 1.156, "step": 6991 }, { "epoch": 0.3822723389714676, "grad_norm": 2.7225453853607178, "learning_rate": 7.084832653785213e-05, "loss": 1.0325, "step": 6992 }, { "epoch": 0.3823270117888262, "grad_norm": 2.732853651046753, "learning_rate": 7.08402790287266e-05, "loss": 1.1237, "step": 6993 }, { "epoch": 0.3823816846061849, "grad_norm": 2.340949058532715, "learning_rate": 7.08322308661725e-05, "loss": 1.1742, "step": 6994 }, { "epoch": 0.3824363574235435, "grad_norm": 2.6247549057006836, "learning_rate": 7.082418205044214e-05, "loss": 1.1142, "step": 6995 }, { "epoch": 0.3824910302409021, "grad_norm": 4.85073184967041, "learning_rate": 7.081613258178794e-05, "loss": 1.0153, "step": 6996 }, { "epoch": 0.38254570305826074, "grad_norm": 1.817420482635498, "learning_rate": 7.080808246046225e-05, "loss": 0.8307, "step": 6997 }, { "epoch": 0.38260037587561935, "grad_norm": 2.508378505706787, "learning_rate": 7.080003168671749e-05, "loss": 1.1577, "step": 6998 }, { "epoch": 0.38265504869297795, "grad_norm": 2.5719025135040283, "learning_rate": 7.079198026080605e-05, "loss": 1.207, "step": 6999 }, { "epoch": 0.38270972151033655, "grad_norm": 2.264488935470581, "learning_rate": 7.07839281829804e-05, "loss": 1.1012, "step": 7000 }, { "epoch": 0.3827643943276952, "grad_norm": 2.2761545181274414, "learning_rate": 7.077587545349301e-05, "loss": 1.0245, "step": 7001 }, { "epoch": 0.3828190671450538, "grad_norm": 2.606241464614868, "learning_rate": 7.076782207259635e-05, "loss": 1.0989, "step": 7002 }, { "epoch": 0.3828737399624124, "grad_norm": 3.0453925132751465, "learning_rate": 7.075976804054297e-05, "loss": 1.3309, "step": 7003 }, { "epoch": 0.3829284127797711, "grad_norm": 2.5247063636779785, "learning_rate": 7.075171335758534e-05, "loss": 1.1154, "step": 7004 }, { "epoch": 0.3829830855971297, "grad_norm": 3.047478437423706, "learning_rate": 7.074365802397602e-05, "loss": 1.0303, "step": 7005 }, { "epoch": 0.3830377584144883, "grad_norm": 2.3271822929382324, "learning_rate": 7.073560203996761e-05, "loss": 1.2481, "step": 7006 }, { "epoch": 0.38309243123184694, "grad_norm": 2.464942693710327, "learning_rate": 7.072754540581266e-05, "loss": 1.0246, "step": 7007 }, { "epoch": 0.38314710404920554, "grad_norm": 2.716627359390259, "learning_rate": 7.071948812176382e-05, "loss": 1.0677, "step": 7008 }, { "epoch": 0.38320177686656415, "grad_norm": 2.672393560409546, "learning_rate": 7.071143018807369e-05, "loss": 1.1506, "step": 7009 }, { "epoch": 0.38325644968392275, "grad_norm": 2.0575151443481445, "learning_rate": 7.070337160499491e-05, "loss": 1.1046, "step": 7010 }, { "epoch": 0.3833111225012814, "grad_norm": 2.6186280250549316, "learning_rate": 7.069531237278018e-05, "loss": 0.9389, "step": 7011 }, { "epoch": 0.38336579531864, "grad_norm": 2.4755916595458984, "learning_rate": 7.068725249168215e-05, "loss": 1.0134, "step": 7012 }, { "epoch": 0.3834204681359986, "grad_norm": 2.5165607929229736, "learning_rate": 7.067919196195358e-05, "loss": 1.1521, "step": 7013 }, { "epoch": 0.3834751409533573, "grad_norm": 2.5634145736694336, "learning_rate": 7.067113078384717e-05, "loss": 1.0443, "step": 7014 }, { "epoch": 0.3835298137707159, "grad_norm": 2.198810577392578, "learning_rate": 7.066306895761567e-05, "loss": 1.0255, "step": 7015 }, { "epoch": 0.3835844865880745, "grad_norm": 2.4618237018585205, "learning_rate": 7.065500648351188e-05, "loss": 1.0577, "step": 7016 }, { "epoch": 0.38363915940543314, "grad_norm": 3.432451009750366, "learning_rate": 7.064694336178855e-05, "loss": 1.1097, "step": 7017 }, { "epoch": 0.38369383222279174, "grad_norm": 2.958516836166382, "learning_rate": 7.063887959269852e-05, "loss": 1.2998, "step": 7018 }, { "epoch": 0.38374850504015035, "grad_norm": 2.6086575984954834, "learning_rate": 7.063081517649462e-05, "loss": 1.1178, "step": 7019 }, { "epoch": 0.38380317785750895, "grad_norm": 2.2654333114624023, "learning_rate": 7.062275011342968e-05, "loss": 0.9927, "step": 7020 }, { "epoch": 0.3838578506748676, "grad_norm": 3.6812822818756104, "learning_rate": 7.061468440375661e-05, "loss": 1.2703, "step": 7021 }, { "epoch": 0.3839125234922262, "grad_norm": 2.3239238262176514, "learning_rate": 7.060661804772827e-05, "loss": 1.0449, "step": 7022 }, { "epoch": 0.3839671963095848, "grad_norm": 2.32498836517334, "learning_rate": 7.05985510455976e-05, "loss": 0.9887, "step": 7023 }, { "epoch": 0.38402186912694347, "grad_norm": 2.760988235473633, "learning_rate": 7.059048339761751e-05, "loss": 1.1535, "step": 7024 }, { "epoch": 0.3840765419443021, "grad_norm": 2.188492774963379, "learning_rate": 7.058241510404097e-05, "loss": 0.9619, "step": 7025 }, { "epoch": 0.3841312147616607, "grad_norm": 2.365527391433716, "learning_rate": 7.057434616512095e-05, "loss": 0.7685, "step": 7026 }, { "epoch": 0.3841858875790193, "grad_norm": 2.570418357849121, "learning_rate": 7.056627658111043e-05, "loss": 1.1144, "step": 7027 }, { "epoch": 0.38424056039637794, "grad_norm": 3.760618209838867, "learning_rate": 7.055820635226245e-05, "loss": 1.0283, "step": 7028 }, { "epoch": 0.38429523321373654, "grad_norm": 2.377516508102417, "learning_rate": 7.055013547883005e-05, "loss": 1.1012, "step": 7029 }, { "epoch": 0.38434990603109515, "grad_norm": 2.7774062156677246, "learning_rate": 7.054206396106624e-05, "loss": 1.1699, "step": 7030 }, { "epoch": 0.3844045788484538, "grad_norm": 2.812800884246826, "learning_rate": 7.053399179922413e-05, "loss": 0.9356, "step": 7031 }, { "epoch": 0.3844592516658124, "grad_norm": 3.6125247478485107, "learning_rate": 7.052591899355682e-05, "loss": 0.9656, "step": 7032 }, { "epoch": 0.384513924483171, "grad_norm": 2.26637864112854, "learning_rate": 7.051784554431741e-05, "loss": 0.9754, "step": 7033 }, { "epoch": 0.38456859730052967, "grad_norm": 2.732628583908081, "learning_rate": 7.050977145175903e-05, "loss": 1.1281, "step": 7034 }, { "epoch": 0.38462327011788827, "grad_norm": 2.4656074047088623, "learning_rate": 7.050169671613487e-05, "loss": 1.1132, "step": 7035 }, { "epoch": 0.3846779429352469, "grad_norm": 3.122145652770996, "learning_rate": 7.049362133769807e-05, "loss": 1.1664, "step": 7036 }, { "epoch": 0.3847326157526055, "grad_norm": 2.995093584060669, "learning_rate": 7.048554531670184e-05, "loss": 1.1886, "step": 7037 }, { "epoch": 0.38478728856996414, "grad_norm": 2.4059102535247803, "learning_rate": 7.047746865339941e-05, "loss": 1.1436, "step": 7038 }, { "epoch": 0.38484196138732274, "grad_norm": 3.433105945587158, "learning_rate": 7.046939134804397e-05, "loss": 0.9533, "step": 7039 }, { "epoch": 0.38489663420468134, "grad_norm": 2.4890761375427246, "learning_rate": 7.046131340088883e-05, "loss": 1.059, "step": 7040 }, { "epoch": 0.38495130702204, "grad_norm": 2.4919698238372803, "learning_rate": 7.045323481218724e-05, "loss": 1.0528, "step": 7041 }, { "epoch": 0.3850059798393986, "grad_norm": 2.481626033782959, "learning_rate": 7.044515558219251e-05, "loss": 1.0593, "step": 7042 }, { "epoch": 0.3850606526567572, "grad_norm": 2.9168875217437744, "learning_rate": 7.043707571115797e-05, "loss": 1.0972, "step": 7043 }, { "epoch": 0.3851153254741158, "grad_norm": 2.094022035598755, "learning_rate": 7.04289951993369e-05, "loss": 1.1515, "step": 7044 }, { "epoch": 0.38516999829147447, "grad_norm": 3.17427659034729, "learning_rate": 7.042091404698271e-05, "loss": 0.978, "step": 7045 }, { "epoch": 0.38522467110883307, "grad_norm": 2.615854501724243, "learning_rate": 7.041283225434876e-05, "loss": 1.1418, "step": 7046 }, { "epoch": 0.3852793439261917, "grad_norm": 2.1498031616210938, "learning_rate": 7.040474982168846e-05, "loss": 1.1276, "step": 7047 }, { "epoch": 0.38533401674355033, "grad_norm": 2.4998068809509277, "learning_rate": 7.039666674925521e-05, "loss": 1.2043, "step": 7048 }, { "epoch": 0.38538868956090894, "grad_norm": 2.608938694000244, "learning_rate": 7.038858303730246e-05, "loss": 0.9894, "step": 7049 }, { "epoch": 0.38544336237826754, "grad_norm": 3.164501428604126, "learning_rate": 7.038049868608365e-05, "loss": 1.1013, "step": 7050 }, { "epoch": 0.3854980351956262, "grad_norm": 2.652146339416504, "learning_rate": 7.03724136958523e-05, "loss": 1.2358, "step": 7051 }, { "epoch": 0.3855527080129848, "grad_norm": 2.6410558223724365, "learning_rate": 7.036432806686185e-05, "loss": 1.0522, "step": 7052 }, { "epoch": 0.3856073808303434, "grad_norm": 2.640373706817627, "learning_rate": 7.035624179936585e-05, "loss": 0.9949, "step": 7053 }, { "epoch": 0.385662053647702, "grad_norm": 2.5051779747009277, "learning_rate": 7.034815489361784e-05, "loss": 1.1521, "step": 7054 }, { "epoch": 0.38571672646506067, "grad_norm": 2.100790023803711, "learning_rate": 7.034006734987136e-05, "loss": 1.0332, "step": 7055 }, { "epoch": 0.38577139928241927, "grad_norm": 2.4234228134155273, "learning_rate": 7.033197916838002e-05, "loss": 0.9538, "step": 7056 }, { "epoch": 0.3858260720997779, "grad_norm": 2.1132559776306152, "learning_rate": 7.032389034939738e-05, "loss": 1.1012, "step": 7057 }, { "epoch": 0.38588074491713653, "grad_norm": 2.5248894691467285, "learning_rate": 7.031580089317709e-05, "loss": 1.0853, "step": 7058 }, { "epoch": 0.38593541773449513, "grad_norm": 4.753327369689941, "learning_rate": 7.030771079997276e-05, "loss": 1.1308, "step": 7059 }, { "epoch": 0.38599009055185374, "grad_norm": 2.4949307441711426, "learning_rate": 7.029962007003807e-05, "loss": 1.0408, "step": 7060 }, { "epoch": 0.3860447633692124, "grad_norm": 2.8032302856445312, "learning_rate": 7.029152870362668e-05, "loss": 1.1671, "step": 7061 }, { "epoch": 0.386099436186571, "grad_norm": 2.2730815410614014, "learning_rate": 7.02834367009923e-05, "loss": 1.1892, "step": 7062 }, { "epoch": 0.3861541090039296, "grad_norm": 3.2616453170776367, "learning_rate": 7.027534406238863e-05, "loss": 1.2174, "step": 7063 }, { "epoch": 0.3862087818212882, "grad_norm": 2.568666696548462, "learning_rate": 7.026725078806944e-05, "loss": 1.0877, "step": 7064 }, { "epoch": 0.38626345463864686, "grad_norm": 2.2981150150299072, "learning_rate": 7.025915687828847e-05, "loss": 0.8472, "step": 7065 }, { "epoch": 0.38631812745600547, "grad_norm": 2.710681200027466, "learning_rate": 7.02510623332995e-05, "loss": 1.128, "step": 7066 }, { "epoch": 0.38637280027336407, "grad_norm": 2.331956624984741, "learning_rate": 7.024296715335629e-05, "loss": 1.1135, "step": 7067 }, { "epoch": 0.38642747309072273, "grad_norm": 3.2859861850738525, "learning_rate": 7.023487133871272e-05, "loss": 1.0612, "step": 7068 }, { "epoch": 0.38648214590808133, "grad_norm": 2.4632129669189453, "learning_rate": 7.022677488962258e-05, "loss": 1.0924, "step": 7069 }, { "epoch": 0.38653681872543993, "grad_norm": 2.612928628921509, "learning_rate": 7.021867780633977e-05, "loss": 1.1928, "step": 7070 }, { "epoch": 0.38659149154279854, "grad_norm": 2.279226064682007, "learning_rate": 7.021058008911812e-05, "loss": 0.9957, "step": 7071 }, { "epoch": 0.3866461643601572, "grad_norm": 2.3624284267425537, "learning_rate": 7.020248173821155e-05, "loss": 1.1228, "step": 7072 }, { "epoch": 0.3867008371775158, "grad_norm": 2.464050769805908, "learning_rate": 7.019438275387398e-05, "loss": 0.8249, "step": 7073 }, { "epoch": 0.3867555099948744, "grad_norm": 2.7699828147888184, "learning_rate": 7.018628313635934e-05, "loss": 1.2937, "step": 7074 }, { "epoch": 0.38681018281223306, "grad_norm": 4.860020160675049, "learning_rate": 7.017818288592158e-05, "loss": 1.0938, "step": 7075 }, { "epoch": 0.38686485562959166, "grad_norm": 2.9227287769317627, "learning_rate": 7.01700820028147e-05, "loss": 1.3129, "step": 7076 }, { "epoch": 0.38691952844695027, "grad_norm": 3.79756236076355, "learning_rate": 7.016198048729268e-05, "loss": 1.1119, "step": 7077 }, { "epoch": 0.3869742012643089, "grad_norm": 2.6447949409484863, "learning_rate": 7.015387833960952e-05, "loss": 1.1519, "step": 7078 }, { "epoch": 0.38702887408166753, "grad_norm": 2.279026508331299, "learning_rate": 7.014577556001927e-05, "loss": 1.0762, "step": 7079 }, { "epoch": 0.38708354689902613, "grad_norm": 2.200467109680176, "learning_rate": 7.0137672148776e-05, "loss": 1.1086, "step": 7080 }, { "epoch": 0.38713821971638473, "grad_norm": 2.4841554164886475, "learning_rate": 7.012956810613377e-05, "loss": 1.0831, "step": 7081 }, { "epoch": 0.3871928925337434, "grad_norm": 2.1923792362213135, "learning_rate": 7.012146343234669e-05, "loss": 1.0088, "step": 7082 }, { "epoch": 0.387247565351102, "grad_norm": 2.6806890964508057, "learning_rate": 7.011335812766883e-05, "loss": 1.099, "step": 7083 }, { "epoch": 0.3873022381684606, "grad_norm": 2.465512752532959, "learning_rate": 7.010525219235438e-05, "loss": 1.0915, "step": 7084 }, { "epoch": 0.38735691098581926, "grad_norm": 2.8685739040374756, "learning_rate": 7.009714562665746e-05, "loss": 1.0906, "step": 7085 }, { "epoch": 0.38741158380317786, "grad_norm": 2.2084786891937256, "learning_rate": 7.008903843083227e-05, "loss": 1.0555, "step": 7086 }, { "epoch": 0.38746625662053646, "grad_norm": 2.0666563510894775, "learning_rate": 7.008093060513299e-05, "loss": 1.0182, "step": 7087 }, { "epoch": 0.3875209294378951, "grad_norm": 3.270881414413452, "learning_rate": 7.007282214981382e-05, "loss": 1.0834, "step": 7088 }, { "epoch": 0.3875756022552537, "grad_norm": 2.068241596221924, "learning_rate": 7.006471306512902e-05, "loss": 0.9737, "step": 7089 }, { "epoch": 0.38763027507261233, "grad_norm": 2.6154227256774902, "learning_rate": 7.005660335133282e-05, "loss": 1.1507, "step": 7090 }, { "epoch": 0.38768494788997093, "grad_norm": 2.3147871494293213, "learning_rate": 7.004849300867951e-05, "loss": 1.0361, "step": 7091 }, { "epoch": 0.3877396207073296, "grad_norm": 2.2148683071136475, "learning_rate": 7.004038203742338e-05, "loss": 0.7518, "step": 7092 }, { "epoch": 0.3877942935246882, "grad_norm": 2.4054174423217773, "learning_rate": 7.003227043781873e-05, "loss": 1.1724, "step": 7093 }, { "epoch": 0.3878489663420468, "grad_norm": 3.0148990154266357, "learning_rate": 7.002415821011991e-05, "loss": 1.1975, "step": 7094 }, { "epoch": 0.38790363915940546, "grad_norm": 2.3407888412475586, "learning_rate": 7.001604535458124e-05, "loss": 0.9017, "step": 7095 }, { "epoch": 0.38795831197676406, "grad_norm": 2.7909133434295654, "learning_rate": 7.000793187145714e-05, "loss": 1.0617, "step": 7096 }, { "epoch": 0.38801298479412266, "grad_norm": 2.160651683807373, "learning_rate": 6.999981776100196e-05, "loss": 0.8614, "step": 7097 }, { "epoch": 0.38806765761148126, "grad_norm": 2.586066484451294, "learning_rate": 6.999170302347013e-05, "loss": 1.0752, "step": 7098 }, { "epoch": 0.3881223304288399, "grad_norm": 2.041672706604004, "learning_rate": 6.998358765911607e-05, "loss": 0.8617, "step": 7099 }, { "epoch": 0.3881770032461985, "grad_norm": 5.028573036193848, "learning_rate": 6.997547166819424e-05, "loss": 1.1618, "step": 7100 }, { "epoch": 0.38823167606355713, "grad_norm": 3.112710475921631, "learning_rate": 6.996735505095911e-05, "loss": 1.076, "step": 7101 }, { "epoch": 0.3882863488809158, "grad_norm": 2.5375583171844482, "learning_rate": 6.995923780766516e-05, "loss": 0.9684, "step": 7102 }, { "epoch": 0.3883410216982744, "grad_norm": 2.4932539463043213, "learning_rate": 6.995111993856689e-05, "loss": 1.0307, "step": 7103 }, { "epoch": 0.388395694515633, "grad_norm": 2.3785154819488525, "learning_rate": 6.994300144391887e-05, "loss": 1.0869, "step": 7104 }, { "epoch": 0.38845036733299165, "grad_norm": 2.355872869491577, "learning_rate": 6.99348823239756e-05, "loss": 1.1443, "step": 7105 }, { "epoch": 0.38850504015035026, "grad_norm": 3.262842893600464, "learning_rate": 6.992676257899167e-05, "loss": 1.0077, "step": 7106 }, { "epoch": 0.38855971296770886, "grad_norm": 2.255765676498413, "learning_rate": 6.991864220922169e-05, "loss": 0.8927, "step": 7107 }, { "epoch": 0.38861438578506746, "grad_norm": 3.2022719383239746, "learning_rate": 6.991052121492021e-05, "loss": 1.0043, "step": 7108 }, { "epoch": 0.3886690586024261, "grad_norm": 2.2321813106536865, "learning_rate": 6.99023995963419e-05, "loss": 1.1384, "step": 7109 }, { "epoch": 0.3887237314197847, "grad_norm": 2.703958034515381, "learning_rate": 6.98942773537414e-05, "loss": 1.0655, "step": 7110 }, { "epoch": 0.3887784042371433, "grad_norm": 2.4119937419891357, "learning_rate": 6.988615448737339e-05, "loss": 1.0004, "step": 7111 }, { "epoch": 0.388833077054502, "grad_norm": 2.4617667198181152, "learning_rate": 6.987803099749252e-05, "loss": 1.0678, "step": 7112 }, { "epoch": 0.3888877498718606, "grad_norm": 2.081735372543335, "learning_rate": 6.986990688435349e-05, "loss": 0.9547, "step": 7113 }, { "epoch": 0.3889424226892192, "grad_norm": 2.693132162094116, "learning_rate": 6.986178214821108e-05, "loss": 0.9959, "step": 7114 }, { "epoch": 0.38899709550657785, "grad_norm": 2.8306498527526855, "learning_rate": 6.985365678931999e-05, "loss": 1.3211, "step": 7115 }, { "epoch": 0.38905176832393645, "grad_norm": 2.131725788116455, "learning_rate": 6.9845530807935e-05, "loss": 0.8529, "step": 7116 }, { "epoch": 0.38910644114129506, "grad_norm": 2.610410690307617, "learning_rate": 6.983740420431088e-05, "loss": 1.0922, "step": 7117 }, { "epoch": 0.38916111395865366, "grad_norm": 2.5427846908569336, "learning_rate": 6.982927697870242e-05, "loss": 0.9652, "step": 7118 }, { "epoch": 0.3892157867760123, "grad_norm": 2.6429762840270996, "learning_rate": 6.982114913136448e-05, "loss": 1.122, "step": 7119 }, { "epoch": 0.3892704595933709, "grad_norm": 2.753218650817871, "learning_rate": 6.981302066255189e-05, "loss": 1.0599, "step": 7120 }, { "epoch": 0.3893251324107295, "grad_norm": 2.583502769470215, "learning_rate": 6.98048915725195e-05, "loss": 1.0817, "step": 7121 }, { "epoch": 0.3893798052280882, "grad_norm": 2.410428524017334, "learning_rate": 6.97967618615222e-05, "loss": 1.0137, "step": 7122 }, { "epoch": 0.3894344780454468, "grad_norm": 2.452141284942627, "learning_rate": 6.978863152981486e-05, "loss": 0.9992, "step": 7123 }, { "epoch": 0.3894891508628054, "grad_norm": 2.945843458175659, "learning_rate": 6.978050057765244e-05, "loss": 1.1424, "step": 7124 }, { "epoch": 0.389543823680164, "grad_norm": 2.3250341415405273, "learning_rate": 6.977236900528985e-05, "loss": 1.1091, "step": 7125 }, { "epoch": 0.38959849649752265, "grad_norm": 2.6190648078918457, "learning_rate": 6.976423681298207e-05, "loss": 0.9403, "step": 7126 }, { "epoch": 0.38965316931488125, "grad_norm": 2.9671106338500977, "learning_rate": 6.975610400098408e-05, "loss": 1.0628, "step": 7127 }, { "epoch": 0.38970784213223986, "grad_norm": 2.975717067718506, "learning_rate": 6.974797056955084e-05, "loss": 1.1402, "step": 7128 }, { "epoch": 0.3897625149495985, "grad_norm": 2.9111616611480713, "learning_rate": 6.97398365189374e-05, "loss": 1.1356, "step": 7129 }, { "epoch": 0.3898171877669571, "grad_norm": 3.5081417560577393, "learning_rate": 6.973170184939882e-05, "loss": 1.2845, "step": 7130 }, { "epoch": 0.3898718605843157, "grad_norm": 2.0567119121551514, "learning_rate": 6.972356656119009e-05, "loss": 1.0267, "step": 7131 }, { "epoch": 0.3899265334016744, "grad_norm": 2.17315411567688, "learning_rate": 6.971543065456632e-05, "loss": 1.0347, "step": 7132 }, { "epoch": 0.389981206219033, "grad_norm": 2.2382071018218994, "learning_rate": 6.970729412978261e-05, "loss": 1.1603, "step": 7133 }, { "epoch": 0.3900358790363916, "grad_norm": 2.4903383255004883, "learning_rate": 6.969915698709406e-05, "loss": 1.4085, "step": 7134 }, { "epoch": 0.3900905518537502, "grad_norm": 2.680903434753418, "learning_rate": 6.969101922675582e-05, "loss": 1.0175, "step": 7135 }, { "epoch": 0.39014522467110885, "grad_norm": 2.6390881538391113, "learning_rate": 6.968288084902301e-05, "loss": 0.8643, "step": 7136 }, { "epoch": 0.39019989748846745, "grad_norm": 2.6854004859924316, "learning_rate": 6.967474185415085e-05, "loss": 1.1254, "step": 7137 }, { "epoch": 0.39025457030582605, "grad_norm": 1.8200881481170654, "learning_rate": 6.966660224239447e-05, "loss": 0.8905, "step": 7138 }, { "epoch": 0.3903092431231847, "grad_norm": 2.363992691040039, "learning_rate": 6.965846201400914e-05, "loss": 1.1241, "step": 7139 }, { "epoch": 0.3903639159405433, "grad_norm": 2.9486184120178223, "learning_rate": 6.965032116925006e-05, "loss": 1.2902, "step": 7140 }, { "epoch": 0.3904185887579019, "grad_norm": 2.813323736190796, "learning_rate": 6.964217970837249e-05, "loss": 1.176, "step": 7141 }, { "epoch": 0.3904732615752606, "grad_norm": 2.211559295654297, "learning_rate": 6.963403763163167e-05, "loss": 1.0566, "step": 7142 }, { "epoch": 0.3905279343926192, "grad_norm": 2.5188636779785156, "learning_rate": 6.962589493928292e-05, "loss": 1.0083, "step": 7143 }, { "epoch": 0.3905826072099778, "grad_norm": 2.3854458332061768, "learning_rate": 6.961775163158154e-05, "loss": 1.1901, "step": 7144 }, { "epoch": 0.3906372800273364, "grad_norm": 2.0905985832214355, "learning_rate": 6.960960770878285e-05, "loss": 0.9557, "step": 7145 }, { "epoch": 0.39069195284469505, "grad_norm": 2.477161169052124, "learning_rate": 6.96014631711422e-05, "loss": 0.7826, "step": 7146 }, { "epoch": 0.39074662566205365, "grad_norm": 2.259427309036255, "learning_rate": 6.959331801891495e-05, "loss": 0.9089, "step": 7147 }, { "epoch": 0.39080129847941225, "grad_norm": 3.675723075866699, "learning_rate": 6.958517225235648e-05, "loss": 1.005, "step": 7148 }, { "epoch": 0.3908559712967709, "grad_norm": 2.562833786010742, "learning_rate": 6.95770258717222e-05, "loss": 1.0817, "step": 7149 }, { "epoch": 0.3909106441141295, "grad_norm": 2.13321590423584, "learning_rate": 6.956887887726753e-05, "loss": 0.9772, "step": 7150 }, { "epoch": 0.3909653169314881, "grad_norm": 3.3484690189361572, "learning_rate": 6.956073126924793e-05, "loss": 1.1172, "step": 7151 }, { "epoch": 0.3910199897488467, "grad_norm": 2.4715943336486816, "learning_rate": 6.955258304791884e-05, "loss": 0.833, "step": 7152 }, { "epoch": 0.3910746625662054, "grad_norm": 2.7362616062164307, "learning_rate": 6.954443421353574e-05, "loss": 1.0226, "step": 7153 }, { "epoch": 0.391129335383564, "grad_norm": 2.489872455596924, "learning_rate": 6.953628476635413e-05, "loss": 1.1342, "step": 7154 }, { "epoch": 0.3911840082009226, "grad_norm": 2.2180705070495605, "learning_rate": 6.952813470662955e-05, "loss": 0.9634, "step": 7155 }, { "epoch": 0.39123868101828124, "grad_norm": 2.9472100734710693, "learning_rate": 6.951998403461751e-05, "loss": 1.1602, "step": 7156 }, { "epoch": 0.39129335383563985, "grad_norm": 2.75018310546875, "learning_rate": 6.951183275057358e-05, "loss": 0.9694, "step": 7157 }, { "epoch": 0.39134802665299845, "grad_norm": 2.1491408348083496, "learning_rate": 6.950368085475334e-05, "loss": 1.0124, "step": 7158 }, { "epoch": 0.3914026994703571, "grad_norm": 2.886963129043579, "learning_rate": 6.949552834741238e-05, "loss": 1.1941, "step": 7159 }, { "epoch": 0.3914573722877157, "grad_norm": 2.7852606773376465, "learning_rate": 6.948737522880631e-05, "loss": 1.0748, "step": 7160 }, { "epoch": 0.3915120451050743, "grad_norm": 2.1665070056915283, "learning_rate": 6.947922149919078e-05, "loss": 1.0329, "step": 7161 }, { "epoch": 0.3915667179224329, "grad_norm": 2.288362503051758, "learning_rate": 6.947106715882142e-05, "loss": 1.0712, "step": 7162 }, { "epoch": 0.3916213907397916, "grad_norm": 2.614828109741211, "learning_rate": 6.946291220795392e-05, "loss": 1.0772, "step": 7163 }, { "epoch": 0.3916760635571502, "grad_norm": 2.7102441787719727, "learning_rate": 6.945475664684395e-05, "loss": 1.2628, "step": 7164 }, { "epoch": 0.3917307363745088, "grad_norm": 2.8071846961975098, "learning_rate": 6.944660047574726e-05, "loss": 1.0681, "step": 7165 }, { "epoch": 0.39178540919186744, "grad_norm": 3.006948471069336, "learning_rate": 6.943844369491955e-05, "loss": 1.0539, "step": 7166 }, { "epoch": 0.39184008200922604, "grad_norm": 2.739684820175171, "learning_rate": 6.943028630461655e-05, "loss": 1.1331, "step": 7167 }, { "epoch": 0.39189475482658465, "grad_norm": 2.504915952682495, "learning_rate": 6.942212830509408e-05, "loss": 0.9058, "step": 7168 }, { "epoch": 0.3919494276439433, "grad_norm": 2.481140375137329, "learning_rate": 6.941396969660789e-05, "loss": 0.9379, "step": 7169 }, { "epoch": 0.3920041004613019, "grad_norm": 2.1603965759277344, "learning_rate": 6.94058104794138e-05, "loss": 1.049, "step": 7170 }, { "epoch": 0.3920587732786605, "grad_norm": 2.2623305320739746, "learning_rate": 6.939765065376763e-05, "loss": 1.0779, "step": 7171 }, { "epoch": 0.3921134460960191, "grad_norm": 2.4450595378875732, "learning_rate": 6.93894902199252e-05, "loss": 1.0173, "step": 7172 }, { "epoch": 0.3921681189133778, "grad_norm": 2.2608838081359863, "learning_rate": 6.938132917814242e-05, "loss": 1.0277, "step": 7173 }, { "epoch": 0.3922227917307364, "grad_norm": 3.3968310356140137, "learning_rate": 6.937316752867515e-05, "loss": 1.1512, "step": 7174 }, { "epoch": 0.392277464548095, "grad_norm": 3.7989463806152344, "learning_rate": 6.93650052717793e-05, "loss": 1.0994, "step": 7175 }, { "epoch": 0.39233213736545364, "grad_norm": 2.178072214126587, "learning_rate": 6.935684240771076e-05, "loss": 1.1128, "step": 7176 }, { "epoch": 0.39238681018281224, "grad_norm": 2.5068187713623047, "learning_rate": 6.934867893672549e-05, "loss": 0.9142, "step": 7177 }, { "epoch": 0.39244148300017084, "grad_norm": 2.2338852882385254, "learning_rate": 6.934051485907947e-05, "loss": 0.9224, "step": 7178 }, { "epoch": 0.39249615581752945, "grad_norm": 2.1786391735076904, "learning_rate": 6.933235017502864e-05, "loss": 0.8796, "step": 7179 }, { "epoch": 0.3925508286348881, "grad_norm": 2.862959861755371, "learning_rate": 6.9324184884829e-05, "loss": 1.1892, "step": 7180 }, { "epoch": 0.3926055014522467, "grad_norm": 2.6893866062164307, "learning_rate": 6.931601898873661e-05, "loss": 1.0915, "step": 7181 }, { "epoch": 0.3926601742696053, "grad_norm": 2.644174098968506, "learning_rate": 6.930785248700745e-05, "loss": 1.0746, "step": 7182 }, { "epoch": 0.39271484708696397, "grad_norm": 2.9505908489227295, "learning_rate": 6.92996853798976e-05, "loss": 1.2142, "step": 7183 }, { "epoch": 0.3927695199043226, "grad_norm": 2.9186179637908936, "learning_rate": 6.929151766766314e-05, "loss": 1.2998, "step": 7184 }, { "epoch": 0.3928241927216812, "grad_norm": 2.22930645942688, "learning_rate": 6.928334935056015e-05, "loss": 0.9293, "step": 7185 }, { "epoch": 0.39287886553903983, "grad_norm": 2.770231246948242, "learning_rate": 6.927518042884475e-05, "loss": 1.1014, "step": 7186 }, { "epoch": 0.39293353835639844, "grad_norm": 2.250847339630127, "learning_rate": 6.926701090277303e-05, "loss": 0.9485, "step": 7187 }, { "epoch": 0.39298821117375704, "grad_norm": 2.1646366119384766, "learning_rate": 6.925884077260119e-05, "loss": 1.0414, "step": 7188 }, { "epoch": 0.39304288399111564, "grad_norm": 2.829880714416504, "learning_rate": 6.925067003858537e-05, "loss": 1.1865, "step": 7189 }, { "epoch": 0.3930975568084743, "grad_norm": 3.2112767696380615, "learning_rate": 6.924249870098177e-05, "loss": 1.2281, "step": 7190 }, { "epoch": 0.3931522296258329, "grad_norm": 2.601760149002075, "learning_rate": 6.923432676004655e-05, "loss": 1.0549, "step": 7191 }, { "epoch": 0.3932069024431915, "grad_norm": 2.086005449295044, "learning_rate": 6.922615421603601e-05, "loss": 1.0485, "step": 7192 }, { "epoch": 0.39326157526055017, "grad_norm": 2.1051836013793945, "learning_rate": 6.921798106920634e-05, "loss": 0.7851, "step": 7193 }, { "epoch": 0.39331624807790877, "grad_norm": 2.5059094429016113, "learning_rate": 6.920980731981382e-05, "loss": 1.0878, "step": 7194 }, { "epoch": 0.3933709208952674, "grad_norm": 2.5362396240234375, "learning_rate": 6.920163296811472e-05, "loss": 1.0957, "step": 7195 }, { "epoch": 0.393425593712626, "grad_norm": 2.0305848121643066, "learning_rate": 6.919345801436535e-05, "loss": 1.0165, "step": 7196 }, { "epoch": 0.39348026652998463, "grad_norm": 2.1961846351623535, "learning_rate": 6.918528245882203e-05, "loss": 0.991, "step": 7197 }, { "epoch": 0.39353493934734324, "grad_norm": 3.666095733642578, "learning_rate": 6.917710630174108e-05, "loss": 1.0133, "step": 7198 }, { "epoch": 0.39358961216470184, "grad_norm": 2.4041507244110107, "learning_rate": 6.916892954337887e-05, "loss": 1.1995, "step": 7199 }, { "epoch": 0.3936442849820605, "grad_norm": 2.7831833362579346, "learning_rate": 6.916075218399178e-05, "loss": 1.1214, "step": 7200 }, { "epoch": 0.3936989577994191, "grad_norm": 2.5261402130126953, "learning_rate": 6.91525742238362e-05, "loss": 1.024, "step": 7201 }, { "epoch": 0.3937536306167777, "grad_norm": 2.7451376914978027, "learning_rate": 6.914439566316853e-05, "loss": 0.9504, "step": 7202 }, { "epoch": 0.39380830343413636, "grad_norm": 3.3394551277160645, "learning_rate": 6.913621650224522e-05, "loss": 1.2291, "step": 7203 }, { "epoch": 0.39386297625149497, "grad_norm": 2.2590701580047607, "learning_rate": 6.91280367413227e-05, "loss": 1.1835, "step": 7204 }, { "epoch": 0.39391764906885357, "grad_norm": 2.4965639114379883, "learning_rate": 6.911985638065746e-05, "loss": 0.9271, "step": 7205 }, { "epoch": 0.3939723218862122, "grad_norm": 2.2695462703704834, "learning_rate": 6.911167542050597e-05, "loss": 1.0232, "step": 7206 }, { "epoch": 0.39402699470357083, "grad_norm": 2.307936906814575, "learning_rate": 6.910349386112474e-05, "loss": 1.0282, "step": 7207 }, { "epoch": 0.39408166752092944, "grad_norm": 2.5534603595733643, "learning_rate": 6.909531170277033e-05, "loss": 0.9328, "step": 7208 }, { "epoch": 0.39413634033828804, "grad_norm": 2.840036392211914, "learning_rate": 6.908712894569924e-05, "loss": 1.0977, "step": 7209 }, { "epoch": 0.3941910131556467, "grad_norm": 2.563532829284668, "learning_rate": 6.907894559016805e-05, "loss": 1.0837, "step": 7210 }, { "epoch": 0.3942456859730053, "grad_norm": 2.5857629776000977, "learning_rate": 6.907076163643331e-05, "loss": 1.0797, "step": 7211 }, { "epoch": 0.3943003587903639, "grad_norm": 2.2750816345214844, "learning_rate": 6.906257708475169e-05, "loss": 1.0706, "step": 7212 }, { "epoch": 0.39435503160772256, "grad_norm": 2.6804447174072266, "learning_rate": 6.905439193537976e-05, "loss": 1.0372, "step": 7213 }, { "epoch": 0.39440970442508116, "grad_norm": 2.2944490909576416, "learning_rate": 6.904620618857417e-05, "loss": 1.0576, "step": 7214 }, { "epoch": 0.39446437724243977, "grad_norm": 3.0662641525268555, "learning_rate": 6.903801984459157e-05, "loss": 0.8299, "step": 7215 }, { "epoch": 0.39451905005979837, "grad_norm": 2.656773567199707, "learning_rate": 6.902983290368862e-05, "loss": 1.0946, "step": 7216 }, { "epoch": 0.39457372287715703, "grad_norm": 2.614293098449707, "learning_rate": 6.902164536612206e-05, "loss": 1.1098, "step": 7217 }, { "epoch": 0.39462839569451563, "grad_norm": 2.8577065467834473, "learning_rate": 6.90134572321486e-05, "loss": 1.1823, "step": 7218 }, { "epoch": 0.39468306851187424, "grad_norm": 2.100572347640991, "learning_rate": 6.900526850202492e-05, "loss": 1.1145, "step": 7219 }, { "epoch": 0.3947377413292329, "grad_norm": 2.8917951583862305, "learning_rate": 6.899707917600781e-05, "loss": 1.1138, "step": 7220 }, { "epoch": 0.3947924141465915, "grad_norm": 2.854998826980591, "learning_rate": 6.898888925435402e-05, "loss": 1.2779, "step": 7221 }, { "epoch": 0.3948470869639501, "grad_norm": 2.842040538787842, "learning_rate": 6.898069873732034e-05, "loss": 1.1626, "step": 7222 }, { "epoch": 0.3949017597813087, "grad_norm": 2.58223032951355, "learning_rate": 6.897250762516361e-05, "loss": 1.0021, "step": 7223 }, { "epoch": 0.39495643259866736, "grad_norm": 2.5072288513183594, "learning_rate": 6.896431591814062e-05, "loss": 1.0826, "step": 7224 }, { "epoch": 0.39501110541602596, "grad_norm": 2.259740114212036, "learning_rate": 6.895612361650823e-05, "loss": 1.051, "step": 7225 }, { "epoch": 0.39506577823338457, "grad_norm": 2.5484440326690674, "learning_rate": 6.894793072052326e-05, "loss": 1.2276, "step": 7226 }, { "epoch": 0.3951204510507432, "grad_norm": 2.587632656097412, "learning_rate": 6.893973723044265e-05, "loss": 1.1446, "step": 7227 }, { "epoch": 0.39517512386810183, "grad_norm": 2.2942233085632324, "learning_rate": 6.893154314652329e-05, "loss": 1.1361, "step": 7228 }, { "epoch": 0.39522979668546043, "grad_norm": 3.181056022644043, "learning_rate": 6.892334846902207e-05, "loss": 1.3359, "step": 7229 }, { "epoch": 0.3952844695028191, "grad_norm": 2.5836987495422363, "learning_rate": 6.891515319819595e-05, "loss": 1.3206, "step": 7230 }, { "epoch": 0.3953391423201777, "grad_norm": 2.0509653091430664, "learning_rate": 6.890695733430186e-05, "loss": 1.0653, "step": 7231 }, { "epoch": 0.3953938151375363, "grad_norm": 3.630737543106079, "learning_rate": 6.88987608775968e-05, "loss": 1.1716, "step": 7232 }, { "epoch": 0.3954484879548949, "grad_norm": 3.048245429992676, "learning_rate": 6.889056382833775e-05, "loss": 1.302, "step": 7233 }, { "epoch": 0.39550316077225356, "grad_norm": 2.293064594268799, "learning_rate": 6.888236618678174e-05, "loss": 0.9589, "step": 7234 }, { "epoch": 0.39555783358961216, "grad_norm": 2.4413375854492188, "learning_rate": 6.887416795318576e-05, "loss": 0.8615, "step": 7235 }, { "epoch": 0.39561250640697077, "grad_norm": 2.2471299171447754, "learning_rate": 6.88659691278069e-05, "loss": 1.1468, "step": 7236 }, { "epoch": 0.3956671792243294, "grad_norm": 2.530984878540039, "learning_rate": 6.88577697109022e-05, "loss": 1.1847, "step": 7237 }, { "epoch": 0.395721852041688, "grad_norm": 2.3924803733825684, "learning_rate": 6.884956970272875e-05, "loss": 1.1053, "step": 7238 }, { "epoch": 0.39577652485904663, "grad_norm": 2.2458651065826416, "learning_rate": 6.884136910354367e-05, "loss": 1.1161, "step": 7239 }, { "epoch": 0.3958311976764053, "grad_norm": 2.076031446456909, "learning_rate": 6.883316791360408e-05, "loss": 0.8784, "step": 7240 }, { "epoch": 0.3958858704937639, "grad_norm": 2.3249480724334717, "learning_rate": 6.882496613316708e-05, "loss": 0.8708, "step": 7241 }, { "epoch": 0.3959405433111225, "grad_norm": 2.4999756813049316, "learning_rate": 6.88167637624899e-05, "loss": 1.109, "step": 7242 }, { "epoch": 0.3959952161284811, "grad_norm": 2.5637552738189697, "learning_rate": 6.880856080182967e-05, "loss": 1.0984, "step": 7243 }, { "epoch": 0.39604988894583976, "grad_norm": 2.495394468307495, "learning_rate": 6.880035725144359e-05, "loss": 1.0983, "step": 7244 }, { "epoch": 0.39610456176319836, "grad_norm": 2.616795063018799, "learning_rate": 6.879215311158889e-05, "loss": 0.9781, "step": 7245 }, { "epoch": 0.39615923458055696, "grad_norm": 2.454268455505371, "learning_rate": 6.878394838252279e-05, "loss": 1.0558, "step": 7246 }, { "epoch": 0.3962139073979156, "grad_norm": 2.250347375869751, "learning_rate": 6.877574306450254e-05, "loss": 0.9456, "step": 7247 }, { "epoch": 0.3962685802152742, "grad_norm": 2.4204325675964355, "learning_rate": 6.876753715778542e-05, "loss": 1.1783, "step": 7248 }, { "epoch": 0.3963232530326328, "grad_norm": 2.2409915924072266, "learning_rate": 6.875933066262873e-05, "loss": 0.729, "step": 7249 }, { "epoch": 0.39637792584999143, "grad_norm": 2.163114547729492, "learning_rate": 6.875112357928977e-05, "loss": 0.8958, "step": 7250 }, { "epoch": 0.3964325986673501, "grad_norm": 2.4273271560668945, "learning_rate": 6.874291590802584e-05, "loss": 1.0873, "step": 7251 }, { "epoch": 0.3964872714847087, "grad_norm": 2.561699151992798, "learning_rate": 6.873470764909432e-05, "loss": 1.0561, "step": 7252 }, { "epoch": 0.3965419443020673, "grad_norm": 2.5358059406280518, "learning_rate": 6.872649880275255e-05, "loss": 1.1023, "step": 7253 }, { "epoch": 0.39659661711942595, "grad_norm": 2.5751962661743164, "learning_rate": 6.871828936925791e-05, "loss": 1.0498, "step": 7254 }, { "epoch": 0.39665128993678456, "grad_norm": 2.539257526397705, "learning_rate": 6.871007934886782e-05, "loss": 1.0736, "step": 7255 }, { "epoch": 0.39670596275414316, "grad_norm": 2.282428026199341, "learning_rate": 6.870186874183969e-05, "loss": 0.9973, "step": 7256 }, { "epoch": 0.3967606355715018, "grad_norm": 2.3696389198303223, "learning_rate": 6.869365754843095e-05, "loss": 0.9454, "step": 7257 }, { "epoch": 0.3968153083888604, "grad_norm": 2.6674060821533203, "learning_rate": 6.868544576889906e-05, "loss": 1.3724, "step": 7258 }, { "epoch": 0.396869981206219, "grad_norm": 2.5536372661590576, "learning_rate": 6.867723340350149e-05, "loss": 1.1379, "step": 7259 }, { "epoch": 0.3969246540235776, "grad_norm": 2.3739311695098877, "learning_rate": 6.866902045249571e-05, "loss": 0.9688, "step": 7260 }, { "epoch": 0.3969793268409363, "grad_norm": 2.9186201095581055, "learning_rate": 6.866080691613928e-05, "loss": 1.1791, "step": 7261 }, { "epoch": 0.3970339996582949, "grad_norm": 3.2612314224243164, "learning_rate": 6.865259279468967e-05, "loss": 1.3441, "step": 7262 }, { "epoch": 0.3970886724756535, "grad_norm": 2.842843770980835, "learning_rate": 6.86443780884045e-05, "loss": 0.9769, "step": 7263 }, { "epoch": 0.39714334529301215, "grad_norm": 2.8560256958007812, "learning_rate": 6.863616279754126e-05, "loss": 0.9335, "step": 7264 }, { "epoch": 0.39719801811037075, "grad_norm": 2.970010995864868, "learning_rate": 6.862794692235756e-05, "loss": 1.1237, "step": 7265 }, { "epoch": 0.39725269092772936, "grad_norm": 2.9784934520721436, "learning_rate": 6.861973046311102e-05, "loss": 1.0051, "step": 7266 }, { "epoch": 0.397307363745088, "grad_norm": 2.8538711071014404, "learning_rate": 6.861151342005925e-05, "loss": 1.1037, "step": 7267 }, { "epoch": 0.3973620365624466, "grad_norm": 2.402890682220459, "learning_rate": 6.860329579345988e-05, "loss": 0.9997, "step": 7268 }, { "epoch": 0.3974167093798052, "grad_norm": 2.4150068759918213, "learning_rate": 6.859507758357055e-05, "loss": 1.062, "step": 7269 }, { "epoch": 0.3974713821971638, "grad_norm": 2.6758804321289062, "learning_rate": 6.858685879064898e-05, "loss": 0.916, "step": 7270 }, { "epoch": 0.3975260550145225, "grad_norm": 2.7021756172180176, "learning_rate": 6.857863941495282e-05, "loss": 1.1185, "step": 7271 }, { "epoch": 0.3975807278318811, "grad_norm": 2.5552172660827637, "learning_rate": 6.857041945673983e-05, "loss": 0.9747, "step": 7272 }, { "epoch": 0.3976354006492397, "grad_norm": 2.344334602355957, "learning_rate": 6.856219891626768e-05, "loss": 1.0937, "step": 7273 }, { "epoch": 0.39769007346659835, "grad_norm": 2.624011278152466, "learning_rate": 6.855397779379415e-05, "loss": 1.1763, "step": 7274 }, { "epoch": 0.39774474628395695, "grad_norm": 3.4097180366516113, "learning_rate": 6.8545756089577e-05, "loss": 1.2034, "step": 7275 }, { "epoch": 0.39779941910131555, "grad_norm": 2.848004102706909, "learning_rate": 6.853753380387404e-05, "loss": 1.0663, "step": 7276 }, { "epoch": 0.39785409191867416, "grad_norm": 2.3168210983276367, "learning_rate": 6.852931093694303e-05, "loss": 0.9781, "step": 7277 }, { "epoch": 0.3979087647360328, "grad_norm": 2.1392321586608887, "learning_rate": 6.852108748904183e-05, "loss": 1.0037, "step": 7278 }, { "epoch": 0.3979634375533914, "grad_norm": 2.531346559524536, "learning_rate": 6.851286346042825e-05, "loss": 1.2629, "step": 7279 }, { "epoch": 0.39801811037075, "grad_norm": 3.6194868087768555, "learning_rate": 6.850463885136014e-05, "loss": 0.9733, "step": 7280 }, { "epoch": 0.3980727831881087, "grad_norm": 2.6368348598480225, "learning_rate": 6.84964136620954e-05, "loss": 0.8997, "step": 7281 }, { "epoch": 0.3981274560054673, "grad_norm": 2.736191987991333, "learning_rate": 6.848818789289192e-05, "loss": 1.2336, "step": 7282 }, { "epoch": 0.3981821288228259, "grad_norm": 2.6464145183563232, "learning_rate": 6.84799615440076e-05, "loss": 1.0764, "step": 7283 }, { "epoch": 0.39823680164018455, "grad_norm": 2.7341814041137695, "learning_rate": 6.84717346157004e-05, "loss": 1.1866, "step": 7284 }, { "epoch": 0.39829147445754315, "grad_norm": 1.9891682863235474, "learning_rate": 6.846350710822822e-05, "loss": 0.8567, "step": 7285 }, { "epoch": 0.39834614727490175, "grad_norm": 2.5006351470947266, "learning_rate": 6.845527902184906e-05, "loss": 1.0702, "step": 7286 }, { "epoch": 0.39840082009226035, "grad_norm": 2.4223105907440186, "learning_rate": 6.844705035682089e-05, "loss": 1.228, "step": 7287 }, { "epoch": 0.398455492909619, "grad_norm": 2.861370325088501, "learning_rate": 6.843882111340174e-05, "loss": 0.9633, "step": 7288 }, { "epoch": 0.3985101657269776, "grad_norm": 3.521036148071289, "learning_rate": 6.843059129184958e-05, "loss": 1.1718, "step": 7289 }, { "epoch": 0.3985648385443362, "grad_norm": 2.242499828338623, "learning_rate": 6.842236089242249e-05, "loss": 1.0114, "step": 7290 }, { "epoch": 0.3986195113616949, "grad_norm": 2.7196834087371826, "learning_rate": 6.841412991537852e-05, "loss": 1.0194, "step": 7291 }, { "epoch": 0.3986741841790535, "grad_norm": 2.076341390609741, "learning_rate": 6.840589836097574e-05, "loss": 0.9609, "step": 7292 }, { "epoch": 0.3987288569964121, "grad_norm": 2.1740005016326904, "learning_rate": 6.839766622947224e-05, "loss": 1.1275, "step": 7293 }, { "epoch": 0.39878352981377074, "grad_norm": 3.1683530807495117, "learning_rate": 6.838943352112614e-05, "loss": 1.192, "step": 7294 }, { "epoch": 0.39883820263112935, "grad_norm": 4.701442241668701, "learning_rate": 6.838120023619554e-05, "loss": 1.0551, "step": 7295 }, { "epoch": 0.39889287544848795, "grad_norm": 2.7499115467071533, "learning_rate": 6.837296637493864e-05, "loss": 1.2686, "step": 7296 }, { "epoch": 0.39894754826584655, "grad_norm": 2.7913761138916016, "learning_rate": 6.836473193761357e-05, "loss": 1.1205, "step": 7297 }, { "epoch": 0.3990022210832052, "grad_norm": 2.2948312759399414, "learning_rate": 6.83564969244785e-05, "loss": 0.9117, "step": 7298 }, { "epoch": 0.3990568939005638, "grad_norm": 1.993944764137268, "learning_rate": 6.834826133579166e-05, "loss": 0.9342, "step": 7299 }, { "epoch": 0.3991115667179224, "grad_norm": 2.508082389831543, "learning_rate": 6.834002517181128e-05, "loss": 0.8757, "step": 7300 }, { "epoch": 0.3991662395352811, "grad_norm": 2.396089553833008, "learning_rate": 6.833178843279557e-05, "loss": 1.1655, "step": 7301 }, { "epoch": 0.3992209123526397, "grad_norm": 2.6885344982147217, "learning_rate": 6.832355111900279e-05, "loss": 1.1287, "step": 7302 }, { "epoch": 0.3992755851699983, "grad_norm": 2.703552484512329, "learning_rate": 6.831531323069121e-05, "loss": 1.2416, "step": 7303 }, { "epoch": 0.3993302579873569, "grad_norm": 4.336801528930664, "learning_rate": 6.830707476811913e-05, "loss": 0.9878, "step": 7304 }, { "epoch": 0.39938493080471554, "grad_norm": 2.4244673252105713, "learning_rate": 6.829883573154487e-05, "loss": 0.9717, "step": 7305 }, { "epoch": 0.39943960362207415, "grad_norm": 3.2322819232940674, "learning_rate": 6.829059612122675e-05, "loss": 1.2531, "step": 7306 }, { "epoch": 0.39949427643943275, "grad_norm": 2.9456088542938232, "learning_rate": 6.828235593742311e-05, "loss": 0.8879, "step": 7307 }, { "epoch": 0.3995489492567914, "grad_norm": 2.7663397789001465, "learning_rate": 6.827411518039231e-05, "loss": 1.3291, "step": 7308 }, { "epoch": 0.39960362207415, "grad_norm": 2.4870195388793945, "learning_rate": 6.826587385039273e-05, "loss": 1.1697, "step": 7309 }, { "epoch": 0.3996582948915086, "grad_norm": 2.586211681365967, "learning_rate": 6.82576319476828e-05, "loss": 1.2256, "step": 7310 }, { "epoch": 0.3997129677088673, "grad_norm": 2.211925506591797, "learning_rate": 6.82493894725209e-05, "loss": 0.9608, "step": 7311 }, { "epoch": 0.3997676405262259, "grad_norm": 2.7090322971343994, "learning_rate": 6.82411464251655e-05, "loss": 1.0489, "step": 7312 }, { "epoch": 0.3998223133435845, "grad_norm": 2.5967679023742676, "learning_rate": 6.823290280587503e-05, "loss": 1.2268, "step": 7313 }, { "epoch": 0.3998769861609431, "grad_norm": 2.8070664405822754, "learning_rate": 6.822465861490795e-05, "loss": 0.9969, "step": 7314 }, { "epoch": 0.39993165897830174, "grad_norm": 1.9511903524398804, "learning_rate": 6.821641385252278e-05, "loss": 0.847, "step": 7315 }, { "epoch": 0.39998633179566034, "grad_norm": 2.2310738563537598, "learning_rate": 6.8208168518978e-05, "loss": 1.2147, "step": 7316 }, { "epoch": 0.40004100461301895, "grad_norm": 2.357914447784424, "learning_rate": 6.819992261453217e-05, "loss": 0.9942, "step": 7317 }, { "epoch": 0.4000956774303776, "grad_norm": 2.3835289478302, "learning_rate": 6.819167613944379e-05, "loss": 0.931, "step": 7318 }, { "epoch": 0.4001503502477362, "grad_norm": 2.465331792831421, "learning_rate": 6.818342909397144e-05, "loss": 0.9737, "step": 7319 }, { "epoch": 0.4002050230650948, "grad_norm": 2.382993221282959, "learning_rate": 6.81751814783737e-05, "loss": 1.064, "step": 7320 }, { "epoch": 0.40025969588245347, "grad_norm": 2.0947370529174805, "learning_rate": 6.816693329290918e-05, "loss": 1.0483, "step": 7321 }, { "epoch": 0.4003143686998121, "grad_norm": 2.101565361022949, "learning_rate": 6.815868453783648e-05, "loss": 0.976, "step": 7322 }, { "epoch": 0.4003690415171707, "grad_norm": 2.5673723220825195, "learning_rate": 6.815043521341423e-05, "loss": 1.0264, "step": 7323 }, { "epoch": 0.4004237143345293, "grad_norm": 2.3102619647979736, "learning_rate": 6.814218531990108e-05, "loss": 0.7002, "step": 7324 }, { "epoch": 0.40047838715188794, "grad_norm": 2.546765089035034, "learning_rate": 6.813393485755571e-05, "loss": 1.0866, "step": 7325 }, { "epoch": 0.40053305996924654, "grad_norm": 2.619220018386841, "learning_rate": 6.81256838266368e-05, "loss": 1.0478, "step": 7326 }, { "epoch": 0.40058773278660514, "grad_norm": 2.5734949111938477, "learning_rate": 6.811743222740305e-05, "loss": 1.1266, "step": 7327 }, { "epoch": 0.4006424056039638, "grad_norm": 2.760627508163452, "learning_rate": 6.81091800601132e-05, "loss": 0.9219, "step": 7328 }, { "epoch": 0.4006970784213224, "grad_norm": 2.9614577293395996, "learning_rate": 6.810092732502595e-05, "loss": 1.1639, "step": 7329 }, { "epoch": 0.400751751238681, "grad_norm": 2.440643787384033, "learning_rate": 6.809267402240009e-05, "loss": 1.0309, "step": 7330 }, { "epoch": 0.4008064240560396, "grad_norm": 2.836648464202881, "learning_rate": 6.808442015249439e-05, "loss": 1.1404, "step": 7331 }, { "epoch": 0.40086109687339827, "grad_norm": 2.7685739994049072, "learning_rate": 6.807616571556763e-05, "loss": 1.0883, "step": 7332 }, { "epoch": 0.4009157696907569, "grad_norm": 2.6261444091796875, "learning_rate": 6.806791071187863e-05, "loss": 1.1682, "step": 7333 }, { "epoch": 0.4009704425081155, "grad_norm": 2.058433771133423, "learning_rate": 6.805965514168621e-05, "loss": 1.0098, "step": 7334 }, { "epoch": 0.40102511532547414, "grad_norm": 3.3794198036193848, "learning_rate": 6.805139900524925e-05, "loss": 1.0265, "step": 7335 }, { "epoch": 0.40107978814283274, "grad_norm": 3.1570968627929688, "learning_rate": 6.804314230282659e-05, "loss": 0.9455, "step": 7336 }, { "epoch": 0.40113446096019134, "grad_norm": 4.787526607513428, "learning_rate": 6.803488503467708e-05, "loss": 0.9546, "step": 7337 }, { "epoch": 0.40118913377755, "grad_norm": 2.1899633407592773, "learning_rate": 6.802662720105966e-05, "loss": 1.0332, "step": 7338 }, { "epoch": 0.4012438065949086, "grad_norm": 2.638824701309204, "learning_rate": 6.801836880223324e-05, "loss": 1.2372, "step": 7339 }, { "epoch": 0.4012984794122672, "grad_norm": 2.808666467666626, "learning_rate": 6.801010983845675e-05, "loss": 1.1864, "step": 7340 }, { "epoch": 0.4013531522296258, "grad_norm": 2.42006778717041, "learning_rate": 6.800185030998913e-05, "loss": 1.0665, "step": 7341 }, { "epoch": 0.40140782504698447, "grad_norm": 2.572575330734253, "learning_rate": 6.799359021708938e-05, "loss": 1.1516, "step": 7342 }, { "epoch": 0.40146249786434307, "grad_norm": 3.0666894912719727, "learning_rate": 6.798532956001646e-05, "loss": 1.1179, "step": 7343 }, { "epoch": 0.4015171706817017, "grad_norm": 2.7279675006866455, "learning_rate": 6.79770683390294e-05, "loss": 1.1623, "step": 7344 }, { "epoch": 0.40157184349906033, "grad_norm": 2.7123188972473145, "learning_rate": 6.796880655438721e-05, "loss": 1.0807, "step": 7345 }, { "epoch": 0.40162651631641894, "grad_norm": 2.320052146911621, "learning_rate": 6.796054420634892e-05, "loss": 1.0638, "step": 7346 }, { "epoch": 0.40168118913377754, "grad_norm": 2.2822728157043457, "learning_rate": 6.795228129517359e-05, "loss": 1.0633, "step": 7347 }, { "epoch": 0.4017358619511362, "grad_norm": 3.2362680435180664, "learning_rate": 6.794401782112034e-05, "loss": 0.8854, "step": 7348 }, { "epoch": 0.4017905347684948, "grad_norm": 3.5136325359344482, "learning_rate": 6.793575378444821e-05, "loss": 1.2195, "step": 7349 }, { "epoch": 0.4018452075858534, "grad_norm": 2.6657474040985107, "learning_rate": 6.792748918541632e-05, "loss": 1.051, "step": 7350 }, { "epoch": 0.401899880403212, "grad_norm": 2.9260878562927246, "learning_rate": 6.791922402428384e-05, "loss": 1.2407, "step": 7351 }, { "epoch": 0.40195455322057067, "grad_norm": 2.645136594772339, "learning_rate": 6.791095830130987e-05, "loss": 1.0586, "step": 7352 }, { "epoch": 0.40200922603792927, "grad_norm": 2.159754514694214, "learning_rate": 6.790269201675358e-05, "loss": 1.0457, "step": 7353 }, { "epoch": 0.40206389885528787, "grad_norm": 2.4695885181427, "learning_rate": 6.789442517087417e-05, "loss": 0.7199, "step": 7354 }, { "epoch": 0.40211857167264653, "grad_norm": 2.5618224143981934, "learning_rate": 6.788615776393085e-05, "loss": 1.1646, "step": 7355 }, { "epoch": 0.40217324449000513, "grad_norm": 2.286104202270508, "learning_rate": 6.787788979618281e-05, "loss": 1.154, "step": 7356 }, { "epoch": 0.40222791730736374, "grad_norm": 2.921776533126831, "learning_rate": 6.78696212678893e-05, "loss": 1.0455, "step": 7357 }, { "epoch": 0.40228259012472234, "grad_norm": 2.3585963249206543, "learning_rate": 6.786135217930955e-05, "loss": 1.0191, "step": 7358 }, { "epoch": 0.402337262942081, "grad_norm": 2.621887683868408, "learning_rate": 6.785308253070288e-05, "loss": 1.1896, "step": 7359 }, { "epoch": 0.4023919357594396, "grad_norm": 2.7436447143554688, "learning_rate": 6.784481232232853e-05, "loss": 1.1841, "step": 7360 }, { "epoch": 0.4024466085767982, "grad_norm": 3.2181437015533447, "learning_rate": 6.783654155444584e-05, "loss": 0.9222, "step": 7361 }, { "epoch": 0.40250128139415686, "grad_norm": 2.7282066345214844, "learning_rate": 6.782827022731408e-05, "loss": 1.1524, "step": 7362 }, { "epoch": 0.40255595421151547, "grad_norm": 2.5475308895111084, "learning_rate": 6.781999834119264e-05, "loss": 1.0199, "step": 7363 }, { "epoch": 0.40261062702887407, "grad_norm": 3.2071921825408936, "learning_rate": 6.781172589634086e-05, "loss": 0.9966, "step": 7364 }, { "epoch": 0.4026652998462327, "grad_norm": 3.6690118312835693, "learning_rate": 6.780345289301812e-05, "loss": 1.0307, "step": 7365 }, { "epoch": 0.40271997266359133, "grad_norm": 2.2335121631622314, "learning_rate": 6.779517933148381e-05, "loss": 1.165, "step": 7366 }, { "epoch": 0.40277464548094993, "grad_norm": 2.2523438930511475, "learning_rate": 6.778690521199734e-05, "loss": 0.9642, "step": 7367 }, { "epoch": 0.40282931829830854, "grad_norm": 2.8648107051849365, "learning_rate": 6.777863053481812e-05, "loss": 1.1549, "step": 7368 }, { "epoch": 0.4028839911156672, "grad_norm": 1.9888899326324463, "learning_rate": 6.777035530020564e-05, "loss": 0.9267, "step": 7369 }, { "epoch": 0.4029386639330258, "grad_norm": 2.726148843765259, "learning_rate": 6.776207950841932e-05, "loss": 1.1582, "step": 7370 }, { "epoch": 0.4029933367503844, "grad_norm": 2.5715537071228027, "learning_rate": 6.775380315971866e-05, "loss": 1.0523, "step": 7371 }, { "epoch": 0.40304800956774306, "grad_norm": 2.378535509109497, "learning_rate": 6.774552625436315e-05, "loss": 1.1869, "step": 7372 }, { "epoch": 0.40310268238510166, "grad_norm": 2.3374409675598145, "learning_rate": 6.77372487926123e-05, "loss": 0.934, "step": 7373 }, { "epoch": 0.40315735520246027, "grad_norm": 2.7272799015045166, "learning_rate": 6.772897077472566e-05, "loss": 0.9767, "step": 7374 }, { "epoch": 0.40321202801981887, "grad_norm": 2.4521484375, "learning_rate": 6.772069220096278e-05, "loss": 1.0952, "step": 7375 }, { "epoch": 0.4032667008371775, "grad_norm": 2.6264917850494385, "learning_rate": 6.77124130715832e-05, "loss": 1.0615, "step": 7376 }, { "epoch": 0.40332137365453613, "grad_norm": 2.668576955795288, "learning_rate": 6.770413338684655e-05, "loss": 1.1142, "step": 7377 }, { "epoch": 0.40337604647189473, "grad_norm": 2.572714328765869, "learning_rate": 6.769585314701237e-05, "loss": 1.0427, "step": 7378 }, { "epoch": 0.4034307192892534, "grad_norm": 1.7523877620697021, "learning_rate": 6.768757235234033e-05, "loss": 0.8069, "step": 7379 }, { "epoch": 0.403485392106612, "grad_norm": 2.768277406692505, "learning_rate": 6.767929100309006e-05, "loss": 1.1149, "step": 7380 }, { "epoch": 0.4035400649239706, "grad_norm": 2.644855260848999, "learning_rate": 6.76710090995212e-05, "loss": 1.0273, "step": 7381 }, { "epoch": 0.40359473774132926, "grad_norm": 2.4302098751068115, "learning_rate": 6.766272664189344e-05, "loss": 1.1818, "step": 7382 }, { "epoch": 0.40364941055868786, "grad_norm": 3.1803834438323975, "learning_rate": 6.765444363046643e-05, "loss": 1.1889, "step": 7383 }, { "epoch": 0.40370408337604646, "grad_norm": 2.425828218460083, "learning_rate": 6.764616006549991e-05, "loss": 1.0441, "step": 7384 }, { "epoch": 0.40375875619340507, "grad_norm": 2.6365015506744385, "learning_rate": 6.763787594725362e-05, "loss": 1.0265, "step": 7385 }, { "epoch": 0.4038134290107637, "grad_norm": 2.5279908180236816, "learning_rate": 6.762959127598726e-05, "loss": 1.0791, "step": 7386 }, { "epoch": 0.40386810182812233, "grad_norm": 2.3263282775878906, "learning_rate": 6.762130605196061e-05, "loss": 1.0199, "step": 7387 }, { "epoch": 0.40392277464548093, "grad_norm": 2.6573057174682617, "learning_rate": 6.761302027543344e-05, "loss": 1.1701, "step": 7388 }, { "epoch": 0.4039774474628396, "grad_norm": 2.430642604827881, "learning_rate": 6.760473394666555e-05, "loss": 0.8959, "step": 7389 }, { "epoch": 0.4040321202801982, "grad_norm": 2.645660877227783, "learning_rate": 6.759644706591675e-05, "loss": 1.1649, "step": 7390 }, { "epoch": 0.4040867930975568, "grad_norm": 2.417754888534546, "learning_rate": 6.758815963344687e-05, "loss": 1.1315, "step": 7391 }, { "epoch": 0.40414146591491545, "grad_norm": 3.0290913581848145, "learning_rate": 6.757987164951573e-05, "loss": 1.1754, "step": 7392 }, { "epoch": 0.40419613873227406, "grad_norm": 3.0262279510498047, "learning_rate": 6.757158311438323e-05, "loss": 1.3639, "step": 7393 }, { "epoch": 0.40425081154963266, "grad_norm": 2.392810106277466, "learning_rate": 6.756329402830922e-05, "loss": 1.1108, "step": 7394 }, { "epoch": 0.40430548436699126, "grad_norm": 2.418708324432373, "learning_rate": 6.755500439155362e-05, "loss": 1.0207, "step": 7395 }, { "epoch": 0.4043601571843499, "grad_norm": 2.442521333694458, "learning_rate": 6.754671420437632e-05, "loss": 1.1732, "step": 7396 }, { "epoch": 0.4044148300017085, "grad_norm": 2.395996332168579, "learning_rate": 6.753842346703729e-05, "loss": 1.0903, "step": 7397 }, { "epoch": 0.40446950281906713, "grad_norm": 2.2890524864196777, "learning_rate": 6.753013217979642e-05, "loss": 1.1321, "step": 7398 }, { "epoch": 0.4045241756364258, "grad_norm": 2.833624839782715, "learning_rate": 6.752184034291374e-05, "loss": 0.8651, "step": 7399 }, { "epoch": 0.4045788484537844, "grad_norm": 2.74930477142334, "learning_rate": 6.751354795664919e-05, "loss": 1.0865, "step": 7400 }, { "epoch": 0.404633521271143, "grad_norm": 2.4143378734588623, "learning_rate": 6.750525502126279e-05, "loss": 1.1675, "step": 7401 }, { "epoch": 0.4046881940885016, "grad_norm": 3.039175033569336, "learning_rate": 6.749696153701453e-05, "loss": 0.9153, "step": 7402 }, { "epoch": 0.40474286690586025, "grad_norm": 8.58753776550293, "learning_rate": 6.748866750416447e-05, "loss": 0.9979, "step": 7403 }, { "epoch": 0.40479753972321886, "grad_norm": 2.548912763595581, "learning_rate": 6.748037292297268e-05, "loss": 1.0535, "step": 7404 }, { "epoch": 0.40485221254057746, "grad_norm": 2.2067787647247314, "learning_rate": 6.74720777936992e-05, "loss": 1.057, "step": 7405 }, { "epoch": 0.4049068853579361, "grad_norm": 2.484757423400879, "learning_rate": 6.746378211660411e-05, "loss": 0.9602, "step": 7406 }, { "epoch": 0.4049615581752947, "grad_norm": 2.9016358852386475, "learning_rate": 6.745548589194752e-05, "loss": 1.1514, "step": 7407 }, { "epoch": 0.4050162309926533, "grad_norm": 3.861582040786743, "learning_rate": 6.744718911998959e-05, "loss": 1.1757, "step": 7408 }, { "epoch": 0.405070903810012, "grad_norm": 2.804708242416382, "learning_rate": 6.74388918009904e-05, "loss": 1.1225, "step": 7409 }, { "epoch": 0.4051255766273706, "grad_norm": 4.853963851928711, "learning_rate": 6.743059393521015e-05, "loss": 1.1875, "step": 7410 }, { "epoch": 0.4051802494447292, "grad_norm": 2.407351493835449, "learning_rate": 6.742229552290898e-05, "loss": 0.8726, "step": 7411 }, { "epoch": 0.4052349222620878, "grad_norm": 2.431044578552246, "learning_rate": 6.741399656434709e-05, "loss": 1.1305, "step": 7412 }, { "epoch": 0.40528959507944645, "grad_norm": 2.180854558944702, "learning_rate": 6.74056970597847e-05, "loss": 0.8879, "step": 7413 }, { "epoch": 0.40534426789680505, "grad_norm": 2.2495124340057373, "learning_rate": 6.739739700948202e-05, "loss": 1.0325, "step": 7414 }, { "epoch": 0.40539894071416366, "grad_norm": 2.708627939224243, "learning_rate": 6.738909641369929e-05, "loss": 1.229, "step": 7415 }, { "epoch": 0.4054536135315223, "grad_norm": 3.097490072250366, "learning_rate": 6.738079527269679e-05, "loss": 1.0092, "step": 7416 }, { "epoch": 0.4055082863488809, "grad_norm": 2.5380406379699707, "learning_rate": 6.737249358673474e-05, "loss": 1.0929, "step": 7417 }, { "epoch": 0.4055629591662395, "grad_norm": 2.2940146923065186, "learning_rate": 6.73641913560735e-05, "loss": 0.8907, "step": 7418 }, { "epoch": 0.4056176319835982, "grad_norm": 2.6672708988189697, "learning_rate": 6.735588858097334e-05, "loss": 1.1404, "step": 7419 }, { "epoch": 0.4056723048009568, "grad_norm": 2.850397825241089, "learning_rate": 6.73475852616946e-05, "loss": 1.0415, "step": 7420 }, { "epoch": 0.4057269776183154, "grad_norm": 2.221389055252075, "learning_rate": 6.73392813984976e-05, "loss": 1.0889, "step": 7421 }, { "epoch": 0.405781650435674, "grad_norm": 3.3243918418884277, "learning_rate": 6.733097699164272e-05, "loss": 1.1606, "step": 7422 }, { "epoch": 0.40583632325303265, "grad_norm": 2.8247427940368652, "learning_rate": 6.732267204139033e-05, "loss": 1.053, "step": 7423 }, { "epoch": 0.40589099607039125, "grad_norm": 2.520341396331787, "learning_rate": 6.731436654800085e-05, "loss": 1.1737, "step": 7424 }, { "epoch": 0.40594566888774986, "grad_norm": 2.4573564529418945, "learning_rate": 6.730606051173466e-05, "loss": 1.046, "step": 7425 }, { "epoch": 0.4060003417051085, "grad_norm": 2.726163864135742, "learning_rate": 6.72977539328522e-05, "loss": 1.2233, "step": 7426 }, { "epoch": 0.4060550145224671, "grad_norm": 3.4148762226104736, "learning_rate": 6.728944681161392e-05, "loss": 1.1992, "step": 7427 }, { "epoch": 0.4061096873398257, "grad_norm": 2.5379111766815186, "learning_rate": 6.728113914828027e-05, "loss": 0.9689, "step": 7428 }, { "epoch": 0.4061643601571843, "grad_norm": 2.7907071113586426, "learning_rate": 6.727283094311172e-05, "loss": 1.068, "step": 7429 }, { "epoch": 0.406219032974543, "grad_norm": 2.6242003440856934, "learning_rate": 6.726452219636881e-05, "loss": 1.1363, "step": 7430 }, { "epoch": 0.4062737057919016, "grad_norm": 3.849083423614502, "learning_rate": 6.725621290831203e-05, "loss": 1.196, "step": 7431 }, { "epoch": 0.4063283786092602, "grad_norm": 3.069064140319824, "learning_rate": 6.724790307920189e-05, "loss": 1.1315, "step": 7432 }, { "epoch": 0.40638305142661885, "grad_norm": 2.732670307159424, "learning_rate": 6.723959270929896e-05, "loss": 0.8693, "step": 7433 }, { "epoch": 0.40643772424397745, "grad_norm": 2.1306920051574707, "learning_rate": 6.723128179886379e-05, "loss": 1.0268, "step": 7434 }, { "epoch": 0.40649239706133605, "grad_norm": 2.3918914794921875, "learning_rate": 6.722297034815698e-05, "loss": 1.1346, "step": 7435 }, { "epoch": 0.4065470698786947, "grad_norm": 2.762876272201538, "learning_rate": 6.721465835743912e-05, "loss": 1.1543, "step": 7436 }, { "epoch": 0.4066017426960533, "grad_norm": 2.7344417572021484, "learning_rate": 6.720634582697081e-05, "loss": 1.0375, "step": 7437 }, { "epoch": 0.4066564155134119, "grad_norm": 2.594611644744873, "learning_rate": 6.719803275701271e-05, "loss": 1.1014, "step": 7438 }, { "epoch": 0.4067110883307705, "grad_norm": 5.073651313781738, "learning_rate": 6.718971914782545e-05, "loss": 1.1714, "step": 7439 }, { "epoch": 0.4067657611481292, "grad_norm": 2.4619925022125244, "learning_rate": 6.71814049996697e-05, "loss": 1.0104, "step": 7440 }, { "epoch": 0.4068204339654878, "grad_norm": 2.643251657485962, "learning_rate": 6.717309031280613e-05, "loss": 1.0652, "step": 7441 }, { "epoch": 0.4068751067828464, "grad_norm": 2.3600475788116455, "learning_rate": 6.716477508749547e-05, "loss": 0.9078, "step": 7442 }, { "epoch": 0.40692977960020504, "grad_norm": 3.09794545173645, "learning_rate": 6.715645932399841e-05, "loss": 1.1608, "step": 7443 }, { "epoch": 0.40698445241756365, "grad_norm": 2.496309757232666, "learning_rate": 6.714814302257569e-05, "loss": 1.1107, "step": 7444 }, { "epoch": 0.40703912523492225, "grad_norm": 2.551112174987793, "learning_rate": 6.713982618348807e-05, "loss": 1.1128, "step": 7445 }, { "epoch": 0.4070937980522809, "grad_norm": 2.335660457611084, "learning_rate": 6.713150880699631e-05, "loss": 1.2116, "step": 7446 }, { "epoch": 0.4071484708696395, "grad_norm": 2.2631282806396484, "learning_rate": 6.712319089336119e-05, "loss": 1.1882, "step": 7447 }, { "epoch": 0.4072031436869981, "grad_norm": 2.7824909687042236, "learning_rate": 6.711487244284351e-05, "loss": 0.9512, "step": 7448 }, { "epoch": 0.4072578165043567, "grad_norm": 3.371596097946167, "learning_rate": 6.710655345570411e-05, "loss": 0.8539, "step": 7449 }, { "epoch": 0.4073124893217154, "grad_norm": 2.425680637359619, "learning_rate": 6.70982339322038e-05, "loss": 1.166, "step": 7450 }, { "epoch": 0.407367162139074, "grad_norm": 3.094066858291626, "learning_rate": 6.708991387260343e-05, "loss": 1.1442, "step": 7451 }, { "epoch": 0.4074218349564326, "grad_norm": 2.7114100456237793, "learning_rate": 6.708159327716386e-05, "loss": 1.1704, "step": 7452 }, { "epoch": 0.40747650777379124, "grad_norm": 2.6875951290130615, "learning_rate": 6.707327214614602e-05, "loss": 0.8743, "step": 7453 }, { "epoch": 0.40753118059114984, "grad_norm": 2.9922220706939697, "learning_rate": 6.706495047981078e-05, "loss": 1.3206, "step": 7454 }, { "epoch": 0.40758585340850845, "grad_norm": 2.8131039142608643, "learning_rate": 6.705662827841905e-05, "loss": 0.9894, "step": 7455 }, { "epoch": 0.40764052622586705, "grad_norm": 2.362309217453003, "learning_rate": 6.704830554223179e-05, "loss": 1.139, "step": 7456 }, { "epoch": 0.4076951990432257, "grad_norm": 2.3006765842437744, "learning_rate": 6.703998227150992e-05, "loss": 1.1436, "step": 7457 }, { "epoch": 0.4077498718605843, "grad_norm": 2.7143795490264893, "learning_rate": 6.703165846651444e-05, "loss": 1.2087, "step": 7458 }, { "epoch": 0.4078045446779429, "grad_norm": 2.032888412475586, "learning_rate": 6.702333412750631e-05, "loss": 1.0722, "step": 7459 }, { "epoch": 0.4078592174953016, "grad_norm": 2.5678136348724365, "learning_rate": 6.701500925474658e-05, "loss": 1.1146, "step": 7460 }, { "epoch": 0.4079138903126602, "grad_norm": 1.8588414192199707, "learning_rate": 6.70066838484962e-05, "loss": 0.9028, "step": 7461 }, { "epoch": 0.4079685631300188, "grad_norm": 2.143970489501953, "learning_rate": 6.699835790901626e-05, "loss": 0.9582, "step": 7462 }, { "epoch": 0.40802323594737744, "grad_norm": 2.4554128646850586, "learning_rate": 6.699003143656779e-05, "loss": 1.1292, "step": 7463 }, { "epoch": 0.40807790876473604, "grad_norm": 2.3618993759155273, "learning_rate": 6.698170443141186e-05, "loss": 0.9293, "step": 7464 }, { "epoch": 0.40813258158209464, "grad_norm": 2.6181015968322754, "learning_rate": 6.697337689380956e-05, "loss": 1.0969, "step": 7465 }, { "epoch": 0.40818725439945325, "grad_norm": 2.3917391300201416, "learning_rate": 6.696504882402198e-05, "loss": 0.8753, "step": 7466 }, { "epoch": 0.4082419272168119, "grad_norm": 3.3657801151275635, "learning_rate": 6.695672022231026e-05, "loss": 1.1717, "step": 7467 }, { "epoch": 0.4082966000341705, "grad_norm": 2.285207509994507, "learning_rate": 6.694839108893552e-05, "loss": 1.1393, "step": 7468 }, { "epoch": 0.4083512728515291, "grad_norm": 2.5754945278167725, "learning_rate": 6.694006142415892e-05, "loss": 1.1238, "step": 7469 }, { "epoch": 0.40840594566888777, "grad_norm": 1.845628261566162, "learning_rate": 6.693173122824164e-05, "loss": 1.051, "step": 7470 }, { "epoch": 0.4084606184862464, "grad_norm": 2.941554307937622, "learning_rate": 6.692340050144483e-05, "loss": 1.1034, "step": 7471 }, { "epoch": 0.408515291303605, "grad_norm": 2.502185106277466, "learning_rate": 6.691506924402973e-05, "loss": 1.1879, "step": 7472 }, { "epoch": 0.40856996412096364, "grad_norm": 2.8441104888916016, "learning_rate": 6.690673745625755e-05, "loss": 1.2414, "step": 7473 }, { "epoch": 0.40862463693832224, "grad_norm": 2.9468746185302734, "learning_rate": 6.689840513838952e-05, "loss": 0.9496, "step": 7474 }, { "epoch": 0.40867930975568084, "grad_norm": 2.6717276573181152, "learning_rate": 6.68900722906869e-05, "loss": 1.2139, "step": 7475 }, { "epoch": 0.40873398257303944, "grad_norm": 2.750361919403076, "learning_rate": 6.688173891341094e-05, "loss": 0.9932, "step": 7476 }, { "epoch": 0.4087886553903981, "grad_norm": 2.4219284057617188, "learning_rate": 6.687340500682294e-05, "loss": 1.0299, "step": 7477 }, { "epoch": 0.4088433282077567, "grad_norm": 2.2599070072174072, "learning_rate": 6.686507057118421e-05, "loss": 1.1973, "step": 7478 }, { "epoch": 0.4088980010251153, "grad_norm": 2.3509621620178223, "learning_rate": 6.685673560675605e-05, "loss": 0.9663, "step": 7479 }, { "epoch": 0.40895267384247397, "grad_norm": 2.9187285900115967, "learning_rate": 6.684840011379982e-05, "loss": 1.1192, "step": 7480 }, { "epoch": 0.40900734665983257, "grad_norm": 2.343066692352295, "learning_rate": 6.684006409257683e-05, "loss": 1.0788, "step": 7481 }, { "epoch": 0.4090620194771912, "grad_norm": 3.262542247772217, "learning_rate": 6.68317275433485e-05, "loss": 1.1431, "step": 7482 }, { "epoch": 0.4091166922945498, "grad_norm": 2.1021101474761963, "learning_rate": 6.682339046637619e-05, "loss": 0.954, "step": 7483 }, { "epoch": 0.40917136511190844, "grad_norm": 3.1988649368286133, "learning_rate": 6.681505286192129e-05, "loss": 1.0035, "step": 7484 }, { "epoch": 0.40922603792926704, "grad_norm": 2.4684133529663086, "learning_rate": 6.680671473024524e-05, "loss": 1.2669, "step": 7485 }, { "epoch": 0.40928071074662564, "grad_norm": 2.79154634475708, "learning_rate": 6.679837607160946e-05, "loss": 1.1183, "step": 7486 }, { "epoch": 0.4093353835639843, "grad_norm": 2.174065351486206, "learning_rate": 6.679003688627541e-05, "loss": 1.1204, "step": 7487 }, { "epoch": 0.4093900563813429, "grad_norm": 2.2293412685394287, "learning_rate": 6.678169717450457e-05, "loss": 0.928, "step": 7488 }, { "epoch": 0.4094447291987015, "grad_norm": 2.8242900371551514, "learning_rate": 6.67733569365584e-05, "loss": 1.057, "step": 7489 }, { "epoch": 0.40949940201606017, "grad_norm": 2.276026725769043, "learning_rate": 6.676501617269841e-05, "loss": 1.0162, "step": 7490 }, { "epoch": 0.40955407483341877, "grad_norm": 2.4911696910858154, "learning_rate": 6.675667488318609e-05, "loss": 1.1157, "step": 7491 }, { "epoch": 0.40960874765077737, "grad_norm": 2.0207479000091553, "learning_rate": 6.674833306828303e-05, "loss": 1.0549, "step": 7492 }, { "epoch": 0.409663420468136, "grad_norm": 2.351156234741211, "learning_rate": 6.673999072825074e-05, "loss": 1.0623, "step": 7493 }, { "epoch": 0.40971809328549463, "grad_norm": 2.898134469985962, "learning_rate": 6.673164786335083e-05, "loss": 1.0547, "step": 7494 }, { "epoch": 0.40977276610285324, "grad_norm": 2.5849783420562744, "learning_rate": 6.672330447384482e-05, "loss": 1.1463, "step": 7495 }, { "epoch": 0.40982743892021184, "grad_norm": 2.5754904747009277, "learning_rate": 6.671496055999434e-05, "loss": 1.135, "step": 7496 }, { "epoch": 0.4098821117375705, "grad_norm": 2.160137414932251, "learning_rate": 6.670661612206101e-05, "loss": 0.8481, "step": 7497 }, { "epoch": 0.4099367845549291, "grad_norm": 2.1692800521850586, "learning_rate": 6.669827116030647e-05, "loss": 1.0666, "step": 7498 }, { "epoch": 0.4099914573722877, "grad_norm": 2.9147143363952637, "learning_rate": 6.668992567499234e-05, "loss": 1.0625, "step": 7499 }, { "epoch": 0.41004613018964636, "grad_norm": 2.269228219985962, "learning_rate": 6.668157966638032e-05, "loss": 0.98, "step": 7500 }, { "epoch": 0.41010080300700497, "grad_norm": 3.3369052410125732, "learning_rate": 6.667323313473206e-05, "loss": 0.91, "step": 7501 }, { "epoch": 0.41015547582436357, "grad_norm": 2.282264471054077, "learning_rate": 6.66648860803093e-05, "loss": 0.952, "step": 7502 }, { "epoch": 0.41021014864172217, "grad_norm": 1.9253196716308594, "learning_rate": 6.665653850337371e-05, "loss": 0.9952, "step": 7503 }, { "epoch": 0.41026482145908083, "grad_norm": 2.3795621395111084, "learning_rate": 6.664819040418704e-05, "loss": 1.1748, "step": 7504 }, { "epoch": 0.41031949427643943, "grad_norm": 5.131730079650879, "learning_rate": 6.663984178301104e-05, "loss": 1.0289, "step": 7505 }, { "epoch": 0.41037416709379804, "grad_norm": 2.2945756912231445, "learning_rate": 6.663149264010747e-05, "loss": 0.913, "step": 7506 }, { "epoch": 0.4104288399111567, "grad_norm": 2.1165709495544434, "learning_rate": 6.66231429757381e-05, "loss": 1.0931, "step": 7507 }, { "epoch": 0.4104835127285153, "grad_norm": 2.6497888565063477, "learning_rate": 6.661479279016474e-05, "loss": 1.2058, "step": 7508 }, { "epoch": 0.4105381855458739, "grad_norm": 2.4232730865478516, "learning_rate": 6.660644208364921e-05, "loss": 0.9668, "step": 7509 }, { "epoch": 0.4105928583632325, "grad_norm": 3.71443247795105, "learning_rate": 6.659809085645332e-05, "loss": 1.0227, "step": 7510 }, { "epoch": 0.41064753118059116, "grad_norm": 2.704176425933838, "learning_rate": 6.658973910883892e-05, "loss": 1.0963, "step": 7511 }, { "epoch": 0.41070220399794977, "grad_norm": 2.396998643875122, "learning_rate": 6.658138684106789e-05, "loss": 1.1419, "step": 7512 }, { "epoch": 0.41075687681530837, "grad_norm": 3.0064573287963867, "learning_rate": 6.657303405340208e-05, "loss": 1.0885, "step": 7513 }, { "epoch": 0.41081154963266703, "grad_norm": 2.6292335987091064, "learning_rate": 6.65646807461034e-05, "loss": 1.2906, "step": 7514 }, { "epoch": 0.41086622245002563, "grad_norm": 2.2747349739074707, "learning_rate": 6.655632691943376e-05, "loss": 1.0616, "step": 7515 }, { "epoch": 0.41092089526738423, "grad_norm": 3.0590546131134033, "learning_rate": 6.654797257365509e-05, "loss": 0.9493, "step": 7516 }, { "epoch": 0.4109755680847429, "grad_norm": 2.9426591396331787, "learning_rate": 6.653961770902932e-05, "loss": 1.054, "step": 7517 }, { "epoch": 0.4110302409021015, "grad_norm": 3.4942548274993896, "learning_rate": 6.653126232581842e-05, "loss": 0.9886, "step": 7518 }, { "epoch": 0.4110849137194601, "grad_norm": 2.5205655097961426, "learning_rate": 6.652290642428437e-05, "loss": 1.0376, "step": 7519 }, { "epoch": 0.4111395865368187, "grad_norm": 2.6883952617645264, "learning_rate": 6.651455000468915e-05, "loss": 1.2932, "step": 7520 }, { "epoch": 0.41119425935417736, "grad_norm": 2.8265292644500732, "learning_rate": 6.650619306729477e-05, "loss": 1.1381, "step": 7521 }, { "epoch": 0.41124893217153596, "grad_norm": 2.479696035385132, "learning_rate": 6.649783561236326e-05, "loss": 0.8946, "step": 7522 }, { "epoch": 0.41130360498889457, "grad_norm": 2.5395047664642334, "learning_rate": 6.648947764015667e-05, "loss": 1.0501, "step": 7523 }, { "epoch": 0.4113582778062532, "grad_norm": 2.6967906951904297, "learning_rate": 6.648111915093702e-05, "loss": 1.0465, "step": 7524 }, { "epoch": 0.41141295062361183, "grad_norm": 2.209543228149414, "learning_rate": 6.647276014496643e-05, "loss": 1.0219, "step": 7525 }, { "epoch": 0.41146762344097043, "grad_norm": 2.837106227874756, "learning_rate": 6.646440062250696e-05, "loss": 1.0197, "step": 7526 }, { "epoch": 0.41152229625832903, "grad_norm": 2.102069854736328, "learning_rate": 6.645604058382072e-05, "loss": 0.9532, "step": 7527 }, { "epoch": 0.4115769690756877, "grad_norm": 2.699594736099243, "learning_rate": 6.644768002916984e-05, "loss": 1.0727, "step": 7528 }, { "epoch": 0.4116316418930463, "grad_norm": 2.5331408977508545, "learning_rate": 6.643931895881645e-05, "loss": 1.0999, "step": 7529 }, { "epoch": 0.4116863147104049, "grad_norm": 2.6878294944763184, "learning_rate": 6.64309573730227e-05, "loss": 1.0174, "step": 7530 }, { "epoch": 0.41174098752776356, "grad_norm": 2.951995849609375, "learning_rate": 6.642259527205076e-05, "loss": 1.1851, "step": 7531 }, { "epoch": 0.41179566034512216, "grad_norm": 2.222425937652588, "learning_rate": 6.641423265616284e-05, "loss": 1.1088, "step": 7532 }, { "epoch": 0.41185033316248076, "grad_norm": 2.313154935836792, "learning_rate": 6.640586952562113e-05, "loss": 0.9588, "step": 7533 }, { "epoch": 0.4119050059798394, "grad_norm": 2.12235426902771, "learning_rate": 6.639750588068783e-05, "loss": 0.6522, "step": 7534 }, { "epoch": 0.411959678797198, "grad_norm": 2.693588972091675, "learning_rate": 6.638914172162519e-05, "loss": 1.2433, "step": 7535 }, { "epoch": 0.41201435161455663, "grad_norm": 2.6991050243377686, "learning_rate": 6.638077704869547e-05, "loss": 1.1431, "step": 7536 }, { "epoch": 0.41206902443191523, "grad_norm": 2.095311164855957, "learning_rate": 6.637241186216092e-05, "loss": 0.9471, "step": 7537 }, { "epoch": 0.4121236972492739, "grad_norm": 3.3739359378814697, "learning_rate": 6.636404616228384e-05, "loss": 1.1257, "step": 7538 }, { "epoch": 0.4121783700666325, "grad_norm": 2.6810319423675537, "learning_rate": 6.63556799493265e-05, "loss": 1.1254, "step": 7539 }, { "epoch": 0.4122330428839911, "grad_norm": 3.1729347705841064, "learning_rate": 6.634731322355123e-05, "loss": 0.8163, "step": 7540 }, { "epoch": 0.41228771570134976, "grad_norm": 2.833003520965576, "learning_rate": 6.633894598522037e-05, "loss": 0.9506, "step": 7541 }, { "epoch": 0.41234238851870836, "grad_norm": 2.127098560333252, "learning_rate": 6.633057823459627e-05, "loss": 0.9991, "step": 7542 }, { "epoch": 0.41239706133606696, "grad_norm": 2.5840468406677246, "learning_rate": 6.63222099719413e-05, "loss": 1.0699, "step": 7543 }, { "epoch": 0.4124517341534256, "grad_norm": 4.097865104675293, "learning_rate": 6.631384119751781e-05, "loss": 0.9584, "step": 7544 }, { "epoch": 0.4125064069707842, "grad_norm": 2.9609618186950684, "learning_rate": 6.63054719115882e-05, "loss": 0.9472, "step": 7545 }, { "epoch": 0.4125610797881428, "grad_norm": 3.3653502464294434, "learning_rate": 6.629710211441491e-05, "loss": 0.9647, "step": 7546 }, { "epoch": 0.41261575260550143, "grad_norm": 2.6781809329986572, "learning_rate": 6.628873180626034e-05, "loss": 1.0458, "step": 7547 }, { "epoch": 0.4126704254228601, "grad_norm": 2.233250617980957, "learning_rate": 6.628036098738695e-05, "loss": 0.9318, "step": 7548 }, { "epoch": 0.4127250982402187, "grad_norm": 2.213526964187622, "learning_rate": 6.62719896580572e-05, "loss": 1.0113, "step": 7549 }, { "epoch": 0.4127797710575773, "grad_norm": 2.2020044326782227, "learning_rate": 6.626361781853354e-05, "loss": 1.111, "step": 7550 }, { "epoch": 0.41283444387493595, "grad_norm": 2.296133518218994, "learning_rate": 6.625524546907849e-05, "loss": 1.0579, "step": 7551 }, { "epoch": 0.41288911669229456, "grad_norm": 2.9914603233337402, "learning_rate": 6.624687260995455e-05, "loss": 1.0893, "step": 7552 }, { "epoch": 0.41294378950965316, "grad_norm": 2.249143362045288, "learning_rate": 6.623849924142424e-05, "loss": 0.9995, "step": 7553 }, { "epoch": 0.41299846232701176, "grad_norm": 2.3736021518707275, "learning_rate": 6.623012536375011e-05, "loss": 0.9979, "step": 7554 }, { "epoch": 0.4130531351443704, "grad_norm": 2.6404507160186768, "learning_rate": 6.62217509771947e-05, "loss": 1.2229, "step": 7555 }, { "epoch": 0.413107807961729, "grad_norm": 2.1319172382354736, "learning_rate": 6.621337608202059e-05, "loss": 1.1247, "step": 7556 }, { "epoch": 0.4131624807790876, "grad_norm": 2.697829246520996, "learning_rate": 6.620500067849035e-05, "loss": 1.0108, "step": 7557 }, { "epoch": 0.4132171535964463, "grad_norm": 2.8955533504486084, "learning_rate": 6.619662476686663e-05, "loss": 1.1769, "step": 7558 }, { "epoch": 0.4132718264138049, "grad_norm": 2.4622652530670166, "learning_rate": 6.6188248347412e-05, "loss": 1.1722, "step": 7559 }, { "epoch": 0.4133264992311635, "grad_norm": 2.107358694076538, "learning_rate": 6.617987142038911e-05, "loss": 1.0336, "step": 7560 }, { "epoch": 0.41338117204852215, "grad_norm": 2.2576217651367188, "learning_rate": 6.617149398606063e-05, "loss": 1.1554, "step": 7561 }, { "epoch": 0.41343584486588075, "grad_norm": 2.4507923126220703, "learning_rate": 6.616311604468921e-05, "loss": 1.1441, "step": 7562 }, { "epoch": 0.41349051768323936, "grad_norm": 2.429560661315918, "learning_rate": 6.615473759653754e-05, "loss": 1.1453, "step": 7563 }, { "epoch": 0.41354519050059796, "grad_norm": 2.126063346862793, "learning_rate": 6.614635864186829e-05, "loss": 0.9184, "step": 7564 }, { "epoch": 0.4135998633179566, "grad_norm": 2.5072524547576904, "learning_rate": 6.61379791809442e-05, "loss": 1.1729, "step": 7565 }, { "epoch": 0.4136545361353152, "grad_norm": 2.230412006378174, "learning_rate": 6.612959921402802e-05, "loss": 1.1589, "step": 7566 }, { "epoch": 0.4137092089526738, "grad_norm": 2.8983497619628906, "learning_rate": 6.612121874138248e-05, "loss": 1.2109, "step": 7567 }, { "epoch": 0.4137638817700325, "grad_norm": 3.3700857162475586, "learning_rate": 6.611283776327033e-05, "loss": 1.2013, "step": 7568 }, { "epoch": 0.4138185545873911, "grad_norm": 3.2291245460510254, "learning_rate": 6.610445627995435e-05, "loss": 1.1191, "step": 7569 }, { "epoch": 0.4138732274047497, "grad_norm": 2.495758533477783, "learning_rate": 6.609607429169735e-05, "loss": 0.9814, "step": 7570 }, { "epoch": 0.41392790022210835, "grad_norm": 2.9884517192840576, "learning_rate": 6.608769179876212e-05, "loss": 1.0517, "step": 7571 }, { "epoch": 0.41398257303946695, "grad_norm": 2.2221100330352783, "learning_rate": 6.60793088014115e-05, "loss": 1.0457, "step": 7572 }, { "epoch": 0.41403724585682555, "grad_norm": 2.972177505493164, "learning_rate": 6.607092529990833e-05, "loss": 1.1802, "step": 7573 }, { "epoch": 0.41409191867418416, "grad_norm": 2.4274191856384277, "learning_rate": 6.606254129451546e-05, "loss": 1.1153, "step": 7574 }, { "epoch": 0.4141465914915428, "grad_norm": 2.581024408340454, "learning_rate": 6.605415678549577e-05, "loss": 1.0233, "step": 7575 }, { "epoch": 0.4142012643089014, "grad_norm": 2.707622528076172, "learning_rate": 6.604577177311216e-05, "loss": 0.7904, "step": 7576 }, { "epoch": 0.41425593712626, "grad_norm": 2.855686902999878, "learning_rate": 6.60373862576275e-05, "loss": 1.0452, "step": 7577 }, { "epoch": 0.4143106099436187, "grad_norm": 2.8915088176727295, "learning_rate": 6.602900023930475e-05, "loss": 1.1861, "step": 7578 }, { "epoch": 0.4143652827609773, "grad_norm": 2.739668369293213, "learning_rate": 6.60206137184068e-05, "loss": 1.1158, "step": 7579 }, { "epoch": 0.4144199555783359, "grad_norm": 2.1636786460876465, "learning_rate": 6.601222669519666e-05, "loss": 1.0675, "step": 7580 }, { "epoch": 0.4144746283956945, "grad_norm": 2.3891425132751465, "learning_rate": 6.600383916993726e-05, "loss": 0.9622, "step": 7581 }, { "epoch": 0.41452930121305315, "grad_norm": 1.9704372882843018, "learning_rate": 6.599545114289159e-05, "loss": 0.9573, "step": 7582 }, { "epoch": 0.41458397403041175, "grad_norm": 2.8858511447906494, "learning_rate": 6.598706261432265e-05, "loss": 1.1406, "step": 7583 }, { "epoch": 0.41463864684777035, "grad_norm": 2.7331442832946777, "learning_rate": 6.597867358449345e-05, "loss": 0.9771, "step": 7584 }, { "epoch": 0.414693319665129, "grad_norm": 3.1792495250701904, "learning_rate": 6.597028405366703e-05, "loss": 1.0922, "step": 7585 }, { "epoch": 0.4147479924824876, "grad_norm": 2.1961898803710938, "learning_rate": 6.596189402210644e-05, "loss": 1.0668, "step": 7586 }, { "epoch": 0.4148026652998462, "grad_norm": 2.7108829021453857, "learning_rate": 6.595350349007473e-05, "loss": 1.2406, "step": 7587 }, { "epoch": 0.4148573381172049, "grad_norm": 2.0562150478363037, "learning_rate": 6.594511245783498e-05, "loss": 0.9776, "step": 7588 }, { "epoch": 0.4149120109345635, "grad_norm": 2.3481991291046143, "learning_rate": 6.593672092565029e-05, "loss": 1.2258, "step": 7589 }, { "epoch": 0.4149666837519221, "grad_norm": 3.2018797397613525, "learning_rate": 6.592832889378376e-05, "loss": 1.151, "step": 7590 }, { "epoch": 0.4150213565692807, "grad_norm": 2.265977621078491, "learning_rate": 6.591993636249851e-05, "loss": 0.8972, "step": 7591 }, { "epoch": 0.41507602938663934, "grad_norm": 2.6215622425079346, "learning_rate": 6.591154333205772e-05, "loss": 1.1606, "step": 7592 }, { "epoch": 0.41513070220399795, "grad_norm": 2.8104019165039062, "learning_rate": 6.590314980272449e-05, "loss": 1.1792, "step": 7593 }, { "epoch": 0.41518537502135655, "grad_norm": 2.7762746810913086, "learning_rate": 6.5894755774762e-05, "loss": 1.1667, "step": 7594 }, { "epoch": 0.4152400478387152, "grad_norm": 2.193875551223755, "learning_rate": 6.58863612484335e-05, "loss": 1.0143, "step": 7595 }, { "epoch": 0.4152947206560738, "grad_norm": 3.0219531059265137, "learning_rate": 6.587796622400211e-05, "loss": 1.2168, "step": 7596 }, { "epoch": 0.4153493934734324, "grad_norm": 2.4990155696868896, "learning_rate": 6.586957070173111e-05, "loss": 1.3127, "step": 7597 }, { "epoch": 0.4154040662907911, "grad_norm": 2.4748923778533936, "learning_rate": 6.58611746818837e-05, "loss": 1.085, "step": 7598 }, { "epoch": 0.4154587391081497, "grad_norm": 2.877659559249878, "learning_rate": 6.585277816472315e-05, "loss": 1.2941, "step": 7599 }, { "epoch": 0.4155134119255083, "grad_norm": 3.164531707763672, "learning_rate": 6.58443811505127e-05, "loss": 1.3164, "step": 7600 }, { "epoch": 0.4155680847428669, "grad_norm": 2.1733171939849854, "learning_rate": 6.583598363951566e-05, "loss": 0.8701, "step": 7601 }, { "epoch": 0.41562275756022554, "grad_norm": 3.9352099895477295, "learning_rate": 6.582758563199531e-05, "loss": 1.2569, "step": 7602 }, { "epoch": 0.41567743037758415, "grad_norm": 2.7439963817596436, "learning_rate": 6.581918712821497e-05, "loss": 0.9305, "step": 7603 }, { "epoch": 0.41573210319494275, "grad_norm": 3.8698525428771973, "learning_rate": 6.581078812843797e-05, "loss": 1.0251, "step": 7604 }, { "epoch": 0.4157867760123014, "grad_norm": 3.089890718460083, "learning_rate": 6.580238863292763e-05, "loss": 1.2069, "step": 7605 }, { "epoch": 0.41584144882966, "grad_norm": 2.37483286857605, "learning_rate": 6.579398864194732e-05, "loss": 0.948, "step": 7606 }, { "epoch": 0.4158961216470186, "grad_norm": 2.5325376987457275, "learning_rate": 6.578558815576044e-05, "loss": 1.0331, "step": 7607 }, { "epoch": 0.4159507944643772, "grad_norm": 2.5252654552459717, "learning_rate": 6.577718717463035e-05, "loss": 1.1907, "step": 7608 }, { "epoch": 0.4160054672817359, "grad_norm": 2.264896869659424, "learning_rate": 6.576878569882046e-05, "loss": 1.0282, "step": 7609 }, { "epoch": 0.4160601400990945, "grad_norm": 2.9700050354003906, "learning_rate": 6.576038372859421e-05, "loss": 1.058, "step": 7610 }, { "epoch": 0.4161148129164531, "grad_norm": 2.6610429286956787, "learning_rate": 6.575198126421501e-05, "loss": 1.2481, "step": 7611 }, { "epoch": 0.41616948573381174, "grad_norm": 2.5123684406280518, "learning_rate": 6.574357830594633e-05, "loss": 0.8127, "step": 7612 }, { "epoch": 0.41622415855117034, "grad_norm": 2.5666699409484863, "learning_rate": 6.573517485405163e-05, "loss": 1.0312, "step": 7613 }, { "epoch": 0.41627883136852895, "grad_norm": 2.079802989959717, "learning_rate": 6.57267709087944e-05, "loss": 0.8927, "step": 7614 }, { "epoch": 0.4163335041858876, "grad_norm": 2.832080125808716, "learning_rate": 6.571836647043811e-05, "loss": 1.1696, "step": 7615 }, { "epoch": 0.4163881770032462, "grad_norm": 2.464066505432129, "learning_rate": 6.570996153924631e-05, "loss": 1.1244, "step": 7616 }, { "epoch": 0.4164428498206048, "grad_norm": 4.220026969909668, "learning_rate": 6.570155611548252e-05, "loss": 1.2248, "step": 7617 }, { "epoch": 0.4164975226379634, "grad_norm": 3.4710161685943604, "learning_rate": 6.569315019941028e-05, "loss": 0.993, "step": 7618 }, { "epoch": 0.41655219545532207, "grad_norm": 2.2896687984466553, "learning_rate": 6.568474379129314e-05, "loss": 1.0066, "step": 7619 }, { "epoch": 0.4166068682726807, "grad_norm": 2.4332873821258545, "learning_rate": 6.567633689139469e-05, "loss": 0.9763, "step": 7620 }, { "epoch": 0.4166615410900393, "grad_norm": 2.1996657848358154, "learning_rate": 6.566792949997853e-05, "loss": 0.9112, "step": 7621 }, { "epoch": 0.41671621390739794, "grad_norm": 3.4634833335876465, "learning_rate": 6.565952161730824e-05, "loss": 1.3938, "step": 7622 }, { "epoch": 0.41677088672475654, "grad_norm": 2.213341474533081, "learning_rate": 6.565111324364745e-05, "loss": 1.0311, "step": 7623 }, { "epoch": 0.41682555954211514, "grad_norm": 2.103454113006592, "learning_rate": 6.564270437925981e-05, "loss": 1.0972, "step": 7624 }, { "epoch": 0.4168802323594738, "grad_norm": 3.3994393348693848, "learning_rate": 6.563429502440897e-05, "loss": 1.0683, "step": 7625 }, { "epoch": 0.4169349051768324, "grad_norm": 2.651750326156616, "learning_rate": 6.562588517935859e-05, "loss": 1.0031, "step": 7626 }, { "epoch": 0.416989577994191, "grad_norm": 2.4113872051239014, "learning_rate": 6.561747484437235e-05, "loss": 1.012, "step": 7627 }, { "epoch": 0.4170442508115496, "grad_norm": 2.649198532104492, "learning_rate": 6.560906401971394e-05, "loss": 1.1036, "step": 7628 }, { "epoch": 0.41709892362890827, "grad_norm": 2.6028804779052734, "learning_rate": 6.560065270564711e-05, "loss": 1.2461, "step": 7629 }, { "epoch": 0.41715359644626687, "grad_norm": 3.70377516746521, "learning_rate": 6.559224090243555e-05, "loss": 1.13, "step": 7630 }, { "epoch": 0.4172082692636255, "grad_norm": 3.817007541656494, "learning_rate": 6.558382861034304e-05, "loss": 0.9763, "step": 7631 }, { "epoch": 0.41726294208098413, "grad_norm": 2.731555700302124, "learning_rate": 6.557541582963331e-05, "loss": 1.0629, "step": 7632 }, { "epoch": 0.41731761489834274, "grad_norm": 2.415450096130371, "learning_rate": 6.556700256057014e-05, "loss": 1.0154, "step": 7633 }, { "epoch": 0.41737228771570134, "grad_norm": 2.460848331451416, "learning_rate": 6.555858880341736e-05, "loss": 0.9001, "step": 7634 }, { "epoch": 0.41742696053305994, "grad_norm": 3.12043833732605, "learning_rate": 6.555017455843872e-05, "loss": 0.9649, "step": 7635 }, { "epoch": 0.4174816333504186, "grad_norm": 1.6953612565994263, "learning_rate": 6.554175982589807e-05, "loss": 0.7661, "step": 7636 }, { "epoch": 0.4175363061677772, "grad_norm": 2.2965478897094727, "learning_rate": 6.553334460605925e-05, "loss": 1.0124, "step": 7637 }, { "epoch": 0.4175909789851358, "grad_norm": 2.4346365928649902, "learning_rate": 6.552492889918608e-05, "loss": 1.1032, "step": 7638 }, { "epoch": 0.41764565180249447, "grad_norm": 2.512260913848877, "learning_rate": 6.551651270554246e-05, "loss": 0.9615, "step": 7639 }, { "epoch": 0.41770032461985307, "grad_norm": 2.6209542751312256, "learning_rate": 6.550809602539228e-05, "loss": 0.9199, "step": 7640 }, { "epoch": 0.4177549974372117, "grad_norm": 2.0949840545654297, "learning_rate": 6.54996788589994e-05, "loss": 0.9633, "step": 7641 }, { "epoch": 0.41780967025457033, "grad_norm": 2.649453639984131, "learning_rate": 6.549126120662777e-05, "loss": 1.2211, "step": 7642 }, { "epoch": 0.41786434307192893, "grad_norm": 3.010263442993164, "learning_rate": 6.548284306854128e-05, "loss": 1.235, "step": 7643 }, { "epoch": 0.41791901588928754, "grad_norm": 2.0226707458496094, "learning_rate": 6.547442444500391e-05, "loss": 1.0394, "step": 7644 }, { "epoch": 0.41797368870664614, "grad_norm": 2.3660120964050293, "learning_rate": 6.54660053362796e-05, "loss": 1.0402, "step": 7645 }, { "epoch": 0.4180283615240048, "grad_norm": 4.170072078704834, "learning_rate": 6.545758574263233e-05, "loss": 1.079, "step": 7646 }, { "epoch": 0.4180830343413634, "grad_norm": 2.1128859519958496, "learning_rate": 6.544916566432608e-05, "loss": 1.012, "step": 7647 }, { "epoch": 0.418137707158722, "grad_norm": 2.313546657562256, "learning_rate": 6.544074510162487e-05, "loss": 0.9673, "step": 7648 }, { "epoch": 0.41819237997608066, "grad_norm": 2.573826789855957, "learning_rate": 6.543232405479269e-05, "loss": 0.8223, "step": 7649 }, { "epoch": 0.41824705279343927, "grad_norm": 2.4208145141601562, "learning_rate": 6.542390252409361e-05, "loss": 1.0267, "step": 7650 }, { "epoch": 0.41830172561079787, "grad_norm": 2.9267055988311768, "learning_rate": 6.541548050979167e-05, "loss": 1.0682, "step": 7651 }, { "epoch": 0.41835639842815653, "grad_norm": 3.306227445602417, "learning_rate": 6.540705801215093e-05, "loss": 1.2961, "step": 7652 }, { "epoch": 0.41841107124551513, "grad_norm": 2.3957345485687256, "learning_rate": 6.539863503143544e-05, "loss": 0.8557, "step": 7653 }, { "epoch": 0.41846574406287373, "grad_norm": 2.7979822158813477, "learning_rate": 6.539021156790935e-05, "loss": 1.2346, "step": 7654 }, { "epoch": 0.41852041688023234, "grad_norm": 3.216808795928955, "learning_rate": 6.538178762183673e-05, "loss": 1.0988, "step": 7655 }, { "epoch": 0.418575089697591, "grad_norm": 2.4328370094299316, "learning_rate": 6.537336319348173e-05, "loss": 0.9113, "step": 7656 }, { "epoch": 0.4186297625149496, "grad_norm": 3.2129597663879395, "learning_rate": 6.536493828310848e-05, "loss": 0.9714, "step": 7657 }, { "epoch": 0.4186844353323082, "grad_norm": 2.59220027923584, "learning_rate": 6.535651289098113e-05, "loss": 1.1942, "step": 7658 }, { "epoch": 0.41873910814966686, "grad_norm": 2.8590683937072754, "learning_rate": 6.534808701736384e-05, "loss": 1.153, "step": 7659 }, { "epoch": 0.41879378096702546, "grad_norm": 2.3482937812805176, "learning_rate": 6.533966066252084e-05, "loss": 1.1119, "step": 7660 }, { "epoch": 0.41884845378438407, "grad_norm": 3.182465076446533, "learning_rate": 6.533123382671629e-05, "loss": 0.971, "step": 7661 }, { "epoch": 0.41890312660174267, "grad_norm": 2.413954734802246, "learning_rate": 6.532280651021442e-05, "loss": 0.8918, "step": 7662 }, { "epoch": 0.41895779941910133, "grad_norm": 2.0537500381469727, "learning_rate": 6.531437871327945e-05, "loss": 0.9884, "step": 7663 }, { "epoch": 0.41901247223645993, "grad_norm": 2.25766658782959, "learning_rate": 6.530595043617564e-05, "loss": 1.0838, "step": 7664 }, { "epoch": 0.41906714505381853, "grad_norm": 2.459980010986328, "learning_rate": 6.529752167916727e-05, "loss": 1.1779, "step": 7665 }, { "epoch": 0.4191218178711772, "grad_norm": 2.538188934326172, "learning_rate": 6.528909244251857e-05, "loss": 0.9335, "step": 7666 }, { "epoch": 0.4191764906885358, "grad_norm": 2.9165258407592773, "learning_rate": 6.528066272649385e-05, "loss": 1.1257, "step": 7667 }, { "epoch": 0.4192311635058944, "grad_norm": 2.0920112133026123, "learning_rate": 6.527223253135743e-05, "loss": 0.8834, "step": 7668 }, { "epoch": 0.41928583632325306, "grad_norm": 2.161823272705078, "learning_rate": 6.526380185737365e-05, "loss": 0.9297, "step": 7669 }, { "epoch": 0.41934050914061166, "grad_norm": 2.3225696086883545, "learning_rate": 6.525537070480679e-05, "loss": 1.0305, "step": 7670 }, { "epoch": 0.41939518195797026, "grad_norm": 2.263427734375, "learning_rate": 6.524693907392124e-05, "loss": 1.0598, "step": 7671 }, { "epoch": 0.41944985477532887, "grad_norm": 2.180983066558838, "learning_rate": 6.523850696498132e-05, "loss": 0.919, "step": 7672 }, { "epoch": 0.4195045275926875, "grad_norm": 2.211033344268799, "learning_rate": 6.52300743782515e-05, "loss": 1.0501, "step": 7673 }, { "epoch": 0.41955920041004613, "grad_norm": 2.3840019702911377, "learning_rate": 6.52216413139961e-05, "loss": 1.0561, "step": 7674 }, { "epoch": 0.41961387322740473, "grad_norm": 2.8664093017578125, "learning_rate": 6.521320777247956e-05, "loss": 1.0995, "step": 7675 }, { "epoch": 0.4196685460447634, "grad_norm": 2.3853914737701416, "learning_rate": 6.52047737539663e-05, "loss": 1.0259, "step": 7676 }, { "epoch": 0.419723218862122, "grad_norm": 2.6360230445861816, "learning_rate": 6.519633925872076e-05, "loss": 1.0089, "step": 7677 }, { "epoch": 0.4197778916794806, "grad_norm": 3.0023257732391357, "learning_rate": 6.51879042870074e-05, "loss": 1.0739, "step": 7678 }, { "epoch": 0.4198325644968392, "grad_norm": 2.0296876430511475, "learning_rate": 6.51794688390907e-05, "loss": 0.9413, "step": 7679 }, { "epoch": 0.41988723731419786, "grad_norm": 2.681100845336914, "learning_rate": 6.517103291523512e-05, "loss": 1.1722, "step": 7680 }, { "epoch": 0.41994191013155646, "grad_norm": 2.4363648891448975, "learning_rate": 6.516259651570518e-05, "loss": 1.2288, "step": 7681 }, { "epoch": 0.41999658294891506, "grad_norm": 2.3602261543273926, "learning_rate": 6.51541596407654e-05, "loss": 0.9686, "step": 7682 }, { "epoch": 0.4200512557662737, "grad_norm": 2.3692750930786133, "learning_rate": 6.514572229068031e-05, "loss": 1.1588, "step": 7683 }, { "epoch": 0.4201059285836323, "grad_norm": 3.317842960357666, "learning_rate": 6.513728446571445e-05, "loss": 1.0982, "step": 7684 }, { "epoch": 0.42016060140099093, "grad_norm": 2.628880262374878, "learning_rate": 6.512884616613238e-05, "loss": 1.0095, "step": 7685 }, { "epoch": 0.4202152742183496, "grad_norm": 2.6520915031433105, "learning_rate": 6.512040739219866e-05, "loss": 0.9307, "step": 7686 }, { "epoch": 0.4202699470357082, "grad_norm": 2.5890097618103027, "learning_rate": 6.51119681441779e-05, "loss": 1.2346, "step": 7687 }, { "epoch": 0.4203246198530668, "grad_norm": 2.085527181625366, "learning_rate": 6.51035284223347e-05, "loss": 0.8913, "step": 7688 }, { "epoch": 0.4203792926704254, "grad_norm": 2.7338836193084717, "learning_rate": 6.509508822693369e-05, "loss": 1.2966, "step": 7689 }, { "epoch": 0.42043396548778406, "grad_norm": 4.899258613586426, "learning_rate": 6.50866475582395e-05, "loss": 1.1186, "step": 7690 }, { "epoch": 0.42048863830514266, "grad_norm": 2.6324622631073, "learning_rate": 6.507820641651676e-05, "loss": 1.1312, "step": 7691 }, { "epoch": 0.42054331112250126, "grad_norm": 3.0681655406951904, "learning_rate": 6.506976480203015e-05, "loss": 1.1402, "step": 7692 }, { "epoch": 0.4205979839398599, "grad_norm": 2.655303716659546, "learning_rate": 6.506132271504438e-05, "loss": 1.0484, "step": 7693 }, { "epoch": 0.4206526567572185, "grad_norm": 2.374983310699463, "learning_rate": 6.505288015582408e-05, "loss": 1.0235, "step": 7694 }, { "epoch": 0.4207073295745771, "grad_norm": 2.9541711807250977, "learning_rate": 6.504443712463401e-05, "loss": 1.063, "step": 7695 }, { "epoch": 0.4207620023919358, "grad_norm": 2.47611403465271, "learning_rate": 6.503599362173887e-05, "loss": 1.0025, "step": 7696 }, { "epoch": 0.4208166752092944, "grad_norm": 3.1604819297790527, "learning_rate": 6.50275496474034e-05, "loss": 1.1917, "step": 7697 }, { "epoch": 0.420871348026653, "grad_norm": 2.3786537647247314, "learning_rate": 6.501910520189236e-05, "loss": 1.0198, "step": 7698 }, { "epoch": 0.4209260208440116, "grad_norm": 2.521864891052246, "learning_rate": 6.501066028547052e-05, "loss": 1.0084, "step": 7699 }, { "epoch": 0.42098069366137025, "grad_norm": 3.2602975368499756, "learning_rate": 6.500221489840267e-05, "loss": 1.1092, "step": 7700 }, { "epoch": 0.42103536647872886, "grad_norm": 2.528489828109741, "learning_rate": 6.499376904095359e-05, "loss": 1.0977, "step": 7701 }, { "epoch": 0.42109003929608746, "grad_norm": 2.111043930053711, "learning_rate": 6.498532271338809e-05, "loss": 0.8702, "step": 7702 }, { "epoch": 0.4211447121134461, "grad_norm": 2.516880512237549, "learning_rate": 6.497687591597103e-05, "loss": 1.1032, "step": 7703 }, { "epoch": 0.4211993849308047, "grad_norm": 2.0841171741485596, "learning_rate": 6.496842864896721e-05, "loss": 0.9238, "step": 7704 }, { "epoch": 0.4212540577481633, "grad_norm": 2.549938201904297, "learning_rate": 6.49599809126415e-05, "loss": 1.2927, "step": 7705 }, { "epoch": 0.4213087305655219, "grad_norm": 3.0578720569610596, "learning_rate": 6.495153270725879e-05, "loss": 0.8988, "step": 7706 }, { "epoch": 0.4213634033828806, "grad_norm": 2.66548752784729, "learning_rate": 6.494308403308396e-05, "loss": 0.9384, "step": 7707 }, { "epoch": 0.4214180762002392, "grad_norm": 2.6837358474731445, "learning_rate": 6.493463489038188e-05, "loss": 1.0954, "step": 7708 }, { "epoch": 0.4214727490175978, "grad_norm": 3.0770299434661865, "learning_rate": 6.492618527941751e-05, "loss": 0.9342, "step": 7709 }, { "epoch": 0.42152742183495645, "grad_norm": 2.673267126083374, "learning_rate": 6.491773520045576e-05, "loss": 0.857, "step": 7710 }, { "epoch": 0.42158209465231505, "grad_norm": 2.4582884311676025, "learning_rate": 6.490928465376157e-05, "loss": 1.1161, "step": 7711 }, { "epoch": 0.42163676746967366, "grad_norm": 2.255495548248291, "learning_rate": 6.490083363959989e-05, "loss": 1.0947, "step": 7712 }, { "epoch": 0.4216914402870323, "grad_norm": 2.5611462593078613, "learning_rate": 6.489238215823572e-05, "loss": 0.9503, "step": 7713 }, { "epoch": 0.4217461131043909, "grad_norm": 2.5066637992858887, "learning_rate": 6.488393020993403e-05, "loss": 0.9159, "step": 7714 }, { "epoch": 0.4218007859217495, "grad_norm": 2.27091908454895, "learning_rate": 6.487547779495981e-05, "loss": 1.1381, "step": 7715 }, { "epoch": 0.4218554587391081, "grad_norm": 2.0302600860595703, "learning_rate": 6.486702491357813e-05, "loss": 0.8989, "step": 7716 }, { "epoch": 0.4219101315564668, "grad_norm": 2.595564842224121, "learning_rate": 6.485857156605399e-05, "loss": 0.9771, "step": 7717 }, { "epoch": 0.4219648043738254, "grad_norm": 2.919123411178589, "learning_rate": 6.485011775265241e-05, "loss": 0.9811, "step": 7718 }, { "epoch": 0.422019477191184, "grad_norm": 2.2780799865722656, "learning_rate": 6.484166347363851e-05, "loss": 1.0309, "step": 7719 }, { "epoch": 0.42207415000854265, "grad_norm": 2.389678955078125, "learning_rate": 6.483320872927732e-05, "loss": 1.1634, "step": 7720 }, { "epoch": 0.42212882282590125, "grad_norm": 2.1704471111297607, "learning_rate": 6.482475351983395e-05, "loss": 1.0173, "step": 7721 }, { "epoch": 0.42218349564325985, "grad_norm": 2.5832083225250244, "learning_rate": 6.481629784557349e-05, "loss": 1.0555, "step": 7722 }, { "epoch": 0.4222381684606185, "grad_norm": 3.0173752307891846, "learning_rate": 6.480784170676108e-05, "loss": 1.1992, "step": 7723 }, { "epoch": 0.4222928412779771, "grad_norm": 2.251737117767334, "learning_rate": 6.479938510366186e-05, "loss": 1.0232, "step": 7724 }, { "epoch": 0.4223475140953357, "grad_norm": 2.9260215759277344, "learning_rate": 6.479092803654096e-05, "loss": 1.0958, "step": 7725 }, { "epoch": 0.4224021869126943, "grad_norm": 1.8922929763793945, "learning_rate": 6.478247050566354e-05, "loss": 0.8588, "step": 7726 }, { "epoch": 0.422456859730053, "grad_norm": 2.5564911365509033, "learning_rate": 6.47740125112948e-05, "loss": 1.1468, "step": 7727 }, { "epoch": 0.4225115325474116, "grad_norm": 3.0501575469970703, "learning_rate": 6.476555405369991e-05, "loss": 1.1155, "step": 7728 }, { "epoch": 0.4225662053647702, "grad_norm": 2.7432913780212402, "learning_rate": 6.475709513314411e-05, "loss": 1.1741, "step": 7729 }, { "epoch": 0.42262087818212885, "grad_norm": 2.3224830627441406, "learning_rate": 6.474863574989259e-05, "loss": 1.2132, "step": 7730 }, { "epoch": 0.42267555099948745, "grad_norm": 3.0685248374938965, "learning_rate": 6.474017590421058e-05, "loss": 0.9258, "step": 7731 }, { "epoch": 0.42273022381684605, "grad_norm": 3.1632080078125, "learning_rate": 6.473171559636338e-05, "loss": 1.0317, "step": 7732 }, { "epoch": 0.42278489663420465, "grad_norm": 2.4819304943084717, "learning_rate": 6.472325482661621e-05, "loss": 1.2313, "step": 7733 }, { "epoch": 0.4228395694515633, "grad_norm": 2.1425955295562744, "learning_rate": 6.471479359523437e-05, "loss": 0.8696, "step": 7734 }, { "epoch": 0.4228942422689219, "grad_norm": 2.177638530731201, "learning_rate": 6.470633190248314e-05, "loss": 0.9191, "step": 7735 }, { "epoch": 0.4229489150862805, "grad_norm": 2.8754959106445312, "learning_rate": 6.469786974862784e-05, "loss": 0.8923, "step": 7736 }, { "epoch": 0.4230035879036392, "grad_norm": 2.485194444656372, "learning_rate": 6.468940713393379e-05, "loss": 1.0636, "step": 7737 }, { "epoch": 0.4230582607209978, "grad_norm": 2.4287428855895996, "learning_rate": 6.468094405866634e-05, "loss": 1.001, "step": 7738 }, { "epoch": 0.4231129335383564, "grad_norm": 2.567363977432251, "learning_rate": 6.467248052309083e-05, "loss": 1.135, "step": 7739 }, { "epoch": 0.42316760635571504, "grad_norm": 2.650818347930908, "learning_rate": 6.466401652747262e-05, "loss": 0.9773, "step": 7740 }, { "epoch": 0.42322227917307365, "grad_norm": 2.5037875175476074, "learning_rate": 6.46555520720771e-05, "loss": 1.0704, "step": 7741 }, { "epoch": 0.42327695199043225, "grad_norm": 2.402099370956421, "learning_rate": 6.464708715716966e-05, "loss": 1.1462, "step": 7742 }, { "epoch": 0.42333162480779085, "grad_norm": 2.3638973236083984, "learning_rate": 6.463862178301571e-05, "loss": 1.0956, "step": 7743 }, { "epoch": 0.4233862976251495, "grad_norm": 2.7118325233459473, "learning_rate": 6.46301559498807e-05, "loss": 0.9013, "step": 7744 }, { "epoch": 0.4234409704425081, "grad_norm": 3.0584630966186523, "learning_rate": 6.462168965803004e-05, "loss": 1.12, "step": 7745 }, { "epoch": 0.4234956432598667, "grad_norm": 2.285524845123291, "learning_rate": 6.461322290772918e-05, "loss": 0.9783, "step": 7746 }, { "epoch": 0.4235503160772254, "grad_norm": 2.40533447265625, "learning_rate": 6.46047556992436e-05, "loss": 0.8798, "step": 7747 }, { "epoch": 0.423604988894584, "grad_norm": 2.1934449672698975, "learning_rate": 6.45962880328388e-05, "loss": 1.0274, "step": 7748 }, { "epoch": 0.4236596617119426, "grad_norm": 3.0144355297088623, "learning_rate": 6.458781990878024e-05, "loss": 1.2381, "step": 7749 }, { "epoch": 0.42371433452930124, "grad_norm": 2.1538991928100586, "learning_rate": 6.457935132733344e-05, "loss": 0.9992, "step": 7750 }, { "epoch": 0.42376900734665984, "grad_norm": 2.638812780380249, "learning_rate": 6.457088228876394e-05, "loss": 0.8877, "step": 7751 }, { "epoch": 0.42382368016401845, "grad_norm": 4.186069965362549, "learning_rate": 6.456241279333728e-05, "loss": 1.1652, "step": 7752 }, { "epoch": 0.42387835298137705, "grad_norm": 2.8970224857330322, "learning_rate": 6.455394284131899e-05, "loss": 0.9404, "step": 7753 }, { "epoch": 0.4239330257987357, "grad_norm": 2.945084571838379, "learning_rate": 6.454547243297467e-05, "loss": 0.9504, "step": 7754 }, { "epoch": 0.4239876986160943, "grad_norm": 2.6153717041015625, "learning_rate": 6.453700156856988e-05, "loss": 1.0286, "step": 7755 }, { "epoch": 0.4240423714334529, "grad_norm": 2.253882646560669, "learning_rate": 6.45285302483702e-05, "loss": 1.0094, "step": 7756 }, { "epoch": 0.4240970442508116, "grad_norm": 2.74641752243042, "learning_rate": 6.452005847264129e-05, "loss": 1.0596, "step": 7757 }, { "epoch": 0.4241517170681702, "grad_norm": 4.461522102355957, "learning_rate": 6.451158624164872e-05, "loss": 1.1104, "step": 7758 }, { "epoch": 0.4242063898855288, "grad_norm": 2.2061965465545654, "learning_rate": 6.450311355565818e-05, "loss": 1.154, "step": 7759 }, { "epoch": 0.4242610627028874, "grad_norm": 2.0048177242279053, "learning_rate": 6.44946404149353e-05, "loss": 1.0848, "step": 7760 }, { "epoch": 0.42431573552024604, "grad_norm": 2.4470126628875732, "learning_rate": 6.448616681974573e-05, "loss": 1.1058, "step": 7761 }, { "epoch": 0.42437040833760464, "grad_norm": 2.508620023727417, "learning_rate": 6.447769277035517e-05, "loss": 0.9747, "step": 7762 }, { "epoch": 0.42442508115496325, "grad_norm": 2.9141123294830322, "learning_rate": 6.446921826702932e-05, "loss": 0.9573, "step": 7763 }, { "epoch": 0.4244797539723219, "grad_norm": 2.250455141067505, "learning_rate": 6.446074331003392e-05, "loss": 1.1118, "step": 7764 }, { "epoch": 0.4245344267896805, "grad_norm": 3.02589750289917, "learning_rate": 6.445226789963462e-05, "loss": 1.1256, "step": 7765 }, { "epoch": 0.4245890996070391, "grad_norm": 2.266688823699951, "learning_rate": 6.444379203609721e-05, "loss": 1.1596, "step": 7766 }, { "epoch": 0.42464377242439777, "grad_norm": 1.8736817836761475, "learning_rate": 6.443531571968744e-05, "loss": 0.9281, "step": 7767 }, { "epoch": 0.4246984452417564, "grad_norm": 3.003507137298584, "learning_rate": 6.442683895067107e-05, "loss": 0.8474, "step": 7768 }, { "epoch": 0.424753118059115, "grad_norm": 2.4764018058776855, "learning_rate": 6.441836172931388e-05, "loss": 0.9775, "step": 7769 }, { "epoch": 0.4248077908764736, "grad_norm": 2.915354013442993, "learning_rate": 6.440988405588167e-05, "loss": 1.2146, "step": 7770 }, { "epoch": 0.42486246369383224, "grad_norm": 2.4453377723693848, "learning_rate": 6.440140593064025e-05, "loss": 1.0256, "step": 7771 }, { "epoch": 0.42491713651119084, "grad_norm": 4.16806697845459, "learning_rate": 6.439292735385544e-05, "loss": 1.0795, "step": 7772 }, { "epoch": 0.42497180932854944, "grad_norm": 2.6275954246520996, "learning_rate": 6.438444832579309e-05, "loss": 1.1276, "step": 7773 }, { "epoch": 0.4250264821459081, "grad_norm": 2.7019619941711426, "learning_rate": 6.437596884671903e-05, "loss": 1.1501, "step": 7774 }, { "epoch": 0.4250811549632667, "grad_norm": 1.9858901500701904, "learning_rate": 6.436748891689914e-05, "loss": 0.9021, "step": 7775 }, { "epoch": 0.4251358277806253, "grad_norm": 2.771967887878418, "learning_rate": 6.435900853659931e-05, "loss": 0.8917, "step": 7776 }, { "epoch": 0.42519050059798397, "grad_norm": 1.9415556192398071, "learning_rate": 6.435052770608543e-05, "loss": 0.8893, "step": 7777 }, { "epoch": 0.42524517341534257, "grad_norm": 2.351630210876465, "learning_rate": 6.43420464256234e-05, "loss": 0.9742, "step": 7778 }, { "epoch": 0.4252998462327012, "grad_norm": 2.55902361869812, "learning_rate": 6.433356469547915e-05, "loss": 1.1018, "step": 7779 }, { "epoch": 0.4253545190500598, "grad_norm": 3.1474366188049316, "learning_rate": 6.43250825159186e-05, "loss": 0.9809, "step": 7780 }, { "epoch": 0.42540919186741843, "grad_norm": 3.0493650436401367, "learning_rate": 6.431659988720772e-05, "loss": 1.1328, "step": 7781 }, { "epoch": 0.42546386468477704, "grad_norm": 2.9714787006378174, "learning_rate": 6.43081168096125e-05, "loss": 1.2322, "step": 7782 }, { "epoch": 0.42551853750213564, "grad_norm": 2.393083333969116, "learning_rate": 6.429963328339887e-05, "loss": 0.8991, "step": 7783 }, { "epoch": 0.4255732103194943, "grad_norm": 3.7612476348876953, "learning_rate": 6.429114930883285e-05, "loss": 1.2525, "step": 7784 }, { "epoch": 0.4256278831368529, "grad_norm": 2.269916534423828, "learning_rate": 6.428266488618042e-05, "loss": 1.0452, "step": 7785 }, { "epoch": 0.4256825559542115, "grad_norm": 2.289846658706665, "learning_rate": 6.427418001570764e-05, "loss": 1.0125, "step": 7786 }, { "epoch": 0.4257372287715701, "grad_norm": 2.3128130435943604, "learning_rate": 6.426569469768053e-05, "loss": 1.24, "step": 7787 }, { "epoch": 0.42579190158892877, "grad_norm": 2.955573320388794, "learning_rate": 6.425720893236515e-05, "loss": 1.0849, "step": 7788 }, { "epoch": 0.42584657440628737, "grad_norm": 2.1937954425811768, "learning_rate": 6.424872272002754e-05, "loss": 1.0854, "step": 7789 }, { "epoch": 0.425901247223646, "grad_norm": 2.057335376739502, "learning_rate": 6.424023606093379e-05, "loss": 0.7992, "step": 7790 }, { "epoch": 0.42595592004100463, "grad_norm": 3.6368446350097656, "learning_rate": 6.423174895534998e-05, "loss": 1.0362, "step": 7791 }, { "epoch": 0.42601059285836324, "grad_norm": 3.480797529220581, "learning_rate": 6.422326140354226e-05, "loss": 0.9887, "step": 7792 }, { "epoch": 0.42606526567572184, "grad_norm": 2.3248987197875977, "learning_rate": 6.42147734057767e-05, "loss": 1.0979, "step": 7793 }, { "epoch": 0.4261199384930805, "grad_norm": 2.9801363945007324, "learning_rate": 6.420628496231944e-05, "loss": 0.9484, "step": 7794 }, { "epoch": 0.4261746113104391, "grad_norm": 2.225353240966797, "learning_rate": 6.419779607343664e-05, "loss": 1.1343, "step": 7795 }, { "epoch": 0.4262292841277977, "grad_norm": 2.7222604751586914, "learning_rate": 6.418930673939447e-05, "loss": 1.197, "step": 7796 }, { "epoch": 0.4262839569451563, "grad_norm": 2.2984085083007812, "learning_rate": 6.41808169604591e-05, "loss": 1.0304, "step": 7797 }, { "epoch": 0.42633862976251496, "grad_norm": 2.8828914165496826, "learning_rate": 6.417232673689673e-05, "loss": 1.1816, "step": 7798 }, { "epoch": 0.42639330257987357, "grad_norm": 2.351348876953125, "learning_rate": 6.416383606897352e-05, "loss": 1.0125, "step": 7799 }, { "epoch": 0.42644797539723217, "grad_norm": 2.658942699432373, "learning_rate": 6.415534495695573e-05, "loss": 1.1993, "step": 7800 }, { "epoch": 0.42650264821459083, "grad_norm": 2.984499216079712, "learning_rate": 6.414685340110958e-05, "loss": 1.2851, "step": 7801 }, { "epoch": 0.42655732103194943, "grad_norm": 2.271599292755127, "learning_rate": 6.413836140170129e-05, "loss": 1.0814, "step": 7802 }, { "epoch": 0.42661199384930804, "grad_norm": 2.7788240909576416, "learning_rate": 6.412986895899717e-05, "loss": 1.0637, "step": 7803 }, { "epoch": 0.4266666666666667, "grad_norm": 2.243281841278076, "learning_rate": 6.412137607326345e-05, "loss": 1.1119, "step": 7804 }, { "epoch": 0.4267213394840253, "grad_norm": 2.183098316192627, "learning_rate": 6.411288274476644e-05, "loss": 1.0643, "step": 7805 }, { "epoch": 0.4267760123013839, "grad_norm": 2.90319561958313, "learning_rate": 6.410438897377243e-05, "loss": 1.152, "step": 7806 }, { "epoch": 0.4268306851187425, "grad_norm": 2.8633947372436523, "learning_rate": 6.409589476054775e-05, "loss": 0.9553, "step": 7807 }, { "epoch": 0.42688535793610116, "grad_norm": 2.6700239181518555, "learning_rate": 6.40874001053587e-05, "loss": 1.0644, "step": 7808 }, { "epoch": 0.42694003075345976, "grad_norm": 2.469721555709839, "learning_rate": 6.407890500847164e-05, "loss": 0.9876, "step": 7809 }, { "epoch": 0.42699470357081837, "grad_norm": 2.8857040405273438, "learning_rate": 6.407040947015292e-05, "loss": 0.9544, "step": 7810 }, { "epoch": 0.427049376388177, "grad_norm": 2.2724967002868652, "learning_rate": 6.406191349066894e-05, "loss": 0.9177, "step": 7811 }, { "epoch": 0.42710404920553563, "grad_norm": 2.5618319511413574, "learning_rate": 6.405341707028604e-05, "loss": 1.052, "step": 7812 }, { "epoch": 0.42715872202289423, "grad_norm": 2.7174453735351562, "learning_rate": 6.404492020927064e-05, "loss": 1.0602, "step": 7813 }, { "epoch": 0.42721339484025284, "grad_norm": 2.0426034927368164, "learning_rate": 6.403642290788915e-05, "loss": 0.9471, "step": 7814 }, { "epoch": 0.4272680676576115, "grad_norm": 3.093864917755127, "learning_rate": 6.402792516640798e-05, "loss": 1.1047, "step": 7815 }, { "epoch": 0.4273227404749701, "grad_norm": 2.5037574768066406, "learning_rate": 6.40194269850936e-05, "loss": 0.9893, "step": 7816 }, { "epoch": 0.4273774132923287, "grad_norm": 3.2471420764923096, "learning_rate": 6.401092836421244e-05, "loss": 1.1798, "step": 7817 }, { "epoch": 0.42743208610968736, "grad_norm": 2.301034450531006, "learning_rate": 6.400242930403098e-05, "loss": 1.102, "step": 7818 }, { "epoch": 0.42748675892704596, "grad_norm": 2.330244302749634, "learning_rate": 6.399392980481568e-05, "loss": 0.8954, "step": 7819 }, { "epoch": 0.42754143174440457, "grad_norm": 2.818171262741089, "learning_rate": 6.398542986683305e-05, "loss": 1.1989, "step": 7820 }, { "epoch": 0.4275961045617632, "grad_norm": 2.8407230377197266, "learning_rate": 6.39769294903496e-05, "loss": 1.1172, "step": 7821 }, { "epoch": 0.4276507773791218, "grad_norm": 2.6370434761047363, "learning_rate": 6.396842867563184e-05, "loss": 1.157, "step": 7822 }, { "epoch": 0.42770545019648043, "grad_norm": 2.7683064937591553, "learning_rate": 6.395992742294633e-05, "loss": 1.2475, "step": 7823 }, { "epoch": 0.42776012301383903, "grad_norm": 2.6604020595550537, "learning_rate": 6.395142573255958e-05, "loss": 1.0315, "step": 7824 }, { "epoch": 0.4278147958311977, "grad_norm": 2.3640449047088623, "learning_rate": 6.394292360473819e-05, "loss": 1.1098, "step": 7825 }, { "epoch": 0.4278694686485563, "grad_norm": 2.770677328109741, "learning_rate": 6.393442103974872e-05, "loss": 1.0067, "step": 7826 }, { "epoch": 0.4279241414659149, "grad_norm": 2.3175129890441895, "learning_rate": 6.392591803785776e-05, "loss": 0.9991, "step": 7827 }, { "epoch": 0.42797881428327356, "grad_norm": 2.912696599960327, "learning_rate": 6.391741459933192e-05, "loss": 0.9455, "step": 7828 }, { "epoch": 0.42803348710063216, "grad_norm": 2.790905237197876, "learning_rate": 6.390891072443781e-05, "loss": 1.0337, "step": 7829 }, { "epoch": 0.42808815991799076, "grad_norm": 2.0747060775756836, "learning_rate": 6.390040641344207e-05, "loss": 0.7657, "step": 7830 }, { "epoch": 0.4281428327353494, "grad_norm": 2.2542169094085693, "learning_rate": 6.389190166661134e-05, "loss": 1.2189, "step": 7831 }, { "epoch": 0.428197505552708, "grad_norm": 2.193044900894165, "learning_rate": 6.38833964842123e-05, "loss": 0.9876, "step": 7832 }, { "epoch": 0.4282521783700666, "grad_norm": 2.11942458152771, "learning_rate": 6.387489086651157e-05, "loss": 0.7135, "step": 7833 }, { "epoch": 0.42830685118742523, "grad_norm": 2.6276607513427734, "learning_rate": 6.386638481377587e-05, "loss": 1.0986, "step": 7834 }, { "epoch": 0.4283615240047839, "grad_norm": 2.5652713775634766, "learning_rate": 6.385787832627191e-05, "loss": 0.9809, "step": 7835 }, { "epoch": 0.4284161968221425, "grad_norm": 2.6086244583129883, "learning_rate": 6.38493714042664e-05, "loss": 0.8909, "step": 7836 }, { "epoch": 0.4284708696395011, "grad_norm": 2.4562268257141113, "learning_rate": 6.384086404802605e-05, "loss": 1.0009, "step": 7837 }, { "epoch": 0.42852554245685975, "grad_norm": 2.8864033222198486, "learning_rate": 6.383235625781761e-05, "loss": 1.1238, "step": 7838 }, { "epoch": 0.42858021527421836, "grad_norm": 2.3278589248657227, "learning_rate": 6.382384803390781e-05, "loss": 1.0735, "step": 7839 }, { "epoch": 0.42863488809157696, "grad_norm": 1.9094387292861938, "learning_rate": 6.381533937656347e-05, "loss": 0.9806, "step": 7840 }, { "epoch": 0.42868956090893556, "grad_norm": 2.9305224418640137, "learning_rate": 6.380683028605134e-05, "loss": 1.1946, "step": 7841 }, { "epoch": 0.4287442337262942, "grad_norm": 3.043297529220581, "learning_rate": 6.379832076263821e-05, "loss": 1.2546, "step": 7842 }, { "epoch": 0.4287989065436528, "grad_norm": 3.1204566955566406, "learning_rate": 6.378981080659092e-05, "loss": 1.0603, "step": 7843 }, { "epoch": 0.4288535793610114, "grad_norm": 2.2539587020874023, "learning_rate": 6.378130041817623e-05, "loss": 1.078, "step": 7844 }, { "epoch": 0.4289082521783701, "grad_norm": 2.8381214141845703, "learning_rate": 6.377278959766104e-05, "loss": 1.0848, "step": 7845 }, { "epoch": 0.4289629249957287, "grad_norm": 3.254544496536255, "learning_rate": 6.376427834531218e-05, "loss": 1.1582, "step": 7846 }, { "epoch": 0.4290175978130873, "grad_norm": 2.4720160961151123, "learning_rate": 6.375576666139649e-05, "loss": 1.1341, "step": 7847 }, { "epoch": 0.42907227063044595, "grad_norm": 2.523736000061035, "learning_rate": 6.374725454618087e-05, "loss": 1.0417, "step": 7848 }, { "epoch": 0.42912694344780455, "grad_norm": 2.836050510406494, "learning_rate": 6.373874199993219e-05, "loss": 1.1621, "step": 7849 }, { "epoch": 0.42918161626516316, "grad_norm": 2.2896182537078857, "learning_rate": 6.373022902291739e-05, "loss": 1.0054, "step": 7850 }, { "epoch": 0.42923628908252176, "grad_norm": 2.727043390274048, "learning_rate": 6.372171561540334e-05, "loss": 1.1746, "step": 7851 }, { "epoch": 0.4292909618998804, "grad_norm": 2.0985095500946045, "learning_rate": 6.371320177765702e-05, "loss": 1.1282, "step": 7852 }, { "epoch": 0.429345634717239, "grad_norm": 2.6968576908111572, "learning_rate": 6.370468750994532e-05, "loss": 1.1373, "step": 7853 }, { "epoch": 0.4294003075345976, "grad_norm": 2.51180362701416, "learning_rate": 6.369617281253523e-05, "loss": 1.0155, "step": 7854 }, { "epoch": 0.4294549803519563, "grad_norm": 2.674215078353882, "learning_rate": 6.368765768569374e-05, "loss": 0.9696, "step": 7855 }, { "epoch": 0.4295096531693149, "grad_norm": 2.5331618785858154, "learning_rate": 6.367914212968779e-05, "loss": 1.0242, "step": 7856 }, { "epoch": 0.4295643259866735, "grad_norm": 2.099879264831543, "learning_rate": 6.36706261447844e-05, "loss": 0.9045, "step": 7857 }, { "epoch": 0.4296189988040321, "grad_norm": 3.651606798171997, "learning_rate": 6.366210973125058e-05, "loss": 1.2085, "step": 7858 }, { "epoch": 0.42967367162139075, "grad_norm": 2.2002148628234863, "learning_rate": 6.365359288935334e-05, "loss": 0.8687, "step": 7859 }, { "epoch": 0.42972834443874935, "grad_norm": 2.4219775199890137, "learning_rate": 6.364507561935975e-05, "loss": 1.2057, "step": 7860 }, { "epoch": 0.42978301725610796, "grad_norm": 3.4431874752044678, "learning_rate": 6.363655792153684e-05, "loss": 0.9695, "step": 7861 }, { "epoch": 0.4298376900734666, "grad_norm": 2.816481590270996, "learning_rate": 6.362803979615168e-05, "loss": 1.1706, "step": 7862 }, { "epoch": 0.4298923628908252, "grad_norm": 2.0359928607940674, "learning_rate": 6.361952124347133e-05, "loss": 1.054, "step": 7863 }, { "epoch": 0.4299470357081838, "grad_norm": 2.2610621452331543, "learning_rate": 6.36110022637629e-05, "loss": 0.8908, "step": 7864 }, { "epoch": 0.4300017085255425, "grad_norm": 2.679384231567383, "learning_rate": 6.360248285729352e-05, "loss": 1.2415, "step": 7865 }, { "epoch": 0.4300563813429011, "grad_norm": 2.908128023147583, "learning_rate": 6.359396302433026e-05, "loss": 0.9059, "step": 7866 }, { "epoch": 0.4301110541602597, "grad_norm": 2.6981372833251953, "learning_rate": 6.358544276514027e-05, "loss": 1.1919, "step": 7867 }, { "epoch": 0.4301657269776183, "grad_norm": 2.8032162189483643, "learning_rate": 6.35769220799907e-05, "loss": 0.8731, "step": 7868 }, { "epoch": 0.43022039979497695, "grad_norm": 2.1782758235931396, "learning_rate": 6.356840096914871e-05, "loss": 1.0639, "step": 7869 }, { "epoch": 0.43027507261233555, "grad_norm": 2.4907822608947754, "learning_rate": 6.355987943288148e-05, "loss": 0.9921, "step": 7870 }, { "epoch": 0.43032974542969415, "grad_norm": 2.3522324562072754, "learning_rate": 6.355135747145618e-05, "loss": 1.0917, "step": 7871 }, { "epoch": 0.4303844182470528, "grad_norm": 3.017390251159668, "learning_rate": 6.354283508514e-05, "loss": 0.9254, "step": 7872 }, { "epoch": 0.4304390910644114, "grad_norm": 2.5590460300445557, "learning_rate": 6.353431227420017e-05, "loss": 1.0955, "step": 7873 }, { "epoch": 0.43049376388177, "grad_norm": 2.5338528156280518, "learning_rate": 6.352578903890392e-05, "loss": 1.1049, "step": 7874 }, { "epoch": 0.4305484366991287, "grad_norm": 2.2876999378204346, "learning_rate": 6.351726537951847e-05, "loss": 0.9829, "step": 7875 }, { "epoch": 0.4306031095164873, "grad_norm": 2.6701669692993164, "learning_rate": 6.350874129631108e-05, "loss": 0.9734, "step": 7876 }, { "epoch": 0.4306577823338459, "grad_norm": 2.359426259994507, "learning_rate": 6.350021678954903e-05, "loss": 1.0575, "step": 7877 }, { "epoch": 0.4307124551512045, "grad_norm": 2.4419264793395996, "learning_rate": 6.349169185949956e-05, "loss": 1.031, "step": 7878 }, { "epoch": 0.43076712796856315, "grad_norm": 2.7138559818267822, "learning_rate": 6.348316650643e-05, "loss": 1.2078, "step": 7879 }, { "epoch": 0.43082180078592175, "grad_norm": 2.0882043838500977, "learning_rate": 6.347464073060763e-05, "loss": 0.9325, "step": 7880 }, { "epoch": 0.43087647360328035, "grad_norm": 2.899677276611328, "learning_rate": 6.34661145322998e-05, "loss": 0.9477, "step": 7881 }, { "epoch": 0.430931146420639, "grad_norm": 2.8124749660491943, "learning_rate": 6.345758791177381e-05, "loss": 1.1325, "step": 7882 }, { "epoch": 0.4309858192379976, "grad_norm": 2.134295701980591, "learning_rate": 6.344906086929701e-05, "loss": 1.0327, "step": 7883 }, { "epoch": 0.4310404920553562, "grad_norm": 2.1519787311553955, "learning_rate": 6.344053340513675e-05, "loss": 0.908, "step": 7884 }, { "epoch": 0.4310951648727148, "grad_norm": 2.530393362045288, "learning_rate": 6.343200551956043e-05, "loss": 1.1283, "step": 7885 }, { "epoch": 0.4311498376900735, "grad_norm": 2.465895891189575, "learning_rate": 6.342347721283543e-05, "loss": 0.7849, "step": 7886 }, { "epoch": 0.4312045105074321, "grad_norm": 2.301058053970337, "learning_rate": 6.341494848522912e-05, "loss": 1.1827, "step": 7887 }, { "epoch": 0.4312591833247907, "grad_norm": 3.1335208415985107, "learning_rate": 6.340641933700893e-05, "loss": 1.0885, "step": 7888 }, { "epoch": 0.43131385614214934, "grad_norm": 3.209986925125122, "learning_rate": 6.339788976844228e-05, "loss": 1.3139, "step": 7889 }, { "epoch": 0.43136852895950795, "grad_norm": 3.289381980895996, "learning_rate": 6.33893597797966e-05, "loss": 1.0095, "step": 7890 }, { "epoch": 0.43142320177686655, "grad_norm": 3.050546884536743, "learning_rate": 6.338082937133935e-05, "loss": 1.2635, "step": 7891 }, { "epoch": 0.4314778745942252, "grad_norm": 2.433422327041626, "learning_rate": 6.3372298543338e-05, "loss": 0.8841, "step": 7892 }, { "epoch": 0.4315325474115838, "grad_norm": 2.087573289871216, "learning_rate": 6.336376729606002e-05, "loss": 0.9897, "step": 7893 }, { "epoch": 0.4315872202289424, "grad_norm": 2.4185478687286377, "learning_rate": 6.335523562977289e-05, "loss": 0.9229, "step": 7894 }, { "epoch": 0.431641893046301, "grad_norm": 2.2633309364318848, "learning_rate": 6.334670354474411e-05, "loss": 1.0139, "step": 7895 }, { "epoch": 0.4316965658636597, "grad_norm": 2.7511417865753174, "learning_rate": 6.333817104124122e-05, "loss": 1.1876, "step": 7896 }, { "epoch": 0.4317512386810183, "grad_norm": 2.5011637210845947, "learning_rate": 6.332963811953175e-05, "loss": 0.9833, "step": 7897 }, { "epoch": 0.4318059114983769, "grad_norm": 2.374281644821167, "learning_rate": 6.33211047798832e-05, "loss": 1.1879, "step": 7898 }, { "epoch": 0.43186058431573554, "grad_norm": 1.9099136590957642, "learning_rate": 6.331257102256317e-05, "loss": 0.9893, "step": 7899 }, { "epoch": 0.43191525713309414, "grad_norm": 2.45601749420166, "learning_rate": 6.330403684783921e-05, "loss": 1.1392, "step": 7900 }, { "epoch": 0.43196992995045275, "grad_norm": 2.414691209793091, "learning_rate": 6.32955022559789e-05, "loss": 0.9912, "step": 7901 }, { "epoch": 0.4320246027678114, "grad_norm": 2.267432451248169, "learning_rate": 6.328696724724983e-05, "loss": 0.9429, "step": 7902 }, { "epoch": 0.43207927558517, "grad_norm": 2.387695074081421, "learning_rate": 6.327843182191961e-05, "loss": 1.022, "step": 7903 }, { "epoch": 0.4321339484025286, "grad_norm": 1.9862931966781616, "learning_rate": 6.326989598025588e-05, "loss": 0.934, "step": 7904 }, { "epoch": 0.4321886212198872, "grad_norm": 2.567931652069092, "learning_rate": 6.326135972252626e-05, "loss": 1.0577, "step": 7905 }, { "epoch": 0.4322432940372459, "grad_norm": 2.7308242321014404, "learning_rate": 6.32528230489984e-05, "loss": 1.2266, "step": 7906 }, { "epoch": 0.4322979668546045, "grad_norm": 2.133206367492676, "learning_rate": 6.324428595993995e-05, "loss": 1.0221, "step": 7907 }, { "epoch": 0.4323526396719631, "grad_norm": 3.1617932319641113, "learning_rate": 6.32357484556186e-05, "loss": 1.1773, "step": 7908 }, { "epoch": 0.43240731248932174, "grad_norm": 2.3792810440063477, "learning_rate": 6.322721053630201e-05, "loss": 1.0619, "step": 7909 }, { "epoch": 0.43246198530668034, "grad_norm": 2.633625030517578, "learning_rate": 6.32186722022579e-05, "loss": 1.1557, "step": 7910 }, { "epoch": 0.43251665812403894, "grad_norm": 2.6447718143463135, "learning_rate": 6.321013345375397e-05, "loss": 1.1286, "step": 7911 }, { "epoch": 0.43257133094139755, "grad_norm": 2.683777093887329, "learning_rate": 6.320159429105797e-05, "loss": 1.1171, "step": 7912 }, { "epoch": 0.4326260037587562, "grad_norm": 2.9065723419189453, "learning_rate": 6.31930547144376e-05, "loss": 1.2018, "step": 7913 }, { "epoch": 0.4326806765761148, "grad_norm": 3.0749082565307617, "learning_rate": 6.318451472416063e-05, "loss": 1.1674, "step": 7914 }, { "epoch": 0.4327353493934734, "grad_norm": 2.4841935634613037, "learning_rate": 6.317597432049484e-05, "loss": 0.8116, "step": 7915 }, { "epoch": 0.43279002221083207, "grad_norm": 2.3699750900268555, "learning_rate": 6.316743350370797e-05, "loss": 1.1063, "step": 7916 }, { "epoch": 0.4328446950281907, "grad_norm": 2.4583966732025146, "learning_rate": 6.315889227406784e-05, "loss": 0.8855, "step": 7917 }, { "epoch": 0.4328993678455493, "grad_norm": 2.628185987472534, "learning_rate": 6.315035063184225e-05, "loss": 1.0858, "step": 7918 }, { "epoch": 0.43295404066290794, "grad_norm": 3.25138521194458, "learning_rate": 6.3141808577299e-05, "loss": 1.154, "step": 7919 }, { "epoch": 0.43300871348026654, "grad_norm": 2.227938652038574, "learning_rate": 6.313326611070593e-05, "loss": 1.053, "step": 7920 }, { "epoch": 0.43306338629762514, "grad_norm": 2.917635440826416, "learning_rate": 6.312472323233089e-05, "loss": 1.0885, "step": 7921 }, { "epoch": 0.43311805911498374, "grad_norm": 2.775538682937622, "learning_rate": 6.311617994244171e-05, "loss": 0.9055, "step": 7922 }, { "epoch": 0.4331727319323424, "grad_norm": 2.7012829780578613, "learning_rate": 6.310763624130627e-05, "loss": 1.067, "step": 7923 }, { "epoch": 0.433227404749701, "grad_norm": 2.7135133743286133, "learning_rate": 6.309909212919246e-05, "loss": 1.0718, "step": 7924 }, { "epoch": 0.4332820775670596, "grad_norm": 3.0564422607421875, "learning_rate": 6.309054760636815e-05, "loss": 1.332, "step": 7925 }, { "epoch": 0.43333675038441827, "grad_norm": 2.390056848526001, "learning_rate": 6.308200267310129e-05, "loss": 1.0011, "step": 7926 }, { "epoch": 0.43339142320177687, "grad_norm": 3.0669167041778564, "learning_rate": 6.307345732965972e-05, "loss": 0.9367, "step": 7927 }, { "epoch": 0.4334460960191355, "grad_norm": 2.818084955215454, "learning_rate": 6.306491157631146e-05, "loss": 1.111, "step": 7928 }, { "epoch": 0.43350076883649413, "grad_norm": 2.3234832286834717, "learning_rate": 6.30563654133244e-05, "loss": 0.9779, "step": 7929 }, { "epoch": 0.43355544165385274, "grad_norm": 2.302565336227417, "learning_rate": 6.304781884096652e-05, "loss": 0.9566, "step": 7930 }, { "epoch": 0.43361011447121134, "grad_norm": 2.0772061347961426, "learning_rate": 6.303927185950579e-05, "loss": 1.0094, "step": 7931 }, { "epoch": 0.43366478728856994, "grad_norm": 2.2686901092529297, "learning_rate": 6.303072446921017e-05, "loss": 1.0281, "step": 7932 }, { "epoch": 0.4337194601059286, "grad_norm": 3.0020289421081543, "learning_rate": 6.302217667034767e-05, "loss": 1.2484, "step": 7933 }, { "epoch": 0.4337741329232872, "grad_norm": 2.4525363445281982, "learning_rate": 6.301362846318632e-05, "loss": 1.1052, "step": 7934 }, { "epoch": 0.4338288057406458, "grad_norm": 2.2846171855926514, "learning_rate": 6.300507984799411e-05, "loss": 1.1055, "step": 7935 }, { "epoch": 0.43388347855800447, "grad_norm": 3.1172103881835938, "learning_rate": 6.299653082503908e-05, "loss": 0.9037, "step": 7936 }, { "epoch": 0.43393815137536307, "grad_norm": 3.1408395767211914, "learning_rate": 6.298798139458928e-05, "loss": 1.1344, "step": 7937 }, { "epoch": 0.43399282419272167, "grad_norm": 2.6504616737365723, "learning_rate": 6.297943155691279e-05, "loss": 1.1114, "step": 7938 }, { "epoch": 0.4340474970100803, "grad_norm": 2.6363418102264404, "learning_rate": 6.297088131227765e-05, "loss": 1.0065, "step": 7939 }, { "epoch": 0.43410216982743893, "grad_norm": 2.188347101211548, "learning_rate": 6.296233066095197e-05, "loss": 1.1141, "step": 7940 }, { "epoch": 0.43415684264479754, "grad_norm": 2.3836143016815186, "learning_rate": 6.295377960320384e-05, "loss": 1.1425, "step": 7941 }, { "epoch": 0.43421151546215614, "grad_norm": 2.9986541271209717, "learning_rate": 6.294522813930137e-05, "loss": 1.2063, "step": 7942 }, { "epoch": 0.4342661882795148, "grad_norm": 2.816300630569458, "learning_rate": 6.293667626951267e-05, "loss": 1.1878, "step": 7943 }, { "epoch": 0.4343208610968734, "grad_norm": 2.2786078453063965, "learning_rate": 6.292812399410591e-05, "loss": 1.0401, "step": 7944 }, { "epoch": 0.434375533914232, "grad_norm": 3.1905436515808105, "learning_rate": 6.291957131334921e-05, "loss": 1.097, "step": 7945 }, { "epoch": 0.43443020673159066, "grad_norm": 2.74084734916687, "learning_rate": 6.291101822751075e-05, "loss": 1.0249, "step": 7946 }, { "epoch": 0.43448487954894927, "grad_norm": 3.0305819511413574, "learning_rate": 6.290246473685869e-05, "loss": 1.0619, "step": 7947 }, { "epoch": 0.43453955236630787, "grad_norm": 2.620666265487671, "learning_rate": 6.28939108416612e-05, "loss": 0.8451, "step": 7948 }, { "epoch": 0.43459422518366647, "grad_norm": 3.005314350128174, "learning_rate": 6.288535654218654e-05, "loss": 1.1023, "step": 7949 }, { "epoch": 0.43464889800102513, "grad_norm": 3.45096755027771, "learning_rate": 6.287680183870287e-05, "loss": 1.1785, "step": 7950 }, { "epoch": 0.43470357081838373, "grad_norm": 2.7128615379333496, "learning_rate": 6.286824673147844e-05, "loss": 0.9075, "step": 7951 }, { "epoch": 0.43475824363574234, "grad_norm": 2.1998989582061768, "learning_rate": 6.285969122078145e-05, "loss": 1.1003, "step": 7952 }, { "epoch": 0.434812916453101, "grad_norm": 2.6316168308258057, "learning_rate": 6.285113530688019e-05, "loss": 1.2052, "step": 7953 }, { "epoch": 0.4348675892704596, "grad_norm": 2.705390453338623, "learning_rate": 6.284257899004293e-05, "loss": 1.0229, "step": 7954 }, { "epoch": 0.4349222620878182, "grad_norm": 2.8609604835510254, "learning_rate": 6.28340222705379e-05, "loss": 1.2256, "step": 7955 }, { "epoch": 0.43497693490517686, "grad_norm": 2.6669089794158936, "learning_rate": 6.282546514863343e-05, "loss": 1.0048, "step": 7956 }, { "epoch": 0.43503160772253546, "grad_norm": 3.2352511882781982, "learning_rate": 6.28169076245978e-05, "loss": 1.1019, "step": 7957 }, { "epoch": 0.43508628053989407, "grad_norm": 2.8369388580322266, "learning_rate": 6.280834969869935e-05, "loss": 1.059, "step": 7958 }, { "epoch": 0.43514095335725267, "grad_norm": 2.4853568077087402, "learning_rate": 6.279979137120638e-05, "loss": 0.921, "step": 7959 }, { "epoch": 0.4351956261746113, "grad_norm": 2.6486525535583496, "learning_rate": 6.279123264238722e-05, "loss": 0.8831, "step": 7960 }, { "epoch": 0.43525029899196993, "grad_norm": 2.6610910892486572, "learning_rate": 6.278267351251024e-05, "loss": 1.0314, "step": 7961 }, { "epoch": 0.43530497180932853, "grad_norm": 2.5559277534484863, "learning_rate": 6.277411398184381e-05, "loss": 0.805, "step": 7962 }, { "epoch": 0.4353596446266872, "grad_norm": 3.149240016937256, "learning_rate": 6.276555405065629e-05, "loss": 1.0537, "step": 7963 }, { "epoch": 0.4354143174440458, "grad_norm": 2.2904293537139893, "learning_rate": 6.275699371921608e-05, "loss": 0.922, "step": 7964 }, { "epoch": 0.4354689902614044, "grad_norm": 2.302957534790039, "learning_rate": 6.274843298779158e-05, "loss": 0.9945, "step": 7965 }, { "epoch": 0.435523663078763, "grad_norm": 3.4579992294311523, "learning_rate": 6.27398718566512e-05, "loss": 0.9832, "step": 7966 }, { "epoch": 0.43557833589612166, "grad_norm": 2.182551622390747, "learning_rate": 6.273131032606337e-05, "loss": 0.9703, "step": 7967 }, { "epoch": 0.43563300871348026, "grad_norm": 2.147580623626709, "learning_rate": 6.272274839629653e-05, "loss": 1.0318, "step": 7968 }, { "epoch": 0.43568768153083887, "grad_norm": 2.1198580265045166, "learning_rate": 6.271418606761911e-05, "loss": 0.9676, "step": 7969 }, { "epoch": 0.4357423543481975, "grad_norm": 2.375446081161499, "learning_rate": 6.270562334029963e-05, "loss": 1.0427, "step": 7970 }, { "epoch": 0.43579702716555613, "grad_norm": 2.234748601913452, "learning_rate": 6.269706021460651e-05, "loss": 0.9422, "step": 7971 }, { "epoch": 0.43585169998291473, "grad_norm": 2.0231595039367676, "learning_rate": 6.268849669080825e-05, "loss": 1.0697, "step": 7972 }, { "epoch": 0.4359063728002734, "grad_norm": 2.117863178253174, "learning_rate": 6.267993276917338e-05, "loss": 1.0196, "step": 7973 }, { "epoch": 0.435961045617632, "grad_norm": 2.2953879833221436, "learning_rate": 6.267136844997039e-05, "loss": 1.1196, "step": 7974 }, { "epoch": 0.4360157184349906, "grad_norm": 2.4335789680480957, "learning_rate": 6.266280373346782e-05, "loss": 1.0516, "step": 7975 }, { "epoch": 0.4360703912523492, "grad_norm": 2.3265187740325928, "learning_rate": 6.26542386199342e-05, "loss": 1.192, "step": 7976 }, { "epoch": 0.43612506406970786, "grad_norm": 2.92002272605896, "learning_rate": 6.264567310963808e-05, "loss": 1.2258, "step": 7977 }, { "epoch": 0.43617973688706646, "grad_norm": 2.4104392528533936, "learning_rate": 6.263710720284802e-05, "loss": 1.0146, "step": 7978 }, { "epoch": 0.43623440970442506, "grad_norm": 2.794773578643799, "learning_rate": 6.262854089983263e-05, "loss": 0.9515, "step": 7979 }, { "epoch": 0.4362890825217837, "grad_norm": 2.5158612728118896, "learning_rate": 6.261997420086045e-05, "loss": 1.0012, "step": 7980 }, { "epoch": 0.4363437553391423, "grad_norm": 2.359497308731079, "learning_rate": 6.26114071062001e-05, "loss": 1.1505, "step": 7981 }, { "epoch": 0.43639842815650093, "grad_norm": 3.1054844856262207, "learning_rate": 6.26028396161202e-05, "loss": 1.0371, "step": 7982 }, { "epoch": 0.4364531009738596, "grad_norm": 2.9633936882019043, "learning_rate": 6.259427173088938e-05, "loss": 0.8786, "step": 7983 }, { "epoch": 0.4365077737912182, "grad_norm": 2.5702834129333496, "learning_rate": 6.258570345077628e-05, "loss": 1.0198, "step": 7984 }, { "epoch": 0.4365624466085768, "grad_norm": 2.7649121284484863, "learning_rate": 6.257713477604954e-05, "loss": 1.0755, "step": 7985 }, { "epoch": 0.4366171194259354, "grad_norm": 2.8101377487182617, "learning_rate": 6.256856570697783e-05, "loss": 1.1107, "step": 7986 }, { "epoch": 0.43667179224329405, "grad_norm": 2.911402463912964, "learning_rate": 6.255999624382982e-05, "loss": 0.8416, "step": 7987 }, { "epoch": 0.43672646506065266, "grad_norm": 1.9870152473449707, "learning_rate": 6.25514263868742e-05, "loss": 1.0692, "step": 7988 }, { "epoch": 0.43678113787801126, "grad_norm": 2.3188083171844482, "learning_rate": 6.254285613637966e-05, "loss": 0.9485, "step": 7989 }, { "epoch": 0.4368358106953699, "grad_norm": 2.1467747688293457, "learning_rate": 6.253428549261494e-05, "loss": 0.9649, "step": 7990 }, { "epoch": 0.4368904835127285, "grad_norm": 3.2498362064361572, "learning_rate": 6.252571445584873e-05, "loss": 1.1785, "step": 7991 }, { "epoch": 0.4369451563300871, "grad_norm": 1.9177579879760742, "learning_rate": 6.25171430263498e-05, "loss": 0.8481, "step": 7992 }, { "epoch": 0.43699982914744573, "grad_norm": 3.010646343231201, "learning_rate": 6.250857120438688e-05, "loss": 1.0952, "step": 7993 }, { "epoch": 0.4370545019648044, "grad_norm": 2.278146505355835, "learning_rate": 6.249999899022874e-05, "loss": 1.0851, "step": 7994 }, { "epoch": 0.437109174782163, "grad_norm": 2.1331822872161865, "learning_rate": 6.249142638414413e-05, "loss": 0.9007, "step": 7995 }, { "epoch": 0.4371638475995216, "grad_norm": 2.9688005447387695, "learning_rate": 6.248285338640188e-05, "loss": 1.0007, "step": 7996 }, { "epoch": 0.43721852041688025, "grad_norm": 2.5702221393585205, "learning_rate": 6.247427999727077e-05, "loss": 1.1325, "step": 7997 }, { "epoch": 0.43727319323423885, "grad_norm": 2.0030839443206787, "learning_rate": 6.24657062170196e-05, "loss": 0.9091, "step": 7998 }, { "epoch": 0.43732786605159746, "grad_norm": 2.2438924312591553, "learning_rate": 6.24571320459172e-05, "loss": 1.0249, "step": 7999 }, { "epoch": 0.4373825388689561, "grad_norm": 2.3238649368286133, "learning_rate": 6.244855748423241e-05, "loss": 0.9683, "step": 8000 }, { "epoch": 0.4374372116863147, "grad_norm": 2.543658494949341, "learning_rate": 6.243998253223407e-05, "loss": 1.0745, "step": 8001 }, { "epoch": 0.4374918845036733, "grad_norm": 1.9413819313049316, "learning_rate": 6.243140719019104e-05, "loss": 0.9183, "step": 8002 }, { "epoch": 0.4375465573210319, "grad_norm": 2.9930295944213867, "learning_rate": 6.242283145837221e-05, "loss": 1.2187, "step": 8003 }, { "epoch": 0.4376012301383906, "grad_norm": 2.543447494506836, "learning_rate": 6.241425533704644e-05, "loss": 1.0117, "step": 8004 }, { "epoch": 0.4376559029557492, "grad_norm": 2.3749008178710938, "learning_rate": 6.240567882648265e-05, "loss": 1.0075, "step": 8005 }, { "epoch": 0.4377105757731078, "grad_norm": 2.4741013050079346, "learning_rate": 6.239710192694972e-05, "loss": 1.0748, "step": 8006 }, { "epoch": 0.43776524859046645, "grad_norm": 3.2740747928619385, "learning_rate": 6.23885246387166e-05, "loss": 1.0722, "step": 8007 }, { "epoch": 0.43781992140782505, "grad_norm": 2.802845001220703, "learning_rate": 6.237994696205221e-05, "loss": 0.9321, "step": 8008 }, { "epoch": 0.43787459422518366, "grad_norm": 2.408681869506836, "learning_rate": 6.237136889722549e-05, "loss": 1.0514, "step": 8009 }, { "epoch": 0.43792926704254226, "grad_norm": 2.8644540309906006, "learning_rate": 6.236279044450542e-05, "loss": 0.9628, "step": 8010 }, { "epoch": 0.4379839398599009, "grad_norm": 2.5714027881622314, "learning_rate": 6.235421160416093e-05, "loss": 0.9925, "step": 8011 }, { "epoch": 0.4380386126772595, "grad_norm": 2.9405124187469482, "learning_rate": 6.234563237646104e-05, "loss": 1.0512, "step": 8012 }, { "epoch": 0.4380932854946181, "grad_norm": 1.8473010063171387, "learning_rate": 6.233705276167473e-05, "loss": 1.0133, "step": 8013 }, { "epoch": 0.4381479583119768, "grad_norm": 2.4974637031555176, "learning_rate": 6.232847276007102e-05, "loss": 1.0191, "step": 8014 }, { "epoch": 0.4382026311293354, "grad_norm": 2.5860469341278076, "learning_rate": 6.23198923719189e-05, "loss": 0.9863, "step": 8015 }, { "epoch": 0.438257303946694, "grad_norm": 2.8489880561828613, "learning_rate": 6.23113115974874e-05, "loss": 1.2211, "step": 8016 }, { "epoch": 0.43831197676405265, "grad_norm": 1.8783208131790161, "learning_rate": 6.23027304370456e-05, "loss": 0.8125, "step": 8017 }, { "epoch": 0.43836664958141125, "grad_norm": 2.2744898796081543, "learning_rate": 6.229414889086253e-05, "loss": 1.2025, "step": 8018 }, { "epoch": 0.43842132239876985, "grad_norm": 2.5235238075256348, "learning_rate": 6.228556695920726e-05, "loss": 1.0096, "step": 8019 }, { "epoch": 0.43847599521612846, "grad_norm": 2.402665615081787, "learning_rate": 6.227698464234887e-05, "loss": 1.0115, "step": 8020 }, { "epoch": 0.4385306680334871, "grad_norm": 3.009110689163208, "learning_rate": 6.226840194055643e-05, "loss": 0.9882, "step": 8021 }, { "epoch": 0.4385853408508457, "grad_norm": 2.1997480392456055, "learning_rate": 6.225981885409908e-05, "loss": 1.1324, "step": 8022 }, { "epoch": 0.4386400136682043, "grad_norm": 2.566363573074341, "learning_rate": 6.225123538324592e-05, "loss": 1.2045, "step": 8023 }, { "epoch": 0.438694686485563, "grad_norm": 3.58520770072937, "learning_rate": 6.224265152826608e-05, "loss": 1.3834, "step": 8024 }, { "epoch": 0.4387493593029216, "grad_norm": 2.844897985458374, "learning_rate": 6.223406728942868e-05, "loss": 1.2444, "step": 8025 }, { "epoch": 0.4388040321202802, "grad_norm": 3.0156078338623047, "learning_rate": 6.222548266700289e-05, "loss": 1.1598, "step": 8026 }, { "epoch": 0.43885870493763884, "grad_norm": 2.5558412075042725, "learning_rate": 6.221689766125787e-05, "loss": 0.8491, "step": 8027 }, { "epoch": 0.43891337775499745, "grad_norm": 2.804514169692993, "learning_rate": 6.220831227246278e-05, "loss": 0.8165, "step": 8028 }, { "epoch": 0.43896805057235605, "grad_norm": 2.776554584503174, "learning_rate": 6.219972650088684e-05, "loss": 1.144, "step": 8029 }, { "epoch": 0.43902272338971465, "grad_norm": 2.7899649143218994, "learning_rate": 6.219114034679922e-05, "loss": 0.9917, "step": 8030 }, { "epoch": 0.4390773962070733, "grad_norm": 2.3090364933013916, "learning_rate": 6.218255381046915e-05, "loss": 0.9901, "step": 8031 }, { "epoch": 0.4391320690244319, "grad_norm": 2.4202587604522705, "learning_rate": 6.217396689216585e-05, "loss": 1.1456, "step": 8032 }, { "epoch": 0.4391867418417905, "grad_norm": 2.5109541416168213, "learning_rate": 6.216537959215854e-05, "loss": 1.1875, "step": 8033 }, { "epoch": 0.4392414146591492, "grad_norm": 2.667292594909668, "learning_rate": 6.215679191071648e-05, "loss": 1.1879, "step": 8034 }, { "epoch": 0.4392960874765078, "grad_norm": 3.5101964473724365, "learning_rate": 6.214820384810891e-05, "loss": 1.1694, "step": 8035 }, { "epoch": 0.4393507602938664, "grad_norm": 2.943028688430786, "learning_rate": 6.213961540460515e-05, "loss": 1.1569, "step": 8036 }, { "epoch": 0.439405433111225, "grad_norm": 3.484066963195801, "learning_rate": 6.213102658047443e-05, "loss": 1.2343, "step": 8037 }, { "epoch": 0.43946010592858364, "grad_norm": 2.6485986709594727, "learning_rate": 6.212243737598607e-05, "loss": 1.1007, "step": 8038 }, { "epoch": 0.43951477874594225, "grad_norm": 2.374451160430908, "learning_rate": 6.211384779140937e-05, "loss": 0.9935, "step": 8039 }, { "epoch": 0.43956945156330085, "grad_norm": 2.689131736755371, "learning_rate": 6.210525782701365e-05, "loss": 1.1501, "step": 8040 }, { "epoch": 0.4396241243806595, "grad_norm": 2.9072721004486084, "learning_rate": 6.209666748306824e-05, "loss": 0.7493, "step": 8041 }, { "epoch": 0.4396787971980181, "grad_norm": 2.1641228199005127, "learning_rate": 6.20880767598425e-05, "loss": 1.094, "step": 8042 }, { "epoch": 0.4397334700153767, "grad_norm": 1.8818297386169434, "learning_rate": 6.207948565760578e-05, "loss": 0.7982, "step": 8043 }, { "epoch": 0.4397881428327354, "grad_norm": 4.05578088760376, "learning_rate": 6.207089417662742e-05, "loss": 0.9494, "step": 8044 }, { "epoch": 0.439842815650094, "grad_norm": 9.01797866821289, "learning_rate": 6.206230231717679e-05, "loss": 1.1248, "step": 8045 }, { "epoch": 0.4398974884674526, "grad_norm": 3.201815605163574, "learning_rate": 6.205371007952334e-05, "loss": 1.1484, "step": 8046 }, { "epoch": 0.4399521612848112, "grad_norm": 2.6530039310455322, "learning_rate": 6.204511746393642e-05, "loss": 1.0398, "step": 8047 }, { "epoch": 0.44000683410216984, "grad_norm": 2.0401134490966797, "learning_rate": 6.203652447068547e-05, "loss": 0.9383, "step": 8048 }, { "epoch": 0.44006150691952844, "grad_norm": 2.5610244274139404, "learning_rate": 6.202793110003989e-05, "loss": 1.1551, "step": 8049 }, { "epoch": 0.44011617973688705, "grad_norm": 2.3170406818389893, "learning_rate": 6.201933735226914e-05, "loss": 1.0825, "step": 8050 }, { "epoch": 0.4401708525542457, "grad_norm": 2.42700457572937, "learning_rate": 6.201074322764268e-05, "loss": 0.8954, "step": 8051 }, { "epoch": 0.4402255253716043, "grad_norm": 2.43112850189209, "learning_rate": 6.200214872642993e-05, "loss": 1.0348, "step": 8052 }, { "epoch": 0.4402801981889629, "grad_norm": 2.8680481910705566, "learning_rate": 6.19935538489004e-05, "loss": 1.1021, "step": 8053 }, { "epoch": 0.44033487100632157, "grad_norm": 2.152280807495117, "learning_rate": 6.198495859532357e-05, "loss": 1.0112, "step": 8054 }, { "epoch": 0.4403895438236802, "grad_norm": 3.7785568237304688, "learning_rate": 6.197636296596892e-05, "loss": 1.0954, "step": 8055 }, { "epoch": 0.4404442166410388, "grad_norm": 2.5063729286193848, "learning_rate": 6.196776696110596e-05, "loss": 0.9371, "step": 8056 }, { "epoch": 0.4404988894583974, "grad_norm": 2.5672028064727783, "learning_rate": 6.195917058100423e-05, "loss": 0.9481, "step": 8057 }, { "epoch": 0.44055356227575604, "grad_norm": 2.299673318862915, "learning_rate": 6.195057382593325e-05, "loss": 0.9598, "step": 8058 }, { "epoch": 0.44060823509311464, "grad_norm": 2.4908580780029297, "learning_rate": 6.194197669616255e-05, "loss": 1.1129, "step": 8059 }, { "epoch": 0.44066290791047324, "grad_norm": 2.2704920768737793, "learning_rate": 6.19333791919617e-05, "loss": 0.8971, "step": 8060 }, { "epoch": 0.4407175807278319, "grad_norm": 2.342359781265259, "learning_rate": 6.192478131360028e-05, "loss": 0.9747, "step": 8061 }, { "epoch": 0.4407722535451905, "grad_norm": 2.6419014930725098, "learning_rate": 6.191618306134784e-05, "loss": 1.2364, "step": 8062 }, { "epoch": 0.4408269263625491, "grad_norm": 2.076524019241333, "learning_rate": 6.1907584435474e-05, "loss": 0.9624, "step": 8063 }, { "epoch": 0.4408815991799077, "grad_norm": 2.590620517730713, "learning_rate": 6.189898543624833e-05, "loss": 1.0301, "step": 8064 }, { "epoch": 0.44093627199726637, "grad_norm": 2.7238500118255615, "learning_rate": 6.189038606394047e-05, "loss": 1.1574, "step": 8065 }, { "epoch": 0.440990944814625, "grad_norm": 2.671313762664795, "learning_rate": 6.188178631882003e-05, "loss": 0.996, "step": 8066 }, { "epoch": 0.4410456176319836, "grad_norm": 2.7666878700256348, "learning_rate": 6.187318620115666e-05, "loss": 0.9003, "step": 8067 }, { "epoch": 0.44110029044934224, "grad_norm": 3.0034196376800537, "learning_rate": 6.186458571122002e-05, "loss": 1.2749, "step": 8068 }, { "epoch": 0.44115496326670084, "grad_norm": 2.4245474338531494, "learning_rate": 6.185598484927973e-05, "loss": 1.1139, "step": 8069 }, { "epoch": 0.44120963608405944, "grad_norm": 2.674421787261963, "learning_rate": 6.184738361560549e-05, "loss": 1.2547, "step": 8070 }, { "epoch": 0.4412643089014181, "grad_norm": 3.2402267456054688, "learning_rate": 6.183878201046699e-05, "loss": 1.3348, "step": 8071 }, { "epoch": 0.4413189817187767, "grad_norm": 2.398038148880005, "learning_rate": 6.183018003413392e-05, "loss": 0.9258, "step": 8072 }, { "epoch": 0.4413736545361353, "grad_norm": 2.7466540336608887, "learning_rate": 6.182157768687597e-05, "loss": 1.208, "step": 8073 }, { "epoch": 0.4414283273534939, "grad_norm": 2.4589154720306396, "learning_rate": 6.181297496896289e-05, "loss": 0.9492, "step": 8074 }, { "epoch": 0.44148300017085257, "grad_norm": 2.339280128479004, "learning_rate": 6.180437188066439e-05, "loss": 1.0193, "step": 8075 }, { "epoch": 0.44153767298821117, "grad_norm": 2.658384323120117, "learning_rate": 6.17957684222502e-05, "loss": 1.1975, "step": 8076 }, { "epoch": 0.4415923458055698, "grad_norm": 2.3538146018981934, "learning_rate": 6.17871645939901e-05, "loss": 0.9935, "step": 8077 }, { "epoch": 0.44164701862292843, "grad_norm": 2.4753963947296143, "learning_rate": 6.177856039615386e-05, "loss": 1.0539, "step": 8078 }, { "epoch": 0.44170169144028704, "grad_norm": 2.3413212299346924, "learning_rate": 6.176995582901122e-05, "loss": 1.1283, "step": 8079 }, { "epoch": 0.44175636425764564, "grad_norm": 2.504810333251953, "learning_rate": 6.176135089283201e-05, "loss": 1.1498, "step": 8080 }, { "epoch": 0.4418110370750043, "grad_norm": 2.016972064971924, "learning_rate": 6.1752745587886e-05, "loss": 0.9007, "step": 8081 }, { "epoch": 0.4418657098923629, "grad_norm": 2.093325138092041, "learning_rate": 6.1744139914443e-05, "loss": 1.0673, "step": 8082 }, { "epoch": 0.4419203827097215, "grad_norm": 2.1152596473693848, "learning_rate": 6.173553387277287e-05, "loss": 0.9926, "step": 8083 }, { "epoch": 0.4419750555270801, "grad_norm": 3.395650625228882, "learning_rate": 6.172692746314541e-05, "loss": 1.2, "step": 8084 }, { "epoch": 0.44202972834443877, "grad_norm": 2.2755868434906006, "learning_rate": 6.171832068583048e-05, "loss": 0.9372, "step": 8085 }, { "epoch": 0.44208440116179737, "grad_norm": 3.091952323913574, "learning_rate": 6.170971354109794e-05, "loss": 1.0146, "step": 8086 }, { "epoch": 0.44213907397915597, "grad_norm": 2.1948204040527344, "learning_rate": 6.170110602921764e-05, "loss": 0.9466, "step": 8087 }, { "epoch": 0.44219374679651463, "grad_norm": 2.3658063411712646, "learning_rate": 6.169249815045949e-05, "loss": 0.8627, "step": 8088 }, { "epoch": 0.44224841961387323, "grad_norm": 3.194199562072754, "learning_rate": 6.168388990509335e-05, "loss": 1.0424, "step": 8089 }, { "epoch": 0.44230309243123184, "grad_norm": 2.365894317626953, "learning_rate": 6.167528129338917e-05, "loss": 0.7854, "step": 8090 }, { "epoch": 0.44235776524859044, "grad_norm": 1.9417816400527954, "learning_rate": 6.166667231561681e-05, "loss": 0.8213, "step": 8091 }, { "epoch": 0.4424124380659491, "grad_norm": 2.373077869415283, "learning_rate": 6.165806297204625e-05, "loss": 1.0579, "step": 8092 }, { "epoch": 0.4424671108833077, "grad_norm": 2.514028787612915, "learning_rate": 6.164945326294739e-05, "loss": 0.9575, "step": 8093 }, { "epoch": 0.4425217837006663, "grad_norm": 3.517606019973755, "learning_rate": 6.164084318859018e-05, "loss": 0.8763, "step": 8094 }, { "epoch": 0.44257645651802496, "grad_norm": 2.616438388824463, "learning_rate": 6.163223274924461e-05, "loss": 1.1282, "step": 8095 }, { "epoch": 0.44263112933538357, "grad_norm": 2.2594752311706543, "learning_rate": 6.162362194518065e-05, "loss": 0.9806, "step": 8096 }, { "epoch": 0.44268580215274217, "grad_norm": 2.331636667251587, "learning_rate": 6.161501077666825e-05, "loss": 1.109, "step": 8097 }, { "epoch": 0.44274047497010083, "grad_norm": 2.0874555110931396, "learning_rate": 6.160639924397743e-05, "loss": 1.085, "step": 8098 }, { "epoch": 0.44279514778745943, "grad_norm": 2.7805793285369873, "learning_rate": 6.159778734737817e-05, "loss": 0.9806, "step": 8099 }, { "epoch": 0.44284982060481803, "grad_norm": 2.4697721004486084, "learning_rate": 6.158917508714056e-05, "loss": 1.0543, "step": 8100 }, { "epoch": 0.44290449342217664, "grad_norm": 3.0561699867248535, "learning_rate": 6.158056246353455e-05, "loss": 1.0596, "step": 8101 }, { "epoch": 0.4429591662395353, "grad_norm": 2.4589178562164307, "learning_rate": 6.157194947683023e-05, "loss": 1.1428, "step": 8102 }, { "epoch": 0.4430138390568939, "grad_norm": 2.849062919616699, "learning_rate": 6.156333612729762e-05, "loss": 0.8892, "step": 8103 }, { "epoch": 0.4430685118742525, "grad_norm": 2.2472970485687256, "learning_rate": 6.15547224152068e-05, "loss": 0.9537, "step": 8104 }, { "epoch": 0.44312318469161116, "grad_norm": 2.6246562004089355, "learning_rate": 6.154610834082786e-05, "loss": 1.0861, "step": 8105 }, { "epoch": 0.44317785750896976, "grad_norm": 2.394998788833618, "learning_rate": 6.153749390443087e-05, "loss": 1.0028, "step": 8106 }, { "epoch": 0.44323253032632837, "grad_norm": 2.701320171356201, "learning_rate": 6.152887910628592e-05, "loss": 1.2835, "step": 8107 }, { "epoch": 0.443287203143687, "grad_norm": 2.7558326721191406, "learning_rate": 6.152026394666313e-05, "loss": 0.956, "step": 8108 }, { "epoch": 0.44334187596104563, "grad_norm": 2.3768930435180664, "learning_rate": 6.151164842583261e-05, "loss": 1.0381, "step": 8109 }, { "epoch": 0.44339654877840423, "grad_norm": 2.5932788848876953, "learning_rate": 6.150303254406453e-05, "loss": 0.9878, "step": 8110 }, { "epoch": 0.44345122159576283, "grad_norm": 3.2495172023773193, "learning_rate": 6.149441630162897e-05, "loss": 1.3399, "step": 8111 }, { "epoch": 0.4435058944131215, "grad_norm": 2.077327013015747, "learning_rate": 6.148579969879615e-05, "loss": 0.8335, "step": 8112 }, { "epoch": 0.4435605672304801, "grad_norm": 2.5668179988861084, "learning_rate": 6.147718273583621e-05, "loss": 1.2242, "step": 8113 }, { "epoch": 0.4436152400478387, "grad_norm": 2.7750742435455322, "learning_rate": 6.146856541301929e-05, "loss": 1.2731, "step": 8114 }, { "epoch": 0.44366991286519736, "grad_norm": 3.200847625732422, "learning_rate": 6.145994773061563e-05, "loss": 0.9759, "step": 8115 }, { "epoch": 0.44372458568255596, "grad_norm": 2.8871560096740723, "learning_rate": 6.145132968889542e-05, "loss": 0.964, "step": 8116 }, { "epoch": 0.44377925849991456, "grad_norm": 2.550662040710449, "learning_rate": 6.144271128812885e-05, "loss": 0.8895, "step": 8117 }, { "epoch": 0.44383393131727317, "grad_norm": 2.622328996658325, "learning_rate": 6.143409252858616e-05, "loss": 1.131, "step": 8118 }, { "epoch": 0.4438886041346318, "grad_norm": 2.2149100303649902, "learning_rate": 6.142547341053757e-05, "loss": 1.1482, "step": 8119 }, { "epoch": 0.44394327695199043, "grad_norm": 4.179569244384766, "learning_rate": 6.141685393425334e-05, "loss": 1.0108, "step": 8120 }, { "epoch": 0.44399794976934903, "grad_norm": 2.704275608062744, "learning_rate": 6.140823410000374e-05, "loss": 1.0725, "step": 8121 }, { "epoch": 0.4440526225867077, "grad_norm": 5.115336894989014, "learning_rate": 6.139961390805899e-05, "loss": 1.2292, "step": 8122 }, { "epoch": 0.4441072954040663, "grad_norm": 1.8699536323547363, "learning_rate": 6.13909933586894e-05, "loss": 0.9512, "step": 8123 }, { "epoch": 0.4441619682214249, "grad_norm": 2.3778483867645264, "learning_rate": 6.138237245216526e-05, "loss": 0.9713, "step": 8124 }, { "epoch": 0.44421664103878356, "grad_norm": 2.324326753616333, "learning_rate": 6.137375118875687e-05, "loss": 0.9307, "step": 8125 }, { "epoch": 0.44427131385614216, "grad_norm": 3.7271435260772705, "learning_rate": 6.136512956873452e-05, "loss": 1.0795, "step": 8126 }, { "epoch": 0.44432598667350076, "grad_norm": 2.457420587539673, "learning_rate": 6.135650759236857e-05, "loss": 0.9835, "step": 8127 }, { "epoch": 0.44438065949085936, "grad_norm": 2.637202262878418, "learning_rate": 6.134788525992933e-05, "loss": 1.1113, "step": 8128 }, { "epoch": 0.444435332308218, "grad_norm": 2.9600284099578857, "learning_rate": 6.133926257168715e-05, "loss": 1.1881, "step": 8129 }, { "epoch": 0.4444900051255766, "grad_norm": 2.875598430633545, "learning_rate": 6.13306395279124e-05, "loss": 1.0629, "step": 8130 }, { "epoch": 0.44454467794293523, "grad_norm": 3.3303589820861816, "learning_rate": 6.132201612887542e-05, "loss": 0.8779, "step": 8131 }, { "epoch": 0.4445993507602939, "grad_norm": 2.3122622966766357, "learning_rate": 6.131339237484662e-05, "loss": 1.0333, "step": 8132 }, { "epoch": 0.4446540235776525, "grad_norm": 2.846025228500366, "learning_rate": 6.130476826609636e-05, "loss": 1.1017, "step": 8133 }, { "epoch": 0.4447086963950111, "grad_norm": 2.8130977153778076, "learning_rate": 6.129614380289507e-05, "loss": 1.0684, "step": 8134 }, { "epoch": 0.44476336921236975, "grad_norm": 2.8241360187530518, "learning_rate": 6.128751898551315e-05, "loss": 1.009, "step": 8135 }, { "epoch": 0.44481804202972836, "grad_norm": 2.560178756713867, "learning_rate": 6.127889381422102e-05, "loss": 1.1318, "step": 8136 }, { "epoch": 0.44487271484708696, "grad_norm": 2.501202344894409, "learning_rate": 6.127026828928912e-05, "loss": 1.0955, "step": 8137 }, { "epoch": 0.44492738766444556, "grad_norm": 2.2799346446990967, "learning_rate": 6.126164241098787e-05, "loss": 1.0444, "step": 8138 }, { "epoch": 0.4449820604818042, "grad_norm": 2.6838090419769287, "learning_rate": 6.125301617958777e-05, "loss": 0.983, "step": 8139 }, { "epoch": 0.4450367332991628, "grad_norm": 2.3140738010406494, "learning_rate": 6.124438959535928e-05, "loss": 1.1354, "step": 8140 }, { "epoch": 0.4450914061165214, "grad_norm": 2.491377592086792, "learning_rate": 6.123576265857284e-05, "loss": 1.1924, "step": 8141 }, { "epoch": 0.4451460789338801, "grad_norm": 2.455648899078369, "learning_rate": 6.122713536949899e-05, "loss": 1.0436, "step": 8142 }, { "epoch": 0.4452007517512387, "grad_norm": 2.3994853496551514, "learning_rate": 6.121850772840818e-05, "loss": 0.9812, "step": 8143 }, { "epoch": 0.4452554245685973, "grad_norm": 2.5186452865600586, "learning_rate": 6.120987973557097e-05, "loss": 1.1087, "step": 8144 }, { "epoch": 0.4453100973859559, "grad_norm": 2.444202423095703, "learning_rate": 6.120125139125788e-05, "loss": 1.0652, "step": 8145 }, { "epoch": 0.44536477020331455, "grad_norm": 2.5664432048797607, "learning_rate": 6.119262269573939e-05, "loss": 0.9427, "step": 8146 }, { "epoch": 0.44541944302067316, "grad_norm": 2.5911009311676025, "learning_rate": 6.118399364928612e-05, "loss": 1.1348, "step": 8147 }, { "epoch": 0.44547411583803176, "grad_norm": 3.04373836517334, "learning_rate": 6.117536425216856e-05, "loss": 1.2045, "step": 8148 }, { "epoch": 0.4455287886553904, "grad_norm": 3.5566625595092773, "learning_rate": 6.116673450465731e-05, "loss": 1.1575, "step": 8149 }, { "epoch": 0.445583461472749, "grad_norm": 2.1286540031433105, "learning_rate": 6.115810440702296e-05, "loss": 0.9004, "step": 8150 }, { "epoch": 0.4456381342901076, "grad_norm": 3.882368803024292, "learning_rate": 6.114947395953608e-05, "loss": 1.0513, "step": 8151 }, { "epoch": 0.4456928071074663, "grad_norm": 3.0272083282470703, "learning_rate": 6.114084316246726e-05, "loss": 0.9564, "step": 8152 }, { "epoch": 0.4457474799248249, "grad_norm": 2.4648847579956055, "learning_rate": 6.113221201608712e-05, "loss": 1.067, "step": 8153 }, { "epoch": 0.4458021527421835, "grad_norm": 2.924166679382324, "learning_rate": 6.112358052066629e-05, "loss": 1.104, "step": 8154 }, { "epoch": 0.4458568255595421, "grad_norm": 2.2463526725769043, "learning_rate": 6.111494867647541e-05, "loss": 1.102, "step": 8155 }, { "epoch": 0.44591149837690075, "grad_norm": 2.3766298294067383, "learning_rate": 6.110631648378511e-05, "loss": 0.9158, "step": 8156 }, { "epoch": 0.44596617119425935, "grad_norm": 3.7029762268066406, "learning_rate": 6.109768394286605e-05, "loss": 0.8834, "step": 8157 }, { "epoch": 0.44602084401161796, "grad_norm": 3.106868267059326, "learning_rate": 6.108905105398887e-05, "loss": 0.8787, "step": 8158 }, { "epoch": 0.4460755168289766, "grad_norm": 2.6067748069763184, "learning_rate": 6.10804178174243e-05, "loss": 0.9713, "step": 8159 }, { "epoch": 0.4461301896463352, "grad_norm": 2.480208158493042, "learning_rate": 6.107178423344298e-05, "loss": 1.0553, "step": 8160 }, { "epoch": 0.4461848624636938, "grad_norm": 2.485490322113037, "learning_rate": 6.106315030231565e-05, "loss": 1.0808, "step": 8161 }, { "epoch": 0.4462395352810524, "grad_norm": 2.251673460006714, "learning_rate": 6.105451602431296e-05, "loss": 0.898, "step": 8162 }, { "epoch": 0.4462942080984111, "grad_norm": 2.906304359436035, "learning_rate": 6.104588139970569e-05, "loss": 1.1366, "step": 8163 }, { "epoch": 0.4463488809157697, "grad_norm": 3.470520496368408, "learning_rate": 6.103724642876454e-05, "loss": 0.8169, "step": 8164 }, { "epoch": 0.4464035537331283, "grad_norm": 2.617236852645874, "learning_rate": 6.102861111176026e-05, "loss": 1.0383, "step": 8165 }, { "epoch": 0.44645822655048695, "grad_norm": 2.3675954341888428, "learning_rate": 6.101997544896359e-05, "loss": 1.0311, "step": 8166 }, { "epoch": 0.44651289936784555, "grad_norm": 3.4374959468841553, "learning_rate": 6.101133944064532e-05, "loss": 1.2327, "step": 8167 }, { "epoch": 0.44656757218520415, "grad_norm": 2.373295307159424, "learning_rate": 6.1002703087076206e-05, "loss": 1.1948, "step": 8168 }, { "epoch": 0.4466222450025628, "grad_norm": 2.3381032943725586, "learning_rate": 6.099406638852701e-05, "loss": 1.0844, "step": 8169 }, { "epoch": 0.4466769178199214, "grad_norm": 1.820388913154602, "learning_rate": 6.0985429345268586e-05, "loss": 0.8553, "step": 8170 }, { "epoch": 0.44673159063728, "grad_norm": 3.423567295074463, "learning_rate": 6.09767919575717e-05, "loss": 1.0941, "step": 8171 }, { "epoch": 0.4467862634546386, "grad_norm": 2.6203744411468506, "learning_rate": 6.0968154225707187e-05, "loss": 0.9392, "step": 8172 }, { "epoch": 0.4468409362719973, "grad_norm": 3.1573188304901123, "learning_rate": 6.095951614994586e-05, "loss": 1.1868, "step": 8173 }, { "epoch": 0.4468956090893559, "grad_norm": 3.3876490592956543, "learning_rate": 6.095087773055856e-05, "loss": 1.2948, "step": 8174 }, { "epoch": 0.4469502819067145, "grad_norm": 2.1881704330444336, "learning_rate": 6.094223896781616e-05, "loss": 0.997, "step": 8175 }, { "epoch": 0.44700495472407314, "grad_norm": 2.562556266784668, "learning_rate": 6.0933599861989475e-05, "loss": 0.9724, "step": 8176 }, { "epoch": 0.44705962754143175, "grad_norm": 2.5815963745117188, "learning_rate": 6.092496041334943e-05, "loss": 1.009, "step": 8177 }, { "epoch": 0.44711430035879035, "grad_norm": 2.8474349975585938, "learning_rate": 6.0916320622166875e-05, "loss": 1.1631, "step": 8178 }, { "epoch": 0.447168973176149, "grad_norm": 2.6677191257476807, "learning_rate": 6.0907680488712706e-05, "loss": 0.7295, "step": 8179 }, { "epoch": 0.4472236459935076, "grad_norm": 2.3985745906829834, "learning_rate": 6.089904001325784e-05, "loss": 1.1255, "step": 8180 }, { "epoch": 0.4472783188108662, "grad_norm": 2.670879364013672, "learning_rate": 6.089039919607318e-05, "loss": 1.0216, "step": 8181 }, { "epoch": 0.4473329916282248, "grad_norm": 3.1100125312805176, "learning_rate": 6.0881758037429636e-05, "loss": 0.9117, "step": 8182 }, { "epoch": 0.4473876644455835, "grad_norm": 2.2206764221191406, "learning_rate": 6.087311653759819e-05, "loss": 0.9615, "step": 8183 }, { "epoch": 0.4474423372629421, "grad_norm": 2.348958969116211, "learning_rate": 6.086447469684974e-05, "loss": 1.0432, "step": 8184 }, { "epoch": 0.4474970100803007, "grad_norm": 2.8975296020507812, "learning_rate": 6.085583251545527e-05, "loss": 0.8659, "step": 8185 }, { "epoch": 0.44755168289765934, "grad_norm": 2.4099578857421875, "learning_rate": 6.084718999368575e-05, "loss": 0.896, "step": 8186 }, { "epoch": 0.44760635571501795, "grad_norm": 2.5973827838897705, "learning_rate": 6.083854713181214e-05, "loss": 1.1647, "step": 8187 }, { "epoch": 0.44766102853237655, "grad_norm": 2.4801621437072754, "learning_rate": 6.082990393010544e-05, "loss": 1.1705, "step": 8188 }, { "epoch": 0.44771570134973515, "grad_norm": 2.021639108657837, "learning_rate": 6.0821260388836645e-05, "loss": 0.9949, "step": 8189 }, { "epoch": 0.4477703741670938, "grad_norm": 2.6987266540527344, "learning_rate": 6.081261650827679e-05, "loss": 1.0349, "step": 8190 }, { "epoch": 0.4478250469844524, "grad_norm": 2.2707011699676514, "learning_rate": 6.0803972288696854e-05, "loss": 0.9778, "step": 8191 }, { "epoch": 0.447879719801811, "grad_norm": 2.323564052581787, "learning_rate": 6.079532773036789e-05, "loss": 1.0415, "step": 8192 }, { "epoch": 0.4479343926191697, "grad_norm": 2.536186695098877, "learning_rate": 6.078668283356096e-05, "loss": 1.1496, "step": 8193 }, { "epoch": 0.4479890654365283, "grad_norm": 2.656554698944092, "learning_rate": 6.0778037598547085e-05, "loss": 0.8668, "step": 8194 }, { "epoch": 0.4480437382538869, "grad_norm": 2.9032504558563232, "learning_rate": 6.076939202559736e-05, "loss": 1.1572, "step": 8195 }, { "epoch": 0.44809841107124554, "grad_norm": 2.5509393215179443, "learning_rate": 6.0760746114982834e-05, "loss": 0.9388, "step": 8196 }, { "epoch": 0.44815308388860414, "grad_norm": 2.994910955429077, "learning_rate": 6.075209986697459e-05, "loss": 1.153, "step": 8197 }, { "epoch": 0.44820775670596275, "grad_norm": 2.425450086593628, "learning_rate": 6.074345328184373e-05, "loss": 0.8768, "step": 8198 }, { "epoch": 0.44826242952332135, "grad_norm": 2.4390335083007812, "learning_rate": 6.073480635986138e-05, "loss": 1.0925, "step": 8199 }, { "epoch": 0.44831710234068, "grad_norm": 2.380871057510376, "learning_rate": 6.072615910129864e-05, "loss": 1.0622, "step": 8200 }, { "epoch": 0.4483717751580386, "grad_norm": 2.796194076538086, "learning_rate": 6.0717511506426626e-05, "loss": 0.913, "step": 8201 }, { "epoch": 0.4484264479753972, "grad_norm": 2.3461124897003174, "learning_rate": 6.0708863575516485e-05, "loss": 1.034, "step": 8202 }, { "epoch": 0.44848112079275587, "grad_norm": 2.9046683311462402, "learning_rate": 6.070021530883938e-05, "loss": 1.1598, "step": 8203 }, { "epoch": 0.4485357936101145, "grad_norm": 2.909498691558838, "learning_rate": 6.069156670666645e-05, "loss": 1.1455, "step": 8204 }, { "epoch": 0.4485904664274731, "grad_norm": 2.173729419708252, "learning_rate": 6.068291776926888e-05, "loss": 0.9438, "step": 8205 }, { "epoch": 0.44864513924483174, "grad_norm": 2.228675365447998, "learning_rate": 6.067426849691783e-05, "loss": 0.9323, "step": 8206 }, { "epoch": 0.44869981206219034, "grad_norm": 2.4191431999206543, "learning_rate": 6.06656188898845e-05, "loss": 0.9632, "step": 8207 }, { "epoch": 0.44875448487954894, "grad_norm": 2.5200579166412354, "learning_rate": 6.0656968948440096e-05, "loss": 1.1656, "step": 8208 }, { "epoch": 0.44880915769690755, "grad_norm": 2.1147377490997314, "learning_rate": 6.064831867285583e-05, "loss": 0.9366, "step": 8209 }, { "epoch": 0.4488638305142662, "grad_norm": 2.7172698974609375, "learning_rate": 6.0639668063402924e-05, "loss": 1.1897, "step": 8210 }, { "epoch": 0.4489185033316248, "grad_norm": 3.323552131652832, "learning_rate": 6.0631017120352597e-05, "loss": 0.8532, "step": 8211 }, { "epoch": 0.4489731761489834, "grad_norm": 3.5784106254577637, "learning_rate": 6.0622365843976095e-05, "loss": 0.8629, "step": 8212 }, { "epoch": 0.44902784896634207, "grad_norm": 2.5835013389587402, "learning_rate": 6.0613714234544674e-05, "loss": 0.9897, "step": 8213 }, { "epoch": 0.44908252178370067, "grad_norm": 3.0331239700317383, "learning_rate": 6.0605062292329606e-05, "loss": 1.1636, "step": 8214 }, { "epoch": 0.4491371946010593, "grad_norm": 2.881279230117798, "learning_rate": 6.059641001760217e-05, "loss": 0.9992, "step": 8215 }, { "epoch": 0.4491918674184179, "grad_norm": 2.7465059757232666, "learning_rate": 6.058775741063363e-05, "loss": 1.1233, "step": 8216 }, { "epoch": 0.44924654023577654, "grad_norm": 2.949702739715576, "learning_rate": 6.057910447169528e-05, "loss": 1.1159, "step": 8217 }, { "epoch": 0.44930121305313514, "grad_norm": 2.3072898387908936, "learning_rate": 6.057045120105844e-05, "loss": 0.9642, "step": 8218 }, { "epoch": 0.44935588587049374, "grad_norm": 2.801971197128296, "learning_rate": 6.056179759899443e-05, "loss": 1.1252, "step": 8219 }, { "epoch": 0.4494105586878524, "grad_norm": 2.4861843585968018, "learning_rate": 6.055314366577457e-05, "loss": 1.0789, "step": 8220 }, { "epoch": 0.449465231505211, "grad_norm": 2.5260162353515625, "learning_rate": 6.054448940167019e-05, "loss": 1.0659, "step": 8221 }, { "epoch": 0.4495199043225696, "grad_norm": 2.5529110431671143, "learning_rate": 6.053583480695263e-05, "loss": 0.9697, "step": 8222 }, { "epoch": 0.44957457713992827, "grad_norm": 2.4261314868927, "learning_rate": 6.052717988189327e-05, "loss": 0.8924, "step": 8223 }, { "epoch": 0.44962924995728687, "grad_norm": 2.6228864192962646, "learning_rate": 6.0518524626763465e-05, "loss": 1.1511, "step": 8224 }, { "epoch": 0.4496839227746455, "grad_norm": 2.1210219860076904, "learning_rate": 6.050986904183459e-05, "loss": 0.994, "step": 8225 }, { "epoch": 0.4497385955920041, "grad_norm": 2.835102081298828, "learning_rate": 6.050121312737803e-05, "loss": 0.9598, "step": 8226 }, { "epoch": 0.44979326840936273, "grad_norm": 2.2338829040527344, "learning_rate": 6.0492556883665195e-05, "loss": 0.8752, "step": 8227 }, { "epoch": 0.44984794122672134, "grad_norm": 4.66346549987793, "learning_rate": 6.048390031096749e-05, "loss": 1.1817, "step": 8228 }, { "epoch": 0.44990261404407994, "grad_norm": 2.734860420227051, "learning_rate": 6.0475243409556325e-05, "loss": 1.2628, "step": 8229 }, { "epoch": 0.4499572868614386, "grad_norm": 2.09549617767334, "learning_rate": 6.046658617970315e-05, "loss": 0.9896, "step": 8230 }, { "epoch": 0.4500119596787972, "grad_norm": 2.3222529888153076, "learning_rate": 6.04579286216794e-05, "loss": 1.0264, "step": 8231 }, { "epoch": 0.4500666324961558, "grad_norm": 2.246497392654419, "learning_rate": 6.044927073575649e-05, "loss": 0.9977, "step": 8232 }, { "epoch": 0.45012130531351446, "grad_norm": 3.144456148147583, "learning_rate": 6.044061252220592e-05, "loss": 1.0843, "step": 8233 }, { "epoch": 0.45017597813087307, "grad_norm": 2.5489063262939453, "learning_rate": 6.043195398129916e-05, "loss": 1.0486, "step": 8234 }, { "epoch": 0.45023065094823167, "grad_norm": 3.0424399375915527, "learning_rate": 6.0423295113307666e-05, "loss": 1.1692, "step": 8235 }, { "epoch": 0.4502853237655903, "grad_norm": 2.131619453430176, "learning_rate": 6.041463591850295e-05, "loss": 0.9008, "step": 8236 }, { "epoch": 0.45033999658294893, "grad_norm": 2.3071084022521973, "learning_rate": 6.0405976397156495e-05, "loss": 1.0767, "step": 8237 }, { "epoch": 0.45039466940030753, "grad_norm": 2.467175245285034, "learning_rate": 6.039731654953984e-05, "loss": 0.9279, "step": 8238 }, { "epoch": 0.45044934221766614, "grad_norm": 2.412198543548584, "learning_rate": 6.038865637592448e-05, "loss": 1.0735, "step": 8239 }, { "epoch": 0.4505040150350248, "grad_norm": 2.055889368057251, "learning_rate": 6.0379995876581964e-05, "loss": 0.9265, "step": 8240 }, { "epoch": 0.4505586878523834, "grad_norm": 1.927783727645874, "learning_rate": 6.0371335051783805e-05, "loss": 0.9484, "step": 8241 }, { "epoch": 0.450613360669742, "grad_norm": 2.4322471618652344, "learning_rate": 6.03626739018016e-05, "loss": 1.0347, "step": 8242 }, { "epoch": 0.4506680334871006, "grad_norm": 2.5360395908355713, "learning_rate": 6.0354012426906894e-05, "loss": 1.1251, "step": 8243 }, { "epoch": 0.45072270630445926, "grad_norm": 2.412639856338501, "learning_rate": 6.034535062737125e-05, "loss": 1.0582, "step": 8244 }, { "epoch": 0.45077737912181787, "grad_norm": 2.670433759689331, "learning_rate": 6.0336688503466255e-05, "loss": 1.07, "step": 8245 }, { "epoch": 0.45083205193917647, "grad_norm": 2.3019251823425293, "learning_rate": 6.032802605546351e-05, "loss": 1.0813, "step": 8246 }, { "epoch": 0.45088672475653513, "grad_norm": 2.985462188720703, "learning_rate": 6.03193632836346e-05, "loss": 1.0565, "step": 8247 }, { "epoch": 0.45094139757389373, "grad_norm": 2.435922145843506, "learning_rate": 6.031070018825117e-05, "loss": 1.171, "step": 8248 }, { "epoch": 0.45099607039125233, "grad_norm": 2.948228359222412, "learning_rate": 6.030203676958481e-05, "loss": 1.0841, "step": 8249 }, { "epoch": 0.451050743208611, "grad_norm": 2.3474295139312744, "learning_rate": 6.029337302790719e-05, "loss": 0.8677, "step": 8250 }, { "epoch": 0.4511054160259696, "grad_norm": 3.1049373149871826, "learning_rate": 6.02847089634899e-05, "loss": 1.0482, "step": 8251 }, { "epoch": 0.4511600888433282, "grad_norm": 2.39521861076355, "learning_rate": 6.027604457660465e-05, "loss": 1.0736, "step": 8252 }, { "epoch": 0.4512147616606868, "grad_norm": 3.1601967811584473, "learning_rate": 6.0267379867523075e-05, "loss": 1.1592, "step": 8253 }, { "epoch": 0.45126943447804546, "grad_norm": 2.525890350341797, "learning_rate": 6.025871483651686e-05, "loss": 1.1169, "step": 8254 }, { "epoch": 0.45132410729540406, "grad_norm": 2.9913907051086426, "learning_rate": 6.0250049483857686e-05, "loss": 1.1745, "step": 8255 }, { "epoch": 0.45137878011276267, "grad_norm": 2.363737106323242, "learning_rate": 6.024138380981723e-05, "loss": 0.9505, "step": 8256 }, { "epoch": 0.4514334529301213, "grad_norm": 2.4242570400238037, "learning_rate": 6.0232717814667225e-05, "loss": 0.905, "step": 8257 }, { "epoch": 0.45148812574747993, "grad_norm": 2.6438190937042236, "learning_rate": 6.0224051498679376e-05, "loss": 1.0145, "step": 8258 }, { "epoch": 0.45154279856483853, "grad_norm": 3.567216157913208, "learning_rate": 6.021538486212541e-05, "loss": 1.1965, "step": 8259 }, { "epoch": 0.4515974713821972, "grad_norm": 2.0768353939056396, "learning_rate": 6.0206717905277054e-05, "loss": 1.1539, "step": 8260 }, { "epoch": 0.4516521441995558, "grad_norm": 2.2603299617767334, "learning_rate": 6.019805062840606e-05, "loss": 0.9558, "step": 8261 }, { "epoch": 0.4517068170169144, "grad_norm": 2.515951633453369, "learning_rate": 6.018938303178416e-05, "loss": 0.9909, "step": 8262 }, { "epoch": 0.451761489834273, "grad_norm": 3.9220194816589355, "learning_rate": 6.018071511568315e-05, "loss": 1.1507, "step": 8263 }, { "epoch": 0.45181616265163166, "grad_norm": 2.707857131958008, "learning_rate": 6.017204688037479e-05, "loss": 0.985, "step": 8264 }, { "epoch": 0.45187083546899026, "grad_norm": 2.4636130332946777, "learning_rate": 6.0163378326130874e-05, "loss": 1.0897, "step": 8265 }, { "epoch": 0.45192550828634886, "grad_norm": 2.4333534240722656, "learning_rate": 6.015470945322319e-05, "loss": 1.1557, "step": 8266 }, { "epoch": 0.4519801811037075, "grad_norm": 2.855628252029419, "learning_rate": 6.014604026192354e-05, "loss": 1.2588, "step": 8267 }, { "epoch": 0.4520348539210661, "grad_norm": 3.3486721515655518, "learning_rate": 6.013737075250374e-05, "loss": 1.0527, "step": 8268 }, { "epoch": 0.45208952673842473, "grad_norm": 2.3267946243286133, "learning_rate": 6.0128700925235616e-05, "loss": 1.0906, "step": 8269 }, { "epoch": 0.45214419955578333, "grad_norm": 2.0909178256988525, "learning_rate": 6.0120030780391e-05, "loss": 0.9392, "step": 8270 }, { "epoch": 0.452198872373142, "grad_norm": 2.3082990646362305, "learning_rate": 6.011136031824175e-05, "loss": 1.1739, "step": 8271 }, { "epoch": 0.4522535451905006, "grad_norm": 2.615340232849121, "learning_rate": 6.010268953905971e-05, "loss": 1.018, "step": 8272 }, { "epoch": 0.4523082180078592, "grad_norm": 2.431100606918335, "learning_rate": 6.009401844311675e-05, "loss": 1.0566, "step": 8273 }, { "epoch": 0.45236289082521786, "grad_norm": 3.0012166500091553, "learning_rate": 6.008534703068474e-05, "loss": 0.8586, "step": 8274 }, { "epoch": 0.45241756364257646, "grad_norm": 2.9688785076141357, "learning_rate": 6.0076675302035556e-05, "loss": 0.9142, "step": 8275 }, { "epoch": 0.45247223645993506, "grad_norm": 2.5916194915771484, "learning_rate": 6.0068003257441085e-05, "loss": 1.1188, "step": 8276 }, { "epoch": 0.4525269092772937, "grad_norm": 2.403113842010498, "learning_rate": 6.005933089717327e-05, "loss": 0.9752, "step": 8277 }, { "epoch": 0.4525815820946523, "grad_norm": 2.430997371673584, "learning_rate": 6.0050658221504e-05, "loss": 0.8348, "step": 8278 }, { "epoch": 0.4526362549120109, "grad_norm": 2.7976744174957275, "learning_rate": 6.00419852307052e-05, "loss": 1.1772, "step": 8279 }, { "epoch": 0.45269092772936953, "grad_norm": 3.60284161567688, "learning_rate": 6.0033311925048805e-05, "loss": 1.159, "step": 8280 }, { "epoch": 0.4527456005467282, "grad_norm": 2.078305721282959, "learning_rate": 6.0024638304806756e-05, "loss": 0.9861, "step": 8281 }, { "epoch": 0.4528002733640868, "grad_norm": 2.3994712829589844, "learning_rate": 6.001596437025102e-05, "loss": 1.0489, "step": 8282 }, { "epoch": 0.4528549461814454, "grad_norm": 2.379992723464966, "learning_rate": 6.0007290121653545e-05, "loss": 0.9231, "step": 8283 }, { "epoch": 0.45290961899880405, "grad_norm": 2.198387861251831, "learning_rate": 5.999861555928632e-05, "loss": 1.1119, "step": 8284 }, { "epoch": 0.45296429181616266, "grad_norm": 2.454561710357666, "learning_rate": 5.9989940683421306e-05, "loss": 1.1037, "step": 8285 }, { "epoch": 0.45301896463352126, "grad_norm": 2.8192121982574463, "learning_rate": 5.998126549433051e-05, "loss": 0.8032, "step": 8286 }, { "epoch": 0.4530736374508799, "grad_norm": 2.455101728439331, "learning_rate": 5.997258999228593e-05, "loss": 1.0112, "step": 8287 }, { "epoch": 0.4531283102682385, "grad_norm": 2.405789375305176, "learning_rate": 5.996391417755959e-05, "loss": 1.1723, "step": 8288 }, { "epoch": 0.4531829830855971, "grad_norm": 2.817535638809204, "learning_rate": 5.9955238050423514e-05, "loss": 1.0851, "step": 8289 }, { "epoch": 0.4532376559029557, "grad_norm": 2.857346773147583, "learning_rate": 5.994656161114971e-05, "loss": 1.1643, "step": 8290 }, { "epoch": 0.4532923287203144, "grad_norm": 4.485684394836426, "learning_rate": 5.993788486001023e-05, "loss": 0.8986, "step": 8291 }, { "epoch": 0.453347001537673, "grad_norm": 2.9990572929382324, "learning_rate": 5.992920779727714e-05, "loss": 0.9825, "step": 8292 }, { "epoch": 0.4534016743550316, "grad_norm": 2.2586746215820312, "learning_rate": 5.99205304232225e-05, "loss": 1.0139, "step": 8293 }, { "epoch": 0.45345634717239025, "grad_norm": 2.8931214809417725, "learning_rate": 5.991185273811837e-05, "loss": 0.9613, "step": 8294 }, { "epoch": 0.45351101998974885, "grad_norm": 2.5839991569519043, "learning_rate": 5.990317474223682e-05, "loss": 1.0933, "step": 8295 }, { "epoch": 0.45356569280710746, "grad_norm": 3.4844512939453125, "learning_rate": 5.989449643584998e-05, "loss": 1.2292, "step": 8296 }, { "epoch": 0.45362036562446606, "grad_norm": 2.5718395709991455, "learning_rate": 5.988581781922992e-05, "loss": 1.144, "step": 8297 }, { "epoch": 0.4536750384418247, "grad_norm": 3.1782310009002686, "learning_rate": 5.987713889264874e-05, "loss": 1.0482, "step": 8298 }, { "epoch": 0.4537297112591833, "grad_norm": 2.3810489177703857, "learning_rate": 5.9868459656378596e-05, "loss": 1.2658, "step": 8299 }, { "epoch": 0.4537843840765419, "grad_norm": 2.011976480484009, "learning_rate": 5.9859780110691585e-05, "loss": 0.7779, "step": 8300 }, { "epoch": 0.4538390568939006, "grad_norm": 3.1618685722351074, "learning_rate": 5.985110025585988e-05, "loss": 1.1897, "step": 8301 }, { "epoch": 0.4538937297112592, "grad_norm": 4.231395244598389, "learning_rate": 5.98424200921556e-05, "loss": 1.2257, "step": 8302 }, { "epoch": 0.4539484025286178, "grad_norm": 3.0959932804107666, "learning_rate": 5.9833739619850914e-05, "loss": 0.8019, "step": 8303 }, { "epoch": 0.45400307534597645, "grad_norm": 2.232781171798706, "learning_rate": 5.9825058839217994e-05, "loss": 1.1298, "step": 8304 }, { "epoch": 0.45405774816333505, "grad_norm": 2.701258897781372, "learning_rate": 5.981637775052901e-05, "loss": 1.1271, "step": 8305 }, { "epoch": 0.45411242098069365, "grad_norm": 2.276721477508545, "learning_rate": 5.980769635405616e-05, "loss": 1.0823, "step": 8306 }, { "epoch": 0.45416709379805226, "grad_norm": 4.0049262046813965, "learning_rate": 5.979901465007164e-05, "loss": 1.4157, "step": 8307 }, { "epoch": 0.4542217666154109, "grad_norm": 2.387406349182129, "learning_rate": 5.9790332638847655e-05, "loss": 1.0113, "step": 8308 }, { "epoch": 0.4542764394327695, "grad_norm": 2.737351179122925, "learning_rate": 5.978165032065641e-05, "loss": 1.2197, "step": 8309 }, { "epoch": 0.4543311122501281, "grad_norm": 2.617727518081665, "learning_rate": 5.9772967695770144e-05, "loss": 0.9559, "step": 8310 }, { "epoch": 0.4543857850674868, "grad_norm": 2.368886709213257, "learning_rate": 5.9764284764461095e-05, "loss": 1.0003, "step": 8311 }, { "epoch": 0.4544404578848454, "grad_norm": 2.5107929706573486, "learning_rate": 5.9755601527001515e-05, "loss": 1.1263, "step": 8312 }, { "epoch": 0.454495130702204, "grad_norm": 2.701183795928955, "learning_rate": 5.974691798366364e-05, "loss": 1.1534, "step": 8313 }, { "epoch": 0.45454980351956265, "grad_norm": 2.6786856651306152, "learning_rate": 5.973823413471975e-05, "loss": 1.2898, "step": 8314 }, { "epoch": 0.45460447633692125, "grad_norm": 2.256483793258667, "learning_rate": 5.97295499804421e-05, "loss": 0.9345, "step": 8315 }, { "epoch": 0.45465914915427985, "grad_norm": 2.7409822940826416, "learning_rate": 5.9720865521103e-05, "loss": 0.9645, "step": 8316 }, { "epoch": 0.45471382197163845, "grad_norm": 2.3459560871124268, "learning_rate": 5.9712180756974737e-05, "loss": 1.0965, "step": 8317 }, { "epoch": 0.4547684947889971, "grad_norm": 3.295973062515259, "learning_rate": 5.97034956883296e-05, "loss": 1.1268, "step": 8318 }, { "epoch": 0.4548231676063557, "grad_norm": 2.6707913875579834, "learning_rate": 5.969481031543991e-05, "loss": 1.1795, "step": 8319 }, { "epoch": 0.4548778404237143, "grad_norm": 2.8950142860412598, "learning_rate": 5.968612463857798e-05, "loss": 1.1152, "step": 8320 }, { "epoch": 0.454932513241073, "grad_norm": 2.416041374206543, "learning_rate": 5.967743865801616e-05, "loss": 1.078, "step": 8321 }, { "epoch": 0.4549871860584316, "grad_norm": 2.640148878097534, "learning_rate": 5.966875237402678e-05, "loss": 0.8942, "step": 8322 }, { "epoch": 0.4550418588757902, "grad_norm": 2.2998085021972656, "learning_rate": 5.96600657868822e-05, "loss": 0.9476, "step": 8323 }, { "epoch": 0.4550965316931488, "grad_norm": 2.8796515464782715, "learning_rate": 5.965137889685477e-05, "loss": 1.0986, "step": 8324 }, { "epoch": 0.45515120451050745, "grad_norm": 2.681016683578491, "learning_rate": 5.964269170421685e-05, "loss": 1.075, "step": 8325 }, { "epoch": 0.45520587732786605, "grad_norm": 2.018112897872925, "learning_rate": 5.9634004209240844e-05, "loss": 0.9445, "step": 8326 }, { "epoch": 0.45526055014522465, "grad_norm": 2.411878824234009, "learning_rate": 5.962531641219913e-05, "loss": 0.9724, "step": 8327 }, { "epoch": 0.4553152229625833, "grad_norm": 3.5402228832244873, "learning_rate": 5.961662831336411e-05, "loss": 0.8877, "step": 8328 }, { "epoch": 0.4553698957799419, "grad_norm": 2.6410064697265625, "learning_rate": 5.960793991300818e-05, "loss": 0.9983, "step": 8329 }, { "epoch": 0.4554245685973005, "grad_norm": 2.389986991882324, "learning_rate": 5.959925121140375e-05, "loss": 1.3502, "step": 8330 }, { "epoch": 0.4554792414146592, "grad_norm": 2.2570555210113525, "learning_rate": 5.959056220882329e-05, "loss": 1.0275, "step": 8331 }, { "epoch": 0.4555339142320178, "grad_norm": 2.41019606590271, "learning_rate": 5.958187290553918e-05, "loss": 1.0955, "step": 8332 }, { "epoch": 0.4555885870493764, "grad_norm": 2.6381518840789795, "learning_rate": 5.957318330182391e-05, "loss": 1.1323, "step": 8333 }, { "epoch": 0.455643259866735, "grad_norm": 2.508328676223755, "learning_rate": 5.956449339794992e-05, "loss": 0.8871, "step": 8334 }, { "epoch": 0.45569793268409364, "grad_norm": 3.4095230102539062, "learning_rate": 5.9555803194189653e-05, "loss": 0.992, "step": 8335 }, { "epoch": 0.45575260550145225, "grad_norm": 1.9330368041992188, "learning_rate": 5.954711269081561e-05, "loss": 0.759, "step": 8336 }, { "epoch": 0.45580727831881085, "grad_norm": 2.1568984985351562, "learning_rate": 5.953842188810027e-05, "loss": 1.1044, "step": 8337 }, { "epoch": 0.4558619511361695, "grad_norm": 2.448932647705078, "learning_rate": 5.952973078631612e-05, "loss": 1.1293, "step": 8338 }, { "epoch": 0.4559166239535281, "grad_norm": 5.54947566986084, "learning_rate": 5.9521039385735655e-05, "loss": 1.1507, "step": 8339 }, { "epoch": 0.4559712967708867, "grad_norm": 2.6733155250549316, "learning_rate": 5.951234768663139e-05, "loss": 1.1261, "step": 8340 }, { "epoch": 0.4560259695882453, "grad_norm": 2.5367093086242676, "learning_rate": 5.950365568927585e-05, "loss": 1.0577, "step": 8341 }, { "epoch": 0.456080642405604, "grad_norm": 2.460893392562866, "learning_rate": 5.949496339394157e-05, "loss": 0.8813, "step": 8342 }, { "epoch": 0.4561353152229626, "grad_norm": 2.4403557777404785, "learning_rate": 5.948627080090109e-05, "loss": 1.1834, "step": 8343 }, { "epoch": 0.4561899880403212, "grad_norm": 2.217484951019287, "learning_rate": 5.947757791042695e-05, "loss": 1.1851, "step": 8344 }, { "epoch": 0.45624466085767984, "grad_norm": 2.418020248413086, "learning_rate": 5.94688847227917e-05, "loss": 0.9498, "step": 8345 }, { "epoch": 0.45629933367503844, "grad_norm": 2.351763963699341, "learning_rate": 5.9460191238267914e-05, "loss": 1.0242, "step": 8346 }, { "epoch": 0.45635400649239705, "grad_norm": 2.1035661697387695, "learning_rate": 5.945149745712818e-05, "loss": 0.8764, "step": 8347 }, { "epoch": 0.4564086793097557, "grad_norm": 1.966633677482605, "learning_rate": 5.944280337964509e-05, "loss": 0.9594, "step": 8348 }, { "epoch": 0.4564633521271143, "grad_norm": 2.5938539505004883, "learning_rate": 5.9434109006091196e-05, "loss": 0.9732, "step": 8349 }, { "epoch": 0.4565180249444729, "grad_norm": 4.274244785308838, "learning_rate": 5.942541433673914e-05, "loss": 1.1553, "step": 8350 }, { "epoch": 0.4565726977618315, "grad_norm": 2.6032540798187256, "learning_rate": 5.9416719371861526e-05, "loss": 1.0722, "step": 8351 }, { "epoch": 0.4566273705791902, "grad_norm": 2.491734266281128, "learning_rate": 5.940802411173099e-05, "loss": 0.9822, "step": 8352 }, { "epoch": 0.4566820433965488, "grad_norm": 3.4813005924224854, "learning_rate": 5.939932855662015e-05, "loss": 1.1437, "step": 8353 }, { "epoch": 0.4567367162139074, "grad_norm": 2.593125820159912, "learning_rate": 5.939063270680164e-05, "loss": 1.135, "step": 8354 }, { "epoch": 0.45679138903126604, "grad_norm": 2.1530869007110596, "learning_rate": 5.938193656254812e-05, "loss": 1.1356, "step": 8355 }, { "epoch": 0.45684606184862464, "grad_norm": 2.5261542797088623, "learning_rate": 5.9373240124132243e-05, "loss": 0.829, "step": 8356 }, { "epoch": 0.45690073466598324, "grad_norm": 2.5223586559295654, "learning_rate": 5.936454339182671e-05, "loss": 1.0784, "step": 8357 }, { "epoch": 0.4569554074833419, "grad_norm": 2.3175461292266846, "learning_rate": 5.9355846365904157e-05, "loss": 1.0476, "step": 8358 }, { "epoch": 0.4570100803007005, "grad_norm": 2.1323630809783936, "learning_rate": 5.9347149046637296e-05, "loss": 1.0745, "step": 8359 }, { "epoch": 0.4570647531180591, "grad_norm": 3.496103525161743, "learning_rate": 5.933845143429882e-05, "loss": 0.7575, "step": 8360 }, { "epoch": 0.4571194259354177, "grad_norm": 2.107301712036133, "learning_rate": 5.932975352916141e-05, "loss": 0.9082, "step": 8361 }, { "epoch": 0.45717409875277637, "grad_norm": 2.5627939701080322, "learning_rate": 5.9321055331497823e-05, "loss": 1.0045, "step": 8362 }, { "epoch": 0.457228771570135, "grad_norm": 2.2242510318756104, "learning_rate": 5.931235684158075e-05, "loss": 1.0935, "step": 8363 }, { "epoch": 0.4572834443874936, "grad_norm": 2.8133738040924072, "learning_rate": 5.930365805968294e-05, "loss": 1.1251, "step": 8364 }, { "epoch": 0.45733811720485223, "grad_norm": 2.9978818893432617, "learning_rate": 5.929495898607715e-05, "loss": 0.848, "step": 8365 }, { "epoch": 0.45739279002221084, "grad_norm": 3.383408784866333, "learning_rate": 5.92862596210361e-05, "loss": 1.0787, "step": 8366 }, { "epoch": 0.45744746283956944, "grad_norm": 3.1794638633728027, "learning_rate": 5.9277559964832575e-05, "loss": 1.071, "step": 8367 }, { "epoch": 0.45750213565692804, "grad_norm": 2.5847322940826416, "learning_rate": 5.926886001773934e-05, "loss": 1.1945, "step": 8368 }, { "epoch": 0.4575568084742867, "grad_norm": 1.9094904661178589, "learning_rate": 5.9260159780029145e-05, "loss": 0.9994, "step": 8369 }, { "epoch": 0.4576114812916453, "grad_norm": 3.1207165718078613, "learning_rate": 5.9251459251974814e-05, "loss": 1.1399, "step": 8370 }, { "epoch": 0.4576661541090039, "grad_norm": 2.7049641609191895, "learning_rate": 5.9242758433849144e-05, "loss": 1.0636, "step": 8371 }, { "epoch": 0.45772082692636257, "grad_norm": 2.2217936515808105, "learning_rate": 5.923405732592493e-05, "loss": 0.9891, "step": 8372 }, { "epoch": 0.45777549974372117, "grad_norm": 2.2268285751342773, "learning_rate": 5.922535592847499e-05, "loss": 0.9832, "step": 8373 }, { "epoch": 0.4578301725610798, "grad_norm": 3.2794158458709717, "learning_rate": 5.921665424177214e-05, "loss": 0.8466, "step": 8374 }, { "epoch": 0.45788484537843843, "grad_norm": 2.771880626678467, "learning_rate": 5.9207952266089215e-05, "loss": 0.944, "step": 8375 }, { "epoch": 0.45793951819579704, "grad_norm": 2.964871406555176, "learning_rate": 5.919925000169908e-05, "loss": 1.1726, "step": 8376 }, { "epoch": 0.45799419101315564, "grad_norm": 2.1679375171661377, "learning_rate": 5.919054744887457e-05, "loss": 0.984, "step": 8377 }, { "epoch": 0.45804886383051424, "grad_norm": 2.656275749206543, "learning_rate": 5.918184460788854e-05, "loss": 1.1794, "step": 8378 }, { "epoch": 0.4581035366478729, "grad_norm": 2.3310813903808594, "learning_rate": 5.917314147901386e-05, "loss": 0.9919, "step": 8379 }, { "epoch": 0.4581582094652315, "grad_norm": 2.990123987197876, "learning_rate": 5.916443806252343e-05, "loss": 1.1806, "step": 8380 }, { "epoch": 0.4582128822825901, "grad_norm": 2.5220861434936523, "learning_rate": 5.915573435869012e-05, "loss": 0.9071, "step": 8381 }, { "epoch": 0.45826755509994876, "grad_norm": 1.9898220300674438, "learning_rate": 5.9147030367786825e-05, "loss": 0.8833, "step": 8382 }, { "epoch": 0.45832222791730737, "grad_norm": 2.3597004413604736, "learning_rate": 5.9138326090086474e-05, "loss": 0.9153, "step": 8383 }, { "epoch": 0.45837690073466597, "grad_norm": 2.182419776916504, "learning_rate": 5.9129621525861935e-05, "loss": 0.8284, "step": 8384 }, { "epoch": 0.45843157355202463, "grad_norm": 2.962985038757324, "learning_rate": 5.9120916675386175e-05, "loss": 0.9183, "step": 8385 }, { "epoch": 0.45848624636938323, "grad_norm": 2.3050758838653564, "learning_rate": 5.9112211538932115e-05, "loss": 0.9625, "step": 8386 }, { "epoch": 0.45854091918674184, "grad_norm": 3.2174479961395264, "learning_rate": 5.91035061167727e-05, "loss": 1.1382, "step": 8387 }, { "epoch": 0.45859559200410044, "grad_norm": 2.4350411891937256, "learning_rate": 5.909480040918087e-05, "loss": 1.007, "step": 8388 }, { "epoch": 0.4586502648214591, "grad_norm": 2.746844530105591, "learning_rate": 5.908609441642958e-05, "loss": 1.1321, "step": 8389 }, { "epoch": 0.4587049376388177, "grad_norm": 2.8831489086151123, "learning_rate": 5.9077388138791836e-05, "loss": 1.0152, "step": 8390 }, { "epoch": 0.4587596104561763, "grad_norm": 2.5153448581695557, "learning_rate": 5.906868157654057e-05, "loss": 0.9023, "step": 8391 }, { "epoch": 0.45881428327353496, "grad_norm": 3.2036542892456055, "learning_rate": 5.90599747299488e-05, "loss": 1.0868, "step": 8392 }, { "epoch": 0.45886895609089356, "grad_norm": 2.4970247745513916, "learning_rate": 5.90512675992895e-05, "loss": 1.1468, "step": 8393 }, { "epoch": 0.45892362890825217, "grad_norm": 2.946532964706421, "learning_rate": 5.904256018483568e-05, "loss": 1.1631, "step": 8394 }, { "epoch": 0.45897830172561077, "grad_norm": 1.9192067384719849, "learning_rate": 5.903385248686036e-05, "loss": 0.7169, "step": 8395 }, { "epoch": 0.45903297454296943, "grad_norm": 2.6338932514190674, "learning_rate": 5.902514450563657e-05, "loss": 1.016, "step": 8396 }, { "epoch": 0.45908764736032803, "grad_norm": 2.2578158378601074, "learning_rate": 5.901643624143732e-05, "loss": 0.9944, "step": 8397 }, { "epoch": 0.45914232017768664, "grad_norm": 2.4301419258117676, "learning_rate": 5.9007727694535664e-05, "loss": 0.9646, "step": 8398 }, { "epoch": 0.4591969929950453, "grad_norm": 2.649878978729248, "learning_rate": 5.899901886520465e-05, "loss": 1.0401, "step": 8399 }, { "epoch": 0.4592516658124039, "grad_norm": 2.633052110671997, "learning_rate": 5.899030975371732e-05, "loss": 1.0791, "step": 8400 }, { "epoch": 0.4593063386297625, "grad_norm": 3.1255061626434326, "learning_rate": 5.898160036034677e-05, "loss": 1.091, "step": 8401 }, { "epoch": 0.45936101144712116, "grad_norm": 2.764806032180786, "learning_rate": 5.897289068536604e-05, "loss": 1.0926, "step": 8402 }, { "epoch": 0.45941568426447976, "grad_norm": 2.3143749237060547, "learning_rate": 5.896418072904824e-05, "loss": 1.0437, "step": 8403 }, { "epoch": 0.45947035708183837, "grad_norm": 2.935728073120117, "learning_rate": 5.895547049166647e-05, "loss": 1.0496, "step": 8404 }, { "epoch": 0.45952502989919697, "grad_norm": 2.9854233264923096, "learning_rate": 5.8946759973493805e-05, "loss": 1.2348, "step": 8405 }, { "epoch": 0.4595797027165556, "grad_norm": 2.1888859272003174, "learning_rate": 5.8938049174803366e-05, "loss": 1.0292, "step": 8406 }, { "epoch": 0.45963437553391423, "grad_norm": 2.063124895095825, "learning_rate": 5.892933809586829e-05, "loss": 1.1794, "step": 8407 }, { "epoch": 0.45968904835127283, "grad_norm": 2.609449625015259, "learning_rate": 5.892062673696166e-05, "loss": 1.1762, "step": 8408 }, { "epoch": 0.4597437211686315, "grad_norm": 2.3451600074768066, "learning_rate": 5.8911915098356675e-05, "loss": 1.0103, "step": 8409 }, { "epoch": 0.4597983939859901, "grad_norm": 2.5215635299682617, "learning_rate": 5.890320318032643e-05, "loss": 0.9825, "step": 8410 }, { "epoch": 0.4598530668033487, "grad_norm": 2.4576377868652344, "learning_rate": 5.8894490983144104e-05, "loss": 1.0952, "step": 8411 }, { "epoch": 0.45990773962070736, "grad_norm": 2.5002217292785645, "learning_rate": 5.888577850708286e-05, "loss": 1.0635, "step": 8412 }, { "epoch": 0.45996241243806596, "grad_norm": 2.9935786724090576, "learning_rate": 5.887706575241585e-05, "loss": 1.0715, "step": 8413 }, { "epoch": 0.46001708525542456, "grad_norm": 2.297964096069336, "learning_rate": 5.8868352719416276e-05, "loss": 1.1265, "step": 8414 }, { "epoch": 0.46007175807278317, "grad_norm": 3.0116336345672607, "learning_rate": 5.885963940835732e-05, "loss": 1.1815, "step": 8415 }, { "epoch": 0.4601264308901418, "grad_norm": 2.574913501739502, "learning_rate": 5.885092581951218e-05, "loss": 1.0189, "step": 8416 }, { "epoch": 0.4601811037075004, "grad_norm": 2.8220136165618896, "learning_rate": 5.884221195315407e-05, "loss": 1.1054, "step": 8417 }, { "epoch": 0.46023577652485903, "grad_norm": 2.976776599884033, "learning_rate": 5.8833497809556195e-05, "loss": 1.0569, "step": 8418 }, { "epoch": 0.4602904493422177, "grad_norm": 2.1785900592803955, "learning_rate": 5.8824783388991776e-05, "loss": 0.956, "step": 8419 }, { "epoch": 0.4603451221595763, "grad_norm": 2.111936092376709, "learning_rate": 5.8816068691734064e-05, "loss": 1.069, "step": 8420 }, { "epoch": 0.4603997949769349, "grad_norm": 2.3467986583709717, "learning_rate": 5.880735371805629e-05, "loss": 0.9585, "step": 8421 }, { "epoch": 0.4604544677942935, "grad_norm": 2.1245341300964355, "learning_rate": 5.87986384682317e-05, "loss": 0.9341, "step": 8422 }, { "epoch": 0.46050914061165216, "grad_norm": 4.196619510650635, "learning_rate": 5.878992294253355e-05, "loss": 1.0365, "step": 8423 }, { "epoch": 0.46056381342901076, "grad_norm": 4.862560749053955, "learning_rate": 5.8781207141235125e-05, "loss": 1.1155, "step": 8424 }, { "epoch": 0.46061848624636936, "grad_norm": 2.603379964828491, "learning_rate": 5.877249106460969e-05, "loss": 1.0702, "step": 8425 }, { "epoch": 0.460673159063728, "grad_norm": 2.1634018421173096, "learning_rate": 5.876377471293054e-05, "loss": 0.9308, "step": 8426 }, { "epoch": 0.4607278318810866, "grad_norm": 2.2838029861450195, "learning_rate": 5.875505808647095e-05, "loss": 0.8722, "step": 8427 }, { "epoch": 0.4607825046984452, "grad_norm": 2.47153902053833, "learning_rate": 5.874634118550423e-05, "loss": 1.0819, "step": 8428 }, { "epoch": 0.4608371775158039, "grad_norm": 2.147078275680542, "learning_rate": 5.873762401030369e-05, "loss": 1.0933, "step": 8429 }, { "epoch": 0.4608918503331625, "grad_norm": 2.704838514328003, "learning_rate": 5.872890656114266e-05, "loss": 1.0493, "step": 8430 }, { "epoch": 0.4609465231505211, "grad_norm": 2.2110652923583984, "learning_rate": 5.872018883829447e-05, "loss": 0.941, "step": 8431 }, { "epoch": 0.4610011959678797, "grad_norm": 3.2359273433685303, "learning_rate": 5.871147084203244e-05, "loss": 1.0346, "step": 8432 }, { "epoch": 0.46105586878523835, "grad_norm": 2.3477885723114014, "learning_rate": 5.8702752572629894e-05, "loss": 0.9422, "step": 8433 }, { "epoch": 0.46111054160259696, "grad_norm": 2.345980167388916, "learning_rate": 5.869403403036023e-05, "loss": 1.3021, "step": 8434 }, { "epoch": 0.46116521441995556, "grad_norm": 4.016470432281494, "learning_rate": 5.86853152154968e-05, "loss": 1.1366, "step": 8435 }, { "epoch": 0.4612198872373142, "grad_norm": 2.591897487640381, "learning_rate": 5.867659612831298e-05, "loss": 1.1684, "step": 8436 }, { "epoch": 0.4612745600546728, "grad_norm": 2.1636593341827393, "learning_rate": 5.866787676908212e-05, "loss": 1.0854, "step": 8437 }, { "epoch": 0.4613292328720314, "grad_norm": 2.117457866668701, "learning_rate": 5.8659157138077624e-05, "loss": 1.0335, "step": 8438 }, { "epoch": 0.4613839056893901, "grad_norm": 2.715751886367798, "learning_rate": 5.86504372355729e-05, "loss": 1.1961, "step": 8439 }, { "epoch": 0.4614385785067487, "grad_norm": 2.536088466644287, "learning_rate": 5.864171706184134e-05, "loss": 0.8905, "step": 8440 }, { "epoch": 0.4614932513241073, "grad_norm": 2.413001537322998, "learning_rate": 5.863299661715635e-05, "loss": 1.2413, "step": 8441 }, { "epoch": 0.4615479241414659, "grad_norm": 3.1308341026306152, "learning_rate": 5.862427590179137e-05, "loss": 0.896, "step": 8442 }, { "epoch": 0.46160259695882455, "grad_norm": 2.849896192550659, "learning_rate": 5.861555491601981e-05, "loss": 1.2781, "step": 8443 }, { "epoch": 0.46165726977618315, "grad_norm": 2.527437686920166, "learning_rate": 5.860683366011514e-05, "loss": 1.1103, "step": 8444 }, { "epoch": 0.46171194259354176, "grad_norm": 2.014732837677002, "learning_rate": 5.859811213435078e-05, "loss": 0.7909, "step": 8445 }, { "epoch": 0.4617666154109004, "grad_norm": 2.5332932472229004, "learning_rate": 5.8589390339000195e-05, "loss": 1.0357, "step": 8446 }, { "epoch": 0.461821288228259, "grad_norm": 3.008936882019043, "learning_rate": 5.858066827433685e-05, "loss": 1.1571, "step": 8447 }, { "epoch": 0.4618759610456176, "grad_norm": 2.624749183654785, "learning_rate": 5.857194594063421e-05, "loss": 1.1496, "step": 8448 }, { "epoch": 0.4619306338629762, "grad_norm": 2.8274075984954834, "learning_rate": 5.856322333816576e-05, "loss": 1.0148, "step": 8449 }, { "epoch": 0.4619853066803349, "grad_norm": 2.4730427265167236, "learning_rate": 5.8554500467204986e-05, "loss": 1.0106, "step": 8450 }, { "epoch": 0.4620399794976935, "grad_norm": 2.3837544918060303, "learning_rate": 5.854577732802541e-05, "loss": 0.9502, "step": 8451 }, { "epoch": 0.4620946523150521, "grad_norm": 2.977660655975342, "learning_rate": 5.8537053920900506e-05, "loss": 1.0438, "step": 8452 }, { "epoch": 0.46214932513241075, "grad_norm": 2.7235336303710938, "learning_rate": 5.852833024610381e-05, "loss": 1.0389, "step": 8453 }, { "epoch": 0.46220399794976935, "grad_norm": 2.4794528484344482, "learning_rate": 5.851960630390884e-05, "loss": 1.071, "step": 8454 }, { "epoch": 0.46225867076712795, "grad_norm": 2.478317975997925, "learning_rate": 5.851088209458912e-05, "loss": 1.0832, "step": 8455 }, { "epoch": 0.4623133435844866, "grad_norm": 2.4454264640808105, "learning_rate": 5.850215761841817e-05, "loss": 1.0166, "step": 8456 }, { "epoch": 0.4623680164018452, "grad_norm": 3.3181209564208984, "learning_rate": 5.84934328756696e-05, "loss": 1.123, "step": 8457 }, { "epoch": 0.4624226892192038, "grad_norm": 2.6590030193328857, "learning_rate": 5.8484707866616917e-05, "loss": 0.8905, "step": 8458 }, { "epoch": 0.4624773620365624, "grad_norm": 2.8476412296295166, "learning_rate": 5.8475982591533697e-05, "loss": 1.1078, "step": 8459 }, { "epoch": 0.4625320348539211, "grad_norm": 2.2311065196990967, "learning_rate": 5.846725705069352e-05, "loss": 0.9622, "step": 8460 }, { "epoch": 0.4625867076712797, "grad_norm": 2.645659923553467, "learning_rate": 5.845853124436996e-05, "loss": 1.0441, "step": 8461 }, { "epoch": 0.4626413804886383, "grad_norm": 2.3741841316223145, "learning_rate": 5.84498051728366e-05, "loss": 0.9634, "step": 8462 }, { "epoch": 0.46269605330599695, "grad_norm": 2.27246356010437, "learning_rate": 5.844107883636706e-05, "loss": 0.9832, "step": 8463 }, { "epoch": 0.46275072612335555, "grad_norm": 2.2222585678100586, "learning_rate": 5.8432352235234936e-05, "loss": 1.1921, "step": 8464 }, { "epoch": 0.46280539894071415, "grad_norm": 2.8955931663513184, "learning_rate": 5.842362536971383e-05, "loss": 1.1778, "step": 8465 }, { "epoch": 0.4628600717580728, "grad_norm": 2.4537463188171387, "learning_rate": 5.8414898240077384e-05, "loss": 1.1364, "step": 8466 }, { "epoch": 0.4629147445754314, "grad_norm": 2.8177456855773926, "learning_rate": 5.840617084659921e-05, "loss": 1.0788, "step": 8467 }, { "epoch": 0.46296941739279, "grad_norm": 2.1763875484466553, "learning_rate": 5.839744318955298e-05, "loss": 0.9086, "step": 8468 }, { "epoch": 0.4630240902101486, "grad_norm": 3.281256914138794, "learning_rate": 5.83887152692123e-05, "loss": 1.0876, "step": 8469 }, { "epoch": 0.4630787630275073, "grad_norm": 2.0050253868103027, "learning_rate": 5.837998708585087e-05, "loss": 1.024, "step": 8470 }, { "epoch": 0.4631334358448659, "grad_norm": 2.2166292667388916, "learning_rate": 5.837125863974232e-05, "loss": 1.0757, "step": 8471 }, { "epoch": 0.4631881086622245, "grad_norm": 2.1880459785461426, "learning_rate": 5.8362529931160336e-05, "loss": 0.9316, "step": 8472 }, { "epoch": 0.46324278147958314, "grad_norm": 2.488258123397827, "learning_rate": 5.8353800960378604e-05, "loss": 0.932, "step": 8473 }, { "epoch": 0.46329745429694175, "grad_norm": 2.7632265090942383, "learning_rate": 5.83450717276708e-05, "loss": 0.9984, "step": 8474 }, { "epoch": 0.46335212711430035, "grad_norm": 2.5234904289245605, "learning_rate": 5.833634223331064e-05, "loss": 1.0343, "step": 8475 }, { "epoch": 0.46340679993165895, "grad_norm": 2.5132668018341064, "learning_rate": 5.8327612477571805e-05, "loss": 1.1377, "step": 8476 }, { "epoch": 0.4634614727490176, "grad_norm": 2.4600796699523926, "learning_rate": 5.831888246072802e-05, "loss": 1.0783, "step": 8477 }, { "epoch": 0.4635161455663762, "grad_norm": 2.438690423965454, "learning_rate": 5.8310152183053013e-05, "loss": 1.0605, "step": 8478 }, { "epoch": 0.4635708183837348, "grad_norm": 3.916799306869507, "learning_rate": 5.830142164482052e-05, "loss": 1.103, "step": 8479 }, { "epoch": 0.4636254912010935, "grad_norm": 2.2817373275756836, "learning_rate": 5.8292690846304266e-05, "loss": 1.1159, "step": 8480 }, { "epoch": 0.4636801640184521, "grad_norm": 3.3203423023223877, "learning_rate": 5.8283959787778e-05, "loss": 0.9265, "step": 8481 }, { "epoch": 0.4637348368358107, "grad_norm": 3.232672929763794, "learning_rate": 5.827522846951546e-05, "loss": 1.1074, "step": 8482 }, { "epoch": 0.46378950965316934, "grad_norm": 2.3118276596069336, "learning_rate": 5.8266496891790444e-05, "loss": 1.0659, "step": 8483 }, { "epoch": 0.46384418247052794, "grad_norm": 2.321387767791748, "learning_rate": 5.825776505487671e-05, "loss": 0.9879, "step": 8484 }, { "epoch": 0.46389885528788655, "grad_norm": 2.8106589317321777, "learning_rate": 5.8249032959048025e-05, "loss": 1.0809, "step": 8485 }, { "epoch": 0.46395352810524515, "grad_norm": 2.54660701751709, "learning_rate": 5.824030060457819e-05, "loss": 1.0844, "step": 8486 }, { "epoch": 0.4640082009226038, "grad_norm": 2.254035711288452, "learning_rate": 5.8231567991740974e-05, "loss": 0.8503, "step": 8487 }, { "epoch": 0.4640628737399624, "grad_norm": 3.6204540729522705, "learning_rate": 5.8222835120810226e-05, "loss": 0.9366, "step": 8488 }, { "epoch": 0.464117546557321, "grad_norm": 2.5852084159851074, "learning_rate": 5.8214101992059724e-05, "loss": 1.1798, "step": 8489 }, { "epoch": 0.4641722193746797, "grad_norm": 2.3990888595581055, "learning_rate": 5.8205368605763286e-05, "loss": 1.0509, "step": 8490 }, { "epoch": 0.4642268921920383, "grad_norm": 2.440941333770752, "learning_rate": 5.8196634962194765e-05, "loss": 0.975, "step": 8491 }, { "epoch": 0.4642815650093969, "grad_norm": 1.934134840965271, "learning_rate": 5.818790106162796e-05, "loss": 0.9036, "step": 8492 }, { "epoch": 0.4643362378267555, "grad_norm": 2.3319902420043945, "learning_rate": 5.8179166904336746e-05, "loss": 1.0958, "step": 8493 }, { "epoch": 0.46439091064411414, "grad_norm": 2.771857261657715, "learning_rate": 5.817043249059496e-05, "loss": 1.0816, "step": 8494 }, { "epoch": 0.46444558346147274, "grad_norm": 2.486799716949463, "learning_rate": 5.8161697820676475e-05, "loss": 1.062, "step": 8495 }, { "epoch": 0.46450025627883135, "grad_norm": 4.415214538574219, "learning_rate": 5.8152962894855147e-05, "loss": 0.9636, "step": 8496 }, { "epoch": 0.46455492909619, "grad_norm": 2.2184557914733887, "learning_rate": 5.8144227713404845e-05, "loss": 0.9991, "step": 8497 }, { "epoch": 0.4646096019135486, "grad_norm": 2.408250331878662, "learning_rate": 5.813549227659948e-05, "loss": 0.8405, "step": 8498 }, { "epoch": 0.4646642747309072, "grad_norm": 2.9804794788360596, "learning_rate": 5.8126756584712915e-05, "loss": 0.9498, "step": 8499 }, { "epoch": 0.46471894754826587, "grad_norm": 2.473064661026001, "learning_rate": 5.8118020638019066e-05, "loss": 1.0302, "step": 8500 }, { "epoch": 0.4647736203656245, "grad_norm": 2.350046157836914, "learning_rate": 5.810928443679183e-05, "loss": 0.9549, "step": 8501 }, { "epoch": 0.4648282931829831, "grad_norm": 2.146092653274536, "learning_rate": 5.810054798130513e-05, "loss": 0.853, "step": 8502 }, { "epoch": 0.4648829660003417, "grad_norm": 2.1682283878326416, "learning_rate": 5.80918112718329e-05, "loss": 0.9495, "step": 8503 }, { "epoch": 0.46493763881770034, "grad_norm": 2.820082902908325, "learning_rate": 5.808307430864906e-05, "loss": 1.1455, "step": 8504 }, { "epoch": 0.46499231163505894, "grad_norm": 2.280837297439575, "learning_rate": 5.807433709202754e-05, "loss": 0.9949, "step": 8505 }, { "epoch": 0.46504698445241754, "grad_norm": 2.4029102325439453, "learning_rate": 5.8065599622242294e-05, "loss": 1.112, "step": 8506 }, { "epoch": 0.4651016572697762, "grad_norm": 2.075730085372925, "learning_rate": 5.8056861899567296e-05, "loss": 0.9883, "step": 8507 }, { "epoch": 0.4651563300871348, "grad_norm": 3.781714916229248, "learning_rate": 5.80481239242765e-05, "loss": 1.1127, "step": 8508 }, { "epoch": 0.4652110029044934, "grad_norm": 2.450247049331665, "learning_rate": 5.8039385696643865e-05, "loss": 0.8913, "step": 8509 }, { "epoch": 0.46526567572185207, "grad_norm": 2.496063470840454, "learning_rate": 5.803064721694338e-05, "loss": 1.004, "step": 8510 }, { "epoch": 0.46532034853921067, "grad_norm": 2.2418346405029297, "learning_rate": 5.802190848544902e-05, "loss": 1.065, "step": 8511 }, { "epoch": 0.4653750213565693, "grad_norm": 2.305436372756958, "learning_rate": 5.801316950243481e-05, "loss": 0.7616, "step": 8512 }, { "epoch": 0.4654296941739279, "grad_norm": 2.383291006088257, "learning_rate": 5.800443026817472e-05, "loss": 1.0001, "step": 8513 }, { "epoch": 0.46548436699128654, "grad_norm": 2.947582960128784, "learning_rate": 5.799569078294278e-05, "loss": 0.9455, "step": 8514 }, { "epoch": 0.46553903980864514, "grad_norm": 2.1617870330810547, "learning_rate": 5.798695104701302e-05, "loss": 0.9347, "step": 8515 }, { "epoch": 0.46559371262600374, "grad_norm": 2.127915620803833, "learning_rate": 5.7978211060659414e-05, "loss": 0.9183, "step": 8516 }, { "epoch": 0.4656483854433624, "grad_norm": 2.8388924598693848, "learning_rate": 5.796947082415606e-05, "loss": 1.1264, "step": 8517 }, { "epoch": 0.465703058260721, "grad_norm": 2.8670177459716797, "learning_rate": 5.796073033777697e-05, "loss": 1.2538, "step": 8518 }, { "epoch": 0.4657577310780796, "grad_norm": 2.4180850982666016, "learning_rate": 5.795198960179621e-05, "loss": 1.0545, "step": 8519 }, { "epoch": 0.4658124038954382, "grad_norm": 3.5267508029937744, "learning_rate": 5.7943248616487814e-05, "loss": 1.3535, "step": 8520 }, { "epoch": 0.46586707671279687, "grad_norm": 2.653438091278076, "learning_rate": 5.793450738212585e-05, "loss": 0.9459, "step": 8521 }, { "epoch": 0.46592174953015547, "grad_norm": 2.609921455383301, "learning_rate": 5.792576589898441e-05, "loss": 0.9863, "step": 8522 }, { "epoch": 0.4659764223475141, "grad_norm": 2.448063850402832, "learning_rate": 5.791702416733757e-05, "loss": 1.1916, "step": 8523 }, { "epoch": 0.46603109516487273, "grad_norm": 2.263805627822876, "learning_rate": 5.7908282187459416e-05, "loss": 0.9726, "step": 8524 }, { "epoch": 0.46608576798223134, "grad_norm": 2.151559591293335, "learning_rate": 5.7899539959624046e-05, "loss": 0.9724, "step": 8525 }, { "epoch": 0.46614044079958994, "grad_norm": 2.65505051612854, "learning_rate": 5.7890797484105564e-05, "loss": 1.025, "step": 8526 }, { "epoch": 0.4661951136169486, "grad_norm": 2.535987377166748, "learning_rate": 5.788205476117808e-05, "loss": 1.0259, "step": 8527 }, { "epoch": 0.4662497864343072, "grad_norm": 2.674345016479492, "learning_rate": 5.7873311791115725e-05, "loss": 1.1423, "step": 8528 }, { "epoch": 0.4663044592516658, "grad_norm": 2.3627874851226807, "learning_rate": 5.7864568574192624e-05, "loss": 1.0025, "step": 8529 }, { "epoch": 0.4663591320690244, "grad_norm": 2.550593137741089, "learning_rate": 5.7855825110682904e-05, "loss": 1.0291, "step": 8530 }, { "epoch": 0.46641380488638307, "grad_norm": 2.7897274494171143, "learning_rate": 5.784708140086069e-05, "loss": 1.1542, "step": 8531 }, { "epoch": 0.46646847770374167, "grad_norm": 2.4993813037872314, "learning_rate": 5.7838337445000176e-05, "loss": 1.0102, "step": 8532 }, { "epoch": 0.46652315052110027, "grad_norm": 2.532879590988159, "learning_rate": 5.782959324337551e-05, "loss": 0.9961, "step": 8533 }, { "epoch": 0.46657782333845893, "grad_norm": 2.519897222518921, "learning_rate": 5.782084879626084e-05, "loss": 0.9749, "step": 8534 }, { "epoch": 0.46663249615581753, "grad_norm": 2.2626290321350098, "learning_rate": 5.7812104103930366e-05, "loss": 1.1989, "step": 8535 }, { "epoch": 0.46668716897317614, "grad_norm": 2.6449060440063477, "learning_rate": 5.7803359166658236e-05, "loss": 0.9164, "step": 8536 }, { "epoch": 0.4667418417905348, "grad_norm": 2.697359323501587, "learning_rate": 5.779461398471866e-05, "loss": 1.1728, "step": 8537 }, { "epoch": 0.4667965146078934, "grad_norm": 2.3875389099121094, "learning_rate": 5.7785868558385834e-05, "loss": 0.9641, "step": 8538 }, { "epoch": 0.466851187425252, "grad_norm": 2.5684516429901123, "learning_rate": 5.7777122887933966e-05, "loss": 1.111, "step": 8539 }, { "epoch": 0.4669058602426106, "grad_norm": 2.757507562637329, "learning_rate": 5.776837697363727e-05, "loss": 0.9917, "step": 8540 }, { "epoch": 0.46696053305996926, "grad_norm": 1.9448434114456177, "learning_rate": 5.775963081576996e-05, "loss": 0.7802, "step": 8541 }, { "epoch": 0.46701520587732787, "grad_norm": 2.4722297191619873, "learning_rate": 5.775088441460626e-05, "loss": 1.2897, "step": 8542 }, { "epoch": 0.46706987869468647, "grad_norm": 2.273313522338867, "learning_rate": 5.7742137770420415e-05, "loss": 1.0033, "step": 8543 }, { "epoch": 0.4671245515120451, "grad_norm": 2.855051279067993, "learning_rate": 5.773339088348667e-05, "loss": 1.342, "step": 8544 }, { "epoch": 0.46717922432940373, "grad_norm": 2.2588157653808594, "learning_rate": 5.7724643754079264e-05, "loss": 1.0663, "step": 8545 }, { "epoch": 0.46723389714676233, "grad_norm": 2.085305690765381, "learning_rate": 5.771589638247248e-05, "loss": 0.8265, "step": 8546 }, { "epoch": 0.46728856996412094, "grad_norm": 3.67437744140625, "learning_rate": 5.7707148768940555e-05, "loss": 0.9842, "step": 8547 }, { "epoch": 0.4673432427814796, "grad_norm": 2.9275882244110107, "learning_rate": 5.7698400913757774e-05, "loss": 0.9156, "step": 8548 }, { "epoch": 0.4673979155988382, "grad_norm": 3.85801362991333, "learning_rate": 5.768965281719843e-05, "loss": 0.8213, "step": 8549 }, { "epoch": 0.4674525884161968, "grad_norm": 2.186504364013672, "learning_rate": 5.7680904479536776e-05, "loss": 1.0957, "step": 8550 }, { "epoch": 0.46750726123355546, "grad_norm": 2.4726743698120117, "learning_rate": 5.767215590104715e-05, "loss": 1.0645, "step": 8551 }, { "epoch": 0.46756193405091406, "grad_norm": 2.5711910724639893, "learning_rate": 5.766340708200384e-05, "loss": 0.9775, "step": 8552 }, { "epoch": 0.46761660686827267, "grad_norm": 2.372225284576416, "learning_rate": 5.765465802268115e-05, "loss": 1.1177, "step": 8553 }, { "epoch": 0.4676712796856313, "grad_norm": 3.072796583175659, "learning_rate": 5.7645908723353416e-05, "loss": 1.0235, "step": 8554 }, { "epoch": 0.46772595250298993, "grad_norm": 2.8509442806243896, "learning_rate": 5.763715918429494e-05, "loss": 1.0024, "step": 8555 }, { "epoch": 0.46778062532034853, "grad_norm": 3.0214033126831055, "learning_rate": 5.762840940578008e-05, "loss": 1.1273, "step": 8556 }, { "epoch": 0.46783529813770713, "grad_norm": 3.703993797302246, "learning_rate": 5.761965938808317e-05, "loss": 1.0559, "step": 8557 }, { "epoch": 0.4678899709550658, "grad_norm": 2.615630865097046, "learning_rate": 5.7610909131478554e-05, "loss": 1.0252, "step": 8558 }, { "epoch": 0.4679446437724244, "grad_norm": 3.198035717010498, "learning_rate": 5.76021586362406e-05, "loss": 1.1086, "step": 8559 }, { "epoch": 0.467999316589783, "grad_norm": 2.2054243087768555, "learning_rate": 5.759340790264364e-05, "loss": 0.7567, "step": 8560 }, { "epoch": 0.46805398940714166, "grad_norm": 2.780017852783203, "learning_rate": 5.758465693096209e-05, "loss": 1.1241, "step": 8561 }, { "epoch": 0.46810866222450026, "grad_norm": 2.0762646198272705, "learning_rate": 5.75759057214703e-05, "loss": 0.9887, "step": 8562 }, { "epoch": 0.46816333504185886, "grad_norm": 2.8673195838928223, "learning_rate": 5.756715427444267e-05, "loss": 0.8396, "step": 8563 }, { "epoch": 0.4682180078592175, "grad_norm": 3.8293704986572266, "learning_rate": 5.755840259015359e-05, "loss": 1.1818, "step": 8564 }, { "epoch": 0.4682726806765761, "grad_norm": 2.343629837036133, "learning_rate": 5.7549650668877455e-05, "loss": 1.007, "step": 8565 }, { "epoch": 0.46832735349393473, "grad_norm": 2.0858664512634277, "learning_rate": 5.754089851088867e-05, "loss": 0.9729, "step": 8566 }, { "epoch": 0.46838202631129333, "grad_norm": 2.080948829650879, "learning_rate": 5.753214611646168e-05, "loss": 1.0887, "step": 8567 }, { "epoch": 0.468436699128652, "grad_norm": 2.5347321033477783, "learning_rate": 5.752339348587088e-05, "loss": 1.0228, "step": 8568 }, { "epoch": 0.4684913719460106, "grad_norm": 2.161433219909668, "learning_rate": 5.751464061939071e-05, "loss": 1.0003, "step": 8569 }, { "epoch": 0.4685460447633692, "grad_norm": 2.597419023513794, "learning_rate": 5.7505887517295596e-05, "loss": 1.0302, "step": 8570 }, { "epoch": 0.46860071758072785, "grad_norm": 2.657381296157837, "learning_rate": 5.7497134179860015e-05, "loss": 0.7667, "step": 8571 }, { "epoch": 0.46865539039808646, "grad_norm": 2.7295660972595215, "learning_rate": 5.74883806073584e-05, "loss": 0.911, "step": 8572 }, { "epoch": 0.46871006321544506, "grad_norm": 2.5026931762695312, "learning_rate": 5.74796268000652e-05, "loss": 1.1744, "step": 8573 }, { "epoch": 0.46876473603280366, "grad_norm": 2.565772533416748, "learning_rate": 5.74708727582549e-05, "loss": 1.0631, "step": 8574 }, { "epoch": 0.4688194088501623, "grad_norm": 2.698751449584961, "learning_rate": 5.746211848220197e-05, "loss": 1.0083, "step": 8575 }, { "epoch": 0.4688740816675209, "grad_norm": 2.637291669845581, "learning_rate": 5.7453363972180886e-05, "loss": 0.7629, "step": 8576 }, { "epoch": 0.46892875448487953, "grad_norm": 2.641406297683716, "learning_rate": 5.7444609228466165e-05, "loss": 0.9317, "step": 8577 }, { "epoch": 0.4689834273022382, "grad_norm": 2.1610138416290283, "learning_rate": 5.7435854251332264e-05, "loss": 0.9905, "step": 8578 }, { "epoch": 0.4690381001195968, "grad_norm": 3.141942262649536, "learning_rate": 5.7427099041053724e-05, "loss": 0.9636, "step": 8579 }, { "epoch": 0.4690927729369554, "grad_norm": 2.494553327560425, "learning_rate": 5.741834359790502e-05, "loss": 0.9004, "step": 8580 }, { "epoch": 0.46914744575431405, "grad_norm": 3.311275005340576, "learning_rate": 5.7409587922160715e-05, "loss": 1.1006, "step": 8581 }, { "epoch": 0.46920211857167266, "grad_norm": 2.4363794326782227, "learning_rate": 5.740083201409531e-05, "loss": 1.0472, "step": 8582 }, { "epoch": 0.46925679138903126, "grad_norm": 3.460111618041992, "learning_rate": 5.7392075873983334e-05, "loss": 1.1669, "step": 8583 }, { "epoch": 0.46931146420638986, "grad_norm": 3.64530348777771, "learning_rate": 5.738331950209934e-05, "loss": 0.9272, "step": 8584 }, { "epoch": 0.4693661370237485, "grad_norm": 2.536186456680298, "learning_rate": 5.737456289871787e-05, "loss": 1.1334, "step": 8585 }, { "epoch": 0.4694208098411071, "grad_norm": 2.7242722511291504, "learning_rate": 5.736580606411347e-05, "loss": 1.174, "step": 8586 }, { "epoch": 0.4694754826584657, "grad_norm": 4.003957271575928, "learning_rate": 5.7357048998560736e-05, "loss": 0.9026, "step": 8587 }, { "epoch": 0.4695301554758244, "grad_norm": 2.040804624557495, "learning_rate": 5.7348291702334204e-05, "loss": 0.8877, "step": 8588 }, { "epoch": 0.469584828293183, "grad_norm": 3.540482997894287, "learning_rate": 5.733953417570846e-05, "loss": 1.2813, "step": 8589 }, { "epoch": 0.4696395011105416, "grad_norm": 2.900564670562744, "learning_rate": 5.73307764189581e-05, "loss": 0.9829, "step": 8590 }, { "epoch": 0.46969417392790025, "grad_norm": 2.654625415802002, "learning_rate": 5.73220184323577e-05, "loss": 0.9254, "step": 8591 }, { "epoch": 0.46974884674525885, "grad_norm": 2.797083854675293, "learning_rate": 5.7313260216181886e-05, "loss": 1.1013, "step": 8592 }, { "epoch": 0.46980351956261746, "grad_norm": 3.744331121444702, "learning_rate": 5.730450177070523e-05, "loss": 0.984, "step": 8593 }, { "epoch": 0.46985819237997606, "grad_norm": 2.375110387802124, "learning_rate": 5.729574309620236e-05, "loss": 1.0814, "step": 8594 }, { "epoch": 0.4699128651973347, "grad_norm": 2.546096086502075, "learning_rate": 5.728698419294789e-05, "loss": 1.2787, "step": 8595 }, { "epoch": 0.4699675380146933, "grad_norm": 2.313955307006836, "learning_rate": 5.727822506121647e-05, "loss": 1.1015, "step": 8596 }, { "epoch": 0.4700222108320519, "grad_norm": 2.7583796977996826, "learning_rate": 5.726946570128271e-05, "loss": 1.0572, "step": 8597 }, { "epoch": 0.4700768836494106, "grad_norm": 4.0020647048950195, "learning_rate": 5.726070611342127e-05, "loss": 1.058, "step": 8598 }, { "epoch": 0.4701315564667692, "grad_norm": 1.9094561338424683, "learning_rate": 5.7251946297906786e-05, "loss": 0.9126, "step": 8599 }, { "epoch": 0.4701862292841278, "grad_norm": 2.531276226043701, "learning_rate": 5.7243186255013915e-05, "loss": 1.0842, "step": 8600 }, { "epoch": 0.4702409021014864, "grad_norm": 1.9912071228027344, "learning_rate": 5.723442598501733e-05, "loss": 0.8453, "step": 8601 }, { "epoch": 0.47029557491884505, "grad_norm": 2.382131814956665, "learning_rate": 5.7225665488191696e-05, "loss": 1.234, "step": 8602 }, { "epoch": 0.47035024773620365, "grad_norm": 2.3442819118499756, "learning_rate": 5.7216904764811685e-05, "loss": 0.9844, "step": 8603 }, { "epoch": 0.47040492055356226, "grad_norm": 2.8996529579162598, "learning_rate": 5.720814381515199e-05, "loss": 1.1806, "step": 8604 }, { "epoch": 0.4704595933709209, "grad_norm": 3.1788008213043213, "learning_rate": 5.71993826394873e-05, "loss": 0.92, "step": 8605 }, { "epoch": 0.4705142661882795, "grad_norm": 2.8636722564697266, "learning_rate": 5.719062123809231e-05, "loss": 1.1244, "step": 8606 }, { "epoch": 0.4705689390056381, "grad_norm": 2.7390856742858887, "learning_rate": 5.718185961124174e-05, "loss": 1.1791, "step": 8607 }, { "epoch": 0.4706236118229968, "grad_norm": 2.99888014793396, "learning_rate": 5.717309775921029e-05, "loss": 0.8466, "step": 8608 }, { "epoch": 0.4706782846403554, "grad_norm": 2.3821165561676025, "learning_rate": 5.716433568227267e-05, "loss": 1.1342, "step": 8609 }, { "epoch": 0.470732957457714, "grad_norm": 4.720338344573975, "learning_rate": 5.715557338070363e-05, "loss": 1.0334, "step": 8610 }, { "epoch": 0.4707876302750726, "grad_norm": 2.713869094848633, "learning_rate": 5.71468108547779e-05, "loss": 1.1834, "step": 8611 }, { "epoch": 0.47084230309243125, "grad_norm": 2.6979212760925293, "learning_rate": 5.7138048104770215e-05, "loss": 1.1714, "step": 8612 }, { "epoch": 0.47089697590978985, "grad_norm": 2.4140331745147705, "learning_rate": 5.7129285130955327e-05, "loss": 0.9117, "step": 8613 }, { "epoch": 0.47095164872714845, "grad_norm": 4.94362211227417, "learning_rate": 5.7120521933607975e-05, "loss": 1.2755, "step": 8614 }, { "epoch": 0.4710063215445071, "grad_norm": 2.5295069217681885, "learning_rate": 5.7111758513002946e-05, "loss": 1.235, "step": 8615 }, { "epoch": 0.4710609943618657, "grad_norm": 4.502867221832275, "learning_rate": 5.7102994869414996e-05, "loss": 1.295, "step": 8616 }, { "epoch": 0.4711156671792243, "grad_norm": 3.364475727081299, "learning_rate": 5.70942310031189e-05, "loss": 0.9539, "step": 8617 }, { "epoch": 0.471170339996583, "grad_norm": 2.916494369506836, "learning_rate": 5.708546691438945e-05, "loss": 1.1451, "step": 8618 }, { "epoch": 0.4712250128139416, "grad_norm": 2.5978128910064697, "learning_rate": 5.707670260350143e-05, "loss": 1.0691, "step": 8619 }, { "epoch": 0.4712796856313002, "grad_norm": 2.8026013374328613, "learning_rate": 5.706793807072963e-05, "loss": 1.1744, "step": 8620 }, { "epoch": 0.4713343584486588, "grad_norm": 2.5022342205047607, "learning_rate": 5.705917331634888e-05, "loss": 1.2306, "step": 8621 }, { "epoch": 0.47138903126601744, "grad_norm": 2.0971667766571045, "learning_rate": 5.705040834063397e-05, "loss": 1.1034, "step": 8622 }, { "epoch": 0.47144370408337605, "grad_norm": 2.4949896335601807, "learning_rate": 5.7041643143859714e-05, "loss": 0.9867, "step": 8623 }, { "epoch": 0.47149837690073465, "grad_norm": 2.1807522773742676, "learning_rate": 5.7032877726300934e-05, "loss": 1.0735, "step": 8624 }, { "epoch": 0.4715530497180933, "grad_norm": 2.5866293907165527, "learning_rate": 5.7024112088232496e-05, "loss": 0.9716, "step": 8625 }, { "epoch": 0.4716077225354519, "grad_norm": 3.11942458152771, "learning_rate": 5.701534622992921e-05, "loss": 1.1327, "step": 8626 }, { "epoch": 0.4716623953528105, "grad_norm": 3.9304049015045166, "learning_rate": 5.700658015166592e-05, "loss": 0.8889, "step": 8627 }, { "epoch": 0.4717170681701691, "grad_norm": 3.0997955799102783, "learning_rate": 5.6997813853717495e-05, "loss": 1.2582, "step": 8628 }, { "epoch": 0.4717717409875278, "grad_norm": 2.2901926040649414, "learning_rate": 5.6989047336358784e-05, "loss": 0.9015, "step": 8629 }, { "epoch": 0.4718264138048864, "grad_norm": 3.492785692214966, "learning_rate": 5.6980280599864646e-05, "loss": 0.9736, "step": 8630 }, { "epoch": 0.471881086622245, "grad_norm": 2.9268550872802734, "learning_rate": 5.697151364450997e-05, "loss": 1.1556, "step": 8631 }, { "epoch": 0.47193575943960364, "grad_norm": 2.249772310256958, "learning_rate": 5.696274647056963e-05, "loss": 0.8878, "step": 8632 }, { "epoch": 0.47199043225696224, "grad_norm": 3.5187861919403076, "learning_rate": 5.695397907831851e-05, "loss": 1.1911, "step": 8633 }, { "epoch": 0.47204510507432085, "grad_norm": 2.6515469551086426, "learning_rate": 5.694521146803151e-05, "loss": 1.0698, "step": 8634 }, { "epoch": 0.4720997778916795, "grad_norm": 2.860790491104126, "learning_rate": 5.6936443639983526e-05, "loss": 1.1314, "step": 8635 }, { "epoch": 0.4721544507090381, "grad_norm": 3.224412202835083, "learning_rate": 5.692767559444947e-05, "loss": 0.967, "step": 8636 }, { "epoch": 0.4722091235263967, "grad_norm": 2.7577309608459473, "learning_rate": 5.691890733170423e-05, "loss": 0.9581, "step": 8637 }, { "epoch": 0.4722637963437553, "grad_norm": 3.0451083183288574, "learning_rate": 5.691013885202278e-05, "loss": 1.2453, "step": 8638 }, { "epoch": 0.472318469161114, "grad_norm": 3.706627130508423, "learning_rate": 5.690137015568e-05, "loss": 1.1793, "step": 8639 }, { "epoch": 0.4723731419784726, "grad_norm": 2.924375534057617, "learning_rate": 5.689260124295085e-05, "loss": 0.9182, "step": 8640 }, { "epoch": 0.4724278147958312, "grad_norm": 1.8180222511291504, "learning_rate": 5.6883832114110266e-05, "loss": 0.8188, "step": 8641 }, { "epoch": 0.47248248761318984, "grad_norm": 2.4485507011413574, "learning_rate": 5.68750627694332e-05, "loss": 0.9252, "step": 8642 }, { "epoch": 0.47253716043054844, "grad_norm": 2.2060558795928955, "learning_rate": 5.6866293209194575e-05, "loss": 0.9294, "step": 8643 }, { "epoch": 0.47259183324790704, "grad_norm": 3.755335807800293, "learning_rate": 5.68575234336694e-05, "loss": 1.0096, "step": 8644 }, { "epoch": 0.47264650606526565, "grad_norm": 2.182692527770996, "learning_rate": 5.684875344313263e-05, "loss": 1.0582, "step": 8645 }, { "epoch": 0.4727011788826243, "grad_norm": 2.164163112640381, "learning_rate": 5.683998323785923e-05, "loss": 1.1878, "step": 8646 }, { "epoch": 0.4727558516999829, "grad_norm": 2.658837080001831, "learning_rate": 5.683121281812418e-05, "loss": 1.0064, "step": 8647 }, { "epoch": 0.4728105245173415, "grad_norm": 2.5966711044311523, "learning_rate": 5.6822442184202474e-05, "loss": 1.1143, "step": 8648 }, { "epoch": 0.47286519733470017, "grad_norm": 2.771843671798706, "learning_rate": 5.68136713363691e-05, "loss": 1.2111, "step": 8649 }, { "epoch": 0.4729198701520588, "grad_norm": 3.2907652854919434, "learning_rate": 5.680490027489908e-05, "loss": 0.8788, "step": 8650 }, { "epoch": 0.4729745429694174, "grad_norm": 2.6807730197906494, "learning_rate": 5.679612900006741e-05, "loss": 1.2639, "step": 8651 }, { "epoch": 0.47302921578677604, "grad_norm": 2.393908977508545, "learning_rate": 5.67873575121491e-05, "loss": 1.0359, "step": 8652 }, { "epoch": 0.47308388860413464, "grad_norm": 2.4628922939300537, "learning_rate": 5.677858581141918e-05, "loss": 1.1656, "step": 8653 }, { "epoch": 0.47313856142149324, "grad_norm": 2.8479602336883545, "learning_rate": 5.676981389815268e-05, "loss": 0.9385, "step": 8654 }, { "epoch": 0.47319323423885185, "grad_norm": 3.0004470348358154, "learning_rate": 5.676104177262463e-05, "loss": 1.0329, "step": 8655 }, { "epoch": 0.4732479070562105, "grad_norm": 2.4739468097686768, "learning_rate": 5.675226943511008e-05, "loss": 1.0393, "step": 8656 }, { "epoch": 0.4733025798735691, "grad_norm": 2.5123820304870605, "learning_rate": 5.6743496885884084e-05, "loss": 1.0387, "step": 8657 }, { "epoch": 0.4733572526909277, "grad_norm": 2.1856112480163574, "learning_rate": 5.6734724125221675e-05, "loss": 1.1124, "step": 8658 }, { "epoch": 0.47341192550828637, "grad_norm": 2.392245054244995, "learning_rate": 5.6725951153397915e-05, "loss": 1.0915, "step": 8659 }, { "epoch": 0.47346659832564497, "grad_norm": 2.581393003463745, "learning_rate": 5.671717797068791e-05, "loss": 0.9434, "step": 8660 }, { "epoch": 0.4735212711430036, "grad_norm": 2.7318172454833984, "learning_rate": 5.6708404577366705e-05, "loss": 1.1566, "step": 8661 }, { "epoch": 0.47357594396036223, "grad_norm": 3.0508196353912354, "learning_rate": 5.6699630973709385e-05, "loss": 0.8948, "step": 8662 }, { "epoch": 0.47363061677772084, "grad_norm": 3.2003989219665527, "learning_rate": 5.669085715999104e-05, "loss": 1.0612, "step": 8663 }, { "epoch": 0.47368528959507944, "grad_norm": 5.474361896514893, "learning_rate": 5.668208313648677e-05, "loss": 1.3022, "step": 8664 }, { "epoch": 0.47373996241243804, "grad_norm": 3.546168088912964, "learning_rate": 5.667330890347168e-05, "loss": 1.1101, "step": 8665 }, { "epoch": 0.4737946352297967, "grad_norm": 3.4414079189300537, "learning_rate": 5.6664534461220864e-05, "loss": 0.8376, "step": 8666 }, { "epoch": 0.4738493080471553, "grad_norm": 2.1474342346191406, "learning_rate": 5.6655759810009444e-05, "loss": 0.8584, "step": 8667 }, { "epoch": 0.4739039808645139, "grad_norm": 2.63381028175354, "learning_rate": 5.6646984950112545e-05, "loss": 1.0055, "step": 8668 }, { "epoch": 0.47395865368187257, "grad_norm": 3.17681622505188, "learning_rate": 5.663820988180529e-05, "loss": 0.9423, "step": 8669 }, { "epoch": 0.47401332649923117, "grad_norm": 3.0876660346984863, "learning_rate": 5.662943460536283e-05, "loss": 1.1042, "step": 8670 }, { "epoch": 0.47406799931658977, "grad_norm": 2.5610055923461914, "learning_rate": 5.662065912106028e-05, "loss": 1.0102, "step": 8671 }, { "epoch": 0.4741226721339484, "grad_norm": 2.8127052783966064, "learning_rate": 5.661188342917281e-05, "loss": 1.1, "step": 8672 }, { "epoch": 0.47417734495130703, "grad_norm": 2.4554238319396973, "learning_rate": 5.660310752997554e-05, "loss": 0.9292, "step": 8673 }, { "epoch": 0.47423201776866564, "grad_norm": 2.122596025466919, "learning_rate": 5.6594331423743674e-05, "loss": 1.0285, "step": 8674 }, { "epoch": 0.47428669058602424, "grad_norm": 2.0998175144195557, "learning_rate": 5.658555511075236e-05, "loss": 0.9974, "step": 8675 }, { "epoch": 0.4743413634033829, "grad_norm": 2.1578946113586426, "learning_rate": 5.6576778591276766e-05, "loss": 0.9013, "step": 8676 }, { "epoch": 0.4743960362207415, "grad_norm": 2.2939233779907227, "learning_rate": 5.656800186559208e-05, "loss": 1.1764, "step": 8677 }, { "epoch": 0.4744507090381001, "grad_norm": 2.4617221355438232, "learning_rate": 5.655922493397348e-05, "loss": 1.1211, "step": 8678 }, { "epoch": 0.47450538185545876, "grad_norm": 2.700828790664673, "learning_rate": 5.655044779669617e-05, "loss": 1.0445, "step": 8679 }, { "epoch": 0.47456005467281737, "grad_norm": 2.66039776802063, "learning_rate": 5.654167045403535e-05, "loss": 0.956, "step": 8680 }, { "epoch": 0.47461472749017597, "grad_norm": 3.149359703063965, "learning_rate": 5.653289290626621e-05, "loss": 0.8968, "step": 8681 }, { "epoch": 0.4746694003075346, "grad_norm": 2.4416799545288086, "learning_rate": 5.652411515366398e-05, "loss": 1.03, "step": 8682 }, { "epoch": 0.47472407312489323, "grad_norm": 2.28037428855896, "learning_rate": 5.6515337196503856e-05, "loss": 0.9128, "step": 8683 }, { "epoch": 0.47477874594225183, "grad_norm": 2.4905054569244385, "learning_rate": 5.650655903506109e-05, "loss": 1.0624, "step": 8684 }, { "epoch": 0.47483341875961044, "grad_norm": 4.854714393615723, "learning_rate": 5.64977806696109e-05, "loss": 1.1215, "step": 8685 }, { "epoch": 0.4748880915769691, "grad_norm": 2.7818779945373535, "learning_rate": 5.648900210042852e-05, "loss": 1.1597, "step": 8686 }, { "epoch": 0.4749427643943277, "grad_norm": 3.5053205490112305, "learning_rate": 5.648022332778922e-05, "loss": 0.9289, "step": 8687 }, { "epoch": 0.4749974372116863, "grad_norm": 2.2934136390686035, "learning_rate": 5.647144435196819e-05, "loss": 1.0392, "step": 8688 }, { "epoch": 0.47505211002904496, "grad_norm": 3.019488573074341, "learning_rate": 5.646266517324076e-05, "loss": 1.0797, "step": 8689 }, { "epoch": 0.47510678284640356, "grad_norm": 2.7000038623809814, "learning_rate": 5.6453885791882155e-05, "loss": 1.0581, "step": 8690 }, { "epoch": 0.47516145566376217, "grad_norm": 3.08056640625, "learning_rate": 5.644510620816765e-05, "loss": 1.0581, "step": 8691 }, { "epoch": 0.47521612848112077, "grad_norm": 3.0750205516815186, "learning_rate": 5.643632642237252e-05, "loss": 1.106, "step": 8692 }, { "epoch": 0.47527080129847943, "grad_norm": 2.159592390060425, "learning_rate": 5.642754643477204e-05, "loss": 0.9875, "step": 8693 }, { "epoch": 0.47532547411583803, "grad_norm": 2.3274784088134766, "learning_rate": 5.6418766245641516e-05, "loss": 1.0965, "step": 8694 }, { "epoch": 0.47538014693319663, "grad_norm": 2.4484786987304688, "learning_rate": 5.6409985855256244e-05, "loss": 0.9718, "step": 8695 }, { "epoch": 0.4754348197505553, "grad_norm": 2.330056667327881, "learning_rate": 5.640120526389151e-05, "loss": 0.9581, "step": 8696 }, { "epoch": 0.4754894925679139, "grad_norm": 2.6101155281066895, "learning_rate": 5.6392424471822625e-05, "loss": 1.1058, "step": 8697 }, { "epoch": 0.4755441653852725, "grad_norm": 2.7190966606140137, "learning_rate": 5.63836434793249e-05, "loss": 1.1917, "step": 8698 }, { "epoch": 0.4755988382026311, "grad_norm": 2.6037497520446777, "learning_rate": 5.637486228667367e-05, "loss": 1.2095, "step": 8699 }, { "epoch": 0.47565351101998976, "grad_norm": 3.250903367996216, "learning_rate": 5.636608089414426e-05, "loss": 0.8472, "step": 8700 }, { "epoch": 0.47570818383734836, "grad_norm": 2.3424792289733887, "learning_rate": 5.6357299302011976e-05, "loss": 0.841, "step": 8701 }, { "epoch": 0.47576285665470697, "grad_norm": 2.3738954067230225, "learning_rate": 5.63485175105522e-05, "loss": 0.7887, "step": 8702 }, { "epoch": 0.4758175294720656, "grad_norm": 2.7740960121154785, "learning_rate": 5.633973552004023e-05, "loss": 0.9452, "step": 8703 }, { "epoch": 0.47587220228942423, "grad_norm": 2.6490478515625, "learning_rate": 5.6330953330751456e-05, "loss": 1.0606, "step": 8704 }, { "epoch": 0.47592687510678283, "grad_norm": 3.2505102157592773, "learning_rate": 5.6322170942961216e-05, "loss": 1.1783, "step": 8705 }, { "epoch": 0.4759815479241415, "grad_norm": 2.463336944580078, "learning_rate": 5.6313388356944884e-05, "loss": 1.0761, "step": 8706 }, { "epoch": 0.4760362207415001, "grad_norm": 2.877760887145996, "learning_rate": 5.630460557297783e-05, "loss": 1.0764, "step": 8707 }, { "epoch": 0.4760908935588587, "grad_norm": 2.565831422805786, "learning_rate": 5.629582259133541e-05, "loss": 0.9888, "step": 8708 }, { "epoch": 0.4761455663762173, "grad_norm": 2.181419849395752, "learning_rate": 5.628703941229304e-05, "loss": 0.9197, "step": 8709 }, { "epoch": 0.47620023919357596, "grad_norm": 4.225300312042236, "learning_rate": 5.627825603612609e-05, "loss": 1.1952, "step": 8710 }, { "epoch": 0.47625491201093456, "grad_norm": 2.73983097076416, "learning_rate": 5.626947246310995e-05, "loss": 1.1672, "step": 8711 }, { "epoch": 0.47630958482829316, "grad_norm": 2.334829092025757, "learning_rate": 5.626068869352004e-05, "loss": 1.1556, "step": 8712 }, { "epoch": 0.4763642576456518, "grad_norm": 2.4313437938690186, "learning_rate": 5.6251904727631734e-05, "loss": 1.133, "step": 8713 }, { "epoch": 0.4764189304630104, "grad_norm": 3.066560745239258, "learning_rate": 5.6243120565720476e-05, "loss": 1.1352, "step": 8714 }, { "epoch": 0.47647360328036903, "grad_norm": 2.3401031494140625, "learning_rate": 5.623433620806168e-05, "loss": 1.0936, "step": 8715 }, { "epoch": 0.4765282760977277, "grad_norm": 2.8660380840301514, "learning_rate": 5.6225551654930766e-05, "loss": 1.0004, "step": 8716 }, { "epoch": 0.4765829489150863, "grad_norm": 3.7352089881896973, "learning_rate": 5.6216766906603155e-05, "loss": 1.2099, "step": 8717 }, { "epoch": 0.4766376217324449, "grad_norm": 2.5796823501586914, "learning_rate": 5.620798196335432e-05, "loss": 1.06, "step": 8718 }, { "epoch": 0.4766922945498035, "grad_norm": 2.2453773021698, "learning_rate": 5.619919682545968e-05, "loss": 0.9625, "step": 8719 }, { "epoch": 0.47674696736716216, "grad_norm": 2.58739972114563, "learning_rate": 5.6190411493194685e-05, "loss": 0.9917, "step": 8720 }, { "epoch": 0.47680164018452076, "grad_norm": 2.3641626834869385, "learning_rate": 5.6181625966834786e-05, "loss": 0.9815, "step": 8721 }, { "epoch": 0.47685631300187936, "grad_norm": 2.951508045196533, "learning_rate": 5.617284024665547e-05, "loss": 1.1294, "step": 8722 }, { "epoch": 0.476910985819238, "grad_norm": 3.186708450317383, "learning_rate": 5.616405433293218e-05, "loss": 1.3464, "step": 8723 }, { "epoch": 0.4769656586365966, "grad_norm": 2.032343626022339, "learning_rate": 5.6155268225940394e-05, "loss": 0.8675, "step": 8724 }, { "epoch": 0.4770203314539552, "grad_norm": 3.9243857860565186, "learning_rate": 5.6146481925955605e-05, "loss": 1.3443, "step": 8725 }, { "epoch": 0.47707500427131383, "grad_norm": 2.4272117614746094, "learning_rate": 5.61376954332533e-05, "loss": 1.0099, "step": 8726 }, { "epoch": 0.4771296770886725, "grad_norm": 2.8474206924438477, "learning_rate": 5.6128908748108965e-05, "loss": 1.2622, "step": 8727 }, { "epoch": 0.4771843499060311, "grad_norm": 2.1073811054229736, "learning_rate": 5.612012187079809e-05, "loss": 1.0177, "step": 8728 }, { "epoch": 0.4772390227233897, "grad_norm": 2.368685007095337, "learning_rate": 5.61113348015962e-05, "loss": 1.1539, "step": 8729 }, { "epoch": 0.47729369554074835, "grad_norm": 2.421858549118042, "learning_rate": 5.610254754077878e-05, "loss": 0.95, "step": 8730 }, { "epoch": 0.47734836835810696, "grad_norm": 2.6798954010009766, "learning_rate": 5.609376008862137e-05, "loss": 1.0394, "step": 8731 }, { "epoch": 0.47740304117546556, "grad_norm": 2.1976842880249023, "learning_rate": 5.6084972445399495e-05, "loss": 1.0264, "step": 8732 }, { "epoch": 0.4774577139928242, "grad_norm": 3.195183038711548, "learning_rate": 5.607618461138866e-05, "loss": 1.0862, "step": 8733 }, { "epoch": 0.4775123868101828, "grad_norm": 2.845214605331421, "learning_rate": 5.606739658686442e-05, "loss": 1.1513, "step": 8734 }, { "epoch": 0.4775670596275414, "grad_norm": 2.736098051071167, "learning_rate": 5.6058608372102306e-05, "loss": 1.0648, "step": 8735 }, { "epoch": 0.4776217324449, "grad_norm": 1.9409934282302856, "learning_rate": 5.604981996737787e-05, "loss": 0.7325, "step": 8736 }, { "epoch": 0.4776764052622587, "grad_norm": 2.4249978065490723, "learning_rate": 5.604103137296666e-05, "loss": 1.0417, "step": 8737 }, { "epoch": 0.4777310780796173, "grad_norm": 3.3869333267211914, "learning_rate": 5.6032242589144236e-05, "loss": 1.253, "step": 8738 }, { "epoch": 0.4777857508969759, "grad_norm": 2.82747745513916, "learning_rate": 5.602345361618616e-05, "loss": 1.0398, "step": 8739 }, { "epoch": 0.47784042371433455, "grad_norm": 2.29107403755188, "learning_rate": 5.6014664454368015e-05, "loss": 1.1011, "step": 8740 }, { "epoch": 0.47789509653169315, "grad_norm": 2.9134135246276855, "learning_rate": 5.600587510396536e-05, "loss": 1.1128, "step": 8741 }, { "epoch": 0.47794976934905176, "grad_norm": 2.7011823654174805, "learning_rate": 5.599708556525378e-05, "loss": 1.058, "step": 8742 }, { "epoch": 0.4780044421664104, "grad_norm": 2.499329090118408, "learning_rate": 5.598829583850889e-05, "loss": 0.9843, "step": 8743 }, { "epoch": 0.478059114983769, "grad_norm": 2.8423476219177246, "learning_rate": 5.597950592400625e-05, "loss": 1.0211, "step": 8744 }, { "epoch": 0.4781137878011276, "grad_norm": 2.674376964569092, "learning_rate": 5.597071582202147e-05, "loss": 0.991, "step": 8745 }, { "epoch": 0.4781684606184862, "grad_norm": 2.099247694015503, "learning_rate": 5.5961925532830174e-05, "loss": 0.7794, "step": 8746 }, { "epoch": 0.4782231334358449, "grad_norm": 3.5978548526763916, "learning_rate": 5.595313505670793e-05, "loss": 1.0515, "step": 8747 }, { "epoch": 0.4782778062532035, "grad_norm": 2.321685791015625, "learning_rate": 5.5944344393930405e-05, "loss": 0.9064, "step": 8748 }, { "epoch": 0.4783324790705621, "grad_norm": 2.3934946060180664, "learning_rate": 5.59355535447732e-05, "loss": 0.7249, "step": 8749 }, { "epoch": 0.47838715188792075, "grad_norm": 2.705949068069458, "learning_rate": 5.592676250951195e-05, "loss": 1.0843, "step": 8750 }, { "epoch": 0.47844182470527935, "grad_norm": 2.3587498664855957, "learning_rate": 5.591797128842229e-05, "loss": 1.0323, "step": 8751 }, { "epoch": 0.47849649752263795, "grad_norm": 2.527895927429199, "learning_rate": 5.590917988177984e-05, "loss": 0.9486, "step": 8752 }, { "epoch": 0.47855117033999656, "grad_norm": 2.3697686195373535, "learning_rate": 5.590038828986027e-05, "loss": 1.1256, "step": 8753 }, { "epoch": 0.4786058431573552, "grad_norm": 2.5189788341522217, "learning_rate": 5.589159651293923e-05, "loss": 0.8746, "step": 8754 }, { "epoch": 0.4786605159747138, "grad_norm": 2.678910970687866, "learning_rate": 5.588280455129238e-05, "loss": 0.9094, "step": 8755 }, { "epoch": 0.4787151887920724, "grad_norm": 4.195160865783691, "learning_rate": 5.5874012405195375e-05, "loss": 0.9973, "step": 8756 }, { "epoch": 0.4787698616094311, "grad_norm": 2.7374277114868164, "learning_rate": 5.5865220074923876e-05, "loss": 1.0389, "step": 8757 }, { "epoch": 0.4788245344267897, "grad_norm": 2.518280267715454, "learning_rate": 5.585642756075359e-05, "loss": 0.9643, "step": 8758 }, { "epoch": 0.4788792072441483, "grad_norm": 3.3184053897857666, "learning_rate": 5.584763486296017e-05, "loss": 1.1315, "step": 8759 }, { "epoch": 0.47893388006150694, "grad_norm": 2.7066099643707275, "learning_rate": 5.583884198181933e-05, "loss": 1.0559, "step": 8760 }, { "epoch": 0.47898855287886555, "grad_norm": 2.8074889183044434, "learning_rate": 5.583004891760673e-05, "loss": 1.1838, "step": 8761 }, { "epoch": 0.47904322569622415, "grad_norm": 2.104726791381836, "learning_rate": 5.5821255670598096e-05, "loss": 0.9557, "step": 8762 }, { "epoch": 0.47909789851358275, "grad_norm": 2.2070014476776123, "learning_rate": 5.581246224106912e-05, "loss": 1.0138, "step": 8763 }, { "epoch": 0.4791525713309414, "grad_norm": 2.9641482830047607, "learning_rate": 5.580366862929551e-05, "loss": 0.8723, "step": 8764 }, { "epoch": 0.4792072441483, "grad_norm": 2.3994498252868652, "learning_rate": 5.5794874835552993e-05, "loss": 0.9149, "step": 8765 }, { "epoch": 0.4792619169656586, "grad_norm": 2.395538091659546, "learning_rate": 5.578608086011727e-05, "loss": 1.0423, "step": 8766 }, { "epoch": 0.4793165897830173, "grad_norm": 2.375521659851074, "learning_rate": 5.57772867032641e-05, "loss": 1.1078, "step": 8767 }, { "epoch": 0.4793712626003759, "grad_norm": 2.3533987998962402, "learning_rate": 5.576849236526919e-05, "loss": 1.0766, "step": 8768 }, { "epoch": 0.4794259354177345, "grad_norm": 3.0122852325439453, "learning_rate": 5.575969784640829e-05, "loss": 1.0717, "step": 8769 }, { "epoch": 0.47948060823509314, "grad_norm": 3.710714817047119, "learning_rate": 5.575090314695714e-05, "loss": 0.9275, "step": 8770 }, { "epoch": 0.47953528105245175, "grad_norm": 2.4691436290740967, "learning_rate": 5.5742108267191486e-05, "loss": 0.9835, "step": 8771 }, { "epoch": 0.47958995386981035, "grad_norm": 2.1832709312438965, "learning_rate": 5.5733313207387106e-05, "loss": 1.0753, "step": 8772 }, { "epoch": 0.47964462668716895, "grad_norm": 2.7394042015075684, "learning_rate": 5.5724517967819735e-05, "loss": 1.0421, "step": 8773 }, { "epoch": 0.4796992995045276, "grad_norm": 2.5037481784820557, "learning_rate": 5.571572254876515e-05, "loss": 0.8852, "step": 8774 }, { "epoch": 0.4797539723218862, "grad_norm": 3.5004546642303467, "learning_rate": 5.570692695049912e-05, "loss": 1.0446, "step": 8775 }, { "epoch": 0.4798086451392448, "grad_norm": 2.8490846157073975, "learning_rate": 5.569813117329742e-05, "loss": 0.8956, "step": 8776 }, { "epoch": 0.4798633179566035, "grad_norm": 2.9905521869659424, "learning_rate": 5.568933521743584e-05, "loss": 1.2282, "step": 8777 }, { "epoch": 0.4799179907739621, "grad_norm": 2.5282645225524902, "learning_rate": 5.56805390831902e-05, "loss": 1.039, "step": 8778 }, { "epoch": 0.4799726635913207, "grad_norm": 2.3401777744293213, "learning_rate": 5.5671742770836234e-05, "loss": 1.148, "step": 8779 }, { "epoch": 0.4800273364086793, "grad_norm": 2.6394355297088623, "learning_rate": 5.566294628064979e-05, "loss": 1.0541, "step": 8780 }, { "epoch": 0.48008200922603794, "grad_norm": 2.752169370651245, "learning_rate": 5.565414961290664e-05, "loss": 0.9985, "step": 8781 }, { "epoch": 0.48013668204339655, "grad_norm": 3.9939374923706055, "learning_rate": 5.564535276788263e-05, "loss": 1.1653, "step": 8782 }, { "epoch": 0.48019135486075515, "grad_norm": 2.878993034362793, "learning_rate": 5.563655574585356e-05, "loss": 0.8897, "step": 8783 }, { "epoch": 0.4802460276781138, "grad_norm": 2.2092785835266113, "learning_rate": 5.562775854709524e-05, "loss": 1.1072, "step": 8784 }, { "epoch": 0.4803007004954724, "grad_norm": 2.662947177886963, "learning_rate": 5.561896117188352e-05, "loss": 1.056, "step": 8785 }, { "epoch": 0.480355373312831, "grad_norm": 4.077225208282471, "learning_rate": 5.5610163620494226e-05, "loss": 1.2128, "step": 8786 }, { "epoch": 0.48041004613018967, "grad_norm": 2.4540421962738037, "learning_rate": 5.560136589320319e-05, "loss": 0.9188, "step": 8787 }, { "epoch": 0.4804647189475483, "grad_norm": 2.169620990753174, "learning_rate": 5.559256799028628e-05, "loss": 0.9663, "step": 8788 }, { "epoch": 0.4805193917649069, "grad_norm": 3.186152219772339, "learning_rate": 5.5583769912019324e-05, "loss": 0.9979, "step": 8789 }, { "epoch": 0.4805740645822655, "grad_norm": 2.7078635692596436, "learning_rate": 5.5574971658678186e-05, "loss": 1.2523, "step": 8790 }, { "epoch": 0.48062873739962414, "grad_norm": 2.8796374797821045, "learning_rate": 5.556617323053872e-05, "loss": 1.064, "step": 8791 }, { "epoch": 0.48068341021698274, "grad_norm": 2.7563271522521973, "learning_rate": 5.55573746278768e-05, "loss": 1.1374, "step": 8792 }, { "epoch": 0.48073808303434135, "grad_norm": 2.8483688831329346, "learning_rate": 5.554857585096831e-05, "loss": 1.1731, "step": 8793 }, { "epoch": 0.4807927558517, "grad_norm": 2.208303213119507, "learning_rate": 5.553977690008911e-05, "loss": 1.1261, "step": 8794 }, { "epoch": 0.4808474286690586, "grad_norm": 2.203683376312256, "learning_rate": 5.553097777551508e-05, "loss": 0.8735, "step": 8795 }, { "epoch": 0.4809021014864172, "grad_norm": 3.0893638134002686, "learning_rate": 5.5522178477522124e-05, "loss": 1.2219, "step": 8796 }, { "epoch": 0.48095677430377587, "grad_norm": 2.171957015991211, "learning_rate": 5.5513379006386126e-05, "loss": 1.0409, "step": 8797 }, { "epoch": 0.48101144712113447, "grad_norm": 2.258255958557129, "learning_rate": 5.5504579362383e-05, "loss": 1.1828, "step": 8798 }, { "epoch": 0.4810661199384931, "grad_norm": 3.432162046432495, "learning_rate": 5.549577954578864e-05, "loss": 1.1075, "step": 8799 }, { "epoch": 0.4811207927558517, "grad_norm": 2.367447853088379, "learning_rate": 5.5486979556878947e-05, "loss": 1.0471, "step": 8800 }, { "epoch": 0.48117546557321034, "grad_norm": 2.7917208671569824, "learning_rate": 5.547817939592984e-05, "loss": 1.0968, "step": 8801 }, { "epoch": 0.48123013839056894, "grad_norm": 2.752331018447876, "learning_rate": 5.5469379063217264e-05, "loss": 1.1831, "step": 8802 }, { "epoch": 0.48128481120792754, "grad_norm": 2.717010736465454, "learning_rate": 5.546057855901713e-05, "loss": 1.1831, "step": 8803 }, { "epoch": 0.4813394840252862, "grad_norm": 2.216576099395752, "learning_rate": 5.5451777883605364e-05, "loss": 1.0403, "step": 8804 }, { "epoch": 0.4813941568426448, "grad_norm": 2.4070184230804443, "learning_rate": 5.544297703725792e-05, "loss": 1.1382, "step": 8805 }, { "epoch": 0.4814488296600034, "grad_norm": 2.1212515830993652, "learning_rate": 5.5434176020250694e-05, "loss": 1.0997, "step": 8806 }, { "epoch": 0.481503502477362, "grad_norm": 2.282808780670166, "learning_rate": 5.54253748328597e-05, "loss": 1.1348, "step": 8807 }, { "epoch": 0.48155817529472067, "grad_norm": 2.8038599491119385, "learning_rate": 5.541657347536085e-05, "loss": 1.1956, "step": 8808 }, { "epoch": 0.4816128481120793, "grad_norm": 2.114292860031128, "learning_rate": 5.540777194803013e-05, "loss": 0.8952, "step": 8809 }, { "epoch": 0.4816675209294379, "grad_norm": 2.324937105178833, "learning_rate": 5.539897025114347e-05, "loss": 1.116, "step": 8810 }, { "epoch": 0.48172219374679653, "grad_norm": 3.3200807571411133, "learning_rate": 5.539016838497686e-05, "loss": 1.3136, "step": 8811 }, { "epoch": 0.48177686656415514, "grad_norm": 2.8815884590148926, "learning_rate": 5.5381366349806276e-05, "loss": 1.2207, "step": 8812 }, { "epoch": 0.48183153938151374, "grad_norm": 4.039943218231201, "learning_rate": 5.5372564145907694e-05, "loss": 1.0271, "step": 8813 }, { "epoch": 0.4818862121988724, "grad_norm": 4.322260856628418, "learning_rate": 5.53637617735571e-05, "loss": 1.0725, "step": 8814 }, { "epoch": 0.481940885016231, "grad_norm": 2.0744872093200684, "learning_rate": 5.535495923303048e-05, "loss": 1.0215, "step": 8815 }, { "epoch": 0.4819955578335896, "grad_norm": 2.7730345726013184, "learning_rate": 5.534615652460384e-05, "loss": 1.1825, "step": 8816 }, { "epoch": 0.4820502306509482, "grad_norm": 2.7727091312408447, "learning_rate": 5.533735364855317e-05, "loss": 0.9786, "step": 8817 }, { "epoch": 0.48210490346830687, "grad_norm": 2.795236349105835, "learning_rate": 5.5328550605154484e-05, "loss": 1.1529, "step": 8818 }, { "epoch": 0.48215957628566547, "grad_norm": 3.0915791988372803, "learning_rate": 5.5319747394683784e-05, "loss": 1.0178, "step": 8819 }, { "epoch": 0.4822142491030241, "grad_norm": 2.012667655944824, "learning_rate": 5.531094401741711e-05, "loss": 0.958, "step": 8820 }, { "epoch": 0.48226892192038273, "grad_norm": 2.492316961288452, "learning_rate": 5.5302140473630456e-05, "loss": 1.0734, "step": 8821 }, { "epoch": 0.48232359473774133, "grad_norm": 2.3695170879364014, "learning_rate": 5.529333676359987e-05, "loss": 1.0403, "step": 8822 }, { "epoch": 0.48237826755509994, "grad_norm": 3.408292770385742, "learning_rate": 5.528453288760137e-05, "loss": 0.8747, "step": 8823 }, { "epoch": 0.48243294037245854, "grad_norm": 3.1968162059783936, "learning_rate": 5.527572884591099e-05, "loss": 1.1267, "step": 8824 }, { "epoch": 0.4824876131898172, "grad_norm": 2.7213382720947266, "learning_rate": 5.526692463880481e-05, "loss": 0.8847, "step": 8825 }, { "epoch": 0.4825422860071758, "grad_norm": 2.75209379196167, "learning_rate": 5.5258120266558836e-05, "loss": 1.0712, "step": 8826 }, { "epoch": 0.4825969588245344, "grad_norm": 3.1845874786376953, "learning_rate": 5.524931572944912e-05, "loss": 1.0772, "step": 8827 }, { "epoch": 0.48265163164189306, "grad_norm": 1.989536166191101, "learning_rate": 5.5240511027751765e-05, "loss": 1.0012, "step": 8828 }, { "epoch": 0.48270630445925167, "grad_norm": 2.104356050491333, "learning_rate": 5.523170616174279e-05, "loss": 0.8325, "step": 8829 }, { "epoch": 0.48276097727661027, "grad_norm": 2.8203179836273193, "learning_rate": 5.522290113169828e-05, "loss": 0.9393, "step": 8830 }, { "epoch": 0.48281565009396893, "grad_norm": 2.5978169441223145, "learning_rate": 5.521409593789432e-05, "loss": 1.2302, "step": 8831 }, { "epoch": 0.48287032291132753, "grad_norm": 2.908008098602295, "learning_rate": 5.520529058060697e-05, "loss": 1.2126, "step": 8832 }, { "epoch": 0.48292499572868613, "grad_norm": 1.9996572732925415, "learning_rate": 5.519648506011233e-05, "loss": 0.9321, "step": 8833 }, { "epoch": 0.48297966854604474, "grad_norm": 2.7949700355529785, "learning_rate": 5.518767937668647e-05, "loss": 1.0089, "step": 8834 }, { "epoch": 0.4830343413634034, "grad_norm": 2.4593400955200195, "learning_rate": 5.51788735306055e-05, "loss": 0.9049, "step": 8835 }, { "epoch": 0.483089014180762, "grad_norm": 3.568291425704956, "learning_rate": 5.517006752214552e-05, "loss": 0.832, "step": 8836 }, { "epoch": 0.4831436869981206, "grad_norm": 2.8471615314483643, "learning_rate": 5.516126135158264e-05, "loss": 1.157, "step": 8837 }, { "epoch": 0.48319835981547926, "grad_norm": 2.4121055603027344, "learning_rate": 5.515245501919295e-05, "loss": 1.1273, "step": 8838 }, { "epoch": 0.48325303263283786, "grad_norm": 2.94476580619812, "learning_rate": 5.514364852525258e-05, "loss": 1.095, "step": 8839 }, { "epoch": 0.48330770545019647, "grad_norm": 2.519773244857788, "learning_rate": 5.513484187003762e-05, "loss": 1.1016, "step": 8840 }, { "epoch": 0.4833623782675551, "grad_norm": 3.053366184234619, "learning_rate": 5.5126035053824244e-05, "loss": 0.8969, "step": 8841 }, { "epoch": 0.48341705108491373, "grad_norm": 2.7001068592071533, "learning_rate": 5.511722807688856e-05, "loss": 0.9306, "step": 8842 }, { "epoch": 0.48347172390227233, "grad_norm": 2.9784770011901855, "learning_rate": 5.51084209395067e-05, "loss": 0.9482, "step": 8843 }, { "epoch": 0.48352639671963094, "grad_norm": 5.940891742706299, "learning_rate": 5.50996136419548e-05, "loss": 1.1348, "step": 8844 }, { "epoch": 0.4835810695369896, "grad_norm": 2.8162996768951416, "learning_rate": 5.5090806184509005e-05, "loss": 1.1854, "step": 8845 }, { "epoch": 0.4836357423543482, "grad_norm": 2.8053057193756104, "learning_rate": 5.508199856744547e-05, "loss": 1.3284, "step": 8846 }, { "epoch": 0.4836904151717068, "grad_norm": 2.5625152587890625, "learning_rate": 5.507319079104036e-05, "loss": 1.2352, "step": 8847 }, { "epoch": 0.48374508798906546, "grad_norm": 2.264728546142578, "learning_rate": 5.506438285556982e-05, "loss": 1.0466, "step": 8848 }, { "epoch": 0.48379976080642406, "grad_norm": 2.283168315887451, "learning_rate": 5.5055574761310026e-05, "loss": 0.8805, "step": 8849 }, { "epoch": 0.48385443362378266, "grad_norm": 2.5292277336120605, "learning_rate": 5.504676650853713e-05, "loss": 1.122, "step": 8850 }, { "epoch": 0.48390910644114127, "grad_norm": 3.49868106842041, "learning_rate": 5.503795809752732e-05, "loss": 0.9787, "step": 8851 }, { "epoch": 0.4839637792584999, "grad_norm": 2.4371440410614014, "learning_rate": 5.502914952855678e-05, "loss": 1.123, "step": 8852 }, { "epoch": 0.48401845207585853, "grad_norm": 2.4613215923309326, "learning_rate": 5.502034080190169e-05, "loss": 1.0816, "step": 8853 }, { "epoch": 0.48407312489321713, "grad_norm": 2.572662115097046, "learning_rate": 5.5011531917838246e-05, "loss": 1.1073, "step": 8854 }, { "epoch": 0.4841277977105758, "grad_norm": 2.865748643875122, "learning_rate": 5.500272287664262e-05, "loss": 1.0857, "step": 8855 }, { "epoch": 0.4841824705279344, "grad_norm": 3.019625663757324, "learning_rate": 5.4993913678591045e-05, "loss": 1.0024, "step": 8856 }, { "epoch": 0.484237143345293, "grad_norm": 2.85066294670105, "learning_rate": 5.498510432395971e-05, "loss": 1.1293, "step": 8857 }, { "epoch": 0.48429181616265166, "grad_norm": 2.5524141788482666, "learning_rate": 5.497629481302482e-05, "loss": 1.1428, "step": 8858 }, { "epoch": 0.48434648898001026, "grad_norm": 4.766934871673584, "learning_rate": 5.496748514606259e-05, "loss": 1.2896, "step": 8859 }, { "epoch": 0.48440116179736886, "grad_norm": 2.1087801456451416, "learning_rate": 5.495867532334923e-05, "loss": 1.1408, "step": 8860 }, { "epoch": 0.48445583461472747, "grad_norm": 2.564361572265625, "learning_rate": 5.4949865345161e-05, "loss": 0.9927, "step": 8861 }, { "epoch": 0.4845105074320861, "grad_norm": 2.899001121520996, "learning_rate": 5.49410552117741e-05, "loss": 1.1659, "step": 8862 }, { "epoch": 0.4845651802494447, "grad_norm": 2.9508025646209717, "learning_rate": 5.493224492346476e-05, "loss": 1.1352, "step": 8863 }, { "epoch": 0.48461985306680333, "grad_norm": 3.3841848373413086, "learning_rate": 5.492343448050924e-05, "loss": 1.0543, "step": 8864 }, { "epoch": 0.484674525884162, "grad_norm": 2.6336538791656494, "learning_rate": 5.491462388318376e-05, "loss": 0.9897, "step": 8865 }, { "epoch": 0.4847291987015206, "grad_norm": 3.3277618885040283, "learning_rate": 5.490581313176458e-05, "loss": 1.105, "step": 8866 }, { "epoch": 0.4847838715188792, "grad_norm": 2.438884735107422, "learning_rate": 5.489700222652796e-05, "loss": 0.7449, "step": 8867 }, { "epoch": 0.48483854433623785, "grad_norm": 2.1030375957489014, "learning_rate": 5.4888191167750155e-05, "loss": 0.9665, "step": 8868 }, { "epoch": 0.48489321715359646, "grad_norm": 3.1110527515411377, "learning_rate": 5.4879379955707435e-05, "loss": 1.4174, "step": 8869 }, { "epoch": 0.48494788997095506, "grad_norm": 2.3436360359191895, "learning_rate": 5.487056859067603e-05, "loss": 0.9928, "step": 8870 }, { "epoch": 0.48500256278831366, "grad_norm": 2.5310654640197754, "learning_rate": 5.486175707293226e-05, "loss": 1.1129, "step": 8871 }, { "epoch": 0.4850572356056723, "grad_norm": 3.2445425987243652, "learning_rate": 5.485294540275239e-05, "loss": 1.2812, "step": 8872 }, { "epoch": 0.4851119084230309, "grad_norm": 3.1987674236297607, "learning_rate": 5.484413358041268e-05, "loss": 0.9414, "step": 8873 }, { "epoch": 0.4851665812403895, "grad_norm": 2.721134901046753, "learning_rate": 5.4835321606189426e-05, "loss": 1.0965, "step": 8874 }, { "epoch": 0.4852212540577482, "grad_norm": 3.045103073120117, "learning_rate": 5.4826509480358936e-05, "loss": 1.1425, "step": 8875 }, { "epoch": 0.4852759268751068, "grad_norm": 2.506284475326538, "learning_rate": 5.4817697203197506e-05, "loss": 1.1783, "step": 8876 }, { "epoch": 0.4853305996924654, "grad_norm": 2.817697286605835, "learning_rate": 5.480888477498142e-05, "loss": 1.0976, "step": 8877 }, { "epoch": 0.485385272509824, "grad_norm": 2.1370160579681396, "learning_rate": 5.4800072195986986e-05, "loss": 0.9246, "step": 8878 }, { "epoch": 0.48543994532718265, "grad_norm": 2.434910774230957, "learning_rate": 5.479125946649052e-05, "loss": 1.3075, "step": 8879 }, { "epoch": 0.48549461814454126, "grad_norm": 2.972290277481079, "learning_rate": 5.478244658676833e-05, "loss": 1.053, "step": 8880 }, { "epoch": 0.48554929096189986, "grad_norm": 2.533572196960449, "learning_rate": 5.477363355709676e-05, "loss": 1.1032, "step": 8881 }, { "epoch": 0.4856039637792585, "grad_norm": 2.274644613265991, "learning_rate": 5.476482037775211e-05, "loss": 1.0368, "step": 8882 }, { "epoch": 0.4856586365966171, "grad_norm": 2.274229049682617, "learning_rate": 5.4756007049010724e-05, "loss": 0.9299, "step": 8883 }, { "epoch": 0.4857133094139757, "grad_norm": 2.4118385314941406, "learning_rate": 5.4747193571148927e-05, "loss": 1.1398, "step": 8884 }, { "epoch": 0.4857679822313344, "grad_norm": 2.30576753616333, "learning_rate": 5.473837994444305e-05, "loss": 1.0961, "step": 8885 }, { "epoch": 0.485822655048693, "grad_norm": 2.3836734294891357, "learning_rate": 5.472956616916945e-05, "loss": 0.8888, "step": 8886 }, { "epoch": 0.4858773278660516, "grad_norm": 2.683981418609619, "learning_rate": 5.472075224560449e-05, "loss": 1.0405, "step": 8887 }, { "epoch": 0.4859320006834102, "grad_norm": 3.2351512908935547, "learning_rate": 5.471193817402449e-05, "loss": 1.1015, "step": 8888 }, { "epoch": 0.48598667350076885, "grad_norm": 2.4668169021606445, "learning_rate": 5.470312395470583e-05, "loss": 1.2227, "step": 8889 }, { "epoch": 0.48604134631812745, "grad_norm": 2.761277437210083, "learning_rate": 5.469430958792485e-05, "loss": 1.1959, "step": 8890 }, { "epoch": 0.48609601913548606, "grad_norm": 3.223613977432251, "learning_rate": 5.4685495073957946e-05, "loss": 1.1821, "step": 8891 }, { "epoch": 0.4861506919528447, "grad_norm": 2.409693479537964, "learning_rate": 5.467668041308147e-05, "loss": 0.9005, "step": 8892 }, { "epoch": 0.4862053647702033, "grad_norm": 2.8181099891662598, "learning_rate": 5.466786560557181e-05, "loss": 1.0268, "step": 8893 }, { "epoch": 0.4862600375875619, "grad_norm": 4.07676362991333, "learning_rate": 5.465905065170531e-05, "loss": 1.2321, "step": 8894 }, { "epoch": 0.4863147104049206, "grad_norm": 3.98415207862854, "learning_rate": 5.465023555175841e-05, "loss": 1.0214, "step": 8895 }, { "epoch": 0.4863693832222792, "grad_norm": 2.4985084533691406, "learning_rate": 5.4641420306007474e-05, "loss": 0.9765, "step": 8896 }, { "epoch": 0.4864240560396378, "grad_norm": 2.8935861587524414, "learning_rate": 5.463260491472889e-05, "loss": 0.8687, "step": 8897 }, { "epoch": 0.4864787288569964, "grad_norm": 2.7468507289886475, "learning_rate": 5.462378937819907e-05, "loss": 0.9949, "step": 8898 }, { "epoch": 0.48653340167435505, "grad_norm": 2.2257912158966064, "learning_rate": 5.4614973696694395e-05, "loss": 1.0867, "step": 8899 }, { "epoch": 0.48658807449171365, "grad_norm": 2.2852320671081543, "learning_rate": 5.46061578704913e-05, "loss": 1.0536, "step": 8900 }, { "epoch": 0.48664274730907225, "grad_norm": 2.718416213989258, "learning_rate": 5.4597341899866186e-05, "loss": 0.9733, "step": 8901 }, { "epoch": 0.4866974201264309, "grad_norm": 2.6890206336975098, "learning_rate": 5.458852578509547e-05, "loss": 1.1788, "step": 8902 }, { "epoch": 0.4867520929437895, "grad_norm": 2.216003656387329, "learning_rate": 5.457970952645557e-05, "loss": 1.016, "step": 8903 }, { "epoch": 0.4868067657611481, "grad_norm": 1.8568695783615112, "learning_rate": 5.45708931242229e-05, "loss": 0.7858, "step": 8904 }, { "epoch": 0.4868614385785067, "grad_norm": 1.9959208965301514, "learning_rate": 5.456207657867393e-05, "loss": 0.9469, "step": 8905 }, { "epoch": 0.4869161113958654, "grad_norm": 2.2756903171539307, "learning_rate": 5.455325989008506e-05, "loss": 1.1673, "step": 8906 }, { "epoch": 0.486970784213224, "grad_norm": 2.410196542739868, "learning_rate": 5.454444305873274e-05, "loss": 0.9484, "step": 8907 }, { "epoch": 0.4870254570305826, "grad_norm": 2.947932720184326, "learning_rate": 5.453562608489342e-05, "loss": 1.0653, "step": 8908 }, { "epoch": 0.48708012984794125, "grad_norm": 2.4677321910858154, "learning_rate": 5.452680896884353e-05, "loss": 0.8942, "step": 8909 }, { "epoch": 0.48713480266529985, "grad_norm": 2.4523282051086426, "learning_rate": 5.451799171085955e-05, "loss": 1.023, "step": 8910 }, { "epoch": 0.48718947548265845, "grad_norm": 2.453313112258911, "learning_rate": 5.4509174311217915e-05, "loss": 1.0844, "step": 8911 }, { "epoch": 0.4872441483000171, "grad_norm": 2.625335454940796, "learning_rate": 5.4500356770195096e-05, "loss": 1.0734, "step": 8912 }, { "epoch": 0.4872988211173757, "grad_norm": 2.6741015911102295, "learning_rate": 5.449153908806756e-05, "loss": 1.136, "step": 8913 }, { "epoch": 0.4873534939347343, "grad_norm": 2.4290554523468018, "learning_rate": 5.448272126511177e-05, "loss": 1.0388, "step": 8914 }, { "epoch": 0.4874081667520929, "grad_norm": 2.3308424949645996, "learning_rate": 5.447390330160421e-05, "loss": 0.866, "step": 8915 }, { "epoch": 0.4874628395694516, "grad_norm": 2.4708120822906494, "learning_rate": 5.446508519782137e-05, "loss": 1.127, "step": 8916 }, { "epoch": 0.4875175123868102, "grad_norm": 2.527226686477661, "learning_rate": 5.445626695403969e-05, "loss": 1.003, "step": 8917 }, { "epoch": 0.4875721852041688, "grad_norm": 3.734586238861084, "learning_rate": 5.4447448570535706e-05, "loss": 1.0492, "step": 8918 }, { "epoch": 0.48762685802152744, "grad_norm": 2.37860369682312, "learning_rate": 5.443863004758589e-05, "loss": 1.1168, "step": 8919 }, { "epoch": 0.48768153083888605, "grad_norm": 1.9137465953826904, "learning_rate": 5.4429811385466746e-05, "loss": 0.8785, "step": 8920 }, { "epoch": 0.48773620365624465, "grad_norm": 3.2114028930664062, "learning_rate": 5.4420992584454764e-05, "loss": 1.1141, "step": 8921 }, { "epoch": 0.4877908764736033, "grad_norm": 3.2236976623535156, "learning_rate": 5.441217364482647e-05, "loss": 0.9521, "step": 8922 }, { "epoch": 0.4878455492909619, "grad_norm": 1.9619297981262207, "learning_rate": 5.4403354566858344e-05, "loss": 0.806, "step": 8923 }, { "epoch": 0.4879002221083205, "grad_norm": 2.1029317378997803, "learning_rate": 5.439453535082692e-05, "loss": 0.932, "step": 8924 }, { "epoch": 0.4879548949256791, "grad_norm": 3.147432565689087, "learning_rate": 5.438571599700872e-05, "loss": 1.1741, "step": 8925 }, { "epoch": 0.4880095677430378, "grad_norm": 2.622077703475952, "learning_rate": 5.437689650568026e-05, "loss": 0.9374, "step": 8926 }, { "epoch": 0.4880642405603964, "grad_norm": 3.0343799591064453, "learning_rate": 5.436807687711808e-05, "loss": 1.3207, "step": 8927 }, { "epoch": 0.488118913377755, "grad_norm": 2.786506175994873, "learning_rate": 5.435925711159868e-05, "loss": 1.0183, "step": 8928 }, { "epoch": 0.48817358619511364, "grad_norm": 2.623276948928833, "learning_rate": 5.435043720939863e-05, "loss": 1.1208, "step": 8929 }, { "epoch": 0.48822825901247224, "grad_norm": 2.4186112880706787, "learning_rate": 5.4341617170794444e-05, "loss": 1.0673, "step": 8930 }, { "epoch": 0.48828293182983085, "grad_norm": 2.7014236450195312, "learning_rate": 5.4332796996062694e-05, "loss": 1.1949, "step": 8931 }, { "epoch": 0.48833760464718945, "grad_norm": 2.8073339462280273, "learning_rate": 5.43239766854799e-05, "loss": 0.9801, "step": 8932 }, { "epoch": 0.4883922774645481, "grad_norm": 2.375197410583496, "learning_rate": 5.431515623932264e-05, "loss": 1.1357, "step": 8933 }, { "epoch": 0.4884469502819067, "grad_norm": 2.2816145420074463, "learning_rate": 5.430633565786746e-05, "loss": 1.0055, "step": 8934 }, { "epoch": 0.4885016230992653, "grad_norm": 5.436169147491455, "learning_rate": 5.429751494139091e-05, "loss": 1.0057, "step": 8935 }, { "epoch": 0.488556295916624, "grad_norm": 2.534119129180908, "learning_rate": 5.4288694090169575e-05, "loss": 1.0314, "step": 8936 }, { "epoch": 0.4886109687339826, "grad_norm": 2.459425449371338, "learning_rate": 5.4279873104480025e-05, "loss": 0.9448, "step": 8937 }, { "epoch": 0.4886656415513412, "grad_norm": 3.1375153064727783, "learning_rate": 5.427105198459881e-05, "loss": 1.1654, "step": 8938 }, { "epoch": 0.48872031436869984, "grad_norm": 3.050347089767456, "learning_rate": 5.426223073080253e-05, "loss": 1.2989, "step": 8939 }, { "epoch": 0.48877498718605844, "grad_norm": 2.2871413230895996, "learning_rate": 5.425340934336778e-05, "loss": 1.0694, "step": 8940 }, { "epoch": 0.48882966000341704, "grad_norm": 2.381321907043457, "learning_rate": 5.4244587822571114e-05, "loss": 1.1888, "step": 8941 }, { "epoch": 0.48888433282077565, "grad_norm": 2.385685920715332, "learning_rate": 5.423576616868915e-05, "loss": 1.0418, "step": 8942 }, { "epoch": 0.4889390056381343, "grad_norm": 2.5360705852508545, "learning_rate": 5.4226944381998443e-05, "loss": 0.8503, "step": 8943 }, { "epoch": 0.4889936784554929, "grad_norm": 2.5357189178466797, "learning_rate": 5.421812246277565e-05, "loss": 1.0318, "step": 8944 }, { "epoch": 0.4890483512728515, "grad_norm": 2.31687068939209, "learning_rate": 5.420930041129735e-05, "loss": 1.0282, "step": 8945 }, { "epoch": 0.48910302409021017, "grad_norm": 3.1548147201538086, "learning_rate": 5.420047822784014e-05, "loss": 1.0002, "step": 8946 }, { "epoch": 0.4891576969075688, "grad_norm": 2.1748642921447754, "learning_rate": 5.4191655912680625e-05, "loss": 0.9059, "step": 8947 }, { "epoch": 0.4892123697249274, "grad_norm": 2.3437674045562744, "learning_rate": 5.418283346609543e-05, "loss": 0.9307, "step": 8948 }, { "epoch": 0.48926704254228603, "grad_norm": 2.5361313819885254, "learning_rate": 5.417401088836119e-05, "loss": 1.0498, "step": 8949 }, { "epoch": 0.48932171535964464, "grad_norm": 2.1880996227264404, "learning_rate": 5.416518817975452e-05, "loss": 1.0353, "step": 8950 }, { "epoch": 0.48937638817700324, "grad_norm": 3.2197279930114746, "learning_rate": 5.415636534055205e-05, "loss": 1.0841, "step": 8951 }, { "epoch": 0.48943106099436184, "grad_norm": 2.6446588039398193, "learning_rate": 5.4147542371030414e-05, "loss": 1.093, "step": 8952 }, { "epoch": 0.4894857338117205, "grad_norm": 3.074270009994507, "learning_rate": 5.413871927146622e-05, "loss": 1.0888, "step": 8953 }, { "epoch": 0.4895404066290791, "grad_norm": 2.9564414024353027, "learning_rate": 5.412989604213615e-05, "loss": 1.064, "step": 8954 }, { "epoch": 0.4895950794464377, "grad_norm": 2.70206356048584, "learning_rate": 5.412107268331683e-05, "loss": 0.9971, "step": 8955 }, { "epoch": 0.48964975226379637, "grad_norm": 2.287541389465332, "learning_rate": 5.4112249195284904e-05, "loss": 0.9835, "step": 8956 }, { "epoch": 0.48970442508115497, "grad_norm": 2.643972873687744, "learning_rate": 5.410342557831703e-05, "loss": 1.157, "step": 8957 }, { "epoch": 0.4897590978985136, "grad_norm": 2.558608055114746, "learning_rate": 5.409460183268986e-05, "loss": 1.2075, "step": 8958 }, { "epoch": 0.4898137707158722, "grad_norm": 3.2916314601898193, "learning_rate": 5.408577795868006e-05, "loss": 0.9426, "step": 8959 }, { "epoch": 0.48986844353323084, "grad_norm": 2.6077346801757812, "learning_rate": 5.4076953956564305e-05, "loss": 1.1243, "step": 8960 }, { "epoch": 0.48992311635058944, "grad_norm": 1.9306119680404663, "learning_rate": 5.4068129826619254e-05, "loss": 0.8157, "step": 8961 }, { "epoch": 0.48997778916794804, "grad_norm": 2.7791531085968018, "learning_rate": 5.4059305569121566e-05, "loss": 0.9512, "step": 8962 }, { "epoch": 0.4900324619853067, "grad_norm": 2.782134771347046, "learning_rate": 5.405048118434792e-05, "loss": 1.2701, "step": 8963 }, { "epoch": 0.4900871348026653, "grad_norm": 2.2171599864959717, "learning_rate": 5.4041656672575034e-05, "loss": 0.9429, "step": 8964 }, { "epoch": 0.4901418076200239, "grad_norm": 2.5844457149505615, "learning_rate": 5.403283203407955e-05, "loss": 0.8483, "step": 8965 }, { "epoch": 0.49019648043738256, "grad_norm": 2.4987189769744873, "learning_rate": 5.402400726913819e-05, "loss": 1.0997, "step": 8966 }, { "epoch": 0.49025115325474117, "grad_norm": 2.1683590412139893, "learning_rate": 5.401518237802762e-05, "loss": 0.8417, "step": 8967 }, { "epoch": 0.49030582607209977, "grad_norm": 5.084044456481934, "learning_rate": 5.400635736102453e-05, "loss": 1.2284, "step": 8968 }, { "epoch": 0.4903604988894584, "grad_norm": 2.646573543548584, "learning_rate": 5.399753221840564e-05, "loss": 1.1964, "step": 8969 }, { "epoch": 0.49041517170681703, "grad_norm": 2.2618489265441895, "learning_rate": 5.398870695044768e-05, "loss": 0.8658, "step": 8970 }, { "epoch": 0.49046984452417564, "grad_norm": 2.6151392459869385, "learning_rate": 5.39798815574273e-05, "loss": 1.1772, "step": 8971 }, { "epoch": 0.49052451734153424, "grad_norm": 2.390544891357422, "learning_rate": 5.397105603962126e-05, "loss": 1.0676, "step": 8972 }, { "epoch": 0.4905791901588929, "grad_norm": 2.6363368034362793, "learning_rate": 5.3962230397306244e-05, "loss": 1.0105, "step": 8973 }, { "epoch": 0.4906338629762515, "grad_norm": 2.373673439025879, "learning_rate": 5.3953404630759e-05, "loss": 1.0204, "step": 8974 }, { "epoch": 0.4906885357936101, "grad_norm": 2.113675832748413, "learning_rate": 5.3944578740256236e-05, "loss": 0.8723, "step": 8975 }, { "epoch": 0.4907432086109687, "grad_norm": 2.9289286136627197, "learning_rate": 5.3935752726074686e-05, "loss": 1.077, "step": 8976 }, { "epoch": 0.49079788142832736, "grad_norm": 2.610100030899048, "learning_rate": 5.392692658849105e-05, "loss": 1.0094, "step": 8977 }, { "epoch": 0.49085255424568597, "grad_norm": 2.6916420459747314, "learning_rate": 5.391810032778213e-05, "loss": 1.0239, "step": 8978 }, { "epoch": 0.49090722706304457, "grad_norm": 2.2631309032440186, "learning_rate": 5.390927394422461e-05, "loss": 1.1221, "step": 8979 }, { "epoch": 0.49096189988040323, "grad_norm": 2.5525074005126953, "learning_rate": 5.390044743809526e-05, "loss": 1.0105, "step": 8980 }, { "epoch": 0.49101657269776183, "grad_norm": 2.657773017883301, "learning_rate": 5.389162080967082e-05, "loss": 1.0727, "step": 8981 }, { "epoch": 0.49107124551512044, "grad_norm": 4.374697208404541, "learning_rate": 5.388279405922803e-05, "loss": 1.2963, "step": 8982 }, { "epoch": 0.4911259183324791, "grad_norm": 2.505939483642578, "learning_rate": 5.387396718704366e-05, "loss": 1.077, "step": 8983 }, { "epoch": 0.4911805911498377, "grad_norm": 2.4026455879211426, "learning_rate": 5.386514019339447e-05, "loss": 1.0275, "step": 8984 }, { "epoch": 0.4912352639671963, "grad_norm": 2.351851463317871, "learning_rate": 5.385631307855721e-05, "loss": 0.9967, "step": 8985 }, { "epoch": 0.4912899367845549, "grad_norm": 2.4681236743927, "learning_rate": 5.384748584280865e-05, "loss": 1.2621, "step": 8986 }, { "epoch": 0.49134460960191356, "grad_norm": 2.573364496231079, "learning_rate": 5.3838658486425565e-05, "loss": 1.1774, "step": 8987 }, { "epoch": 0.49139928241927217, "grad_norm": 3.8421976566314697, "learning_rate": 5.382983100968474e-05, "loss": 0.8754, "step": 8988 }, { "epoch": 0.49145395523663077, "grad_norm": 2.5183730125427246, "learning_rate": 5.382100341286293e-05, "loss": 0.9903, "step": 8989 }, { "epoch": 0.4915086280539894, "grad_norm": 4.0774827003479, "learning_rate": 5.381217569623692e-05, "loss": 1.0087, "step": 8990 }, { "epoch": 0.49156330087134803, "grad_norm": 3.537536859512329, "learning_rate": 5.380334786008352e-05, "loss": 1.1989, "step": 8991 }, { "epoch": 0.49161797368870663, "grad_norm": 3.0093801021575928, "learning_rate": 5.3794519904679475e-05, "loss": 1.0155, "step": 8992 }, { "epoch": 0.4916726465060653, "grad_norm": 2.7470450401306152, "learning_rate": 5.378569183030162e-05, "loss": 1.0628, "step": 8993 }, { "epoch": 0.4917273193234239, "grad_norm": 2.645456075668335, "learning_rate": 5.377686363722674e-05, "loss": 1.0765, "step": 8994 }, { "epoch": 0.4917819921407825, "grad_norm": 2.3021631240844727, "learning_rate": 5.376803532573162e-05, "loss": 0.9234, "step": 8995 }, { "epoch": 0.4918366649581411, "grad_norm": 2.6057016849517822, "learning_rate": 5.3759206896093084e-05, "loss": 1.078, "step": 8996 }, { "epoch": 0.49189133777549976, "grad_norm": 2.7782211303710938, "learning_rate": 5.3750378348587925e-05, "loss": 1.216, "step": 8997 }, { "epoch": 0.49194601059285836, "grad_norm": 2.3115105628967285, "learning_rate": 5.374154968349294e-05, "loss": 0.9728, "step": 8998 }, { "epoch": 0.49200068341021697, "grad_norm": 2.3995234966278076, "learning_rate": 5.373272090108499e-05, "loss": 0.9524, "step": 8999 }, { "epoch": 0.4920553562275756, "grad_norm": 2.18552303314209, "learning_rate": 5.372389200164085e-05, "loss": 0.9595, "step": 9000 }, { "epoch": 0.4921100290449342, "grad_norm": 2.4288361072540283, "learning_rate": 5.371506298543737e-05, "loss": 1.0226, "step": 9001 }, { "epoch": 0.49216470186229283, "grad_norm": 2.3748111724853516, "learning_rate": 5.370623385275136e-05, "loss": 1.0189, "step": 9002 }, { "epoch": 0.49221937467965143, "grad_norm": 3.6386172771453857, "learning_rate": 5.369740460385967e-05, "loss": 1.3235, "step": 9003 }, { "epoch": 0.4922740474970101, "grad_norm": 3.5139098167419434, "learning_rate": 5.3688575239039086e-05, "loss": 1.0752, "step": 9004 }, { "epoch": 0.4923287203143687, "grad_norm": 3.8775458335876465, "learning_rate": 5.36797457585665e-05, "loss": 0.9811, "step": 9005 }, { "epoch": 0.4923833931317273, "grad_norm": 3.036611318588257, "learning_rate": 5.3670916162718734e-05, "loss": 1.053, "step": 9006 }, { "epoch": 0.49243806594908596, "grad_norm": 3.6225719451904297, "learning_rate": 5.366208645177262e-05, "loss": 1.0642, "step": 9007 }, { "epoch": 0.49249273876644456, "grad_norm": 3.35721755027771, "learning_rate": 5.365325662600501e-05, "loss": 1.0924, "step": 9008 }, { "epoch": 0.49254741158380316, "grad_norm": 3.0943796634674072, "learning_rate": 5.364442668569276e-05, "loss": 1.091, "step": 9009 }, { "epoch": 0.4926020844011618, "grad_norm": 2.642934560775757, "learning_rate": 5.363559663111273e-05, "loss": 1.0587, "step": 9010 }, { "epoch": 0.4926567572185204, "grad_norm": 3.2059502601623535, "learning_rate": 5.3626766462541755e-05, "loss": 1.1833, "step": 9011 }, { "epoch": 0.49271143003587903, "grad_norm": 2.839372396469116, "learning_rate": 5.3617936180256735e-05, "loss": 1.1345, "step": 9012 }, { "epoch": 0.49276610285323763, "grad_norm": 2.5150020122528076, "learning_rate": 5.360910578453451e-05, "loss": 1.0834, "step": 9013 }, { "epoch": 0.4928207756705963, "grad_norm": 2.6423468589782715, "learning_rate": 5.360027527565196e-05, "loss": 1.0058, "step": 9014 }, { "epoch": 0.4928754484879549, "grad_norm": 2.3847765922546387, "learning_rate": 5.3591444653885946e-05, "loss": 1.104, "step": 9015 }, { "epoch": 0.4929301213053135, "grad_norm": 2.588247776031494, "learning_rate": 5.358261391951336e-05, "loss": 0.9334, "step": 9016 }, { "epoch": 0.49298479412267215, "grad_norm": 2.6051793098449707, "learning_rate": 5.3573783072811046e-05, "loss": 1.0973, "step": 9017 }, { "epoch": 0.49303946694003076, "grad_norm": 4.429516792297363, "learning_rate": 5.3564952114055936e-05, "loss": 1.1706, "step": 9018 }, { "epoch": 0.49309413975738936, "grad_norm": 3.1104156970977783, "learning_rate": 5.35561210435249e-05, "loss": 0.9967, "step": 9019 }, { "epoch": 0.493148812574748, "grad_norm": 2.622262954711914, "learning_rate": 5.3547289861494806e-05, "loss": 1.0205, "step": 9020 }, { "epoch": 0.4932034853921066, "grad_norm": 3.633965253829956, "learning_rate": 5.353845856824258e-05, "loss": 1.3466, "step": 9021 }, { "epoch": 0.4932581582094652, "grad_norm": 2.329836130142212, "learning_rate": 5.352962716404509e-05, "loss": 0.9599, "step": 9022 }, { "epoch": 0.49331283102682383, "grad_norm": 1.9372072219848633, "learning_rate": 5.352079564917927e-05, "loss": 0.9103, "step": 9023 }, { "epoch": 0.4933675038441825, "grad_norm": 4.681174278259277, "learning_rate": 5.3511964023922e-05, "loss": 0.9496, "step": 9024 }, { "epoch": 0.4934221766615411, "grad_norm": 2.2721736431121826, "learning_rate": 5.350313228855018e-05, "loss": 1.0492, "step": 9025 }, { "epoch": 0.4934768494788997, "grad_norm": 2.2253191471099854, "learning_rate": 5.349430044334076e-05, "loss": 0.8325, "step": 9026 }, { "epoch": 0.49353152229625835, "grad_norm": 2.9598028659820557, "learning_rate": 5.348546848857061e-05, "loss": 1.057, "step": 9027 }, { "epoch": 0.49358619511361695, "grad_norm": 2.869166135787964, "learning_rate": 5.347663642451668e-05, "loss": 0.9783, "step": 9028 }, { "epoch": 0.49364086793097556, "grad_norm": 2.534822702407837, "learning_rate": 5.346780425145588e-05, "loss": 1.2114, "step": 9029 }, { "epoch": 0.49369554074833416, "grad_norm": 2.210524559020996, "learning_rate": 5.345897196966513e-05, "loss": 1.0786, "step": 9030 }, { "epoch": 0.4937502135656928, "grad_norm": 3.0439584255218506, "learning_rate": 5.345013957942134e-05, "loss": 0.9065, "step": 9031 }, { "epoch": 0.4938048863830514, "grad_norm": 3.434354305267334, "learning_rate": 5.34413070810015e-05, "loss": 1.1127, "step": 9032 }, { "epoch": 0.49385955920041, "grad_norm": 2.572155714035034, "learning_rate": 5.3432474474682504e-05, "loss": 0.9412, "step": 9033 }, { "epoch": 0.4939142320177687, "grad_norm": 2.3685498237609863, "learning_rate": 5.342364176074128e-05, "loss": 1.1315, "step": 9034 }, { "epoch": 0.4939689048351273, "grad_norm": 2.3511769771575928, "learning_rate": 5.341480893945481e-05, "loss": 1.0365, "step": 9035 }, { "epoch": 0.4940235776524859, "grad_norm": 2.557197332382202, "learning_rate": 5.340597601109999e-05, "loss": 1.1133, "step": 9036 }, { "epoch": 0.49407825046984455, "grad_norm": 2.767559289932251, "learning_rate": 5.339714297595382e-05, "loss": 0.9814, "step": 9037 }, { "epoch": 0.49413292328720315, "grad_norm": 2.5954809188842773, "learning_rate": 5.3388309834293216e-05, "loss": 1.0559, "step": 9038 }, { "epoch": 0.49418759610456175, "grad_norm": 2.0658655166625977, "learning_rate": 5.3379476586395136e-05, "loss": 0.8988, "step": 9039 }, { "epoch": 0.49424226892192036, "grad_norm": 3.4473929405212402, "learning_rate": 5.337064323253656e-05, "loss": 0.8504, "step": 9040 }, { "epoch": 0.494296941739279, "grad_norm": 2.344867706298828, "learning_rate": 5.3361809772994434e-05, "loss": 1.0887, "step": 9041 }, { "epoch": 0.4943516145566376, "grad_norm": 2.9091804027557373, "learning_rate": 5.3352976208045715e-05, "loss": 1.0084, "step": 9042 }, { "epoch": 0.4944062873739962, "grad_norm": 2.892996072769165, "learning_rate": 5.33441425379674e-05, "loss": 1.2146, "step": 9043 }, { "epoch": 0.4944609601913549, "grad_norm": 2.716458797454834, "learning_rate": 5.333530876303644e-05, "loss": 1.1098, "step": 9044 }, { "epoch": 0.4945156330087135, "grad_norm": 2.816884994506836, "learning_rate": 5.332647488352981e-05, "loss": 0.9699, "step": 9045 }, { "epoch": 0.4945703058260721, "grad_norm": 2.5272536277770996, "learning_rate": 5.3317640899724484e-05, "loss": 0.8592, "step": 9046 }, { "epoch": 0.49462497864343075, "grad_norm": 2.4940574169158936, "learning_rate": 5.330880681189746e-05, "loss": 0.821, "step": 9047 }, { "epoch": 0.49467965146078935, "grad_norm": 4.864889621734619, "learning_rate": 5.329997262032572e-05, "loss": 1.1198, "step": 9048 }, { "epoch": 0.49473432427814795, "grad_norm": 3.5408787727355957, "learning_rate": 5.329113832528624e-05, "loss": 1.082, "step": 9049 }, { "epoch": 0.49478899709550656, "grad_norm": 2.488349199295044, "learning_rate": 5.328230392705603e-05, "loss": 0.9931, "step": 9050 }, { "epoch": 0.4948436699128652, "grad_norm": 2.4080443382263184, "learning_rate": 5.327346942591206e-05, "loss": 1.0057, "step": 9051 }, { "epoch": 0.4948983427302238, "grad_norm": 2.75531005859375, "learning_rate": 5.326463482213134e-05, "loss": 1.1074, "step": 9052 }, { "epoch": 0.4949530155475824, "grad_norm": 2.6094489097595215, "learning_rate": 5.3255800115990895e-05, "loss": 0.9924, "step": 9053 }, { "epoch": 0.4950076883649411, "grad_norm": 2.6015563011169434, "learning_rate": 5.324696530776769e-05, "loss": 0.8639, "step": 9054 }, { "epoch": 0.4950623611822997, "grad_norm": 2.3140952587127686, "learning_rate": 5.3238130397738764e-05, "loss": 1.0059, "step": 9055 }, { "epoch": 0.4951170339996583, "grad_norm": 3.4382519721984863, "learning_rate": 5.3229295386181086e-05, "loss": 0.933, "step": 9056 }, { "epoch": 0.4951717068170169, "grad_norm": 3.0019900798797607, "learning_rate": 5.322046027337172e-05, "loss": 1.0753, "step": 9057 }, { "epoch": 0.49522637963437555, "grad_norm": 3.7078607082366943, "learning_rate": 5.321162505958767e-05, "loss": 1.0636, "step": 9058 }, { "epoch": 0.49528105245173415, "grad_norm": 2.6665396690368652, "learning_rate": 5.320278974510593e-05, "loss": 1.1481, "step": 9059 }, { "epoch": 0.49533572526909275, "grad_norm": 2.3510754108428955, "learning_rate": 5.319395433020354e-05, "loss": 1.1282, "step": 9060 }, { "epoch": 0.4953903980864514, "grad_norm": 2.655787467956543, "learning_rate": 5.318511881515753e-05, "loss": 1.1091, "step": 9061 }, { "epoch": 0.49544507090381, "grad_norm": 4.860716819763184, "learning_rate": 5.317628320024494e-05, "loss": 0.9249, "step": 9062 }, { "epoch": 0.4954997437211686, "grad_norm": 2.3528127670288086, "learning_rate": 5.3167447485742784e-05, "loss": 1.1711, "step": 9063 }, { "epoch": 0.4955544165385273, "grad_norm": 2.8121912479400635, "learning_rate": 5.31586116719281e-05, "loss": 1.1801, "step": 9064 }, { "epoch": 0.4956090893558859, "grad_norm": 2.335580587387085, "learning_rate": 5.3149775759077936e-05, "loss": 0.8942, "step": 9065 }, { "epoch": 0.4956637621732445, "grad_norm": 2.3781259059906006, "learning_rate": 5.314093974746932e-05, "loss": 0.98, "step": 9066 }, { "epoch": 0.4957184349906031, "grad_norm": 3.4017996788024902, "learning_rate": 5.313210363737932e-05, "loss": 1.1697, "step": 9067 }, { "epoch": 0.49577310780796174, "grad_norm": 3.0335500240325928, "learning_rate": 5.3123267429084966e-05, "loss": 0.9821, "step": 9068 }, { "epoch": 0.49582778062532035, "grad_norm": 2.36653733253479, "learning_rate": 5.311443112286332e-05, "loss": 1.0429, "step": 9069 }, { "epoch": 0.49588245344267895, "grad_norm": 3.4131927490234375, "learning_rate": 5.310559471899143e-05, "loss": 1.0422, "step": 9070 }, { "epoch": 0.4959371262600376, "grad_norm": 3.4293200969696045, "learning_rate": 5.3096758217746334e-05, "loss": 1.1302, "step": 9071 }, { "epoch": 0.4959917990773962, "grad_norm": 2.7822842597961426, "learning_rate": 5.3087921619405136e-05, "loss": 1.2586, "step": 9072 }, { "epoch": 0.4960464718947548, "grad_norm": 2.7554919719696045, "learning_rate": 5.307908492424488e-05, "loss": 0.9404, "step": 9073 }, { "epoch": 0.4961011447121135, "grad_norm": 2.853869915008545, "learning_rate": 5.307024813254262e-05, "loss": 0.9727, "step": 9074 }, { "epoch": 0.4961558175294721, "grad_norm": 2.225767135620117, "learning_rate": 5.3061411244575454e-05, "loss": 1.0429, "step": 9075 }, { "epoch": 0.4962104903468307, "grad_norm": 2.0531349182128906, "learning_rate": 5.305257426062041e-05, "loss": 1.0591, "step": 9076 }, { "epoch": 0.4962651631641893, "grad_norm": 3.123828172683716, "learning_rate": 5.304373718095461e-05, "loss": 1.231, "step": 9077 }, { "epoch": 0.49631983598154794, "grad_norm": 2.571728229522705, "learning_rate": 5.3034900005855115e-05, "loss": 1.028, "step": 9078 }, { "epoch": 0.49637450879890654, "grad_norm": 2.301037073135376, "learning_rate": 5.3026062735599e-05, "loss": 1.0867, "step": 9079 }, { "epoch": 0.49642918161626515, "grad_norm": 2.2893612384796143, "learning_rate": 5.301722537046335e-05, "loss": 0.9748, "step": 9080 }, { "epoch": 0.4964838544336238, "grad_norm": 3.1028761863708496, "learning_rate": 5.300838791072527e-05, "loss": 0.961, "step": 9081 }, { "epoch": 0.4965385272509824, "grad_norm": 3.142061948776245, "learning_rate": 5.299955035666183e-05, "loss": 1.277, "step": 9082 }, { "epoch": 0.496593200068341, "grad_norm": 2.8090145587921143, "learning_rate": 5.299071270855014e-05, "loss": 1.1238, "step": 9083 }, { "epoch": 0.4966478728856996, "grad_norm": 2.713192939758301, "learning_rate": 5.298187496666729e-05, "loss": 1.0334, "step": 9084 }, { "epoch": 0.4967025457030583, "grad_norm": 2.6196773052215576, "learning_rate": 5.297303713129036e-05, "loss": 1.1455, "step": 9085 }, { "epoch": 0.4967572185204169, "grad_norm": 3.122955560684204, "learning_rate": 5.2964199202696496e-05, "loss": 1.0581, "step": 9086 }, { "epoch": 0.4968118913377755, "grad_norm": 3.185612201690674, "learning_rate": 5.295536118116277e-05, "loss": 1.302, "step": 9087 }, { "epoch": 0.49686656415513414, "grad_norm": 2.6759445667266846, "learning_rate": 5.2946523066966304e-05, "loss": 0.9593, "step": 9088 }, { "epoch": 0.49692123697249274, "grad_norm": 3.276606559753418, "learning_rate": 5.2937684860384195e-05, "loss": 0.8899, "step": 9089 }, { "epoch": 0.49697590978985134, "grad_norm": 3.0620503425598145, "learning_rate": 5.292884656169358e-05, "loss": 1.2001, "step": 9090 }, { "epoch": 0.49703058260721, "grad_norm": 3.010430097579956, "learning_rate": 5.2920008171171545e-05, "loss": 0.8554, "step": 9091 }, { "epoch": 0.4970852554245686, "grad_norm": 3.194749355316162, "learning_rate": 5.291116968909524e-05, "loss": 0.9537, "step": 9092 }, { "epoch": 0.4971399282419272, "grad_norm": 2.5346434116363525, "learning_rate": 5.2902331115741775e-05, "loss": 1.0437, "step": 9093 }, { "epoch": 0.4971946010592858, "grad_norm": 3.5306432247161865, "learning_rate": 5.2893492451388285e-05, "loss": 1.041, "step": 9094 }, { "epoch": 0.49724927387664447, "grad_norm": 2.460732936859131, "learning_rate": 5.288465369631188e-05, "loss": 1.0778, "step": 9095 }, { "epoch": 0.4973039466940031, "grad_norm": 2.0752174854278564, "learning_rate": 5.2875814850789706e-05, "loss": 1.0084, "step": 9096 }, { "epoch": 0.4973586195113617, "grad_norm": 2.9197146892547607, "learning_rate": 5.2866975915098894e-05, "loss": 0.9001, "step": 9097 }, { "epoch": 0.49741329232872034, "grad_norm": 2.2872414588928223, "learning_rate": 5.285813688951656e-05, "loss": 0.9876, "step": 9098 }, { "epoch": 0.49746796514607894, "grad_norm": 3.2731001377105713, "learning_rate": 5.2849297774319886e-05, "loss": 1.2455, "step": 9099 }, { "epoch": 0.49752263796343754, "grad_norm": 2.6271302700042725, "learning_rate": 5.284045856978598e-05, "loss": 1.2947, "step": 9100 }, { "epoch": 0.4975773107807962, "grad_norm": 2.7401793003082275, "learning_rate": 5.2831619276192e-05, "loss": 1.0248, "step": 9101 }, { "epoch": 0.4976319835981548, "grad_norm": 3.1164968013763428, "learning_rate": 5.28227798938151e-05, "loss": 1.115, "step": 9102 }, { "epoch": 0.4976866564155134, "grad_norm": 2.157217502593994, "learning_rate": 5.281394042293243e-05, "loss": 1.1251, "step": 9103 }, { "epoch": 0.497741329232872, "grad_norm": 2.4039368629455566, "learning_rate": 5.280510086382112e-05, "loss": 1.2224, "step": 9104 }, { "epoch": 0.49779600205023067, "grad_norm": 2.7509799003601074, "learning_rate": 5.2796261216758355e-05, "loss": 1.0543, "step": 9105 }, { "epoch": 0.49785067486758927, "grad_norm": 2.9936749935150146, "learning_rate": 5.2787421482021296e-05, "loss": 1.0037, "step": 9106 }, { "epoch": 0.4979053476849479, "grad_norm": 2.683661937713623, "learning_rate": 5.277858165988708e-05, "loss": 1.0453, "step": 9107 }, { "epoch": 0.49796002050230653, "grad_norm": 2.674375057220459, "learning_rate": 5.2769741750632896e-05, "loss": 1.024, "step": 9108 }, { "epoch": 0.49801469331966514, "grad_norm": 2.571901559829712, "learning_rate": 5.276090175453589e-05, "loss": 0.9567, "step": 9109 }, { "epoch": 0.49806936613702374, "grad_norm": 1.9124329090118408, "learning_rate": 5.275206167187324e-05, "loss": 0.8554, "step": 9110 }, { "epoch": 0.49812403895438234, "grad_norm": 2.598048210144043, "learning_rate": 5.274322150292214e-05, "loss": 0.8397, "step": 9111 }, { "epoch": 0.498178711771741, "grad_norm": 2.8068783283233643, "learning_rate": 5.273438124795974e-05, "loss": 1.0259, "step": 9112 }, { "epoch": 0.4982333845890996, "grad_norm": 2.6359031200408936, "learning_rate": 5.272554090726323e-05, "loss": 1.1908, "step": 9113 }, { "epoch": 0.4982880574064582, "grad_norm": 2.3964462280273438, "learning_rate": 5.2716700481109784e-05, "loss": 0.8946, "step": 9114 }, { "epoch": 0.49834273022381687, "grad_norm": 2.3921639919281006, "learning_rate": 5.270785996977657e-05, "loss": 0.9874, "step": 9115 }, { "epoch": 0.49839740304117547, "grad_norm": 2.7778327465057373, "learning_rate": 5.2699019373540815e-05, "loss": 0.9715, "step": 9116 }, { "epoch": 0.49845207585853407, "grad_norm": 2.612825632095337, "learning_rate": 5.269017869267969e-05, "loss": 0.6844, "step": 9117 }, { "epoch": 0.49850674867589273, "grad_norm": 3.5769107341766357, "learning_rate": 5.2681337927470375e-05, "loss": 1.0732, "step": 9118 }, { "epoch": 0.49856142149325133, "grad_norm": 2.3915600776672363, "learning_rate": 5.267249707819008e-05, "loss": 1.0001, "step": 9119 }, { "epoch": 0.49861609431060994, "grad_norm": 2.346667528152466, "learning_rate": 5.266365614511598e-05, "loss": 0.9551, "step": 9120 }, { "epoch": 0.49867076712796854, "grad_norm": 2.2326748371124268, "learning_rate": 5.26548151285253e-05, "loss": 0.9207, "step": 9121 }, { "epoch": 0.4987254399453272, "grad_norm": 2.4535253047943115, "learning_rate": 5.264597402869523e-05, "loss": 0.9283, "step": 9122 }, { "epoch": 0.4987801127626858, "grad_norm": 2.309375286102295, "learning_rate": 5.263713284590299e-05, "loss": 0.9233, "step": 9123 }, { "epoch": 0.4988347855800444, "grad_norm": 2.578866481781006, "learning_rate": 5.262829158042577e-05, "loss": 0.8483, "step": 9124 }, { "epoch": 0.49888945839740306, "grad_norm": 2.1863040924072266, "learning_rate": 5.261945023254077e-05, "loss": 0.9538, "step": 9125 }, { "epoch": 0.49894413121476167, "grad_norm": 3.259605646133423, "learning_rate": 5.261060880252522e-05, "loss": 1.1204, "step": 9126 }, { "epoch": 0.49899880403212027, "grad_norm": 2.3286540508270264, "learning_rate": 5.2601767290656345e-05, "loss": 0.8319, "step": 9127 }, { "epoch": 0.49905347684947887, "grad_norm": 3.489224433898926, "learning_rate": 5.2592925697211336e-05, "loss": 1.2151, "step": 9128 }, { "epoch": 0.49910814966683753, "grad_norm": 3.004009962081909, "learning_rate": 5.258408402246744e-05, "loss": 0.8246, "step": 9129 }, { "epoch": 0.49916282248419613, "grad_norm": 2.393650770187378, "learning_rate": 5.2575242266701855e-05, "loss": 1.0761, "step": 9130 }, { "epoch": 0.49921749530155474, "grad_norm": 3.219508171081543, "learning_rate": 5.256640043019183e-05, "loss": 0.9766, "step": 9131 }, { "epoch": 0.4992721681189134, "grad_norm": 2.2942585945129395, "learning_rate": 5.255755851321458e-05, "loss": 0.7978, "step": 9132 }, { "epoch": 0.499326840936272, "grad_norm": 2.9688172340393066, "learning_rate": 5.254871651604733e-05, "loss": 1.2326, "step": 9133 }, { "epoch": 0.4993815137536306, "grad_norm": 2.3724005222320557, "learning_rate": 5.253987443896733e-05, "loss": 0.7822, "step": 9134 }, { "epoch": 0.49943618657098926, "grad_norm": 2.305957317352295, "learning_rate": 5.2531032282251805e-05, "loss": 0.9434, "step": 9135 }, { "epoch": 0.49949085938834786, "grad_norm": 2.517637014389038, "learning_rate": 5.252219004617799e-05, "loss": 0.9479, "step": 9136 }, { "epoch": 0.49954553220570647, "grad_norm": 2.7250707149505615, "learning_rate": 5.251334773102313e-05, "loss": 0.9305, "step": 9137 }, { "epoch": 0.49960020502306507, "grad_norm": 2.6899125576019287, "learning_rate": 5.250450533706447e-05, "loss": 1.0273, "step": 9138 }, { "epoch": 0.49965487784042373, "grad_norm": 2.8502635955810547, "learning_rate": 5.2495662864579244e-05, "loss": 0.9923, "step": 9139 }, { "epoch": 0.49970955065778233, "grad_norm": 2.821950912475586, "learning_rate": 5.248682031384472e-05, "loss": 1.1713, "step": 9140 }, { "epoch": 0.49976422347514093, "grad_norm": 2.17283034324646, "learning_rate": 5.2477977685138136e-05, "loss": 1.1698, "step": 9141 }, { "epoch": 0.4998188962924996, "grad_norm": 2.4520153999328613, "learning_rate": 5.246913497873675e-05, "loss": 0.8506, "step": 9142 }, { "epoch": 0.4998735691098582, "grad_norm": 2.7994067668914795, "learning_rate": 5.246029219491781e-05, "loss": 1.0469, "step": 9143 }, { "epoch": 0.4999282419272168, "grad_norm": 2.4701080322265625, "learning_rate": 5.245144933395856e-05, "loss": 1.0468, "step": 9144 }, { "epoch": 0.49998291474457546, "grad_norm": 3.2990407943725586, "learning_rate": 5.24426063961363e-05, "loss": 1.169, "step": 9145 }, { "epoch": 0.5000375875619341, "grad_norm": 2.0415704250335693, "learning_rate": 5.243376338172825e-05, "loss": 0.8843, "step": 9146 }, { "epoch": 0.5000922603792927, "grad_norm": 2.6079514026641846, "learning_rate": 5.2424920291011716e-05, "loss": 0.9613, "step": 9147 }, { "epoch": 0.5001469331966513, "grad_norm": 2.8013455867767334, "learning_rate": 5.2416077124263926e-05, "loss": 1.1645, "step": 9148 }, { "epoch": 0.5002016060140099, "grad_norm": 5.221279621124268, "learning_rate": 5.240723388176217e-05, "loss": 1.097, "step": 9149 }, { "epoch": 0.5002562788313686, "grad_norm": 2.959892511367798, "learning_rate": 5.239839056378373e-05, "loss": 1.123, "step": 9150 }, { "epoch": 0.5003109516487272, "grad_norm": 2.1569788455963135, "learning_rate": 5.2389547170605865e-05, "loss": 1.0542, "step": 9151 }, { "epoch": 0.5003656244660858, "grad_norm": 2.9317963123321533, "learning_rate": 5.238070370250585e-05, "loss": 0.9254, "step": 9152 }, { "epoch": 0.5004202972834444, "grad_norm": 2.6727888584136963, "learning_rate": 5.2371860159760974e-05, "loss": 1.0559, "step": 9153 }, { "epoch": 0.500474970100803, "grad_norm": 2.207549810409546, "learning_rate": 5.2363016542648504e-05, "loss": 0.9671, "step": 9154 }, { "epoch": 0.5005296429181616, "grad_norm": 2.7962841987609863, "learning_rate": 5.235417285144575e-05, "loss": 1.1243, "step": 9155 }, { "epoch": 0.5005843157355202, "grad_norm": 2.2828688621520996, "learning_rate": 5.2345329086429976e-05, "loss": 0.9667, "step": 9156 }, { "epoch": 0.5006389885528789, "grad_norm": 2.8625125885009766, "learning_rate": 5.233648524787846e-05, "loss": 1.253, "step": 9157 }, { "epoch": 0.5006936613702375, "grad_norm": 2.4022278785705566, "learning_rate": 5.232764133606853e-05, "loss": 1.005, "step": 9158 }, { "epoch": 0.5007483341875961, "grad_norm": 2.5656306743621826, "learning_rate": 5.2318797351277434e-05, "loss": 1.1023, "step": 9159 }, { "epoch": 0.5008030070049547, "grad_norm": 2.4899208545684814, "learning_rate": 5.230995329378251e-05, "loss": 0.9227, "step": 9160 }, { "epoch": 0.5008576798223133, "grad_norm": 3.354396104812622, "learning_rate": 5.230110916386104e-05, "loss": 1.1612, "step": 9161 }, { "epoch": 0.5009123526396719, "grad_norm": 2.3633453845977783, "learning_rate": 5.2292264961790315e-05, "loss": 1.0022, "step": 9162 }, { "epoch": 0.5009670254570305, "grad_norm": 2.4919278621673584, "learning_rate": 5.228342068784764e-05, "loss": 1.0852, "step": 9163 }, { "epoch": 0.5010216982743892, "grad_norm": 3.0119893550872803, "learning_rate": 5.227457634231031e-05, "loss": 1.1096, "step": 9164 }, { "epoch": 0.5010763710917479, "grad_norm": 3.2569587230682373, "learning_rate": 5.2265731925455664e-05, "loss": 1.2458, "step": 9165 }, { "epoch": 0.5011310439091065, "grad_norm": 2.489163875579834, "learning_rate": 5.225688743756099e-05, "loss": 1.0298, "step": 9166 }, { "epoch": 0.5011857167264651, "grad_norm": 2.822164535522461, "learning_rate": 5.224804287890359e-05, "loss": 1.0519, "step": 9167 }, { "epoch": 0.5012403895438237, "grad_norm": 2.8772265911102295, "learning_rate": 5.2239198249760804e-05, "loss": 0.9008, "step": 9168 }, { "epoch": 0.5012950623611823, "grad_norm": 2.9989001750946045, "learning_rate": 5.22303535504099e-05, "loss": 1.1894, "step": 9169 }, { "epoch": 0.5013497351785409, "grad_norm": 2.781906843185425, "learning_rate": 5.222150878112825e-05, "loss": 1.0899, "step": 9170 }, { "epoch": 0.5014044079958996, "grad_norm": 2.608522415161133, "learning_rate": 5.221266394219315e-05, "loss": 0.8183, "step": 9171 }, { "epoch": 0.5014590808132582, "grad_norm": 2.7915616035461426, "learning_rate": 5.2203819033881916e-05, "loss": 0.9809, "step": 9172 }, { "epoch": 0.5015137536306168, "grad_norm": 2.2577407360076904, "learning_rate": 5.219497405647189e-05, "loss": 0.9561, "step": 9173 }, { "epoch": 0.5015684264479754, "grad_norm": 2.0779082775115967, "learning_rate": 5.218612901024037e-05, "loss": 0.9251, "step": 9174 }, { "epoch": 0.501623099265334, "grad_norm": 3.1910202503204346, "learning_rate": 5.217728389546471e-05, "loss": 1.2169, "step": 9175 }, { "epoch": 0.5016777720826926, "grad_norm": 2.492957353591919, "learning_rate": 5.216843871242224e-05, "loss": 1.2017, "step": 9176 }, { "epoch": 0.5017324449000513, "grad_norm": 2.255390167236328, "learning_rate": 5.215959346139028e-05, "loss": 1.0093, "step": 9177 }, { "epoch": 0.5017871177174099, "grad_norm": 2.3651487827301025, "learning_rate": 5.2150748142646176e-05, "loss": 1.0603, "step": 9178 }, { "epoch": 0.5018417905347685, "grad_norm": 2.5484402179718018, "learning_rate": 5.2141902756467244e-05, "loss": 0.8995, "step": 9179 }, { "epoch": 0.5018964633521271, "grad_norm": 2.9173970222473145, "learning_rate": 5.213305730313085e-05, "loss": 1.0963, "step": 9180 }, { "epoch": 0.5019511361694857, "grad_norm": 2.361344575881958, "learning_rate": 5.212421178291434e-05, "loss": 0.8495, "step": 9181 }, { "epoch": 0.5020058089868443, "grad_norm": 2.520787000656128, "learning_rate": 5.211536619609502e-05, "loss": 1.0714, "step": 9182 }, { "epoch": 0.5020604818042029, "grad_norm": 2.966918468475342, "learning_rate": 5.210652054295027e-05, "loss": 0.995, "step": 9183 }, { "epoch": 0.5021151546215616, "grad_norm": 2.7730202674865723, "learning_rate": 5.2097674823757413e-05, "loss": 0.7885, "step": 9184 }, { "epoch": 0.5021698274389202, "grad_norm": 3.0569698810577393, "learning_rate": 5.208882903879382e-05, "loss": 1.0505, "step": 9185 }, { "epoch": 0.5022245002562788, "grad_norm": 3.649807929992676, "learning_rate": 5.207998318833682e-05, "loss": 1.2725, "step": 9186 }, { "epoch": 0.5022791730736375, "grad_norm": 2.466765880584717, "learning_rate": 5.207113727266381e-05, "loss": 0.9908, "step": 9187 }, { "epoch": 0.5023338458909961, "grad_norm": 2.6242892742156982, "learning_rate": 5.206229129205209e-05, "loss": 1.1906, "step": 9188 }, { "epoch": 0.5023885187083547, "grad_norm": 2.7238242626190186, "learning_rate": 5.2053445246779067e-05, "loss": 1.2067, "step": 9189 }, { "epoch": 0.5024431915257133, "grad_norm": 2.6473183631896973, "learning_rate": 5.204459913712206e-05, "loss": 1.0529, "step": 9190 }, { "epoch": 0.502497864343072, "grad_norm": 2.5769054889678955, "learning_rate": 5.203575296335845e-05, "loss": 0.9675, "step": 9191 }, { "epoch": 0.5025525371604306, "grad_norm": 3.2236533164978027, "learning_rate": 5.202690672576561e-05, "loss": 1.2348, "step": 9192 }, { "epoch": 0.5026072099777892, "grad_norm": 2.433925151824951, "learning_rate": 5.2018060424620896e-05, "loss": 1.0741, "step": 9193 }, { "epoch": 0.5026618827951478, "grad_norm": 2.3465492725372314, "learning_rate": 5.200921406020167e-05, "loss": 0.9992, "step": 9194 }, { "epoch": 0.5027165556125064, "grad_norm": 2.1136715412139893, "learning_rate": 5.2000367632785315e-05, "loss": 0.8985, "step": 9195 }, { "epoch": 0.502771228429865, "grad_norm": 1.96901535987854, "learning_rate": 5.1991521142649194e-05, "loss": 0.8256, "step": 9196 }, { "epoch": 0.5028259012472236, "grad_norm": 3.307103395462036, "learning_rate": 5.198267459007068e-05, "loss": 1.2609, "step": 9197 }, { "epoch": 0.5028805740645823, "grad_norm": 2.947913408279419, "learning_rate": 5.197382797532715e-05, "loss": 1.0441, "step": 9198 }, { "epoch": 0.5029352468819409, "grad_norm": 1.949992299079895, "learning_rate": 5.1964981298695994e-05, "loss": 0.8671, "step": 9199 }, { "epoch": 0.5029899196992995, "grad_norm": 2.601372718811035, "learning_rate": 5.195613456045457e-05, "loss": 1.1813, "step": 9200 }, { "epoch": 0.5030445925166581, "grad_norm": 2.7407710552215576, "learning_rate": 5.194728776088028e-05, "loss": 1.2215, "step": 9201 }, { "epoch": 0.5030992653340167, "grad_norm": 2.5374350547790527, "learning_rate": 5.1938440900250496e-05, "loss": 1.1587, "step": 9202 }, { "epoch": 0.5031539381513753, "grad_norm": 2.8290019035339355, "learning_rate": 5.1929593978842596e-05, "loss": 1.0447, "step": 9203 }, { "epoch": 0.503208610968734, "grad_norm": 2.0493054389953613, "learning_rate": 5.1920746996933986e-05, "loss": 0.8478, "step": 9204 }, { "epoch": 0.5032632837860926, "grad_norm": 1.9820046424865723, "learning_rate": 5.191189995480206e-05, "loss": 0.9803, "step": 9205 }, { "epoch": 0.5033179566034512, "grad_norm": 3.150169610977173, "learning_rate": 5.1903052852724185e-05, "loss": 1.0467, "step": 9206 }, { "epoch": 0.5033726294208098, "grad_norm": 2.3506782054901123, "learning_rate": 5.189420569097777e-05, "loss": 0.9121, "step": 9207 }, { "epoch": 0.5034273022381685, "grad_norm": 3.8324053287506104, "learning_rate": 5.188535846984019e-05, "loss": 1.0694, "step": 9208 }, { "epoch": 0.503481975055527, "grad_norm": 2.6256370544433594, "learning_rate": 5.187651118958887e-05, "loss": 0.9829, "step": 9209 }, { "epoch": 0.5035366478728857, "grad_norm": 2.026811122894287, "learning_rate": 5.1867663850501205e-05, "loss": 0.8033, "step": 9210 }, { "epoch": 0.5035913206902444, "grad_norm": 2.1719326972961426, "learning_rate": 5.1858816452854574e-05, "loss": 1.0378, "step": 9211 }, { "epoch": 0.503645993507603, "grad_norm": 2.5475845336914062, "learning_rate": 5.184996899692639e-05, "loss": 1.0903, "step": 9212 }, { "epoch": 0.5037006663249616, "grad_norm": 2.6060409545898438, "learning_rate": 5.184112148299406e-05, "loss": 1.0142, "step": 9213 }, { "epoch": 0.5037553391423202, "grad_norm": 2.3037455081939697, "learning_rate": 5.1832273911334994e-05, "loss": 1.1335, "step": 9214 }, { "epoch": 0.5038100119596788, "grad_norm": 2.7082982063293457, "learning_rate": 5.1823426282226594e-05, "loss": 0.9739, "step": 9215 }, { "epoch": 0.5038646847770374, "grad_norm": 2.7706520557403564, "learning_rate": 5.181457859594627e-05, "loss": 1.0915, "step": 9216 }, { "epoch": 0.503919357594396, "grad_norm": 2.1628429889678955, "learning_rate": 5.180573085277144e-05, "loss": 0.9615, "step": 9217 }, { "epoch": 0.5039740304117547, "grad_norm": 2.490555763244629, "learning_rate": 5.17968830529795e-05, "loss": 0.9802, "step": 9218 }, { "epoch": 0.5040287032291133, "grad_norm": 2.3498892784118652, "learning_rate": 5.178803519684787e-05, "loss": 1.0045, "step": 9219 }, { "epoch": 0.5040833760464719, "grad_norm": 2.781214952468872, "learning_rate": 5.1779187284653985e-05, "loss": 1.0789, "step": 9220 }, { "epoch": 0.5041380488638305, "grad_norm": 2.118727922439575, "learning_rate": 5.1770339316675256e-05, "loss": 0.9397, "step": 9221 }, { "epoch": 0.5041927216811891, "grad_norm": 3.316206216812134, "learning_rate": 5.176149129318909e-05, "loss": 0.9921, "step": 9222 }, { "epoch": 0.5042473944985477, "grad_norm": 2.477076530456543, "learning_rate": 5.1752643214472904e-05, "loss": 1.0231, "step": 9223 }, { "epoch": 0.5043020673159063, "grad_norm": 3.498319149017334, "learning_rate": 5.1743795080804155e-05, "loss": 1.2108, "step": 9224 }, { "epoch": 0.504356740133265, "grad_norm": 2.1860873699188232, "learning_rate": 5.173494689246024e-05, "loss": 0.9103, "step": 9225 }, { "epoch": 0.5044114129506236, "grad_norm": 2.404517650604248, "learning_rate": 5.17260986497186e-05, "loss": 1.0534, "step": 9226 }, { "epoch": 0.5044660857679822, "grad_norm": 2.64787220954895, "learning_rate": 5.1717250352856664e-05, "loss": 1.0356, "step": 9227 }, { "epoch": 0.5045207585853408, "grad_norm": 3.3056323528289795, "learning_rate": 5.1708402002151836e-05, "loss": 1.1237, "step": 9228 }, { "epoch": 0.5045754314026994, "grad_norm": 2.4093456268310547, "learning_rate": 5.169955359788159e-05, "loss": 1.078, "step": 9229 }, { "epoch": 0.504630104220058, "grad_norm": 2.6558127403259277, "learning_rate": 5.169070514032334e-05, "loss": 1.0322, "step": 9230 }, { "epoch": 0.5046847770374167, "grad_norm": 2.376100778579712, "learning_rate": 5.168185662975451e-05, "loss": 1.0941, "step": 9231 }, { "epoch": 0.5047394498547754, "grad_norm": 2.0593903064727783, "learning_rate": 5.167300806645255e-05, "loss": 1.0126, "step": 9232 }, { "epoch": 0.504794122672134, "grad_norm": 1.9931668043136597, "learning_rate": 5.166415945069488e-05, "loss": 0.9704, "step": 9233 }, { "epoch": 0.5048487954894926, "grad_norm": 2.0369937419891357, "learning_rate": 5.165531078275898e-05, "loss": 1.0921, "step": 9234 }, { "epoch": 0.5049034683068512, "grad_norm": 2.955349922180176, "learning_rate": 5.164646206292227e-05, "loss": 0.9606, "step": 9235 }, { "epoch": 0.5049581411242098, "grad_norm": 2.205962657928467, "learning_rate": 5.163761329146219e-05, "loss": 0.8141, "step": 9236 }, { "epoch": 0.5050128139415684, "grad_norm": 2.2035210132598877, "learning_rate": 5.1628764468656185e-05, "loss": 0.9578, "step": 9237 }, { "epoch": 0.5050674867589271, "grad_norm": 2.5798704624176025, "learning_rate": 5.161991559478171e-05, "loss": 0.8729, "step": 9238 }, { "epoch": 0.5051221595762857, "grad_norm": 2.869593858718872, "learning_rate": 5.16110666701162e-05, "loss": 1.0322, "step": 9239 }, { "epoch": 0.5051768323936443, "grad_norm": 2.6599249839782715, "learning_rate": 5.160221769493713e-05, "loss": 0.8925, "step": 9240 }, { "epoch": 0.5052315052110029, "grad_norm": 2.585294723510742, "learning_rate": 5.159336866952194e-05, "loss": 0.9297, "step": 9241 }, { "epoch": 0.5052861780283615, "grad_norm": 2.2686846256256104, "learning_rate": 5.158451959414805e-05, "loss": 1.0759, "step": 9242 }, { "epoch": 0.5053408508457201, "grad_norm": 2.579606533050537, "learning_rate": 5.1575670469092965e-05, "loss": 1.0294, "step": 9243 }, { "epoch": 0.5053955236630787, "grad_norm": 4.462007522583008, "learning_rate": 5.156682129463413e-05, "loss": 1.1984, "step": 9244 }, { "epoch": 0.5054501964804374, "grad_norm": 3.2690463066101074, "learning_rate": 5.1557972071048975e-05, "loss": 0.9569, "step": 9245 }, { "epoch": 0.505504869297796, "grad_norm": 2.556533098220825, "learning_rate": 5.1549122798615003e-05, "loss": 1.0751, "step": 9246 }, { "epoch": 0.5055595421151546, "grad_norm": 2.771909475326538, "learning_rate": 5.154027347760962e-05, "loss": 1.1807, "step": 9247 }, { "epoch": 0.5056142149325132, "grad_norm": 2.8495070934295654, "learning_rate": 5.1531424108310345e-05, "loss": 0.9862, "step": 9248 }, { "epoch": 0.5056688877498718, "grad_norm": 2.017375946044922, "learning_rate": 5.152257469099461e-05, "loss": 1.0617, "step": 9249 }, { "epoch": 0.5057235605672304, "grad_norm": 2.2820651531219482, "learning_rate": 5.151372522593989e-05, "loss": 0.9489, "step": 9250 }, { "epoch": 0.505778233384589, "grad_norm": 4.865434169769287, "learning_rate": 5.150487571342365e-05, "loss": 1.2345, "step": 9251 }, { "epoch": 0.5058329062019478, "grad_norm": 2.8217411041259766, "learning_rate": 5.149602615372334e-05, "loss": 1.0913, "step": 9252 }, { "epoch": 0.5058875790193064, "grad_norm": 3.3876616954803467, "learning_rate": 5.1487176547116475e-05, "loss": 0.7616, "step": 9253 }, { "epoch": 0.505942251836665, "grad_norm": 2.806852102279663, "learning_rate": 5.147832689388049e-05, "loss": 1.0961, "step": 9254 }, { "epoch": 0.5059969246540236, "grad_norm": 2.551486015319824, "learning_rate": 5.146947719429287e-05, "loss": 1.198, "step": 9255 }, { "epoch": 0.5060515974713822, "grad_norm": 2.2635509967803955, "learning_rate": 5.1460627448631096e-05, "loss": 0.7757, "step": 9256 }, { "epoch": 0.5061062702887408, "grad_norm": 2.597794771194458, "learning_rate": 5.145177765717262e-05, "loss": 0.9502, "step": 9257 }, { "epoch": 0.5061609431060994, "grad_norm": 2.2944631576538086, "learning_rate": 5.144292782019494e-05, "loss": 1.0199, "step": 9258 }, { "epoch": 0.5062156159234581, "grad_norm": 2.3944342136383057, "learning_rate": 5.1434077937975534e-05, "loss": 1.1241, "step": 9259 }, { "epoch": 0.5062702887408167, "grad_norm": 2.512648582458496, "learning_rate": 5.1425228010791884e-05, "loss": 1.1637, "step": 9260 }, { "epoch": 0.5063249615581753, "grad_norm": 2.4268980026245117, "learning_rate": 5.141637803892145e-05, "loss": 1.0882, "step": 9261 }, { "epoch": 0.5063796343755339, "grad_norm": 2.270355224609375, "learning_rate": 5.1407528022641735e-05, "loss": 0.9179, "step": 9262 }, { "epoch": 0.5064343071928925, "grad_norm": 2.866748809814453, "learning_rate": 5.1398677962230224e-05, "loss": 1.0428, "step": 9263 }, { "epoch": 0.5064889800102511, "grad_norm": 3.328669786453247, "learning_rate": 5.13898278579644e-05, "loss": 1.2229, "step": 9264 }, { "epoch": 0.5065436528276098, "grad_norm": 2.9096240997314453, "learning_rate": 5.138097771012176e-05, "loss": 1.1758, "step": 9265 }, { "epoch": 0.5065983256449684, "grad_norm": 3.7058587074279785, "learning_rate": 5.137212751897977e-05, "loss": 1.1118, "step": 9266 }, { "epoch": 0.506652998462327, "grad_norm": 2.4245359897613525, "learning_rate": 5.136327728481593e-05, "loss": 1.0349, "step": 9267 }, { "epoch": 0.5067076712796856, "grad_norm": 2.807100772857666, "learning_rate": 5.135442700790772e-05, "loss": 1.0395, "step": 9268 }, { "epoch": 0.5067623440970442, "grad_norm": 3.3872199058532715, "learning_rate": 5.134557668853267e-05, "loss": 1.171, "step": 9269 }, { "epoch": 0.5068170169144028, "grad_norm": 1.770879864692688, "learning_rate": 5.133672632696823e-05, "loss": 0.7916, "step": 9270 }, { "epoch": 0.5068716897317614, "grad_norm": 2.3711698055267334, "learning_rate": 5.132787592349193e-05, "loss": 1.0601, "step": 9271 }, { "epoch": 0.5069263625491202, "grad_norm": 3.5858757495880127, "learning_rate": 5.131902547838123e-05, "loss": 1.1904, "step": 9272 }, { "epoch": 0.5069810353664788, "grad_norm": 2.3308348655700684, "learning_rate": 5.1310174991913675e-05, "loss": 1.0326, "step": 9273 }, { "epoch": 0.5070357081838374, "grad_norm": 2.610224485397339, "learning_rate": 5.130132446436672e-05, "loss": 1.2269, "step": 9274 }, { "epoch": 0.507090381001196, "grad_norm": 2.773394823074341, "learning_rate": 5.129247389601789e-05, "loss": 1.0101, "step": 9275 }, { "epoch": 0.5071450538185546, "grad_norm": 2.2161240577697754, "learning_rate": 5.128362328714469e-05, "loss": 0.8737, "step": 9276 }, { "epoch": 0.5071997266359132, "grad_norm": 2.3662683963775635, "learning_rate": 5.12747726380246e-05, "loss": 1.1212, "step": 9277 }, { "epoch": 0.5072543994532718, "grad_norm": 2.3311986923217773, "learning_rate": 5.1265921948935135e-05, "loss": 1.0467, "step": 9278 }, { "epoch": 0.5073090722706305, "grad_norm": 2.469175100326538, "learning_rate": 5.1257071220153805e-05, "loss": 0.8553, "step": 9279 }, { "epoch": 0.5073637450879891, "grad_norm": 2.254748582839966, "learning_rate": 5.124822045195813e-05, "loss": 1.0284, "step": 9280 }, { "epoch": 0.5074184179053477, "grad_norm": 3.7056164741516113, "learning_rate": 5.123936964462559e-05, "loss": 1.1525, "step": 9281 }, { "epoch": 0.5074730907227063, "grad_norm": 2.4576327800750732, "learning_rate": 5.123051879843371e-05, "loss": 1.1333, "step": 9282 }, { "epoch": 0.5075277635400649, "grad_norm": 2.8264200687408447, "learning_rate": 5.122166791366e-05, "loss": 1.1157, "step": 9283 }, { "epoch": 0.5075824363574235, "grad_norm": 2.1330740451812744, "learning_rate": 5.121281699058197e-05, "loss": 0.9868, "step": 9284 }, { "epoch": 0.5076371091747821, "grad_norm": 2.594386100769043, "learning_rate": 5.1203966029477126e-05, "loss": 1.0776, "step": 9285 }, { "epoch": 0.5076917819921408, "grad_norm": 2.25480318069458, "learning_rate": 5.119511503062299e-05, "loss": 0.9524, "step": 9286 }, { "epoch": 0.5077464548094994, "grad_norm": 3.059096097946167, "learning_rate": 5.118626399429708e-05, "loss": 1.0967, "step": 9287 }, { "epoch": 0.507801127626858, "grad_norm": 2.360778331756592, "learning_rate": 5.1177412920776905e-05, "loss": 1.0104, "step": 9288 }, { "epoch": 0.5078558004442166, "grad_norm": 3.7832014560699463, "learning_rate": 5.1168561810339985e-05, "loss": 0.9399, "step": 9289 }, { "epoch": 0.5079104732615752, "grad_norm": 2.860525131225586, "learning_rate": 5.115971066326385e-05, "loss": 1.09, "step": 9290 }, { "epoch": 0.5079651460789338, "grad_norm": 2.6277883052825928, "learning_rate": 5.1150859479825984e-05, "loss": 0.8593, "step": 9291 }, { "epoch": 0.5080198188962926, "grad_norm": 2.3761844635009766, "learning_rate": 5.114200826030395e-05, "loss": 1.0462, "step": 9292 }, { "epoch": 0.5080744917136512, "grad_norm": 2.9001433849334717, "learning_rate": 5.1133157004975264e-05, "loss": 1.089, "step": 9293 }, { "epoch": 0.5081291645310098, "grad_norm": 2.5414552688598633, "learning_rate": 5.1124305714117426e-05, "loss": 0.9833, "step": 9294 }, { "epoch": 0.5081838373483684, "grad_norm": 2.5451931953430176, "learning_rate": 5.111545438800799e-05, "loss": 1.0981, "step": 9295 }, { "epoch": 0.508238510165727, "grad_norm": 3.594196081161499, "learning_rate": 5.110660302692444e-05, "loss": 1.1624, "step": 9296 }, { "epoch": 0.5082931829830856, "grad_norm": 2.2274136543273926, "learning_rate": 5.1097751631144344e-05, "loss": 1.0396, "step": 9297 }, { "epoch": 0.5083478558004442, "grad_norm": 2.2288618087768555, "learning_rate": 5.10889002009452e-05, "loss": 0.9875, "step": 9298 }, { "epoch": 0.5084025286178029, "grad_norm": 2.2214043140411377, "learning_rate": 5.108004873660457e-05, "loss": 1.0012, "step": 9299 }, { "epoch": 0.5084572014351615, "grad_norm": 3.2010927200317383, "learning_rate": 5.107119723839995e-05, "loss": 0.9884, "step": 9300 }, { "epoch": 0.5085118742525201, "grad_norm": 2.5256145000457764, "learning_rate": 5.106234570660888e-05, "loss": 1.0138, "step": 9301 }, { "epoch": 0.5085665470698787, "grad_norm": 2.209670305252075, "learning_rate": 5.105349414150891e-05, "loss": 0.9769, "step": 9302 }, { "epoch": 0.5086212198872373, "grad_norm": 2.660433292388916, "learning_rate": 5.1044642543377555e-05, "loss": 1.2037, "step": 9303 }, { "epoch": 0.5086758927045959, "grad_norm": 2.2206485271453857, "learning_rate": 5.1035790912492354e-05, "loss": 0.7738, "step": 9304 }, { "epoch": 0.5087305655219545, "grad_norm": 2.262700319290161, "learning_rate": 5.1026939249130846e-05, "loss": 1.0077, "step": 9305 }, { "epoch": 0.5087852383393132, "grad_norm": 2.495983600616455, "learning_rate": 5.1018087553570546e-05, "loss": 0.9453, "step": 9306 }, { "epoch": 0.5088399111566718, "grad_norm": 3.397940158843994, "learning_rate": 5.1009235826089016e-05, "loss": 0.9271, "step": 9307 }, { "epoch": 0.5088945839740304, "grad_norm": 3.4098236560821533, "learning_rate": 5.10003840669638e-05, "loss": 1.0114, "step": 9308 }, { "epoch": 0.508949256791389, "grad_norm": 2.7021706104278564, "learning_rate": 5.0991532276472424e-05, "loss": 1.1353, "step": 9309 }, { "epoch": 0.5090039296087476, "grad_norm": 2.261645793914795, "learning_rate": 5.098268045489242e-05, "loss": 0.9618, "step": 9310 }, { "epoch": 0.5090586024261062, "grad_norm": 2.8186018466949463, "learning_rate": 5.097382860250132e-05, "loss": 1.0044, "step": 9311 }, { "epoch": 0.5091132752434648, "grad_norm": 3.710683822631836, "learning_rate": 5.096497671957669e-05, "loss": 1.0778, "step": 9312 }, { "epoch": 0.5091679480608235, "grad_norm": 2.5446503162384033, "learning_rate": 5.095612480639609e-05, "loss": 1.1713, "step": 9313 }, { "epoch": 0.5092226208781822, "grad_norm": 2.168875217437744, "learning_rate": 5.0947272863237015e-05, "loss": 1.0041, "step": 9314 }, { "epoch": 0.5092772936955408, "grad_norm": 2.288097620010376, "learning_rate": 5.093842089037705e-05, "loss": 0.9712, "step": 9315 }, { "epoch": 0.5093319665128994, "grad_norm": 2.4636569023132324, "learning_rate": 5.0929568888093717e-05, "loss": 0.9721, "step": 9316 }, { "epoch": 0.509386639330258, "grad_norm": 2.096709728240967, "learning_rate": 5.0920716856664565e-05, "loss": 1.0061, "step": 9317 }, { "epoch": 0.5094413121476166, "grad_norm": 6.454636573791504, "learning_rate": 5.091186479636716e-05, "loss": 1.0675, "step": 9318 }, { "epoch": 0.5094959849649753, "grad_norm": 2.5392045974731445, "learning_rate": 5.0903012707479034e-05, "loss": 0.8901, "step": 9319 }, { "epoch": 0.5095506577823339, "grad_norm": 3.057706594467163, "learning_rate": 5.089416059027774e-05, "loss": 1.1382, "step": 9320 }, { "epoch": 0.5096053305996925, "grad_norm": 2.8848941326141357, "learning_rate": 5.088530844504082e-05, "loss": 0.9118, "step": 9321 }, { "epoch": 0.5096600034170511, "grad_norm": 2.631098985671997, "learning_rate": 5.087645627204585e-05, "loss": 1.0275, "step": 9322 }, { "epoch": 0.5097146762344097, "grad_norm": 2.0819380283355713, "learning_rate": 5.086760407157035e-05, "loss": 0.8864, "step": 9323 }, { "epoch": 0.5097693490517683, "grad_norm": 2.7014002799987793, "learning_rate": 5.0858751843891906e-05, "loss": 0.8784, "step": 9324 }, { "epoch": 0.5098240218691269, "grad_norm": 3.575676202774048, "learning_rate": 5.084989958928805e-05, "loss": 0.829, "step": 9325 }, { "epoch": 0.5098786946864856, "grad_norm": 3.0285842418670654, "learning_rate": 5.084104730803633e-05, "loss": 1.303, "step": 9326 }, { "epoch": 0.5099333675038442, "grad_norm": 2.9735007286071777, "learning_rate": 5.083219500041432e-05, "loss": 1.0961, "step": 9327 }, { "epoch": 0.5099880403212028, "grad_norm": 2.232311248779297, "learning_rate": 5.082334266669957e-05, "loss": 1.1666, "step": 9328 }, { "epoch": 0.5100427131385614, "grad_norm": 2.336662530899048, "learning_rate": 5.0814490307169646e-05, "loss": 0.9986, "step": 9329 }, { "epoch": 0.51009738595592, "grad_norm": 2.405318260192871, "learning_rate": 5.080563792210209e-05, "loss": 0.9639, "step": 9330 }, { "epoch": 0.5101520587732786, "grad_norm": 2.562044143676758, "learning_rate": 5.079678551177446e-05, "loss": 1.148, "step": 9331 }, { "epoch": 0.5102067315906372, "grad_norm": 3.0752899646759033, "learning_rate": 5.078793307646432e-05, "loss": 1.1878, "step": 9332 }, { "epoch": 0.5102614044079959, "grad_norm": 3.248011589050293, "learning_rate": 5.077908061644925e-05, "loss": 0.9495, "step": 9333 }, { "epoch": 0.5103160772253545, "grad_norm": 2.1878433227539062, "learning_rate": 5.077022813200678e-05, "loss": 1.0126, "step": 9334 }, { "epoch": 0.5103707500427132, "grad_norm": 2.484487295150757, "learning_rate": 5.07613756234145e-05, "loss": 0.9176, "step": 9335 }, { "epoch": 0.5104254228600718, "grad_norm": 2.481933355331421, "learning_rate": 5.0752523090949934e-05, "loss": 0.7956, "step": 9336 }, { "epoch": 0.5104800956774304, "grad_norm": 2.81548810005188, "learning_rate": 5.0743670534890686e-05, "loss": 1.1559, "step": 9337 }, { "epoch": 0.510534768494789, "grad_norm": 2.4963667392730713, "learning_rate": 5.0734817955514314e-05, "loss": 1.0295, "step": 9338 }, { "epoch": 0.5105894413121476, "grad_norm": 3.267099142074585, "learning_rate": 5.072596535309836e-05, "loss": 1.0388, "step": 9339 }, { "epoch": 0.5106441141295063, "grad_norm": 3.1418111324310303, "learning_rate": 5.0717112727920405e-05, "loss": 1.0585, "step": 9340 }, { "epoch": 0.5106987869468649, "grad_norm": 2.373615264892578, "learning_rate": 5.0708260080258006e-05, "loss": 0.8128, "step": 9341 }, { "epoch": 0.5107534597642235, "grad_norm": 3.424349546432495, "learning_rate": 5.069940741038875e-05, "loss": 1.137, "step": 9342 }, { "epoch": 0.5108081325815821, "grad_norm": 2.382664918899536, "learning_rate": 5.069055471859018e-05, "loss": 1.1175, "step": 9343 }, { "epoch": 0.5108628053989407, "grad_norm": 2.1221799850463867, "learning_rate": 5.0681702005139876e-05, "loss": 0.9985, "step": 9344 }, { "epoch": 0.5109174782162993, "grad_norm": 2.0776219367980957, "learning_rate": 5.06728492703154e-05, "loss": 0.8681, "step": 9345 }, { "epoch": 0.510972151033658, "grad_norm": 2.712411403656006, "learning_rate": 5.066399651439434e-05, "loss": 0.9835, "step": 9346 }, { "epoch": 0.5110268238510166, "grad_norm": 2.388138771057129, "learning_rate": 5.0655143737654254e-05, "loss": 1.1625, "step": 9347 }, { "epoch": 0.5110814966683752, "grad_norm": 2.6609323024749756, "learning_rate": 5.064629094037272e-05, "loss": 1.2778, "step": 9348 }, { "epoch": 0.5111361694857338, "grad_norm": 2.6765220165252686, "learning_rate": 5.0637438122827294e-05, "loss": 0.9691, "step": 9349 }, { "epoch": 0.5111908423030924, "grad_norm": 2.3964760303497314, "learning_rate": 5.062858528529555e-05, "loss": 1.1023, "step": 9350 }, { "epoch": 0.511245515120451, "grad_norm": 2.860358715057373, "learning_rate": 5.061973242805508e-05, "loss": 1.0029, "step": 9351 }, { "epoch": 0.5113001879378096, "grad_norm": 2.6053624153137207, "learning_rate": 5.061087955138345e-05, "loss": 1.1142, "step": 9352 }, { "epoch": 0.5113548607551683, "grad_norm": 2.148047685623169, "learning_rate": 5.060202665555822e-05, "loss": 0.9387, "step": 9353 }, { "epoch": 0.5114095335725269, "grad_norm": 2.3672373294830322, "learning_rate": 5.059317374085699e-05, "loss": 1.0658, "step": 9354 }, { "epoch": 0.5114642063898855, "grad_norm": 2.6008458137512207, "learning_rate": 5.058432080755729e-05, "loss": 0.6726, "step": 9355 }, { "epoch": 0.5115188792072441, "grad_norm": 2.171250581741333, "learning_rate": 5.0575467855936755e-05, "loss": 0.8998, "step": 9356 }, { "epoch": 0.5115735520246028, "grad_norm": 2.6216189861297607, "learning_rate": 5.0566614886272924e-05, "loss": 1.1188, "step": 9357 }, { "epoch": 0.5116282248419614, "grad_norm": 3.1984643936157227, "learning_rate": 5.0557761898843383e-05, "loss": 1.2775, "step": 9358 }, { "epoch": 0.51168289765932, "grad_norm": 2.8595423698425293, "learning_rate": 5.0548908893925716e-05, "loss": 0.8781, "step": 9359 }, { "epoch": 0.5117375704766787, "grad_norm": 2.4667513370513916, "learning_rate": 5.054005587179748e-05, "loss": 1.0125, "step": 9360 }, { "epoch": 0.5117922432940373, "grad_norm": 2.7196707725524902, "learning_rate": 5.053120283273627e-05, "loss": 1.1252, "step": 9361 }, { "epoch": 0.5118469161113959, "grad_norm": 2.424628734588623, "learning_rate": 5.0522349777019674e-05, "loss": 1.0714, "step": 9362 }, { "epoch": 0.5119015889287545, "grad_norm": 2.6990933418273926, "learning_rate": 5.051349670492525e-05, "loss": 1.1345, "step": 9363 }, { "epoch": 0.5119562617461131, "grad_norm": 2.353626251220703, "learning_rate": 5.0504643616730606e-05, "loss": 0.8956, "step": 9364 }, { "epoch": 0.5120109345634717, "grad_norm": 2.0010972023010254, "learning_rate": 5.049579051271328e-05, "loss": 0.9293, "step": 9365 }, { "epoch": 0.5120656073808303, "grad_norm": 3.791835308074951, "learning_rate": 5.04869373931509e-05, "loss": 1.0299, "step": 9366 }, { "epoch": 0.512120280198189, "grad_norm": 2.6238291263580322, "learning_rate": 5.0478084258321024e-05, "loss": 1.1397, "step": 9367 }, { "epoch": 0.5121749530155476, "grad_norm": 2.9058403968811035, "learning_rate": 5.0469231108501234e-05, "loss": 1.0088, "step": 9368 }, { "epoch": 0.5122296258329062, "grad_norm": 2.7213425636291504, "learning_rate": 5.0460377943969125e-05, "loss": 0.9478, "step": 9369 }, { "epoch": 0.5122842986502648, "grad_norm": 2.3222193717956543, "learning_rate": 5.045152476500227e-05, "loss": 0.929, "step": 9370 }, { "epoch": 0.5123389714676234, "grad_norm": 3.3571932315826416, "learning_rate": 5.044267157187824e-05, "loss": 1.1409, "step": 9371 }, { "epoch": 0.512393644284982, "grad_norm": 2.5055222511291504, "learning_rate": 5.043381836487464e-05, "loss": 1.072, "step": 9372 }, { "epoch": 0.5124483171023407, "grad_norm": 2.1413865089416504, "learning_rate": 5.0424965144269054e-05, "loss": 1.0484, "step": 9373 }, { "epoch": 0.5125029899196993, "grad_norm": 3.287078619003296, "learning_rate": 5.041611191033906e-05, "loss": 0.9556, "step": 9374 }, { "epoch": 0.5125576627370579, "grad_norm": 3.0853028297424316, "learning_rate": 5.040725866336225e-05, "loss": 0.9846, "step": 9375 }, { "epoch": 0.5126123355544165, "grad_norm": 6.804008483886719, "learning_rate": 5.039840540361619e-05, "loss": 0.8784, "step": 9376 }, { "epoch": 0.5126670083717751, "grad_norm": 2.5058555603027344, "learning_rate": 5.038955213137848e-05, "loss": 0.9332, "step": 9377 }, { "epoch": 0.5127216811891337, "grad_norm": 1.8348954916000366, "learning_rate": 5.03806988469267e-05, "loss": 0.8897, "step": 9378 }, { "epoch": 0.5127763540064924, "grad_norm": 2.6286680698394775, "learning_rate": 5.037184555053846e-05, "loss": 1.0709, "step": 9379 }, { "epoch": 0.5128310268238511, "grad_norm": 2.16806960105896, "learning_rate": 5.0362992242491327e-05, "loss": 0.82, "step": 9380 }, { "epoch": 0.5128856996412097, "grad_norm": 2.3826472759246826, "learning_rate": 5.0354138923062886e-05, "loss": 0.9983, "step": 9381 }, { "epoch": 0.5129403724585683, "grad_norm": 2.699069023132324, "learning_rate": 5.034528559253073e-05, "loss": 1.2419, "step": 9382 }, { "epoch": 0.5129950452759269, "grad_norm": 2.64884352684021, "learning_rate": 5.033643225117246e-05, "loss": 0.9814, "step": 9383 }, { "epoch": 0.5130497180932855, "grad_norm": 2.4538612365722656, "learning_rate": 5.032757889926565e-05, "loss": 1.1003, "step": 9384 }, { "epoch": 0.5131043909106441, "grad_norm": 2.2726047039031982, "learning_rate": 5.0318725537087876e-05, "loss": 1.056, "step": 9385 }, { "epoch": 0.5131590637280027, "grad_norm": 2.479680299758911, "learning_rate": 5.030987216491676e-05, "loss": 0.8967, "step": 9386 }, { "epoch": 0.5132137365453614, "grad_norm": 2.2864701747894287, "learning_rate": 5.030101878302987e-05, "loss": 0.9319, "step": 9387 }, { "epoch": 0.51326840936272, "grad_norm": 2.476497173309326, "learning_rate": 5.0292165391704807e-05, "loss": 1.0749, "step": 9388 }, { "epoch": 0.5133230821800786, "grad_norm": 2.3129138946533203, "learning_rate": 5.028331199121915e-05, "loss": 0.9766, "step": 9389 }, { "epoch": 0.5133777549974372, "grad_norm": 4.471121311187744, "learning_rate": 5.027445858185049e-05, "loss": 1.0562, "step": 9390 }, { "epoch": 0.5134324278147958, "grad_norm": 2.528262138366699, "learning_rate": 5.026560516387644e-05, "loss": 1.0527, "step": 9391 }, { "epoch": 0.5134871006321544, "grad_norm": 2.0440151691436768, "learning_rate": 5.025675173757456e-05, "loss": 0.8885, "step": 9392 }, { "epoch": 0.513541773449513, "grad_norm": 1.9672008752822876, "learning_rate": 5.0247898303222466e-05, "loss": 0.9903, "step": 9393 }, { "epoch": 0.5135964462668717, "grad_norm": 2.9134981632232666, "learning_rate": 5.023904486109773e-05, "loss": 1.0358, "step": 9394 }, { "epoch": 0.5136511190842303, "grad_norm": 2.323634624481201, "learning_rate": 5.023019141147795e-05, "loss": 0.9668, "step": 9395 }, { "epoch": 0.5137057919015889, "grad_norm": 3.4308786392211914, "learning_rate": 5.022133795464073e-05, "loss": 1.226, "step": 9396 }, { "epoch": 0.5137604647189475, "grad_norm": 2.4971792697906494, "learning_rate": 5.0212484490863654e-05, "loss": 1.0197, "step": 9397 }, { "epoch": 0.5138151375363061, "grad_norm": 2.2550575733184814, "learning_rate": 5.0203631020424315e-05, "loss": 1.1093, "step": 9398 }, { "epoch": 0.5138698103536647, "grad_norm": 2.212369918823242, "learning_rate": 5.0194777543600294e-05, "loss": 0.8594, "step": 9399 }, { "epoch": 0.5139244831710235, "grad_norm": 2.1860508918762207, "learning_rate": 5.01859240606692e-05, "loss": 0.9507, "step": 9400 }, { "epoch": 0.5139791559883821, "grad_norm": 2.566206455230713, "learning_rate": 5.0177070571908625e-05, "loss": 0.9485, "step": 9401 }, { "epoch": 0.5140338288057407, "grad_norm": 2.5255846977233887, "learning_rate": 5.016821707759616e-05, "loss": 1.0093, "step": 9402 }, { "epoch": 0.5140885016230993, "grad_norm": 3.428682804107666, "learning_rate": 5.0159363578009386e-05, "loss": 1.0916, "step": 9403 }, { "epoch": 0.5141431744404579, "grad_norm": 2.6554408073425293, "learning_rate": 5.015051007342591e-05, "loss": 1.04, "step": 9404 }, { "epoch": 0.5141978472578165, "grad_norm": 2.198415517807007, "learning_rate": 5.014165656412333e-05, "loss": 0.8929, "step": 9405 }, { "epoch": 0.5142525200751751, "grad_norm": 2.3085083961486816, "learning_rate": 5.013280305037924e-05, "loss": 1.1243, "step": 9406 }, { "epoch": 0.5143071928925338, "grad_norm": 2.670306444168091, "learning_rate": 5.012394953247121e-05, "loss": 1.0844, "step": 9407 }, { "epoch": 0.5143618657098924, "grad_norm": 3.124332904815674, "learning_rate": 5.0115096010676864e-05, "loss": 1.1721, "step": 9408 }, { "epoch": 0.514416538527251, "grad_norm": 3.3546395301818848, "learning_rate": 5.010624248527378e-05, "loss": 1.0306, "step": 9409 }, { "epoch": 0.5144712113446096, "grad_norm": 2.3541507720947266, "learning_rate": 5.009738895653956e-05, "loss": 0.968, "step": 9410 }, { "epoch": 0.5145258841619682, "grad_norm": 2.482480764389038, "learning_rate": 5.0088535424751796e-05, "loss": 1.0116, "step": 9411 }, { "epoch": 0.5145805569793268, "grad_norm": 2.939253330230713, "learning_rate": 5.0079681890188065e-05, "loss": 1.1521, "step": 9412 }, { "epoch": 0.5146352297966854, "grad_norm": 2.47662091255188, "learning_rate": 5.0070828353126e-05, "loss": 1.0766, "step": 9413 }, { "epoch": 0.5146899026140441, "grad_norm": 2.521371364593506, "learning_rate": 5.006197481384316e-05, "loss": 1.0574, "step": 9414 }, { "epoch": 0.5147445754314027, "grad_norm": 2.3436942100524902, "learning_rate": 5.005312127261716e-05, "loss": 0.8824, "step": 9415 }, { "epoch": 0.5147992482487613, "grad_norm": 3.040817975997925, "learning_rate": 5.0044267729725594e-05, "loss": 0.9556, "step": 9416 }, { "epoch": 0.5148539210661199, "grad_norm": 2.8085668087005615, "learning_rate": 5.003541418544605e-05, "loss": 1.0683, "step": 9417 }, { "epoch": 0.5149085938834785, "grad_norm": 2.2373087406158447, "learning_rate": 5.002656064005612e-05, "loss": 0.9495, "step": 9418 }, { "epoch": 0.5149632667008371, "grad_norm": 2.1521592140197754, "learning_rate": 5.00177070938334e-05, "loss": 1.0406, "step": 9419 }, { "epoch": 0.5150179395181957, "grad_norm": 2.342576026916504, "learning_rate": 5.0008853547055504e-05, "loss": 1.1403, "step": 9420 }, { "epoch": 0.5150726123355545, "grad_norm": 2.7761788368225098, "learning_rate": 5e-05, "loss": 1.003, "step": 9421 }, { "epoch": 0.5151272851529131, "grad_norm": 2.1909849643707275, "learning_rate": 4.999114645294451e-05, "loss": 1.076, "step": 9422 }, { "epoch": 0.5151819579702717, "grad_norm": 3.334455966949463, "learning_rate": 4.998229290616661e-05, "loss": 0.9862, "step": 9423 }, { "epoch": 0.5152366307876303, "grad_norm": 3.4415857791900635, "learning_rate": 4.99734393599439e-05, "loss": 1.1188, "step": 9424 }, { "epoch": 0.5152913036049889, "grad_norm": 2.2623131275177, "learning_rate": 4.9964585814553975e-05, "loss": 0.8893, "step": 9425 }, { "epoch": 0.5153459764223475, "grad_norm": 2.3397910594940186, "learning_rate": 4.995573227027441e-05, "loss": 1.0217, "step": 9426 }, { "epoch": 0.5154006492397062, "grad_norm": 2.336261034011841, "learning_rate": 4.994687872738284e-05, "loss": 0.9915, "step": 9427 }, { "epoch": 0.5154553220570648, "grad_norm": 2.2809855937957764, "learning_rate": 4.9938025186156846e-05, "loss": 0.8286, "step": 9428 }, { "epoch": 0.5155099948744234, "grad_norm": 2.7243473529815674, "learning_rate": 4.992917164687401e-05, "loss": 0.9744, "step": 9429 }, { "epoch": 0.515564667691782, "grad_norm": 2.551927328109741, "learning_rate": 4.992031810981194e-05, "loss": 0.9374, "step": 9430 }, { "epoch": 0.5156193405091406, "grad_norm": 2.3770751953125, "learning_rate": 4.991146457524822e-05, "loss": 1.1264, "step": 9431 }, { "epoch": 0.5156740133264992, "grad_norm": 2.1504759788513184, "learning_rate": 4.9902611043460457e-05, "loss": 0.8249, "step": 9432 }, { "epoch": 0.5157286861438578, "grad_norm": 3.0391082763671875, "learning_rate": 4.989375751472624e-05, "loss": 0.8762, "step": 9433 }, { "epoch": 0.5157833589612165, "grad_norm": 2.1576364040374756, "learning_rate": 4.9884903989323155e-05, "loss": 0.7761, "step": 9434 }, { "epoch": 0.5158380317785751, "grad_norm": 2.7225518226623535, "learning_rate": 4.9876050467528805e-05, "loss": 0.979, "step": 9435 }, { "epoch": 0.5158927045959337, "grad_norm": 2.6957263946533203, "learning_rate": 4.9867196949620765e-05, "loss": 0.9989, "step": 9436 }, { "epoch": 0.5159473774132923, "grad_norm": 2.6923153400421143, "learning_rate": 4.985834343587667e-05, "loss": 0.8338, "step": 9437 }, { "epoch": 0.5160020502306509, "grad_norm": 2.245013475418091, "learning_rate": 4.984948992657409e-05, "loss": 1.0375, "step": 9438 }, { "epoch": 0.5160567230480095, "grad_norm": 3.198185920715332, "learning_rate": 4.984063642199062e-05, "loss": 1.1386, "step": 9439 }, { "epoch": 0.5161113958653681, "grad_norm": 2.7451541423797607, "learning_rate": 4.9831782922403853e-05, "loss": 1.1624, "step": 9440 }, { "epoch": 0.5161660686827269, "grad_norm": 3.0546727180480957, "learning_rate": 4.9822929428091386e-05, "loss": 1.1713, "step": 9441 }, { "epoch": 0.5162207415000855, "grad_norm": 3.0572142601013184, "learning_rate": 4.9814075939330814e-05, "loss": 1.1389, "step": 9442 }, { "epoch": 0.5162754143174441, "grad_norm": 2.5143184661865234, "learning_rate": 4.980522245639972e-05, "loss": 1.0538, "step": 9443 }, { "epoch": 0.5163300871348027, "grad_norm": 2.381920337677002, "learning_rate": 4.979636897957571e-05, "loss": 0.9117, "step": 9444 }, { "epoch": 0.5163847599521613, "grad_norm": 3.2046144008636475, "learning_rate": 4.9787515509136365e-05, "loss": 1.179, "step": 9445 }, { "epoch": 0.5164394327695199, "grad_norm": 2.2334892749786377, "learning_rate": 4.977866204535927e-05, "loss": 0.9296, "step": 9446 }, { "epoch": 0.5164941055868785, "grad_norm": 2.739686965942383, "learning_rate": 4.976980858852205e-05, "loss": 1.0008, "step": 9447 }, { "epoch": 0.5165487784042372, "grad_norm": 3.1880223751068115, "learning_rate": 4.9760955138902274e-05, "loss": 1.0647, "step": 9448 }, { "epoch": 0.5166034512215958, "grad_norm": 2.2986741065979004, "learning_rate": 4.9752101696777546e-05, "loss": 0.7349, "step": 9449 }, { "epoch": 0.5166581240389544, "grad_norm": 2.012845277786255, "learning_rate": 4.974324826242545e-05, "loss": 0.9624, "step": 9450 }, { "epoch": 0.516712796856313, "grad_norm": 2.2406113147735596, "learning_rate": 4.9734394836123576e-05, "loss": 0.8811, "step": 9451 }, { "epoch": 0.5167674696736716, "grad_norm": 2.700038433074951, "learning_rate": 4.972554141814952e-05, "loss": 1.0119, "step": 9452 }, { "epoch": 0.5168221424910302, "grad_norm": 3.1414170265197754, "learning_rate": 4.9716688008780864e-05, "loss": 1.2275, "step": 9453 }, { "epoch": 0.5168768153083889, "grad_norm": 3.1270384788513184, "learning_rate": 4.970783460829521e-05, "loss": 1.1851, "step": 9454 }, { "epoch": 0.5169314881257475, "grad_norm": 3.9117231369018555, "learning_rate": 4.969898121697015e-05, "loss": 0.9296, "step": 9455 }, { "epoch": 0.5169861609431061, "grad_norm": 3.9788248538970947, "learning_rate": 4.969012783508325e-05, "loss": 1.1151, "step": 9456 }, { "epoch": 0.5170408337604647, "grad_norm": 2.9142093658447266, "learning_rate": 4.9681274462912136e-05, "loss": 0.9742, "step": 9457 }, { "epoch": 0.5170955065778233, "grad_norm": 2.7683634757995605, "learning_rate": 4.967242110073436e-05, "loss": 1.074, "step": 9458 }, { "epoch": 0.5171501793951819, "grad_norm": 2.323016405105591, "learning_rate": 4.966356774882755e-05, "loss": 0.9203, "step": 9459 }, { "epoch": 0.5172048522125405, "grad_norm": 3.2109084129333496, "learning_rate": 4.9654714407469274e-05, "loss": 1.1593, "step": 9460 }, { "epoch": 0.5172595250298992, "grad_norm": 3.413766384124756, "learning_rate": 4.9645861076937126e-05, "loss": 0.8458, "step": 9461 }, { "epoch": 0.5173141978472579, "grad_norm": 2.494792938232422, "learning_rate": 4.963700775750869e-05, "loss": 0.8349, "step": 9462 }, { "epoch": 0.5173688706646165, "grad_norm": 2.382140874862671, "learning_rate": 4.9628154449461555e-05, "loss": 0.9337, "step": 9463 }, { "epoch": 0.5174235434819751, "grad_norm": 2.5824923515319824, "learning_rate": 4.961930115307331e-05, "loss": 1.1444, "step": 9464 }, { "epoch": 0.5174782162993337, "grad_norm": 2.6022980213165283, "learning_rate": 4.961044786862154e-05, "loss": 0.8776, "step": 9465 }, { "epoch": 0.5175328891166923, "grad_norm": 2.191767454147339, "learning_rate": 4.960159459638383e-05, "loss": 0.9585, "step": 9466 }, { "epoch": 0.5175875619340509, "grad_norm": 2.9476101398468018, "learning_rate": 4.959274133663777e-05, "loss": 1.289, "step": 9467 }, { "epoch": 0.5176422347514096, "grad_norm": 2.2398080825805664, "learning_rate": 4.958388808966095e-05, "loss": 1.1018, "step": 9468 }, { "epoch": 0.5176969075687682, "grad_norm": 2.845184326171875, "learning_rate": 4.957503485573096e-05, "loss": 1.0785, "step": 9469 }, { "epoch": 0.5177515803861268, "grad_norm": 2.668987274169922, "learning_rate": 4.956618163512537e-05, "loss": 0.9878, "step": 9470 }, { "epoch": 0.5178062532034854, "grad_norm": 2.4075300693511963, "learning_rate": 4.9557328428121775e-05, "loss": 0.9483, "step": 9471 }, { "epoch": 0.517860926020844, "grad_norm": 2.8018317222595215, "learning_rate": 4.9548475234997744e-05, "loss": 1.0387, "step": 9472 }, { "epoch": 0.5179155988382026, "grad_norm": 3.1441593170166016, "learning_rate": 4.953962205603088e-05, "loss": 1.06, "step": 9473 }, { "epoch": 0.5179702716555612, "grad_norm": 2.344195604324341, "learning_rate": 4.953076889149877e-05, "loss": 0.9372, "step": 9474 }, { "epoch": 0.5180249444729199, "grad_norm": 2.26790714263916, "learning_rate": 4.9521915741678974e-05, "loss": 1.1059, "step": 9475 }, { "epoch": 0.5180796172902785, "grad_norm": 2.668004274368286, "learning_rate": 4.95130626068491e-05, "loss": 0.9732, "step": 9476 }, { "epoch": 0.5181342901076371, "grad_norm": 2.4939911365509033, "learning_rate": 4.9504209487286715e-05, "loss": 1.0186, "step": 9477 }, { "epoch": 0.5181889629249957, "grad_norm": 3.091137170791626, "learning_rate": 4.949535638326941e-05, "loss": 0.9225, "step": 9478 }, { "epoch": 0.5182436357423543, "grad_norm": 2.231820583343506, "learning_rate": 4.948650329507475e-05, "loss": 0.9737, "step": 9479 }, { "epoch": 0.5182983085597129, "grad_norm": 2.4308183193206787, "learning_rate": 4.947765022298034e-05, "loss": 1.1843, "step": 9480 }, { "epoch": 0.5183529813770716, "grad_norm": 2.2596662044525146, "learning_rate": 4.946879716726374e-05, "loss": 1.0443, "step": 9481 }, { "epoch": 0.5184076541944302, "grad_norm": 2.4114694595336914, "learning_rate": 4.9459944128202534e-05, "loss": 1.168, "step": 9482 }, { "epoch": 0.5184623270117888, "grad_norm": 2.519137382507324, "learning_rate": 4.945109110607431e-05, "loss": 1.072, "step": 9483 }, { "epoch": 0.5185169998291475, "grad_norm": 2.5470499992370605, "learning_rate": 4.9442238101156635e-05, "loss": 1.1279, "step": 9484 }, { "epoch": 0.518571672646506, "grad_norm": 2.5355541706085205, "learning_rate": 4.9433385113727074e-05, "loss": 1.1737, "step": 9485 }, { "epoch": 0.5186263454638647, "grad_norm": 2.502551555633545, "learning_rate": 4.9424532144063243e-05, "loss": 1.1051, "step": 9486 }, { "epoch": 0.5186810182812233, "grad_norm": 2.3340401649475098, "learning_rate": 4.9415679192442705e-05, "loss": 0.9885, "step": 9487 }, { "epoch": 0.518735691098582, "grad_norm": 2.28654146194458, "learning_rate": 4.940682625914302e-05, "loss": 1.041, "step": 9488 }, { "epoch": 0.5187903639159406, "grad_norm": 2.3155691623687744, "learning_rate": 4.9397973344441784e-05, "loss": 0.9952, "step": 9489 }, { "epoch": 0.5188450367332992, "grad_norm": 2.652132511138916, "learning_rate": 4.938912044861656e-05, "loss": 0.9468, "step": 9490 }, { "epoch": 0.5188997095506578, "grad_norm": 2.3393919467926025, "learning_rate": 4.9380267571944925e-05, "loss": 1.0237, "step": 9491 }, { "epoch": 0.5189543823680164, "grad_norm": 2.4904839992523193, "learning_rate": 4.937141471470446e-05, "loss": 1.0584, "step": 9492 }, { "epoch": 0.519009055185375, "grad_norm": 3.212307929992676, "learning_rate": 4.9362561877172725e-05, "loss": 1.0247, "step": 9493 }, { "epoch": 0.5190637280027336, "grad_norm": 2.2352163791656494, "learning_rate": 4.9353709059627304e-05, "loss": 0.9561, "step": 9494 }, { "epoch": 0.5191184008200923, "grad_norm": 2.996509313583374, "learning_rate": 4.934485626234574e-05, "loss": 1.1316, "step": 9495 }, { "epoch": 0.5191730736374509, "grad_norm": 2.491023540496826, "learning_rate": 4.933600348560566e-05, "loss": 0.9675, "step": 9496 }, { "epoch": 0.5192277464548095, "grad_norm": 3.147508382797241, "learning_rate": 4.93271507296846e-05, "loss": 1.0818, "step": 9497 }, { "epoch": 0.5192824192721681, "grad_norm": 2.748566150665283, "learning_rate": 4.931829799486013e-05, "loss": 1.0172, "step": 9498 }, { "epoch": 0.5193370920895267, "grad_norm": 2.413475751876831, "learning_rate": 4.930944528140983e-05, "loss": 0.8811, "step": 9499 }, { "epoch": 0.5193917649068853, "grad_norm": 2.2360148429870605, "learning_rate": 4.930059258961127e-05, "loss": 0.961, "step": 9500 }, { "epoch": 0.5194464377242439, "grad_norm": 2.7115578651428223, "learning_rate": 4.9291739919742006e-05, "loss": 0.8082, "step": 9501 }, { "epoch": 0.5195011105416026, "grad_norm": 2.419760227203369, "learning_rate": 4.928288727207962e-05, "loss": 1.0572, "step": 9502 }, { "epoch": 0.5195557833589612, "grad_norm": 2.1738877296447754, "learning_rate": 4.927403464690166e-05, "loss": 0.9689, "step": 9503 }, { "epoch": 0.5196104561763198, "grad_norm": 2.666435480117798, "learning_rate": 4.926518204448571e-05, "loss": 0.8878, "step": 9504 }, { "epoch": 0.5196651289936784, "grad_norm": 3.052823305130005, "learning_rate": 4.9256329465109306e-05, "loss": 1.0965, "step": 9505 }, { "epoch": 0.519719801811037, "grad_norm": 2.9976847171783447, "learning_rate": 4.9247476909050064e-05, "loss": 0.7514, "step": 9506 }, { "epoch": 0.5197744746283957, "grad_norm": 3.011233329772949, "learning_rate": 4.9238624376585514e-05, "loss": 0.9828, "step": 9507 }, { "epoch": 0.5198291474457544, "grad_norm": 2.405305862426758, "learning_rate": 4.9229771867993226e-05, "loss": 0.9051, "step": 9508 }, { "epoch": 0.519883820263113, "grad_norm": 2.1031839847564697, "learning_rate": 4.922091938355077e-05, "loss": 1.0242, "step": 9509 }, { "epoch": 0.5199384930804716, "grad_norm": 2.6371679306030273, "learning_rate": 4.9212066923535685e-05, "loss": 0.9107, "step": 9510 }, { "epoch": 0.5199931658978302, "grad_norm": 2.42689847946167, "learning_rate": 4.920321448822556e-05, "loss": 1.0112, "step": 9511 }, { "epoch": 0.5200478387151888, "grad_norm": 2.6748440265655518, "learning_rate": 4.9194362077897934e-05, "loss": 1.105, "step": 9512 }, { "epoch": 0.5201025115325474, "grad_norm": 2.640070676803589, "learning_rate": 4.918550969283038e-05, "loss": 1.196, "step": 9513 }, { "epoch": 0.520157184349906, "grad_norm": 3.4130077362060547, "learning_rate": 4.9176657333300447e-05, "loss": 1.1, "step": 9514 }, { "epoch": 0.5202118571672647, "grad_norm": 2.063671588897705, "learning_rate": 4.916780499958568e-05, "loss": 0.8109, "step": 9515 }, { "epoch": 0.5202665299846233, "grad_norm": 2.4015445709228516, "learning_rate": 4.9158952691963675e-05, "loss": 1.1525, "step": 9516 }, { "epoch": 0.5203212028019819, "grad_norm": 2.258222818374634, "learning_rate": 4.915010041071196e-05, "loss": 1.144, "step": 9517 }, { "epoch": 0.5203758756193405, "grad_norm": 2.966055393218994, "learning_rate": 4.9141248156108105e-05, "loss": 1.181, "step": 9518 }, { "epoch": 0.5204305484366991, "grad_norm": 2.5947604179382324, "learning_rate": 4.913239592842965e-05, "loss": 0.8081, "step": 9519 }, { "epoch": 0.5204852212540577, "grad_norm": 2.44514799118042, "learning_rate": 4.912354372795417e-05, "loss": 0.9545, "step": 9520 }, { "epoch": 0.5205398940714163, "grad_norm": 3.024573564529419, "learning_rate": 4.911469155495919e-05, "loss": 1.191, "step": 9521 }, { "epoch": 0.520594566888775, "grad_norm": 2.6630945205688477, "learning_rate": 4.9105839409722285e-05, "loss": 1.1116, "step": 9522 }, { "epoch": 0.5206492397061336, "grad_norm": 2.8028433322906494, "learning_rate": 4.909698729252099e-05, "loss": 1.1477, "step": 9523 }, { "epoch": 0.5207039125234922, "grad_norm": 2.7391839027404785, "learning_rate": 4.9088135203632864e-05, "loss": 1.1649, "step": 9524 }, { "epoch": 0.5207585853408508, "grad_norm": 2.6629834175109863, "learning_rate": 4.9079283143335433e-05, "loss": 0.9597, "step": 9525 }, { "epoch": 0.5208132581582094, "grad_norm": 2.2997426986694336, "learning_rate": 4.907043111190629e-05, "loss": 1.0154, "step": 9526 }, { "epoch": 0.520867930975568, "grad_norm": 2.7524099349975586, "learning_rate": 4.906157910962296e-05, "loss": 1.0717, "step": 9527 }, { "epoch": 0.5209226037929267, "grad_norm": 2.3653647899627686, "learning_rate": 4.905272713676299e-05, "loss": 1.0465, "step": 9528 }, { "epoch": 0.5209772766102854, "grad_norm": 2.527165651321411, "learning_rate": 4.904387519360392e-05, "loss": 1.1596, "step": 9529 }, { "epoch": 0.521031949427644, "grad_norm": 2.331372022628784, "learning_rate": 4.903502328042331e-05, "loss": 1.0962, "step": 9530 }, { "epoch": 0.5210866222450026, "grad_norm": 2.1264727115631104, "learning_rate": 4.902617139749869e-05, "loss": 0.8329, "step": 9531 }, { "epoch": 0.5211412950623612, "grad_norm": 2.7638044357299805, "learning_rate": 4.901731954510761e-05, "loss": 1.1057, "step": 9532 }, { "epoch": 0.5211959678797198, "grad_norm": 2.4504685401916504, "learning_rate": 4.90084677235276e-05, "loss": 0.9442, "step": 9533 }, { "epoch": 0.5212506406970784, "grad_norm": 2.4546971321105957, "learning_rate": 4.89996159330362e-05, "loss": 0.8126, "step": 9534 }, { "epoch": 0.521305313514437, "grad_norm": 2.4698398113250732, "learning_rate": 4.8990764173910975e-05, "loss": 0.8322, "step": 9535 }, { "epoch": 0.5213599863317957, "grad_norm": 2.074974298477173, "learning_rate": 4.898191244642945e-05, "loss": 0.7674, "step": 9536 }, { "epoch": 0.5214146591491543, "grad_norm": 2.505584716796875, "learning_rate": 4.897306075086917e-05, "loss": 1.0618, "step": 9537 }, { "epoch": 0.5214693319665129, "grad_norm": 2.4175992012023926, "learning_rate": 4.896420908750766e-05, "loss": 1.1797, "step": 9538 }, { "epoch": 0.5215240047838715, "grad_norm": 2.4035775661468506, "learning_rate": 4.8955357456622456e-05, "loss": 0.9309, "step": 9539 }, { "epoch": 0.5215786776012301, "grad_norm": 2.892869472503662, "learning_rate": 4.8946505858491104e-05, "loss": 1.1728, "step": 9540 }, { "epoch": 0.5216333504185887, "grad_norm": 2.7821860313415527, "learning_rate": 4.893765429339113e-05, "loss": 1.0698, "step": 9541 }, { "epoch": 0.5216880232359474, "grad_norm": 2.7158403396606445, "learning_rate": 4.8928802761600076e-05, "loss": 1.0474, "step": 9542 }, { "epoch": 0.521742696053306, "grad_norm": 2.6279845237731934, "learning_rate": 4.891995126339546e-05, "loss": 0.8743, "step": 9543 }, { "epoch": 0.5217973688706646, "grad_norm": 4.150029182434082, "learning_rate": 4.89110997990548e-05, "loss": 1.021, "step": 9544 }, { "epoch": 0.5218520416880232, "grad_norm": 2.6377053260803223, "learning_rate": 4.890224836885566e-05, "loss": 1.1174, "step": 9545 }, { "epoch": 0.5219067145053818, "grad_norm": 4.343605995178223, "learning_rate": 4.889339697307556e-05, "loss": 1.0493, "step": 9546 }, { "epoch": 0.5219613873227404, "grad_norm": 2.2826030254364014, "learning_rate": 4.888454561199203e-05, "loss": 0.8678, "step": 9547 }, { "epoch": 0.522016060140099, "grad_norm": 2.4712088108062744, "learning_rate": 4.887569428588258e-05, "loss": 0.9632, "step": 9548 }, { "epoch": 0.5220707329574578, "grad_norm": 2.24879789352417, "learning_rate": 4.886684299502475e-05, "loss": 0.8963, "step": 9549 }, { "epoch": 0.5221254057748164, "grad_norm": 3.077791690826416, "learning_rate": 4.885799173969605e-05, "loss": 1.0252, "step": 9550 }, { "epoch": 0.522180078592175, "grad_norm": 2.6830599308013916, "learning_rate": 4.884914052017403e-05, "loss": 1.0112, "step": 9551 }, { "epoch": 0.5222347514095336, "grad_norm": 2.841108560562134, "learning_rate": 4.884028933673618e-05, "loss": 1.1066, "step": 9552 }, { "epoch": 0.5222894242268922, "grad_norm": 2.709855794906616, "learning_rate": 4.8831438189660034e-05, "loss": 1.0756, "step": 9553 }, { "epoch": 0.5223440970442508, "grad_norm": 2.3492565155029297, "learning_rate": 4.882258707922311e-05, "loss": 0.9882, "step": 9554 }, { "epoch": 0.5223987698616094, "grad_norm": 2.5116171836853027, "learning_rate": 4.881373600570294e-05, "loss": 1.1939, "step": 9555 }, { "epoch": 0.5224534426789681, "grad_norm": 2.221219301223755, "learning_rate": 4.8804884969377025e-05, "loss": 0.9985, "step": 9556 }, { "epoch": 0.5225081154963267, "grad_norm": 2.3145592212677, "learning_rate": 4.879603397052289e-05, "loss": 1.0703, "step": 9557 }, { "epoch": 0.5225627883136853, "grad_norm": 2.6204633712768555, "learning_rate": 4.8787183009418044e-05, "loss": 1.0026, "step": 9558 }, { "epoch": 0.5226174611310439, "grad_norm": 2.2719457149505615, "learning_rate": 4.8778332086340014e-05, "loss": 1.0978, "step": 9559 }, { "epoch": 0.5226721339484025, "grad_norm": 3.1366889476776123, "learning_rate": 4.8769481201566305e-05, "loss": 1.0944, "step": 9560 }, { "epoch": 0.5227268067657611, "grad_norm": 3.3661139011383057, "learning_rate": 4.876063035537442e-05, "loss": 1.1596, "step": 9561 }, { "epoch": 0.5227814795831197, "grad_norm": 2.2464234828948975, "learning_rate": 4.875177954804189e-05, "loss": 1.1193, "step": 9562 }, { "epoch": 0.5228361524004784, "grad_norm": 2.571305513381958, "learning_rate": 4.8742928779846206e-05, "loss": 1.2086, "step": 9563 }, { "epoch": 0.522890825217837, "grad_norm": 2.6648430824279785, "learning_rate": 4.873407805106487e-05, "loss": 1.1701, "step": 9564 }, { "epoch": 0.5229454980351956, "grad_norm": 2.6258420944213867, "learning_rate": 4.872522736197541e-05, "loss": 0.9296, "step": 9565 }, { "epoch": 0.5230001708525542, "grad_norm": 3.0482935905456543, "learning_rate": 4.8716376712855326e-05, "loss": 0.7946, "step": 9566 }, { "epoch": 0.5230548436699128, "grad_norm": 3.1449851989746094, "learning_rate": 4.8707526103982116e-05, "loss": 0.9631, "step": 9567 }, { "epoch": 0.5231095164872714, "grad_norm": 2.971334934234619, "learning_rate": 4.8698675535633285e-05, "loss": 1.21, "step": 9568 }, { "epoch": 0.5231641893046302, "grad_norm": 2.727179527282715, "learning_rate": 4.868982500808634e-05, "loss": 0.9256, "step": 9569 }, { "epoch": 0.5232188621219888, "grad_norm": 2.517134428024292, "learning_rate": 4.868097452161878e-05, "loss": 1.0981, "step": 9570 }, { "epoch": 0.5232735349393474, "grad_norm": 2.26780366897583, "learning_rate": 4.867212407650809e-05, "loss": 1.0495, "step": 9571 }, { "epoch": 0.523328207756706, "grad_norm": 2.9983346462249756, "learning_rate": 4.866327367303177e-05, "loss": 1.1498, "step": 9572 }, { "epoch": 0.5233828805740646, "grad_norm": 2.7702488899230957, "learning_rate": 4.8654423311467346e-05, "loss": 1.1606, "step": 9573 }, { "epoch": 0.5234375533914232, "grad_norm": 2.7760050296783447, "learning_rate": 4.864557299209228e-05, "loss": 1.1511, "step": 9574 }, { "epoch": 0.5234922262087818, "grad_norm": 2.4623162746429443, "learning_rate": 4.863672271518408e-05, "loss": 1.15, "step": 9575 }, { "epoch": 0.5235468990261405, "grad_norm": 2.0854671001434326, "learning_rate": 4.8627872481020245e-05, "loss": 0.7991, "step": 9576 }, { "epoch": 0.5236015718434991, "grad_norm": 2.4369208812713623, "learning_rate": 4.861902228987825e-05, "loss": 1.0904, "step": 9577 }, { "epoch": 0.5236562446608577, "grad_norm": 3.330198287963867, "learning_rate": 4.86101721420356e-05, "loss": 1.0404, "step": 9578 }, { "epoch": 0.5237109174782163, "grad_norm": 4.005612373352051, "learning_rate": 4.860132203776978e-05, "loss": 0.9909, "step": 9579 }, { "epoch": 0.5237655902955749, "grad_norm": 2.5276427268981934, "learning_rate": 4.859247197735827e-05, "loss": 1.0668, "step": 9580 }, { "epoch": 0.5238202631129335, "grad_norm": 3.100693941116333, "learning_rate": 4.8583621961078565e-05, "loss": 1.2096, "step": 9581 }, { "epoch": 0.5238749359302921, "grad_norm": 3.640291929244995, "learning_rate": 4.857477198920815e-05, "loss": 1.0074, "step": 9582 }, { "epoch": 0.5239296087476508, "grad_norm": 3.0364668369293213, "learning_rate": 4.8565922062024464e-05, "loss": 1.1205, "step": 9583 }, { "epoch": 0.5239842815650094, "grad_norm": 1.8743482828140259, "learning_rate": 4.8557072179805064e-05, "loss": 0.8298, "step": 9584 }, { "epoch": 0.524038954382368, "grad_norm": 2.3814854621887207, "learning_rate": 4.854822234282739e-05, "loss": 1.0291, "step": 9585 }, { "epoch": 0.5240936271997266, "grad_norm": 2.3598270416259766, "learning_rate": 4.853937255136892e-05, "loss": 1.1306, "step": 9586 }, { "epoch": 0.5241483000170852, "grad_norm": 2.8821825981140137, "learning_rate": 4.853052280570714e-05, "loss": 0.9854, "step": 9587 }, { "epoch": 0.5242029728344438, "grad_norm": 2.918771982192993, "learning_rate": 4.852167310611952e-05, "loss": 1.0535, "step": 9588 }, { "epoch": 0.5242576456518024, "grad_norm": 2.2471697330474854, "learning_rate": 4.8512823452883537e-05, "loss": 1.0459, "step": 9589 }, { "epoch": 0.5243123184691612, "grad_norm": 2.8341355323791504, "learning_rate": 4.850397384627666e-05, "loss": 1.0891, "step": 9590 }, { "epoch": 0.5243669912865198, "grad_norm": 2.288498640060425, "learning_rate": 4.8495124286576374e-05, "loss": 1.0885, "step": 9591 }, { "epoch": 0.5244216641038784, "grad_norm": 2.9271411895751953, "learning_rate": 4.848627477406013e-05, "loss": 1.068, "step": 9592 }, { "epoch": 0.524476336921237, "grad_norm": 2.2749483585357666, "learning_rate": 4.847742530900539e-05, "loss": 1.0949, "step": 9593 }, { "epoch": 0.5245310097385956, "grad_norm": 2.3861751556396484, "learning_rate": 4.846857589168965e-05, "loss": 1.1033, "step": 9594 }, { "epoch": 0.5245856825559542, "grad_norm": 2.6349728107452393, "learning_rate": 4.8459726522390376e-05, "loss": 0.9511, "step": 9595 }, { "epoch": 0.5246403553733129, "grad_norm": 2.336009979248047, "learning_rate": 4.8450877201385015e-05, "loss": 1.0245, "step": 9596 }, { "epoch": 0.5246950281906715, "grad_norm": 2.548062562942505, "learning_rate": 4.844202792895103e-05, "loss": 1.0053, "step": 9597 }, { "epoch": 0.5247497010080301, "grad_norm": 3.0078585147857666, "learning_rate": 4.843317870536589e-05, "loss": 0.8825, "step": 9598 }, { "epoch": 0.5248043738253887, "grad_norm": 2.4842734336853027, "learning_rate": 4.842432953090704e-05, "loss": 1.1744, "step": 9599 }, { "epoch": 0.5248590466427473, "grad_norm": 2.400251865386963, "learning_rate": 4.841548040585196e-05, "loss": 0.9639, "step": 9600 }, { "epoch": 0.5249137194601059, "grad_norm": 2.6599538326263428, "learning_rate": 4.840663133047809e-05, "loss": 1.0189, "step": 9601 }, { "epoch": 0.5249683922774645, "grad_norm": 2.9272258281707764, "learning_rate": 4.83977823050629e-05, "loss": 1.126, "step": 9602 }, { "epoch": 0.5250230650948232, "grad_norm": 2.539767026901245, "learning_rate": 4.8388933329883795e-05, "loss": 0.8858, "step": 9603 }, { "epoch": 0.5250777379121818, "grad_norm": 2.531949520111084, "learning_rate": 4.8380084405218296e-05, "loss": 0.8375, "step": 9604 }, { "epoch": 0.5251324107295404, "grad_norm": 2.8144116401672363, "learning_rate": 4.837123553134382e-05, "loss": 0.925, "step": 9605 }, { "epoch": 0.525187083546899, "grad_norm": 2.596900701522827, "learning_rate": 4.836238670853782e-05, "loss": 1.0539, "step": 9606 }, { "epoch": 0.5252417563642576, "grad_norm": 3.170757293701172, "learning_rate": 4.8353537937077745e-05, "loss": 0.9707, "step": 9607 }, { "epoch": 0.5252964291816162, "grad_norm": 2.7128498554229736, "learning_rate": 4.834468921724102e-05, "loss": 1.1842, "step": 9608 }, { "epoch": 0.5253511019989748, "grad_norm": 2.515183448791504, "learning_rate": 4.8335840549305124e-05, "loss": 1.0012, "step": 9609 }, { "epoch": 0.5254057748163335, "grad_norm": 2.412853956222534, "learning_rate": 4.832699193354747e-05, "loss": 1.1064, "step": 9610 }, { "epoch": 0.5254604476336922, "grad_norm": 3.0312962532043457, "learning_rate": 4.831814337024552e-05, "loss": 1.1658, "step": 9611 }, { "epoch": 0.5255151204510508, "grad_norm": 2.8729958534240723, "learning_rate": 4.830929485967669e-05, "loss": 1.0663, "step": 9612 }, { "epoch": 0.5255697932684094, "grad_norm": 2.274554967880249, "learning_rate": 4.830044640211841e-05, "loss": 1.1004, "step": 9613 }, { "epoch": 0.525624466085768, "grad_norm": 2.8690030574798584, "learning_rate": 4.829159799784816e-05, "loss": 1.0678, "step": 9614 }, { "epoch": 0.5256791389031266, "grad_norm": 2.094744920730591, "learning_rate": 4.828274964714335e-05, "loss": 0.7661, "step": 9615 }, { "epoch": 0.5257338117204852, "grad_norm": 2.427381753921509, "learning_rate": 4.8273901350281403e-05, "loss": 1.0497, "step": 9616 }, { "epoch": 0.5257884845378439, "grad_norm": 3.939725160598755, "learning_rate": 4.826505310753976e-05, "loss": 1.1406, "step": 9617 }, { "epoch": 0.5258431573552025, "grad_norm": 4.081753253936768, "learning_rate": 4.8256204919195856e-05, "loss": 1.115, "step": 9618 }, { "epoch": 0.5258978301725611, "grad_norm": 2.51045823097229, "learning_rate": 4.82473567855271e-05, "loss": 1.0287, "step": 9619 }, { "epoch": 0.5259525029899197, "grad_norm": 4.2140793800354, "learning_rate": 4.823850870681093e-05, "loss": 1.0101, "step": 9620 }, { "epoch": 0.5260071758072783, "grad_norm": 2.6386923789978027, "learning_rate": 4.8229660683324776e-05, "loss": 1.0696, "step": 9621 }, { "epoch": 0.5260618486246369, "grad_norm": 2.1819961071014404, "learning_rate": 4.822081271534604e-05, "loss": 1.0075, "step": 9622 }, { "epoch": 0.5261165214419956, "grad_norm": 2.4478888511657715, "learning_rate": 4.821196480315213e-05, "loss": 1.072, "step": 9623 }, { "epoch": 0.5261711942593542, "grad_norm": 6.864362716674805, "learning_rate": 4.820311694702051e-05, "loss": 0.8959, "step": 9624 }, { "epoch": 0.5262258670767128, "grad_norm": 2.6198368072509766, "learning_rate": 4.819426914722858e-05, "loss": 1.0901, "step": 9625 }, { "epoch": 0.5262805398940714, "grad_norm": 2.5520784854888916, "learning_rate": 4.818542140405374e-05, "loss": 1.1751, "step": 9626 }, { "epoch": 0.52633521271143, "grad_norm": 2.4123294353485107, "learning_rate": 4.8176573717773424e-05, "loss": 0.9395, "step": 9627 }, { "epoch": 0.5263898855287886, "grad_norm": 2.813955783843994, "learning_rate": 4.8167726088665024e-05, "loss": 1.0755, "step": 9628 }, { "epoch": 0.5264445583461472, "grad_norm": 3.7979187965393066, "learning_rate": 4.815887851700595e-05, "loss": 1.1046, "step": 9629 }, { "epoch": 0.5264992311635059, "grad_norm": 2.5998923778533936, "learning_rate": 4.815003100307363e-05, "loss": 1.0418, "step": 9630 }, { "epoch": 0.5265539039808645, "grad_norm": 2.640510082244873, "learning_rate": 4.814118354714545e-05, "loss": 0.9866, "step": 9631 }, { "epoch": 0.5266085767982231, "grad_norm": 3.656085252761841, "learning_rate": 4.81323361494988e-05, "loss": 0.9015, "step": 9632 }, { "epoch": 0.5266632496155818, "grad_norm": 2.5488948822021484, "learning_rate": 4.812348881041113e-05, "loss": 1.108, "step": 9633 }, { "epoch": 0.5267179224329404, "grad_norm": 3.280390739440918, "learning_rate": 4.811464153015981e-05, "loss": 1.3107, "step": 9634 }, { "epoch": 0.526772595250299, "grad_norm": 2.4036567211151123, "learning_rate": 4.810579430902224e-05, "loss": 0.8, "step": 9635 }, { "epoch": 0.5268272680676576, "grad_norm": 2.3518857955932617, "learning_rate": 4.809694714727582e-05, "loss": 0.8064, "step": 9636 }, { "epoch": 0.5268819408850163, "grad_norm": 3.2978577613830566, "learning_rate": 4.8088100045197954e-05, "loss": 1.0753, "step": 9637 }, { "epoch": 0.5269366137023749, "grad_norm": 2.6617372035980225, "learning_rate": 4.807925300306602e-05, "loss": 1.212, "step": 9638 }, { "epoch": 0.5269912865197335, "grad_norm": 4.193991661071777, "learning_rate": 4.807040602115741e-05, "loss": 1.1755, "step": 9639 }, { "epoch": 0.5270459593370921, "grad_norm": 2.860567569732666, "learning_rate": 4.806155909974952e-05, "loss": 0.8553, "step": 9640 }, { "epoch": 0.5271006321544507, "grad_norm": 2.2089855670928955, "learning_rate": 4.805271223911974e-05, "loss": 0.9831, "step": 9641 }, { "epoch": 0.5271553049718093, "grad_norm": 2.765695810317993, "learning_rate": 4.804386543954544e-05, "loss": 0.929, "step": 9642 }, { "epoch": 0.5272099777891679, "grad_norm": 2.776995897293091, "learning_rate": 4.8035018701304025e-05, "loss": 1.11, "step": 9643 }, { "epoch": 0.5272646506065266, "grad_norm": 2.290076971054077, "learning_rate": 4.802617202467286e-05, "loss": 0.9519, "step": 9644 }, { "epoch": 0.5273193234238852, "grad_norm": 2.6744277477264404, "learning_rate": 4.801732540992933e-05, "loss": 1.1147, "step": 9645 }, { "epoch": 0.5273739962412438, "grad_norm": 3.288377285003662, "learning_rate": 4.800847885735082e-05, "loss": 1.1914, "step": 9646 }, { "epoch": 0.5274286690586024, "grad_norm": 2.0876166820526123, "learning_rate": 4.7999632367214696e-05, "loss": 0.8602, "step": 9647 }, { "epoch": 0.527483341875961, "grad_norm": 2.2400565147399902, "learning_rate": 4.7990785939798336e-05, "loss": 0.9815, "step": 9648 }, { "epoch": 0.5275380146933196, "grad_norm": 2.6672475337982178, "learning_rate": 4.798193957537912e-05, "loss": 0.9901, "step": 9649 }, { "epoch": 0.5275926875106783, "grad_norm": 2.5001227855682373, "learning_rate": 4.79730932742344e-05, "loss": 1.1241, "step": 9650 }, { "epoch": 0.5276473603280369, "grad_norm": 3.338334798812866, "learning_rate": 4.796424703664156e-05, "loss": 1.227, "step": 9651 }, { "epoch": 0.5277020331453955, "grad_norm": 2.4416143894195557, "learning_rate": 4.795540086287795e-05, "loss": 1.1062, "step": 9652 }, { "epoch": 0.5277567059627541, "grad_norm": 2.571153402328491, "learning_rate": 4.794655475322095e-05, "loss": 0.954, "step": 9653 }, { "epoch": 0.5278113787801127, "grad_norm": 2.03518009185791, "learning_rate": 4.793770870794792e-05, "loss": 1.012, "step": 9654 }, { "epoch": 0.5278660515974714, "grad_norm": 2.995652437210083, "learning_rate": 4.792886272733621e-05, "loss": 1.0273, "step": 9655 }, { "epoch": 0.52792072441483, "grad_norm": 2.1587295532226562, "learning_rate": 4.792001681166318e-05, "loss": 0.9913, "step": 9656 }, { "epoch": 0.5279753972321887, "grad_norm": 2.1437487602233887, "learning_rate": 4.79111709612062e-05, "loss": 0.9198, "step": 9657 }, { "epoch": 0.5280300700495473, "grad_norm": 2.640500068664551, "learning_rate": 4.79023251762426e-05, "loss": 1.0456, "step": 9658 }, { "epoch": 0.5280847428669059, "grad_norm": 3.479947566986084, "learning_rate": 4.789347945704974e-05, "loss": 1.0088, "step": 9659 }, { "epoch": 0.5281394156842645, "grad_norm": 4.539355754852295, "learning_rate": 4.788463380390499e-05, "loss": 1.1753, "step": 9660 }, { "epoch": 0.5281940885016231, "grad_norm": 2.3733971118927, "learning_rate": 4.787578821708568e-05, "loss": 1.0014, "step": 9661 }, { "epoch": 0.5282487613189817, "grad_norm": 1.9907441139221191, "learning_rate": 4.7866942696869146e-05, "loss": 0.9574, "step": 9662 }, { "epoch": 0.5283034341363403, "grad_norm": 1.9983546733856201, "learning_rate": 4.7858097243532754e-05, "loss": 0.9628, "step": 9663 }, { "epoch": 0.528358106953699, "grad_norm": 2.014500379562378, "learning_rate": 4.7849251857353836e-05, "loss": 0.8391, "step": 9664 }, { "epoch": 0.5284127797710576, "grad_norm": 2.458315849304199, "learning_rate": 4.7840406538609725e-05, "loss": 0.7827, "step": 9665 }, { "epoch": 0.5284674525884162, "grad_norm": 3.086851119995117, "learning_rate": 4.783156128757777e-05, "loss": 1.0282, "step": 9666 }, { "epoch": 0.5285221254057748, "grad_norm": 2.6074910163879395, "learning_rate": 4.78227161045353e-05, "loss": 1.1176, "step": 9667 }, { "epoch": 0.5285767982231334, "grad_norm": 2.650207996368408, "learning_rate": 4.781387098975964e-05, "loss": 1.1255, "step": 9668 }, { "epoch": 0.528631471040492, "grad_norm": 3.0874669551849365, "learning_rate": 4.780502594352813e-05, "loss": 1.1091, "step": 9669 }, { "epoch": 0.5286861438578506, "grad_norm": 2.660423755645752, "learning_rate": 4.77961809661181e-05, "loss": 0.9875, "step": 9670 }, { "epoch": 0.5287408166752093, "grad_norm": 2.2462105751037598, "learning_rate": 4.778733605780687e-05, "loss": 0.764, "step": 9671 }, { "epoch": 0.5287954894925679, "grad_norm": 2.320819616317749, "learning_rate": 4.777849121887175e-05, "loss": 0.9541, "step": 9672 }, { "epoch": 0.5288501623099265, "grad_norm": 2.625594139099121, "learning_rate": 4.7769646449590096e-05, "loss": 1.0069, "step": 9673 }, { "epoch": 0.5289048351272851, "grad_norm": 3.084310293197632, "learning_rate": 4.7760801750239214e-05, "loss": 1.1873, "step": 9674 }, { "epoch": 0.5289595079446437, "grad_norm": 3.1893153190612793, "learning_rate": 4.775195712109642e-05, "loss": 1.0335, "step": 9675 }, { "epoch": 0.5290141807620024, "grad_norm": 3.3757576942443848, "learning_rate": 4.7743112562439025e-05, "loss": 0.9768, "step": 9676 }, { "epoch": 0.5290688535793611, "grad_norm": 2.3380045890808105, "learning_rate": 4.773426807454435e-05, "loss": 1.0442, "step": 9677 }, { "epoch": 0.5291235263967197, "grad_norm": 4.441566467285156, "learning_rate": 4.7725423657689694e-05, "loss": 0.8827, "step": 9678 }, { "epoch": 0.5291781992140783, "grad_norm": 3.374950647354126, "learning_rate": 4.771657931215238e-05, "loss": 1.0466, "step": 9679 }, { "epoch": 0.5292328720314369, "grad_norm": 2.1786227226257324, "learning_rate": 4.770773503820971e-05, "loss": 1.0934, "step": 9680 }, { "epoch": 0.5292875448487955, "grad_norm": 4.112006664276123, "learning_rate": 4.769889083613899e-05, "loss": 0.9702, "step": 9681 }, { "epoch": 0.5293422176661541, "grad_norm": 2.657130241394043, "learning_rate": 4.769004670621749e-05, "loss": 1.041, "step": 9682 }, { "epoch": 0.5293968904835127, "grad_norm": 2.0341789722442627, "learning_rate": 4.7681202648722564e-05, "loss": 0.8702, "step": 9683 }, { "epoch": 0.5294515633008714, "grad_norm": 2.44177508354187, "learning_rate": 4.767235866393148e-05, "loss": 0.9852, "step": 9684 }, { "epoch": 0.52950623611823, "grad_norm": 2.2527244091033936, "learning_rate": 4.7663514752121544e-05, "loss": 1.0154, "step": 9685 }, { "epoch": 0.5295609089355886, "grad_norm": 2.221094846725464, "learning_rate": 4.765467091357004e-05, "loss": 1.052, "step": 9686 }, { "epoch": 0.5296155817529472, "grad_norm": 2.407197952270508, "learning_rate": 4.764582714855427e-05, "loss": 1.0796, "step": 9687 }, { "epoch": 0.5296702545703058, "grad_norm": 2.222156286239624, "learning_rate": 4.763698345735151e-05, "loss": 0.903, "step": 9688 }, { "epoch": 0.5297249273876644, "grad_norm": 2.3323819637298584, "learning_rate": 4.7628139840239044e-05, "loss": 1.0396, "step": 9689 }, { "epoch": 0.529779600205023, "grad_norm": 2.570315361022949, "learning_rate": 4.761929629749417e-05, "loss": 1.0235, "step": 9690 }, { "epoch": 0.5298342730223817, "grad_norm": 2.387951135635376, "learning_rate": 4.761045282939414e-05, "loss": 0.8655, "step": 9691 }, { "epoch": 0.5298889458397403, "grad_norm": 3.564060926437378, "learning_rate": 4.760160943621627e-05, "loss": 0.7844, "step": 9692 }, { "epoch": 0.5299436186570989, "grad_norm": 2.745591878890991, "learning_rate": 4.759276611823783e-05, "loss": 1.0926, "step": 9693 }, { "epoch": 0.5299982914744575, "grad_norm": 2.8714756965637207, "learning_rate": 4.758392287573608e-05, "loss": 0.9984, "step": 9694 }, { "epoch": 0.5300529642918161, "grad_norm": 3.1287147998809814, "learning_rate": 4.7575079708988295e-05, "loss": 1.1035, "step": 9695 }, { "epoch": 0.5301076371091747, "grad_norm": 2.1967413425445557, "learning_rate": 4.7566236618271754e-05, "loss": 1.0274, "step": 9696 }, { "epoch": 0.5301623099265333, "grad_norm": 2.8066790103912354, "learning_rate": 4.755739360386372e-05, "loss": 0.9755, "step": 9697 }, { "epoch": 0.5302169827438921, "grad_norm": 3.2080419063568115, "learning_rate": 4.754855066604145e-05, "loss": 1.0757, "step": 9698 }, { "epoch": 0.5302716555612507, "grad_norm": 2.322503089904785, "learning_rate": 4.753970780508222e-05, "loss": 0.8734, "step": 9699 }, { "epoch": 0.5303263283786093, "grad_norm": 3.52531361579895, "learning_rate": 4.7530865021263285e-05, "loss": 1.058, "step": 9700 }, { "epoch": 0.5303810011959679, "grad_norm": 2.3614399433135986, "learning_rate": 4.752202231486187e-05, "loss": 0.8133, "step": 9701 }, { "epoch": 0.5304356740133265, "grad_norm": 2.720149278640747, "learning_rate": 4.751317968615528e-05, "loss": 0.9992, "step": 9702 }, { "epoch": 0.5304903468306851, "grad_norm": 3.2429535388946533, "learning_rate": 4.7504337135420754e-05, "loss": 1.0409, "step": 9703 }, { "epoch": 0.5305450196480438, "grad_norm": 2.336674213409424, "learning_rate": 4.7495494662935544e-05, "loss": 1.1045, "step": 9704 }, { "epoch": 0.5305996924654024, "grad_norm": 2.5380373001098633, "learning_rate": 4.748665226897688e-05, "loss": 1.0079, "step": 9705 }, { "epoch": 0.530654365282761, "grad_norm": 2.8114309310913086, "learning_rate": 4.747780995382202e-05, "loss": 0.9908, "step": 9706 }, { "epoch": 0.5307090381001196, "grad_norm": 2.5294365882873535, "learning_rate": 4.7468967717748213e-05, "loss": 1.0019, "step": 9707 }, { "epoch": 0.5307637109174782, "grad_norm": 2.9050095081329346, "learning_rate": 4.7460125561032684e-05, "loss": 1.131, "step": 9708 }, { "epoch": 0.5308183837348368, "grad_norm": 2.654212713241577, "learning_rate": 4.7451283483952685e-05, "loss": 1.2454, "step": 9709 }, { "epoch": 0.5308730565521954, "grad_norm": 2.8115317821502686, "learning_rate": 4.744244148678544e-05, "loss": 0.998, "step": 9710 }, { "epoch": 0.5309277293695541, "grad_norm": 2.48496675491333, "learning_rate": 4.7433599569808174e-05, "loss": 1.1223, "step": 9711 }, { "epoch": 0.5309824021869127, "grad_norm": 2.4483931064605713, "learning_rate": 4.742475773329814e-05, "loss": 1.0361, "step": 9712 }, { "epoch": 0.5310370750042713, "grad_norm": 2.24886155128479, "learning_rate": 4.7415915977532564e-05, "loss": 1.0487, "step": 9713 }, { "epoch": 0.5310917478216299, "grad_norm": 2.3393356800079346, "learning_rate": 4.740707430278867e-05, "loss": 1.0832, "step": 9714 }, { "epoch": 0.5311464206389885, "grad_norm": 2.6897618770599365, "learning_rate": 4.739823270934367e-05, "loss": 1.0234, "step": 9715 }, { "epoch": 0.5312010934563471, "grad_norm": 3.380488395690918, "learning_rate": 4.7389391197474794e-05, "loss": 0.9756, "step": 9716 }, { "epoch": 0.5312557662737057, "grad_norm": 3.000164747238159, "learning_rate": 4.738054976745925e-05, "loss": 1.1302, "step": 9717 }, { "epoch": 0.5313104390910645, "grad_norm": 2.9570369720458984, "learning_rate": 4.7371708419574255e-05, "loss": 1.0298, "step": 9718 }, { "epoch": 0.5313651119084231, "grad_norm": 2.742873191833496, "learning_rate": 4.7362867154097035e-05, "loss": 0.9351, "step": 9719 }, { "epoch": 0.5314197847257817, "grad_norm": 3.4529054164886475, "learning_rate": 4.7354025971304786e-05, "loss": 1.0066, "step": 9720 }, { "epoch": 0.5314744575431403, "grad_norm": 2.853416919708252, "learning_rate": 4.73451848714747e-05, "loss": 1.0836, "step": 9721 }, { "epoch": 0.5315291303604989, "grad_norm": 2.194859027862549, "learning_rate": 4.733634385488402e-05, "loss": 0.8408, "step": 9722 }, { "epoch": 0.5315838031778575, "grad_norm": 2.4808027744293213, "learning_rate": 4.7327502921809926e-05, "loss": 0.9646, "step": 9723 }, { "epoch": 0.5316384759952161, "grad_norm": 2.4118258953094482, "learning_rate": 4.7318662072529636e-05, "loss": 0.9777, "step": 9724 }, { "epoch": 0.5316931488125748, "grad_norm": 3.0437591075897217, "learning_rate": 4.730982130732032e-05, "loss": 1.0046, "step": 9725 }, { "epoch": 0.5317478216299334, "grad_norm": 2.037019729614258, "learning_rate": 4.73009806264592e-05, "loss": 0.9972, "step": 9726 }, { "epoch": 0.531802494447292, "grad_norm": 2.630587339401245, "learning_rate": 4.729214003022343e-05, "loss": 0.9884, "step": 9727 }, { "epoch": 0.5318571672646506, "grad_norm": 2.5582752227783203, "learning_rate": 4.728329951889025e-05, "loss": 1.1033, "step": 9728 }, { "epoch": 0.5319118400820092, "grad_norm": 3.2600903511047363, "learning_rate": 4.72744590927368e-05, "loss": 1.2679, "step": 9729 }, { "epoch": 0.5319665128993678, "grad_norm": 2.485714912414551, "learning_rate": 4.726561875204029e-05, "loss": 1.065, "step": 9730 }, { "epoch": 0.5320211857167265, "grad_norm": 2.6707615852355957, "learning_rate": 4.7256778497077874e-05, "loss": 0.9951, "step": 9731 }, { "epoch": 0.5320758585340851, "grad_norm": 2.478881597518921, "learning_rate": 4.7247938328126756e-05, "loss": 1.0317, "step": 9732 }, { "epoch": 0.5321305313514437, "grad_norm": 2.6693289279937744, "learning_rate": 4.723909824546411e-05, "loss": 1.0204, "step": 9733 }, { "epoch": 0.5321852041688023, "grad_norm": 2.5622148513793945, "learning_rate": 4.7230258249367116e-05, "loss": 0.9753, "step": 9734 }, { "epoch": 0.5322398769861609, "grad_norm": 2.729936361312866, "learning_rate": 4.7221418340112925e-05, "loss": 1.0288, "step": 9735 }, { "epoch": 0.5322945498035195, "grad_norm": 1.9929267168045044, "learning_rate": 4.7212578517978715e-05, "loss": 1.0329, "step": 9736 }, { "epoch": 0.5323492226208781, "grad_norm": 2.7119855880737305, "learning_rate": 4.720373878324165e-05, "loss": 1.0322, "step": 9737 }, { "epoch": 0.5324038954382369, "grad_norm": 2.85040283203125, "learning_rate": 4.719489913617889e-05, "loss": 0.9206, "step": 9738 }, { "epoch": 0.5324585682555955, "grad_norm": 2.2560863494873047, "learning_rate": 4.7186059577067596e-05, "loss": 1.0257, "step": 9739 }, { "epoch": 0.5325132410729541, "grad_norm": 2.4606471061706543, "learning_rate": 4.7177220106184905e-05, "loss": 0.9967, "step": 9740 }, { "epoch": 0.5325679138903127, "grad_norm": 3.8283791542053223, "learning_rate": 4.7168380723808e-05, "loss": 1.0559, "step": 9741 }, { "epoch": 0.5326225867076713, "grad_norm": 2.9581458568573, "learning_rate": 4.715954143021403e-05, "loss": 0.8916, "step": 9742 }, { "epoch": 0.5326772595250299, "grad_norm": 2.4605984687805176, "learning_rate": 4.715070222568013e-05, "loss": 1.0431, "step": 9743 }, { "epoch": 0.5327319323423885, "grad_norm": 2.780435085296631, "learning_rate": 4.7141863110483456e-05, "loss": 1.0895, "step": 9744 }, { "epoch": 0.5327866051597472, "grad_norm": 2.291919231414795, "learning_rate": 4.7133024084901124e-05, "loss": 0.9947, "step": 9745 }, { "epoch": 0.5328412779771058, "grad_norm": 2.5399866104125977, "learning_rate": 4.7124185149210306e-05, "loss": 0.9567, "step": 9746 }, { "epoch": 0.5328959507944644, "grad_norm": 2.5130374431610107, "learning_rate": 4.711534630368813e-05, "loss": 0.9077, "step": 9747 }, { "epoch": 0.532950623611823, "grad_norm": 2.523634910583496, "learning_rate": 4.7106507548611727e-05, "loss": 1.0301, "step": 9748 }, { "epoch": 0.5330052964291816, "grad_norm": 2.3208813667297363, "learning_rate": 4.7097668884258237e-05, "loss": 0.9096, "step": 9749 }, { "epoch": 0.5330599692465402, "grad_norm": 2.5593223571777344, "learning_rate": 4.7088830310904755e-05, "loss": 1.014, "step": 9750 }, { "epoch": 0.5331146420638988, "grad_norm": 2.44307541847229, "learning_rate": 4.707999182882845e-05, "loss": 1.0748, "step": 9751 }, { "epoch": 0.5331693148812575, "grad_norm": 3.711379051208496, "learning_rate": 4.707115343830643e-05, "loss": 0.9175, "step": 9752 }, { "epoch": 0.5332239876986161, "grad_norm": 2.444183349609375, "learning_rate": 4.706231513961581e-05, "loss": 0.9353, "step": 9753 }, { "epoch": 0.5332786605159747, "grad_norm": 2.0972111225128174, "learning_rate": 4.705347693303371e-05, "loss": 0.825, "step": 9754 }, { "epoch": 0.5333333333333333, "grad_norm": 2.4710094928741455, "learning_rate": 4.704463881883724e-05, "loss": 1.1664, "step": 9755 }, { "epoch": 0.5333880061506919, "grad_norm": 2.027160882949829, "learning_rate": 4.703580079730352e-05, "loss": 0.7423, "step": 9756 }, { "epoch": 0.5334426789680505, "grad_norm": 2.6506361961364746, "learning_rate": 4.7026962868709643e-05, "loss": 1.0952, "step": 9757 }, { "epoch": 0.5334973517854092, "grad_norm": 2.1555356979370117, "learning_rate": 4.701812503333273e-05, "loss": 0.9842, "step": 9758 }, { "epoch": 0.5335520246027678, "grad_norm": 2.8014936447143555, "learning_rate": 4.700928729144987e-05, "loss": 0.9686, "step": 9759 }, { "epoch": 0.5336066974201265, "grad_norm": 2.1976659297943115, "learning_rate": 4.7000449643338165e-05, "loss": 0.9436, "step": 9760 }, { "epoch": 0.533661370237485, "grad_norm": 4.234999179840088, "learning_rate": 4.699161208927474e-05, "loss": 0.8743, "step": 9761 }, { "epoch": 0.5337160430548437, "grad_norm": 2.9276390075683594, "learning_rate": 4.6982774629536654e-05, "loss": 1.1329, "step": 9762 }, { "epoch": 0.5337707158722023, "grad_norm": 2.7247393131256104, "learning_rate": 4.697393726440101e-05, "loss": 1.0356, "step": 9763 }, { "epoch": 0.5338253886895609, "grad_norm": 2.0790276527404785, "learning_rate": 4.6965099994144904e-05, "loss": 1.0318, "step": 9764 }, { "epoch": 0.5338800615069196, "grad_norm": 2.4121572971343994, "learning_rate": 4.69562628190454e-05, "loss": 1.0274, "step": 9765 }, { "epoch": 0.5339347343242782, "grad_norm": 3.3269152641296387, "learning_rate": 4.69474257393796e-05, "loss": 1.1448, "step": 9766 }, { "epoch": 0.5339894071416368, "grad_norm": 3.2874369621276855, "learning_rate": 4.693858875542457e-05, "loss": 1.1053, "step": 9767 }, { "epoch": 0.5340440799589954, "grad_norm": 2.2811872959136963, "learning_rate": 4.69297518674574e-05, "loss": 1.033, "step": 9768 }, { "epoch": 0.534098752776354, "grad_norm": 3.447573184967041, "learning_rate": 4.6920915075755145e-05, "loss": 1.1477, "step": 9769 }, { "epoch": 0.5341534255937126, "grad_norm": 2.2531023025512695, "learning_rate": 4.691207838059486e-05, "loss": 0.9601, "step": 9770 }, { "epoch": 0.5342080984110712, "grad_norm": 2.279039144515991, "learning_rate": 4.690324178225366e-05, "loss": 0.9152, "step": 9771 }, { "epoch": 0.5342627712284299, "grad_norm": 2.6323843002319336, "learning_rate": 4.6894405281008584e-05, "loss": 1.1556, "step": 9772 }, { "epoch": 0.5343174440457885, "grad_norm": 2.614262819290161, "learning_rate": 4.68855688771367e-05, "loss": 1.0794, "step": 9773 }, { "epoch": 0.5343721168631471, "grad_norm": 3.1186881065368652, "learning_rate": 4.687673257091505e-05, "loss": 0.8023, "step": 9774 }, { "epoch": 0.5344267896805057, "grad_norm": 4.0010480880737305, "learning_rate": 4.6867896362620695e-05, "loss": 1.1112, "step": 9775 }, { "epoch": 0.5344814624978643, "grad_norm": 3.998013496398926, "learning_rate": 4.6859060252530693e-05, "loss": 0.8289, "step": 9776 }, { "epoch": 0.5345361353152229, "grad_norm": 2.221714973449707, "learning_rate": 4.685022424092209e-05, "loss": 0.981, "step": 9777 }, { "epoch": 0.5345908081325815, "grad_norm": 2.6301381587982178, "learning_rate": 4.684138832807192e-05, "loss": 0.9747, "step": 9778 }, { "epoch": 0.5346454809499402, "grad_norm": 2.2332816123962402, "learning_rate": 4.683255251425724e-05, "loss": 1.0363, "step": 9779 }, { "epoch": 0.5347001537672988, "grad_norm": 3.47473406791687, "learning_rate": 4.6823716799755065e-05, "loss": 0.9698, "step": 9780 }, { "epoch": 0.5347548265846575, "grad_norm": 2.5796825885772705, "learning_rate": 4.681488118484247e-05, "loss": 1.2274, "step": 9781 }, { "epoch": 0.534809499402016, "grad_norm": 2.9540584087371826, "learning_rate": 4.680604566979646e-05, "loss": 1.0183, "step": 9782 }, { "epoch": 0.5348641722193747, "grad_norm": 2.8292181491851807, "learning_rate": 4.679721025489408e-05, "loss": 0.9474, "step": 9783 }, { "epoch": 0.5349188450367333, "grad_norm": 3.61492657661438, "learning_rate": 4.678837494041235e-05, "loss": 0.8853, "step": 9784 }, { "epoch": 0.534973517854092, "grad_norm": 2.4259092807769775, "learning_rate": 4.677953972662829e-05, "loss": 1.2086, "step": 9785 }, { "epoch": 0.5350281906714506, "grad_norm": 3.3820178508758545, "learning_rate": 4.677070461381892e-05, "loss": 0.9162, "step": 9786 }, { "epoch": 0.5350828634888092, "grad_norm": 2.739278554916382, "learning_rate": 4.676186960226127e-05, "loss": 0.9916, "step": 9787 }, { "epoch": 0.5351375363061678, "grad_norm": 2.552140712738037, "learning_rate": 4.6753034692232334e-05, "loss": 1.1287, "step": 9788 }, { "epoch": 0.5351922091235264, "grad_norm": 2.571026086807251, "learning_rate": 4.674419988400911e-05, "loss": 1.0401, "step": 9789 }, { "epoch": 0.535246881940885, "grad_norm": 2.2481637001037598, "learning_rate": 4.6735365177868656e-05, "loss": 1.0611, "step": 9790 }, { "epoch": 0.5353015547582436, "grad_norm": 2.09824538230896, "learning_rate": 4.6726530574087947e-05, "loss": 0.9458, "step": 9791 }, { "epoch": 0.5353562275756023, "grad_norm": 2.2794151306152344, "learning_rate": 4.671769607294398e-05, "loss": 1.1805, "step": 9792 }, { "epoch": 0.5354109003929609, "grad_norm": 3.4010610580444336, "learning_rate": 4.6708861674713767e-05, "loss": 1.0752, "step": 9793 }, { "epoch": 0.5354655732103195, "grad_norm": 2.6252455711364746, "learning_rate": 4.6700027379674296e-05, "loss": 0.9846, "step": 9794 }, { "epoch": 0.5355202460276781, "grad_norm": 1.8419805765151978, "learning_rate": 4.669119318810255e-05, "loss": 0.7624, "step": 9795 }, { "epoch": 0.5355749188450367, "grad_norm": 2.34621262550354, "learning_rate": 4.668235910027553e-05, "loss": 0.9753, "step": 9796 }, { "epoch": 0.5356295916623953, "grad_norm": 3.0827951431274414, "learning_rate": 4.667352511647021e-05, "loss": 0.9863, "step": 9797 }, { "epoch": 0.5356842644797539, "grad_norm": 2.4840049743652344, "learning_rate": 4.666469123696359e-05, "loss": 0.6598, "step": 9798 }, { "epoch": 0.5357389372971126, "grad_norm": 2.507683038711548, "learning_rate": 4.6655857462032604e-05, "loss": 0.869, "step": 9799 }, { "epoch": 0.5357936101144712, "grad_norm": 2.5619125366210938, "learning_rate": 4.664702379195428e-05, "loss": 0.9747, "step": 9800 }, { "epoch": 0.5358482829318298, "grad_norm": 2.4125001430511475, "learning_rate": 4.663819022700557e-05, "loss": 0.7101, "step": 9801 }, { "epoch": 0.5359029557491884, "grad_norm": 3.0559823513031006, "learning_rate": 4.662935676746344e-05, "loss": 1.3117, "step": 9802 }, { "epoch": 0.535957628566547, "grad_norm": 2.746975898742676, "learning_rate": 4.662052341360487e-05, "loss": 1.1253, "step": 9803 }, { "epoch": 0.5360123013839057, "grad_norm": 2.44889760017395, "learning_rate": 4.66116901657068e-05, "loss": 1.1407, "step": 9804 }, { "epoch": 0.5360669742012643, "grad_norm": 3.240601062774658, "learning_rate": 4.66028570240462e-05, "loss": 1.1983, "step": 9805 }, { "epoch": 0.536121647018623, "grad_norm": 2.615835189819336, "learning_rate": 4.659402398890001e-05, "loss": 1.0392, "step": 9806 }, { "epoch": 0.5361763198359816, "grad_norm": 2.3757994174957275, "learning_rate": 4.6585191060545215e-05, "loss": 1.0345, "step": 9807 }, { "epoch": 0.5362309926533402, "grad_norm": 2.7232439517974854, "learning_rate": 4.6576358239258735e-05, "loss": 1.1108, "step": 9808 }, { "epoch": 0.5362856654706988, "grad_norm": 3.843351364135742, "learning_rate": 4.65675255253175e-05, "loss": 0.8974, "step": 9809 }, { "epoch": 0.5363403382880574, "grad_norm": 2.6095402240753174, "learning_rate": 4.65586929189985e-05, "loss": 1.0121, "step": 9810 }, { "epoch": 0.536395011105416, "grad_norm": 2.7451353073120117, "learning_rate": 4.654986042057865e-05, "loss": 0.9213, "step": 9811 }, { "epoch": 0.5364496839227747, "grad_norm": 2.3134148120880127, "learning_rate": 4.654102803033489e-05, "loss": 1.0815, "step": 9812 }, { "epoch": 0.5365043567401333, "grad_norm": 1.8371622562408447, "learning_rate": 4.653219574854414e-05, "loss": 0.8881, "step": 9813 }, { "epoch": 0.5365590295574919, "grad_norm": 2.093592405319214, "learning_rate": 4.6523363575483334e-05, "loss": 0.834, "step": 9814 }, { "epoch": 0.5366137023748505, "grad_norm": 2.4466559886932373, "learning_rate": 4.65145315114294e-05, "loss": 1.0468, "step": 9815 }, { "epoch": 0.5366683751922091, "grad_norm": 2.1702964305877686, "learning_rate": 4.650569955665927e-05, "loss": 0.9244, "step": 9816 }, { "epoch": 0.5367230480095677, "grad_norm": 2.0683281421661377, "learning_rate": 4.6496867711449835e-05, "loss": 0.9549, "step": 9817 }, { "epoch": 0.5367777208269263, "grad_norm": 2.3322718143463135, "learning_rate": 4.6488035976078026e-05, "loss": 1.0118, "step": 9818 }, { "epoch": 0.536832393644285, "grad_norm": 2.1622469425201416, "learning_rate": 4.6479204350820736e-05, "loss": 0.8024, "step": 9819 }, { "epoch": 0.5368870664616436, "grad_norm": 3.0606436729431152, "learning_rate": 4.6470372835954906e-05, "loss": 1.0708, "step": 9820 }, { "epoch": 0.5369417392790022, "grad_norm": 2.6609952449798584, "learning_rate": 4.646154143175743e-05, "loss": 1.1281, "step": 9821 }, { "epoch": 0.5369964120963608, "grad_norm": 2.531975746154785, "learning_rate": 4.64527101385052e-05, "loss": 1.1281, "step": 9822 }, { "epoch": 0.5370510849137194, "grad_norm": 2.511762857437134, "learning_rate": 4.644387895647512e-05, "loss": 0.9794, "step": 9823 }, { "epoch": 0.537105757731078, "grad_norm": 2.831585168838501, "learning_rate": 4.6435047885944076e-05, "loss": 0.7833, "step": 9824 }, { "epoch": 0.5371604305484367, "grad_norm": 2.423907518386841, "learning_rate": 4.6426216927188966e-05, "loss": 1.0018, "step": 9825 }, { "epoch": 0.5372151033657954, "grad_norm": 2.690812349319458, "learning_rate": 4.641738608048667e-05, "loss": 1.1404, "step": 9826 }, { "epoch": 0.537269776183154, "grad_norm": 2.4244391918182373, "learning_rate": 4.640855534611408e-05, "loss": 1.0689, "step": 9827 }, { "epoch": 0.5373244490005126, "grad_norm": 2.8507728576660156, "learning_rate": 4.6399724724348066e-05, "loss": 1.1695, "step": 9828 }, { "epoch": 0.5373791218178712, "grad_norm": 3.01786470413208, "learning_rate": 4.63908942154655e-05, "loss": 1.056, "step": 9829 }, { "epoch": 0.5374337946352298, "grad_norm": 3.056818723678589, "learning_rate": 4.638206381974328e-05, "loss": 1.0724, "step": 9830 }, { "epoch": 0.5374884674525884, "grad_norm": 2.3840765953063965, "learning_rate": 4.637323353745825e-05, "loss": 0.9155, "step": 9831 }, { "epoch": 0.537543140269947, "grad_norm": 3.4510397911071777, "learning_rate": 4.6364403368887274e-05, "loss": 0.938, "step": 9832 }, { "epoch": 0.5375978130873057, "grad_norm": 3.329761028289795, "learning_rate": 4.635557331430725e-05, "loss": 1.132, "step": 9833 }, { "epoch": 0.5376524859046643, "grad_norm": 2.732173204421997, "learning_rate": 4.6346743373995e-05, "loss": 1.1965, "step": 9834 }, { "epoch": 0.5377071587220229, "grad_norm": 2.694725513458252, "learning_rate": 4.6337913548227396e-05, "loss": 0.9926, "step": 9835 }, { "epoch": 0.5377618315393815, "grad_norm": 3.3237287998199463, "learning_rate": 4.6329083837281284e-05, "loss": 1.153, "step": 9836 }, { "epoch": 0.5378165043567401, "grad_norm": 3.6698169708251953, "learning_rate": 4.6320254241433506e-05, "loss": 1.2031, "step": 9837 }, { "epoch": 0.5378711771740987, "grad_norm": 2.1125237941741943, "learning_rate": 4.631142476096092e-05, "loss": 0.7924, "step": 9838 }, { "epoch": 0.5379258499914574, "grad_norm": 3.2676312923431396, "learning_rate": 4.630259539614035e-05, "loss": 1.2229, "step": 9839 }, { "epoch": 0.537980522808816, "grad_norm": 2.322852849960327, "learning_rate": 4.629376614724865e-05, "loss": 0.8546, "step": 9840 }, { "epoch": 0.5380351956261746, "grad_norm": 2.467367649078369, "learning_rate": 4.6284937014562633e-05, "loss": 1.1333, "step": 9841 }, { "epoch": 0.5380898684435332, "grad_norm": 2.6035478115081787, "learning_rate": 4.627610799835915e-05, "loss": 1.1576, "step": 9842 }, { "epoch": 0.5381445412608918, "grad_norm": 2.3061470985412598, "learning_rate": 4.626727909891502e-05, "loss": 1.0582, "step": 9843 }, { "epoch": 0.5381992140782504, "grad_norm": 2.683835506439209, "learning_rate": 4.625845031650707e-05, "loss": 1.0584, "step": 9844 }, { "epoch": 0.538253886895609, "grad_norm": 2.4950332641601562, "learning_rate": 4.624962165141209e-05, "loss": 1.0852, "step": 9845 }, { "epoch": 0.5383085597129678, "grad_norm": 5.059168815612793, "learning_rate": 4.6240793103906935e-05, "loss": 1.3925, "step": 9846 }, { "epoch": 0.5383632325303264, "grad_norm": 1.9658961296081543, "learning_rate": 4.623196467426839e-05, "loss": 0.6902, "step": 9847 }, { "epoch": 0.538417905347685, "grad_norm": 2.5702426433563232, "learning_rate": 4.622313636277326e-05, "loss": 1.0222, "step": 9848 }, { "epoch": 0.5384725781650436, "grad_norm": 3.004037857055664, "learning_rate": 4.621430816969838e-05, "loss": 1.1732, "step": 9849 }, { "epoch": 0.5385272509824022, "grad_norm": 5.527766227722168, "learning_rate": 4.620548009532052e-05, "loss": 1.048, "step": 9850 }, { "epoch": 0.5385819237997608, "grad_norm": 7.373105049133301, "learning_rate": 4.619665213991649e-05, "loss": 0.9859, "step": 9851 }, { "epoch": 0.5386365966171194, "grad_norm": 3.571381092071533, "learning_rate": 4.618782430376308e-05, "loss": 0.9478, "step": 9852 }, { "epoch": 0.5386912694344781, "grad_norm": 3.4191417694091797, "learning_rate": 4.6178996587137085e-05, "loss": 0.989, "step": 9853 }, { "epoch": 0.5387459422518367, "grad_norm": 2.5487382411956787, "learning_rate": 4.617016899031528e-05, "loss": 0.9526, "step": 9854 }, { "epoch": 0.5388006150691953, "grad_norm": 4.025608062744141, "learning_rate": 4.616134151357444e-05, "loss": 1.1609, "step": 9855 }, { "epoch": 0.5388552878865539, "grad_norm": 2.619175672531128, "learning_rate": 4.6152514157191365e-05, "loss": 0.9245, "step": 9856 }, { "epoch": 0.5389099607039125, "grad_norm": 2.363248109817505, "learning_rate": 4.614368692144281e-05, "loss": 0.8209, "step": 9857 }, { "epoch": 0.5389646335212711, "grad_norm": 2.808295249938965, "learning_rate": 4.613485980660553e-05, "loss": 1.3683, "step": 9858 }, { "epoch": 0.5390193063386297, "grad_norm": 2.4820334911346436, "learning_rate": 4.612603281295634e-05, "loss": 1.111, "step": 9859 }, { "epoch": 0.5390739791559884, "grad_norm": 2.474212169647217, "learning_rate": 4.6117205940771976e-05, "loss": 1.0682, "step": 9860 }, { "epoch": 0.539128651973347, "grad_norm": 2.360513210296631, "learning_rate": 4.610837919032919e-05, "loss": 0.9259, "step": 9861 }, { "epoch": 0.5391833247907056, "grad_norm": 2.629102945327759, "learning_rate": 4.609955256190475e-05, "loss": 1.1066, "step": 9862 }, { "epoch": 0.5392379976080642, "grad_norm": 2.5528318881988525, "learning_rate": 4.60907260557754e-05, "loss": 0.9206, "step": 9863 }, { "epoch": 0.5392926704254228, "grad_norm": 2.3857383728027344, "learning_rate": 4.6081899672217884e-05, "loss": 0.9741, "step": 9864 }, { "epoch": 0.5393473432427814, "grad_norm": 2.875258445739746, "learning_rate": 4.607307341150895e-05, "loss": 1.0422, "step": 9865 }, { "epoch": 0.53940201606014, "grad_norm": 2.7787797451019287, "learning_rate": 4.606424727392534e-05, "loss": 1.0506, "step": 9866 }, { "epoch": 0.5394566888774988, "grad_norm": 2.2684080600738525, "learning_rate": 4.605542125974379e-05, "loss": 1.2145, "step": 9867 }, { "epoch": 0.5395113616948574, "grad_norm": 3.875270366668701, "learning_rate": 4.6046595369241e-05, "loss": 0.9264, "step": 9868 }, { "epoch": 0.539566034512216, "grad_norm": 3.102518320083618, "learning_rate": 4.6037769602693754e-05, "loss": 1.0713, "step": 9869 }, { "epoch": 0.5396207073295746, "grad_norm": 3.0290298461914062, "learning_rate": 4.602894396037875e-05, "loss": 1.1207, "step": 9870 }, { "epoch": 0.5396753801469332, "grad_norm": 2.7536048889160156, "learning_rate": 4.602011844257271e-05, "loss": 1.0738, "step": 9871 }, { "epoch": 0.5397300529642918, "grad_norm": 2.5690066814422607, "learning_rate": 4.601129304955234e-05, "loss": 1.1193, "step": 9872 }, { "epoch": 0.5397847257816505, "grad_norm": 2.512847900390625, "learning_rate": 4.600246778159436e-05, "loss": 1.1381, "step": 9873 }, { "epoch": 0.5398393985990091, "grad_norm": 2.306866407394409, "learning_rate": 4.599364263897548e-05, "loss": 0.7754, "step": 9874 }, { "epoch": 0.5398940714163677, "grad_norm": 2.4741058349609375, "learning_rate": 4.598481762197241e-05, "loss": 0.9177, "step": 9875 }, { "epoch": 0.5399487442337263, "grad_norm": 4.9492669105529785, "learning_rate": 4.5975992730861836e-05, "loss": 0.9858, "step": 9876 }, { "epoch": 0.5400034170510849, "grad_norm": 2.4738993644714355, "learning_rate": 4.5967167965920465e-05, "loss": 1.0634, "step": 9877 }, { "epoch": 0.5400580898684435, "grad_norm": 2.9574344158172607, "learning_rate": 4.595834332742497e-05, "loss": 1.2037, "step": 9878 }, { "epoch": 0.5401127626858021, "grad_norm": 2.288666248321533, "learning_rate": 4.594951881565207e-05, "loss": 0.9994, "step": 9879 }, { "epoch": 0.5401674355031608, "grad_norm": 2.8512487411499023, "learning_rate": 4.5940694430878446e-05, "loss": 1.0803, "step": 9880 }, { "epoch": 0.5402221083205194, "grad_norm": 3.290311336517334, "learning_rate": 4.5931870173380764e-05, "loss": 0.9581, "step": 9881 }, { "epoch": 0.540276781137878, "grad_norm": 2.7669975757598877, "learning_rate": 4.59230460434357e-05, "loss": 1.0299, "step": 9882 }, { "epoch": 0.5403314539552366, "grad_norm": 2.532066583633423, "learning_rate": 4.591422204131994e-05, "loss": 0.9553, "step": 9883 }, { "epoch": 0.5403861267725952, "grad_norm": 2.557126045227051, "learning_rate": 4.590539816731015e-05, "loss": 1.0322, "step": 9884 }, { "epoch": 0.5404407995899538, "grad_norm": 2.6530709266662598, "learning_rate": 4.589657442168299e-05, "loss": 1.039, "step": 9885 }, { "epoch": 0.5404954724073124, "grad_norm": 2.4412169456481934, "learning_rate": 4.588775080471512e-05, "loss": 1.1365, "step": 9886 }, { "epoch": 0.5405501452246712, "grad_norm": 3.4897310733795166, "learning_rate": 4.5878927316683196e-05, "loss": 0.9138, "step": 9887 }, { "epoch": 0.5406048180420298, "grad_norm": 2.9584391117095947, "learning_rate": 4.5870103957863856e-05, "loss": 0.9526, "step": 9888 }, { "epoch": 0.5406594908593884, "grad_norm": 2.66583514213562, "learning_rate": 4.5861280728533776e-05, "loss": 1.1247, "step": 9889 }, { "epoch": 0.540714163676747, "grad_norm": 2.6651721000671387, "learning_rate": 4.5852457628969605e-05, "loss": 1.0595, "step": 9890 }, { "epoch": 0.5407688364941056, "grad_norm": 3.384992837905884, "learning_rate": 4.584363465944796e-05, "loss": 1.1302, "step": 9891 }, { "epoch": 0.5408235093114642, "grad_norm": 2.4674272537231445, "learning_rate": 4.583481182024548e-05, "loss": 0.9633, "step": 9892 }, { "epoch": 0.5408781821288228, "grad_norm": 2.7070789337158203, "learning_rate": 4.5825989111638815e-05, "loss": 1.2233, "step": 9893 }, { "epoch": 0.5409328549461815, "grad_norm": 1.9285069704055786, "learning_rate": 4.581716653390458e-05, "loss": 0.8023, "step": 9894 }, { "epoch": 0.5409875277635401, "grad_norm": 2.1502325534820557, "learning_rate": 4.58083440873194e-05, "loss": 0.9456, "step": 9895 }, { "epoch": 0.5410422005808987, "grad_norm": 2.3947603702545166, "learning_rate": 4.5799521772159895e-05, "loss": 1.0473, "step": 9896 }, { "epoch": 0.5410968733982573, "grad_norm": 2.4685187339782715, "learning_rate": 4.5790699588702656e-05, "loss": 1.1524, "step": 9897 }, { "epoch": 0.5411515462156159, "grad_norm": 2.3388383388519287, "learning_rate": 4.578187753722435e-05, "loss": 1.0076, "step": 9898 }, { "epoch": 0.5412062190329745, "grad_norm": 2.9186222553253174, "learning_rate": 4.577305561800155e-05, "loss": 1.0758, "step": 9899 }, { "epoch": 0.5412608918503332, "grad_norm": 2.845759153366089, "learning_rate": 4.5764233831310865e-05, "loss": 1.2882, "step": 9900 }, { "epoch": 0.5413155646676918, "grad_norm": 3.030702829360962, "learning_rate": 4.57554121774289e-05, "loss": 0.9487, "step": 9901 }, { "epoch": 0.5413702374850504, "grad_norm": 2.513608694076538, "learning_rate": 4.574659065663223e-05, "loss": 1.0307, "step": 9902 }, { "epoch": 0.541424910302409, "grad_norm": 2.5761702060699463, "learning_rate": 4.5737769269197475e-05, "loss": 0.9977, "step": 9903 }, { "epoch": 0.5414795831197676, "grad_norm": 2.4222352504730225, "learning_rate": 4.57289480154012e-05, "loss": 0.8618, "step": 9904 }, { "epoch": 0.5415342559371262, "grad_norm": 2.582996368408203, "learning_rate": 4.572012689552e-05, "loss": 1.0386, "step": 9905 }, { "epoch": 0.5415889287544848, "grad_norm": 2.5206868648529053, "learning_rate": 4.571130590983044e-05, "loss": 0.8947, "step": 9906 }, { "epoch": 0.5416436015718435, "grad_norm": 2.6964101791381836, "learning_rate": 4.5702485058609093e-05, "loss": 0.8964, "step": 9907 }, { "epoch": 0.5416982743892022, "grad_norm": 3.4844954013824463, "learning_rate": 4.5693664342132546e-05, "loss": 1.0704, "step": 9908 }, { "epoch": 0.5417529472065608, "grad_norm": 3.758699655532837, "learning_rate": 4.568484376067737e-05, "loss": 0.901, "step": 9909 }, { "epoch": 0.5418076200239194, "grad_norm": 2.571211814880371, "learning_rate": 4.56760233145201e-05, "loss": 1.0156, "step": 9910 }, { "epoch": 0.541862292841278, "grad_norm": 3.8510310649871826, "learning_rate": 4.566720300393732e-05, "loss": 1.111, "step": 9911 }, { "epoch": 0.5419169656586366, "grad_norm": 2.870448350906372, "learning_rate": 4.565838282920556e-05, "loss": 1.0236, "step": 9912 }, { "epoch": 0.5419716384759952, "grad_norm": 2.859294891357422, "learning_rate": 4.564956279060138e-05, "loss": 1.1331, "step": 9913 }, { "epoch": 0.5420263112933539, "grad_norm": 1.9610892534255981, "learning_rate": 4.564074288840133e-05, "loss": 0.9317, "step": 9914 }, { "epoch": 0.5420809841107125, "grad_norm": 2.8342344760894775, "learning_rate": 4.5631923122881945e-05, "loss": 1.16, "step": 9915 }, { "epoch": 0.5421356569280711, "grad_norm": 3.472011089324951, "learning_rate": 4.5623103494319756e-05, "loss": 1.1795, "step": 9916 }, { "epoch": 0.5421903297454297, "grad_norm": 2.2529070377349854, "learning_rate": 4.5614284002991284e-05, "loss": 1.0077, "step": 9917 }, { "epoch": 0.5422450025627883, "grad_norm": 2.289177656173706, "learning_rate": 4.560546464917309e-05, "loss": 0.9972, "step": 9918 }, { "epoch": 0.5422996753801469, "grad_norm": 3.490976333618164, "learning_rate": 4.559664543314166e-05, "loss": 1.0658, "step": 9919 }, { "epoch": 0.5423543481975055, "grad_norm": 2.4626872539520264, "learning_rate": 4.558782635517355e-05, "loss": 0.9675, "step": 9920 }, { "epoch": 0.5424090210148642, "grad_norm": 2.7757627964019775, "learning_rate": 4.557900741554524e-05, "loss": 0.9835, "step": 9921 }, { "epoch": 0.5424636938322228, "grad_norm": 2.4528403282165527, "learning_rate": 4.5570188614533266e-05, "loss": 0.9633, "step": 9922 }, { "epoch": 0.5425183666495814, "grad_norm": 3.4577407836914062, "learning_rate": 4.556136995241412e-05, "loss": 1.0618, "step": 9923 }, { "epoch": 0.54257303946694, "grad_norm": 2.2945139408111572, "learning_rate": 4.5552551429464306e-05, "loss": 0.9016, "step": 9924 }, { "epoch": 0.5426277122842986, "grad_norm": 1.981272578239441, "learning_rate": 4.5543733045960325e-05, "loss": 0.9572, "step": 9925 }, { "epoch": 0.5426823851016572, "grad_norm": 2.2261600494384766, "learning_rate": 4.553491480217866e-05, "loss": 1.0584, "step": 9926 }, { "epoch": 0.5427370579190159, "grad_norm": 3.97570538520813, "learning_rate": 4.5526096698395796e-05, "loss": 1.152, "step": 9927 }, { "epoch": 0.5427917307363745, "grad_norm": 3.2690048217773438, "learning_rate": 4.5517278734888237e-05, "loss": 1.1089, "step": 9928 }, { "epoch": 0.5428464035537331, "grad_norm": 2.364675998687744, "learning_rate": 4.550846091193245e-05, "loss": 1.0952, "step": 9929 }, { "epoch": 0.5429010763710918, "grad_norm": 2.624072790145874, "learning_rate": 4.5499643229804916e-05, "loss": 1.0859, "step": 9930 }, { "epoch": 0.5429557491884504, "grad_norm": 2.251692295074463, "learning_rate": 4.5490825688782104e-05, "loss": 0.9099, "step": 9931 }, { "epoch": 0.543010422005809, "grad_norm": 2.881380319595337, "learning_rate": 4.5482008289140454e-05, "loss": 1.0425, "step": 9932 }, { "epoch": 0.5430650948231676, "grad_norm": 3.009481906890869, "learning_rate": 4.547319103115647e-05, "loss": 1.1135, "step": 9933 }, { "epoch": 0.5431197676405263, "grad_norm": 2.8671064376831055, "learning_rate": 4.546437391510659e-05, "loss": 0.9878, "step": 9934 }, { "epoch": 0.5431744404578849, "grad_norm": 3.464885950088501, "learning_rate": 4.545555694126727e-05, "loss": 1.003, "step": 9935 }, { "epoch": 0.5432291132752435, "grad_norm": 2.5147695541381836, "learning_rate": 4.5446740109914955e-05, "loss": 0.8883, "step": 9936 }, { "epoch": 0.5432837860926021, "grad_norm": 3.1680943965911865, "learning_rate": 4.543792342132607e-05, "loss": 1.2662, "step": 9937 }, { "epoch": 0.5433384589099607, "grad_norm": 2.535961389541626, "learning_rate": 4.5429106875777097e-05, "loss": 0.9894, "step": 9938 }, { "epoch": 0.5433931317273193, "grad_norm": 2.6936066150665283, "learning_rate": 4.5420290473544444e-05, "loss": 1.0615, "step": 9939 }, { "epoch": 0.5434478045446779, "grad_norm": 3.6995034217834473, "learning_rate": 4.5411474214904543e-05, "loss": 0.8821, "step": 9940 }, { "epoch": 0.5435024773620366, "grad_norm": 2.710261106491089, "learning_rate": 4.5402658100133826e-05, "loss": 1.2139, "step": 9941 }, { "epoch": 0.5435571501793952, "grad_norm": 2.134211778640747, "learning_rate": 4.5393842129508716e-05, "loss": 1.0208, "step": 9942 }, { "epoch": 0.5436118229967538, "grad_norm": 2.430196762084961, "learning_rate": 4.5385026303305616e-05, "loss": 1.0102, "step": 9943 }, { "epoch": 0.5436664958141124, "grad_norm": 2.86659836769104, "learning_rate": 4.537621062180095e-05, "loss": 1.0831, "step": 9944 }, { "epoch": 0.543721168631471, "grad_norm": 2.3142714500427246, "learning_rate": 4.5367395085271113e-05, "loss": 1.0077, "step": 9945 }, { "epoch": 0.5437758414488296, "grad_norm": 2.431317090988159, "learning_rate": 4.5358579693992524e-05, "loss": 0.9571, "step": 9946 }, { "epoch": 0.5438305142661882, "grad_norm": 2.478902816772461, "learning_rate": 4.534976444824158e-05, "loss": 0.8244, "step": 9947 }, { "epoch": 0.5438851870835469, "grad_norm": 2.799922227859497, "learning_rate": 4.534094934829468e-05, "loss": 1.1753, "step": 9948 }, { "epoch": 0.5439398599009055, "grad_norm": 2.9134464263916016, "learning_rate": 4.53321343944282e-05, "loss": 1.0558, "step": 9949 }, { "epoch": 0.5439945327182641, "grad_norm": 4.212754726409912, "learning_rate": 4.532331958691854e-05, "loss": 0.7827, "step": 9950 }, { "epoch": 0.5440492055356227, "grad_norm": 2.6497340202331543, "learning_rate": 4.5314504926042065e-05, "loss": 0.9852, "step": 9951 }, { "epoch": 0.5441038783529814, "grad_norm": 2.4403598308563232, "learning_rate": 4.530569041207516e-05, "loss": 0.9024, "step": 9952 }, { "epoch": 0.54415855117034, "grad_norm": 2.359140157699585, "learning_rate": 4.529687604529419e-05, "loss": 0.9868, "step": 9953 }, { "epoch": 0.5442132239876987, "grad_norm": 3.2456634044647217, "learning_rate": 4.528806182597552e-05, "loss": 1.0548, "step": 9954 }, { "epoch": 0.5442678968050573, "grad_norm": 2.530679225921631, "learning_rate": 4.527924775439553e-05, "loss": 1.0991, "step": 9955 }, { "epoch": 0.5443225696224159, "grad_norm": 2.5146780014038086, "learning_rate": 4.527043383083054e-05, "loss": 1.1744, "step": 9956 }, { "epoch": 0.5443772424397745, "grad_norm": 2.442106246948242, "learning_rate": 4.526162005555695e-05, "loss": 1.1096, "step": 9957 }, { "epoch": 0.5444319152571331, "grad_norm": 2.6039421558380127, "learning_rate": 4.525280642885108e-05, "loss": 1.0955, "step": 9958 }, { "epoch": 0.5444865880744917, "grad_norm": 3.4334394931793213, "learning_rate": 4.524399295098928e-05, "loss": 1.2435, "step": 9959 }, { "epoch": 0.5445412608918503, "grad_norm": 2.4236273765563965, "learning_rate": 4.52351796222479e-05, "loss": 1.0632, "step": 9960 }, { "epoch": 0.544595933709209, "grad_norm": 2.896811008453369, "learning_rate": 4.5226366442903253e-05, "loss": 1.1986, "step": 9961 }, { "epoch": 0.5446506065265676, "grad_norm": 3.19537091255188, "learning_rate": 4.5217553413231675e-05, "loss": 1.1633, "step": 9962 }, { "epoch": 0.5447052793439262, "grad_norm": 2.658235788345337, "learning_rate": 4.52087405335095e-05, "loss": 1.1569, "step": 9963 }, { "epoch": 0.5447599521612848, "grad_norm": 2.5503053665161133, "learning_rate": 4.519992780401304e-05, "loss": 1.0173, "step": 9964 }, { "epoch": 0.5448146249786434, "grad_norm": 3.7313833236694336, "learning_rate": 4.519111522501861e-05, "loss": 1.0038, "step": 9965 }, { "epoch": 0.544869297796002, "grad_norm": 3.9415371417999268, "learning_rate": 4.51823027968025e-05, "loss": 1.038, "step": 9966 }, { "epoch": 0.5449239706133606, "grad_norm": 2.0477752685546875, "learning_rate": 4.517349051964106e-05, "loss": 0.9372, "step": 9967 }, { "epoch": 0.5449786434307193, "grad_norm": 2.5465290546417236, "learning_rate": 4.516467839381057e-05, "loss": 1.0993, "step": 9968 }, { "epoch": 0.5450333162480779, "grad_norm": 2.6032981872558594, "learning_rate": 4.515586641958733e-05, "loss": 1.1694, "step": 9969 }, { "epoch": 0.5450879890654365, "grad_norm": 2.5674209594726562, "learning_rate": 4.514705459724763e-05, "loss": 1.0964, "step": 9970 }, { "epoch": 0.5451426618827951, "grad_norm": 2.051086664199829, "learning_rate": 4.513824292706775e-05, "loss": 0.8482, "step": 9971 }, { "epoch": 0.5451973347001537, "grad_norm": 2.480954647064209, "learning_rate": 4.512943140932398e-05, "loss": 1.1488, "step": 9972 }, { "epoch": 0.5452520075175123, "grad_norm": 2.5932531356811523, "learning_rate": 4.51206200442926e-05, "loss": 1.1848, "step": 9973 }, { "epoch": 0.545306680334871, "grad_norm": 2.3448386192321777, "learning_rate": 4.511180883224986e-05, "loss": 1.0394, "step": 9974 }, { "epoch": 0.5453613531522297, "grad_norm": 3.415750026702881, "learning_rate": 4.5102997773472056e-05, "loss": 1.0195, "step": 9975 }, { "epoch": 0.5454160259695883, "grad_norm": 3.0846500396728516, "learning_rate": 4.5094186868235416e-05, "loss": 1.0551, "step": 9976 }, { "epoch": 0.5454706987869469, "grad_norm": 2.8505849838256836, "learning_rate": 4.5085376116816246e-05, "loss": 1.0415, "step": 9977 }, { "epoch": 0.5455253716043055, "grad_norm": 2.9504313468933105, "learning_rate": 4.5076565519490774e-05, "loss": 1.0011, "step": 9978 }, { "epoch": 0.5455800444216641, "grad_norm": 1.9499369859695435, "learning_rate": 4.5067755076535254e-05, "loss": 0.9564, "step": 9979 }, { "epoch": 0.5456347172390227, "grad_norm": 2.3464181423187256, "learning_rate": 4.505894478822592e-05, "loss": 1.0346, "step": 9980 }, { "epoch": 0.5456893900563814, "grad_norm": 2.3108043670654297, "learning_rate": 4.5050134654839014e-05, "loss": 1.0539, "step": 9981 }, { "epoch": 0.54574406287374, "grad_norm": 1.9194544553756714, "learning_rate": 4.504132467665078e-05, "loss": 0.859, "step": 9982 }, { "epoch": 0.5457987356910986, "grad_norm": 2.5840179920196533, "learning_rate": 4.503251485393743e-05, "loss": 1.0054, "step": 9983 }, { "epoch": 0.5458534085084572, "grad_norm": 2.236428737640381, "learning_rate": 4.5023705186975206e-05, "loss": 1.0674, "step": 9984 }, { "epoch": 0.5459080813258158, "grad_norm": 2.478926181793213, "learning_rate": 4.5014895676040314e-05, "loss": 1.0704, "step": 9985 }, { "epoch": 0.5459627541431744, "grad_norm": 2.5208778381347656, "learning_rate": 4.500608632140895e-05, "loss": 0.9309, "step": 9986 }, { "epoch": 0.546017426960533, "grad_norm": 2.8418710231781006, "learning_rate": 4.499727712335737e-05, "loss": 1.0448, "step": 9987 }, { "epoch": 0.5460720997778917, "grad_norm": 2.6729166507720947, "learning_rate": 4.498846808216176e-05, "loss": 1.0692, "step": 9988 }, { "epoch": 0.5461267725952503, "grad_norm": 2.1581101417541504, "learning_rate": 4.497965919809831e-05, "loss": 1.0745, "step": 9989 }, { "epoch": 0.5461814454126089, "grad_norm": 2.507079601287842, "learning_rate": 4.497085047144323e-05, "loss": 1.1146, "step": 9990 }, { "epoch": 0.5462361182299675, "grad_norm": 2.7606096267700195, "learning_rate": 4.496204190247269e-05, "loss": 1.0471, "step": 9991 }, { "epoch": 0.5462907910473261, "grad_norm": 3.4630675315856934, "learning_rate": 4.495323349146289e-05, "loss": 1.1687, "step": 9992 }, { "epoch": 0.5463454638646847, "grad_norm": 3.7090578079223633, "learning_rate": 4.494442523869e-05, "loss": 1.0004, "step": 9993 }, { "epoch": 0.5464001366820433, "grad_norm": 2.309988498687744, "learning_rate": 4.49356171444302e-05, "loss": 0.982, "step": 9994 }, { "epoch": 0.5464548094994021, "grad_norm": 3.480496644973755, "learning_rate": 4.492680920895966e-05, "loss": 1.0915, "step": 9995 }, { "epoch": 0.5465094823167607, "grad_norm": 2.120620012283325, "learning_rate": 4.491800143255453e-05, "loss": 0.8625, "step": 9996 }, { "epoch": 0.5465641551341193, "grad_norm": 2.9825901985168457, "learning_rate": 4.4909193815491e-05, "loss": 1.1894, "step": 9997 }, { "epoch": 0.5466188279514779, "grad_norm": 2.599862575531006, "learning_rate": 4.490038635804521e-05, "loss": 1.0134, "step": 9998 }, { "epoch": 0.5466735007688365, "grad_norm": 2.533151626586914, "learning_rate": 4.4891579060493316e-05, "loss": 0.9671, "step": 9999 }, { "epoch": 0.5467281735861951, "grad_norm": 2.680510997772217, "learning_rate": 4.488277192311145e-05, "loss": 0.9878, "step": 10000 }, { "epoch": 0.5467828464035537, "grad_norm": 2.3909735679626465, "learning_rate": 4.487396494617576e-05, "loss": 0.9211, "step": 10001 }, { "epoch": 0.5468375192209124, "grad_norm": 2.208702325820923, "learning_rate": 4.486515812996239e-05, "loss": 0.999, "step": 10002 }, { "epoch": 0.546892192038271, "grad_norm": 2.7711095809936523, "learning_rate": 4.485635147474745e-05, "loss": 1.0299, "step": 10003 }, { "epoch": 0.5469468648556296, "grad_norm": 3.0069539546966553, "learning_rate": 4.484754498080708e-05, "loss": 0.9603, "step": 10004 }, { "epoch": 0.5470015376729882, "grad_norm": 2.3029391765594482, "learning_rate": 4.483873864841738e-05, "loss": 1.0088, "step": 10005 }, { "epoch": 0.5470562104903468, "grad_norm": 2.40031361579895, "learning_rate": 4.4829932477854474e-05, "loss": 0.9498, "step": 10006 }, { "epoch": 0.5471108833077054, "grad_norm": 2.5852255821228027, "learning_rate": 4.48211264693945e-05, "loss": 0.9734, "step": 10007 }, { "epoch": 0.5471655561250641, "grad_norm": 2.8529956340789795, "learning_rate": 4.4812320623313534e-05, "loss": 0.9688, "step": 10008 }, { "epoch": 0.5472202289424227, "grad_norm": 2.475066900253296, "learning_rate": 4.480351493988768e-05, "loss": 1.0034, "step": 10009 }, { "epoch": 0.5472749017597813, "grad_norm": 2.6021716594696045, "learning_rate": 4.479470941939304e-05, "loss": 1.1152, "step": 10010 }, { "epoch": 0.5473295745771399, "grad_norm": 3.1026735305786133, "learning_rate": 4.4785904062105694e-05, "loss": 1.0126, "step": 10011 }, { "epoch": 0.5473842473944985, "grad_norm": 2.9927470684051514, "learning_rate": 4.477709886830173e-05, "loss": 0.9304, "step": 10012 }, { "epoch": 0.5474389202118571, "grad_norm": 2.6741178035736084, "learning_rate": 4.476829383825722e-05, "loss": 1.1361, "step": 10013 }, { "epoch": 0.5474935930292157, "grad_norm": 2.2292885780334473, "learning_rate": 4.475948897224826e-05, "loss": 0.8987, "step": 10014 }, { "epoch": 0.5475482658465745, "grad_norm": 2.3484628200531006, "learning_rate": 4.475068427055088e-05, "loss": 0.9472, "step": 10015 }, { "epoch": 0.5476029386639331, "grad_norm": 3.041321039199829, "learning_rate": 4.474187973344118e-05, "loss": 1.0637, "step": 10016 }, { "epoch": 0.5476576114812917, "grad_norm": 2.1073732376098633, "learning_rate": 4.473307536119521e-05, "loss": 1.1701, "step": 10017 }, { "epoch": 0.5477122842986503, "grad_norm": 2.374349594116211, "learning_rate": 4.472427115408902e-05, "loss": 0.8404, "step": 10018 }, { "epoch": 0.5477669571160089, "grad_norm": 2.195373773574829, "learning_rate": 4.471546711239864e-05, "loss": 1.0002, "step": 10019 }, { "epoch": 0.5478216299333675, "grad_norm": 1.9730709791183472, "learning_rate": 4.470666323640014e-05, "loss": 0.9602, "step": 10020 }, { "epoch": 0.5478763027507261, "grad_norm": 2.6745615005493164, "learning_rate": 4.469785952636955e-05, "loss": 1.1636, "step": 10021 }, { "epoch": 0.5479309755680848, "grad_norm": 2.684149742126465, "learning_rate": 4.468905598258291e-05, "loss": 0.9131, "step": 10022 }, { "epoch": 0.5479856483854434, "grad_norm": 1.8601785898208618, "learning_rate": 4.468025260531622e-05, "loss": 0.81, "step": 10023 }, { "epoch": 0.548040321202802, "grad_norm": 2.559952974319458, "learning_rate": 4.4671449394845535e-05, "loss": 0.9821, "step": 10024 }, { "epoch": 0.5480949940201606, "grad_norm": 2.7838094234466553, "learning_rate": 4.466264635144683e-05, "loss": 1.0227, "step": 10025 }, { "epoch": 0.5481496668375192, "grad_norm": 2.44677734375, "learning_rate": 4.4653843475396164e-05, "loss": 1.0642, "step": 10026 }, { "epoch": 0.5482043396548778, "grad_norm": 3.0213828086853027, "learning_rate": 4.464504076696952e-05, "loss": 1.2006, "step": 10027 }, { "epoch": 0.5482590124722364, "grad_norm": 2.5980420112609863, "learning_rate": 4.463623822644291e-05, "loss": 0.9395, "step": 10028 }, { "epoch": 0.5483136852895951, "grad_norm": 1.968849539756775, "learning_rate": 4.462743585409232e-05, "loss": 0.9907, "step": 10029 }, { "epoch": 0.5483683581069537, "grad_norm": 2.9258737564086914, "learning_rate": 4.4618633650193736e-05, "loss": 0.9055, "step": 10030 }, { "epoch": 0.5484230309243123, "grad_norm": 2.2892110347747803, "learning_rate": 4.4609831615023155e-05, "loss": 1.0274, "step": 10031 }, { "epoch": 0.5484777037416709, "grad_norm": 2.865370750427246, "learning_rate": 4.460102974885654e-05, "loss": 1.2694, "step": 10032 }, { "epoch": 0.5485323765590295, "grad_norm": 2.1563262939453125, "learning_rate": 4.459222805196989e-05, "loss": 0.8513, "step": 10033 }, { "epoch": 0.5485870493763881, "grad_norm": 2.861171245574951, "learning_rate": 4.458342652463915e-05, "loss": 0.9801, "step": 10034 }, { "epoch": 0.5486417221937469, "grad_norm": 2.3529486656188965, "learning_rate": 4.45746251671403e-05, "loss": 0.8702, "step": 10035 }, { "epoch": 0.5486963950111055, "grad_norm": 3.3158907890319824, "learning_rate": 4.45658239797493e-05, "loss": 0.9943, "step": 10036 }, { "epoch": 0.5487510678284641, "grad_norm": 2.9064292907714844, "learning_rate": 4.45570229627421e-05, "loss": 1.1372, "step": 10037 }, { "epoch": 0.5488057406458227, "grad_norm": 2.475527763366699, "learning_rate": 4.454822211639464e-05, "loss": 1.0531, "step": 10038 }, { "epoch": 0.5488604134631813, "grad_norm": 4.479443073272705, "learning_rate": 4.453942144098288e-05, "loss": 1.2272, "step": 10039 }, { "epoch": 0.5489150862805399, "grad_norm": 2.7032644748687744, "learning_rate": 4.453062093678275e-05, "loss": 0.9948, "step": 10040 }, { "epoch": 0.5489697590978985, "grad_norm": 2.745303153991699, "learning_rate": 4.452182060407017e-05, "loss": 0.9054, "step": 10041 }, { "epoch": 0.5490244319152572, "grad_norm": 3.7525761127471924, "learning_rate": 4.451302044312107e-05, "loss": 1.0063, "step": 10042 }, { "epoch": 0.5490791047326158, "grad_norm": 2.4880712032318115, "learning_rate": 4.450422045421139e-05, "loss": 1.1198, "step": 10043 }, { "epoch": 0.5491337775499744, "grad_norm": 3.1285321712493896, "learning_rate": 4.449542063761702e-05, "loss": 1.0589, "step": 10044 }, { "epoch": 0.549188450367333, "grad_norm": 2.8505492210388184, "learning_rate": 4.448662099361387e-05, "loss": 0.9097, "step": 10045 }, { "epoch": 0.5492431231846916, "grad_norm": 2.9788923263549805, "learning_rate": 4.447782152247788e-05, "loss": 1.0166, "step": 10046 }, { "epoch": 0.5492977960020502, "grad_norm": 2.2847886085510254, "learning_rate": 4.4469022224484925e-05, "loss": 0.9081, "step": 10047 }, { "epoch": 0.5493524688194088, "grad_norm": 2.131443500518799, "learning_rate": 4.4460223099910905e-05, "loss": 1.0816, "step": 10048 }, { "epoch": 0.5494071416367675, "grad_norm": 2.440868377685547, "learning_rate": 4.44514241490317e-05, "loss": 0.9509, "step": 10049 }, { "epoch": 0.5494618144541261, "grad_norm": 3.15267014503479, "learning_rate": 4.4442625372123206e-05, "loss": 0.9886, "step": 10050 }, { "epoch": 0.5495164872714847, "grad_norm": 2.307255506515503, "learning_rate": 4.443382676946129e-05, "loss": 0.8288, "step": 10051 }, { "epoch": 0.5495711600888433, "grad_norm": 2.807551860809326, "learning_rate": 4.442502834132183e-05, "loss": 1.2328, "step": 10052 }, { "epoch": 0.5496258329062019, "grad_norm": 3.2470743656158447, "learning_rate": 4.4416230087980694e-05, "loss": 0.9681, "step": 10053 }, { "epoch": 0.5496805057235605, "grad_norm": 2.6146044731140137, "learning_rate": 4.440743200971372e-05, "loss": 1.0299, "step": 10054 }, { "epoch": 0.5497351785409191, "grad_norm": 2.5128684043884277, "learning_rate": 4.43986341067968e-05, "loss": 0.9023, "step": 10055 }, { "epoch": 0.5497898513582778, "grad_norm": 2.1247498989105225, "learning_rate": 4.438983637950578e-05, "loss": 0.9348, "step": 10056 }, { "epoch": 0.5498445241756365, "grad_norm": 2.3731746673583984, "learning_rate": 4.4381038828116484e-05, "loss": 1.0832, "step": 10057 }, { "epoch": 0.549899196992995, "grad_norm": 2.8649981021881104, "learning_rate": 4.437224145290477e-05, "loss": 0.8912, "step": 10058 }, { "epoch": 0.5499538698103537, "grad_norm": 2.361280679702759, "learning_rate": 4.436344425414646e-05, "loss": 0.9263, "step": 10059 }, { "epoch": 0.5500085426277123, "grad_norm": 3.0551586151123047, "learning_rate": 4.4354647232117384e-05, "loss": 1.191, "step": 10060 }, { "epoch": 0.5500632154450709, "grad_norm": 3.1403706073760986, "learning_rate": 4.434585038709337e-05, "loss": 1.169, "step": 10061 }, { "epoch": 0.5501178882624296, "grad_norm": 2.6014795303344727, "learning_rate": 4.4337053719350236e-05, "loss": 1.1763, "step": 10062 }, { "epoch": 0.5501725610797882, "grad_norm": 2.5049943923950195, "learning_rate": 4.4328257229163784e-05, "loss": 0.8574, "step": 10063 }, { "epoch": 0.5502272338971468, "grad_norm": 2.754692316055298, "learning_rate": 4.4319460916809806e-05, "loss": 1.0978, "step": 10064 }, { "epoch": 0.5502819067145054, "grad_norm": 2.4137070178985596, "learning_rate": 4.431066478256415e-05, "loss": 1.0919, "step": 10065 }, { "epoch": 0.550336579531864, "grad_norm": 2.3142054080963135, "learning_rate": 4.430186882670258e-05, "loss": 0.9539, "step": 10066 }, { "epoch": 0.5503912523492226, "grad_norm": 2.7793097496032715, "learning_rate": 4.429307304950089e-05, "loss": 1.0798, "step": 10067 }, { "epoch": 0.5504459251665812, "grad_norm": 2.354543924331665, "learning_rate": 4.428427745123487e-05, "loss": 1.1412, "step": 10068 }, { "epoch": 0.5505005979839399, "grad_norm": 2.4948441982269287, "learning_rate": 4.427548203218028e-05, "loss": 0.9511, "step": 10069 }, { "epoch": 0.5505552708012985, "grad_norm": 2.835660457611084, "learning_rate": 4.426668679261291e-05, "loss": 1.1966, "step": 10070 }, { "epoch": 0.5506099436186571, "grad_norm": 3.2321269512176514, "learning_rate": 4.425789173280852e-05, "loss": 1.1816, "step": 10071 }, { "epoch": 0.5506646164360157, "grad_norm": 2.345663070678711, "learning_rate": 4.4249096853042875e-05, "loss": 0.8864, "step": 10072 }, { "epoch": 0.5507192892533743, "grad_norm": 2.953592538833618, "learning_rate": 4.424030215359173e-05, "loss": 0.9847, "step": 10073 }, { "epoch": 0.5507739620707329, "grad_norm": 2.565886974334717, "learning_rate": 4.4231507634730804e-05, "loss": 1.1675, "step": 10074 }, { "epoch": 0.5508286348880915, "grad_norm": 2.6664955615997314, "learning_rate": 4.4222713296735904e-05, "loss": 1.3222, "step": 10075 }, { "epoch": 0.5508833077054502, "grad_norm": 2.3817546367645264, "learning_rate": 4.4213919139882726e-05, "loss": 1.0085, "step": 10076 }, { "epoch": 0.5509379805228088, "grad_norm": 2.369227886199951, "learning_rate": 4.420512516444701e-05, "loss": 1.0396, "step": 10077 }, { "epoch": 0.5509926533401674, "grad_norm": 2.6905622482299805, "learning_rate": 4.41963313707045e-05, "loss": 0.9358, "step": 10078 }, { "epoch": 0.551047326157526, "grad_norm": 2.5431318283081055, "learning_rate": 4.41875377589309e-05, "loss": 0.9423, "step": 10079 }, { "epoch": 0.5511019989748847, "grad_norm": 2.9652607440948486, "learning_rate": 4.4178744329401916e-05, "loss": 0.9998, "step": 10080 }, { "epoch": 0.5511566717922433, "grad_norm": 1.9593149423599243, "learning_rate": 4.4169951082393285e-05, "loss": 0.9122, "step": 10081 }, { "epoch": 0.5512113446096019, "grad_norm": 3.579338788986206, "learning_rate": 4.416115801818069e-05, "loss": 1.1522, "step": 10082 }, { "epoch": 0.5512660174269606, "grad_norm": 3.294532537460327, "learning_rate": 4.415236513703984e-05, "loss": 0.9466, "step": 10083 }, { "epoch": 0.5513206902443192, "grad_norm": 2.9036667346954346, "learning_rate": 4.414357243924641e-05, "loss": 1.0277, "step": 10084 }, { "epoch": 0.5513753630616778, "grad_norm": 2.376655101776123, "learning_rate": 4.413477992507612e-05, "loss": 1.0265, "step": 10085 }, { "epoch": 0.5514300358790364, "grad_norm": 2.4177231788635254, "learning_rate": 4.412598759480464e-05, "loss": 1.1807, "step": 10086 }, { "epoch": 0.551484708696395, "grad_norm": 3.084043025970459, "learning_rate": 4.411719544870763e-05, "loss": 1.1471, "step": 10087 }, { "epoch": 0.5515393815137536, "grad_norm": 2.31962251663208, "learning_rate": 4.410840348706078e-05, "loss": 1.087, "step": 10088 }, { "epoch": 0.5515940543311123, "grad_norm": 2.559480905532837, "learning_rate": 4.409961171013974e-05, "loss": 1.0802, "step": 10089 }, { "epoch": 0.5516487271484709, "grad_norm": 2.0559427738189697, "learning_rate": 4.4090820118220174e-05, "loss": 0.9001, "step": 10090 }, { "epoch": 0.5517033999658295, "grad_norm": 2.3894476890563965, "learning_rate": 4.408202871157774e-05, "loss": 1.0866, "step": 10091 }, { "epoch": 0.5517580727831881, "grad_norm": 2.4348998069763184, "learning_rate": 4.4073237490488073e-05, "loss": 1.0531, "step": 10092 }, { "epoch": 0.5518127456005467, "grad_norm": 2.7692110538482666, "learning_rate": 4.406444645522682e-05, "loss": 0.9916, "step": 10093 }, { "epoch": 0.5518674184179053, "grad_norm": 2.8266689777374268, "learning_rate": 4.405565560606959e-05, "loss": 1.3574, "step": 10094 }, { "epoch": 0.5519220912352639, "grad_norm": 2.69448184967041, "learning_rate": 4.404686494329206e-05, "loss": 1.0713, "step": 10095 }, { "epoch": 0.5519767640526226, "grad_norm": 2.3146584033966064, "learning_rate": 4.4038074467169845e-05, "loss": 1.0158, "step": 10096 }, { "epoch": 0.5520314368699812, "grad_norm": 2.523606300354004, "learning_rate": 4.4029284177978534e-05, "loss": 1.0737, "step": 10097 }, { "epoch": 0.5520861096873398, "grad_norm": 3.161536455154419, "learning_rate": 4.402049407599376e-05, "loss": 1.3653, "step": 10098 }, { "epoch": 0.5521407825046984, "grad_norm": 3.0182299613952637, "learning_rate": 4.401170416149113e-05, "loss": 1.2526, "step": 10099 }, { "epoch": 0.552195455322057, "grad_norm": 2.861794948577881, "learning_rate": 4.400291443474623e-05, "loss": 0.9016, "step": 10100 }, { "epoch": 0.5522501281394157, "grad_norm": 2.302746057510376, "learning_rate": 4.3994124896034656e-05, "loss": 1.0849, "step": 10101 }, { "epoch": 0.5523048009567743, "grad_norm": 3.3842742443084717, "learning_rate": 4.3985335545632004e-05, "loss": 1.1915, "step": 10102 }, { "epoch": 0.552359473774133, "grad_norm": 2.858504056930542, "learning_rate": 4.397654638381386e-05, "loss": 1.2127, "step": 10103 }, { "epoch": 0.5524141465914916, "grad_norm": 2.210198163986206, "learning_rate": 4.396775741085578e-05, "loss": 1.024, "step": 10104 }, { "epoch": 0.5524688194088502, "grad_norm": 3.4584388732910156, "learning_rate": 4.395896862703336e-05, "loss": 0.9812, "step": 10105 }, { "epoch": 0.5525234922262088, "grad_norm": 2.7156100273132324, "learning_rate": 4.3950180032622136e-05, "loss": 1.1842, "step": 10106 }, { "epoch": 0.5525781650435674, "grad_norm": 2.3504104614257812, "learning_rate": 4.39413916278977e-05, "loss": 1.1139, "step": 10107 }, { "epoch": 0.552632837860926, "grad_norm": 2.4398691654205322, "learning_rate": 4.3932603413135585e-05, "loss": 0.9633, "step": 10108 }, { "epoch": 0.5526875106782846, "grad_norm": 2.327224016189575, "learning_rate": 4.3923815388611346e-05, "loss": 0.9387, "step": 10109 }, { "epoch": 0.5527421834956433, "grad_norm": 2.383014678955078, "learning_rate": 4.391502755460052e-05, "loss": 0.8519, "step": 10110 }, { "epoch": 0.5527968563130019, "grad_norm": 3.13301420211792, "learning_rate": 4.3906239911378635e-05, "loss": 1.1149, "step": 10111 }, { "epoch": 0.5528515291303605, "grad_norm": 2.5022034645080566, "learning_rate": 4.389745245922123e-05, "loss": 1.1092, "step": 10112 }, { "epoch": 0.5529062019477191, "grad_norm": 2.6445844173431396, "learning_rate": 4.388866519840381e-05, "loss": 0.9389, "step": 10113 }, { "epoch": 0.5529608747650777, "grad_norm": 3.598634958267212, "learning_rate": 4.387987812920191e-05, "loss": 0.9294, "step": 10114 }, { "epoch": 0.5530155475824363, "grad_norm": 3.2624824047088623, "learning_rate": 4.387109125189105e-05, "loss": 0.8955, "step": 10115 }, { "epoch": 0.553070220399795, "grad_norm": 2.5055902004241943, "learning_rate": 4.386230456674671e-05, "loss": 1.1272, "step": 10116 }, { "epoch": 0.5531248932171536, "grad_norm": 2.5467493534088135, "learning_rate": 4.38535180740444e-05, "loss": 1.1173, "step": 10117 }, { "epoch": 0.5531795660345122, "grad_norm": 2.175621509552002, "learning_rate": 4.384473177405962e-05, "loss": 0.9646, "step": 10118 }, { "epoch": 0.5532342388518708, "grad_norm": 3.0819127559661865, "learning_rate": 4.383594566706783e-05, "loss": 1.0282, "step": 10119 }, { "epoch": 0.5532889116692294, "grad_norm": 2.9306161403656006, "learning_rate": 4.3827159753344544e-05, "loss": 1.0717, "step": 10120 }, { "epoch": 0.553343584486588, "grad_norm": 2.2342095375061035, "learning_rate": 4.381837403316522e-05, "loss": 1.006, "step": 10121 }, { "epoch": 0.5533982573039467, "grad_norm": 2.4783217906951904, "learning_rate": 4.3809588506805334e-05, "loss": 0.8817, "step": 10122 }, { "epoch": 0.5534529301213054, "grad_norm": 3.4247987270355225, "learning_rate": 4.3800803174540325e-05, "loss": 0.8897, "step": 10123 }, { "epoch": 0.553507602938664, "grad_norm": 2.2313640117645264, "learning_rate": 4.379201803664568e-05, "loss": 0.8461, "step": 10124 }, { "epoch": 0.5535622757560226, "grad_norm": 2.2428979873657227, "learning_rate": 4.378323309339684e-05, "loss": 1.0972, "step": 10125 }, { "epoch": 0.5536169485733812, "grad_norm": 2.3720102310180664, "learning_rate": 4.3774448345069246e-05, "loss": 0.9585, "step": 10126 }, { "epoch": 0.5536716213907398, "grad_norm": 2.8535823822021484, "learning_rate": 4.376566379193833e-05, "loss": 1.2061, "step": 10127 }, { "epoch": 0.5537262942080984, "grad_norm": 2.4661192893981934, "learning_rate": 4.375687943427954e-05, "loss": 1.1211, "step": 10128 }, { "epoch": 0.553780967025457, "grad_norm": 2.639019250869751, "learning_rate": 4.3748095272368284e-05, "loss": 1.1087, "step": 10129 }, { "epoch": 0.5538356398428157, "grad_norm": 2.9054393768310547, "learning_rate": 4.373931130647999e-05, "loss": 1.1577, "step": 10130 }, { "epoch": 0.5538903126601743, "grad_norm": 3.2734196186065674, "learning_rate": 4.3730527536890077e-05, "loss": 1.1759, "step": 10131 }, { "epoch": 0.5539449854775329, "grad_norm": 2.586921453475952, "learning_rate": 4.372174396387393e-05, "loss": 1.0724, "step": 10132 }, { "epoch": 0.5539996582948915, "grad_norm": 2.290672540664673, "learning_rate": 4.371296058770696e-05, "loss": 1.0266, "step": 10133 }, { "epoch": 0.5540543311122501, "grad_norm": 2.7091681957244873, "learning_rate": 4.370417740866459e-05, "loss": 1.0791, "step": 10134 }, { "epoch": 0.5541090039296087, "grad_norm": 2.533175468444824, "learning_rate": 4.369539442702218e-05, "loss": 1.0201, "step": 10135 }, { "epoch": 0.5541636767469673, "grad_norm": 2.739716053009033, "learning_rate": 4.368661164305512e-05, "loss": 0.8508, "step": 10136 }, { "epoch": 0.554218349564326, "grad_norm": 2.3980190753936768, "learning_rate": 4.367782905703879e-05, "loss": 1.0218, "step": 10137 }, { "epoch": 0.5542730223816846, "grad_norm": 2.2093780040740967, "learning_rate": 4.366904666924856e-05, "loss": 0.9705, "step": 10138 }, { "epoch": 0.5543276951990432, "grad_norm": 2.2982888221740723, "learning_rate": 4.3660264479959775e-05, "loss": 1.0121, "step": 10139 }, { "epoch": 0.5543823680164018, "grad_norm": 2.9006621837615967, "learning_rate": 4.365148248944783e-05, "loss": 1.026, "step": 10140 }, { "epoch": 0.5544370408337604, "grad_norm": 2.450671434402466, "learning_rate": 4.3642700697988035e-05, "loss": 1.0482, "step": 10141 }, { "epoch": 0.554491713651119, "grad_norm": 2.32944655418396, "learning_rate": 4.363391910585577e-05, "loss": 0.9923, "step": 10142 }, { "epoch": 0.5545463864684778, "grad_norm": 2.754563331604004, "learning_rate": 4.362513771332633e-05, "loss": 1.1405, "step": 10143 }, { "epoch": 0.5546010592858364, "grad_norm": 2.7294979095458984, "learning_rate": 4.36163565206751e-05, "loss": 1.0762, "step": 10144 }, { "epoch": 0.554655732103195, "grad_norm": 2.6878063678741455, "learning_rate": 4.3607575528177387e-05, "loss": 1.09, "step": 10145 }, { "epoch": 0.5547104049205536, "grad_norm": 2.453920364379883, "learning_rate": 4.35987947361085e-05, "loss": 1.1085, "step": 10146 }, { "epoch": 0.5547650777379122, "grad_norm": 2.001033306121826, "learning_rate": 4.359001414474377e-05, "loss": 0.695, "step": 10147 }, { "epoch": 0.5548197505552708, "grad_norm": 2.1802940368652344, "learning_rate": 4.358123375435849e-05, "loss": 1.0393, "step": 10148 }, { "epoch": 0.5548744233726294, "grad_norm": 2.5184166431427, "learning_rate": 4.357245356522797e-05, "loss": 0.9965, "step": 10149 }, { "epoch": 0.5549290961899881, "grad_norm": 2.229250431060791, "learning_rate": 4.35636735776275e-05, "loss": 0.9213, "step": 10150 }, { "epoch": 0.5549837690073467, "grad_norm": 2.79008412361145, "learning_rate": 4.355489379183237e-05, "loss": 1.0764, "step": 10151 }, { "epoch": 0.5550384418247053, "grad_norm": 3.242875337600708, "learning_rate": 4.354611420811786e-05, "loss": 1.1689, "step": 10152 }, { "epoch": 0.5550931146420639, "grad_norm": 2.0950021743774414, "learning_rate": 4.3537334826759234e-05, "loss": 0.6862, "step": 10153 }, { "epoch": 0.5551477874594225, "grad_norm": 2.040600538253784, "learning_rate": 4.35285556480318e-05, "loss": 0.7859, "step": 10154 }, { "epoch": 0.5552024602767811, "grad_norm": 2.4498023986816406, "learning_rate": 4.35197766722108e-05, "loss": 1.016, "step": 10155 }, { "epoch": 0.5552571330941397, "grad_norm": 2.321786642074585, "learning_rate": 4.351099789957148e-05, "loss": 0.8226, "step": 10156 }, { "epoch": 0.5553118059114984, "grad_norm": 2.1347744464874268, "learning_rate": 4.350221933038911e-05, "loss": 0.8232, "step": 10157 }, { "epoch": 0.555366478728857, "grad_norm": 2.6883792877197266, "learning_rate": 4.3493440964938926e-05, "loss": 1.0479, "step": 10158 }, { "epoch": 0.5554211515462156, "grad_norm": 4.48663854598999, "learning_rate": 4.3484662803496155e-05, "loss": 0.9304, "step": 10159 }, { "epoch": 0.5554758243635742, "grad_norm": 3.0003983974456787, "learning_rate": 4.347588484633605e-05, "loss": 1.0739, "step": 10160 }, { "epoch": 0.5555304971809328, "grad_norm": 2.498021125793457, "learning_rate": 4.346710709373381e-05, "loss": 1.0152, "step": 10161 }, { "epoch": 0.5555851699982914, "grad_norm": 2.543520450592041, "learning_rate": 4.345832954596466e-05, "loss": 0.7694, "step": 10162 }, { "epoch": 0.55563984281565, "grad_norm": 2.450552225112915, "learning_rate": 4.3449552203303825e-05, "loss": 0.905, "step": 10163 }, { "epoch": 0.5556945156330088, "grad_norm": 3.116391897201538, "learning_rate": 4.344077506602652e-05, "loss": 1.1916, "step": 10164 }, { "epoch": 0.5557491884503674, "grad_norm": 2.733074188232422, "learning_rate": 4.343199813440793e-05, "loss": 1.0467, "step": 10165 }, { "epoch": 0.555803861267726, "grad_norm": 2.3861289024353027, "learning_rate": 4.342322140872324e-05, "loss": 0.9456, "step": 10166 }, { "epoch": 0.5558585340850846, "grad_norm": 2.548663854598999, "learning_rate": 4.341444488924765e-05, "loss": 0.8662, "step": 10167 }, { "epoch": 0.5559132069024432, "grad_norm": 2.2591912746429443, "learning_rate": 4.340566857625633e-05, "loss": 0.9983, "step": 10168 }, { "epoch": 0.5559678797198018, "grad_norm": 2.2175650596618652, "learning_rate": 4.339689247002447e-05, "loss": 0.9958, "step": 10169 }, { "epoch": 0.5560225525371605, "grad_norm": 3.399373769760132, "learning_rate": 4.3388116570827215e-05, "loss": 1.0303, "step": 10170 }, { "epoch": 0.5560772253545191, "grad_norm": 3.9864118099212646, "learning_rate": 4.337934087893974e-05, "loss": 0.8287, "step": 10171 }, { "epoch": 0.5561318981718777, "grad_norm": 2.6390790939331055, "learning_rate": 4.3370565394637175e-05, "loss": 1.1185, "step": 10172 }, { "epoch": 0.5561865709892363, "grad_norm": 2.551753520965576, "learning_rate": 4.336179011819471e-05, "loss": 1.0492, "step": 10173 }, { "epoch": 0.5562412438065949, "grad_norm": 2.5775222778320312, "learning_rate": 4.335301504988746e-05, "loss": 0.939, "step": 10174 }, { "epoch": 0.5562959166239535, "grad_norm": 2.2751872539520264, "learning_rate": 4.334424018999056e-05, "loss": 0.9364, "step": 10175 }, { "epoch": 0.5563505894413121, "grad_norm": 2.367556571960449, "learning_rate": 4.333546553877915e-05, "loss": 1.1112, "step": 10176 }, { "epoch": 0.5564052622586708, "grad_norm": 3.0790045261383057, "learning_rate": 4.332669109652834e-05, "loss": 1.0884, "step": 10177 }, { "epoch": 0.5564599350760294, "grad_norm": 2.2731809616088867, "learning_rate": 4.331791686351324e-05, "loss": 1.1461, "step": 10178 }, { "epoch": 0.556514607893388, "grad_norm": 2.7457263469696045, "learning_rate": 4.3309142840008974e-05, "loss": 1.2025, "step": 10179 }, { "epoch": 0.5565692807107466, "grad_norm": 2.9717304706573486, "learning_rate": 4.3300369026290634e-05, "loss": 1.1662, "step": 10180 }, { "epoch": 0.5566239535281052, "grad_norm": 3.3147504329681396, "learning_rate": 4.329159542263332e-05, "loss": 1.2697, "step": 10181 }, { "epoch": 0.5566786263454638, "grad_norm": 2.3801112174987793, "learning_rate": 4.328282202931209e-05, "loss": 0.8699, "step": 10182 }, { "epoch": 0.5567332991628224, "grad_norm": 2.646559715270996, "learning_rate": 4.3274048846602076e-05, "loss": 1.1036, "step": 10183 }, { "epoch": 0.5567879719801812, "grad_norm": 2.5131757259368896, "learning_rate": 4.326527587477833e-05, "loss": 1.1431, "step": 10184 }, { "epoch": 0.5568426447975398, "grad_norm": 3.4795427322387695, "learning_rate": 4.3256503114115934e-05, "loss": 0.7328, "step": 10185 }, { "epoch": 0.5568973176148984, "grad_norm": 3.083543539047241, "learning_rate": 4.324773056488993e-05, "loss": 0.8412, "step": 10186 }, { "epoch": 0.556951990432257, "grad_norm": 2.287855386734009, "learning_rate": 4.323895822737538e-05, "loss": 1.0576, "step": 10187 }, { "epoch": 0.5570066632496156, "grad_norm": 2.667590618133545, "learning_rate": 4.323018610184733e-05, "loss": 1.1535, "step": 10188 }, { "epoch": 0.5570613360669742, "grad_norm": 2.489227056503296, "learning_rate": 4.322141418858083e-05, "loss": 1.1546, "step": 10189 }, { "epoch": 0.5571160088843328, "grad_norm": 2.1285393238067627, "learning_rate": 4.321264248785092e-05, "loss": 0.9387, "step": 10190 }, { "epoch": 0.5571706817016915, "grad_norm": 3.4462175369262695, "learning_rate": 4.320387099993262e-05, "loss": 0.9385, "step": 10191 }, { "epoch": 0.5572253545190501, "grad_norm": 2.4388864040374756, "learning_rate": 4.319509972510093e-05, "loss": 1.2547, "step": 10192 }, { "epoch": 0.5572800273364087, "grad_norm": 2.7669589519500732, "learning_rate": 4.31863286636309e-05, "loss": 1.2292, "step": 10193 }, { "epoch": 0.5573347001537673, "grad_norm": 2.2253267765045166, "learning_rate": 4.317755781579754e-05, "loss": 1.1005, "step": 10194 }, { "epoch": 0.5573893729711259, "grad_norm": 2.677935838699341, "learning_rate": 4.316878718187583e-05, "loss": 1.057, "step": 10195 }, { "epoch": 0.5574440457884845, "grad_norm": 2.247343063354492, "learning_rate": 4.316001676214079e-05, "loss": 1.0858, "step": 10196 }, { "epoch": 0.5574987186058431, "grad_norm": 2.557159185409546, "learning_rate": 4.315124655686738e-05, "loss": 1.1302, "step": 10197 }, { "epoch": 0.5575533914232018, "grad_norm": 2.419443130493164, "learning_rate": 4.31424765663306e-05, "loss": 0.7591, "step": 10198 }, { "epoch": 0.5576080642405604, "grad_norm": 3.2273550033569336, "learning_rate": 4.313370679080543e-05, "loss": 1.1903, "step": 10199 }, { "epoch": 0.557662737057919, "grad_norm": 2.228236198425293, "learning_rate": 4.3124937230566826e-05, "loss": 1.0587, "step": 10200 }, { "epoch": 0.5577174098752776, "grad_norm": 2.2565066814422607, "learning_rate": 4.311616788588975e-05, "loss": 1.0004, "step": 10201 }, { "epoch": 0.5577720826926362, "grad_norm": 3.899799108505249, "learning_rate": 4.3107398757049155e-05, "loss": 1.1164, "step": 10202 }, { "epoch": 0.5578267555099948, "grad_norm": 2.3466999530792236, "learning_rate": 4.309862984432001e-05, "loss": 1.0516, "step": 10203 }, { "epoch": 0.5578814283273535, "grad_norm": 2.994870901107788, "learning_rate": 4.308986114797724e-05, "loss": 0.8602, "step": 10204 }, { "epoch": 0.5579361011447121, "grad_norm": 2.1182548999786377, "learning_rate": 4.3081092668295776e-05, "loss": 0.9078, "step": 10205 }, { "epoch": 0.5579907739620708, "grad_norm": 2.4705183506011963, "learning_rate": 4.307232440555055e-05, "loss": 1.0399, "step": 10206 }, { "epoch": 0.5580454467794294, "grad_norm": 3.632556438446045, "learning_rate": 4.3063556360016486e-05, "loss": 1.1231, "step": 10207 }, { "epoch": 0.558100119596788, "grad_norm": 2.312551259994507, "learning_rate": 4.3054788531968506e-05, "loss": 0.9566, "step": 10208 }, { "epoch": 0.5581547924141466, "grad_norm": 2.274386167526245, "learning_rate": 4.30460209216815e-05, "loss": 1.2265, "step": 10209 }, { "epoch": 0.5582094652315052, "grad_norm": 2.6449332237243652, "learning_rate": 4.303725352943039e-05, "loss": 1.0452, "step": 10210 }, { "epoch": 0.5582641380488639, "grad_norm": 2.7679128646850586, "learning_rate": 4.3028486355490036e-05, "loss": 1.0966, "step": 10211 }, { "epoch": 0.5583188108662225, "grad_norm": 2.6794991493225098, "learning_rate": 4.301971940013536e-05, "loss": 0.974, "step": 10212 }, { "epoch": 0.5583734836835811, "grad_norm": 2.3729658126831055, "learning_rate": 4.301095266364123e-05, "loss": 0.9762, "step": 10213 }, { "epoch": 0.5584281565009397, "grad_norm": 2.6156115531921387, "learning_rate": 4.300218614628252e-05, "loss": 0.8145, "step": 10214 }, { "epoch": 0.5584828293182983, "grad_norm": 3.1716959476470947, "learning_rate": 4.299341984833409e-05, "loss": 1.0816, "step": 10215 }, { "epoch": 0.5585375021356569, "grad_norm": 2.9810452461242676, "learning_rate": 4.29846537700708e-05, "loss": 1.0423, "step": 10216 }, { "epoch": 0.5585921749530155, "grad_norm": 2.5227274894714355, "learning_rate": 4.2975887911767516e-05, "loss": 1.0796, "step": 10217 }, { "epoch": 0.5586468477703742, "grad_norm": 4.217520713806152, "learning_rate": 4.296712227369907e-05, "loss": 1.0888, "step": 10218 }, { "epoch": 0.5587015205877328, "grad_norm": 2.7174534797668457, "learning_rate": 4.29583568561403e-05, "loss": 1.0351, "step": 10219 }, { "epoch": 0.5587561934050914, "grad_norm": 2.2764291763305664, "learning_rate": 4.2949591659366043e-05, "loss": 1.1216, "step": 10220 }, { "epoch": 0.55881086622245, "grad_norm": 3.0415782928466797, "learning_rate": 4.294082668365112e-05, "loss": 1.1543, "step": 10221 }, { "epoch": 0.5588655390398086, "grad_norm": 3.20919132232666, "learning_rate": 4.293206192927036e-05, "loss": 1.1758, "step": 10222 }, { "epoch": 0.5589202118571672, "grad_norm": 2.7775793075561523, "learning_rate": 4.292329739649858e-05, "loss": 1.0957, "step": 10223 }, { "epoch": 0.5589748846745258, "grad_norm": 2.5076818466186523, "learning_rate": 4.2914533085610556e-05, "loss": 0.9935, "step": 10224 }, { "epoch": 0.5590295574918845, "grad_norm": 2.722410202026367, "learning_rate": 4.290576899688111e-05, "loss": 1.1033, "step": 10225 }, { "epoch": 0.5590842303092431, "grad_norm": 2.6365106105804443, "learning_rate": 4.2897005130585016e-05, "loss": 1.037, "step": 10226 }, { "epoch": 0.5591389031266017, "grad_norm": 4.144082069396973, "learning_rate": 4.2888241486997066e-05, "loss": 1.1525, "step": 10227 }, { "epoch": 0.5591935759439604, "grad_norm": 2.803262233734131, "learning_rate": 4.2879478066392036e-05, "loss": 0.9709, "step": 10228 }, { "epoch": 0.559248248761319, "grad_norm": 2.6081392765045166, "learning_rate": 4.28707148690447e-05, "loss": 0.9934, "step": 10229 }, { "epoch": 0.5593029215786776, "grad_norm": 2.799360513687134, "learning_rate": 4.286195189522981e-05, "loss": 1.1585, "step": 10230 }, { "epoch": 0.5593575943960363, "grad_norm": 2.1220781803131104, "learning_rate": 4.285318914522209e-05, "loss": 0.9506, "step": 10231 }, { "epoch": 0.5594122672133949, "grad_norm": 2.215542793273926, "learning_rate": 4.2844426619296366e-05, "loss": 0.9667, "step": 10232 }, { "epoch": 0.5594669400307535, "grad_norm": 2.86076021194458, "learning_rate": 4.283566431772733e-05, "loss": 1.0781, "step": 10233 }, { "epoch": 0.5595216128481121, "grad_norm": 2.179307222366333, "learning_rate": 4.282690224078972e-05, "loss": 1.004, "step": 10234 }, { "epoch": 0.5595762856654707, "grad_norm": 2.5749056339263916, "learning_rate": 4.281814038875828e-05, "loss": 1.0961, "step": 10235 }, { "epoch": 0.5596309584828293, "grad_norm": 2.4247093200683594, "learning_rate": 4.2809378761907705e-05, "loss": 1.0166, "step": 10236 }, { "epoch": 0.5596856313001879, "grad_norm": 2.7924132347106934, "learning_rate": 4.280061736051272e-05, "loss": 1.2154, "step": 10237 }, { "epoch": 0.5597403041175466, "grad_norm": 2.2949318885803223, "learning_rate": 4.2791856184848026e-05, "loss": 1.0051, "step": 10238 }, { "epoch": 0.5597949769349052, "grad_norm": 2.1372499465942383, "learning_rate": 4.2783095235188334e-05, "loss": 1.065, "step": 10239 }, { "epoch": 0.5598496497522638, "grad_norm": 2.2943549156188965, "learning_rate": 4.2774334511808336e-05, "loss": 0.8667, "step": 10240 }, { "epoch": 0.5599043225696224, "grad_norm": 2.2107486724853516, "learning_rate": 4.2765574014982676e-05, "loss": 1.0968, "step": 10241 }, { "epoch": 0.559958995386981, "grad_norm": 2.3767335414886475, "learning_rate": 4.275681374498609e-05, "loss": 0.8635, "step": 10242 }, { "epoch": 0.5600136682043396, "grad_norm": 2.5584311485290527, "learning_rate": 4.274805370209322e-05, "loss": 0.9669, "step": 10243 }, { "epoch": 0.5600683410216982, "grad_norm": 2.699021100997925, "learning_rate": 4.273929388657874e-05, "loss": 1.1694, "step": 10244 }, { "epoch": 0.5601230138390569, "grad_norm": 2.2232038974761963, "learning_rate": 4.2730534298717295e-05, "loss": 0.829, "step": 10245 }, { "epoch": 0.5601776866564155, "grad_norm": 2.8473706245422363, "learning_rate": 4.2721774938783546e-05, "loss": 1.1341, "step": 10246 }, { "epoch": 0.5602323594737741, "grad_norm": 2.7006192207336426, "learning_rate": 4.271301580705212e-05, "loss": 1.1231, "step": 10247 }, { "epoch": 0.5602870322911327, "grad_norm": 2.2685413360595703, "learning_rate": 4.2704256903797656e-05, "loss": 1.0622, "step": 10248 }, { "epoch": 0.5603417051084914, "grad_norm": 2.405258893966675, "learning_rate": 4.269549822929479e-05, "loss": 1.0496, "step": 10249 }, { "epoch": 0.56039637792585, "grad_norm": 2.3531901836395264, "learning_rate": 4.268673978381814e-05, "loss": 1.0388, "step": 10250 }, { "epoch": 0.5604510507432086, "grad_norm": 2.5424001216888428, "learning_rate": 4.2677981567642296e-05, "loss": 0.9836, "step": 10251 }, { "epoch": 0.5605057235605673, "grad_norm": 3.378347635269165, "learning_rate": 4.2669223581041906e-05, "loss": 0.9491, "step": 10252 }, { "epoch": 0.5605603963779259, "grad_norm": 2.365358829498291, "learning_rate": 4.266046582429154e-05, "loss": 1.0124, "step": 10253 }, { "epoch": 0.5606150691952845, "grad_norm": 2.4313058853149414, "learning_rate": 4.26517082976658e-05, "loss": 1.0431, "step": 10254 }, { "epoch": 0.5606697420126431, "grad_norm": 1.9218921661376953, "learning_rate": 4.264295100143928e-05, "loss": 0.8891, "step": 10255 }, { "epoch": 0.5607244148300017, "grad_norm": 2.4368667602539062, "learning_rate": 4.2634193935886534e-05, "loss": 0.9652, "step": 10256 }, { "epoch": 0.5607790876473603, "grad_norm": 2.8616514205932617, "learning_rate": 4.262543710128215e-05, "loss": 1.0294, "step": 10257 }, { "epoch": 0.560833760464719, "grad_norm": 2.821279764175415, "learning_rate": 4.261668049790068e-05, "loss": 1.1802, "step": 10258 }, { "epoch": 0.5608884332820776, "grad_norm": 2.647372007369995, "learning_rate": 4.2607924126016684e-05, "loss": 1.1111, "step": 10259 }, { "epoch": 0.5609431060994362, "grad_norm": 2.372340440750122, "learning_rate": 4.259916798590472e-05, "loss": 1.0935, "step": 10260 }, { "epoch": 0.5609977789167948, "grad_norm": 2.5806467533111572, "learning_rate": 4.259041207783929e-05, "loss": 1.1093, "step": 10261 }, { "epoch": 0.5610524517341534, "grad_norm": 3.1686768531799316, "learning_rate": 4.258165640209497e-05, "loss": 0.8921, "step": 10262 }, { "epoch": 0.561107124551512, "grad_norm": 2.1001052856445312, "learning_rate": 4.257290095894629e-05, "loss": 0.9104, "step": 10263 }, { "epoch": 0.5611617973688706, "grad_norm": 2.4653029441833496, "learning_rate": 4.256414574866775e-05, "loss": 1.004, "step": 10264 }, { "epoch": 0.5612164701862293, "grad_norm": 2.5902814865112305, "learning_rate": 4.255539077153385e-05, "loss": 1.0365, "step": 10265 }, { "epoch": 0.5612711430035879, "grad_norm": 2.653973340988159, "learning_rate": 4.254663602781912e-05, "loss": 1.1393, "step": 10266 }, { "epoch": 0.5613258158209465, "grad_norm": 2.5257632732391357, "learning_rate": 4.253788151779805e-05, "loss": 0.9979, "step": 10267 }, { "epoch": 0.5613804886383051, "grad_norm": 3.105801582336426, "learning_rate": 4.252912724174513e-05, "loss": 0.9513, "step": 10268 }, { "epoch": 0.5614351614556637, "grad_norm": 2.234098434448242, "learning_rate": 4.252037319993483e-05, "loss": 0.8348, "step": 10269 }, { "epoch": 0.5614898342730223, "grad_norm": 2.3449759483337402, "learning_rate": 4.251161939264161e-05, "loss": 0.8526, "step": 10270 }, { "epoch": 0.561544507090381, "grad_norm": 3.002946615219116, "learning_rate": 4.250286582013999e-05, "loss": 1.2723, "step": 10271 }, { "epoch": 0.5615991799077397, "grad_norm": 2.3995025157928467, "learning_rate": 4.24941124827044e-05, "loss": 1.0787, "step": 10272 }, { "epoch": 0.5616538527250983, "grad_norm": 2.367809772491455, "learning_rate": 4.24853593806093e-05, "loss": 0.9293, "step": 10273 }, { "epoch": 0.5617085255424569, "grad_norm": 2.9400744438171387, "learning_rate": 4.247660651412913e-05, "loss": 0.8772, "step": 10274 }, { "epoch": 0.5617631983598155, "grad_norm": 2.822192430496216, "learning_rate": 4.246785388353833e-05, "loss": 0.8106, "step": 10275 }, { "epoch": 0.5618178711771741, "grad_norm": 3.0316507816314697, "learning_rate": 4.245910148911133e-05, "loss": 1.228, "step": 10276 }, { "epoch": 0.5618725439945327, "grad_norm": 2.144723415374756, "learning_rate": 4.2450349331122563e-05, "loss": 0.8748, "step": 10277 }, { "epoch": 0.5619272168118913, "grad_norm": 2.107236862182617, "learning_rate": 4.2441597409846435e-05, "loss": 0.9064, "step": 10278 }, { "epoch": 0.56198188962925, "grad_norm": 2.7485294342041016, "learning_rate": 4.2432845725557345e-05, "loss": 1.0122, "step": 10279 }, { "epoch": 0.5620365624466086, "grad_norm": 3.4044911861419678, "learning_rate": 4.24240942785297e-05, "loss": 1.0359, "step": 10280 }, { "epoch": 0.5620912352639672, "grad_norm": 3.191507339477539, "learning_rate": 4.241534306903791e-05, "loss": 1.2158, "step": 10281 }, { "epoch": 0.5621459080813258, "grad_norm": 3.641356945037842, "learning_rate": 4.2406592097356354e-05, "loss": 1.2892, "step": 10282 }, { "epoch": 0.5622005808986844, "grad_norm": 2.2706544399261475, "learning_rate": 4.239784136375942e-05, "loss": 0.7947, "step": 10283 }, { "epoch": 0.562255253716043, "grad_norm": 2.8437013626098633, "learning_rate": 4.238909086852145e-05, "loss": 1.0923, "step": 10284 }, { "epoch": 0.5623099265334017, "grad_norm": 2.039172649383545, "learning_rate": 4.238034061191684e-05, "loss": 1.095, "step": 10285 }, { "epoch": 0.5623645993507603, "grad_norm": 2.951517343521118, "learning_rate": 4.237159059421993e-05, "loss": 0.8502, "step": 10286 }, { "epoch": 0.5624192721681189, "grad_norm": 2.836383819580078, "learning_rate": 4.236284081570507e-05, "loss": 1.0497, "step": 10287 }, { "epoch": 0.5624739449854775, "grad_norm": 2.6626949310302734, "learning_rate": 4.23540912766466e-05, "loss": 1.0672, "step": 10288 }, { "epoch": 0.5625286178028361, "grad_norm": 2.4327852725982666, "learning_rate": 4.234534197731887e-05, "loss": 1.0695, "step": 10289 }, { "epoch": 0.5625832906201947, "grad_norm": 2.9003326892852783, "learning_rate": 4.233659291799617e-05, "loss": 0.9026, "step": 10290 }, { "epoch": 0.5626379634375533, "grad_norm": 2.4004812240600586, "learning_rate": 4.232784409895286e-05, "loss": 0.9142, "step": 10291 }, { "epoch": 0.5626926362549121, "grad_norm": 2.6296932697296143, "learning_rate": 4.2319095520463236e-05, "loss": 1.0467, "step": 10292 }, { "epoch": 0.5627473090722707, "grad_norm": 2.012535572052002, "learning_rate": 4.2310347182801584e-05, "loss": 1.0314, "step": 10293 }, { "epoch": 0.5628019818896293, "grad_norm": 2.326786994934082, "learning_rate": 4.230159908624223e-05, "loss": 1.0271, "step": 10294 }, { "epoch": 0.5628566547069879, "grad_norm": 2.4514169692993164, "learning_rate": 4.229285123105946e-05, "loss": 0.9587, "step": 10295 }, { "epoch": 0.5629113275243465, "grad_norm": 4.237452507019043, "learning_rate": 4.228410361752753e-05, "loss": 0.9176, "step": 10296 }, { "epoch": 0.5629660003417051, "grad_norm": 5.232177734375, "learning_rate": 4.227535624592074e-05, "loss": 1.0435, "step": 10297 }, { "epoch": 0.5630206731590637, "grad_norm": 2.5889134407043457, "learning_rate": 4.226660911651334e-05, "loss": 0.9697, "step": 10298 }, { "epoch": 0.5630753459764224, "grad_norm": 2.3977272510528564, "learning_rate": 4.225786222957959e-05, "loss": 1.1021, "step": 10299 }, { "epoch": 0.563130018793781, "grad_norm": 2.7331321239471436, "learning_rate": 4.224911558539374e-05, "loss": 1.1655, "step": 10300 }, { "epoch": 0.5631846916111396, "grad_norm": 2.919999361038208, "learning_rate": 4.224036918423005e-05, "loss": 1.128, "step": 10301 }, { "epoch": 0.5632393644284982, "grad_norm": 3.2440109252929688, "learning_rate": 4.223162302636274e-05, "loss": 1.015, "step": 10302 }, { "epoch": 0.5632940372458568, "grad_norm": 2.4173784255981445, "learning_rate": 4.2222877112066046e-05, "loss": 0.9888, "step": 10303 }, { "epoch": 0.5633487100632154, "grad_norm": 2.411604881286621, "learning_rate": 4.221413144161418e-05, "loss": 1.0462, "step": 10304 }, { "epoch": 0.563403382880574, "grad_norm": 3.4869558811187744, "learning_rate": 4.220538601528136e-05, "loss": 1.1272, "step": 10305 }, { "epoch": 0.5634580556979327, "grad_norm": 2.8866281509399414, "learning_rate": 4.2196640833341776e-05, "loss": 1.2082, "step": 10306 }, { "epoch": 0.5635127285152913, "grad_norm": 3.0551135540008545, "learning_rate": 4.218789589606965e-05, "loss": 1.0582, "step": 10307 }, { "epoch": 0.5635674013326499, "grad_norm": 3.073774576187134, "learning_rate": 4.217915120373916e-05, "loss": 1.2591, "step": 10308 }, { "epoch": 0.5636220741500085, "grad_norm": 3.529003858566284, "learning_rate": 4.21704067566245e-05, "loss": 1.2234, "step": 10309 }, { "epoch": 0.5636767469673671, "grad_norm": 2.8846473693847656, "learning_rate": 4.2161662554999815e-05, "loss": 1.0582, "step": 10310 }, { "epoch": 0.5637314197847257, "grad_norm": 2.2368528842926025, "learning_rate": 4.21529185991393e-05, "loss": 0.9533, "step": 10311 }, { "epoch": 0.5637860926020845, "grad_norm": 2.4009766578674316, "learning_rate": 4.2144174889317114e-05, "loss": 1.0169, "step": 10312 }, { "epoch": 0.5638407654194431, "grad_norm": 2.0401229858398438, "learning_rate": 4.2135431425807394e-05, "loss": 0.9853, "step": 10313 }, { "epoch": 0.5638954382368017, "grad_norm": 2.1537046432495117, "learning_rate": 4.2126688208884286e-05, "loss": 0.9221, "step": 10314 }, { "epoch": 0.5639501110541603, "grad_norm": 2.8528621196746826, "learning_rate": 4.2117945238821924e-05, "loss": 1.171, "step": 10315 }, { "epoch": 0.5640047838715189, "grad_norm": 2.58808970451355, "learning_rate": 4.210920251589445e-05, "loss": 0.9626, "step": 10316 }, { "epoch": 0.5640594566888775, "grad_norm": 2.12294602394104, "learning_rate": 4.2100460040375965e-05, "loss": 0.787, "step": 10317 }, { "epoch": 0.5641141295062361, "grad_norm": 2.5840957164764404, "learning_rate": 4.2091717812540595e-05, "loss": 1.133, "step": 10318 }, { "epoch": 0.5641688023235948, "grad_norm": 4.042721748352051, "learning_rate": 4.208297583266243e-05, "loss": 1.0646, "step": 10319 }, { "epoch": 0.5642234751409534, "grad_norm": 3.011537551879883, "learning_rate": 4.207423410101559e-05, "loss": 1.324, "step": 10320 }, { "epoch": 0.564278147958312, "grad_norm": 2.099736213684082, "learning_rate": 4.206549261787415e-05, "loss": 0.9417, "step": 10321 }, { "epoch": 0.5643328207756706, "grad_norm": 2.4573965072631836, "learning_rate": 4.20567513835122e-05, "loss": 0.929, "step": 10322 }, { "epoch": 0.5643874935930292, "grad_norm": 2.506979465484619, "learning_rate": 4.204801039820381e-05, "loss": 1.0164, "step": 10323 }, { "epoch": 0.5644421664103878, "grad_norm": 2.323634624481201, "learning_rate": 4.2039269662223034e-05, "loss": 1.2035, "step": 10324 }, { "epoch": 0.5644968392277464, "grad_norm": 2.098381519317627, "learning_rate": 4.203052917584395e-05, "loss": 0.8793, "step": 10325 }, { "epoch": 0.5645515120451051, "grad_norm": 2.318413019180298, "learning_rate": 4.20217889393406e-05, "loss": 1.0996, "step": 10326 }, { "epoch": 0.5646061848624637, "grad_norm": 2.5419740676879883, "learning_rate": 4.201304895298701e-05, "loss": 1.0399, "step": 10327 }, { "epoch": 0.5646608576798223, "grad_norm": 2.4561331272125244, "learning_rate": 4.200430921705724e-05, "loss": 1.0452, "step": 10328 }, { "epoch": 0.5647155304971809, "grad_norm": 2.9091434478759766, "learning_rate": 4.199556973182528e-05, "loss": 1.2008, "step": 10329 }, { "epoch": 0.5647702033145395, "grad_norm": 2.5250866413116455, "learning_rate": 4.1986830497565196e-05, "loss": 1.0483, "step": 10330 }, { "epoch": 0.5648248761318981, "grad_norm": 3.1052253246307373, "learning_rate": 4.197809151455098e-05, "loss": 0.9026, "step": 10331 }, { "epoch": 0.5648795489492567, "grad_norm": 2.7278096675872803, "learning_rate": 4.196935278305663e-05, "loss": 1.076, "step": 10332 }, { "epoch": 0.5649342217666155, "grad_norm": 2.7280890941619873, "learning_rate": 4.196061430335615e-05, "loss": 1.1252, "step": 10333 }, { "epoch": 0.564988894583974, "grad_norm": 2.463745355606079, "learning_rate": 4.195187607572352e-05, "loss": 0.9772, "step": 10334 }, { "epoch": 0.5650435674013327, "grad_norm": 2.2484052181243896, "learning_rate": 4.1943138100432716e-05, "loss": 0.9072, "step": 10335 }, { "epoch": 0.5650982402186913, "grad_norm": 2.7207260131835938, "learning_rate": 4.193440037775772e-05, "loss": 1.0447, "step": 10336 }, { "epoch": 0.5651529130360499, "grad_norm": 2.2273855209350586, "learning_rate": 4.192566290797248e-05, "loss": 1.0152, "step": 10337 }, { "epoch": 0.5652075858534085, "grad_norm": 2.7604784965515137, "learning_rate": 4.191692569135097e-05, "loss": 1.1572, "step": 10338 }, { "epoch": 0.5652622586707672, "grad_norm": 2.315934419631958, "learning_rate": 4.19081887281671e-05, "loss": 0.9019, "step": 10339 }, { "epoch": 0.5653169314881258, "grad_norm": 2.992288827896118, "learning_rate": 4.189945201869487e-05, "loss": 0.9214, "step": 10340 }, { "epoch": 0.5653716043054844, "grad_norm": 2.6391875743865967, "learning_rate": 4.1890715563208175e-05, "loss": 0.9903, "step": 10341 }, { "epoch": 0.565426277122843, "grad_norm": 2.183837652206421, "learning_rate": 4.1881979361980945e-05, "loss": 0.8772, "step": 10342 }, { "epoch": 0.5654809499402016, "grad_norm": 2.480879306793213, "learning_rate": 4.1873243415287096e-05, "loss": 1.1598, "step": 10343 }, { "epoch": 0.5655356227575602, "grad_norm": 3.1085424423217773, "learning_rate": 4.186450772340054e-05, "loss": 0.9677, "step": 10344 }, { "epoch": 0.5655902955749188, "grad_norm": 2.6059675216674805, "learning_rate": 4.185577228659516e-05, "loss": 1.0346, "step": 10345 }, { "epoch": 0.5656449683922775, "grad_norm": 2.803743600845337, "learning_rate": 4.184703710514487e-05, "loss": 1.197, "step": 10346 }, { "epoch": 0.5656996412096361, "grad_norm": 2.7960569858551025, "learning_rate": 4.1838302179323544e-05, "loss": 1.1237, "step": 10347 }, { "epoch": 0.5657543140269947, "grad_norm": 2.974832534790039, "learning_rate": 4.182956750940505e-05, "loss": 1.1357, "step": 10348 }, { "epoch": 0.5658089868443533, "grad_norm": 3.2416574954986572, "learning_rate": 4.182083309566325e-05, "loss": 0.9431, "step": 10349 }, { "epoch": 0.5658636596617119, "grad_norm": 2.1862587928771973, "learning_rate": 4.181209893837205e-05, "loss": 0.8663, "step": 10350 }, { "epoch": 0.5659183324790705, "grad_norm": 2.9129550457000732, "learning_rate": 4.1803365037805253e-05, "loss": 0.9782, "step": 10351 }, { "epoch": 0.5659730052964291, "grad_norm": 2.1742758750915527, "learning_rate": 4.179463139423672e-05, "loss": 0.9692, "step": 10352 }, { "epoch": 0.5660276781137878, "grad_norm": 2.8311984539031982, "learning_rate": 4.1785898007940294e-05, "loss": 1.2116, "step": 10353 }, { "epoch": 0.5660823509311464, "grad_norm": 2.3754396438598633, "learning_rate": 4.177716487918979e-05, "loss": 1.0794, "step": 10354 }, { "epoch": 0.566137023748505, "grad_norm": 2.6160848140716553, "learning_rate": 4.176843200825903e-05, "loss": 1.0787, "step": 10355 }, { "epoch": 0.5661916965658637, "grad_norm": 2.698512315750122, "learning_rate": 4.175969939542184e-05, "loss": 1.1682, "step": 10356 }, { "epoch": 0.5662463693832223, "grad_norm": 2.5750839710235596, "learning_rate": 4.1750967040951993e-05, "loss": 0.9504, "step": 10357 }, { "epoch": 0.5663010422005809, "grad_norm": 2.285320997238159, "learning_rate": 4.1742234945123314e-05, "loss": 1.0465, "step": 10358 }, { "epoch": 0.5663557150179395, "grad_norm": 2.903813362121582, "learning_rate": 4.1733503108209554e-05, "loss": 1.0573, "step": 10359 }, { "epoch": 0.5664103878352982, "grad_norm": 2.665259838104248, "learning_rate": 4.1724771530484536e-05, "loss": 0.9894, "step": 10360 }, { "epoch": 0.5664650606526568, "grad_norm": 3.1374058723449707, "learning_rate": 4.171604021222202e-05, "loss": 0.746, "step": 10361 }, { "epoch": 0.5665197334700154, "grad_norm": 2.6109907627105713, "learning_rate": 4.170730915369575e-05, "loss": 1.1212, "step": 10362 }, { "epoch": 0.566574406287374, "grad_norm": 2.663008689880371, "learning_rate": 4.1698578355179496e-05, "loss": 0.9558, "step": 10363 }, { "epoch": 0.5666290791047326, "grad_norm": 2.3577942848205566, "learning_rate": 4.1689847816947e-05, "loss": 0.9096, "step": 10364 }, { "epoch": 0.5666837519220912, "grad_norm": 2.659162998199463, "learning_rate": 4.1681117539272e-05, "loss": 1.1524, "step": 10365 }, { "epoch": 0.5667384247394499, "grad_norm": 3.0013787746429443, "learning_rate": 4.167238752242822e-05, "loss": 1.1188, "step": 10366 }, { "epoch": 0.5667930975568085, "grad_norm": 2.8025684356689453, "learning_rate": 4.166365776668939e-05, "loss": 1.0706, "step": 10367 }, { "epoch": 0.5668477703741671, "grad_norm": 2.8618216514587402, "learning_rate": 4.16549282723292e-05, "loss": 0.9926, "step": 10368 }, { "epoch": 0.5669024431915257, "grad_norm": 3.0342297554016113, "learning_rate": 4.16461990396214e-05, "loss": 0.9232, "step": 10369 }, { "epoch": 0.5669571160088843, "grad_norm": 2.596970796585083, "learning_rate": 4.163747006883967e-05, "loss": 1.0213, "step": 10370 }, { "epoch": 0.5670117888262429, "grad_norm": 2.854912281036377, "learning_rate": 4.162874136025769e-05, "loss": 1.1218, "step": 10371 }, { "epoch": 0.5670664616436015, "grad_norm": 2.117215394973755, "learning_rate": 4.1620012914149145e-05, "loss": 0.9476, "step": 10372 }, { "epoch": 0.5671211344609602, "grad_norm": 2.2040483951568604, "learning_rate": 4.1611284730787706e-05, "loss": 0.9201, "step": 10373 }, { "epoch": 0.5671758072783188, "grad_norm": 2.8704323768615723, "learning_rate": 4.160255681044703e-05, "loss": 1.1242, "step": 10374 }, { "epoch": 0.5672304800956774, "grad_norm": 2.996661424636841, "learning_rate": 4.15938291534008e-05, "loss": 0.9219, "step": 10375 }, { "epoch": 0.567285152913036, "grad_norm": 2.048470973968506, "learning_rate": 4.158510175992264e-05, "loss": 1.0823, "step": 10376 }, { "epoch": 0.5673398257303947, "grad_norm": 2.993779182434082, "learning_rate": 4.1576374630286194e-05, "loss": 1.1242, "step": 10377 }, { "epoch": 0.5673944985477533, "grad_norm": 4.7708539962768555, "learning_rate": 4.156764776476508e-05, "loss": 1.0313, "step": 10378 }, { "epoch": 0.5674491713651119, "grad_norm": 2.280259370803833, "learning_rate": 4.155892116363295e-05, "loss": 0.9013, "step": 10379 }, { "epoch": 0.5675038441824706, "grad_norm": 3.5478742122650146, "learning_rate": 4.15501948271634e-05, "loss": 1.1984, "step": 10380 }, { "epoch": 0.5675585169998292, "grad_norm": 2.3928070068359375, "learning_rate": 4.154146875563005e-05, "loss": 0.9976, "step": 10381 }, { "epoch": 0.5676131898171878, "grad_norm": 2.5003714561462402, "learning_rate": 4.153274294930649e-05, "loss": 1.1352, "step": 10382 }, { "epoch": 0.5676678626345464, "grad_norm": 2.722825765609741, "learning_rate": 4.152401740846631e-05, "loss": 1.0498, "step": 10383 }, { "epoch": 0.567722535451905, "grad_norm": 4.967984199523926, "learning_rate": 4.1515292133383095e-05, "loss": 1.2213, "step": 10384 }, { "epoch": 0.5677772082692636, "grad_norm": 2.9779138565063477, "learning_rate": 4.150656712433041e-05, "loss": 0.9978, "step": 10385 }, { "epoch": 0.5678318810866222, "grad_norm": 3.032851219177246, "learning_rate": 4.149784238158183e-05, "loss": 0.9128, "step": 10386 }, { "epoch": 0.5678865539039809, "grad_norm": 2.493696451187134, "learning_rate": 4.148911790541091e-05, "loss": 0.7141, "step": 10387 }, { "epoch": 0.5679412267213395, "grad_norm": 2.399465799331665, "learning_rate": 4.148039369609117e-05, "loss": 0.9579, "step": 10388 }, { "epoch": 0.5679958995386981, "grad_norm": 3.0015957355499268, "learning_rate": 4.1471669753896206e-05, "loss": 1.1556, "step": 10389 }, { "epoch": 0.5680505723560567, "grad_norm": 2.3852717876434326, "learning_rate": 4.14629460790995e-05, "loss": 1.0855, "step": 10390 }, { "epoch": 0.5681052451734153, "grad_norm": 3.493877410888672, "learning_rate": 4.145422267197461e-05, "loss": 1.0303, "step": 10391 }, { "epoch": 0.5681599179907739, "grad_norm": 2.8736934661865234, "learning_rate": 4.144549953279502e-05, "loss": 1.1327, "step": 10392 }, { "epoch": 0.5682145908081326, "grad_norm": 2.9638144969940186, "learning_rate": 4.1436776661834245e-05, "loss": 0.9106, "step": 10393 }, { "epoch": 0.5682692636254912, "grad_norm": 2.6167829036712646, "learning_rate": 4.14280540593658e-05, "loss": 0.9516, "step": 10394 }, { "epoch": 0.5683239364428498, "grad_norm": 2.2259998321533203, "learning_rate": 4.141933172566317e-05, "loss": 1.1246, "step": 10395 }, { "epoch": 0.5683786092602084, "grad_norm": 2.590139150619507, "learning_rate": 4.1410609660999824e-05, "loss": 0.8459, "step": 10396 }, { "epoch": 0.568433282077567, "grad_norm": 3.3493053913116455, "learning_rate": 4.140188786564924e-05, "loss": 1.2198, "step": 10397 }, { "epoch": 0.5684879548949257, "grad_norm": 2.5284011363983154, "learning_rate": 4.139316633988487e-05, "loss": 1.0781, "step": 10398 }, { "epoch": 0.5685426277122843, "grad_norm": 3.745347499847412, "learning_rate": 4.1384445083980186e-05, "loss": 1.0052, "step": 10399 }, { "epoch": 0.568597300529643, "grad_norm": 2.5339348316192627, "learning_rate": 4.137572409820864e-05, "loss": 0.9576, "step": 10400 }, { "epoch": 0.5686519733470016, "grad_norm": 3.351139545440674, "learning_rate": 4.136700338284366e-05, "loss": 1.1682, "step": 10401 }, { "epoch": 0.5687066461643602, "grad_norm": 3.0806543827056885, "learning_rate": 4.1358282938158674e-05, "loss": 1.0596, "step": 10402 }, { "epoch": 0.5687613189817188, "grad_norm": 2.466367721557617, "learning_rate": 4.134956276442712e-05, "loss": 1.0372, "step": 10403 }, { "epoch": 0.5688159917990774, "grad_norm": 2.272099256515503, "learning_rate": 4.134084286192239e-05, "loss": 0.9989, "step": 10404 }, { "epoch": 0.568870664616436, "grad_norm": 3.1677463054656982, "learning_rate": 4.13321232309179e-05, "loss": 1.192, "step": 10405 }, { "epoch": 0.5689253374337946, "grad_norm": 2.6859242916107178, "learning_rate": 4.1323403871687033e-05, "loss": 1.0165, "step": 10406 }, { "epoch": 0.5689800102511533, "grad_norm": 2.3162150382995605, "learning_rate": 4.13146847845032e-05, "loss": 0.9493, "step": 10407 }, { "epoch": 0.5690346830685119, "grad_norm": 3.145681619644165, "learning_rate": 4.130596596963976e-05, "loss": 1.0665, "step": 10408 }, { "epoch": 0.5690893558858705, "grad_norm": 2.9120376110076904, "learning_rate": 4.12972474273701e-05, "loss": 1.2116, "step": 10409 }, { "epoch": 0.5691440287032291, "grad_norm": 3.5415492057800293, "learning_rate": 4.128852915796758e-05, "loss": 1.0313, "step": 10410 }, { "epoch": 0.5691987015205877, "grad_norm": 2.429558277130127, "learning_rate": 4.127981116170555e-05, "loss": 1.116, "step": 10411 }, { "epoch": 0.5692533743379463, "grad_norm": 2.6775333881378174, "learning_rate": 4.1271093438857344e-05, "loss": 0.9589, "step": 10412 }, { "epoch": 0.5693080471553049, "grad_norm": 2.820289134979248, "learning_rate": 4.126237598969632e-05, "loss": 0.91, "step": 10413 }, { "epoch": 0.5693627199726636, "grad_norm": 3.195564031600952, "learning_rate": 4.125365881449578e-05, "loss": 1.1589, "step": 10414 }, { "epoch": 0.5694173927900222, "grad_norm": 2.3963818550109863, "learning_rate": 4.1244941913529066e-05, "loss": 1.1499, "step": 10415 }, { "epoch": 0.5694720656073808, "grad_norm": 2.4577128887176514, "learning_rate": 4.1236225287069486e-05, "loss": 0.9017, "step": 10416 }, { "epoch": 0.5695267384247394, "grad_norm": 2.4962801933288574, "learning_rate": 4.122750893539032e-05, "loss": 1.0463, "step": 10417 }, { "epoch": 0.569581411242098, "grad_norm": 2.2712252140045166, "learning_rate": 4.121879285876487e-05, "loss": 1.0205, "step": 10418 }, { "epoch": 0.5696360840594566, "grad_norm": 2.7204818725585938, "learning_rate": 4.1210077057466446e-05, "loss": 0.9556, "step": 10419 }, { "epoch": 0.5696907568768154, "grad_norm": 2.3885765075683594, "learning_rate": 4.120136153176831e-05, "loss": 1.1008, "step": 10420 }, { "epoch": 0.569745429694174, "grad_norm": 4.976446628570557, "learning_rate": 4.119264628194372e-05, "loss": 1.2479, "step": 10421 }, { "epoch": 0.5698001025115326, "grad_norm": 2.942326307296753, "learning_rate": 4.118393130826594e-05, "loss": 0.9724, "step": 10422 }, { "epoch": 0.5698547753288912, "grad_norm": 2.1906914710998535, "learning_rate": 4.1175216611008235e-05, "loss": 0.9799, "step": 10423 }, { "epoch": 0.5699094481462498, "grad_norm": 3.2057459354400635, "learning_rate": 4.1166502190443823e-05, "loss": 1.1837, "step": 10424 }, { "epoch": 0.5699641209636084, "grad_norm": 4.2367329597473145, "learning_rate": 4.1157788046845945e-05, "loss": 0.9368, "step": 10425 }, { "epoch": 0.570018793780967, "grad_norm": 2.6125540733337402, "learning_rate": 4.114907418048783e-05, "loss": 0.9352, "step": 10426 }, { "epoch": 0.5700734665983257, "grad_norm": 4.325918674468994, "learning_rate": 4.114036059164268e-05, "loss": 0.79, "step": 10427 }, { "epoch": 0.5701281394156843, "grad_norm": 2.514040231704712, "learning_rate": 4.113164728058373e-05, "loss": 0.9073, "step": 10428 }, { "epoch": 0.5701828122330429, "grad_norm": 2.635946273803711, "learning_rate": 4.112293424758416e-05, "loss": 1.1586, "step": 10429 }, { "epoch": 0.5702374850504015, "grad_norm": 2.3963701725006104, "learning_rate": 4.1114221492917153e-05, "loss": 1.1376, "step": 10430 }, { "epoch": 0.5702921578677601, "grad_norm": 2.777758836746216, "learning_rate": 4.11055090168559e-05, "loss": 0.988, "step": 10431 }, { "epoch": 0.5703468306851187, "grad_norm": 2.2863950729370117, "learning_rate": 4.109679681967358e-05, "loss": 0.9638, "step": 10432 }, { "epoch": 0.5704015035024773, "grad_norm": 2.8607213497161865, "learning_rate": 4.1088084901643343e-05, "loss": 0.9741, "step": 10433 }, { "epoch": 0.570456176319836, "grad_norm": 2.2024567127227783, "learning_rate": 4.107937326303835e-05, "loss": 0.9822, "step": 10434 }, { "epoch": 0.5705108491371946, "grad_norm": 2.96246337890625, "learning_rate": 4.1070661904131736e-05, "loss": 0.9191, "step": 10435 }, { "epoch": 0.5705655219545532, "grad_norm": 2.2554357051849365, "learning_rate": 4.106195082519665e-05, "loss": 1.0293, "step": 10436 }, { "epoch": 0.5706201947719118, "grad_norm": 2.1353566646575928, "learning_rate": 4.105324002650619e-05, "loss": 1.0649, "step": 10437 }, { "epoch": 0.5706748675892704, "grad_norm": 3.0578372478485107, "learning_rate": 4.104452950833354e-05, "loss": 1.0869, "step": 10438 }, { "epoch": 0.570729540406629, "grad_norm": 2.2109150886535645, "learning_rate": 4.103581927095176e-05, "loss": 1.0336, "step": 10439 }, { "epoch": 0.5707842132239876, "grad_norm": 6.373142242431641, "learning_rate": 4.102710931463396e-05, "loss": 1.0238, "step": 10440 }, { "epoch": 0.5708388860413464, "grad_norm": 2.8551557064056396, "learning_rate": 4.1018399639653245e-05, "loss": 1.1389, "step": 10441 }, { "epoch": 0.570893558858705, "grad_norm": 2.5712759494781494, "learning_rate": 4.100969024628269e-05, "loss": 1.0056, "step": 10442 }, { "epoch": 0.5709482316760636, "grad_norm": 2.971067428588867, "learning_rate": 4.100098113479537e-05, "loss": 1.182, "step": 10443 }, { "epoch": 0.5710029044934222, "grad_norm": 2.0156099796295166, "learning_rate": 4.0992272305464354e-05, "loss": 0.8275, "step": 10444 }, { "epoch": 0.5710575773107808, "grad_norm": 2.990112781524658, "learning_rate": 4.09835637585627e-05, "loss": 1.081, "step": 10445 }, { "epoch": 0.5711122501281394, "grad_norm": 2.783926248550415, "learning_rate": 4.097485549436345e-05, "loss": 1.0171, "step": 10446 }, { "epoch": 0.5711669229454981, "grad_norm": 2.5302014350891113, "learning_rate": 4.0966147513139636e-05, "loss": 0.8925, "step": 10447 }, { "epoch": 0.5712215957628567, "grad_norm": 3.1283950805664062, "learning_rate": 4.0957439815164324e-05, "loss": 0.8328, "step": 10448 }, { "epoch": 0.5712762685802153, "grad_norm": 3.196240186691284, "learning_rate": 4.094873240071051e-05, "loss": 1.0976, "step": 10449 }, { "epoch": 0.5713309413975739, "grad_norm": 2.9269561767578125, "learning_rate": 4.094002527005121e-05, "loss": 1.2354, "step": 10450 }, { "epoch": 0.5713856142149325, "grad_norm": 2.5227513313293457, "learning_rate": 4.093131842345944e-05, "loss": 0.9569, "step": 10451 }, { "epoch": 0.5714402870322911, "grad_norm": 2.5968456268310547, "learning_rate": 4.092261186120818e-05, "loss": 1.2517, "step": 10452 }, { "epoch": 0.5714949598496497, "grad_norm": 2.3005480766296387, "learning_rate": 4.0913905583570425e-05, "loss": 0.9289, "step": 10453 }, { "epoch": 0.5715496326670084, "grad_norm": 2.9530105590820312, "learning_rate": 4.090519959081915e-05, "loss": 1.1365, "step": 10454 }, { "epoch": 0.571604305484367, "grad_norm": 2.5477137565612793, "learning_rate": 4.089649388322732e-05, "loss": 0.9078, "step": 10455 }, { "epoch": 0.5716589783017256, "grad_norm": 2.25970458984375, "learning_rate": 4.08877884610679e-05, "loss": 0.8606, "step": 10456 }, { "epoch": 0.5717136511190842, "grad_norm": 4.970610618591309, "learning_rate": 4.087908332461382e-05, "loss": 1.1174, "step": 10457 }, { "epoch": 0.5717683239364428, "grad_norm": 2.181105136871338, "learning_rate": 4.0870378474138064e-05, "loss": 1.0526, "step": 10458 }, { "epoch": 0.5718229967538014, "grad_norm": 3.1135823726654053, "learning_rate": 4.0861673909913544e-05, "loss": 0.9574, "step": 10459 }, { "epoch": 0.57187766957116, "grad_norm": 2.3827743530273438, "learning_rate": 4.0852969632213186e-05, "loss": 0.7401, "step": 10460 }, { "epoch": 0.5719323423885188, "grad_norm": 2.3894824981689453, "learning_rate": 4.084426564130989e-05, "loss": 1.0554, "step": 10461 }, { "epoch": 0.5719870152058774, "grad_norm": 2.683547019958496, "learning_rate": 4.083556193747658e-05, "loss": 1.0603, "step": 10462 }, { "epoch": 0.572041688023236, "grad_norm": 2.150965690612793, "learning_rate": 4.082685852098615e-05, "loss": 0.9815, "step": 10463 }, { "epoch": 0.5720963608405946, "grad_norm": 2.6475002765655518, "learning_rate": 4.081815539211148e-05, "loss": 0.9761, "step": 10464 }, { "epoch": 0.5721510336579532, "grad_norm": 3.2210302352905273, "learning_rate": 4.0809452551125455e-05, "loss": 1.1327, "step": 10465 }, { "epoch": 0.5722057064753118, "grad_norm": 2.2479093074798584, "learning_rate": 4.080074999830094e-05, "loss": 0.9492, "step": 10466 }, { "epoch": 0.5722603792926704, "grad_norm": 2.601545810699463, "learning_rate": 4.0792047733910776e-05, "loss": 0.9568, "step": 10467 }, { "epoch": 0.5723150521100291, "grad_norm": 3.3464040756225586, "learning_rate": 4.078334575822787e-05, "loss": 1.1698, "step": 10468 }, { "epoch": 0.5723697249273877, "grad_norm": 2.5841336250305176, "learning_rate": 4.077464407152502e-05, "loss": 0.9654, "step": 10469 }, { "epoch": 0.5724243977447463, "grad_norm": 1.982918620109558, "learning_rate": 4.076594267407508e-05, "loss": 0.9666, "step": 10470 }, { "epoch": 0.5724790705621049, "grad_norm": 2.8887879848480225, "learning_rate": 4.075724156615086e-05, "loss": 1.1582, "step": 10471 }, { "epoch": 0.5725337433794635, "grad_norm": 2.682485580444336, "learning_rate": 4.074854074802519e-05, "loss": 1.0537, "step": 10472 }, { "epoch": 0.5725884161968221, "grad_norm": 2.9991655349731445, "learning_rate": 4.0739840219970874e-05, "loss": 1.074, "step": 10473 }, { "epoch": 0.5726430890141808, "grad_norm": 2.5903334617614746, "learning_rate": 4.0731139982260694e-05, "loss": 1.0628, "step": 10474 }, { "epoch": 0.5726977618315394, "grad_norm": 2.3347978591918945, "learning_rate": 4.072244003516745e-05, "loss": 0.9701, "step": 10475 }, { "epoch": 0.572752434648898, "grad_norm": 2.6533467769622803, "learning_rate": 4.07137403789639e-05, "loss": 1.0815, "step": 10476 }, { "epoch": 0.5728071074662566, "grad_norm": 2.7152445316314697, "learning_rate": 4.070504101392286e-05, "loss": 1.1185, "step": 10477 }, { "epoch": 0.5728617802836152, "grad_norm": 2.0825271606445312, "learning_rate": 4.069634194031706e-05, "loss": 0.8249, "step": 10478 }, { "epoch": 0.5729164531009738, "grad_norm": 2.512906551361084, "learning_rate": 4.068764315841926e-05, "loss": 0.9872, "step": 10479 }, { "epoch": 0.5729711259183324, "grad_norm": 3.4777183532714844, "learning_rate": 4.067894466850218e-05, "loss": 1.0791, "step": 10480 }, { "epoch": 0.5730257987356911, "grad_norm": 3.189575672149658, "learning_rate": 4.06702464708386e-05, "loss": 1.1041, "step": 10481 }, { "epoch": 0.5730804715530498, "grad_norm": 2.979349136352539, "learning_rate": 4.06615485657012e-05, "loss": 1.0984, "step": 10482 }, { "epoch": 0.5731351443704084, "grad_norm": 2.4670612812042236, "learning_rate": 4.065285095336272e-05, "loss": 0.8949, "step": 10483 }, { "epoch": 0.573189817187767, "grad_norm": 2.9847846031188965, "learning_rate": 4.0644153634095855e-05, "loss": 1.0003, "step": 10484 }, { "epoch": 0.5732444900051256, "grad_norm": 3.1925182342529297, "learning_rate": 4.063545660817331e-05, "loss": 1.0655, "step": 10485 }, { "epoch": 0.5732991628224842, "grad_norm": 4.485002040863037, "learning_rate": 4.062675987586775e-05, "loss": 1.1239, "step": 10486 }, { "epoch": 0.5733538356398428, "grad_norm": 2.2581229209899902, "learning_rate": 4.061806343745189e-05, "loss": 1.0574, "step": 10487 }, { "epoch": 0.5734085084572015, "grad_norm": 2.806992530822754, "learning_rate": 4.060936729319837e-05, "loss": 1.1647, "step": 10488 }, { "epoch": 0.5734631812745601, "grad_norm": 4.263067245483398, "learning_rate": 4.060067144337987e-05, "loss": 0.8487, "step": 10489 }, { "epoch": 0.5735178540919187, "grad_norm": 2.4514386653900146, "learning_rate": 4.059197588826902e-05, "loss": 1.0569, "step": 10490 }, { "epoch": 0.5735725269092773, "grad_norm": 2.6202852725982666, "learning_rate": 4.058328062813848e-05, "loss": 1.1447, "step": 10491 }, { "epoch": 0.5736271997266359, "grad_norm": 3.229187250137329, "learning_rate": 4.057458566326087e-05, "loss": 1.0695, "step": 10492 }, { "epoch": 0.5736818725439945, "grad_norm": 2.6451644897460938, "learning_rate": 4.056589099390881e-05, "loss": 1.0394, "step": 10493 }, { "epoch": 0.5737365453613531, "grad_norm": 3.047943115234375, "learning_rate": 4.055719662035493e-05, "loss": 1.0203, "step": 10494 }, { "epoch": 0.5737912181787118, "grad_norm": 3.1720588207244873, "learning_rate": 4.0548502542871824e-05, "loss": 1.0648, "step": 10495 }, { "epoch": 0.5738458909960704, "grad_norm": 2.9689271450042725, "learning_rate": 4.0539808761732084e-05, "loss": 1.1298, "step": 10496 }, { "epoch": 0.573900563813429, "grad_norm": 2.2940256595611572, "learning_rate": 4.0531115277208307e-05, "loss": 0.9331, "step": 10497 }, { "epoch": 0.5739552366307876, "grad_norm": 2.8267571926116943, "learning_rate": 4.052242208957307e-05, "loss": 1.0328, "step": 10498 }, { "epoch": 0.5740099094481462, "grad_norm": 3.246598482131958, "learning_rate": 4.051372919909892e-05, "loss": 1.117, "step": 10499 }, { "epoch": 0.5740645822655048, "grad_norm": 2.5798633098602295, "learning_rate": 4.0505036606058434e-05, "loss": 1.3017, "step": 10500 }, { "epoch": 0.5741192550828634, "grad_norm": 2.626892566680908, "learning_rate": 4.049634431072416e-05, "loss": 1.1797, "step": 10501 }, { "epoch": 0.5741739279002221, "grad_norm": 2.741666555404663, "learning_rate": 4.0487652313368625e-05, "loss": 1.1472, "step": 10502 }, { "epoch": 0.5742286007175808, "grad_norm": 3.1848807334899902, "learning_rate": 4.0478960614264364e-05, "loss": 1.1267, "step": 10503 }, { "epoch": 0.5742832735349394, "grad_norm": 2.076796054840088, "learning_rate": 4.047026921368391e-05, "loss": 0.975, "step": 10504 }, { "epoch": 0.574337946352298, "grad_norm": 2.5721707344055176, "learning_rate": 4.046157811189975e-05, "loss": 0.7205, "step": 10505 }, { "epoch": 0.5743926191696566, "grad_norm": 2.992461919784546, "learning_rate": 4.045288730918439e-05, "loss": 1.1382, "step": 10506 }, { "epoch": 0.5744472919870152, "grad_norm": 2.950761318206787, "learning_rate": 4.044419680581035e-05, "loss": 1.1666, "step": 10507 }, { "epoch": 0.5745019648043739, "grad_norm": 2.97153902053833, "learning_rate": 4.043550660205009e-05, "loss": 1.0164, "step": 10508 }, { "epoch": 0.5745566376217325, "grad_norm": 3.590555429458618, "learning_rate": 4.0426816698176096e-05, "loss": 1.0036, "step": 10509 }, { "epoch": 0.5746113104390911, "grad_norm": 2.738844633102417, "learning_rate": 4.041812709446082e-05, "loss": 1.0214, "step": 10510 }, { "epoch": 0.5746659832564497, "grad_norm": 2.911916971206665, "learning_rate": 4.040943779117673e-05, "loss": 1.0226, "step": 10511 }, { "epoch": 0.5747206560738083, "grad_norm": 2.3060386180877686, "learning_rate": 4.040074878859625e-05, "loss": 0.9399, "step": 10512 }, { "epoch": 0.5747753288911669, "grad_norm": 3.578054189682007, "learning_rate": 4.039206008699184e-05, "loss": 1.1353, "step": 10513 }, { "epoch": 0.5748300017085255, "grad_norm": 2.3081517219543457, "learning_rate": 4.038337168663591e-05, "loss": 1.0591, "step": 10514 }, { "epoch": 0.5748846745258842, "grad_norm": 3.4443013668060303, "learning_rate": 4.037468358780089e-05, "loss": 1.0841, "step": 10515 }, { "epoch": 0.5749393473432428, "grad_norm": 2.774986982345581, "learning_rate": 4.0365995790759154e-05, "loss": 1.0546, "step": 10516 }, { "epoch": 0.5749940201606014, "grad_norm": 2.173128128051758, "learning_rate": 4.035730829578315e-05, "loss": 0.9479, "step": 10517 }, { "epoch": 0.57504869297796, "grad_norm": 2.700596570968628, "learning_rate": 4.034862110314524e-05, "loss": 0.8642, "step": 10518 }, { "epoch": 0.5751033657953186, "grad_norm": 4.595466613769531, "learning_rate": 4.0339934213117816e-05, "loss": 1.065, "step": 10519 }, { "epoch": 0.5751580386126772, "grad_norm": 2.7065062522888184, "learning_rate": 4.033124762597323e-05, "loss": 0.8883, "step": 10520 }, { "epoch": 0.5752127114300358, "grad_norm": 2.2387049198150635, "learning_rate": 4.032256134198385e-05, "loss": 0.8795, "step": 10521 }, { "epoch": 0.5752673842473945, "grad_norm": 2.7658073902130127, "learning_rate": 4.031387536142203e-05, "loss": 1.1228, "step": 10522 }, { "epoch": 0.5753220570647531, "grad_norm": 2.451977014541626, "learning_rate": 4.0305189684560113e-05, "loss": 0.9409, "step": 10523 }, { "epoch": 0.5753767298821117, "grad_norm": 2.2951016426086426, "learning_rate": 4.029650431167042e-05, "loss": 0.8198, "step": 10524 }, { "epoch": 0.5754314026994704, "grad_norm": 2.469600200653076, "learning_rate": 4.028781924302527e-05, "loss": 1.056, "step": 10525 }, { "epoch": 0.575486075516829, "grad_norm": 3.0487911701202393, "learning_rate": 4.0279134478897e-05, "loss": 1.1796, "step": 10526 }, { "epoch": 0.5755407483341876, "grad_norm": 3.3382914066314697, "learning_rate": 4.02704500195579e-05, "loss": 1.2136, "step": 10527 }, { "epoch": 0.5755954211515462, "grad_norm": 2.537606954574585, "learning_rate": 4.026176586528025e-05, "loss": 1.0797, "step": 10528 }, { "epoch": 0.5756500939689049, "grad_norm": 2.824282169342041, "learning_rate": 4.0253082016336365e-05, "loss": 1.1308, "step": 10529 }, { "epoch": 0.5757047667862635, "grad_norm": 3.2217612266540527, "learning_rate": 4.024439847299849e-05, "loss": 1.3234, "step": 10530 }, { "epoch": 0.5757594396036221, "grad_norm": 1.909704566001892, "learning_rate": 4.023571523553891e-05, "loss": 0.9934, "step": 10531 }, { "epoch": 0.5758141124209807, "grad_norm": 2.4052045345306396, "learning_rate": 4.022703230422986e-05, "loss": 0.8924, "step": 10532 }, { "epoch": 0.5758687852383393, "grad_norm": 2.297316074371338, "learning_rate": 4.02183496793436e-05, "loss": 1.0979, "step": 10533 }, { "epoch": 0.5759234580556979, "grad_norm": 2.2393524646759033, "learning_rate": 4.020966736115237e-05, "loss": 1.0007, "step": 10534 }, { "epoch": 0.5759781308730566, "grad_norm": 2.1607353687286377, "learning_rate": 4.020098534992836e-05, "loss": 0.906, "step": 10535 }, { "epoch": 0.5760328036904152, "grad_norm": 3.7186191082000732, "learning_rate": 4.019230364594384e-05, "loss": 1.0328, "step": 10536 }, { "epoch": 0.5760874765077738, "grad_norm": 2.0170655250549316, "learning_rate": 4.018362224947099e-05, "loss": 0.8268, "step": 10537 }, { "epoch": 0.5761421493251324, "grad_norm": 2.632305145263672, "learning_rate": 4.017494116078201e-05, "loss": 1.1878, "step": 10538 }, { "epoch": 0.576196822142491, "grad_norm": 3.998126268386841, "learning_rate": 4.016626038014909e-05, "loss": 1.205, "step": 10539 }, { "epoch": 0.5762514949598496, "grad_norm": 2.492316961288452, "learning_rate": 4.015757990784441e-05, "loss": 1.2561, "step": 10540 }, { "epoch": 0.5763061677772082, "grad_norm": 2.8559327125549316, "learning_rate": 4.014889974414014e-05, "loss": 0.9341, "step": 10541 }, { "epoch": 0.5763608405945669, "grad_norm": 2.2711997032165527, "learning_rate": 4.014021988930842e-05, "loss": 1.0944, "step": 10542 }, { "epoch": 0.5764155134119255, "grad_norm": 2.23410701751709, "learning_rate": 4.013154034362142e-05, "loss": 1.0213, "step": 10543 }, { "epoch": 0.5764701862292841, "grad_norm": 3.3252274990081787, "learning_rate": 4.012286110735127e-05, "loss": 1.1879, "step": 10544 }, { "epoch": 0.5765248590466427, "grad_norm": 2.468144655227661, "learning_rate": 4.0114182180770086e-05, "loss": 0.8169, "step": 10545 }, { "epoch": 0.5765795318640013, "grad_norm": 2.4185080528259277, "learning_rate": 4.0105503564150024e-05, "loss": 0.9629, "step": 10546 }, { "epoch": 0.57663420468136, "grad_norm": 2.2397334575653076, "learning_rate": 4.009682525776318e-05, "loss": 1.0236, "step": 10547 }, { "epoch": 0.5766888774987186, "grad_norm": 2.0732312202453613, "learning_rate": 4.0088147261881644e-05, "loss": 0.9704, "step": 10548 }, { "epoch": 0.5767435503160773, "grad_norm": 2.290557861328125, "learning_rate": 4.0079469576777514e-05, "loss": 0.9532, "step": 10549 }, { "epoch": 0.5767982231334359, "grad_norm": 1.9888004064559937, "learning_rate": 4.007079220272287e-05, "loss": 0.9414, "step": 10550 }, { "epoch": 0.5768528959507945, "grad_norm": 2.8712193965911865, "learning_rate": 4.0062115139989784e-05, "loss": 0.9618, "step": 10551 }, { "epoch": 0.5769075687681531, "grad_norm": 3.0473570823669434, "learning_rate": 4.005343838885031e-05, "loss": 1.0431, "step": 10552 }, { "epoch": 0.5769622415855117, "grad_norm": 2.5355594158172607, "learning_rate": 4.004476194957652e-05, "loss": 0.9752, "step": 10553 }, { "epoch": 0.5770169144028703, "grad_norm": 2.9340548515319824, "learning_rate": 4.003608582244043e-05, "loss": 1.1011, "step": 10554 }, { "epoch": 0.5770715872202289, "grad_norm": 2.326842784881592, "learning_rate": 4.002741000771407e-05, "loss": 1.0284, "step": 10555 }, { "epoch": 0.5771262600375876, "grad_norm": 3.5574820041656494, "learning_rate": 4.00187345056695e-05, "loss": 1.0158, "step": 10556 }, { "epoch": 0.5771809328549462, "grad_norm": 2.4719743728637695, "learning_rate": 4.0010059316578706e-05, "loss": 0.833, "step": 10557 }, { "epoch": 0.5772356056723048, "grad_norm": 2.797973155975342, "learning_rate": 4.00013844407137e-05, "loss": 1.2123, "step": 10558 }, { "epoch": 0.5772902784896634, "grad_norm": 2.5325260162353516, "learning_rate": 3.999270987834646e-05, "loss": 0.9124, "step": 10559 }, { "epoch": 0.577344951307022, "grad_norm": 3.114271879196167, "learning_rate": 3.9984035629749e-05, "loss": 1.1129, "step": 10560 }, { "epoch": 0.5773996241243806, "grad_norm": 2.547419786453247, "learning_rate": 3.9975361695193255e-05, "loss": 1.1496, "step": 10561 }, { "epoch": 0.5774542969417393, "grad_norm": 2.753340482711792, "learning_rate": 3.9966688074951206e-05, "loss": 1.0984, "step": 10562 }, { "epoch": 0.5775089697590979, "grad_norm": 3.0990378856658936, "learning_rate": 3.9958014769294816e-05, "loss": 1.0719, "step": 10563 }, { "epoch": 0.5775636425764565, "grad_norm": 3.0746030807495117, "learning_rate": 3.994934177849602e-05, "loss": 1.0868, "step": 10564 }, { "epoch": 0.5776183153938151, "grad_norm": 2.7228620052337646, "learning_rate": 3.994066910282674e-05, "loss": 0.8945, "step": 10565 }, { "epoch": 0.5776729882111737, "grad_norm": 2.494069814682007, "learning_rate": 3.993199674255892e-05, "loss": 1.0433, "step": 10566 }, { "epoch": 0.5777276610285323, "grad_norm": 2.5871598720550537, "learning_rate": 3.992332469796446e-05, "loss": 1.0972, "step": 10567 }, { "epoch": 0.577782333845891, "grad_norm": 3.699025869369507, "learning_rate": 3.991465296931528e-05, "loss": 0.9614, "step": 10568 }, { "epoch": 0.5778370066632497, "grad_norm": 8.922294616699219, "learning_rate": 3.990598155688326e-05, "loss": 1.1489, "step": 10569 }, { "epoch": 0.5778916794806083, "grad_norm": 2.6142232418060303, "learning_rate": 3.98973104609403e-05, "loss": 0.9718, "step": 10570 }, { "epoch": 0.5779463522979669, "grad_norm": 2.3516032695770264, "learning_rate": 3.988863968175826e-05, "loss": 1.0527, "step": 10571 }, { "epoch": 0.5780010251153255, "grad_norm": 3.209195852279663, "learning_rate": 3.9879969219609005e-05, "loss": 1.2654, "step": 10572 }, { "epoch": 0.5780556979326841, "grad_norm": 2.4272329807281494, "learning_rate": 3.98712990747644e-05, "loss": 0.9716, "step": 10573 }, { "epoch": 0.5781103707500427, "grad_norm": 2.7120652198791504, "learning_rate": 3.986262924749628e-05, "loss": 1.2574, "step": 10574 }, { "epoch": 0.5781650435674013, "grad_norm": 2.5099501609802246, "learning_rate": 3.985395973807647e-05, "loss": 1.011, "step": 10575 }, { "epoch": 0.57821971638476, "grad_norm": 4.224826335906982, "learning_rate": 3.984529054677682e-05, "loss": 1.0094, "step": 10576 }, { "epoch": 0.5782743892021186, "grad_norm": 2.7765402793884277, "learning_rate": 3.983662167386913e-05, "loss": 1.0621, "step": 10577 }, { "epoch": 0.5783290620194772, "grad_norm": 2.353482723236084, "learning_rate": 3.982795311962521e-05, "loss": 0.9724, "step": 10578 }, { "epoch": 0.5783837348368358, "grad_norm": 2.350281000137329, "learning_rate": 3.981928488431686e-05, "loss": 1.134, "step": 10579 }, { "epoch": 0.5784384076541944, "grad_norm": 2.7353622913360596, "learning_rate": 3.981061696821584e-05, "loss": 0.9486, "step": 10580 }, { "epoch": 0.578493080471553, "grad_norm": 2.056424856185913, "learning_rate": 3.9801949371593954e-05, "loss": 0.9132, "step": 10581 }, { "epoch": 0.5785477532889116, "grad_norm": 2.701495409011841, "learning_rate": 3.979328209472296e-05, "loss": 1.1505, "step": 10582 }, { "epoch": 0.5786024261062703, "grad_norm": 2.223292350769043, "learning_rate": 3.97846151378746e-05, "loss": 0.9143, "step": 10583 }, { "epoch": 0.5786570989236289, "grad_norm": 2.6535675525665283, "learning_rate": 3.977594850132062e-05, "loss": 1.0242, "step": 10584 }, { "epoch": 0.5787117717409875, "grad_norm": 3.8294312953948975, "learning_rate": 3.976728218533277e-05, "loss": 1.1348, "step": 10585 }, { "epoch": 0.5787664445583461, "grad_norm": 3.021907091140747, "learning_rate": 3.975861619018277e-05, "loss": 1.304, "step": 10586 }, { "epoch": 0.5788211173757047, "grad_norm": 3.323946714401245, "learning_rate": 3.9749950516142325e-05, "loss": 1.0598, "step": 10587 }, { "epoch": 0.5788757901930633, "grad_norm": 2.6516711711883545, "learning_rate": 3.974128516348315e-05, "loss": 1.0959, "step": 10588 }, { "epoch": 0.5789304630104221, "grad_norm": 3.6284821033477783, "learning_rate": 3.9732620132476937e-05, "loss": 0.925, "step": 10589 }, { "epoch": 0.5789851358277807, "grad_norm": 2.4264166355133057, "learning_rate": 3.9723955423395366e-05, "loss": 0.9242, "step": 10590 }, { "epoch": 0.5790398086451393, "grad_norm": 3.0994555950164795, "learning_rate": 3.971529103651011e-05, "loss": 1.2136, "step": 10591 }, { "epoch": 0.5790944814624979, "grad_norm": 2.9340662956237793, "learning_rate": 3.9706626972092844e-05, "loss": 1.1117, "step": 10592 }, { "epoch": 0.5791491542798565, "grad_norm": 2.6167733669281006, "learning_rate": 3.96979632304152e-05, "loss": 1.189, "step": 10593 }, { "epoch": 0.5792038270972151, "grad_norm": 2.874238967895508, "learning_rate": 3.968929981174884e-05, "loss": 0.8475, "step": 10594 }, { "epoch": 0.5792584999145737, "grad_norm": 2.6340725421905518, "learning_rate": 3.9680636716365395e-05, "loss": 0.8931, "step": 10595 }, { "epoch": 0.5793131727319324, "grad_norm": 2.7573928833007812, "learning_rate": 3.96719739445365e-05, "loss": 1.1385, "step": 10596 }, { "epoch": 0.579367845549291, "grad_norm": 2.677847385406494, "learning_rate": 3.966331149653375e-05, "loss": 1.1337, "step": 10597 }, { "epoch": 0.5794225183666496, "grad_norm": 2.4940783977508545, "learning_rate": 3.965464937262876e-05, "loss": 0.8914, "step": 10598 }, { "epoch": 0.5794771911840082, "grad_norm": 2.8162808418273926, "learning_rate": 3.964598757309312e-05, "loss": 0.9222, "step": 10599 }, { "epoch": 0.5795318640013668, "grad_norm": 3.24996280670166, "learning_rate": 3.9637326098198405e-05, "loss": 1.1113, "step": 10600 }, { "epoch": 0.5795865368187254, "grad_norm": 2.6784093379974365, "learning_rate": 3.96286649482162e-05, "loss": 0.9765, "step": 10601 }, { "epoch": 0.579641209636084, "grad_norm": 2.472166061401367, "learning_rate": 3.962000412341806e-05, "loss": 0.8815, "step": 10602 }, { "epoch": 0.5796958824534427, "grad_norm": 2.920283794403076, "learning_rate": 3.961134362407554e-05, "loss": 1.082, "step": 10603 }, { "epoch": 0.5797505552708013, "grad_norm": 3.2131593227386475, "learning_rate": 3.9602683450460164e-05, "loss": 1.0711, "step": 10604 }, { "epoch": 0.5798052280881599, "grad_norm": 2.576098680496216, "learning_rate": 3.95940236028435e-05, "loss": 1.0767, "step": 10605 }, { "epoch": 0.5798599009055185, "grad_norm": 2.5338244438171387, "learning_rate": 3.9585364081497055e-05, "loss": 0.9546, "step": 10606 }, { "epoch": 0.5799145737228771, "grad_norm": 2.392469882965088, "learning_rate": 3.957670488669234e-05, "loss": 0.9627, "step": 10607 }, { "epoch": 0.5799692465402357, "grad_norm": 2.3599064350128174, "learning_rate": 3.956804601870086e-05, "loss": 1.0441, "step": 10608 }, { "epoch": 0.5800239193575943, "grad_norm": 2.6215736865997314, "learning_rate": 3.9559387477794085e-05, "loss": 1.053, "step": 10609 }, { "epoch": 0.5800785921749531, "grad_norm": 3.0420265197753906, "learning_rate": 3.955072926424352e-05, "loss": 0.8731, "step": 10610 }, { "epoch": 0.5801332649923117, "grad_norm": 2.851897954940796, "learning_rate": 3.954207137832063e-05, "loss": 0.9404, "step": 10611 }, { "epoch": 0.5801879378096703, "grad_norm": 2.20934796333313, "learning_rate": 3.9533413820296866e-05, "loss": 0.9729, "step": 10612 }, { "epoch": 0.5802426106270289, "grad_norm": 3.1361429691314697, "learning_rate": 3.952475659044369e-05, "loss": 1.2039, "step": 10613 }, { "epoch": 0.5802972834443875, "grad_norm": 2.711461067199707, "learning_rate": 3.9516099689032514e-05, "loss": 1.0731, "step": 10614 }, { "epoch": 0.5803519562617461, "grad_norm": 2.2256102561950684, "learning_rate": 3.950744311633481e-05, "loss": 1.0297, "step": 10615 }, { "epoch": 0.5804066290791048, "grad_norm": 2.4186458587646484, "learning_rate": 3.949878687262197e-05, "loss": 0.695, "step": 10616 }, { "epoch": 0.5804613018964634, "grad_norm": 2.4187185764312744, "learning_rate": 3.9490130958165424e-05, "loss": 0.7514, "step": 10617 }, { "epoch": 0.580515974713822, "grad_norm": 2.430276870727539, "learning_rate": 3.948147537323655e-05, "loss": 1.0159, "step": 10618 }, { "epoch": 0.5805706475311806, "grad_norm": 3.560664176940918, "learning_rate": 3.9472820118106744e-05, "loss": 1.0259, "step": 10619 }, { "epoch": 0.5806253203485392, "grad_norm": 2.5645973682403564, "learning_rate": 3.946416519304738e-05, "loss": 1.033, "step": 10620 }, { "epoch": 0.5806799931658978, "grad_norm": 3.0149691104888916, "learning_rate": 3.945551059832983e-05, "loss": 1.0474, "step": 10621 }, { "epoch": 0.5807346659832564, "grad_norm": 2.2990078926086426, "learning_rate": 3.944685633422545e-05, "loss": 0.9887, "step": 10622 }, { "epoch": 0.5807893388006151, "grad_norm": 3.081294536590576, "learning_rate": 3.943820240100559e-05, "loss": 1.0712, "step": 10623 }, { "epoch": 0.5808440116179737, "grad_norm": 2.43465518951416, "learning_rate": 3.942954879894155e-05, "loss": 0.896, "step": 10624 }, { "epoch": 0.5808986844353323, "grad_norm": 2.614017963409424, "learning_rate": 3.9420895528304716e-05, "loss": 1.1122, "step": 10625 }, { "epoch": 0.5809533572526909, "grad_norm": 3.9172496795654297, "learning_rate": 3.941224258936638e-05, "loss": 0.9844, "step": 10626 }, { "epoch": 0.5810080300700495, "grad_norm": 2.304750680923462, "learning_rate": 3.9403589982397845e-05, "loss": 0.9663, "step": 10627 }, { "epoch": 0.5810627028874081, "grad_norm": 2.305609941482544, "learning_rate": 3.93949377076704e-05, "loss": 1.0786, "step": 10628 }, { "epoch": 0.5811173757047667, "grad_norm": 2.2409603595733643, "learning_rate": 3.938628576545533e-05, "loss": 0.9277, "step": 10629 }, { "epoch": 0.5811720485221255, "grad_norm": 2.4574413299560547, "learning_rate": 3.937763415602392e-05, "loss": 0.9293, "step": 10630 }, { "epoch": 0.581226721339484, "grad_norm": 1.9150646924972534, "learning_rate": 3.936898287964743e-05, "loss": 0.9756, "step": 10631 }, { "epoch": 0.5812813941568427, "grad_norm": 3.0813558101654053, "learning_rate": 3.936033193659711e-05, "loss": 1.1817, "step": 10632 }, { "epoch": 0.5813360669742013, "grad_norm": 2.680332660675049, "learning_rate": 3.935168132714417e-05, "loss": 1.1779, "step": 10633 }, { "epoch": 0.5813907397915599, "grad_norm": 3.3084728717803955, "learning_rate": 3.93430310515599e-05, "loss": 1.0956, "step": 10634 }, { "epoch": 0.5814454126089185, "grad_norm": 2.968931198120117, "learning_rate": 3.9334381110115505e-05, "loss": 1.1369, "step": 10635 }, { "epoch": 0.5815000854262771, "grad_norm": 2.849268674850464, "learning_rate": 3.932573150308218e-05, "loss": 1.1444, "step": 10636 }, { "epoch": 0.5815547582436358, "grad_norm": 2.864386558532715, "learning_rate": 3.931708223073113e-05, "loss": 0.9048, "step": 10637 }, { "epoch": 0.5816094310609944, "grad_norm": 2.976440191268921, "learning_rate": 3.9308433293333556e-05, "loss": 1.0139, "step": 10638 }, { "epoch": 0.581664103878353, "grad_norm": 2.896207809448242, "learning_rate": 3.929978469116063e-05, "loss": 1.0867, "step": 10639 }, { "epoch": 0.5817187766957116, "grad_norm": 2.4241855144500732, "learning_rate": 3.929113642448352e-05, "loss": 0.9722, "step": 10640 }, { "epoch": 0.5817734495130702, "grad_norm": 2.8576369285583496, "learning_rate": 3.9282488493573385e-05, "loss": 1.0671, "step": 10641 }, { "epoch": 0.5818281223304288, "grad_norm": 2.401650905609131, "learning_rate": 3.927384089870139e-05, "loss": 0.9855, "step": 10642 }, { "epoch": 0.5818827951477875, "grad_norm": 2.7270610332489014, "learning_rate": 3.926519364013862e-05, "loss": 1.031, "step": 10643 }, { "epoch": 0.5819374679651461, "grad_norm": 2.5803182125091553, "learning_rate": 3.925654671815626e-05, "loss": 1.078, "step": 10644 }, { "epoch": 0.5819921407825047, "grad_norm": 2.4954144954681396, "learning_rate": 3.9247900133025414e-05, "loss": 1.1289, "step": 10645 }, { "epoch": 0.5820468135998633, "grad_norm": 2.464019775390625, "learning_rate": 3.923925388501718e-05, "loss": 0.9132, "step": 10646 }, { "epoch": 0.5821014864172219, "grad_norm": 3.2339041233062744, "learning_rate": 3.9230607974402656e-05, "loss": 0.9362, "step": 10647 }, { "epoch": 0.5821561592345805, "grad_norm": 2.320953130722046, "learning_rate": 3.922196240145292e-05, "loss": 0.7511, "step": 10648 }, { "epoch": 0.5822108320519391, "grad_norm": 2.743190050125122, "learning_rate": 3.921331716643905e-05, "loss": 1.2167, "step": 10649 }, { "epoch": 0.5822655048692978, "grad_norm": 2.500342845916748, "learning_rate": 3.920467226963211e-05, "loss": 0.9663, "step": 10650 }, { "epoch": 0.5823201776866564, "grad_norm": 2.7531898021698, "learning_rate": 3.9196027711303164e-05, "loss": 1.2892, "step": 10651 }, { "epoch": 0.582374850504015, "grad_norm": 2.6281769275665283, "learning_rate": 3.9187383491723236e-05, "loss": 1.0439, "step": 10652 }, { "epoch": 0.5824295233213737, "grad_norm": 3.1094789505004883, "learning_rate": 3.917873961116336e-05, "loss": 1.2118, "step": 10653 }, { "epoch": 0.5824841961387323, "grad_norm": 2.545689821243286, "learning_rate": 3.9170096069894566e-05, "loss": 0.9908, "step": 10654 }, { "epoch": 0.5825388689560909, "grad_norm": 2.5421674251556396, "learning_rate": 3.916145286818787e-05, "loss": 1.0715, "step": 10655 }, { "epoch": 0.5825935417734495, "grad_norm": 2.5241570472717285, "learning_rate": 3.915281000631427e-05, "loss": 1.1374, "step": 10656 }, { "epoch": 0.5826482145908082, "grad_norm": 2.705495834350586, "learning_rate": 3.914416748454474e-05, "loss": 1.0051, "step": 10657 }, { "epoch": 0.5827028874081668, "grad_norm": 2.5581753253936768, "learning_rate": 3.913552530315027e-05, "loss": 1.2126, "step": 10658 }, { "epoch": 0.5827575602255254, "grad_norm": 2.771484613418579, "learning_rate": 3.912688346240183e-05, "loss": 1.2001, "step": 10659 }, { "epoch": 0.582812233042884, "grad_norm": 5.13767671585083, "learning_rate": 3.9118241962570376e-05, "loss": 1.0808, "step": 10660 }, { "epoch": 0.5828669058602426, "grad_norm": 2.2540736198425293, "learning_rate": 3.910960080392685e-05, "loss": 1.0472, "step": 10661 }, { "epoch": 0.5829215786776012, "grad_norm": 3.2842466831207275, "learning_rate": 3.910095998674218e-05, "loss": 0.9844, "step": 10662 }, { "epoch": 0.5829762514949598, "grad_norm": 2.4018731117248535, "learning_rate": 3.90923195112873e-05, "loss": 0.9288, "step": 10663 }, { "epoch": 0.5830309243123185, "grad_norm": 2.3805806636810303, "learning_rate": 3.9083679377833136e-05, "loss": 0.8842, "step": 10664 }, { "epoch": 0.5830855971296771, "grad_norm": 2.913158416748047, "learning_rate": 3.907503958665059e-05, "loss": 1.1019, "step": 10665 }, { "epoch": 0.5831402699470357, "grad_norm": 2.4862918853759766, "learning_rate": 3.9066400138010537e-05, "loss": 1.0398, "step": 10666 }, { "epoch": 0.5831949427643943, "grad_norm": 2.5927963256835938, "learning_rate": 3.9057761032183854e-05, "loss": 0.876, "step": 10667 }, { "epoch": 0.5832496155817529, "grad_norm": 3.1756069660186768, "learning_rate": 3.9049122269441444e-05, "loss": 1.138, "step": 10668 }, { "epoch": 0.5833042883991115, "grad_norm": 2.9087209701538086, "learning_rate": 3.904048385005416e-05, "loss": 0.8981, "step": 10669 }, { "epoch": 0.5833589612164702, "grad_norm": 1.959430456161499, "learning_rate": 3.9031845774292825e-05, "loss": 0.8316, "step": 10670 }, { "epoch": 0.5834136340338288, "grad_norm": 2.326957941055298, "learning_rate": 3.9023208042428305e-05, "loss": 1.1468, "step": 10671 }, { "epoch": 0.5834683068511874, "grad_norm": 3.095750093460083, "learning_rate": 3.901457065473142e-05, "loss": 1.0478, "step": 10672 }, { "epoch": 0.583522979668546, "grad_norm": 2.8450379371643066, "learning_rate": 3.900593361147298e-05, "loss": 0.9283, "step": 10673 }, { "epoch": 0.5835776524859047, "grad_norm": 3.204777240753174, "learning_rate": 3.8997296912923805e-05, "loss": 0.9368, "step": 10674 }, { "epoch": 0.5836323253032633, "grad_norm": 2.63446044921875, "learning_rate": 3.898866055935469e-05, "loss": 1.0858, "step": 10675 }, { "epoch": 0.5836869981206219, "grad_norm": 2.680551767349243, "learning_rate": 3.898002455103642e-05, "loss": 1.1439, "step": 10676 }, { "epoch": 0.5837416709379806, "grad_norm": 2.551666736602783, "learning_rate": 3.8971388888239757e-05, "loss": 1.0865, "step": 10677 }, { "epoch": 0.5837963437553392, "grad_norm": 3.129082679748535, "learning_rate": 3.896275357123548e-05, "loss": 1.081, "step": 10678 }, { "epoch": 0.5838510165726978, "grad_norm": 2.9333975315093994, "learning_rate": 3.8954118600294326e-05, "loss": 1.1491, "step": 10679 }, { "epoch": 0.5839056893900564, "grad_norm": 2.790213108062744, "learning_rate": 3.894548397568704e-05, "loss": 1.2636, "step": 10680 }, { "epoch": 0.583960362207415, "grad_norm": 2.8718197345733643, "learning_rate": 3.8936849697684366e-05, "loss": 1.0688, "step": 10681 }, { "epoch": 0.5840150350247736, "grad_norm": 2.5239346027374268, "learning_rate": 3.8928215766557017e-05, "loss": 0.9264, "step": 10682 }, { "epoch": 0.5840697078421322, "grad_norm": 2.759105682373047, "learning_rate": 3.89195821825757e-05, "loss": 0.9678, "step": 10683 }, { "epoch": 0.5841243806594909, "grad_norm": 2.1128830909729004, "learning_rate": 3.8910948946011124e-05, "loss": 0.8722, "step": 10684 }, { "epoch": 0.5841790534768495, "grad_norm": 2.8948936462402344, "learning_rate": 3.890231605713396e-05, "loss": 1.1939, "step": 10685 }, { "epoch": 0.5842337262942081, "grad_norm": 2.601318836212158, "learning_rate": 3.8893683516214896e-05, "loss": 1.2388, "step": 10686 }, { "epoch": 0.5842883991115667, "grad_norm": 2.3007423877716064, "learning_rate": 3.8885051323524604e-05, "loss": 0.9695, "step": 10687 }, { "epoch": 0.5843430719289253, "grad_norm": 2.1598029136657715, "learning_rate": 3.8876419479333713e-05, "loss": 0.861, "step": 10688 }, { "epoch": 0.5843977447462839, "grad_norm": 3.1026084423065186, "learning_rate": 3.8867787983912894e-05, "loss": 1.1868, "step": 10689 }, { "epoch": 0.5844524175636425, "grad_norm": 3.3147025108337402, "learning_rate": 3.885915683753276e-05, "loss": 1.0206, "step": 10690 }, { "epoch": 0.5845070903810012, "grad_norm": 2.3579704761505127, "learning_rate": 3.885052604046395e-05, "loss": 1.0961, "step": 10691 }, { "epoch": 0.5845617631983598, "grad_norm": 2.4756150245666504, "learning_rate": 3.884189559297705e-05, "loss": 1.0708, "step": 10692 }, { "epoch": 0.5846164360157184, "grad_norm": 2.8866806030273438, "learning_rate": 3.883326549534268e-05, "loss": 1.2922, "step": 10693 }, { "epoch": 0.584671108833077, "grad_norm": 3.020824432373047, "learning_rate": 3.882463574783145e-05, "loss": 0.857, "step": 10694 }, { "epoch": 0.5847257816504356, "grad_norm": 3.068058729171753, "learning_rate": 3.8816006350713896e-05, "loss": 1.1395, "step": 10695 }, { "epoch": 0.5847804544677943, "grad_norm": 2.3889074325561523, "learning_rate": 3.8807377304260605e-05, "loss": 1.1674, "step": 10696 }, { "epoch": 0.584835127285153, "grad_norm": 2.6262006759643555, "learning_rate": 3.879874860874214e-05, "loss": 1.1646, "step": 10697 }, { "epoch": 0.5848898001025116, "grad_norm": 2.672638416290283, "learning_rate": 3.879012026442903e-05, "loss": 1.0788, "step": 10698 }, { "epoch": 0.5849444729198702, "grad_norm": 2.7854163646698, "learning_rate": 3.8781492271591824e-05, "loss": 1.1064, "step": 10699 }, { "epoch": 0.5849991457372288, "grad_norm": 3.0656232833862305, "learning_rate": 3.877286463050104e-05, "loss": 1.0501, "step": 10700 }, { "epoch": 0.5850538185545874, "grad_norm": 2.238344669342041, "learning_rate": 3.876423734142718e-05, "loss": 1.1522, "step": 10701 }, { "epoch": 0.585108491371946, "grad_norm": 2.9727275371551514, "learning_rate": 3.875561040464073e-05, "loss": 0.885, "step": 10702 }, { "epoch": 0.5851631641893046, "grad_norm": 2.606991767883301, "learning_rate": 3.8746983820412234e-05, "loss": 0.9468, "step": 10703 }, { "epoch": 0.5852178370066633, "grad_norm": 2.495445489883423, "learning_rate": 3.873835758901213e-05, "loss": 1.0855, "step": 10704 }, { "epoch": 0.5852725098240219, "grad_norm": 2.3295016288757324, "learning_rate": 3.87297317107109e-05, "loss": 0.7924, "step": 10705 }, { "epoch": 0.5853271826413805, "grad_norm": 3.394028663635254, "learning_rate": 3.8721106185779e-05, "loss": 1.0074, "step": 10706 }, { "epoch": 0.5853818554587391, "grad_norm": 3.033639430999756, "learning_rate": 3.8712481014486866e-05, "loss": 1.1752, "step": 10707 }, { "epoch": 0.5854365282760977, "grad_norm": 2.421478748321533, "learning_rate": 3.870385619710494e-05, "loss": 1.0512, "step": 10708 }, { "epoch": 0.5854912010934563, "grad_norm": 3.121297836303711, "learning_rate": 3.8695231733903654e-05, "loss": 0.9509, "step": 10709 }, { "epoch": 0.5855458739108149, "grad_norm": 2.5828540325164795, "learning_rate": 3.86866076251534e-05, "loss": 1.0235, "step": 10710 }, { "epoch": 0.5856005467281736, "grad_norm": 2.094597339630127, "learning_rate": 3.8677983871124595e-05, "loss": 0.8818, "step": 10711 }, { "epoch": 0.5856552195455322, "grad_norm": 2.3949177265167236, "learning_rate": 3.86693604720876e-05, "loss": 1.0789, "step": 10712 }, { "epoch": 0.5857098923628908, "grad_norm": 3.0403261184692383, "learning_rate": 3.866073742831285e-05, "loss": 1.2159, "step": 10713 }, { "epoch": 0.5857645651802494, "grad_norm": 2.2897872924804688, "learning_rate": 3.865211474007067e-05, "loss": 1.1389, "step": 10714 }, { "epoch": 0.585819237997608, "grad_norm": 2.6772072315216064, "learning_rate": 3.864349240763143e-05, "loss": 0.9578, "step": 10715 }, { "epoch": 0.5858739108149666, "grad_norm": 2.479583263397217, "learning_rate": 3.863487043126548e-05, "loss": 1.1452, "step": 10716 }, { "epoch": 0.5859285836323253, "grad_norm": 2.57830548286438, "learning_rate": 3.8626248811243146e-05, "loss": 1.0238, "step": 10717 }, { "epoch": 0.585983256449684, "grad_norm": 2.622368574142456, "learning_rate": 3.8617627547834755e-05, "loss": 1.1508, "step": 10718 }, { "epoch": 0.5860379292670426, "grad_norm": 2.2426857948303223, "learning_rate": 3.860900664131061e-05, "loss": 0.8609, "step": 10719 }, { "epoch": 0.5860926020844012, "grad_norm": 2.6525964736938477, "learning_rate": 3.8600386091941034e-05, "loss": 1.0611, "step": 10720 }, { "epoch": 0.5861472749017598, "grad_norm": 2.8820528984069824, "learning_rate": 3.859176589999629e-05, "loss": 1.0514, "step": 10721 }, { "epoch": 0.5862019477191184, "grad_norm": 2.177455186843872, "learning_rate": 3.8583146065746656e-05, "loss": 0.775, "step": 10722 }, { "epoch": 0.586256620536477, "grad_norm": 3.2555270195007324, "learning_rate": 3.857452658946243e-05, "loss": 0.8905, "step": 10723 }, { "epoch": 0.5863112933538357, "grad_norm": 2.603189706802368, "learning_rate": 3.856590747141385e-05, "loss": 0.8361, "step": 10724 }, { "epoch": 0.5863659661711943, "grad_norm": 2.5344977378845215, "learning_rate": 3.855728871187116e-05, "loss": 0.9168, "step": 10725 }, { "epoch": 0.5864206389885529, "grad_norm": 2.681429147720337, "learning_rate": 3.8548670311104594e-05, "loss": 0.9781, "step": 10726 }, { "epoch": 0.5864753118059115, "grad_norm": 2.482264995574951, "learning_rate": 3.854005226938438e-05, "loss": 0.9092, "step": 10727 }, { "epoch": 0.5865299846232701, "grad_norm": 2.23201322555542, "learning_rate": 3.853143458698072e-05, "loss": 1.0683, "step": 10728 }, { "epoch": 0.5865846574406287, "grad_norm": 2.8761253356933594, "learning_rate": 3.852281726416382e-05, "loss": 1.1143, "step": 10729 }, { "epoch": 0.5866393302579873, "grad_norm": 2.7190754413604736, "learning_rate": 3.851420030120387e-05, "loss": 1.3515, "step": 10730 }, { "epoch": 0.586694003075346, "grad_norm": 2.449772834777832, "learning_rate": 3.850558369837104e-05, "loss": 1.0253, "step": 10731 }, { "epoch": 0.5867486758927046, "grad_norm": 2.2492566108703613, "learning_rate": 3.849696745593548e-05, "loss": 0.8542, "step": 10732 }, { "epoch": 0.5868033487100632, "grad_norm": 2.4412670135498047, "learning_rate": 3.8488351574167384e-05, "loss": 1.0676, "step": 10733 }, { "epoch": 0.5868580215274218, "grad_norm": 3.7204887866973877, "learning_rate": 3.847973605333688e-05, "loss": 1.2476, "step": 10734 }, { "epoch": 0.5869126943447804, "grad_norm": 3.1648457050323486, "learning_rate": 3.84711208937141e-05, "loss": 1.0416, "step": 10735 }, { "epoch": 0.586967367162139, "grad_norm": 3.142864227294922, "learning_rate": 3.846250609556915e-05, "loss": 0.9243, "step": 10736 }, { "epoch": 0.5870220399794976, "grad_norm": 2.4626569747924805, "learning_rate": 3.8453891659172156e-05, "loss": 0.9559, "step": 10737 }, { "epoch": 0.5870767127968564, "grad_norm": 2.3100481033325195, "learning_rate": 3.844527758479321e-05, "loss": 1.0472, "step": 10738 }, { "epoch": 0.587131385614215, "grad_norm": 2.2881476879119873, "learning_rate": 3.843666387270239e-05, "loss": 0.9978, "step": 10739 }, { "epoch": 0.5871860584315736, "grad_norm": 2.2043845653533936, "learning_rate": 3.8428050523169794e-05, "loss": 1.0849, "step": 10740 }, { "epoch": 0.5872407312489322, "grad_norm": 2.692554235458374, "learning_rate": 3.8419437536465445e-05, "loss": 1.0736, "step": 10741 }, { "epoch": 0.5872954040662908, "grad_norm": 2.6292834281921387, "learning_rate": 3.841082491285944e-05, "loss": 1.0153, "step": 10742 }, { "epoch": 0.5873500768836494, "grad_norm": 2.4609808921813965, "learning_rate": 3.840221265262182e-05, "loss": 1.0547, "step": 10743 }, { "epoch": 0.587404749701008, "grad_norm": 3.416256904602051, "learning_rate": 3.839360075602258e-05, "loss": 1.106, "step": 10744 }, { "epoch": 0.5874594225183667, "grad_norm": 3.797182083129883, "learning_rate": 3.8384989223331766e-05, "loss": 1.0748, "step": 10745 }, { "epoch": 0.5875140953357253, "grad_norm": 2.1324992179870605, "learning_rate": 3.837637805481937e-05, "loss": 0.9588, "step": 10746 }, { "epoch": 0.5875687681530839, "grad_norm": 3.001718759536743, "learning_rate": 3.83677672507554e-05, "loss": 1.0982, "step": 10747 }, { "epoch": 0.5876234409704425, "grad_norm": 3.638441562652588, "learning_rate": 3.835915681140982e-05, "loss": 0.9565, "step": 10748 }, { "epoch": 0.5876781137878011, "grad_norm": 2.5429000854492188, "learning_rate": 3.8350546737052635e-05, "loss": 1.1084, "step": 10749 }, { "epoch": 0.5877327866051597, "grad_norm": 2.982666254043579, "learning_rate": 3.8341937027953775e-05, "loss": 0.8033, "step": 10750 }, { "epoch": 0.5877874594225184, "grad_norm": 2.247427225112915, "learning_rate": 3.833332768438319e-05, "loss": 0.95, "step": 10751 }, { "epoch": 0.587842132239877, "grad_norm": 3.3744771480560303, "learning_rate": 3.832471870661085e-05, "loss": 1.1469, "step": 10752 }, { "epoch": 0.5878968050572356, "grad_norm": 2.717653274536133, "learning_rate": 3.831611009490665e-05, "loss": 1.1358, "step": 10753 }, { "epoch": 0.5879514778745942, "grad_norm": 2.9981489181518555, "learning_rate": 3.830750184954052e-05, "loss": 0.7401, "step": 10754 }, { "epoch": 0.5880061506919528, "grad_norm": 2.385190486907959, "learning_rate": 3.829889397078237e-05, "loss": 0.8562, "step": 10755 }, { "epoch": 0.5880608235093114, "grad_norm": 2.374774217605591, "learning_rate": 3.829028645890208e-05, "loss": 1.0416, "step": 10756 }, { "epoch": 0.58811549632667, "grad_norm": 3.5986764430999756, "learning_rate": 3.8281679314169534e-05, "loss": 0.9031, "step": 10757 }, { "epoch": 0.5881701691440288, "grad_norm": 2.0555715560913086, "learning_rate": 3.8273072536854606e-05, "loss": 0.987, "step": 10758 }, { "epoch": 0.5882248419613874, "grad_norm": 2.6257052421569824, "learning_rate": 3.826446612722715e-05, "loss": 1.0022, "step": 10759 }, { "epoch": 0.588279514778746, "grad_norm": 2.9049501419067383, "learning_rate": 3.825586008555701e-05, "loss": 1.0902, "step": 10760 }, { "epoch": 0.5883341875961046, "grad_norm": 2.229400634765625, "learning_rate": 3.824725441211402e-05, "loss": 0.9781, "step": 10761 }, { "epoch": 0.5883888604134632, "grad_norm": 2.1474897861480713, "learning_rate": 3.823864910716801e-05, "loss": 0.9656, "step": 10762 }, { "epoch": 0.5884435332308218, "grad_norm": 2.2271814346313477, "learning_rate": 3.823004417098879e-05, "loss": 1.1974, "step": 10763 }, { "epoch": 0.5884982060481804, "grad_norm": 3.243607521057129, "learning_rate": 3.822143960384616e-05, "loss": 1.2127, "step": 10764 }, { "epoch": 0.5885528788655391, "grad_norm": 3.0860869884490967, "learning_rate": 3.8212835406009905e-05, "loss": 0.9789, "step": 10765 }, { "epoch": 0.5886075516828977, "grad_norm": 3.0526418685913086, "learning_rate": 3.820423157774981e-05, "loss": 0.9393, "step": 10766 }, { "epoch": 0.5886622245002563, "grad_norm": 3.7947027683258057, "learning_rate": 3.8195628119335627e-05, "loss": 0.9254, "step": 10767 }, { "epoch": 0.5887168973176149, "grad_norm": 3.033508062362671, "learning_rate": 3.8187025031037124e-05, "loss": 0.668, "step": 10768 }, { "epoch": 0.5887715701349735, "grad_norm": 2.3985917568206787, "learning_rate": 3.817842231312403e-05, "loss": 1.0155, "step": 10769 }, { "epoch": 0.5888262429523321, "grad_norm": 3.1355137825012207, "learning_rate": 3.816981996586609e-05, "loss": 1.1067, "step": 10770 }, { "epoch": 0.5888809157696907, "grad_norm": 3.4893293380737305, "learning_rate": 3.8161217989533e-05, "loss": 1.2317, "step": 10771 }, { "epoch": 0.5889355885870494, "grad_norm": 2.949925422668457, "learning_rate": 3.815261638439451e-05, "loss": 1.0693, "step": 10772 }, { "epoch": 0.588990261404408, "grad_norm": 4.350092887878418, "learning_rate": 3.814401515072028e-05, "loss": 1.1213, "step": 10773 }, { "epoch": 0.5890449342217666, "grad_norm": 3.272434949874878, "learning_rate": 3.813541428878e-05, "loss": 0.9411, "step": 10774 }, { "epoch": 0.5890996070391252, "grad_norm": 8.741384506225586, "learning_rate": 3.812681379884334e-05, "loss": 1.1145, "step": 10775 }, { "epoch": 0.5891542798564838, "grad_norm": 3.3511528968811035, "learning_rate": 3.811821368117998e-05, "loss": 1.0319, "step": 10776 }, { "epoch": 0.5892089526738424, "grad_norm": 3.145974636077881, "learning_rate": 3.8109613936059546e-05, "loss": 1.0344, "step": 10777 }, { "epoch": 0.5892636254912011, "grad_norm": 2.5344669818878174, "learning_rate": 3.810101456375169e-05, "loss": 1.1127, "step": 10778 }, { "epoch": 0.5893182983085598, "grad_norm": 3.826698064804077, "learning_rate": 3.809241556452602e-05, "loss": 1.2763, "step": 10779 }, { "epoch": 0.5893729711259184, "grad_norm": 3.8410634994506836, "learning_rate": 3.8083816938652164e-05, "loss": 1.0356, "step": 10780 }, { "epoch": 0.589427643943277, "grad_norm": 3.0250790119171143, "learning_rate": 3.807521868639973e-05, "loss": 0.8381, "step": 10781 }, { "epoch": 0.5894823167606356, "grad_norm": 2.0868101119995117, "learning_rate": 3.80666208080383e-05, "loss": 1.0274, "step": 10782 }, { "epoch": 0.5895369895779942, "grad_norm": 2.604717493057251, "learning_rate": 3.805802330383745e-05, "loss": 0.9509, "step": 10783 }, { "epoch": 0.5895916623953528, "grad_norm": 2.6974525451660156, "learning_rate": 3.804942617406677e-05, "loss": 1.0542, "step": 10784 }, { "epoch": 0.5896463352127115, "grad_norm": 2.468550443649292, "learning_rate": 3.804082941899578e-05, "loss": 0.9446, "step": 10785 }, { "epoch": 0.5897010080300701, "grad_norm": 3.9149742126464844, "learning_rate": 3.803223303889405e-05, "loss": 1.0221, "step": 10786 }, { "epoch": 0.5897556808474287, "grad_norm": 3.0403032302856445, "learning_rate": 3.8023637034031095e-05, "loss": 1.1734, "step": 10787 }, { "epoch": 0.5898103536647873, "grad_norm": 3.164440393447876, "learning_rate": 3.801504140467645e-05, "loss": 0.8647, "step": 10788 }, { "epoch": 0.5898650264821459, "grad_norm": 2.99349308013916, "learning_rate": 3.8006446151099614e-05, "loss": 1.0804, "step": 10789 }, { "epoch": 0.5899196992995045, "grad_norm": 3.211707830429077, "learning_rate": 3.799785127357006e-05, "loss": 1.1499, "step": 10790 }, { "epoch": 0.5899743721168631, "grad_norm": 2.2773663997650146, "learning_rate": 3.798925677235733e-05, "loss": 1.0492, "step": 10791 }, { "epoch": 0.5900290449342218, "grad_norm": 3.0103282928466797, "learning_rate": 3.7980662647730855e-05, "loss": 1.0757, "step": 10792 }, { "epoch": 0.5900837177515804, "grad_norm": 2.4981138706207275, "learning_rate": 3.7972068899960114e-05, "loss": 1.0002, "step": 10793 }, { "epoch": 0.590138390568939, "grad_norm": 2.774897575378418, "learning_rate": 3.796347552931454e-05, "loss": 0.7822, "step": 10794 }, { "epoch": 0.5901930633862976, "grad_norm": 2.732347249984741, "learning_rate": 3.7954882536063593e-05, "loss": 1.2374, "step": 10795 }, { "epoch": 0.5902477362036562, "grad_norm": 3.354264736175537, "learning_rate": 3.7946289920476677e-05, "loss": 1.1637, "step": 10796 }, { "epoch": 0.5903024090210148, "grad_norm": 2.4279699325561523, "learning_rate": 3.7937697682823216e-05, "loss": 0.9018, "step": 10797 }, { "epoch": 0.5903570818383734, "grad_norm": 2.595083475112915, "learning_rate": 3.792910582337261e-05, "loss": 1.0207, "step": 10798 }, { "epoch": 0.5904117546557321, "grad_norm": 2.6595706939697266, "learning_rate": 3.7920514342394253e-05, "loss": 1.1562, "step": 10799 }, { "epoch": 0.5904664274730907, "grad_norm": 2.426372766494751, "learning_rate": 3.791192324015749e-05, "loss": 0.9185, "step": 10800 }, { "epoch": 0.5905211002904494, "grad_norm": 2.365196466445923, "learning_rate": 3.790333251693175e-05, "loss": 1.09, "step": 10801 }, { "epoch": 0.590575773107808, "grad_norm": 2.665865659713745, "learning_rate": 3.789474217298635e-05, "loss": 1.1328, "step": 10802 }, { "epoch": 0.5906304459251666, "grad_norm": 2.7859442234039307, "learning_rate": 3.788615220859064e-05, "loss": 0.974, "step": 10803 }, { "epoch": 0.5906851187425252, "grad_norm": 2.174898624420166, "learning_rate": 3.7877562624013943e-05, "loss": 1.0026, "step": 10804 }, { "epoch": 0.5907397915598839, "grad_norm": 1.9897478818893433, "learning_rate": 3.7868973419525585e-05, "loss": 0.7858, "step": 10805 }, { "epoch": 0.5907944643772425, "grad_norm": 2.323911190032959, "learning_rate": 3.786038459539487e-05, "loss": 1.0815, "step": 10806 }, { "epoch": 0.5908491371946011, "grad_norm": 2.968151807785034, "learning_rate": 3.785179615189109e-05, "loss": 0.9925, "step": 10807 }, { "epoch": 0.5909038100119597, "grad_norm": 2.5983502864837646, "learning_rate": 3.7843208089283546e-05, "loss": 1.0938, "step": 10808 }, { "epoch": 0.5909584828293183, "grad_norm": 2.885746717453003, "learning_rate": 3.783462040784148e-05, "loss": 1.0303, "step": 10809 }, { "epoch": 0.5910131556466769, "grad_norm": 2.3876867294311523, "learning_rate": 3.7826033107834155e-05, "loss": 0.8296, "step": 10810 }, { "epoch": 0.5910678284640355, "grad_norm": 2.3688650131225586, "learning_rate": 3.7817446189530846e-05, "loss": 1.0642, "step": 10811 }, { "epoch": 0.5911225012813942, "grad_norm": 2.1475183963775635, "learning_rate": 3.780885965320078e-05, "loss": 0.7108, "step": 10812 }, { "epoch": 0.5911771740987528, "grad_norm": 2.2974255084991455, "learning_rate": 3.7800273499113165e-05, "loss": 0.8919, "step": 10813 }, { "epoch": 0.5912318469161114, "grad_norm": 3.120415687561035, "learning_rate": 3.7791687727537216e-05, "loss": 1.3112, "step": 10814 }, { "epoch": 0.59128651973347, "grad_norm": 3.4454755783081055, "learning_rate": 3.778310233874214e-05, "loss": 0.9663, "step": 10815 }, { "epoch": 0.5913411925508286, "grad_norm": 2.456611156463623, "learning_rate": 3.777451733299713e-05, "loss": 1.0046, "step": 10816 }, { "epoch": 0.5913958653681872, "grad_norm": 3.0854313373565674, "learning_rate": 3.7765932710571336e-05, "loss": 1.1858, "step": 10817 }, { "epoch": 0.5914505381855458, "grad_norm": 2.8609862327575684, "learning_rate": 3.775734847173394e-05, "loss": 1.005, "step": 10818 }, { "epoch": 0.5915052110029045, "grad_norm": 2.3688266277313232, "learning_rate": 3.774876461675409e-05, "loss": 0.8793, "step": 10819 }, { "epoch": 0.5915598838202631, "grad_norm": 2.41092586517334, "learning_rate": 3.774018114590091e-05, "loss": 0.9325, "step": 10820 }, { "epoch": 0.5916145566376217, "grad_norm": 3.131631851196289, "learning_rate": 3.7731598059443564e-05, "loss": 1.0898, "step": 10821 }, { "epoch": 0.5916692294549803, "grad_norm": 1.9282946586608887, "learning_rate": 3.772301535765114e-05, "loss": 0.9806, "step": 10822 }, { "epoch": 0.591723902272339, "grad_norm": 2.5756638050079346, "learning_rate": 3.771443304079275e-05, "loss": 0.924, "step": 10823 }, { "epoch": 0.5917785750896976, "grad_norm": 2.366725444793701, "learning_rate": 3.770585110913748e-05, "loss": 1.2149, "step": 10824 }, { "epoch": 0.5918332479070562, "grad_norm": 2.5492312908172607, "learning_rate": 3.769726956295441e-05, "loss": 1.0771, "step": 10825 }, { "epoch": 0.5918879207244149, "grad_norm": 2.9161386489868164, "learning_rate": 3.768868840251261e-05, "loss": 1.1643, "step": 10826 }, { "epoch": 0.5919425935417735, "grad_norm": 2.9050323963165283, "learning_rate": 3.768010762808113e-05, "loss": 1.0156, "step": 10827 }, { "epoch": 0.5919972663591321, "grad_norm": 2.2083215713500977, "learning_rate": 3.767152723992901e-05, "loss": 1.0569, "step": 10828 }, { "epoch": 0.5920519391764907, "grad_norm": 2.518555164337158, "learning_rate": 3.766294723832529e-05, "loss": 1.1519, "step": 10829 }, { "epoch": 0.5921066119938493, "grad_norm": 2.9744627475738525, "learning_rate": 3.765436762353896e-05, "loss": 0.9888, "step": 10830 }, { "epoch": 0.5921612848112079, "grad_norm": 2.7628438472747803, "learning_rate": 3.7645788395839074e-05, "loss": 0.9756, "step": 10831 }, { "epoch": 0.5922159576285665, "grad_norm": 2.2772154808044434, "learning_rate": 3.76372095554946e-05, "loss": 0.8998, "step": 10832 }, { "epoch": 0.5922706304459252, "grad_norm": 2.5200343132019043, "learning_rate": 3.762863110277452e-05, "loss": 0.8787, "step": 10833 }, { "epoch": 0.5923253032632838, "grad_norm": 2.776367425918579, "learning_rate": 3.762005303794781e-05, "loss": 1.13, "step": 10834 }, { "epoch": 0.5923799760806424, "grad_norm": 3.2950897216796875, "learning_rate": 3.7611475361283414e-05, "loss": 0.8894, "step": 10835 }, { "epoch": 0.592434648898001, "grad_norm": 2.292189359664917, "learning_rate": 3.7602898073050296e-05, "loss": 1.1026, "step": 10836 }, { "epoch": 0.5924893217153596, "grad_norm": 2.3212890625, "learning_rate": 3.759432117351738e-05, "loss": 1.0404, "step": 10837 }, { "epoch": 0.5925439945327182, "grad_norm": 2.374040126800537, "learning_rate": 3.758574466295358e-05, "loss": 0.9685, "step": 10838 }, { "epoch": 0.5925986673500769, "grad_norm": 2.529508352279663, "learning_rate": 3.757716854162781e-05, "loss": 1.1974, "step": 10839 }, { "epoch": 0.5926533401674355, "grad_norm": 2.9198780059814453, "learning_rate": 3.756859280980897e-05, "loss": 1.1972, "step": 10840 }, { "epoch": 0.5927080129847941, "grad_norm": 3.3070240020751953, "learning_rate": 3.7560017467765935e-05, "loss": 1.0589, "step": 10841 }, { "epoch": 0.5927626858021527, "grad_norm": 2.9871068000793457, "learning_rate": 3.75514425157676e-05, "loss": 1.1269, "step": 10842 }, { "epoch": 0.5928173586195113, "grad_norm": 3.1912178993225098, "learning_rate": 3.7542867954082807e-05, "loss": 1.2271, "step": 10843 }, { "epoch": 0.59287203143687, "grad_norm": 2.9976015090942383, "learning_rate": 3.753429378298041e-05, "loss": 0.8815, "step": 10844 }, { "epoch": 0.5929267042542286, "grad_norm": 2.792604923248291, "learning_rate": 3.752572000272924e-05, "loss": 1.1014, "step": 10845 }, { "epoch": 0.5929813770715873, "grad_norm": 2.6151788234710693, "learning_rate": 3.751714661359813e-05, "loss": 1.0045, "step": 10846 }, { "epoch": 0.5930360498889459, "grad_norm": 2.8471319675445557, "learning_rate": 3.750857361585587e-05, "loss": 1.0776, "step": 10847 }, { "epoch": 0.5930907227063045, "grad_norm": 4.019384860992432, "learning_rate": 3.7500001009771283e-05, "loss": 1.0712, "step": 10848 }, { "epoch": 0.5931453955236631, "grad_norm": 2.5448691844940186, "learning_rate": 3.749142879561313e-05, "loss": 1.1861, "step": 10849 }, { "epoch": 0.5932000683410217, "grad_norm": 2.2556045055389404, "learning_rate": 3.748285697365022e-05, "loss": 1.0409, "step": 10850 }, { "epoch": 0.5932547411583803, "grad_norm": 6.26469087600708, "learning_rate": 3.747428554415128e-05, "loss": 1.1166, "step": 10851 }, { "epoch": 0.5933094139757389, "grad_norm": 2.8087024688720703, "learning_rate": 3.746571450738508e-05, "loss": 1.0295, "step": 10852 }, { "epoch": 0.5933640867930976, "grad_norm": 2.70340633392334, "learning_rate": 3.7457143863620355e-05, "loss": 1.1258, "step": 10853 }, { "epoch": 0.5934187596104562, "grad_norm": 3.0445713996887207, "learning_rate": 3.7448573613125814e-05, "loss": 0.8165, "step": 10854 }, { "epoch": 0.5934734324278148, "grad_norm": 3.109837293624878, "learning_rate": 3.7440003756170194e-05, "loss": 0.843, "step": 10855 }, { "epoch": 0.5935281052451734, "grad_norm": 6.975893020629883, "learning_rate": 3.743143429302218e-05, "loss": 1.0743, "step": 10856 }, { "epoch": 0.593582778062532, "grad_norm": 3.153676986694336, "learning_rate": 3.7422865223950464e-05, "loss": 1.1405, "step": 10857 }, { "epoch": 0.5936374508798906, "grad_norm": 2.8808770179748535, "learning_rate": 3.7414296549223726e-05, "loss": 1.1751, "step": 10858 }, { "epoch": 0.5936921236972492, "grad_norm": 3.1606404781341553, "learning_rate": 3.740572826911061e-05, "loss": 1.1431, "step": 10859 }, { "epoch": 0.5937467965146079, "grad_norm": 2.2101893424987793, "learning_rate": 3.739716038387979e-05, "loss": 1.0652, "step": 10860 }, { "epoch": 0.5938014693319665, "grad_norm": 2.2170350551605225, "learning_rate": 3.73885928937999e-05, "loss": 0.9255, "step": 10861 }, { "epoch": 0.5938561421493251, "grad_norm": 2.6382250785827637, "learning_rate": 3.738002579913956e-05, "loss": 0.7869, "step": 10862 }, { "epoch": 0.5939108149666837, "grad_norm": 3.1448678970336914, "learning_rate": 3.737145910016739e-05, "loss": 1.0719, "step": 10863 }, { "epoch": 0.5939654877840423, "grad_norm": 2.1357250213623047, "learning_rate": 3.736289279715198e-05, "loss": 0.9689, "step": 10864 }, { "epoch": 0.594020160601401, "grad_norm": 2.711756944656372, "learning_rate": 3.7354326890361935e-05, "loss": 0.886, "step": 10865 }, { "epoch": 0.5940748334187597, "grad_norm": 2.680432081222534, "learning_rate": 3.734576138006582e-05, "loss": 0.8589, "step": 10866 }, { "epoch": 0.5941295062361183, "grad_norm": 2.9521167278289795, "learning_rate": 3.7337196266532186e-05, "loss": 0.8938, "step": 10867 }, { "epoch": 0.5941841790534769, "grad_norm": 2.41656231880188, "learning_rate": 3.732863155002961e-05, "loss": 1.165, "step": 10868 }, { "epoch": 0.5942388518708355, "grad_norm": 3.0873794555664062, "learning_rate": 3.7320067230826614e-05, "loss": 1.1998, "step": 10869 }, { "epoch": 0.5942935246881941, "grad_norm": 4.231683254241943, "learning_rate": 3.7311503309191744e-05, "loss": 1.0892, "step": 10870 }, { "epoch": 0.5943481975055527, "grad_norm": 2.3011608123779297, "learning_rate": 3.73029397853935e-05, "loss": 0.9422, "step": 10871 }, { "epoch": 0.5944028703229113, "grad_norm": 2.06486177444458, "learning_rate": 3.7294376659700384e-05, "loss": 0.8689, "step": 10872 }, { "epoch": 0.59445754314027, "grad_norm": 2.326488733291626, "learning_rate": 3.7285813932380885e-05, "loss": 1.1139, "step": 10873 }, { "epoch": 0.5945122159576286, "grad_norm": 2.37508225440979, "learning_rate": 3.727725160370349e-05, "loss": 1.1028, "step": 10874 }, { "epoch": 0.5945668887749872, "grad_norm": 2.0413966178894043, "learning_rate": 3.726868967393665e-05, "loss": 0.6731, "step": 10875 }, { "epoch": 0.5946215615923458, "grad_norm": 3.6731510162353516, "learning_rate": 3.7260128143348816e-05, "loss": 1.101, "step": 10876 }, { "epoch": 0.5946762344097044, "grad_norm": 2.7333691120147705, "learning_rate": 3.7251567012208446e-05, "loss": 1.2257, "step": 10877 }, { "epoch": 0.594730907227063, "grad_norm": 3.135963201522827, "learning_rate": 3.724300628078394e-05, "loss": 0.7655, "step": 10878 }, { "epoch": 0.5947855800444216, "grad_norm": 2.5810441970825195, "learning_rate": 3.723444594934371e-05, "loss": 0.9777, "step": 10879 }, { "epoch": 0.5948402528617803, "grad_norm": 2.7119174003601074, "learning_rate": 3.72258860181562e-05, "loss": 1.2094, "step": 10880 }, { "epoch": 0.5948949256791389, "grad_norm": 2.9360992908477783, "learning_rate": 3.7217326487489767e-05, "loss": 1.0584, "step": 10881 }, { "epoch": 0.5949495984964975, "grad_norm": 2.7070775032043457, "learning_rate": 3.7208767357612796e-05, "loss": 1.1976, "step": 10882 }, { "epoch": 0.5950042713138561, "grad_norm": 2.150533676147461, "learning_rate": 3.720020862879364e-05, "loss": 0.8865, "step": 10883 }, { "epoch": 0.5950589441312147, "grad_norm": 3.093388080596924, "learning_rate": 3.7191650301300666e-05, "loss": 1.1695, "step": 10884 }, { "epoch": 0.5951136169485733, "grad_norm": 3.080345630645752, "learning_rate": 3.718309237540221e-05, "loss": 1.0731, "step": 10885 }, { "epoch": 0.595168289765932, "grad_norm": 2.969397783279419, "learning_rate": 3.7174534851366586e-05, "loss": 0.9332, "step": 10886 }, { "epoch": 0.5952229625832907, "grad_norm": 2.3922345638275146, "learning_rate": 3.716597772946212e-05, "loss": 1.0597, "step": 10887 }, { "epoch": 0.5952776354006493, "grad_norm": 2.2863619327545166, "learning_rate": 3.7157421009957105e-05, "loss": 0.9741, "step": 10888 }, { "epoch": 0.5953323082180079, "grad_norm": 2.441349983215332, "learning_rate": 3.714886469311981e-05, "loss": 1.0681, "step": 10889 }, { "epoch": 0.5953869810353665, "grad_norm": 2.4515583515167236, "learning_rate": 3.714030877921856e-05, "loss": 1.1429, "step": 10890 }, { "epoch": 0.5954416538527251, "grad_norm": 2.427943706512451, "learning_rate": 3.713175326852159e-05, "loss": 1.1231, "step": 10891 }, { "epoch": 0.5954963266700837, "grad_norm": 2.2355751991271973, "learning_rate": 3.712319816129715e-05, "loss": 0.9871, "step": 10892 }, { "epoch": 0.5955509994874424, "grad_norm": 2.2037205696105957, "learning_rate": 3.711464345781347e-05, "loss": 0.9936, "step": 10893 }, { "epoch": 0.595605672304801, "grad_norm": 2.399258852005005, "learning_rate": 3.71060891583388e-05, "loss": 1.2224, "step": 10894 }, { "epoch": 0.5956603451221596, "grad_norm": 2.6365883350372314, "learning_rate": 3.709753526314133e-05, "loss": 0.931, "step": 10895 }, { "epoch": 0.5957150179395182, "grad_norm": 2.8699750900268555, "learning_rate": 3.7088981772489276e-05, "loss": 1.161, "step": 10896 }, { "epoch": 0.5957696907568768, "grad_norm": 2.7790634632110596, "learning_rate": 3.7080428686650804e-05, "loss": 0.9018, "step": 10897 }, { "epoch": 0.5958243635742354, "grad_norm": 2.9783756732940674, "learning_rate": 3.707187600589409e-05, "loss": 1.0439, "step": 10898 }, { "epoch": 0.595879036391594, "grad_norm": 1.870211124420166, "learning_rate": 3.7063323730487323e-05, "loss": 1.0097, "step": 10899 }, { "epoch": 0.5959337092089527, "grad_norm": 3.1321680545806885, "learning_rate": 3.7054771860698635e-05, "loss": 1.0493, "step": 10900 }, { "epoch": 0.5959883820263113, "grad_norm": 3.0675787925720215, "learning_rate": 3.704622039679617e-05, "loss": 0.9828, "step": 10901 }, { "epoch": 0.5960430548436699, "grad_norm": 2.9821887016296387, "learning_rate": 3.703766933904804e-05, "loss": 0.8419, "step": 10902 }, { "epoch": 0.5960977276610285, "grad_norm": 2.6389880180358887, "learning_rate": 3.702911868772236e-05, "loss": 0.8664, "step": 10903 }, { "epoch": 0.5961524004783871, "grad_norm": 3.4746921062469482, "learning_rate": 3.7020568443087226e-05, "loss": 1.1605, "step": 10904 }, { "epoch": 0.5962070732957457, "grad_norm": 2.2079708576202393, "learning_rate": 3.7012018605410734e-05, "loss": 1.0778, "step": 10905 }, { "epoch": 0.5962617461131043, "grad_norm": 2.2535295486450195, "learning_rate": 3.7003469174960945e-05, "loss": 1.047, "step": 10906 }, { "epoch": 0.596316418930463, "grad_norm": 2.9708988666534424, "learning_rate": 3.699492015200592e-05, "loss": 0.8839, "step": 10907 }, { "epoch": 0.5963710917478217, "grad_norm": 3.5975630283355713, "learning_rate": 3.698637153681369e-05, "loss": 0.9638, "step": 10908 }, { "epoch": 0.5964257645651803, "grad_norm": 2.903036594390869, "learning_rate": 3.697782332965233e-05, "loss": 0.9448, "step": 10909 }, { "epoch": 0.5964804373825389, "grad_norm": 2.830258846282959, "learning_rate": 3.696927553078984e-05, "loss": 0.9303, "step": 10910 }, { "epoch": 0.5965351101998975, "grad_norm": 2.8862757682800293, "learning_rate": 3.696072814049423e-05, "loss": 0.9799, "step": 10911 }, { "epoch": 0.5965897830172561, "grad_norm": 2.1947522163391113, "learning_rate": 3.695218115903348e-05, "loss": 1.0645, "step": 10912 }, { "epoch": 0.5966444558346147, "grad_norm": 2.798154830932617, "learning_rate": 3.69436345866756e-05, "loss": 1.0789, "step": 10913 }, { "epoch": 0.5966991286519734, "grad_norm": 2.2974305152893066, "learning_rate": 3.693508842368855e-05, "loss": 0.9568, "step": 10914 }, { "epoch": 0.596753801469332, "grad_norm": 2.295241117477417, "learning_rate": 3.692654267034028e-05, "loss": 0.8859, "step": 10915 }, { "epoch": 0.5968084742866906, "grad_norm": 2.7963132858276367, "learning_rate": 3.691799732689874e-05, "loss": 0.8994, "step": 10916 }, { "epoch": 0.5968631471040492, "grad_norm": 2.399285316467285, "learning_rate": 3.690945239363186e-05, "loss": 1.0236, "step": 10917 }, { "epoch": 0.5969178199214078, "grad_norm": 2.441338539123535, "learning_rate": 3.6900907870807546e-05, "loss": 0.8772, "step": 10918 }, { "epoch": 0.5969724927387664, "grad_norm": 3.941290855407715, "learning_rate": 3.6892363758693724e-05, "loss": 0.8181, "step": 10919 }, { "epoch": 0.5970271655561251, "grad_norm": 2.5526628494262695, "learning_rate": 3.6883820057558297e-05, "loss": 0.9929, "step": 10920 }, { "epoch": 0.5970818383734837, "grad_norm": 2.54420804977417, "learning_rate": 3.687527676766912e-05, "loss": 0.8953, "step": 10921 }, { "epoch": 0.5971365111908423, "grad_norm": 2.4592604637145996, "learning_rate": 3.686673388929408e-05, "loss": 0.9717, "step": 10922 }, { "epoch": 0.5971911840082009, "grad_norm": 2.3120651245117188, "learning_rate": 3.6858191422701005e-05, "loss": 1.0852, "step": 10923 }, { "epoch": 0.5972458568255595, "grad_norm": 3.0920445919036865, "learning_rate": 3.684964936815776e-05, "loss": 1.0485, "step": 10924 }, { "epoch": 0.5973005296429181, "grad_norm": 2.8647665977478027, "learning_rate": 3.684110772593217e-05, "loss": 0.9867, "step": 10925 }, { "epoch": 0.5973552024602767, "grad_norm": 2.4388680458068848, "learning_rate": 3.6832566496292044e-05, "loss": 0.8973, "step": 10926 }, { "epoch": 0.5974098752776354, "grad_norm": 2.5792434215545654, "learning_rate": 3.6824025679505185e-05, "loss": 0.8511, "step": 10927 }, { "epoch": 0.597464548094994, "grad_norm": 2.202836275100708, "learning_rate": 3.681548527583937e-05, "loss": 0.9326, "step": 10928 }, { "epoch": 0.5975192209123527, "grad_norm": 2.6422979831695557, "learning_rate": 3.6806945285562404e-05, "loss": 0.988, "step": 10929 }, { "epoch": 0.5975738937297113, "grad_norm": 3.1086089611053467, "learning_rate": 3.6798405708942044e-05, "loss": 0.9718, "step": 10930 }, { "epoch": 0.5976285665470699, "grad_norm": 3.7105820178985596, "learning_rate": 3.678986654624603e-05, "loss": 0.9227, "step": 10931 }, { "epoch": 0.5976832393644285, "grad_norm": 2.930126190185547, "learning_rate": 3.6781327797742115e-05, "loss": 0.9456, "step": 10932 }, { "epoch": 0.5977379121817871, "grad_norm": 3.3147330284118652, "learning_rate": 3.677278946369801e-05, "loss": 1.0464, "step": 10933 }, { "epoch": 0.5977925849991458, "grad_norm": 2.6226353645324707, "learning_rate": 3.676425154438142e-05, "loss": 1.0989, "step": 10934 }, { "epoch": 0.5978472578165044, "grad_norm": 3.0418570041656494, "learning_rate": 3.675571404006006e-05, "loss": 0.916, "step": 10935 }, { "epoch": 0.597901930633863, "grad_norm": 2.4979147911071777, "learning_rate": 3.6747176951001614e-05, "loss": 1.0272, "step": 10936 }, { "epoch": 0.5979566034512216, "grad_norm": 2.1910598278045654, "learning_rate": 3.673864027747376e-05, "loss": 0.9167, "step": 10937 }, { "epoch": 0.5980112762685802, "grad_norm": 2.5579335689544678, "learning_rate": 3.673010401974412e-05, "loss": 1.0815, "step": 10938 }, { "epoch": 0.5980659490859388, "grad_norm": 2.5298218727111816, "learning_rate": 3.672156817808039e-05, "loss": 1.0269, "step": 10939 }, { "epoch": 0.5981206219032974, "grad_norm": 3.0179765224456787, "learning_rate": 3.6713032752750184e-05, "loss": 1.0274, "step": 10940 }, { "epoch": 0.5981752947206561, "grad_norm": 2.3535096645355225, "learning_rate": 3.6704497744021116e-05, "loss": 1.0289, "step": 10941 }, { "epoch": 0.5982299675380147, "grad_norm": 3.010141611099243, "learning_rate": 3.66959631521608e-05, "loss": 0.949, "step": 10942 }, { "epoch": 0.5982846403553733, "grad_norm": 2.8627333641052246, "learning_rate": 3.668742897743684e-05, "loss": 0.9882, "step": 10943 }, { "epoch": 0.5983393131727319, "grad_norm": 2.322315216064453, "learning_rate": 3.6678895220116804e-05, "loss": 0.8957, "step": 10944 }, { "epoch": 0.5983939859900905, "grad_norm": 3.4750967025756836, "learning_rate": 3.667036188046827e-05, "loss": 1.0236, "step": 10945 }, { "epoch": 0.5984486588074491, "grad_norm": 2.266801595687866, "learning_rate": 3.666182895875879e-05, "loss": 0.9012, "step": 10946 }, { "epoch": 0.5985033316248078, "grad_norm": 4.313389301300049, "learning_rate": 3.665329645525588e-05, "loss": 1.1412, "step": 10947 }, { "epoch": 0.5985580044421664, "grad_norm": 3.1728060245513916, "learning_rate": 3.664476437022712e-05, "loss": 1.1794, "step": 10948 }, { "epoch": 0.598612677259525, "grad_norm": 3.4022297859191895, "learning_rate": 3.6636232703939986e-05, "loss": 1.0283, "step": 10949 }, { "epoch": 0.5986673500768837, "grad_norm": 2.3128318786621094, "learning_rate": 3.662770145666201e-05, "loss": 0.9734, "step": 10950 }, { "epoch": 0.5987220228942423, "grad_norm": 4.6871442794799805, "learning_rate": 3.661917062866065e-05, "loss": 1.071, "step": 10951 }, { "epoch": 0.5987766957116009, "grad_norm": 2.7560997009277344, "learning_rate": 3.661064022020341e-05, "loss": 0.8764, "step": 10952 }, { "epoch": 0.5988313685289595, "grad_norm": 2.588955879211426, "learning_rate": 3.660211023155774e-05, "loss": 1.1404, "step": 10953 }, { "epoch": 0.5988860413463182, "grad_norm": 2.7386932373046875, "learning_rate": 3.659358066299108e-05, "loss": 0.8471, "step": 10954 }, { "epoch": 0.5989407141636768, "grad_norm": 4.742741107940674, "learning_rate": 3.658505151477089e-05, "loss": 1.4548, "step": 10955 }, { "epoch": 0.5989953869810354, "grad_norm": 2.4716691970825195, "learning_rate": 3.657652278716459e-05, "loss": 1.0348, "step": 10956 }, { "epoch": 0.599050059798394, "grad_norm": 2.296034097671509, "learning_rate": 3.656799448043956e-05, "loss": 0.8884, "step": 10957 }, { "epoch": 0.5991047326157526, "grad_norm": 2.599329710006714, "learning_rate": 3.6559466594863244e-05, "loss": 1.0456, "step": 10958 }, { "epoch": 0.5991594054331112, "grad_norm": 2.6722137928009033, "learning_rate": 3.6550939130703e-05, "loss": 1.1031, "step": 10959 }, { "epoch": 0.5992140782504698, "grad_norm": 2.7163188457489014, "learning_rate": 3.654241208822621e-05, "loss": 1.1018, "step": 10960 }, { "epoch": 0.5992687510678285, "grad_norm": 2.3175389766693115, "learning_rate": 3.653388546770021e-05, "loss": 0.9269, "step": 10961 }, { "epoch": 0.5993234238851871, "grad_norm": 3.1396231651306152, "learning_rate": 3.652535926939237e-05, "loss": 1.1769, "step": 10962 }, { "epoch": 0.5993780967025457, "grad_norm": 2.4030649662017822, "learning_rate": 3.6516833493570014e-05, "loss": 0.9258, "step": 10963 }, { "epoch": 0.5994327695199043, "grad_norm": 3.365790367126465, "learning_rate": 3.650830814050045e-05, "loss": 0.8468, "step": 10964 }, { "epoch": 0.5994874423372629, "grad_norm": 2.942127227783203, "learning_rate": 3.6499783210451e-05, "loss": 1.1216, "step": 10965 }, { "epoch": 0.5995421151546215, "grad_norm": 2.6403708457946777, "learning_rate": 3.649125870368894e-05, "loss": 1.0479, "step": 10966 }, { "epoch": 0.5995967879719801, "grad_norm": 2.329845905303955, "learning_rate": 3.6482734620481526e-05, "loss": 1.0273, "step": 10967 }, { "epoch": 0.5996514607893388, "grad_norm": 2.6153206825256348, "learning_rate": 3.647421096109608e-05, "loss": 0.9732, "step": 10968 }, { "epoch": 0.5997061336066974, "grad_norm": 4.4521708488464355, "learning_rate": 3.646568772579983e-05, "loss": 1.0365, "step": 10969 }, { "epoch": 0.599760806424056, "grad_norm": 2.327033758163452, "learning_rate": 3.645716491486001e-05, "loss": 1.0642, "step": 10970 }, { "epoch": 0.5998154792414147, "grad_norm": 2.3606560230255127, "learning_rate": 3.644864252854383e-05, "loss": 1.0408, "step": 10971 }, { "epoch": 0.5998701520587733, "grad_norm": 2.3905928134918213, "learning_rate": 3.6440120567118535e-05, "loss": 1.1482, "step": 10972 }, { "epoch": 0.5999248248761319, "grad_norm": 2.6976003646850586, "learning_rate": 3.6431599030851294e-05, "loss": 0.9606, "step": 10973 }, { "epoch": 0.5999794976934906, "grad_norm": 2.025200366973877, "learning_rate": 3.642307792000931e-05, "loss": 0.8685, "step": 10974 }, { "epoch": 0.6000341705108492, "grad_norm": 2.716580390930176, "learning_rate": 3.641455723485975e-05, "loss": 0.9557, "step": 10975 }, { "epoch": 0.6000888433282078, "grad_norm": 2.6443965435028076, "learning_rate": 3.640603697566977e-05, "loss": 0.9923, "step": 10976 }, { "epoch": 0.6001435161455664, "grad_norm": 2.2919650077819824, "learning_rate": 3.6397517142706496e-05, "loss": 1.0384, "step": 10977 }, { "epoch": 0.600198188962925, "grad_norm": 2.544064998626709, "learning_rate": 3.63889977362371e-05, "loss": 0.9385, "step": 10978 }, { "epoch": 0.6002528617802836, "grad_norm": 3.059080123901367, "learning_rate": 3.638047875652868e-05, "loss": 1.0219, "step": 10979 }, { "epoch": 0.6003075345976422, "grad_norm": 3.5563619136810303, "learning_rate": 3.637196020384834e-05, "loss": 1.1904, "step": 10980 }, { "epoch": 0.6003622074150009, "grad_norm": 4.006916522979736, "learning_rate": 3.6363442078463176e-05, "loss": 1.0114, "step": 10981 }, { "epoch": 0.6004168802323595, "grad_norm": 3.1446855068206787, "learning_rate": 3.635492438064027e-05, "loss": 1.0879, "step": 10982 }, { "epoch": 0.6004715530497181, "grad_norm": 2.702962875366211, "learning_rate": 3.634640711064667e-05, "loss": 1.1882, "step": 10983 }, { "epoch": 0.6005262258670767, "grad_norm": 2.919248580932617, "learning_rate": 3.633789026874944e-05, "loss": 1.1151, "step": 10984 }, { "epoch": 0.6005808986844353, "grad_norm": 2.4193685054779053, "learning_rate": 3.632937385521562e-05, "loss": 0.9232, "step": 10985 }, { "epoch": 0.6006355715017939, "grad_norm": 4.810605525970459, "learning_rate": 3.6320857870312234e-05, "loss": 1.0713, "step": 10986 }, { "epoch": 0.6006902443191525, "grad_norm": 3.616182565689087, "learning_rate": 3.631234231430627e-05, "loss": 0.9662, "step": 10987 }, { "epoch": 0.6007449171365112, "grad_norm": 2.6941030025482178, "learning_rate": 3.630382718746476e-05, "loss": 1.1477, "step": 10988 }, { "epoch": 0.6007995899538698, "grad_norm": 2.2292611598968506, "learning_rate": 3.629531249005468e-05, "loss": 0.9058, "step": 10989 }, { "epoch": 0.6008542627712284, "grad_norm": 2.4199938774108887, "learning_rate": 3.628679822234299e-05, "loss": 1.1332, "step": 10990 }, { "epoch": 0.600908935588587, "grad_norm": 2.9582552909851074, "learning_rate": 3.627828438459666e-05, "loss": 1.1021, "step": 10991 }, { "epoch": 0.6009636084059456, "grad_norm": 2.7868854999542236, "learning_rate": 3.6269770977082626e-05, "loss": 1.0401, "step": 10992 }, { "epoch": 0.6010182812233043, "grad_norm": 2.395763874053955, "learning_rate": 3.626125800006781e-05, "loss": 0.9335, "step": 10993 }, { "epoch": 0.6010729540406629, "grad_norm": 3.736503839492798, "learning_rate": 3.625274545381915e-05, "loss": 0.9547, "step": 10994 }, { "epoch": 0.6011276268580216, "grad_norm": 2.6676688194274902, "learning_rate": 3.6244233338603526e-05, "loss": 1.2438, "step": 10995 }, { "epoch": 0.6011822996753802, "grad_norm": 2.601841926574707, "learning_rate": 3.6235721654687825e-05, "loss": 0.8518, "step": 10996 }, { "epoch": 0.6012369724927388, "grad_norm": 2.296675205230713, "learning_rate": 3.6227210402338954e-05, "loss": 0.7964, "step": 10997 }, { "epoch": 0.6012916453100974, "grad_norm": 2.1083219051361084, "learning_rate": 3.6218699581823764e-05, "loss": 0.7854, "step": 10998 }, { "epoch": 0.601346318127456, "grad_norm": 2.583651065826416, "learning_rate": 3.6210189193409095e-05, "loss": 1.1194, "step": 10999 }, { "epoch": 0.6014009909448146, "grad_norm": 2.679100513458252, "learning_rate": 3.6201679237361785e-05, "loss": 1.1051, "step": 11000 }, { "epoch": 0.6014556637621733, "grad_norm": 2.17378568649292, "learning_rate": 3.619316971394867e-05, "loss": 0.9323, "step": 11001 }, { "epoch": 0.6015103365795319, "grad_norm": 2.4513089656829834, "learning_rate": 3.618466062343654e-05, "loss": 0.9701, "step": 11002 }, { "epoch": 0.6015650093968905, "grad_norm": 2.178784132003784, "learning_rate": 3.617615196609219e-05, "loss": 0.8666, "step": 11003 }, { "epoch": 0.6016196822142491, "grad_norm": 2.7623441219329834, "learning_rate": 3.616764374218242e-05, "loss": 0.921, "step": 11004 }, { "epoch": 0.6016743550316077, "grad_norm": 2.233020067214966, "learning_rate": 3.615913595197398e-05, "loss": 0.9773, "step": 11005 }, { "epoch": 0.6017290278489663, "grad_norm": 2.896496295928955, "learning_rate": 3.61506285957336e-05, "loss": 1.2434, "step": 11006 }, { "epoch": 0.6017837006663249, "grad_norm": 2.3496222496032715, "learning_rate": 3.6142121673728094e-05, "loss": 0.9667, "step": 11007 }, { "epoch": 0.6018383734836836, "grad_norm": 2.222086191177368, "learning_rate": 3.6133615186224134e-05, "loss": 1.0512, "step": 11008 }, { "epoch": 0.6018930463010422, "grad_norm": 3.690521717071533, "learning_rate": 3.6125109133488444e-05, "loss": 1.0879, "step": 11009 }, { "epoch": 0.6019477191184008, "grad_norm": 1.9861540794372559, "learning_rate": 3.611660351578773e-05, "loss": 0.9486, "step": 11010 }, { "epoch": 0.6020023919357594, "grad_norm": 3.2758030891418457, "learning_rate": 3.610809833338867e-05, "loss": 0.9834, "step": 11011 }, { "epoch": 0.602057064753118, "grad_norm": 2.9952504634857178, "learning_rate": 3.6099593586557946e-05, "loss": 1.1751, "step": 11012 }, { "epoch": 0.6021117375704766, "grad_norm": 2.6560041904449463, "learning_rate": 3.60910892755622e-05, "loss": 0.9274, "step": 11013 }, { "epoch": 0.6021664103878352, "grad_norm": 2.029926300048828, "learning_rate": 3.60825854006681e-05, "loss": 0.977, "step": 11014 }, { "epoch": 0.602221083205194, "grad_norm": 2.35311222076416, "learning_rate": 3.607408196214226e-05, "loss": 0.783, "step": 11015 }, { "epoch": 0.6022757560225526, "grad_norm": 2.4377248287200928, "learning_rate": 3.6065578960251276e-05, "loss": 1.0201, "step": 11016 }, { "epoch": 0.6023304288399112, "grad_norm": 2.9431352615356445, "learning_rate": 3.605707639526181e-05, "loss": 1.1361, "step": 11017 }, { "epoch": 0.6023851016572698, "grad_norm": 2.3431315422058105, "learning_rate": 3.6048574267440415e-05, "loss": 0.8582, "step": 11018 }, { "epoch": 0.6024397744746284, "grad_norm": 3.5839388370513916, "learning_rate": 3.604007257705369e-05, "loss": 1.031, "step": 11019 }, { "epoch": 0.602494447291987, "grad_norm": 2.7154409885406494, "learning_rate": 3.603157132436816e-05, "loss": 0.9405, "step": 11020 }, { "epoch": 0.6025491201093456, "grad_norm": 2.359715700149536, "learning_rate": 3.6023070509650416e-05, "loss": 0.847, "step": 11021 }, { "epoch": 0.6026037929267043, "grad_norm": 2.6364448070526123, "learning_rate": 3.6014570133166966e-05, "loss": 0.8197, "step": 11022 }, { "epoch": 0.6026584657440629, "grad_norm": 4.882740020751953, "learning_rate": 3.6006070195184335e-05, "loss": 1.3024, "step": 11023 }, { "epoch": 0.6027131385614215, "grad_norm": 3.050079345703125, "learning_rate": 3.599757069596905e-05, "loss": 0.98, "step": 11024 }, { "epoch": 0.6027678113787801, "grad_norm": 2.3593642711639404, "learning_rate": 3.5989071635787584e-05, "loss": 0.9678, "step": 11025 }, { "epoch": 0.6028224841961387, "grad_norm": 2.2606983184814453, "learning_rate": 3.5980573014906416e-05, "loss": 1.0319, "step": 11026 }, { "epoch": 0.6028771570134973, "grad_norm": 2.6233632564544678, "learning_rate": 3.597207483359203e-05, "loss": 1.1851, "step": 11027 }, { "epoch": 0.602931829830856, "grad_norm": 3.270794630050659, "learning_rate": 3.596357709211087e-05, "loss": 1.2187, "step": 11028 }, { "epoch": 0.6029865026482146, "grad_norm": 2.978911876678467, "learning_rate": 3.595507979072937e-05, "loss": 1.0868, "step": 11029 }, { "epoch": 0.6030411754655732, "grad_norm": 3.2290475368499756, "learning_rate": 3.594658292971397e-05, "loss": 1.0047, "step": 11030 }, { "epoch": 0.6030958482829318, "grad_norm": 2.8530075550079346, "learning_rate": 3.5938086509331085e-05, "loss": 0.9755, "step": 11031 }, { "epoch": 0.6031505211002904, "grad_norm": 3.5078296661376953, "learning_rate": 3.5929590529847076e-05, "loss": 1.0237, "step": 11032 }, { "epoch": 0.603205193917649, "grad_norm": 3.802722215652466, "learning_rate": 3.592109499152837e-05, "loss": 1.1595, "step": 11033 }, { "epoch": 0.6032598667350076, "grad_norm": 2.6636219024658203, "learning_rate": 3.591259989464132e-05, "loss": 1.0141, "step": 11034 }, { "epoch": 0.6033145395523664, "grad_norm": 2.481597423553467, "learning_rate": 3.590410523945227e-05, "loss": 1.1211, "step": 11035 }, { "epoch": 0.603369212369725, "grad_norm": 2.251180410385132, "learning_rate": 3.5895611026227575e-05, "loss": 1.0333, "step": 11036 }, { "epoch": 0.6034238851870836, "grad_norm": 2.4106645584106445, "learning_rate": 3.588711725523357e-05, "loss": 1.2236, "step": 11037 }, { "epoch": 0.6034785580044422, "grad_norm": 2.4443202018737793, "learning_rate": 3.5878623926736554e-05, "loss": 0.7565, "step": 11038 }, { "epoch": 0.6035332308218008, "grad_norm": 2.7198426723480225, "learning_rate": 3.5870131041002844e-05, "loss": 1.0701, "step": 11039 }, { "epoch": 0.6035879036391594, "grad_norm": 2.10520076751709, "learning_rate": 3.586163859829871e-05, "loss": 1.1023, "step": 11040 }, { "epoch": 0.603642576456518, "grad_norm": 2.705235719680786, "learning_rate": 3.585314659889043e-05, "loss": 0.973, "step": 11041 }, { "epoch": 0.6036972492738767, "grad_norm": 4.003464221954346, "learning_rate": 3.584465504304428e-05, "loss": 1.1431, "step": 11042 }, { "epoch": 0.6037519220912353, "grad_norm": 2.87483549118042, "learning_rate": 3.583616393102649e-05, "loss": 1.089, "step": 11043 }, { "epoch": 0.6038065949085939, "grad_norm": 2.5462841987609863, "learning_rate": 3.582767326310329e-05, "loss": 0.9203, "step": 11044 }, { "epoch": 0.6038612677259525, "grad_norm": 3.400630474090576, "learning_rate": 3.5819183039540905e-05, "loss": 0.8967, "step": 11045 }, { "epoch": 0.6039159405433111, "grad_norm": 2.5177016258239746, "learning_rate": 3.581069326060552e-05, "loss": 1.1786, "step": 11046 }, { "epoch": 0.6039706133606697, "grad_norm": 2.5365493297576904, "learning_rate": 3.5802203926563346e-05, "loss": 1.2015, "step": 11047 }, { "epoch": 0.6040252861780283, "grad_norm": 2.546854257583618, "learning_rate": 3.579371503768056e-05, "loss": 1.0926, "step": 11048 }, { "epoch": 0.604079958995387, "grad_norm": 2.381798267364502, "learning_rate": 3.578522659422332e-05, "loss": 1.0701, "step": 11049 }, { "epoch": 0.6041346318127456, "grad_norm": 2.6974873542785645, "learning_rate": 3.577673859645776e-05, "loss": 0.9738, "step": 11050 }, { "epoch": 0.6041893046301042, "grad_norm": 2.602307081222534, "learning_rate": 3.576825104465003e-05, "loss": 1.1226, "step": 11051 }, { "epoch": 0.6042439774474628, "grad_norm": 5.3563923835754395, "learning_rate": 3.575976393906623e-05, "loss": 0.9631, "step": 11052 }, { "epoch": 0.6042986502648214, "grad_norm": 2.564340829849243, "learning_rate": 3.5751277279972485e-05, "loss": 1.1106, "step": 11053 }, { "epoch": 0.60435332308218, "grad_norm": 2.6534264087677, "learning_rate": 3.5742791067634864e-05, "loss": 1.1391, "step": 11054 }, { "epoch": 0.6044079958995388, "grad_norm": 3.09690260887146, "learning_rate": 3.5734305302319464e-05, "loss": 0.9371, "step": 11055 }, { "epoch": 0.6044626687168974, "grad_norm": 2.5991945266723633, "learning_rate": 3.572581998429236e-05, "loss": 0.9844, "step": 11056 }, { "epoch": 0.604517341534256, "grad_norm": 2.288313627243042, "learning_rate": 3.5717335113819585e-05, "loss": 1.012, "step": 11057 }, { "epoch": 0.6045720143516146, "grad_norm": 3.937643527984619, "learning_rate": 3.570885069116717e-05, "loss": 1.2291, "step": 11058 }, { "epoch": 0.6046266871689732, "grad_norm": 2.0362768173217773, "learning_rate": 3.5700366716601144e-05, "loss": 0.8918, "step": 11059 }, { "epoch": 0.6046813599863318, "grad_norm": 2.744450092315674, "learning_rate": 3.569188319038752e-05, "loss": 1.1098, "step": 11060 }, { "epoch": 0.6047360328036904, "grad_norm": 2.1418309211730957, "learning_rate": 3.568340011279228e-05, "loss": 1.0651, "step": 11061 }, { "epoch": 0.6047907056210491, "grad_norm": 2.4306607246398926, "learning_rate": 3.567491748408141e-05, "loss": 0.9979, "step": 11062 }, { "epoch": 0.6048453784384077, "grad_norm": 2.1452436447143555, "learning_rate": 3.566643530452087e-05, "loss": 1.0677, "step": 11063 }, { "epoch": 0.6049000512557663, "grad_norm": 2.3023440837860107, "learning_rate": 3.565795357437662e-05, "loss": 1.0777, "step": 11064 }, { "epoch": 0.6049547240731249, "grad_norm": 3.8123059272766113, "learning_rate": 3.564947229391457e-05, "loss": 0.9979, "step": 11065 }, { "epoch": 0.6050093968904835, "grad_norm": 2.8673808574676514, "learning_rate": 3.564099146340069e-05, "loss": 1.1216, "step": 11066 }, { "epoch": 0.6050640697078421, "grad_norm": 2.495232343673706, "learning_rate": 3.563251108310086e-05, "loss": 1.1502, "step": 11067 }, { "epoch": 0.6051187425252007, "grad_norm": 2.0906383991241455, "learning_rate": 3.562403115328098e-05, "loss": 0.8413, "step": 11068 }, { "epoch": 0.6051734153425594, "grad_norm": 2.1953964233398438, "learning_rate": 3.5615551674206924e-05, "loss": 1.0144, "step": 11069 }, { "epoch": 0.605228088159918, "grad_norm": 3.453472852706909, "learning_rate": 3.560707264614457e-05, "loss": 1.1126, "step": 11070 }, { "epoch": 0.6052827609772766, "grad_norm": 3.1347947120666504, "learning_rate": 3.559859406935977e-05, "loss": 0.994, "step": 11071 }, { "epoch": 0.6053374337946352, "grad_norm": 2.4772839546203613, "learning_rate": 3.559011594411835e-05, "loss": 0.8828, "step": 11072 }, { "epoch": 0.6053921066119938, "grad_norm": 3.025675058364868, "learning_rate": 3.558163827068614e-05, "loss": 1.026, "step": 11073 }, { "epoch": 0.6054467794293524, "grad_norm": 2.9888572692871094, "learning_rate": 3.557316104932895e-05, "loss": 1.1118, "step": 11074 }, { "epoch": 0.605501452246711, "grad_norm": 2.6489477157592773, "learning_rate": 3.556468428031257e-05, "loss": 0.8887, "step": 11075 }, { "epoch": 0.6055561250640698, "grad_norm": 2.5540993213653564, "learning_rate": 3.55562079639028e-05, "loss": 0.9958, "step": 11076 }, { "epoch": 0.6056107978814284, "grad_norm": 2.263803005218506, "learning_rate": 3.5547732100365394e-05, "loss": 0.9054, "step": 11077 }, { "epoch": 0.605665470698787, "grad_norm": 2.5430080890655518, "learning_rate": 3.55392566899661e-05, "loss": 0.9309, "step": 11078 }, { "epoch": 0.6057201435161456, "grad_norm": 3.2241289615631104, "learning_rate": 3.553078173297068e-05, "loss": 1.0441, "step": 11079 }, { "epoch": 0.6057748163335042, "grad_norm": 2.4875638484954834, "learning_rate": 3.552230722964484e-05, "loss": 0.9394, "step": 11080 }, { "epoch": 0.6058294891508628, "grad_norm": 2.5719199180603027, "learning_rate": 3.5513833180254285e-05, "loss": 0.9505, "step": 11081 }, { "epoch": 0.6058841619682215, "grad_norm": 2.235663414001465, "learning_rate": 3.550535958506473e-05, "loss": 0.9692, "step": 11082 }, { "epoch": 0.6059388347855801, "grad_norm": 2.549605131149292, "learning_rate": 3.549688644434184e-05, "loss": 0.966, "step": 11083 }, { "epoch": 0.6059935076029387, "grad_norm": 2.377014636993408, "learning_rate": 3.5488413758351294e-05, "loss": 1.0377, "step": 11084 }, { "epoch": 0.6060481804202973, "grad_norm": 2.6432816982269287, "learning_rate": 3.547994152735872e-05, "loss": 1.1661, "step": 11085 }, { "epoch": 0.6061028532376559, "grad_norm": 2.4759304523468018, "learning_rate": 3.547146975162979e-05, "loss": 0.796, "step": 11086 }, { "epoch": 0.6061575260550145, "grad_norm": 2.6457457542419434, "learning_rate": 3.546299843143013e-05, "loss": 0.9235, "step": 11087 }, { "epoch": 0.6062121988723731, "grad_norm": 2.2616357803344727, "learning_rate": 3.545452756702534e-05, "loss": 0.7616, "step": 11088 }, { "epoch": 0.6062668716897318, "grad_norm": 3.577911853790283, "learning_rate": 3.544605715868101e-05, "loss": 1.1168, "step": 11089 }, { "epoch": 0.6063215445070904, "grad_norm": 2.2825734615325928, "learning_rate": 3.543758720666273e-05, "loss": 0.9045, "step": 11090 }, { "epoch": 0.606376217324449, "grad_norm": 1.9913227558135986, "learning_rate": 3.5429117711236065e-05, "loss": 0.9837, "step": 11091 }, { "epoch": 0.6064308901418076, "grad_norm": 2.8178248405456543, "learning_rate": 3.542064867266657e-05, "loss": 0.9893, "step": 11092 }, { "epoch": 0.6064855629591662, "grad_norm": 3.379176139831543, "learning_rate": 3.541218009121978e-05, "loss": 0.9172, "step": 11093 }, { "epoch": 0.6065402357765248, "grad_norm": 2.4829134941101074, "learning_rate": 3.5403711967161225e-05, "loss": 1.2178, "step": 11094 }, { "epoch": 0.6065949085938834, "grad_norm": 2.47696852684021, "learning_rate": 3.539524430075639e-05, "loss": 0.8132, "step": 11095 }, { "epoch": 0.6066495814112421, "grad_norm": 2.8272836208343506, "learning_rate": 3.538677709227082e-05, "loss": 1.0964, "step": 11096 }, { "epoch": 0.6067042542286007, "grad_norm": 2.7287042140960693, "learning_rate": 3.537831034196997e-05, "loss": 1.0539, "step": 11097 }, { "epoch": 0.6067589270459594, "grad_norm": 2.440561294555664, "learning_rate": 3.536984405011931e-05, "loss": 1.0187, "step": 11098 }, { "epoch": 0.606813599863318, "grad_norm": 2.2570483684539795, "learning_rate": 3.5361378216984284e-05, "loss": 1.0942, "step": 11099 }, { "epoch": 0.6068682726806766, "grad_norm": 2.969646453857422, "learning_rate": 3.5352912842830354e-05, "loss": 1.0774, "step": 11100 }, { "epoch": 0.6069229454980352, "grad_norm": 2.2548768520355225, "learning_rate": 3.534444792792292e-05, "loss": 0.8664, "step": 11101 }, { "epoch": 0.6069776183153938, "grad_norm": 2.8283324241638184, "learning_rate": 3.53359834725274e-05, "loss": 1.1094, "step": 11102 }, { "epoch": 0.6070322911327525, "grad_norm": 2.807953119277954, "learning_rate": 3.53275194769092e-05, "loss": 1.06, "step": 11103 }, { "epoch": 0.6070869639501111, "grad_norm": 3.4360744953155518, "learning_rate": 3.531905594133366e-05, "loss": 1.1603, "step": 11104 }, { "epoch": 0.6071416367674697, "grad_norm": 3.7383835315704346, "learning_rate": 3.53105928660662e-05, "loss": 1.1387, "step": 11105 }, { "epoch": 0.6071963095848283, "grad_norm": 2.4269497394561768, "learning_rate": 3.530213025137216e-05, "loss": 0.9931, "step": 11106 }, { "epoch": 0.6072509824021869, "grad_norm": 2.4692533016204834, "learning_rate": 3.529366809751686e-05, "loss": 0.9858, "step": 11107 }, { "epoch": 0.6073056552195455, "grad_norm": 3.117854595184326, "learning_rate": 3.528520640476564e-05, "loss": 1.0806, "step": 11108 }, { "epoch": 0.6073603280369042, "grad_norm": 2.6036224365234375, "learning_rate": 3.52767451733838e-05, "loss": 1.0471, "step": 11109 }, { "epoch": 0.6074150008542628, "grad_norm": 3.5866847038269043, "learning_rate": 3.526828440363663e-05, "loss": 1.0877, "step": 11110 }, { "epoch": 0.6074696736716214, "grad_norm": 2.6620965003967285, "learning_rate": 3.525982409578942e-05, "loss": 0.7021, "step": 11111 }, { "epoch": 0.60752434648898, "grad_norm": 2.124075174331665, "learning_rate": 3.525136425010743e-05, "loss": 0.9279, "step": 11112 }, { "epoch": 0.6075790193063386, "grad_norm": 2.0826191902160645, "learning_rate": 3.5242904866855916e-05, "loss": 0.9671, "step": 11113 }, { "epoch": 0.6076336921236972, "grad_norm": 2.955681324005127, "learning_rate": 3.523444594630009e-05, "loss": 0.8724, "step": 11114 }, { "epoch": 0.6076883649410558, "grad_norm": 2.5901825428009033, "learning_rate": 3.52259874887052e-05, "loss": 1.0474, "step": 11115 }, { "epoch": 0.6077430377584145, "grad_norm": 3.114124059677124, "learning_rate": 3.5217529494336463e-05, "loss": 1.2142, "step": 11116 }, { "epoch": 0.6077977105757731, "grad_norm": 2.4158573150634766, "learning_rate": 3.520907196345905e-05, "loss": 0.9164, "step": 11117 }, { "epoch": 0.6078523833931317, "grad_norm": 3.816871166229248, "learning_rate": 3.5200614896338154e-05, "loss": 0.9623, "step": 11118 }, { "epoch": 0.6079070562104903, "grad_norm": 2.558852195739746, "learning_rate": 3.519215829323892e-05, "loss": 0.9232, "step": 11119 }, { "epoch": 0.607961729027849, "grad_norm": 4.033980369567871, "learning_rate": 3.518370215442652e-05, "loss": 1.2344, "step": 11120 }, { "epoch": 0.6080164018452076, "grad_norm": 2.4360153675079346, "learning_rate": 3.517524648016607e-05, "loss": 1.0256, "step": 11121 }, { "epoch": 0.6080710746625662, "grad_norm": 2.270265817642212, "learning_rate": 3.51667912707227e-05, "loss": 0.9741, "step": 11122 }, { "epoch": 0.6081257474799249, "grad_norm": 3.401545286178589, "learning_rate": 3.515833652636151e-05, "loss": 1.1362, "step": 11123 }, { "epoch": 0.6081804202972835, "grad_norm": 2.4612481594085693, "learning_rate": 3.5149882247347584e-05, "loss": 0.9986, "step": 11124 }, { "epoch": 0.6082350931146421, "grad_norm": 4.079896450042725, "learning_rate": 3.514142843394603e-05, "loss": 1.1229, "step": 11125 }, { "epoch": 0.6082897659320007, "grad_norm": 2.9495766162872314, "learning_rate": 3.513297508642188e-05, "loss": 1.0001, "step": 11126 }, { "epoch": 0.6083444387493593, "grad_norm": 2.3027541637420654, "learning_rate": 3.512452220504019e-05, "loss": 1.0436, "step": 11127 }, { "epoch": 0.6083991115667179, "grad_norm": 2.7821898460388184, "learning_rate": 3.511606979006598e-05, "loss": 0.994, "step": 11128 }, { "epoch": 0.6084537843840765, "grad_norm": 2.377978801727295, "learning_rate": 3.5107617841764296e-05, "loss": 1.0343, "step": 11129 }, { "epoch": 0.6085084572014352, "grad_norm": 2.4419567584991455, "learning_rate": 3.509916636040012e-05, "loss": 0.8825, "step": 11130 }, { "epoch": 0.6085631300187938, "grad_norm": 2.524610757827759, "learning_rate": 3.509071534623845e-05, "loss": 0.9879, "step": 11131 }, { "epoch": 0.6086178028361524, "grad_norm": 2.2708563804626465, "learning_rate": 3.5082264799544265e-05, "loss": 1.0935, "step": 11132 }, { "epoch": 0.608672475653511, "grad_norm": 2.426847219467163, "learning_rate": 3.5073814720582496e-05, "loss": 0.9911, "step": 11133 }, { "epoch": 0.6087271484708696, "grad_norm": 2.3498551845550537, "learning_rate": 3.5065365109618114e-05, "loss": 1.0375, "step": 11134 }, { "epoch": 0.6087818212882282, "grad_norm": 2.9399192333221436, "learning_rate": 3.505691596691605e-05, "loss": 1.1444, "step": 11135 }, { "epoch": 0.6088364941055869, "grad_norm": 2.6065053939819336, "learning_rate": 3.504846729274121e-05, "loss": 0.9438, "step": 11136 }, { "epoch": 0.6088911669229455, "grad_norm": 2.5070855617523193, "learning_rate": 3.50400190873585e-05, "loss": 0.9514, "step": 11137 }, { "epoch": 0.6089458397403041, "grad_norm": 2.337038040161133, "learning_rate": 3.50315713510328e-05, "loss": 1.0661, "step": 11138 }, { "epoch": 0.6090005125576627, "grad_norm": 2.8876664638519287, "learning_rate": 3.502312408402899e-05, "loss": 0.8785, "step": 11139 }, { "epoch": 0.6090551853750213, "grad_norm": 2.436940908432007, "learning_rate": 3.501467728661192e-05, "loss": 1.0761, "step": 11140 }, { "epoch": 0.60910985819238, "grad_norm": 2.8980655670166016, "learning_rate": 3.500623095904641e-05, "loss": 1.163, "step": 11141 }, { "epoch": 0.6091645310097386, "grad_norm": 3.0108323097229004, "learning_rate": 3.499778510159734e-05, "loss": 1.1503, "step": 11142 }, { "epoch": 0.6092192038270973, "grad_norm": 2.412034034729004, "learning_rate": 3.4989339714529476e-05, "loss": 1.0873, "step": 11143 }, { "epoch": 0.6092738766444559, "grad_norm": 2.787564754486084, "learning_rate": 3.498089479810763e-05, "loss": 0.942, "step": 11144 }, { "epoch": 0.6093285494618145, "grad_norm": 2.291520595550537, "learning_rate": 3.49724503525966e-05, "loss": 1.1176, "step": 11145 }, { "epoch": 0.6093832222791731, "grad_norm": 2.8909687995910645, "learning_rate": 3.4964006378261146e-05, "loss": 1.0975, "step": 11146 }, { "epoch": 0.6094378950965317, "grad_norm": 2.808771848678589, "learning_rate": 3.4955562875366014e-05, "loss": 0.8578, "step": 11147 }, { "epoch": 0.6094925679138903, "grad_norm": 2.8409645557403564, "learning_rate": 3.4947119844175934e-05, "loss": 1.1966, "step": 11148 }, { "epoch": 0.6095472407312489, "grad_norm": 2.271873712539673, "learning_rate": 3.493867728495565e-05, "loss": 0.8563, "step": 11149 }, { "epoch": 0.6096019135486076, "grad_norm": 2.70359468460083, "learning_rate": 3.493023519796986e-05, "loss": 0.9466, "step": 11150 }, { "epoch": 0.6096565863659662, "grad_norm": 2.402970790863037, "learning_rate": 3.4921793583483256e-05, "loss": 1.0503, "step": 11151 }, { "epoch": 0.6097112591833248, "grad_norm": 2.3459620475769043, "learning_rate": 3.4913352441760525e-05, "loss": 0.9044, "step": 11152 }, { "epoch": 0.6097659320006834, "grad_norm": 1.9818718433380127, "learning_rate": 3.4904911773066326e-05, "loss": 0.9053, "step": 11153 }, { "epoch": 0.609820604818042, "grad_norm": 2.5214571952819824, "learning_rate": 3.4896471577665304e-05, "loss": 1.0071, "step": 11154 }, { "epoch": 0.6098752776354006, "grad_norm": 2.240553140640259, "learning_rate": 3.488803185582211e-05, "loss": 0.8478, "step": 11155 }, { "epoch": 0.6099299504527592, "grad_norm": 2.609283447265625, "learning_rate": 3.4879592607801355e-05, "loss": 1.2442, "step": 11156 }, { "epoch": 0.6099846232701179, "grad_norm": 2.7914085388183594, "learning_rate": 3.487115383386764e-05, "loss": 1.1661, "step": 11157 }, { "epoch": 0.6100392960874765, "grad_norm": 3.3017704486846924, "learning_rate": 3.486271553428557e-05, "loss": 1.2635, "step": 11158 }, { "epoch": 0.6100939689048351, "grad_norm": 4.825277328491211, "learning_rate": 3.485427770931971e-05, "loss": 1.0738, "step": 11159 }, { "epoch": 0.6101486417221937, "grad_norm": 2.393352746963501, "learning_rate": 3.484584035923461e-05, "loss": 1.1608, "step": 11160 }, { "epoch": 0.6102033145395523, "grad_norm": 3.0673863887786865, "learning_rate": 3.483740348429483e-05, "loss": 1.0295, "step": 11161 }, { "epoch": 0.610257987356911, "grad_norm": 3.3665759563446045, "learning_rate": 3.4828967084764896e-05, "loss": 0.9746, "step": 11162 }, { "epoch": 0.6103126601742696, "grad_norm": 2.522916555404663, "learning_rate": 3.482053116090931e-05, "loss": 0.9862, "step": 11163 }, { "epoch": 0.6103673329916283, "grad_norm": 3.4448680877685547, "learning_rate": 3.48120957129926e-05, "loss": 0.9375, "step": 11164 }, { "epoch": 0.6104220058089869, "grad_norm": 2.587164878845215, "learning_rate": 3.480366074127924e-05, "loss": 1.0777, "step": 11165 }, { "epoch": 0.6104766786263455, "grad_norm": 2.693239450454712, "learning_rate": 3.479522624603371e-05, "loss": 1.0043, "step": 11166 }, { "epoch": 0.6105313514437041, "grad_norm": 2.2729148864746094, "learning_rate": 3.478679222752045e-05, "loss": 0.8472, "step": 11167 }, { "epoch": 0.6105860242610627, "grad_norm": 2.623197555541992, "learning_rate": 3.477835868600392e-05, "loss": 0.9774, "step": 11168 }, { "epoch": 0.6106406970784213, "grad_norm": 2.3005266189575195, "learning_rate": 3.4769925621748525e-05, "loss": 1.0533, "step": 11169 }, { "epoch": 0.61069536989578, "grad_norm": 3.4899628162384033, "learning_rate": 3.4761493035018676e-05, "loss": 1.1099, "step": 11170 }, { "epoch": 0.6107500427131386, "grad_norm": 2.5396130084991455, "learning_rate": 3.4753060926078795e-05, "loss": 1.0839, "step": 11171 }, { "epoch": 0.6108047155304972, "grad_norm": 2.4956958293914795, "learning_rate": 3.474462929519324e-05, "loss": 0.9687, "step": 11172 }, { "epoch": 0.6108593883478558, "grad_norm": 2.2327661514282227, "learning_rate": 3.4736198142626365e-05, "loss": 0.9679, "step": 11173 }, { "epoch": 0.6109140611652144, "grad_norm": 2.8867108821868896, "learning_rate": 3.472776746864256e-05, "loss": 1.0139, "step": 11174 }, { "epoch": 0.610968733982573, "grad_norm": 3.5598948001861572, "learning_rate": 3.4719337273506145e-05, "loss": 1.2431, "step": 11175 }, { "epoch": 0.6110234067999316, "grad_norm": 3.3721346855163574, "learning_rate": 3.4710907557481435e-05, "loss": 1.0834, "step": 11176 }, { "epoch": 0.6110780796172903, "grad_norm": 2.6161341667175293, "learning_rate": 3.4702478320832745e-05, "loss": 1.0474, "step": 11177 }, { "epoch": 0.6111327524346489, "grad_norm": 3.2237794399261475, "learning_rate": 3.469404956382436e-05, "loss": 1.0995, "step": 11178 }, { "epoch": 0.6111874252520075, "grad_norm": 2.784050226211548, "learning_rate": 3.468562128672056e-05, "loss": 1.1987, "step": 11179 }, { "epoch": 0.6112420980693661, "grad_norm": 2.827517032623291, "learning_rate": 3.4677193489785595e-05, "loss": 1.0007, "step": 11180 }, { "epoch": 0.6112967708867247, "grad_norm": 2.7177023887634277, "learning_rate": 3.4668766173283726e-05, "loss": 1.1821, "step": 11181 }, { "epoch": 0.6113514437040833, "grad_norm": 2.3633134365081787, "learning_rate": 3.466033933747919e-05, "loss": 0.9368, "step": 11182 }, { "epoch": 0.611406116521442, "grad_norm": 3.02945876121521, "learning_rate": 3.465191298263615e-05, "loss": 0.9819, "step": 11183 }, { "epoch": 0.6114607893388007, "grad_norm": 2.4563162326812744, "learning_rate": 3.464348710901888e-05, "loss": 1.0213, "step": 11184 }, { "epoch": 0.6115154621561593, "grad_norm": 2.0180647373199463, "learning_rate": 3.4635061716891535e-05, "loss": 0.9604, "step": 11185 }, { "epoch": 0.6115701349735179, "grad_norm": 2.565490245819092, "learning_rate": 3.4626636806518274e-05, "loss": 1.0056, "step": 11186 }, { "epoch": 0.6116248077908765, "grad_norm": 3.153111457824707, "learning_rate": 3.461821237816327e-05, "loss": 1.0241, "step": 11187 }, { "epoch": 0.6116794806082351, "grad_norm": 2.4262232780456543, "learning_rate": 3.460978843209066e-05, "loss": 0.9103, "step": 11188 }, { "epoch": 0.6117341534255937, "grad_norm": 2.874565362930298, "learning_rate": 3.460136496856456e-05, "loss": 0.9716, "step": 11189 }, { "epoch": 0.6117888262429523, "grad_norm": 2.609893321990967, "learning_rate": 3.4592941987849096e-05, "loss": 0.8456, "step": 11190 }, { "epoch": 0.611843499060311, "grad_norm": 2.559105157852173, "learning_rate": 3.4584519490208344e-05, "loss": 0.8775, "step": 11191 }, { "epoch": 0.6118981718776696, "grad_norm": 2.4094619750976562, "learning_rate": 3.45760974759064e-05, "loss": 0.9203, "step": 11192 }, { "epoch": 0.6119528446950282, "grad_norm": 2.912926435470581, "learning_rate": 3.45676759452073e-05, "loss": 1.115, "step": 11193 }, { "epoch": 0.6120075175123868, "grad_norm": 2.838901996612549, "learning_rate": 3.455925489837514e-05, "loss": 0.9972, "step": 11194 }, { "epoch": 0.6120621903297454, "grad_norm": 2.4126477241516113, "learning_rate": 3.455083433567392e-05, "loss": 1.0081, "step": 11195 }, { "epoch": 0.612116863147104, "grad_norm": 2.4261038303375244, "learning_rate": 3.4542414257367676e-05, "loss": 1.0357, "step": 11196 }, { "epoch": 0.6121715359644627, "grad_norm": 2.1864562034606934, "learning_rate": 3.453399466372041e-05, "loss": 1.0024, "step": 11197 }, { "epoch": 0.6122262087818213, "grad_norm": 2.3678109645843506, "learning_rate": 3.4525575554996104e-05, "loss": 0.9071, "step": 11198 }, { "epoch": 0.6122808815991799, "grad_norm": 2.675381660461426, "learning_rate": 3.4517156931458735e-05, "loss": 1.0581, "step": 11199 }, { "epoch": 0.6123355544165385, "grad_norm": 2.9909586906433105, "learning_rate": 3.450873879337225e-05, "loss": 0.8744, "step": 11200 }, { "epoch": 0.6123902272338971, "grad_norm": 2.4704017639160156, "learning_rate": 3.4500321141000624e-05, "loss": 1.1289, "step": 11201 }, { "epoch": 0.6124449000512557, "grad_norm": 2.401986837387085, "learning_rate": 3.449190397460775e-05, "loss": 1.0389, "step": 11202 }, { "epoch": 0.6124995728686143, "grad_norm": 2.556337833404541, "learning_rate": 3.448348729445754e-05, "loss": 1.2456, "step": 11203 }, { "epoch": 0.612554245685973, "grad_norm": 2.3586905002593994, "learning_rate": 3.447507110081393e-05, "loss": 1.0174, "step": 11204 }, { "epoch": 0.6126089185033317, "grad_norm": 2.6575655937194824, "learning_rate": 3.446665539394077e-05, "loss": 1.0996, "step": 11205 }, { "epoch": 0.6126635913206903, "grad_norm": 2.9571585655212402, "learning_rate": 3.445824017410194e-05, "loss": 1.0513, "step": 11206 }, { "epoch": 0.6127182641380489, "grad_norm": 3.2588412761688232, "learning_rate": 3.4449825441561296e-05, "loss": 1.1748, "step": 11207 }, { "epoch": 0.6127729369554075, "grad_norm": 2.6925430297851562, "learning_rate": 3.444141119658266e-05, "loss": 1.1465, "step": 11208 }, { "epoch": 0.6128276097727661, "grad_norm": 2.916215658187866, "learning_rate": 3.443299743942986e-05, "loss": 1.0609, "step": 11209 }, { "epoch": 0.6128822825901247, "grad_norm": 3.5968525409698486, "learning_rate": 3.44245841703667e-05, "loss": 0.8901, "step": 11210 }, { "epoch": 0.6129369554074834, "grad_norm": 2.510143756866455, "learning_rate": 3.441617138965698e-05, "loss": 0.9727, "step": 11211 }, { "epoch": 0.612991628224842, "grad_norm": 2.5496907234191895, "learning_rate": 3.4407759097564454e-05, "loss": 1.0399, "step": 11212 }, { "epoch": 0.6130463010422006, "grad_norm": 3.086334466934204, "learning_rate": 3.4399347294352904e-05, "loss": 1.0209, "step": 11213 }, { "epoch": 0.6131009738595592, "grad_norm": 3.609001398086548, "learning_rate": 3.439093598028607e-05, "loss": 0.8778, "step": 11214 }, { "epoch": 0.6131556466769178, "grad_norm": 2.5887043476104736, "learning_rate": 3.438252515562767e-05, "loss": 1.1586, "step": 11215 }, { "epoch": 0.6132103194942764, "grad_norm": 2.5590567588806152, "learning_rate": 3.4374114820641425e-05, "loss": 0.9707, "step": 11216 }, { "epoch": 0.613264992311635, "grad_norm": 3.4075980186462402, "learning_rate": 3.436570497559104e-05, "loss": 0.8711, "step": 11217 }, { "epoch": 0.6133196651289937, "grad_norm": 2.34057879447937, "learning_rate": 3.435729562074019e-05, "loss": 1.156, "step": 11218 }, { "epoch": 0.6133743379463523, "grad_norm": 2.818343162536621, "learning_rate": 3.4348886756352555e-05, "loss": 1.0258, "step": 11219 }, { "epoch": 0.6134290107637109, "grad_norm": 2.14361834526062, "learning_rate": 3.434047838269178e-05, "loss": 0.8481, "step": 11220 }, { "epoch": 0.6134836835810695, "grad_norm": 2.8885459899902344, "learning_rate": 3.4332070500021486e-05, "loss": 1.16, "step": 11221 }, { "epoch": 0.6135383563984281, "grad_norm": 2.9908618927001953, "learning_rate": 3.432366310860531e-05, "loss": 1.1035, "step": 11222 }, { "epoch": 0.6135930292157867, "grad_norm": 3.087287187576294, "learning_rate": 3.431525620870686e-05, "loss": 1.0971, "step": 11223 }, { "epoch": 0.6136477020331454, "grad_norm": 2.6161067485809326, "learning_rate": 3.4306849800589727e-05, "loss": 0.8163, "step": 11224 }, { "epoch": 0.613702374850504, "grad_norm": 2.6199114322662354, "learning_rate": 3.429844388451749e-05, "loss": 0.9538, "step": 11225 }, { "epoch": 0.6137570476678627, "grad_norm": 2.4626829624176025, "learning_rate": 3.429003846075369e-05, "loss": 1.0179, "step": 11226 }, { "epoch": 0.6138117204852213, "grad_norm": 2.7534687519073486, "learning_rate": 3.42816335295619e-05, "loss": 1.0478, "step": 11227 }, { "epoch": 0.6138663933025799, "grad_norm": 3.1118643283843994, "learning_rate": 3.4273229091205616e-05, "loss": 1.071, "step": 11228 }, { "epoch": 0.6139210661199385, "grad_norm": 2.3379745483398438, "learning_rate": 3.426482514594838e-05, "loss": 1.0218, "step": 11229 }, { "epoch": 0.6139757389372971, "grad_norm": 2.8472378253936768, "learning_rate": 3.425642169405368e-05, "loss": 1.1336, "step": 11230 }, { "epoch": 0.6140304117546558, "grad_norm": 3.0430424213409424, "learning_rate": 3.4248018735785e-05, "loss": 1.0715, "step": 11231 }, { "epoch": 0.6140850845720144, "grad_norm": 2.644174814224243, "learning_rate": 3.4239616271405796e-05, "loss": 1.0064, "step": 11232 }, { "epoch": 0.614139757389373, "grad_norm": 3.0218396186828613, "learning_rate": 3.4231214301179536e-05, "loss": 1.1116, "step": 11233 }, { "epoch": 0.6141944302067316, "grad_norm": 2.87256121635437, "learning_rate": 3.422281282536965e-05, "loss": 1.2023, "step": 11234 }, { "epoch": 0.6142491030240902, "grad_norm": 2.6398117542266846, "learning_rate": 3.421441184423957e-05, "loss": 1.193, "step": 11235 }, { "epoch": 0.6143037758414488, "grad_norm": 3.5579473972320557, "learning_rate": 3.420601135805268e-05, "loss": 1.0442, "step": 11236 }, { "epoch": 0.6143584486588074, "grad_norm": 2.1076033115386963, "learning_rate": 3.419761136707238e-05, "loss": 0.9298, "step": 11237 }, { "epoch": 0.6144131214761661, "grad_norm": 2.388772964477539, "learning_rate": 3.418921187156206e-05, "loss": 1.0699, "step": 11238 }, { "epoch": 0.6144677942935247, "grad_norm": 2.977623701095581, "learning_rate": 3.418081287178504e-05, "loss": 0.9739, "step": 11239 }, { "epoch": 0.6145224671108833, "grad_norm": 2.353693962097168, "learning_rate": 3.41724143680047e-05, "loss": 1.0403, "step": 11240 }, { "epoch": 0.6145771399282419, "grad_norm": 4.487499237060547, "learning_rate": 3.416401636048434e-05, "loss": 1.2133, "step": 11241 }, { "epoch": 0.6146318127456005, "grad_norm": 3.107408046722412, "learning_rate": 3.4155618849487294e-05, "loss": 0.9504, "step": 11242 }, { "epoch": 0.6146864855629591, "grad_norm": 3.068514108657837, "learning_rate": 3.4147221835276856e-05, "loss": 0.891, "step": 11243 }, { "epoch": 0.6147411583803177, "grad_norm": 2.2983036041259766, "learning_rate": 3.41388253181163e-05, "loss": 0.8554, "step": 11244 }, { "epoch": 0.6147958311976764, "grad_norm": 2.3512566089630127, "learning_rate": 3.41304292982689e-05, "loss": 1.0126, "step": 11245 }, { "epoch": 0.614850504015035, "grad_norm": 2.1558077335357666, "learning_rate": 3.412203377599789e-05, "loss": 1.113, "step": 11246 }, { "epoch": 0.6149051768323937, "grad_norm": 2.497243642807007, "learning_rate": 3.411363875156652e-05, "loss": 0.9519, "step": 11247 }, { "epoch": 0.6149598496497523, "grad_norm": 2.860261917114258, "learning_rate": 3.4105244225238e-05, "loss": 1.1092, "step": 11248 }, { "epoch": 0.6150145224671109, "grad_norm": 1.8585351705551147, "learning_rate": 3.409685019727554e-05, "loss": 0.7392, "step": 11249 }, { "epoch": 0.6150691952844695, "grad_norm": 2.5594124794006348, "learning_rate": 3.4088456667942315e-05, "loss": 1.0166, "step": 11250 }, { "epoch": 0.6151238681018282, "grad_norm": 2.601747512817383, "learning_rate": 3.4080063637501504e-05, "loss": 0.9705, "step": 11251 }, { "epoch": 0.6151785409191868, "grad_norm": 2.3058087825775146, "learning_rate": 3.4071671106216246e-05, "loss": 1.0327, "step": 11252 }, { "epoch": 0.6152332137365454, "grad_norm": 2.2855639457702637, "learning_rate": 3.406327907434972e-05, "loss": 0.8252, "step": 11253 }, { "epoch": 0.615287886553904, "grad_norm": 3.00826358795166, "learning_rate": 3.405488754216502e-05, "loss": 1.1562, "step": 11254 }, { "epoch": 0.6153425593712626, "grad_norm": 3.4628372192382812, "learning_rate": 3.404649650992528e-05, "loss": 1.2155, "step": 11255 }, { "epoch": 0.6153972321886212, "grad_norm": 2.829380750656128, "learning_rate": 3.403810597789357e-05, "loss": 1.1472, "step": 11256 }, { "epoch": 0.6154519050059798, "grad_norm": 3.205989122390747, "learning_rate": 3.4029715946332976e-05, "loss": 1.09, "step": 11257 }, { "epoch": 0.6155065778233385, "grad_norm": 2.377565860748291, "learning_rate": 3.402132641550656e-05, "loss": 1.0651, "step": 11258 }, { "epoch": 0.6155612506406971, "grad_norm": 5.010770320892334, "learning_rate": 3.4012937385677366e-05, "loss": 0.9534, "step": 11259 }, { "epoch": 0.6156159234580557, "grad_norm": 2.6472482681274414, "learning_rate": 3.400454885710843e-05, "loss": 0.9432, "step": 11260 }, { "epoch": 0.6156705962754143, "grad_norm": 2.3248844146728516, "learning_rate": 3.399616083006274e-05, "loss": 1.1745, "step": 11261 }, { "epoch": 0.6157252690927729, "grad_norm": 2.826390266418457, "learning_rate": 3.398777330480334e-05, "loss": 1.0711, "step": 11262 }, { "epoch": 0.6157799419101315, "grad_norm": 2.8849782943725586, "learning_rate": 3.3979386281593186e-05, "loss": 1.0486, "step": 11263 }, { "epoch": 0.6158346147274901, "grad_norm": 2.543565273284912, "learning_rate": 3.3970999760695266e-05, "loss": 1.1494, "step": 11264 }, { "epoch": 0.6158892875448488, "grad_norm": 2.8216466903686523, "learning_rate": 3.396261374237251e-05, "loss": 1.0152, "step": 11265 }, { "epoch": 0.6159439603622074, "grad_norm": 2.6289188861846924, "learning_rate": 3.3954228226887855e-05, "loss": 1.0483, "step": 11266 }, { "epoch": 0.615998633179566, "grad_norm": 2.4384515285491943, "learning_rate": 3.394584321450424e-05, "loss": 0.8938, "step": 11267 }, { "epoch": 0.6160533059969246, "grad_norm": 2.5777816772460938, "learning_rate": 3.393745870548455e-05, "loss": 1.0135, "step": 11268 }, { "epoch": 0.6161079788142833, "grad_norm": 2.81430983543396, "learning_rate": 3.3929074700091686e-05, "loss": 1.2111, "step": 11269 }, { "epoch": 0.6161626516316419, "grad_norm": 2.232149362564087, "learning_rate": 3.392069119858852e-05, "loss": 1.0171, "step": 11270 }, { "epoch": 0.6162173244490005, "grad_norm": 2.9850685596466064, "learning_rate": 3.3912308201237883e-05, "loss": 0.9205, "step": 11271 }, { "epoch": 0.6162719972663592, "grad_norm": 5.228956699371338, "learning_rate": 3.390392570830266e-05, "loss": 1.0465, "step": 11272 }, { "epoch": 0.6163266700837178, "grad_norm": 2.2235171794891357, "learning_rate": 3.389554372004565e-05, "loss": 0.956, "step": 11273 }, { "epoch": 0.6163813429010764, "grad_norm": 2.1070284843444824, "learning_rate": 3.388716223672968e-05, "loss": 0.91, "step": 11274 }, { "epoch": 0.616436015718435, "grad_norm": 3.79069185256958, "learning_rate": 3.387878125861753e-05, "loss": 0.9839, "step": 11275 }, { "epoch": 0.6164906885357936, "grad_norm": 1.983031153678894, "learning_rate": 3.3870400785971975e-05, "loss": 0.8557, "step": 11276 }, { "epoch": 0.6165453613531522, "grad_norm": 2.8667211532592773, "learning_rate": 3.38620208190558e-05, "loss": 0.8944, "step": 11277 }, { "epoch": 0.6166000341705109, "grad_norm": 3.6923837661743164, "learning_rate": 3.3853641358131726e-05, "loss": 0.9974, "step": 11278 }, { "epoch": 0.6166547069878695, "grad_norm": 2.607879161834717, "learning_rate": 3.384526240346249e-05, "loss": 0.9448, "step": 11279 }, { "epoch": 0.6167093798052281, "grad_norm": 2.3643572330474854, "learning_rate": 3.383688395531082e-05, "loss": 1.0911, "step": 11280 }, { "epoch": 0.6167640526225867, "grad_norm": 2.4818332195281982, "learning_rate": 3.382850601393937e-05, "loss": 0.9728, "step": 11281 }, { "epoch": 0.6168187254399453, "grad_norm": 2.848545551300049, "learning_rate": 3.3820128579610885e-05, "loss": 1.0222, "step": 11282 }, { "epoch": 0.6168733982573039, "grad_norm": 4.476296901702881, "learning_rate": 3.381175165258801e-05, "loss": 1.0551, "step": 11283 }, { "epoch": 0.6169280710746625, "grad_norm": 2.3146212100982666, "learning_rate": 3.3803375233133385e-05, "loss": 1.063, "step": 11284 }, { "epoch": 0.6169827438920212, "grad_norm": 2.592437982559204, "learning_rate": 3.3794999321509646e-05, "loss": 1.0346, "step": 11285 }, { "epoch": 0.6170374167093798, "grad_norm": 2.2753984928131104, "learning_rate": 3.378662391797942e-05, "loss": 0.9165, "step": 11286 }, { "epoch": 0.6170920895267384, "grad_norm": 2.791895866394043, "learning_rate": 3.377824902280532e-05, "loss": 0.8256, "step": 11287 }, { "epoch": 0.617146762344097, "grad_norm": 2.2491977214813232, "learning_rate": 3.376987463624991e-05, "loss": 1.0531, "step": 11288 }, { "epoch": 0.6172014351614556, "grad_norm": 3.828245162963867, "learning_rate": 3.376150075857577e-05, "loss": 1.1446, "step": 11289 }, { "epoch": 0.6172561079788143, "grad_norm": 3.7243337631225586, "learning_rate": 3.3753127390045466e-05, "loss": 1.2937, "step": 11290 }, { "epoch": 0.6173107807961729, "grad_norm": 2.7419087886810303, "learning_rate": 3.374475453092151e-05, "loss": 1.0001, "step": 11291 }, { "epoch": 0.6173654536135316, "grad_norm": 2.75825572013855, "learning_rate": 3.3736382181466463e-05, "loss": 1.1005, "step": 11292 }, { "epoch": 0.6174201264308902, "grad_norm": 3.344243049621582, "learning_rate": 3.372801034194282e-05, "loss": 1.1208, "step": 11293 }, { "epoch": 0.6174747992482488, "grad_norm": 2.8779921531677246, "learning_rate": 3.371963901261306e-05, "loss": 0.8542, "step": 11294 }, { "epoch": 0.6175294720656074, "grad_norm": 2.9931116104125977, "learning_rate": 3.371126819373967e-05, "loss": 1.1609, "step": 11295 }, { "epoch": 0.617584144882966, "grad_norm": 2.495422840118408, "learning_rate": 3.370289788558511e-05, "loss": 0.9073, "step": 11296 }, { "epoch": 0.6176388177003246, "grad_norm": 2.7097978591918945, "learning_rate": 3.3694528088411806e-05, "loss": 1.0165, "step": 11297 }, { "epoch": 0.6176934905176832, "grad_norm": 3.05073881149292, "learning_rate": 3.3686158802482214e-05, "loss": 0.9526, "step": 11298 }, { "epoch": 0.6177481633350419, "grad_norm": 3.2425827980041504, "learning_rate": 3.367779002805872e-05, "loss": 1.2404, "step": 11299 }, { "epoch": 0.6178028361524005, "grad_norm": 2.6523549556732178, "learning_rate": 3.366942176540374e-05, "loss": 1.1539, "step": 11300 }, { "epoch": 0.6178575089697591, "grad_norm": 2.516632556915283, "learning_rate": 3.366105401477963e-05, "loss": 1.13, "step": 11301 }, { "epoch": 0.6179121817871177, "grad_norm": 3.0118558406829834, "learning_rate": 3.365268677644877e-05, "loss": 1.0014, "step": 11302 }, { "epoch": 0.6179668546044763, "grad_norm": 2.3509440422058105, "learning_rate": 3.364432005067351e-05, "loss": 0.8971, "step": 11303 }, { "epoch": 0.6180215274218349, "grad_norm": 2.3789963722229004, "learning_rate": 3.363595383771618e-05, "loss": 0.9287, "step": 11304 }, { "epoch": 0.6180762002391936, "grad_norm": 2.6430776119232178, "learning_rate": 3.362758813783909e-05, "loss": 0.5608, "step": 11305 }, { "epoch": 0.6181308730565522, "grad_norm": 3.6746695041656494, "learning_rate": 3.361922295130454e-05, "loss": 0.8861, "step": 11306 }, { "epoch": 0.6181855458739108, "grad_norm": 3.294128656387329, "learning_rate": 3.3610858278374815e-05, "loss": 1.0251, "step": 11307 }, { "epoch": 0.6182402186912694, "grad_norm": 2.5436317920684814, "learning_rate": 3.360249411931218e-05, "loss": 1.1399, "step": 11308 }, { "epoch": 0.618294891508628, "grad_norm": 2.8124043941497803, "learning_rate": 3.359413047437889e-05, "loss": 1.1084, "step": 11309 }, { "epoch": 0.6183495643259866, "grad_norm": 2.171372413635254, "learning_rate": 3.358576734383717e-05, "loss": 0.8014, "step": 11310 }, { "epoch": 0.6184042371433452, "grad_norm": 2.8075289726257324, "learning_rate": 3.3577404727949235e-05, "loss": 1.1285, "step": 11311 }, { "epoch": 0.618458909960704, "grad_norm": 2.415982961654663, "learning_rate": 3.356904262697731e-05, "loss": 0.9827, "step": 11312 }, { "epoch": 0.6185135827780626, "grad_norm": 2.5774567127227783, "learning_rate": 3.3560681041183575e-05, "loss": 1.0935, "step": 11313 }, { "epoch": 0.6185682555954212, "grad_norm": 2.45941424369812, "learning_rate": 3.355231997083018e-05, "loss": 1.0157, "step": 11314 }, { "epoch": 0.6186229284127798, "grad_norm": 2.5065908432006836, "learning_rate": 3.354395941617929e-05, "loss": 0.9949, "step": 11315 }, { "epoch": 0.6186776012301384, "grad_norm": 2.8652594089508057, "learning_rate": 3.3535599377493056e-05, "loss": 1.1386, "step": 11316 }, { "epoch": 0.618732274047497, "grad_norm": 2.6417202949523926, "learning_rate": 3.3527239855033587e-05, "loss": 1.0718, "step": 11317 }, { "epoch": 0.6187869468648556, "grad_norm": 2.5943195819854736, "learning_rate": 3.351888084906298e-05, "loss": 0.8556, "step": 11318 }, { "epoch": 0.6188416196822143, "grad_norm": 2.3872153759002686, "learning_rate": 3.351052235984336e-05, "loss": 0.9595, "step": 11319 }, { "epoch": 0.6188962924995729, "grad_norm": 2.107696533203125, "learning_rate": 3.350216438763674e-05, "loss": 0.9241, "step": 11320 }, { "epoch": 0.6189509653169315, "grad_norm": 3.2596495151519775, "learning_rate": 3.349380693270524e-05, "loss": 1.3061, "step": 11321 }, { "epoch": 0.6190056381342901, "grad_norm": 2.314124822616577, "learning_rate": 3.348544999531086e-05, "loss": 0.9635, "step": 11322 }, { "epoch": 0.6190603109516487, "grad_norm": 2.421661376953125, "learning_rate": 3.347709357571564e-05, "loss": 0.9998, "step": 11323 }, { "epoch": 0.6191149837690073, "grad_norm": 2.149174928665161, "learning_rate": 3.3468737674181585e-05, "loss": 0.8414, "step": 11324 }, { "epoch": 0.6191696565863659, "grad_norm": 3.1862988471984863, "learning_rate": 3.3460382290970684e-05, "loss": 1.1512, "step": 11325 }, { "epoch": 0.6192243294037246, "grad_norm": 2.5030622482299805, "learning_rate": 3.3452027426344925e-05, "loss": 0.9392, "step": 11326 }, { "epoch": 0.6192790022210832, "grad_norm": 3.3690760135650635, "learning_rate": 3.344367308056625e-05, "loss": 1.2172, "step": 11327 }, { "epoch": 0.6193336750384418, "grad_norm": 2.9706943035125732, "learning_rate": 3.34353192538966e-05, "loss": 0.91, "step": 11328 }, { "epoch": 0.6193883478558004, "grad_norm": 2.323453187942505, "learning_rate": 3.3426965946597924e-05, "loss": 1.1813, "step": 11329 }, { "epoch": 0.619443020673159, "grad_norm": 2.7832627296447754, "learning_rate": 3.341861315893211e-05, "loss": 0.9806, "step": 11330 }, { "epoch": 0.6194976934905176, "grad_norm": 2.445439100265503, "learning_rate": 3.341026089116107e-05, "loss": 1.1075, "step": 11331 }, { "epoch": 0.6195523663078764, "grad_norm": 2.3039228916168213, "learning_rate": 3.340190914354668e-05, "loss": 0.9454, "step": 11332 }, { "epoch": 0.619607039125235, "grad_norm": 2.9809317588806152, "learning_rate": 3.339355791635079e-05, "loss": 1.0409, "step": 11333 }, { "epoch": 0.6196617119425936, "grad_norm": 3.5575907230377197, "learning_rate": 3.338520720983526e-05, "loss": 1.0885, "step": 11334 }, { "epoch": 0.6197163847599522, "grad_norm": 2.3180692195892334, "learning_rate": 3.337685702426191e-05, "loss": 0.81, "step": 11335 }, { "epoch": 0.6197710575773108, "grad_norm": 2.3967435359954834, "learning_rate": 3.3368507359892546e-05, "loss": 1.1037, "step": 11336 }, { "epoch": 0.6198257303946694, "grad_norm": 2.385634422302246, "learning_rate": 3.336015821698898e-05, "loss": 0.7063, "step": 11337 }, { "epoch": 0.619880403212028, "grad_norm": 2.471714496612549, "learning_rate": 3.3351809595812976e-05, "loss": 0.9898, "step": 11338 }, { "epoch": 0.6199350760293867, "grad_norm": 2.492748498916626, "learning_rate": 3.334346149662632e-05, "loss": 0.9937, "step": 11339 }, { "epoch": 0.6199897488467453, "grad_norm": 2.260105848312378, "learning_rate": 3.333511391969071e-05, "loss": 1.1316, "step": 11340 }, { "epoch": 0.6200444216641039, "grad_norm": 2.5667171478271484, "learning_rate": 3.3326766865267935e-05, "loss": 1.0529, "step": 11341 }, { "epoch": 0.6200990944814625, "grad_norm": 2.7341132164001465, "learning_rate": 3.3318420333619685e-05, "loss": 0.9665, "step": 11342 }, { "epoch": 0.6201537672988211, "grad_norm": 2.8245909214019775, "learning_rate": 3.331007432500767e-05, "loss": 1.0485, "step": 11343 }, { "epoch": 0.6202084401161797, "grad_norm": 3.038878917694092, "learning_rate": 3.3301728839693546e-05, "loss": 1.1819, "step": 11344 }, { "epoch": 0.6202631129335383, "grad_norm": 2.6756832599639893, "learning_rate": 3.3293383877939e-05, "loss": 1.1351, "step": 11345 }, { "epoch": 0.620317785750897, "grad_norm": 2.913323402404785, "learning_rate": 3.3285039440005675e-05, "loss": 1.0363, "step": 11346 }, { "epoch": 0.6203724585682556, "grad_norm": 2.2711851596832275, "learning_rate": 3.327669552615521e-05, "loss": 1.074, "step": 11347 }, { "epoch": 0.6204271313856142, "grad_norm": 2.3881750106811523, "learning_rate": 3.3268352136649207e-05, "loss": 1.0461, "step": 11348 }, { "epoch": 0.6204818042029728, "grad_norm": 1.7402220964431763, "learning_rate": 3.326000927174927e-05, "loss": 0.8294, "step": 11349 }, { "epoch": 0.6205364770203314, "grad_norm": 2.367844581604004, "learning_rate": 3.325166693171697e-05, "loss": 0.9916, "step": 11350 }, { "epoch": 0.62059114983769, "grad_norm": 2.605163812637329, "learning_rate": 3.32433251168139e-05, "loss": 1.0756, "step": 11351 }, { "epoch": 0.6206458226550486, "grad_norm": 2.3605611324310303, "learning_rate": 3.3234983827301616e-05, "loss": 1.0744, "step": 11352 }, { "epoch": 0.6207004954724074, "grad_norm": 2.2778847217559814, "learning_rate": 3.322664306344162e-05, "loss": 0.9708, "step": 11353 }, { "epoch": 0.620755168289766, "grad_norm": 2.5383694171905518, "learning_rate": 3.321830282549545e-05, "loss": 1.1743, "step": 11354 }, { "epoch": 0.6208098411071246, "grad_norm": 2.404040813446045, "learning_rate": 3.3209963113724596e-05, "loss": 1.0456, "step": 11355 }, { "epoch": 0.6208645139244832, "grad_norm": 2.601590156555176, "learning_rate": 3.3201623928390543e-05, "loss": 1.0405, "step": 11356 }, { "epoch": 0.6209191867418418, "grad_norm": 2.341108798980713, "learning_rate": 3.319328526975478e-05, "loss": 0.9667, "step": 11357 }, { "epoch": 0.6209738595592004, "grad_norm": 2.6585779190063477, "learning_rate": 3.318494713807873e-05, "loss": 1.0168, "step": 11358 }, { "epoch": 0.6210285323765591, "grad_norm": 2.3479552268981934, "learning_rate": 3.317660953362384e-05, "loss": 0.9371, "step": 11359 }, { "epoch": 0.6210832051939177, "grad_norm": 5.657269477844238, "learning_rate": 3.3168272456651504e-05, "loss": 1.2194, "step": 11360 }, { "epoch": 0.6211378780112763, "grad_norm": 2.362636089324951, "learning_rate": 3.315993590742317e-05, "loss": 1.0137, "step": 11361 }, { "epoch": 0.6211925508286349, "grad_norm": 2.739064931869507, "learning_rate": 3.31515998862002e-05, "loss": 1.126, "step": 11362 }, { "epoch": 0.6212472236459935, "grad_norm": 4.156414031982422, "learning_rate": 3.3143264393243956e-05, "loss": 1.0233, "step": 11363 }, { "epoch": 0.6213018964633521, "grad_norm": 2.3241310119628906, "learning_rate": 3.313492942881581e-05, "loss": 0.9113, "step": 11364 }, { "epoch": 0.6213565692807107, "grad_norm": 2.391261577606201, "learning_rate": 3.312659499317707e-05, "loss": 1.007, "step": 11365 }, { "epoch": 0.6214112420980694, "grad_norm": 2.177250385284424, "learning_rate": 3.311826108658907e-05, "loss": 0.9704, "step": 11366 }, { "epoch": 0.621465914915428, "grad_norm": 3.9051601886749268, "learning_rate": 3.310992770931313e-05, "loss": 1.0117, "step": 11367 }, { "epoch": 0.6215205877327866, "grad_norm": 2.3022377490997314, "learning_rate": 3.31015948616105e-05, "loss": 1.0188, "step": 11368 }, { "epoch": 0.6215752605501452, "grad_norm": 3.307324171066284, "learning_rate": 3.309326254374244e-05, "loss": 0.8839, "step": 11369 }, { "epoch": 0.6216299333675038, "grad_norm": 2.4037909507751465, "learning_rate": 3.3084930755970266e-05, "loss": 1.1134, "step": 11370 }, { "epoch": 0.6216846061848624, "grad_norm": 3.1529581546783447, "learning_rate": 3.307659949855517e-05, "loss": 1.0056, "step": 11371 }, { "epoch": 0.621739279002221, "grad_norm": 4.378432273864746, "learning_rate": 3.306826877175837e-05, "loss": 1.0875, "step": 11372 }, { "epoch": 0.6217939518195797, "grad_norm": 2.9124269485473633, "learning_rate": 3.305993857584109e-05, "loss": 1.0585, "step": 11373 }, { "epoch": 0.6218486246369384, "grad_norm": 2.633430004119873, "learning_rate": 3.305160891106449e-05, "loss": 1.0569, "step": 11374 }, { "epoch": 0.621903297454297, "grad_norm": 2.114931583404541, "learning_rate": 3.304327977768975e-05, "loss": 0.9271, "step": 11375 }, { "epoch": 0.6219579702716556, "grad_norm": 2.953267812728882, "learning_rate": 3.303495117597804e-05, "loss": 1.1413, "step": 11376 }, { "epoch": 0.6220126430890142, "grad_norm": 2.6348929405212402, "learning_rate": 3.3026623106190463e-05, "loss": 1.051, "step": 11377 }, { "epoch": 0.6220673159063728, "grad_norm": 3.038480043411255, "learning_rate": 3.301829556858817e-05, "loss": 1.0592, "step": 11378 }, { "epoch": 0.6221219887237314, "grad_norm": 2.1831064224243164, "learning_rate": 3.300996856343221e-05, "loss": 0.9506, "step": 11379 }, { "epoch": 0.6221766615410901, "grad_norm": 3.912869691848755, "learning_rate": 3.300164209098374e-05, "loss": 0.9118, "step": 11380 }, { "epoch": 0.6222313343584487, "grad_norm": 2.8514721393585205, "learning_rate": 3.2993316151503794e-05, "loss": 1.1182, "step": 11381 }, { "epoch": 0.6222860071758073, "grad_norm": 3.4168503284454346, "learning_rate": 3.298499074525343e-05, "loss": 0.9841, "step": 11382 }, { "epoch": 0.6223406799931659, "grad_norm": 4.777209758758545, "learning_rate": 3.2976665872493683e-05, "loss": 1.222, "step": 11383 }, { "epoch": 0.6223953528105245, "grad_norm": 2.4362409114837646, "learning_rate": 3.296834153348557e-05, "loss": 1.2069, "step": 11384 }, { "epoch": 0.6224500256278831, "grad_norm": 3.034712314605713, "learning_rate": 3.2960017728490086e-05, "loss": 1.1692, "step": 11385 }, { "epoch": 0.6225046984452418, "grad_norm": 3.755056619644165, "learning_rate": 3.295169445776823e-05, "loss": 1.1213, "step": 11386 }, { "epoch": 0.6225593712626004, "grad_norm": 2.6196632385253906, "learning_rate": 3.2943371721580965e-05, "loss": 1.0461, "step": 11387 }, { "epoch": 0.622614044079959, "grad_norm": 2.4276180267333984, "learning_rate": 3.293504952018924e-05, "loss": 0.9684, "step": 11388 }, { "epoch": 0.6226687168973176, "grad_norm": 2.3818814754486084, "learning_rate": 3.292672785385398e-05, "loss": 1.0207, "step": 11389 }, { "epoch": 0.6227233897146762, "grad_norm": 2.250683069229126, "learning_rate": 3.2918406722836134e-05, "loss": 1.0931, "step": 11390 }, { "epoch": 0.6227780625320348, "grad_norm": 2.2238831520080566, "learning_rate": 3.291008612739659e-05, "loss": 0.9481, "step": 11391 }, { "epoch": 0.6228327353493934, "grad_norm": 2.9347751140594482, "learning_rate": 3.290176606779622e-05, "loss": 1.1974, "step": 11392 }, { "epoch": 0.6228874081667521, "grad_norm": 4.207540035247803, "learning_rate": 3.289344654429591e-05, "loss": 0.9162, "step": 11393 }, { "epoch": 0.6229420809841107, "grad_norm": 2.7264797687530518, "learning_rate": 3.2885127557156496e-05, "loss": 1.1222, "step": 11394 }, { "epoch": 0.6229967538014693, "grad_norm": 2.392897605895996, "learning_rate": 3.287680910663883e-05, "loss": 1.0514, "step": 11395 }, { "epoch": 0.623051426618828, "grad_norm": 3.174159288406372, "learning_rate": 3.286849119300371e-05, "loss": 1.084, "step": 11396 }, { "epoch": 0.6231060994361866, "grad_norm": 3.188493490219116, "learning_rate": 3.2860173816511945e-05, "loss": 1.0594, "step": 11397 }, { "epoch": 0.6231607722535452, "grad_norm": 2.918163776397705, "learning_rate": 3.285185697742432e-05, "loss": 1.1515, "step": 11398 }, { "epoch": 0.6232154450709038, "grad_norm": 2.4338998794555664, "learning_rate": 3.284354067600161e-05, "loss": 0.9962, "step": 11399 }, { "epoch": 0.6232701178882625, "grad_norm": 2.456003189086914, "learning_rate": 3.283522491250455e-05, "loss": 0.8369, "step": 11400 }, { "epoch": 0.6233247907056211, "grad_norm": 2.562519073486328, "learning_rate": 3.282690968719388e-05, "loss": 1.0375, "step": 11401 }, { "epoch": 0.6233794635229797, "grad_norm": 2.8784995079040527, "learning_rate": 3.281859500033031e-05, "loss": 1.049, "step": 11402 }, { "epoch": 0.6234341363403383, "grad_norm": 2.5041768550872803, "learning_rate": 3.281028085217456e-05, "loss": 1.0853, "step": 11403 }, { "epoch": 0.6234888091576969, "grad_norm": 3.0707638263702393, "learning_rate": 3.2801967242987296e-05, "loss": 0.9297, "step": 11404 }, { "epoch": 0.6235434819750555, "grad_norm": 3.059764862060547, "learning_rate": 3.279365417302919e-05, "loss": 1.0672, "step": 11405 }, { "epoch": 0.6235981547924141, "grad_norm": 2.958948850631714, "learning_rate": 3.278534164256089e-05, "loss": 1.1178, "step": 11406 }, { "epoch": 0.6236528276097728, "grad_norm": 2.2460885047912598, "learning_rate": 3.277702965184303e-05, "loss": 0.9031, "step": 11407 }, { "epoch": 0.6237075004271314, "grad_norm": 2.2743544578552246, "learning_rate": 3.276871820113622e-05, "loss": 1.0497, "step": 11408 }, { "epoch": 0.62376217324449, "grad_norm": 3.1066627502441406, "learning_rate": 3.276040729070105e-05, "loss": 1.1148, "step": 11409 }, { "epoch": 0.6238168460618486, "grad_norm": 2.567964792251587, "learning_rate": 3.2752096920798116e-05, "loss": 1.0387, "step": 11410 }, { "epoch": 0.6238715188792072, "grad_norm": 3.495002508163452, "learning_rate": 3.2743787091687984e-05, "loss": 0.8904, "step": 11411 }, { "epoch": 0.6239261916965658, "grad_norm": 2.9943528175354004, "learning_rate": 3.273547780363119e-05, "loss": 0.9431, "step": 11412 }, { "epoch": 0.6239808645139245, "grad_norm": 2.8389766216278076, "learning_rate": 3.2727169056888274e-05, "loss": 1.1573, "step": 11413 }, { "epoch": 0.6240355373312831, "grad_norm": 2.7698349952697754, "learning_rate": 3.271886085171974e-05, "loss": 1.1357, "step": 11414 }, { "epoch": 0.6240902101486417, "grad_norm": 2.8151795864105225, "learning_rate": 3.271055318838609e-05, "loss": 1.1422, "step": 11415 }, { "epoch": 0.6241448829660003, "grad_norm": 2.4221644401550293, "learning_rate": 3.2702246067147804e-05, "loss": 0.8998, "step": 11416 }, { "epoch": 0.624199555783359, "grad_norm": 2.7894134521484375, "learning_rate": 3.269393948826535e-05, "loss": 0.9352, "step": 11417 }, { "epoch": 0.6242542286007176, "grad_norm": 2.3331105709075928, "learning_rate": 3.268563345199915e-05, "loss": 1.069, "step": 11418 }, { "epoch": 0.6243089014180762, "grad_norm": 2.346484899520874, "learning_rate": 3.2677327958609663e-05, "loss": 0.9071, "step": 11419 }, { "epoch": 0.6243635742354349, "grad_norm": 2.61273193359375, "learning_rate": 3.2669023008357286e-05, "loss": 0.9999, "step": 11420 }, { "epoch": 0.6244182470527935, "grad_norm": 5.192748546600342, "learning_rate": 3.2660718601502416e-05, "loss": 1.2729, "step": 11421 }, { "epoch": 0.6244729198701521, "grad_norm": 3.319197654724121, "learning_rate": 3.2652414738305424e-05, "loss": 1.0628, "step": 11422 }, { "epoch": 0.6245275926875107, "grad_norm": 3.5482335090637207, "learning_rate": 3.264411141902668e-05, "loss": 0.8532, "step": 11423 }, { "epoch": 0.6245822655048693, "grad_norm": 2.6651065349578857, "learning_rate": 3.2635808643926514e-05, "loss": 1.1447, "step": 11424 }, { "epoch": 0.6246369383222279, "grad_norm": 2.372817277908325, "learning_rate": 3.262750641326527e-05, "loss": 1.0905, "step": 11425 }, { "epoch": 0.6246916111395865, "grad_norm": 2.484815835952759, "learning_rate": 3.2619204727303246e-05, "loss": 0.9301, "step": 11426 }, { "epoch": 0.6247462839569452, "grad_norm": 2.8229784965515137, "learning_rate": 3.261090358630073e-05, "loss": 1.0401, "step": 11427 }, { "epoch": 0.6248009567743038, "grad_norm": 2.9441330432891846, "learning_rate": 3.260260299051798e-05, "loss": 1.0603, "step": 11428 }, { "epoch": 0.6248556295916624, "grad_norm": 3.042646646499634, "learning_rate": 3.2594302940215305e-05, "loss": 0.9015, "step": 11429 }, { "epoch": 0.624910302409021, "grad_norm": 2.0171725749969482, "learning_rate": 3.2586003435652915e-05, "loss": 0.9897, "step": 11430 }, { "epoch": 0.6249649752263796, "grad_norm": 3.6418635845184326, "learning_rate": 3.257770447709103e-05, "loss": 0.9519, "step": 11431 }, { "epoch": 0.6250196480437382, "grad_norm": 2.389961004257202, "learning_rate": 3.2569406064789865e-05, "loss": 0.9076, "step": 11432 }, { "epoch": 0.6250743208610968, "grad_norm": 2.5530436038970947, "learning_rate": 3.25611081990096e-05, "loss": 0.9332, "step": 11433 }, { "epoch": 0.6251289936784555, "grad_norm": 3.114403486251831, "learning_rate": 3.255281088001043e-05, "loss": 0.8816, "step": 11434 }, { "epoch": 0.6251836664958141, "grad_norm": 2.7705485820770264, "learning_rate": 3.254451410805248e-05, "loss": 1.1888, "step": 11435 }, { "epoch": 0.6252383393131727, "grad_norm": 2.136159658432007, "learning_rate": 3.253621788339591e-05, "loss": 0.9046, "step": 11436 }, { "epoch": 0.6252930121305313, "grad_norm": 3.067265033721924, "learning_rate": 3.252792220630083e-05, "loss": 1.1149, "step": 11437 }, { "epoch": 0.62534768494789, "grad_norm": 2.589555025100708, "learning_rate": 3.2519627077027326e-05, "loss": 1.0403, "step": 11438 }, { "epoch": 0.6254023577652486, "grad_norm": 2.601050615310669, "learning_rate": 3.2511332495835526e-05, "loss": 0.9939, "step": 11439 }, { "epoch": 0.6254570305826073, "grad_norm": 2.3656086921691895, "learning_rate": 3.250303846298547e-05, "loss": 1.1878, "step": 11440 }, { "epoch": 0.6255117033999659, "grad_norm": 2.2266833782196045, "learning_rate": 3.249474497873723e-05, "loss": 1.0333, "step": 11441 }, { "epoch": 0.6255663762173245, "grad_norm": 2.8779819011688232, "learning_rate": 3.2486452043350824e-05, "loss": 0.8545, "step": 11442 }, { "epoch": 0.6256210490346831, "grad_norm": 2.418339490890503, "learning_rate": 3.2478159657086274e-05, "loss": 0.9701, "step": 11443 }, { "epoch": 0.6256757218520417, "grad_norm": 2.7221426963806152, "learning_rate": 3.246986782020358e-05, "loss": 1.0047, "step": 11444 }, { "epoch": 0.6257303946694003, "grad_norm": 1.9123128652572632, "learning_rate": 3.2461576532962734e-05, "loss": 0.9248, "step": 11445 }, { "epoch": 0.6257850674867589, "grad_norm": 2.496032476425171, "learning_rate": 3.245328579562369e-05, "loss": 1.0432, "step": 11446 }, { "epoch": 0.6258397403041176, "grad_norm": 2.8881945610046387, "learning_rate": 3.24449956084464e-05, "loss": 1.0512, "step": 11447 }, { "epoch": 0.6258944131214762, "grad_norm": 3.6401004791259766, "learning_rate": 3.2436705971690774e-05, "loss": 0.959, "step": 11448 }, { "epoch": 0.6259490859388348, "grad_norm": 1.905701994895935, "learning_rate": 3.2428416885616775e-05, "loss": 0.9388, "step": 11449 }, { "epoch": 0.6260037587561934, "grad_norm": 2.505368947982788, "learning_rate": 3.242012835048427e-05, "loss": 1.0931, "step": 11450 }, { "epoch": 0.626058431573552, "grad_norm": 2.432368516921997, "learning_rate": 3.2411840366553145e-05, "loss": 1.0536, "step": 11451 }, { "epoch": 0.6261131043909106, "grad_norm": 2.32846999168396, "learning_rate": 3.240355293408326e-05, "loss": 0.8086, "step": 11452 }, { "epoch": 0.6261677772082692, "grad_norm": 1.9987629652023315, "learning_rate": 3.239526605333446e-05, "loss": 0.8912, "step": 11453 }, { "epoch": 0.6262224500256279, "grad_norm": 2.3389201164245605, "learning_rate": 3.238697972456657e-05, "loss": 0.8545, "step": 11454 }, { "epoch": 0.6262771228429865, "grad_norm": 3.3599064350128174, "learning_rate": 3.237869394803941e-05, "loss": 1.2638, "step": 11455 }, { "epoch": 0.6263317956603451, "grad_norm": 2.590883255004883, "learning_rate": 3.237040872401276e-05, "loss": 1.1078, "step": 11456 }, { "epoch": 0.6263864684777037, "grad_norm": 2.948392868041992, "learning_rate": 3.236212405274641e-05, "loss": 0.965, "step": 11457 }, { "epoch": 0.6264411412950623, "grad_norm": 2.5403857231140137, "learning_rate": 3.2353839934500085e-05, "loss": 0.851, "step": 11458 }, { "epoch": 0.626495814112421, "grad_norm": 2.9064621925354004, "learning_rate": 3.234555636953358e-05, "loss": 0.8839, "step": 11459 }, { "epoch": 0.6265504869297795, "grad_norm": 2.4437572956085205, "learning_rate": 3.2337273358106576e-05, "loss": 1.0554, "step": 11460 }, { "epoch": 0.6266051597471383, "grad_norm": 2.1600449085235596, "learning_rate": 3.23289909004788e-05, "loss": 0.8656, "step": 11461 }, { "epoch": 0.6266598325644969, "grad_norm": 2.5090548992156982, "learning_rate": 3.232070899690995e-05, "loss": 0.9378, "step": 11462 }, { "epoch": 0.6267145053818555, "grad_norm": 3.1309263706207275, "learning_rate": 3.2312427647659674e-05, "loss": 1.0332, "step": 11463 }, { "epoch": 0.6267691781992141, "grad_norm": 3.9877712726593018, "learning_rate": 3.230414685298764e-05, "loss": 1.0888, "step": 11464 }, { "epoch": 0.6268238510165727, "grad_norm": 3.096964120864868, "learning_rate": 3.229586661315348e-05, "loss": 0.9718, "step": 11465 }, { "epoch": 0.6268785238339313, "grad_norm": 2.9491336345672607, "learning_rate": 3.2287586928416815e-05, "loss": 1.003, "step": 11466 }, { "epoch": 0.6269331966512899, "grad_norm": 2.408464193344116, "learning_rate": 3.227930779903724e-05, "loss": 0.943, "step": 11467 }, { "epoch": 0.6269878694686486, "grad_norm": 3.8293204307556152, "learning_rate": 3.227102922527434e-05, "loss": 1.1832, "step": 11468 }, { "epoch": 0.6270425422860072, "grad_norm": 2.3048393726348877, "learning_rate": 3.22627512073877e-05, "loss": 0.864, "step": 11469 }, { "epoch": 0.6270972151033658, "grad_norm": 3.1555473804473877, "learning_rate": 3.2254473745636856e-05, "loss": 1.0164, "step": 11470 }, { "epoch": 0.6271518879207244, "grad_norm": 2.419908285140991, "learning_rate": 3.224619684028135e-05, "loss": 0.9342, "step": 11471 }, { "epoch": 0.627206560738083, "grad_norm": 2.3169734477996826, "learning_rate": 3.2237920491580694e-05, "loss": 1.0676, "step": 11472 }, { "epoch": 0.6272612335554416, "grad_norm": 2.4342427253723145, "learning_rate": 3.222964469979438e-05, "loss": 1.0231, "step": 11473 }, { "epoch": 0.6273159063728003, "grad_norm": 2.672186851501465, "learning_rate": 3.222136946518188e-05, "loss": 1.1407, "step": 11474 }, { "epoch": 0.6273705791901589, "grad_norm": 2.342735767364502, "learning_rate": 3.221309478800269e-05, "loss": 1.0534, "step": 11475 }, { "epoch": 0.6274252520075175, "grad_norm": 2.7157185077667236, "learning_rate": 3.220482066851621e-05, "loss": 0.9951, "step": 11476 }, { "epoch": 0.6274799248248761, "grad_norm": 2.6366944313049316, "learning_rate": 3.219654710698188e-05, "loss": 1.1176, "step": 11477 }, { "epoch": 0.6275345976422347, "grad_norm": 2.21175479888916, "learning_rate": 3.218827410365915e-05, "loss": 0.9243, "step": 11478 }, { "epoch": 0.6275892704595933, "grad_norm": 3.3731045722961426, "learning_rate": 3.218000165880737e-05, "loss": 1.2526, "step": 11479 }, { "epoch": 0.6276439432769519, "grad_norm": 2.332334518432617, "learning_rate": 3.2171729772685926e-05, "loss": 0.9912, "step": 11480 }, { "epoch": 0.6276986160943107, "grad_norm": 2.6703476905822754, "learning_rate": 3.216345844555419e-05, "loss": 1.1006, "step": 11481 }, { "epoch": 0.6277532889116693, "grad_norm": 2.944490671157837, "learning_rate": 3.215518767767148e-05, "loss": 1.0079, "step": 11482 }, { "epoch": 0.6278079617290279, "grad_norm": 2.490513563156128, "learning_rate": 3.2146917469297136e-05, "loss": 0.9109, "step": 11483 }, { "epoch": 0.6278626345463865, "grad_norm": 2.9624338150024414, "learning_rate": 3.2138647820690446e-05, "loss": 1.0164, "step": 11484 }, { "epoch": 0.6279173073637451, "grad_norm": 2.378687858581543, "learning_rate": 3.2130378732110715e-05, "loss": 0.9675, "step": 11485 }, { "epoch": 0.6279719801811037, "grad_norm": 1.9000221490859985, "learning_rate": 3.2122110203817204e-05, "loss": 0.9929, "step": 11486 }, { "epoch": 0.6280266529984623, "grad_norm": 2.779033660888672, "learning_rate": 3.211384223606916e-05, "loss": 1.0482, "step": 11487 }, { "epoch": 0.628081325815821, "grad_norm": 2.619210958480835, "learning_rate": 3.210557482912583e-05, "loss": 1.059, "step": 11488 }, { "epoch": 0.6281359986331796, "grad_norm": 2.764002799987793, "learning_rate": 3.2097307983246424e-05, "loss": 1.0658, "step": 11489 }, { "epoch": 0.6281906714505382, "grad_norm": 2.268847942352295, "learning_rate": 3.2089041698690146e-05, "loss": 1.0399, "step": 11490 }, { "epoch": 0.6282453442678968, "grad_norm": 2.6690657138824463, "learning_rate": 3.208077597571618e-05, "loss": 0.9779, "step": 11491 }, { "epoch": 0.6283000170852554, "grad_norm": 2.446913957595825, "learning_rate": 3.207251081458369e-05, "loss": 1.0471, "step": 11492 }, { "epoch": 0.628354689902614, "grad_norm": 2.0621016025543213, "learning_rate": 3.206424621555181e-05, "loss": 0.9755, "step": 11493 }, { "epoch": 0.6284093627199726, "grad_norm": 3.5137360095977783, "learning_rate": 3.205598217887969e-05, "loss": 1.1584, "step": 11494 }, { "epoch": 0.6284640355373313, "grad_norm": 2.565302848815918, "learning_rate": 3.204771870482641e-05, "loss": 1.1573, "step": 11495 }, { "epoch": 0.6285187083546899, "grad_norm": 2.5675582885742188, "learning_rate": 3.2039455793651095e-05, "loss": 1.1228, "step": 11496 }, { "epoch": 0.6285733811720485, "grad_norm": 2.6842939853668213, "learning_rate": 3.2031193445612805e-05, "loss": 0.9237, "step": 11497 }, { "epoch": 0.6286280539894071, "grad_norm": 2.1335248947143555, "learning_rate": 3.202293166097061e-05, "loss": 0.8837, "step": 11498 }, { "epoch": 0.6286827268067657, "grad_norm": 2.844848394393921, "learning_rate": 3.201467043998354e-05, "loss": 1.1115, "step": 11499 }, { "epoch": 0.6287373996241243, "grad_norm": 2.327498197555542, "learning_rate": 3.200640978291063e-05, "loss": 1.0825, "step": 11500 }, { "epoch": 0.628792072441483, "grad_norm": 2.1203672885894775, "learning_rate": 3.199814969001088e-05, "loss": 0.8494, "step": 11501 }, { "epoch": 0.6288467452588417, "grad_norm": 2.390345573425293, "learning_rate": 3.198989016154325e-05, "loss": 1.1512, "step": 11502 }, { "epoch": 0.6289014180762003, "grad_norm": 2.4789462089538574, "learning_rate": 3.198163119776677e-05, "loss": 1.1026, "step": 11503 }, { "epoch": 0.6289560908935589, "grad_norm": 2.385344982147217, "learning_rate": 3.1973372798940346e-05, "loss": 0.9853, "step": 11504 }, { "epoch": 0.6290107637109175, "grad_norm": 2.0906784534454346, "learning_rate": 3.196511496532293e-05, "loss": 1.0863, "step": 11505 }, { "epoch": 0.6290654365282761, "grad_norm": 2.5873913764953613, "learning_rate": 3.195685769717344e-05, "loss": 0.8803, "step": 11506 }, { "epoch": 0.6291201093456347, "grad_norm": 2.369168281555176, "learning_rate": 3.194860099475076e-05, "loss": 0.8216, "step": 11507 }, { "epoch": 0.6291747821629934, "grad_norm": 2.597766637802124, "learning_rate": 3.1940344858313776e-05, "loss": 1.1148, "step": 11508 }, { "epoch": 0.629229454980352, "grad_norm": 2.4616544246673584, "learning_rate": 3.193208928812137e-05, "loss": 0.9766, "step": 11509 }, { "epoch": 0.6292841277977106, "grad_norm": 2.1278982162475586, "learning_rate": 3.192383428443238e-05, "loss": 1.1469, "step": 11510 }, { "epoch": 0.6293388006150692, "grad_norm": 2.8980448246002197, "learning_rate": 3.1915579847505625e-05, "loss": 1.026, "step": 11511 }, { "epoch": 0.6293934734324278, "grad_norm": 2.1987905502319336, "learning_rate": 3.1907325977599925e-05, "loss": 0.9002, "step": 11512 }, { "epoch": 0.6294481462497864, "grad_norm": 3.1131811141967773, "learning_rate": 3.1899072674974065e-05, "loss": 1.0782, "step": 11513 }, { "epoch": 0.629502819067145, "grad_norm": 2.1749625205993652, "learning_rate": 3.189081993988683e-05, "loss": 0.8287, "step": 11514 }, { "epoch": 0.6295574918845037, "grad_norm": 3.5057711601257324, "learning_rate": 3.188256777259695e-05, "loss": 1.2048, "step": 11515 }, { "epoch": 0.6296121647018623, "grad_norm": 2.409409284591675, "learning_rate": 3.187431617336321e-05, "loss": 0.7395, "step": 11516 }, { "epoch": 0.6296668375192209, "grad_norm": 2.9476070404052734, "learning_rate": 3.1866065142444285e-05, "loss": 1.1064, "step": 11517 }, { "epoch": 0.6297215103365795, "grad_norm": 2.2569611072540283, "learning_rate": 3.185781468009892e-05, "loss": 0.9363, "step": 11518 }, { "epoch": 0.6297761831539381, "grad_norm": 2.4444704055786133, "learning_rate": 3.184956478658577e-05, "loss": 0.9558, "step": 11519 }, { "epoch": 0.6298308559712967, "grad_norm": 2.9520232677459717, "learning_rate": 3.184131546216353e-05, "loss": 1.0723, "step": 11520 }, { "epoch": 0.6298855287886553, "grad_norm": 2.8052899837493896, "learning_rate": 3.183306670709083e-05, "loss": 1.1137, "step": 11521 }, { "epoch": 0.629940201606014, "grad_norm": 2.327049970626831, "learning_rate": 3.182481852162631e-05, "loss": 0.9946, "step": 11522 }, { "epoch": 0.6299948744233727, "grad_norm": 2.7260665893554688, "learning_rate": 3.1816570906028576e-05, "loss": 1.0802, "step": 11523 }, { "epoch": 0.6300495472407313, "grad_norm": 2.8378567695617676, "learning_rate": 3.1808323860556236e-05, "loss": 1.1899, "step": 11524 }, { "epoch": 0.6301042200580899, "grad_norm": 2.13187837600708, "learning_rate": 3.1800077385467867e-05, "loss": 0.7897, "step": 11525 }, { "epoch": 0.6301588928754485, "grad_norm": 2.161470651626587, "learning_rate": 3.1791831481021995e-05, "loss": 0.9626, "step": 11526 }, { "epoch": 0.6302135656928071, "grad_norm": 3.3061904907226562, "learning_rate": 3.178358614747723e-05, "loss": 1.2138, "step": 11527 }, { "epoch": 0.6302682385101658, "grad_norm": 2.4057955741882324, "learning_rate": 3.177534138509205e-05, "loss": 0.6952, "step": 11528 }, { "epoch": 0.6303229113275244, "grad_norm": 3.5979018211364746, "learning_rate": 3.1767097194124984e-05, "loss": 0.8974, "step": 11529 }, { "epoch": 0.630377584144883, "grad_norm": 4.176516532897949, "learning_rate": 3.175885357483451e-05, "loss": 1.1346, "step": 11530 }, { "epoch": 0.6304322569622416, "grad_norm": 3.2530276775360107, "learning_rate": 3.1750610527479097e-05, "loss": 1.0777, "step": 11531 }, { "epoch": 0.6304869297796002, "grad_norm": 2.358572006225586, "learning_rate": 3.174236805231721e-05, "loss": 0.9894, "step": 11532 }, { "epoch": 0.6305416025969588, "grad_norm": 3.201853036880493, "learning_rate": 3.173412614960727e-05, "loss": 1.1545, "step": 11533 }, { "epoch": 0.6305962754143174, "grad_norm": 2.719782590866089, "learning_rate": 3.1725884819607704e-05, "loss": 1.1054, "step": 11534 }, { "epoch": 0.6306509482316761, "grad_norm": 2.2510457038879395, "learning_rate": 3.1717644062576913e-05, "loss": 0.9553, "step": 11535 }, { "epoch": 0.6307056210490347, "grad_norm": 2.5224621295928955, "learning_rate": 3.170940387877325e-05, "loss": 0.7343, "step": 11536 }, { "epoch": 0.6307602938663933, "grad_norm": 2.5143582820892334, "learning_rate": 3.170116426845513e-05, "loss": 0.884, "step": 11537 }, { "epoch": 0.6308149666837519, "grad_norm": 2.9167120456695557, "learning_rate": 3.1692925231880864e-05, "loss": 0.9072, "step": 11538 }, { "epoch": 0.6308696395011105, "grad_norm": 2.877408266067505, "learning_rate": 3.168468676930879e-05, "loss": 1.024, "step": 11539 }, { "epoch": 0.6309243123184691, "grad_norm": 2.6899828910827637, "learning_rate": 3.1676448880997225e-05, "loss": 1.0541, "step": 11540 }, { "epoch": 0.6309789851358277, "grad_norm": 2.408245801925659, "learning_rate": 3.1668211567204445e-05, "loss": 1.0571, "step": 11541 }, { "epoch": 0.6310336579531864, "grad_norm": 4.051649570465088, "learning_rate": 3.1659974828188735e-05, "loss": 1.0645, "step": 11542 }, { "epoch": 0.631088330770545, "grad_norm": 2.7013444900512695, "learning_rate": 3.1651738664208344e-05, "loss": 0.9483, "step": 11543 }, { "epoch": 0.6311430035879037, "grad_norm": 2.928206443786621, "learning_rate": 3.164350307552151e-05, "loss": 1.189, "step": 11544 }, { "epoch": 0.6311976764052623, "grad_norm": 5.602543830871582, "learning_rate": 3.163526806238646e-05, "loss": 1.2086, "step": 11545 }, { "epoch": 0.6312523492226209, "grad_norm": 2.611600160598755, "learning_rate": 3.162703362506136e-05, "loss": 1.0657, "step": 11546 }, { "epoch": 0.6313070220399795, "grad_norm": 2.332736015319824, "learning_rate": 3.161879976380445e-05, "loss": 0.9194, "step": 11547 }, { "epoch": 0.6313616948573381, "grad_norm": 2.789717197418213, "learning_rate": 3.161056647887387e-05, "loss": 1.062, "step": 11548 }, { "epoch": 0.6314163676746968, "grad_norm": 2.2994518280029297, "learning_rate": 3.160233377052777e-05, "loss": 0.9332, "step": 11549 }, { "epoch": 0.6314710404920554, "grad_norm": 2.651026964187622, "learning_rate": 3.159410163902427e-05, "loss": 0.9769, "step": 11550 }, { "epoch": 0.631525713309414, "grad_norm": 2.649014711380005, "learning_rate": 3.158587008462149e-05, "loss": 1.1661, "step": 11551 }, { "epoch": 0.6315803861267726, "grad_norm": 2.643476963043213, "learning_rate": 3.1577639107577515e-05, "loss": 0.9121, "step": 11552 }, { "epoch": 0.6316350589441312, "grad_norm": 2.6601779460906982, "learning_rate": 3.156940870815043e-05, "loss": 1.1593, "step": 11553 }, { "epoch": 0.6316897317614898, "grad_norm": 2.130854845046997, "learning_rate": 3.156117888659829e-05, "loss": 0.8051, "step": 11554 }, { "epoch": 0.6317444045788485, "grad_norm": 2.353330135345459, "learning_rate": 3.155294964317912e-05, "loss": 1.0791, "step": 11555 }, { "epoch": 0.6317990773962071, "grad_norm": 2.9736738204956055, "learning_rate": 3.154472097815094e-05, "loss": 1.0473, "step": 11556 }, { "epoch": 0.6318537502135657, "grad_norm": 2.9076435565948486, "learning_rate": 3.153649289177179e-05, "loss": 0.9774, "step": 11557 }, { "epoch": 0.6319084230309243, "grad_norm": 2.5113558769226074, "learning_rate": 3.152826538429961e-05, "loss": 1.2151, "step": 11558 }, { "epoch": 0.6319630958482829, "grad_norm": 3.434474468231201, "learning_rate": 3.15200384559924e-05, "loss": 1.0364, "step": 11559 }, { "epoch": 0.6320177686656415, "grad_norm": 2.68308424949646, "learning_rate": 3.151181210710809e-05, "loss": 1.1926, "step": 11560 }, { "epoch": 0.6320724414830001, "grad_norm": 2.4855904579162598, "learning_rate": 3.1503586337904614e-05, "loss": 0.8352, "step": 11561 }, { "epoch": 0.6321271143003588, "grad_norm": 2.2890052795410156, "learning_rate": 3.149536114863988e-05, "loss": 0.9299, "step": 11562 }, { "epoch": 0.6321817871177174, "grad_norm": 2.9738380908966064, "learning_rate": 3.148713653957178e-05, "loss": 0.9987, "step": 11563 }, { "epoch": 0.632236459935076, "grad_norm": 2.573559284210205, "learning_rate": 3.14789125109582e-05, "loss": 0.9568, "step": 11564 }, { "epoch": 0.6322911327524346, "grad_norm": 2.0578677654266357, "learning_rate": 3.147068906305699e-05, "loss": 1.017, "step": 11565 }, { "epoch": 0.6323458055697933, "grad_norm": 2.163954973220825, "learning_rate": 3.146246619612596e-05, "loss": 0.8883, "step": 11566 }, { "epoch": 0.6324004783871519, "grad_norm": 3.3020920753479004, "learning_rate": 3.1454243910422994e-05, "loss": 0.9787, "step": 11567 }, { "epoch": 0.6324551512045105, "grad_norm": 2.9957242012023926, "learning_rate": 3.144602220620585e-05, "loss": 0.9584, "step": 11568 }, { "epoch": 0.6325098240218692, "grad_norm": 2.066993236541748, "learning_rate": 3.143780108373233e-05, "loss": 1.0284, "step": 11569 }, { "epoch": 0.6325644968392278, "grad_norm": 2.5456509590148926, "learning_rate": 3.142958054326019e-05, "loss": 0.9125, "step": 11570 }, { "epoch": 0.6326191696565864, "grad_norm": 2.2990589141845703, "learning_rate": 3.142136058504718e-05, "loss": 1.027, "step": 11571 }, { "epoch": 0.632673842473945, "grad_norm": 2.5735855102539062, "learning_rate": 3.1413141209351035e-05, "loss": 0.9847, "step": 11572 }, { "epoch": 0.6327285152913036, "grad_norm": 3.636666774749756, "learning_rate": 3.140492241642946e-05, "loss": 1.1434, "step": 11573 }, { "epoch": 0.6327831881086622, "grad_norm": 2.3192923069000244, "learning_rate": 3.139670420654015e-05, "loss": 0.9057, "step": 11574 }, { "epoch": 0.6328378609260208, "grad_norm": 2.105116128921509, "learning_rate": 3.1388486579940766e-05, "loss": 0.8377, "step": 11575 }, { "epoch": 0.6328925337433795, "grad_norm": 2.942150592803955, "learning_rate": 3.1380269536888984e-05, "loss": 0.966, "step": 11576 }, { "epoch": 0.6329472065607381, "grad_norm": 4.527381896972656, "learning_rate": 3.137205307764244e-05, "loss": 1.0013, "step": 11577 }, { "epoch": 0.6330018793780967, "grad_norm": 2.700320243835449, "learning_rate": 3.136383720245876e-05, "loss": 1.0486, "step": 11578 }, { "epoch": 0.6330565521954553, "grad_norm": 2.3973569869995117, "learning_rate": 3.1355621911595526e-05, "loss": 0.9405, "step": 11579 }, { "epoch": 0.6331112250128139, "grad_norm": 3.0999040603637695, "learning_rate": 3.1347407205310334e-05, "loss": 1.05, "step": 11580 }, { "epoch": 0.6331658978301725, "grad_norm": 2.719832181930542, "learning_rate": 3.133919308386074e-05, "loss": 1.0619, "step": 11581 }, { "epoch": 0.6332205706475312, "grad_norm": 2.708763599395752, "learning_rate": 3.13309795475043e-05, "loss": 1.2748, "step": 11582 }, { "epoch": 0.6332752434648898, "grad_norm": 2.431729793548584, "learning_rate": 3.132276659649854e-05, "loss": 1.0244, "step": 11583 }, { "epoch": 0.6333299162822484, "grad_norm": 2.6422207355499268, "learning_rate": 3.131455423110097e-05, "loss": 1.1528, "step": 11584 }, { "epoch": 0.633384589099607, "grad_norm": 2.239453077316284, "learning_rate": 3.1306342451569057e-05, "loss": 0.9364, "step": 11585 }, { "epoch": 0.6334392619169656, "grad_norm": 3.361384391784668, "learning_rate": 3.1298131258160324e-05, "loss": 0.9516, "step": 11586 }, { "epoch": 0.6334939347343242, "grad_norm": 2.693387031555176, "learning_rate": 3.1289920651132185e-05, "loss": 0.9485, "step": 11587 }, { "epoch": 0.6335486075516829, "grad_norm": 3.106365442276001, "learning_rate": 3.12817106307421e-05, "loss": 0.9099, "step": 11588 }, { "epoch": 0.6336032803690416, "grad_norm": 2.4016151428222656, "learning_rate": 3.127350119724746e-05, "loss": 1.0984, "step": 11589 }, { "epoch": 0.6336579531864002, "grad_norm": 1.9095720052719116, "learning_rate": 3.12652923509057e-05, "loss": 0.9003, "step": 11590 }, { "epoch": 0.6337126260037588, "grad_norm": 2.384453296661377, "learning_rate": 3.125708409197417e-05, "loss": 0.9272, "step": 11591 }, { "epoch": 0.6337672988211174, "grad_norm": 1.9711341857910156, "learning_rate": 3.1248876420710246e-05, "loss": 0.9319, "step": 11592 }, { "epoch": 0.633821971638476, "grad_norm": 2.522219181060791, "learning_rate": 3.124066933737128e-05, "loss": 1.0209, "step": 11593 }, { "epoch": 0.6338766444558346, "grad_norm": 2.534971237182617, "learning_rate": 3.123246284221458e-05, "loss": 1.0069, "step": 11594 }, { "epoch": 0.6339313172731932, "grad_norm": 2.7092106342315674, "learning_rate": 3.1224256935497466e-05, "loss": 1.1036, "step": 11595 }, { "epoch": 0.6339859900905519, "grad_norm": 3.1456286907196045, "learning_rate": 3.121605161747723e-05, "loss": 1.0468, "step": 11596 }, { "epoch": 0.6340406629079105, "grad_norm": 3.048910140991211, "learning_rate": 3.120784688841113e-05, "loss": 0.9335, "step": 11597 }, { "epoch": 0.6340953357252691, "grad_norm": 2.133481740951538, "learning_rate": 3.119964274855642e-05, "loss": 0.7529, "step": 11598 }, { "epoch": 0.6341500085426277, "grad_norm": 3.1103241443634033, "learning_rate": 3.1191439198170345e-05, "loss": 1.1485, "step": 11599 }, { "epoch": 0.6342046813599863, "grad_norm": 2.316526174545288, "learning_rate": 3.1183236237510114e-05, "loss": 1.0083, "step": 11600 }, { "epoch": 0.6342593541773449, "grad_norm": 2.8318421840667725, "learning_rate": 3.117503386683292e-05, "loss": 0.9669, "step": 11601 }, { "epoch": 0.6343140269947035, "grad_norm": 2.737133026123047, "learning_rate": 3.116683208639593e-05, "loss": 0.9161, "step": 11602 }, { "epoch": 0.6343686998120622, "grad_norm": 2.472853660583496, "learning_rate": 3.115863089645633e-05, "loss": 0.944, "step": 11603 }, { "epoch": 0.6344233726294208, "grad_norm": 2.1979756355285645, "learning_rate": 3.1150430297271256e-05, "loss": 0.8808, "step": 11604 }, { "epoch": 0.6344780454467794, "grad_norm": 2.837543487548828, "learning_rate": 3.114223028909781e-05, "loss": 1.0831, "step": 11605 }, { "epoch": 0.634532718264138, "grad_norm": 2.6712069511413574, "learning_rate": 3.113403087219311e-05, "loss": 0.8927, "step": 11606 }, { "epoch": 0.6345873910814966, "grad_norm": 2.5680735111236572, "learning_rate": 3.1125832046814244e-05, "loss": 1.0304, "step": 11607 }, { "epoch": 0.6346420638988552, "grad_norm": 2.3600242137908936, "learning_rate": 3.1117633813218286e-05, "loss": 1.0892, "step": 11608 }, { "epoch": 0.634696736716214, "grad_norm": 2.7148735523223877, "learning_rate": 3.1109436171662254e-05, "loss": 1.1183, "step": 11609 }, { "epoch": 0.6347514095335726, "grad_norm": 2.926623821258545, "learning_rate": 3.110123912240321e-05, "loss": 1.0498, "step": 11610 }, { "epoch": 0.6348060823509312, "grad_norm": 2.3991997241973877, "learning_rate": 3.109304266569815e-05, "loss": 0.973, "step": 11611 }, { "epoch": 0.6348607551682898, "grad_norm": 2.594379186630249, "learning_rate": 3.1084846801804075e-05, "loss": 1.0819, "step": 11612 }, { "epoch": 0.6349154279856484, "grad_norm": 2.9373562335968018, "learning_rate": 3.107665153097795e-05, "loss": 1.0465, "step": 11613 }, { "epoch": 0.634970100803007, "grad_norm": 2.2021684646606445, "learning_rate": 3.106845685347673e-05, "loss": 0.9817, "step": 11614 }, { "epoch": 0.6350247736203656, "grad_norm": 2.015235662460327, "learning_rate": 3.106026276955734e-05, "loss": 0.9564, "step": 11615 }, { "epoch": 0.6350794464377243, "grad_norm": 2.509680986404419, "learning_rate": 3.1052069279476734e-05, "loss": 1.0145, "step": 11616 }, { "epoch": 0.6351341192550829, "grad_norm": 2.6690073013305664, "learning_rate": 3.1043876383491785e-05, "loss": 1.1198, "step": 11617 }, { "epoch": 0.6351887920724415, "grad_norm": 2.2790348529815674, "learning_rate": 3.103568408185939e-05, "loss": 0.8797, "step": 11618 }, { "epoch": 0.6352434648898001, "grad_norm": 2.2196974754333496, "learning_rate": 3.10274923748364e-05, "loss": 0.9644, "step": 11619 }, { "epoch": 0.6352981377071587, "grad_norm": 2.5807650089263916, "learning_rate": 3.1019301262679654e-05, "loss": 0.8749, "step": 11620 }, { "epoch": 0.6353528105245173, "grad_norm": 2.3314244747161865, "learning_rate": 3.1011110745645996e-05, "loss": 0.8774, "step": 11621 }, { "epoch": 0.6354074833418759, "grad_norm": 3.018894910812378, "learning_rate": 3.100292082399222e-05, "loss": 1.022, "step": 11622 }, { "epoch": 0.6354621561592346, "grad_norm": 3.2520253658294678, "learning_rate": 3.09947314979751e-05, "loss": 1.0876, "step": 11623 }, { "epoch": 0.6355168289765932, "grad_norm": 2.802065849304199, "learning_rate": 3.0986542767851434e-05, "loss": 1.0268, "step": 11624 }, { "epoch": 0.6355715017939518, "grad_norm": 2.488755702972412, "learning_rate": 3.097835463387793e-05, "loss": 1.0323, "step": 11625 }, { "epoch": 0.6356261746113104, "grad_norm": 2.4944934844970703, "learning_rate": 3.097016709631137e-05, "loss": 0.9651, "step": 11626 }, { "epoch": 0.635680847428669, "grad_norm": 3.184196710586548, "learning_rate": 3.0961980155408446e-05, "loss": 1.1993, "step": 11627 }, { "epoch": 0.6357355202460276, "grad_norm": 2.059155225753784, "learning_rate": 3.0953793811425846e-05, "loss": 0.9373, "step": 11628 }, { "epoch": 0.6357901930633862, "grad_norm": 2.4830820560455322, "learning_rate": 3.094560806462026e-05, "loss": 1.0081, "step": 11629 }, { "epoch": 0.635844865880745, "grad_norm": 2.5995190143585205, "learning_rate": 3.0937422915248325e-05, "loss": 0.9142, "step": 11630 }, { "epoch": 0.6358995386981036, "grad_norm": 2.5527563095092773, "learning_rate": 3.092923836356669e-05, "loss": 0.8496, "step": 11631 }, { "epoch": 0.6359542115154622, "grad_norm": 2.8147356510162354, "learning_rate": 3.0921054409831984e-05, "loss": 1.0641, "step": 11632 }, { "epoch": 0.6360088843328208, "grad_norm": 2.6042850017547607, "learning_rate": 3.091287105430078e-05, "loss": 0.9898, "step": 11633 }, { "epoch": 0.6360635571501794, "grad_norm": 2.7544281482696533, "learning_rate": 3.090468829722968e-05, "loss": 0.9556, "step": 11634 }, { "epoch": 0.636118229967538, "grad_norm": 2.6485424041748047, "learning_rate": 3.089650613887525e-05, "loss": 1.0886, "step": 11635 }, { "epoch": 0.6361729027848967, "grad_norm": 2.2135748863220215, "learning_rate": 3.088832457949403e-05, "loss": 1.0763, "step": 11636 }, { "epoch": 0.6362275756022553, "grad_norm": 2.372096300125122, "learning_rate": 3.088014361934255e-05, "loss": 1.0269, "step": 11637 }, { "epoch": 0.6362822484196139, "grad_norm": 2.6053466796875, "learning_rate": 3.087196325867731e-05, "loss": 1.0399, "step": 11638 }, { "epoch": 0.6363369212369725, "grad_norm": 2.278350353240967, "learning_rate": 3.086378349775479e-05, "loss": 0.952, "step": 11639 }, { "epoch": 0.6363915940543311, "grad_norm": 2.362116575241089, "learning_rate": 3.085560433683148e-05, "loss": 0.9134, "step": 11640 }, { "epoch": 0.6364462668716897, "grad_norm": 2.7299764156341553, "learning_rate": 3.0847425776163815e-05, "loss": 1.1709, "step": 11641 }, { "epoch": 0.6365009396890483, "grad_norm": 2.554149627685547, "learning_rate": 3.0839247816008234e-05, "loss": 0.9526, "step": 11642 }, { "epoch": 0.636555612506407, "grad_norm": 3.502462387084961, "learning_rate": 3.083107045662114e-05, "loss": 1.0838, "step": 11643 }, { "epoch": 0.6366102853237656, "grad_norm": 2.776002883911133, "learning_rate": 3.0822893698258915e-05, "loss": 1.0726, "step": 11644 }, { "epoch": 0.6366649581411242, "grad_norm": 2.706256866455078, "learning_rate": 3.081471754117797e-05, "loss": 1.097, "step": 11645 }, { "epoch": 0.6367196309584828, "grad_norm": 2.9814374446868896, "learning_rate": 3.080654198563465e-05, "loss": 1.1797, "step": 11646 }, { "epoch": 0.6367743037758414, "grad_norm": 2.587355852127075, "learning_rate": 3.0798367031885284e-05, "loss": 1.118, "step": 11647 }, { "epoch": 0.6368289765932, "grad_norm": 2.8533003330230713, "learning_rate": 3.079019268018619e-05, "loss": 1.0755, "step": 11648 }, { "epoch": 0.6368836494105586, "grad_norm": 1.8868223428726196, "learning_rate": 3.0782018930793664e-05, "loss": 0.8408, "step": 11649 }, { "epoch": 0.6369383222279174, "grad_norm": 3.0532405376434326, "learning_rate": 3.077384578396401e-05, "loss": 0.9202, "step": 11650 }, { "epoch": 0.636992995045276, "grad_norm": 2.7797563076019287, "learning_rate": 3.076567323995345e-05, "loss": 1.1728, "step": 11651 }, { "epoch": 0.6370476678626346, "grad_norm": 2.1951534748077393, "learning_rate": 3.0757501299018264e-05, "loss": 0.8389, "step": 11652 }, { "epoch": 0.6371023406799932, "grad_norm": 2.7899134159088135, "learning_rate": 3.074932996141466e-05, "loss": 1.0192, "step": 11653 }, { "epoch": 0.6371570134973518, "grad_norm": 2.5093257427215576, "learning_rate": 3.074115922739882e-05, "loss": 1.0111, "step": 11654 }, { "epoch": 0.6372116863147104, "grad_norm": 2.3241448402404785, "learning_rate": 3.073298909722697e-05, "loss": 1.0262, "step": 11655 }, { "epoch": 0.637266359132069, "grad_norm": 2.7986509799957275, "learning_rate": 3.072481957115527e-05, "loss": 1.02, "step": 11656 }, { "epoch": 0.6373210319494277, "grad_norm": 3.083491802215576, "learning_rate": 3.071665064943986e-05, "loss": 1.0766, "step": 11657 }, { "epoch": 0.6373757047667863, "grad_norm": 2.28265380859375, "learning_rate": 3.070848233233686e-05, "loss": 0.8168, "step": 11658 }, { "epoch": 0.6374303775841449, "grad_norm": 2.4202396869659424, "learning_rate": 3.07003146201024e-05, "loss": 0.8641, "step": 11659 }, { "epoch": 0.6374850504015035, "grad_norm": 2.4282758235931396, "learning_rate": 3.069214751299256e-05, "loss": 0.9237, "step": 11660 }, { "epoch": 0.6375397232188621, "grad_norm": 2.2941269874572754, "learning_rate": 3.0683981011263405e-05, "loss": 0.9189, "step": 11661 }, { "epoch": 0.6375943960362207, "grad_norm": 3.03743839263916, "learning_rate": 3.0675815115171005e-05, "loss": 1.086, "step": 11662 }, { "epoch": 0.6376490688535794, "grad_norm": 3.030585289001465, "learning_rate": 3.066764982497139e-05, "loss": 1.0747, "step": 11663 }, { "epoch": 0.637703741670938, "grad_norm": 2.845850944519043, "learning_rate": 3.065948514092054e-05, "loss": 1.0547, "step": 11664 }, { "epoch": 0.6377584144882966, "grad_norm": 2.4980437755584717, "learning_rate": 3.065132106327451e-05, "loss": 1.1106, "step": 11665 }, { "epoch": 0.6378130873056552, "grad_norm": 2.5529189109802246, "learning_rate": 3.064315759228925e-05, "loss": 1.1381, "step": 11666 }, { "epoch": 0.6378677601230138, "grad_norm": 2.8538308143615723, "learning_rate": 3.0634994728220724e-05, "loss": 1.1204, "step": 11667 }, { "epoch": 0.6379224329403724, "grad_norm": 2.6957547664642334, "learning_rate": 3.062683247132486e-05, "loss": 1.2007, "step": 11668 }, { "epoch": 0.637977105757731, "grad_norm": 2.349856376647949, "learning_rate": 3.0618670821857587e-05, "loss": 1.0734, "step": 11669 }, { "epoch": 0.6380317785750897, "grad_norm": 3.331256866455078, "learning_rate": 3.061050978007481e-05, "loss": 1.182, "step": 11670 }, { "epoch": 0.6380864513924484, "grad_norm": 2.267761707305908, "learning_rate": 3.060234934623239e-05, "loss": 0.9088, "step": 11671 }, { "epoch": 0.638141124209807, "grad_norm": 2.945868968963623, "learning_rate": 3.059418952058623e-05, "loss": 1.1277, "step": 11672 }, { "epoch": 0.6381957970271656, "grad_norm": 3.5980136394500732, "learning_rate": 3.0586030303392135e-05, "loss": 0.9612, "step": 11673 }, { "epoch": 0.6382504698445242, "grad_norm": 2.781802177429199, "learning_rate": 3.0577871694905936e-05, "loss": 1.0453, "step": 11674 }, { "epoch": 0.6383051426618828, "grad_norm": 4.479666709899902, "learning_rate": 3.056971369538346e-05, "loss": 0.8954, "step": 11675 }, { "epoch": 0.6383598154792414, "grad_norm": 3.0894699096679688, "learning_rate": 3.0561556305080466e-05, "loss": 1.1931, "step": 11676 }, { "epoch": 0.6384144882966001, "grad_norm": 3.1533753871917725, "learning_rate": 3.0553399524252755e-05, "loss": 1.3203, "step": 11677 }, { "epoch": 0.6384691611139587, "grad_norm": 3.0662856101989746, "learning_rate": 3.054524335315605e-05, "loss": 1.097, "step": 11678 }, { "epoch": 0.6385238339313173, "grad_norm": 2.0480332374572754, "learning_rate": 3.0537087792046096e-05, "loss": 0.8936, "step": 11679 }, { "epoch": 0.6385785067486759, "grad_norm": 2.6449460983276367, "learning_rate": 3.05289328411786e-05, "loss": 0.9281, "step": 11680 }, { "epoch": 0.6386331795660345, "grad_norm": 4.382903575897217, "learning_rate": 3.052077850080925e-05, "loss": 1.2246, "step": 11681 }, { "epoch": 0.6386878523833931, "grad_norm": 2.3115785121917725, "learning_rate": 3.051262477119371e-05, "loss": 0.8684, "step": 11682 }, { "epoch": 0.6387425252007517, "grad_norm": 2.1708452701568604, "learning_rate": 3.050447165258763e-05, "loss": 0.8439, "step": 11683 }, { "epoch": 0.6387971980181104, "grad_norm": 2.0149447917938232, "learning_rate": 3.0496319145246665e-05, "loss": 0.7774, "step": 11684 }, { "epoch": 0.638851870835469, "grad_norm": 2.0212695598602295, "learning_rate": 3.0488167249426426e-05, "loss": 0.8892, "step": 11685 }, { "epoch": 0.6389065436528276, "grad_norm": 2.9556920528411865, "learning_rate": 3.0480015965382502e-05, "loss": 1.1321, "step": 11686 }, { "epoch": 0.6389612164701862, "grad_norm": 2.737745761871338, "learning_rate": 3.047186529337046e-05, "loss": 1.1446, "step": 11687 }, { "epoch": 0.6390158892875448, "grad_norm": 2.740924835205078, "learning_rate": 3.0463715233645872e-05, "loss": 0.946, "step": 11688 }, { "epoch": 0.6390705621049034, "grad_norm": 2.907820463180542, "learning_rate": 3.0455565786464262e-05, "loss": 1.2257, "step": 11689 }, { "epoch": 0.6391252349222621, "grad_norm": 3.390298366546631, "learning_rate": 3.0447416952081163e-05, "loss": 1.0824, "step": 11690 }, { "epoch": 0.6391799077396207, "grad_norm": 2.6024794578552246, "learning_rate": 3.0439268730752075e-05, "loss": 1.19, "step": 11691 }, { "epoch": 0.6392345805569793, "grad_norm": 2.678724527359009, "learning_rate": 3.0431121122732463e-05, "loss": 1.1152, "step": 11692 }, { "epoch": 0.639289253374338, "grad_norm": 2.490264415740967, "learning_rate": 3.0422974128277792e-05, "loss": 0.8515, "step": 11693 }, { "epoch": 0.6393439261916966, "grad_norm": 3.019721269607544, "learning_rate": 3.0414827747643527e-05, "loss": 1.095, "step": 11694 }, { "epoch": 0.6393985990090552, "grad_norm": 2.263127565383911, "learning_rate": 3.0406681981085062e-05, "loss": 0.9578, "step": 11695 }, { "epoch": 0.6394532718264138, "grad_norm": 2.969142436981201, "learning_rate": 3.039853682885781e-05, "loss": 1.0341, "step": 11696 }, { "epoch": 0.6395079446437725, "grad_norm": 2.3528218269348145, "learning_rate": 3.0390392291217155e-05, "loss": 0.8508, "step": 11697 }, { "epoch": 0.6395626174611311, "grad_norm": 3.294503688812256, "learning_rate": 3.0382248368418464e-05, "loss": 0.8324, "step": 11698 }, { "epoch": 0.6396172902784897, "grad_norm": 2.8889026641845703, "learning_rate": 3.0374105060717085e-05, "loss": 1.1725, "step": 11699 }, { "epoch": 0.6396719630958483, "grad_norm": 2.82841420173645, "learning_rate": 3.036596236836834e-05, "loss": 0.9318, "step": 11700 }, { "epoch": 0.6397266359132069, "grad_norm": 3.4754273891448975, "learning_rate": 3.0357820291627536e-05, "loss": 0.976, "step": 11701 }, { "epoch": 0.6397813087305655, "grad_norm": 2.3226137161254883, "learning_rate": 3.0349678830749943e-05, "loss": 1.1163, "step": 11702 }, { "epoch": 0.6398359815479241, "grad_norm": 3.0331876277923584, "learning_rate": 3.0341537985990852e-05, "loss": 0.9492, "step": 11703 }, { "epoch": 0.6398906543652828, "grad_norm": 3.215097427368164, "learning_rate": 3.033339775760552e-05, "loss": 1.0923, "step": 11704 }, { "epoch": 0.6399453271826414, "grad_norm": 3.146986961364746, "learning_rate": 3.0325258145849168e-05, "loss": 1.1117, "step": 11705 }, { "epoch": 0.64, "grad_norm": 3.3379600048065186, "learning_rate": 3.0317119150976992e-05, "loss": 0.9351, "step": 11706 }, { "epoch": 0.6400546728173586, "grad_norm": 2.999953269958496, "learning_rate": 3.03089807732442e-05, "loss": 0.9225, "step": 11707 }, { "epoch": 0.6401093456347172, "grad_norm": 2.768157482147217, "learning_rate": 3.0300843012905954e-05, "loss": 1.0337, "step": 11708 }, { "epoch": 0.6401640184520758, "grad_norm": 2.354764461517334, "learning_rate": 3.0292705870217407e-05, "loss": 0.9195, "step": 11709 }, { "epoch": 0.6402186912694344, "grad_norm": 2.7682011127471924, "learning_rate": 3.02845693454337e-05, "loss": 1.1852, "step": 11710 }, { "epoch": 0.6402733640867931, "grad_norm": 3.846144437789917, "learning_rate": 3.0276433438809935e-05, "loss": 0.9922, "step": 11711 }, { "epoch": 0.6403280369041517, "grad_norm": 2.5991952419281006, "learning_rate": 3.0268298150601215e-05, "loss": 1.0799, "step": 11712 }, { "epoch": 0.6403827097215103, "grad_norm": 2.8349270820617676, "learning_rate": 3.0260163481062585e-05, "loss": 1.0913, "step": 11713 }, { "epoch": 0.640437382538869, "grad_norm": 2.8428823947906494, "learning_rate": 3.0252029430449157e-05, "loss": 1.1394, "step": 11714 }, { "epoch": 0.6404920553562276, "grad_norm": 2.1338653564453125, "learning_rate": 3.024389599901593e-05, "loss": 0.8413, "step": 11715 }, { "epoch": 0.6405467281735862, "grad_norm": 3.349242925643921, "learning_rate": 3.023576318701793e-05, "loss": 1.0452, "step": 11716 }, { "epoch": 0.6406014009909449, "grad_norm": 2.5022542476654053, "learning_rate": 3.0227630994710154e-05, "loss": 1.0538, "step": 11717 }, { "epoch": 0.6406560738083035, "grad_norm": 2.8535373210906982, "learning_rate": 3.0219499422347573e-05, "loss": 1.0232, "step": 11718 }, { "epoch": 0.6407107466256621, "grad_norm": 2.6371817588806152, "learning_rate": 3.0211368470185152e-05, "loss": 1.0513, "step": 11719 }, { "epoch": 0.6407654194430207, "grad_norm": 2.6618425846099854, "learning_rate": 3.0203238138477828e-05, "loss": 1.159, "step": 11720 }, { "epoch": 0.6408200922603793, "grad_norm": 2.0510432720184326, "learning_rate": 3.0195108427480524e-05, "loss": 0.924, "step": 11721 }, { "epoch": 0.6408747650777379, "grad_norm": 2.893127918243408, "learning_rate": 3.0186979337448128e-05, "loss": 0.9922, "step": 11722 }, { "epoch": 0.6409294378950965, "grad_norm": 2.4404311180114746, "learning_rate": 3.017885086863551e-05, "loss": 0.9464, "step": 11723 }, { "epoch": 0.6409841107124552, "grad_norm": 5.720233917236328, "learning_rate": 3.0170723021297575e-05, "loss": 0.9982, "step": 11724 }, { "epoch": 0.6410387835298138, "grad_norm": 2.2256124019622803, "learning_rate": 3.016259579568913e-05, "loss": 1.036, "step": 11725 }, { "epoch": 0.6410934563471724, "grad_norm": 2.539724826812744, "learning_rate": 3.0154469192065015e-05, "loss": 0.9438, "step": 11726 }, { "epoch": 0.641148129164531, "grad_norm": 2.580334186553955, "learning_rate": 3.0146343210680015e-05, "loss": 1.0575, "step": 11727 }, { "epoch": 0.6412028019818896, "grad_norm": 2.816864013671875, "learning_rate": 3.013821785178893e-05, "loss": 1.0669, "step": 11728 }, { "epoch": 0.6412574747992482, "grad_norm": 2.9006404876708984, "learning_rate": 3.013009311564651e-05, "loss": 1.2666, "step": 11729 }, { "epoch": 0.6413121476166068, "grad_norm": 2.6643967628479004, "learning_rate": 3.01219690025075e-05, "loss": 1.2168, "step": 11730 }, { "epoch": 0.6413668204339655, "grad_norm": 2.323021173477173, "learning_rate": 3.0113845512626636e-05, "loss": 1.1545, "step": 11731 }, { "epoch": 0.6414214932513241, "grad_norm": 2.66060733795166, "learning_rate": 3.0105722646258596e-05, "loss": 0.8017, "step": 11732 }, { "epoch": 0.6414761660686827, "grad_norm": 2.509080171585083, "learning_rate": 3.0097600403658092e-05, "loss": 0.9473, "step": 11733 }, { "epoch": 0.6415308388860413, "grad_norm": 4.057717800140381, "learning_rate": 3.0089478785079796e-05, "loss": 1.3179, "step": 11734 }, { "epoch": 0.6415855117034, "grad_norm": 2.969836473464966, "learning_rate": 3.008135779077833e-05, "loss": 1.1991, "step": 11735 }, { "epoch": 0.6416401845207585, "grad_norm": 2.343193769454956, "learning_rate": 3.007323742100833e-05, "loss": 0.9574, "step": 11736 }, { "epoch": 0.6416948573381172, "grad_norm": 2.551574468612671, "learning_rate": 3.0065117676024413e-05, "loss": 0.9017, "step": 11737 }, { "epoch": 0.6417495301554759, "grad_norm": 2.611671209335327, "learning_rate": 3.005699855608115e-05, "loss": 1.0319, "step": 11738 }, { "epoch": 0.6418042029728345, "grad_norm": 2.6044118404388428, "learning_rate": 3.0048880061433116e-05, "loss": 1.1159, "step": 11739 }, { "epoch": 0.6418588757901931, "grad_norm": 3.5683679580688477, "learning_rate": 3.0040762192334865e-05, "loss": 1.1538, "step": 11740 }, { "epoch": 0.6419135486075517, "grad_norm": 2.5098516941070557, "learning_rate": 3.003264494904091e-05, "loss": 0.7476, "step": 11741 }, { "epoch": 0.6419682214249103, "grad_norm": 2.5075223445892334, "learning_rate": 3.0024528331805764e-05, "loss": 0.9298, "step": 11742 }, { "epoch": 0.6420228942422689, "grad_norm": 3.1615054607391357, "learning_rate": 3.0016412340883936e-05, "loss": 1.0617, "step": 11743 }, { "epoch": 0.6420775670596276, "grad_norm": 1.9247630834579468, "learning_rate": 3.0008296976529883e-05, "loss": 0.998, "step": 11744 }, { "epoch": 0.6421322398769862, "grad_norm": 2.5250420570373535, "learning_rate": 3.000018223899805e-05, "loss": 1.002, "step": 11745 }, { "epoch": 0.6421869126943448, "grad_norm": 2.7185792922973633, "learning_rate": 2.999206812854287e-05, "loss": 0.9993, "step": 11746 }, { "epoch": 0.6422415855117034, "grad_norm": 3.030510663986206, "learning_rate": 2.9983954645418767e-05, "loss": 1.0548, "step": 11747 }, { "epoch": 0.642296258329062, "grad_norm": 2.5353918075561523, "learning_rate": 2.997584178988011e-05, "loss": 1.2217, "step": 11748 }, { "epoch": 0.6423509311464206, "grad_norm": 2.869710683822632, "learning_rate": 2.996772956218128e-05, "loss": 1.0894, "step": 11749 }, { "epoch": 0.6424056039637792, "grad_norm": 2.718487501144409, "learning_rate": 2.9959617962576637e-05, "loss": 0.8678, "step": 11750 }, { "epoch": 0.6424602767811379, "grad_norm": 2.038533926010132, "learning_rate": 2.99515069913205e-05, "loss": 0.8297, "step": 11751 }, { "epoch": 0.6425149495984965, "grad_norm": 2.695002794265747, "learning_rate": 2.9943396648667177e-05, "loss": 0.8187, "step": 11752 }, { "epoch": 0.6425696224158551, "grad_norm": 2.946560859680176, "learning_rate": 2.9935286934870975e-05, "loss": 1.2672, "step": 11753 }, { "epoch": 0.6426242952332137, "grad_norm": 2.6214311122894287, "learning_rate": 2.9927177850186177e-05, "loss": 0.8777, "step": 11754 }, { "epoch": 0.6426789680505723, "grad_norm": 2.6104965209960938, "learning_rate": 2.9919069394867015e-05, "loss": 1.0726, "step": 11755 }, { "epoch": 0.6427336408679309, "grad_norm": 2.3596031665802, "learning_rate": 2.9910961569167735e-05, "loss": 0.9667, "step": 11756 }, { "epoch": 0.6427883136852895, "grad_norm": 2.9046382904052734, "learning_rate": 2.9902854373342537e-05, "loss": 1.0716, "step": 11757 }, { "epoch": 0.6428429865026483, "grad_norm": 2.9731249809265137, "learning_rate": 2.989474780764563e-05, "loss": 0.929, "step": 11758 }, { "epoch": 0.6428976593200069, "grad_norm": 2.419900894165039, "learning_rate": 2.9886641872331177e-05, "loss": 0.8386, "step": 11759 }, { "epoch": 0.6429523321373655, "grad_norm": 2.7512905597686768, "learning_rate": 2.9878536567653336e-05, "loss": 1.1297, "step": 11760 }, { "epoch": 0.6430070049547241, "grad_norm": 2.312248945236206, "learning_rate": 2.9870431893866245e-05, "loss": 1.0502, "step": 11761 }, { "epoch": 0.6430616777720827, "grad_norm": 4.178068161010742, "learning_rate": 2.986232785122401e-05, "loss": 1.1755, "step": 11762 }, { "epoch": 0.6431163505894413, "grad_norm": 2.737783670425415, "learning_rate": 2.9854224439980726e-05, "loss": 1.0412, "step": 11763 }, { "epoch": 0.6431710234067999, "grad_norm": 2.966203451156616, "learning_rate": 2.984612166039049e-05, "loss": 1.1066, "step": 11764 }, { "epoch": 0.6432256962241586, "grad_norm": 4.020266056060791, "learning_rate": 2.983801951270734e-05, "loss": 1.1698, "step": 11765 }, { "epoch": 0.6432803690415172, "grad_norm": 3.1547176837921143, "learning_rate": 2.9829917997185313e-05, "loss": 1.0696, "step": 11766 }, { "epoch": 0.6433350418588758, "grad_norm": 2.168876886367798, "learning_rate": 2.9821817114078427e-05, "loss": 0.862, "step": 11767 }, { "epoch": 0.6433897146762344, "grad_norm": 2.834252119064331, "learning_rate": 2.9813716863640674e-05, "loss": 0.9763, "step": 11768 }, { "epoch": 0.643444387493593, "grad_norm": 3.116004467010498, "learning_rate": 2.9805617246126037e-05, "loss": 1.1332, "step": 11769 }, { "epoch": 0.6434990603109516, "grad_norm": 2.647531032562256, "learning_rate": 2.979751826178847e-05, "loss": 1.1275, "step": 11770 }, { "epoch": 0.6435537331283103, "grad_norm": 2.5584781169891357, "learning_rate": 2.97894199108819e-05, "loss": 1.2127, "step": 11771 }, { "epoch": 0.6436084059456689, "grad_norm": 3.024080514907837, "learning_rate": 2.978132219366025e-05, "loss": 1.1295, "step": 11772 }, { "epoch": 0.6436630787630275, "grad_norm": 3.771848440170288, "learning_rate": 2.9773225110377422e-05, "loss": 1.101, "step": 11773 }, { "epoch": 0.6437177515803861, "grad_norm": 2.3145911693573, "learning_rate": 2.97651286612873e-05, "loss": 0.9363, "step": 11774 }, { "epoch": 0.6437724243977447, "grad_norm": 2.122609853744507, "learning_rate": 2.9757032846643716e-05, "loss": 1.0404, "step": 11775 }, { "epoch": 0.6438270972151033, "grad_norm": 3.3994107246398926, "learning_rate": 2.974893766670052e-05, "loss": 0.9711, "step": 11776 }, { "epoch": 0.6438817700324619, "grad_norm": 2.295832872390747, "learning_rate": 2.9740843121711542e-05, "loss": 1.0789, "step": 11777 }, { "epoch": 0.6439364428498207, "grad_norm": 3.322117328643799, "learning_rate": 2.9732749211930565e-05, "loss": 1.0671, "step": 11778 }, { "epoch": 0.6439911156671793, "grad_norm": 2.7365458011627197, "learning_rate": 2.9724655937611368e-05, "loss": 1.0967, "step": 11779 }, { "epoch": 0.6440457884845379, "grad_norm": 2.2519571781158447, "learning_rate": 2.9716563299007717e-05, "loss": 0.9677, "step": 11780 }, { "epoch": 0.6441004613018965, "grad_norm": 3.112241506576538, "learning_rate": 2.9708471296373334e-05, "loss": 1.039, "step": 11781 }, { "epoch": 0.6441551341192551, "grad_norm": 2.3551158905029297, "learning_rate": 2.9700379929961942e-05, "loss": 0.9082, "step": 11782 }, { "epoch": 0.6442098069366137, "grad_norm": 2.9739861488342285, "learning_rate": 2.9692289200027244e-05, "loss": 0.9915, "step": 11783 }, { "epoch": 0.6442644797539723, "grad_norm": 3.1764109134674072, "learning_rate": 2.968419910682292e-05, "loss": 1.1047, "step": 11784 }, { "epoch": 0.644319152571331, "grad_norm": 2.9671967029571533, "learning_rate": 2.9676109650602625e-05, "loss": 0.9244, "step": 11785 }, { "epoch": 0.6443738253886896, "grad_norm": 2.9802701473236084, "learning_rate": 2.9668020831619993e-05, "loss": 1.1919, "step": 11786 }, { "epoch": 0.6444284982060482, "grad_norm": 2.250166177749634, "learning_rate": 2.965993265012864e-05, "loss": 0.9194, "step": 11787 }, { "epoch": 0.6444831710234068, "grad_norm": 2.962134838104248, "learning_rate": 2.9651845106382174e-05, "loss": 1.0851, "step": 11788 }, { "epoch": 0.6445378438407654, "grad_norm": 2.0531160831451416, "learning_rate": 2.9643758200634154e-05, "loss": 0.7695, "step": 11789 }, { "epoch": 0.644592516658124, "grad_norm": 3.644275188446045, "learning_rate": 2.9635671933138165e-05, "loss": 1.2009, "step": 11790 }, { "epoch": 0.6446471894754826, "grad_norm": 2.580817222595215, "learning_rate": 2.9627586304147714e-05, "loss": 1.2316, "step": 11791 }, { "epoch": 0.6447018622928413, "grad_norm": 2.6716320514678955, "learning_rate": 2.9619501313916342e-05, "loss": 1.1428, "step": 11792 }, { "epoch": 0.6447565351101999, "grad_norm": 3.0331573486328125, "learning_rate": 2.9611416962697545e-05, "loss": 1.0667, "step": 11793 }, { "epoch": 0.6448112079275585, "grad_norm": 2.1424882411956787, "learning_rate": 2.960333325074479e-05, "loss": 1.052, "step": 11794 }, { "epoch": 0.6448658807449171, "grad_norm": 2.8127009868621826, "learning_rate": 2.959525017831155e-05, "loss": 1.1217, "step": 11795 }, { "epoch": 0.6449205535622757, "grad_norm": 2.7482948303222656, "learning_rate": 2.9587167745651245e-05, "loss": 1.1578, "step": 11796 }, { "epoch": 0.6449752263796343, "grad_norm": 2.2309491634368896, "learning_rate": 2.95790859530173e-05, "loss": 0.9499, "step": 11797 }, { "epoch": 0.6450298991969929, "grad_norm": 2.418714761734009, "learning_rate": 2.9571004800663114e-05, "loss": 0.9008, "step": 11798 }, { "epoch": 0.6450845720143517, "grad_norm": 2.871641159057617, "learning_rate": 2.9562924288842064e-05, "loss": 1.0264, "step": 11799 }, { "epoch": 0.6451392448317103, "grad_norm": 2.4587533473968506, "learning_rate": 2.9554844417807503e-05, "loss": 1.2742, "step": 11800 }, { "epoch": 0.6451939176490689, "grad_norm": 3.287733316421509, "learning_rate": 2.954676518781275e-05, "loss": 1.1146, "step": 11801 }, { "epoch": 0.6452485904664275, "grad_norm": 2.4728474617004395, "learning_rate": 2.9538686599111165e-05, "loss": 0.82, "step": 11802 }, { "epoch": 0.6453032632837861, "grad_norm": 2.4903576374053955, "learning_rate": 2.9530608651956025e-05, "loss": 1.1483, "step": 11803 }, { "epoch": 0.6453579361011447, "grad_norm": 3.0286543369293213, "learning_rate": 2.9522531346600612e-05, "loss": 0.9891, "step": 11804 }, { "epoch": 0.6454126089185034, "grad_norm": 3.6340482234954834, "learning_rate": 2.9514454683298166e-05, "loss": 0.9034, "step": 11805 }, { "epoch": 0.645467281735862, "grad_norm": 2.7794699668884277, "learning_rate": 2.9506378662301935e-05, "loss": 1.2186, "step": 11806 }, { "epoch": 0.6455219545532206, "grad_norm": 2.572368860244751, "learning_rate": 2.949830328386515e-05, "loss": 0.8565, "step": 11807 }, { "epoch": 0.6455766273705792, "grad_norm": 3.037026882171631, "learning_rate": 2.949022854824097e-05, "loss": 1.1557, "step": 11808 }, { "epoch": 0.6456313001879378, "grad_norm": 2.6399216651916504, "learning_rate": 2.948215445568261e-05, "loss": 1.103, "step": 11809 }, { "epoch": 0.6456859730052964, "grad_norm": 2.883786678314209, "learning_rate": 2.94740810064432e-05, "loss": 1.1745, "step": 11810 }, { "epoch": 0.645740645822655, "grad_norm": 3.2731683254241943, "learning_rate": 2.9466008200775862e-05, "loss": 1.1238, "step": 11811 }, { "epoch": 0.6457953186400137, "grad_norm": 2.5020925998687744, "learning_rate": 2.9457936038933764e-05, "loss": 0.9196, "step": 11812 }, { "epoch": 0.6458499914573723, "grad_norm": 2.348727226257324, "learning_rate": 2.9449864521169966e-05, "loss": 1.0217, "step": 11813 }, { "epoch": 0.6459046642747309, "grad_norm": 2.7676913738250732, "learning_rate": 2.9441793647737547e-05, "loss": 1.1042, "step": 11814 }, { "epoch": 0.6459593370920895, "grad_norm": 2.8467907905578613, "learning_rate": 2.943372341888957e-05, "loss": 0.7613, "step": 11815 }, { "epoch": 0.6460140099094481, "grad_norm": 2.2761237621307373, "learning_rate": 2.9425653834879065e-05, "loss": 0.923, "step": 11816 }, { "epoch": 0.6460686827268067, "grad_norm": 2.9239795207977295, "learning_rate": 2.9417584895959048e-05, "loss": 0.9018, "step": 11817 }, { "epoch": 0.6461233555441653, "grad_norm": 2.3298614025115967, "learning_rate": 2.9409516602382507e-05, "loss": 0.9924, "step": 11818 }, { "epoch": 0.646178028361524, "grad_norm": 2.7269537448883057, "learning_rate": 2.940144895440242e-05, "loss": 1.1349, "step": 11819 }, { "epoch": 0.6462327011788827, "grad_norm": 4.51564884185791, "learning_rate": 2.939338195227175e-05, "loss": 1.3509, "step": 11820 }, { "epoch": 0.6462873739962413, "grad_norm": 2.4809796810150146, "learning_rate": 2.9385315596243397e-05, "loss": 1.0274, "step": 11821 }, { "epoch": 0.6463420468135999, "grad_norm": 2.711426019668579, "learning_rate": 2.9377249886570326e-05, "loss": 1.0219, "step": 11822 }, { "epoch": 0.6463967196309585, "grad_norm": 2.874178886413574, "learning_rate": 2.936918482350539e-05, "loss": 0.9433, "step": 11823 }, { "epoch": 0.6464513924483171, "grad_norm": 2.696103096008301, "learning_rate": 2.936112040730149e-05, "loss": 1.1278, "step": 11824 }, { "epoch": 0.6465060652656757, "grad_norm": 2.1552658081054688, "learning_rate": 2.9353056638211463e-05, "loss": 0.9861, "step": 11825 }, { "epoch": 0.6465607380830344, "grad_norm": 2.6862740516662598, "learning_rate": 2.934499351648814e-05, "loss": 1.1818, "step": 11826 }, { "epoch": 0.646615410900393, "grad_norm": 2.792325258255005, "learning_rate": 2.9336931042384334e-05, "loss": 1.0837, "step": 11827 }, { "epoch": 0.6466700837177516, "grad_norm": 2.7334859371185303, "learning_rate": 2.9328869216152842e-05, "loss": 1.0859, "step": 11828 }, { "epoch": 0.6467247565351102, "grad_norm": 3.1588194370269775, "learning_rate": 2.9320808038046434e-05, "loss": 1.1442, "step": 11829 }, { "epoch": 0.6467794293524688, "grad_norm": 2.342802047729492, "learning_rate": 2.931274750831786e-05, "loss": 1.0325, "step": 11830 }, { "epoch": 0.6468341021698274, "grad_norm": 2.4548585414886475, "learning_rate": 2.930468762721983e-05, "loss": 0.8877, "step": 11831 }, { "epoch": 0.6468887749871861, "grad_norm": 2.41115665435791, "learning_rate": 2.92966283950051e-05, "loss": 0.9838, "step": 11832 }, { "epoch": 0.6469434478045447, "grad_norm": 2.3061957359313965, "learning_rate": 2.9288569811926326e-05, "loss": 0.953, "step": 11833 }, { "epoch": 0.6469981206219033, "grad_norm": 2.5527048110961914, "learning_rate": 2.9280511878236193e-05, "loss": 1.0736, "step": 11834 }, { "epoch": 0.6470527934392619, "grad_norm": 5.244910717010498, "learning_rate": 2.9272454594187337e-05, "loss": 1.148, "step": 11835 }, { "epoch": 0.6471074662566205, "grad_norm": 2.4849154949188232, "learning_rate": 2.9264397960032407e-05, "loss": 0.862, "step": 11836 }, { "epoch": 0.6471621390739791, "grad_norm": 2.2507734298706055, "learning_rate": 2.9256341976023992e-05, "loss": 0.9261, "step": 11837 }, { "epoch": 0.6472168118913377, "grad_norm": 2.2184276580810547, "learning_rate": 2.9248286642414684e-05, "loss": 1.0264, "step": 11838 }, { "epoch": 0.6472714847086964, "grad_norm": 3.409519672393799, "learning_rate": 2.924023195945706e-05, "loss": 1.108, "step": 11839 }, { "epoch": 0.647326157526055, "grad_norm": 2.583242893218994, "learning_rate": 2.9232177927403636e-05, "loss": 1.0184, "step": 11840 }, { "epoch": 0.6473808303434136, "grad_norm": 2.7520217895507812, "learning_rate": 2.9224124546506992e-05, "loss": 1.0622, "step": 11841 }, { "epoch": 0.6474355031607723, "grad_norm": 3.5748884677886963, "learning_rate": 2.9216071817019602e-05, "loss": 1.0542, "step": 11842 }, { "epoch": 0.6474901759781309, "grad_norm": 2.4326012134552, "learning_rate": 2.9208019739193958e-05, "loss": 1.0272, "step": 11843 }, { "epoch": 0.6475448487954895, "grad_norm": 2.8202834129333496, "learning_rate": 2.9199968313282533e-05, "loss": 1.1245, "step": 11844 }, { "epoch": 0.6475995216128481, "grad_norm": 3.7089056968688965, "learning_rate": 2.9191917539537762e-05, "loss": 0.906, "step": 11845 }, { "epoch": 0.6476541944302068, "grad_norm": 2.7193245887756348, "learning_rate": 2.9183867418212062e-05, "loss": 1.017, "step": 11846 }, { "epoch": 0.6477088672475654, "grad_norm": 2.2844979763031006, "learning_rate": 2.917581794955786e-05, "loss": 1.0135, "step": 11847 }, { "epoch": 0.647763540064924, "grad_norm": 2.885793924331665, "learning_rate": 2.9167769133827527e-05, "loss": 1.2415, "step": 11848 }, { "epoch": 0.6478182128822826, "grad_norm": 2.557497024536133, "learning_rate": 2.915972097127342e-05, "loss": 0.9947, "step": 11849 }, { "epoch": 0.6478728856996412, "grad_norm": 2.440556526184082, "learning_rate": 2.9151673462147878e-05, "loss": 0.9408, "step": 11850 }, { "epoch": 0.6479275585169998, "grad_norm": 2.43100905418396, "learning_rate": 2.914362660670325e-05, "loss": 0.9158, "step": 11851 }, { "epoch": 0.6479822313343584, "grad_norm": 4.469820976257324, "learning_rate": 2.9135580405191825e-05, "loss": 0.9668, "step": 11852 }, { "epoch": 0.6480369041517171, "grad_norm": 2.6531190872192383, "learning_rate": 2.9127534857865884e-05, "loss": 1.1804, "step": 11853 }, { "epoch": 0.6480915769690757, "grad_norm": 2.4337666034698486, "learning_rate": 2.9119489964977685e-05, "loss": 1.0132, "step": 11854 }, { "epoch": 0.6481462497864343, "grad_norm": 2.6745972633361816, "learning_rate": 2.9111445726779473e-05, "loss": 0.904, "step": 11855 }, { "epoch": 0.6482009226037929, "grad_norm": 2.8120291233062744, "learning_rate": 2.9103402143523467e-05, "loss": 1.2049, "step": 11856 }, { "epoch": 0.6482555954211515, "grad_norm": 2.3639471530914307, "learning_rate": 2.909535921546186e-05, "loss": 1.0973, "step": 11857 }, { "epoch": 0.6483102682385101, "grad_norm": 2.761594533920288, "learning_rate": 2.9087316942846843e-05, "loss": 1.2302, "step": 11858 }, { "epoch": 0.6483649410558688, "grad_norm": 2.862318515777588, "learning_rate": 2.9079275325930566e-05, "loss": 1.0835, "step": 11859 }, { "epoch": 0.6484196138732274, "grad_norm": 2.8021373748779297, "learning_rate": 2.9071234364965138e-05, "loss": 0.8367, "step": 11860 }, { "epoch": 0.648474286690586, "grad_norm": 2.786557674407959, "learning_rate": 2.9063194060202738e-05, "loss": 1.0571, "step": 11861 }, { "epoch": 0.6485289595079446, "grad_norm": 2.6968042850494385, "learning_rate": 2.9055154411895426e-05, "loss": 1.1906, "step": 11862 }, { "epoch": 0.6485836323253032, "grad_norm": 2.5328595638275146, "learning_rate": 2.9047115420295278e-05, "loss": 0.9372, "step": 11863 }, { "epoch": 0.6486383051426619, "grad_norm": 2.5230720043182373, "learning_rate": 2.9039077085654365e-05, "loss": 1.1431, "step": 11864 }, { "epoch": 0.6486929779600205, "grad_norm": 3.7414379119873047, "learning_rate": 2.9031039408224704e-05, "loss": 1.1131, "step": 11865 }, { "epoch": 0.6487476507773792, "grad_norm": 2.9256885051727295, "learning_rate": 2.9023002388258326e-05, "loss": 1.0637, "step": 11866 }, { "epoch": 0.6488023235947378, "grad_norm": 2.3303604125976562, "learning_rate": 2.9014966026007208e-05, "loss": 0.9609, "step": 11867 }, { "epoch": 0.6488569964120964, "grad_norm": 3.119436264038086, "learning_rate": 2.9006930321723324e-05, "loss": 1.1683, "step": 11868 }, { "epoch": 0.648911669229455, "grad_norm": 2.5272321701049805, "learning_rate": 2.8998895275658644e-05, "loss": 0.9542, "step": 11869 }, { "epoch": 0.6489663420468136, "grad_norm": 3.0200343132019043, "learning_rate": 2.8990860888065064e-05, "loss": 1.0578, "step": 11870 }, { "epoch": 0.6490210148641722, "grad_norm": 2.8860955238342285, "learning_rate": 2.8982827159194544e-05, "loss": 1.1034, "step": 11871 }, { "epoch": 0.6490756876815308, "grad_norm": 2.8429627418518066, "learning_rate": 2.8974794089298946e-05, "loss": 1.0648, "step": 11872 }, { "epoch": 0.6491303604988895, "grad_norm": 2.7959299087524414, "learning_rate": 2.8966761678630145e-05, "loss": 1.0683, "step": 11873 }, { "epoch": 0.6491850333162481, "grad_norm": 2.3370625972747803, "learning_rate": 2.8958729927439986e-05, "loss": 1.0691, "step": 11874 }, { "epoch": 0.6492397061336067, "grad_norm": 2.8582262992858887, "learning_rate": 2.8950698835980304e-05, "loss": 0.9627, "step": 11875 }, { "epoch": 0.6492943789509653, "grad_norm": 2.8243248462677, "learning_rate": 2.894266840450291e-05, "loss": 1.0158, "step": 11876 }, { "epoch": 0.6493490517683239, "grad_norm": 2.478778600692749, "learning_rate": 2.893463863325958e-05, "loss": 0.8906, "step": 11877 }, { "epoch": 0.6494037245856825, "grad_norm": 2.3083157539367676, "learning_rate": 2.892660952250208e-05, "loss": 1.0416, "step": 11878 }, { "epoch": 0.6494583974030411, "grad_norm": 2.4515724182128906, "learning_rate": 2.8918581072482164e-05, "loss": 0.915, "step": 11879 }, { "epoch": 0.6495130702203998, "grad_norm": 3.490391492843628, "learning_rate": 2.8910553283451534e-05, "loss": 1.2087, "step": 11880 }, { "epoch": 0.6495677430377584, "grad_norm": 3.1157608032226562, "learning_rate": 2.8902526155661936e-05, "loss": 1.0172, "step": 11881 }, { "epoch": 0.649622415855117, "grad_norm": 2.1082589626312256, "learning_rate": 2.8894499689365028e-05, "loss": 0.9289, "step": 11882 }, { "epoch": 0.6496770886724756, "grad_norm": 2.3461015224456787, "learning_rate": 2.888647388481248e-05, "loss": 1.0676, "step": 11883 }, { "epoch": 0.6497317614898342, "grad_norm": 2.0497219562530518, "learning_rate": 2.887844874225593e-05, "loss": 1.037, "step": 11884 }, { "epoch": 0.6497864343071929, "grad_norm": 2.8189709186553955, "learning_rate": 2.8870424261947e-05, "loss": 1.0516, "step": 11885 }, { "epoch": 0.6498411071245516, "grad_norm": 3.2416064739227295, "learning_rate": 2.8862400444137284e-05, "loss": 1.0603, "step": 11886 }, { "epoch": 0.6498957799419102, "grad_norm": 2.2156474590301514, "learning_rate": 2.8854377289078372e-05, "loss": 1.0861, "step": 11887 }, { "epoch": 0.6499504527592688, "grad_norm": 3.514875888824463, "learning_rate": 2.8846354797021825e-05, "loss": 1.035, "step": 11888 }, { "epoch": 0.6500051255766274, "grad_norm": 2.4415981769561768, "learning_rate": 2.8838332968219146e-05, "loss": 0.9657, "step": 11889 }, { "epoch": 0.650059798393986, "grad_norm": 2.397490978240967, "learning_rate": 2.8830311802921905e-05, "loss": 0.9376, "step": 11890 }, { "epoch": 0.6501144712113446, "grad_norm": 2.744018793106079, "learning_rate": 2.8822291301381575e-05, "loss": 1.0165, "step": 11891 }, { "epoch": 0.6501691440287032, "grad_norm": 2.5941479206085205, "learning_rate": 2.8814271463849628e-05, "loss": 1.0189, "step": 11892 }, { "epoch": 0.6502238168460619, "grad_norm": 2.2673468589782715, "learning_rate": 2.880625229057753e-05, "loss": 1.0288, "step": 11893 }, { "epoch": 0.6502784896634205, "grad_norm": 3.449195384979248, "learning_rate": 2.8798233781816698e-05, "loss": 1.0714, "step": 11894 }, { "epoch": 0.6503331624807791, "grad_norm": 2.569705009460449, "learning_rate": 2.879021593781856e-05, "loss": 1.0303, "step": 11895 }, { "epoch": 0.6503878352981377, "grad_norm": 2.5399363040924072, "learning_rate": 2.8782198758834505e-05, "loss": 1.0376, "step": 11896 }, { "epoch": 0.6504425081154963, "grad_norm": 3.055917263031006, "learning_rate": 2.87741822451159e-05, "loss": 1.077, "step": 11897 }, { "epoch": 0.6504971809328549, "grad_norm": 2.2601661682128906, "learning_rate": 2.8766166396914102e-05, "loss": 0.7071, "step": 11898 }, { "epoch": 0.6505518537502135, "grad_norm": 2.0013880729675293, "learning_rate": 2.8758151214480432e-05, "loss": 0.9213, "step": 11899 }, { "epoch": 0.6506065265675722, "grad_norm": 2.2727746963500977, "learning_rate": 2.8750136698066187e-05, "loss": 0.8897, "step": 11900 }, { "epoch": 0.6506611993849308, "grad_norm": 2.790989875793457, "learning_rate": 2.87421228479227e-05, "loss": 1.0918, "step": 11901 }, { "epoch": 0.6507158722022894, "grad_norm": 2.1847362518310547, "learning_rate": 2.87341096643012e-05, "loss": 0.8375, "step": 11902 }, { "epoch": 0.650770545019648, "grad_norm": 2.3546414375305176, "learning_rate": 2.8726097147452947e-05, "loss": 1.0654, "step": 11903 }, { "epoch": 0.6508252178370066, "grad_norm": 2.5051746368408203, "learning_rate": 2.871808529762917e-05, "loss": 1.0795, "step": 11904 }, { "epoch": 0.6508798906543652, "grad_norm": 3.6273531913757324, "learning_rate": 2.8710074115081058e-05, "loss": 1.1534, "step": 11905 }, { "epoch": 0.6509345634717238, "grad_norm": 3.505453586578369, "learning_rate": 2.870206360005981e-05, "loss": 0.9854, "step": 11906 }, { "epoch": 0.6509892362890826, "grad_norm": 2.2440550327301025, "learning_rate": 2.869405375281658e-05, "loss": 0.9584, "step": 11907 }, { "epoch": 0.6510439091064412, "grad_norm": 2.839899778366089, "learning_rate": 2.8686044573602512e-05, "loss": 1.1725, "step": 11908 }, { "epoch": 0.6510985819237998, "grad_norm": 2.5473294258117676, "learning_rate": 2.8678036062668723e-05, "loss": 1.1316, "step": 11909 }, { "epoch": 0.6511532547411584, "grad_norm": 2.5849688053131104, "learning_rate": 2.8670028220266322e-05, "loss": 0.8484, "step": 11910 }, { "epoch": 0.651207927558517, "grad_norm": 2.1185874938964844, "learning_rate": 2.866202104664638e-05, "loss": 0.9285, "step": 11911 }, { "epoch": 0.6512626003758756, "grad_norm": 2.891080856323242, "learning_rate": 2.865401454205996e-05, "loss": 1.0832, "step": 11912 }, { "epoch": 0.6513172731932343, "grad_norm": 2.5014760494232178, "learning_rate": 2.8646008706758076e-05, "loss": 0.7816, "step": 11913 }, { "epoch": 0.6513719460105929, "grad_norm": 2.9206414222717285, "learning_rate": 2.8638003540991775e-05, "loss": 0.8839, "step": 11914 }, { "epoch": 0.6514266188279515, "grad_norm": 2.335580348968506, "learning_rate": 2.8629999045012052e-05, "loss": 0.9494, "step": 11915 }, { "epoch": 0.6514812916453101, "grad_norm": 3.03769588470459, "learning_rate": 2.8621995219069864e-05, "loss": 0.897, "step": 11916 }, { "epoch": 0.6515359644626687, "grad_norm": 2.3703083992004395, "learning_rate": 2.8613992063416173e-05, "loss": 0.9246, "step": 11917 }, { "epoch": 0.6515906372800273, "grad_norm": 2.204996347427368, "learning_rate": 2.8605989578301906e-05, "loss": 0.8947, "step": 11918 }, { "epoch": 0.6516453100973859, "grad_norm": 2.4006102085113525, "learning_rate": 2.8597987763977973e-05, "loss": 0.8725, "step": 11919 }, { "epoch": 0.6516999829147446, "grad_norm": 2.7192862033843994, "learning_rate": 2.858998662069527e-05, "loss": 0.8428, "step": 11920 }, { "epoch": 0.6517546557321032, "grad_norm": 2.215757131576538, "learning_rate": 2.858198614870466e-05, "loss": 0.8422, "step": 11921 }, { "epoch": 0.6518093285494618, "grad_norm": 2.124504327774048, "learning_rate": 2.8573986348256993e-05, "loss": 0.8858, "step": 11922 }, { "epoch": 0.6518640013668204, "grad_norm": 4.021902084350586, "learning_rate": 2.8565987219603095e-05, "loss": 1.1549, "step": 11923 }, { "epoch": 0.651918674184179, "grad_norm": 3.1667189598083496, "learning_rate": 2.855798876299377e-05, "loss": 1.131, "step": 11924 }, { "epoch": 0.6519733470015376, "grad_norm": 2.521461248397827, "learning_rate": 2.8549990978679813e-05, "loss": 1.1654, "step": 11925 }, { "epoch": 0.6520280198188962, "grad_norm": 2.5703723430633545, "learning_rate": 2.8541993866911953e-05, "loss": 0.961, "step": 11926 }, { "epoch": 0.652082692636255, "grad_norm": 2.864370584487915, "learning_rate": 2.8533997427940984e-05, "loss": 0.9883, "step": 11927 }, { "epoch": 0.6521373654536136, "grad_norm": 2.4138431549072266, "learning_rate": 2.8526001662017594e-05, "loss": 0.9439, "step": 11928 }, { "epoch": 0.6521920382709722, "grad_norm": 4.311678409576416, "learning_rate": 2.8518006569392498e-05, "loss": 1.2174, "step": 11929 }, { "epoch": 0.6522467110883308, "grad_norm": 2.750365734100342, "learning_rate": 2.8510012150316363e-05, "loss": 0.9039, "step": 11930 }, { "epoch": 0.6523013839056894, "grad_norm": 2.6508290767669678, "learning_rate": 2.8502018405039854e-05, "loss": 1.0552, "step": 11931 }, { "epoch": 0.652356056723048, "grad_norm": 2.4251458644866943, "learning_rate": 2.84940253338136e-05, "loss": 0.9171, "step": 11932 }, { "epoch": 0.6524107295404066, "grad_norm": 3.6402440071105957, "learning_rate": 2.848603293688823e-05, "loss": 1.1367, "step": 11933 }, { "epoch": 0.6524654023577653, "grad_norm": 2.585844039916992, "learning_rate": 2.8478041214514333e-05, "loss": 0.8628, "step": 11934 }, { "epoch": 0.6525200751751239, "grad_norm": 3.3080410957336426, "learning_rate": 2.8470050166942476e-05, "loss": 1.1295, "step": 11935 }, { "epoch": 0.6525747479924825, "grad_norm": 3.293436050415039, "learning_rate": 2.8462059794423217e-05, "loss": 1.1454, "step": 11936 }, { "epoch": 0.6526294208098411, "grad_norm": 2.6096556186676025, "learning_rate": 2.8454070097207087e-05, "loss": 0.9814, "step": 11937 }, { "epoch": 0.6526840936271997, "grad_norm": 2.6260721683502197, "learning_rate": 2.8446081075544595e-05, "loss": 1.0011, "step": 11938 }, { "epoch": 0.6527387664445583, "grad_norm": 2.8307971954345703, "learning_rate": 2.8438092729686205e-05, "loss": 1.0575, "step": 11939 }, { "epoch": 0.652793439261917, "grad_norm": 3.4382827281951904, "learning_rate": 2.843010505988244e-05, "loss": 0.9267, "step": 11940 }, { "epoch": 0.6528481120792756, "grad_norm": 2.518480062484741, "learning_rate": 2.8422118066383706e-05, "loss": 1.0677, "step": 11941 }, { "epoch": 0.6529027848966342, "grad_norm": 2.228278636932373, "learning_rate": 2.841413174944044e-05, "loss": 0.9306, "step": 11942 }, { "epoch": 0.6529574577139928, "grad_norm": 2.926370859146118, "learning_rate": 2.8406146109303044e-05, "loss": 0.9585, "step": 11943 }, { "epoch": 0.6530121305313514, "grad_norm": 2.448106527328491, "learning_rate": 2.8398161146221904e-05, "loss": 0.8234, "step": 11944 }, { "epoch": 0.65306680334871, "grad_norm": 2.609927177429199, "learning_rate": 2.839017686044737e-05, "loss": 0.9836, "step": 11945 }, { "epoch": 0.6531214761660686, "grad_norm": 2.49892520904541, "learning_rate": 2.8382193252229795e-05, "loss": 0.7829, "step": 11946 }, { "epoch": 0.6531761489834274, "grad_norm": 3.116260290145874, "learning_rate": 2.837421032181949e-05, "loss": 0.9883, "step": 11947 }, { "epoch": 0.653230821800786, "grad_norm": 2.5571537017822266, "learning_rate": 2.8366228069466737e-05, "loss": 0.9661, "step": 11948 }, { "epoch": 0.6532854946181446, "grad_norm": 2.6457722187042236, "learning_rate": 2.8358246495421854e-05, "loss": 1.0293, "step": 11949 }, { "epoch": 0.6533401674355032, "grad_norm": 2.619002103805542, "learning_rate": 2.8350265599935066e-05, "loss": 1.087, "step": 11950 }, { "epoch": 0.6533948402528618, "grad_norm": 2.8543050289154053, "learning_rate": 2.8342285383256622e-05, "loss": 0.9367, "step": 11951 }, { "epoch": 0.6534495130702204, "grad_norm": 2.460864543914795, "learning_rate": 2.8334305845636723e-05, "loss": 0.9662, "step": 11952 }, { "epoch": 0.653504185887579, "grad_norm": 2.5918846130371094, "learning_rate": 2.832632698732557e-05, "loss": 0.9453, "step": 11953 }, { "epoch": 0.6535588587049377, "grad_norm": 2.3417160511016846, "learning_rate": 2.8318348808573326e-05, "loss": 0.9028, "step": 11954 }, { "epoch": 0.6536135315222963, "grad_norm": 2.349461317062378, "learning_rate": 2.8310371309630136e-05, "loss": 0.9666, "step": 11955 }, { "epoch": 0.6536682043396549, "grad_norm": 2.364762544631958, "learning_rate": 2.830239449074613e-05, "loss": 0.9355, "step": 11956 }, { "epoch": 0.6537228771570135, "grad_norm": 2.616438388824463, "learning_rate": 2.8294418352171424e-05, "loss": 1.0073, "step": 11957 }, { "epoch": 0.6537775499743721, "grad_norm": 2.786741256713867, "learning_rate": 2.8286442894156072e-05, "loss": 1.1825, "step": 11958 }, { "epoch": 0.6538322227917307, "grad_norm": 3.3672618865966797, "learning_rate": 2.8278468116950184e-05, "loss": 1.2047, "step": 11959 }, { "epoch": 0.6538868956090893, "grad_norm": 2.690314531326294, "learning_rate": 2.8270494020803783e-05, "loss": 1.2166, "step": 11960 }, { "epoch": 0.653941568426448, "grad_norm": 2.145333766937256, "learning_rate": 2.826252060596688e-05, "loss": 0.9697, "step": 11961 }, { "epoch": 0.6539962412438066, "grad_norm": 2.664067506790161, "learning_rate": 2.825454787268948e-05, "loss": 0.9089, "step": 11962 }, { "epoch": 0.6540509140611652, "grad_norm": 3.0716307163238525, "learning_rate": 2.8246575821221566e-05, "loss": 1.0628, "step": 11963 }, { "epoch": 0.6541055868785238, "grad_norm": 2.1962971687316895, "learning_rate": 2.823860445181308e-05, "loss": 0.9502, "step": 11964 }, { "epoch": 0.6541602596958824, "grad_norm": 2.6897435188293457, "learning_rate": 2.8230633764713976e-05, "loss": 0.9798, "step": 11965 }, { "epoch": 0.654214932513241, "grad_norm": 2.2586138248443604, "learning_rate": 2.8222663760174163e-05, "loss": 1.0694, "step": 11966 }, { "epoch": 0.6542696053305997, "grad_norm": 2.4476726055145264, "learning_rate": 2.821469443844352e-05, "loss": 1.0863, "step": 11967 }, { "epoch": 0.6543242781479583, "grad_norm": 3.0136966705322266, "learning_rate": 2.820672579977191e-05, "loss": 1.1903, "step": 11968 }, { "epoch": 0.654378950965317, "grad_norm": 3.0336620807647705, "learning_rate": 2.8198757844409223e-05, "loss": 1.1898, "step": 11969 }, { "epoch": 0.6544336237826756, "grad_norm": 2.9064483642578125, "learning_rate": 2.8190790572605264e-05, "loss": 1.0105, "step": 11970 }, { "epoch": 0.6544882966000342, "grad_norm": 2.939809799194336, "learning_rate": 2.818282398460984e-05, "loss": 0.9205, "step": 11971 }, { "epoch": 0.6545429694173928, "grad_norm": 2.1249804496765137, "learning_rate": 2.8174858080672735e-05, "loss": 0.8789, "step": 11972 }, { "epoch": 0.6545976422347514, "grad_norm": 2.550508975982666, "learning_rate": 2.8166892861043714e-05, "loss": 0.8863, "step": 11973 }, { "epoch": 0.6546523150521101, "grad_norm": 2.9235196113586426, "learning_rate": 2.815892832597252e-05, "loss": 1.1077, "step": 11974 }, { "epoch": 0.6547069878694687, "grad_norm": 2.4314823150634766, "learning_rate": 2.8150964475708875e-05, "loss": 1.1219, "step": 11975 }, { "epoch": 0.6547616606868273, "grad_norm": 1.9918862581253052, "learning_rate": 2.8143001310502482e-05, "loss": 0.9001, "step": 11976 }, { "epoch": 0.6548163335041859, "grad_norm": 2.7005667686462402, "learning_rate": 2.813503883060301e-05, "loss": 1.008, "step": 11977 }, { "epoch": 0.6548710063215445, "grad_norm": 2.822535991668701, "learning_rate": 2.8127077036260096e-05, "loss": 1.1118, "step": 11978 }, { "epoch": 0.6549256791389031, "grad_norm": 2.694166660308838, "learning_rate": 2.8119115927723428e-05, "loss": 1.0311, "step": 11979 }, { "epoch": 0.6549803519562617, "grad_norm": 2.247936487197876, "learning_rate": 2.8111155505242583e-05, "loss": 0.8621, "step": 11980 }, { "epoch": 0.6550350247736204, "grad_norm": 2.6395046710968018, "learning_rate": 2.8103195769067165e-05, "loss": 1.1166, "step": 11981 }, { "epoch": 0.655089697590979, "grad_norm": 2.6850337982177734, "learning_rate": 2.809523671944674e-05, "loss": 0.9077, "step": 11982 }, { "epoch": 0.6551443704083376, "grad_norm": 3.1475813388824463, "learning_rate": 2.8087278356630853e-05, "loss": 0.9636, "step": 11983 }, { "epoch": 0.6551990432256962, "grad_norm": 4.21506404876709, "learning_rate": 2.8079320680869036e-05, "loss": 1.029, "step": 11984 }, { "epoch": 0.6552537160430548, "grad_norm": 1.8831509351730347, "learning_rate": 2.8071363692410802e-05, "loss": 0.729, "step": 11985 }, { "epoch": 0.6553083888604134, "grad_norm": 3.778463125228882, "learning_rate": 2.806340739150562e-05, "loss": 1.1065, "step": 11986 }, { "epoch": 0.655363061677772, "grad_norm": 2.665227174758911, "learning_rate": 2.8055451778402965e-05, "loss": 0.8226, "step": 11987 }, { "epoch": 0.6554177344951307, "grad_norm": 2.4763095378875732, "learning_rate": 2.804749685335225e-05, "loss": 1.1603, "step": 11988 }, { "epoch": 0.6554724073124893, "grad_norm": 2.3143470287323, "learning_rate": 2.8039542616602943e-05, "loss": 0.8659, "step": 11989 }, { "epoch": 0.655527080129848, "grad_norm": 3.225654125213623, "learning_rate": 2.8031589068404413e-05, "loss": 1.062, "step": 11990 }, { "epoch": 0.6555817529472066, "grad_norm": 2.552877187728882, "learning_rate": 2.8023636209006043e-05, "loss": 1.0084, "step": 11991 }, { "epoch": 0.6556364257645652, "grad_norm": 3.1238486766815186, "learning_rate": 2.8015684038657187e-05, "loss": 1.1204, "step": 11992 }, { "epoch": 0.6556910985819238, "grad_norm": 2.6871209144592285, "learning_rate": 2.800773255760718e-05, "loss": 1.1356, "step": 11993 }, { "epoch": 0.6557457713992825, "grad_norm": 2.4873530864715576, "learning_rate": 2.7999781766105326e-05, "loss": 1.1151, "step": 11994 }, { "epoch": 0.6558004442166411, "grad_norm": 3.1219124794006348, "learning_rate": 2.799183166440092e-05, "loss": 1.0845, "step": 11995 }, { "epoch": 0.6558551170339997, "grad_norm": 3.0293281078338623, "learning_rate": 2.7983882252743233e-05, "loss": 1.1603, "step": 11996 }, { "epoch": 0.6559097898513583, "grad_norm": 2.94466233253479, "learning_rate": 2.797593353138149e-05, "loss": 1.031, "step": 11997 }, { "epoch": 0.6559644626687169, "grad_norm": 2.6921699047088623, "learning_rate": 2.796798550056495e-05, "loss": 0.8974, "step": 11998 }, { "epoch": 0.6560191354860755, "grad_norm": 2.478196382522583, "learning_rate": 2.7960038160542807e-05, "loss": 0.9585, "step": 11999 }, { "epoch": 0.6560738083034341, "grad_norm": 2.0191218852996826, "learning_rate": 2.795209151156424e-05, "loss": 0.933, "step": 12000 }, { "epoch": 0.6561284811207928, "grad_norm": 2.4098939895629883, "learning_rate": 2.7944145553878397e-05, "loss": 0.9698, "step": 12001 }, { "epoch": 0.6561831539381514, "grad_norm": 2.72658109664917, "learning_rate": 2.7936200287734438e-05, "loss": 1.0375, "step": 12002 }, { "epoch": 0.65623782675551, "grad_norm": 2.4217076301574707, "learning_rate": 2.7928255713381457e-05, "loss": 1.1336, "step": 12003 }, { "epoch": 0.6562924995728686, "grad_norm": 2.593467950820923, "learning_rate": 2.792031183106857e-05, "loss": 1.1034, "step": 12004 }, { "epoch": 0.6563471723902272, "grad_norm": 2.7061479091644287, "learning_rate": 2.7912368641044834e-05, "loss": 1.2256, "step": 12005 }, { "epoch": 0.6564018452075858, "grad_norm": 2.3508543968200684, "learning_rate": 2.7904426143559316e-05, "loss": 1.0598, "step": 12006 }, { "epoch": 0.6564565180249444, "grad_norm": 2.780989408493042, "learning_rate": 2.7896484338861005e-05, "loss": 0.8559, "step": 12007 }, { "epoch": 0.6565111908423031, "grad_norm": 2.6613612174987793, "learning_rate": 2.788854322719897e-05, "loss": 1.0788, "step": 12008 }, { "epoch": 0.6565658636596617, "grad_norm": 2.7635114192962646, "learning_rate": 2.7880602808822164e-05, "loss": 1.1979, "step": 12009 }, { "epoch": 0.6566205364770203, "grad_norm": 3.090155601501465, "learning_rate": 2.7872663083979566e-05, "loss": 0.9077, "step": 12010 }, { "epoch": 0.656675209294379, "grad_norm": 2.552290439605713, "learning_rate": 2.7864724052920105e-05, "loss": 0.9615, "step": 12011 }, { "epoch": 0.6567298821117376, "grad_norm": 2.8730852603912354, "learning_rate": 2.7856785715892707e-05, "loss": 1.0999, "step": 12012 }, { "epoch": 0.6567845549290962, "grad_norm": 2.62611722946167, "learning_rate": 2.7848848073146274e-05, "loss": 0.8441, "step": 12013 }, { "epoch": 0.6568392277464548, "grad_norm": 2.5540883541107178, "learning_rate": 2.7840911124929682e-05, "loss": 0.9661, "step": 12014 }, { "epoch": 0.6568939005638135, "grad_norm": 3.1450297832489014, "learning_rate": 2.7832974871491784e-05, "loss": 0.9734, "step": 12015 }, { "epoch": 0.6569485733811721, "grad_norm": 3.450895309448242, "learning_rate": 2.7825039313081425e-05, "loss": 0.9297, "step": 12016 }, { "epoch": 0.6570032461985307, "grad_norm": 2.8878324031829834, "learning_rate": 2.7817104449947377e-05, "loss": 0.9843, "step": 12017 }, { "epoch": 0.6570579190158893, "grad_norm": 3.5556352138519287, "learning_rate": 2.7809170282338493e-05, "loss": 1.1193, "step": 12018 }, { "epoch": 0.6571125918332479, "grad_norm": 2.229369878768921, "learning_rate": 2.7801236810503505e-05, "loss": 0.9358, "step": 12019 }, { "epoch": 0.6571672646506065, "grad_norm": 2.5675065517425537, "learning_rate": 2.7793304034691174e-05, "loss": 0.9229, "step": 12020 }, { "epoch": 0.6572219374679652, "grad_norm": 2.987492561340332, "learning_rate": 2.778537195515022e-05, "loss": 0.8617, "step": 12021 }, { "epoch": 0.6572766102853238, "grad_norm": 1.9651315212249756, "learning_rate": 2.777744057212933e-05, "loss": 0.8615, "step": 12022 }, { "epoch": 0.6573312831026824, "grad_norm": 2.4593772888183594, "learning_rate": 2.7769509885877214e-05, "loss": 1.0594, "step": 12023 }, { "epoch": 0.657385955920041, "grad_norm": 2.3910698890686035, "learning_rate": 2.776157989664252e-05, "loss": 0.8942, "step": 12024 }, { "epoch": 0.6574406287373996, "grad_norm": 2.8305933475494385, "learning_rate": 2.7753650604673875e-05, "loss": 1.1161, "step": 12025 }, { "epoch": 0.6574953015547582, "grad_norm": 2.41095232963562, "learning_rate": 2.7745722010219904e-05, "loss": 0.9759, "step": 12026 }, { "epoch": 0.6575499743721168, "grad_norm": 2.7499516010284424, "learning_rate": 2.7737794113529182e-05, "loss": 0.9928, "step": 12027 }, { "epoch": 0.6576046471894755, "grad_norm": 2.424713611602783, "learning_rate": 2.7729866914850322e-05, "loss": 0.9355, "step": 12028 }, { "epoch": 0.6576593200068341, "grad_norm": 2.6454930305480957, "learning_rate": 2.772194041443185e-05, "loss": 1.301, "step": 12029 }, { "epoch": 0.6577139928241927, "grad_norm": 2.72678804397583, "learning_rate": 2.77140146125223e-05, "loss": 0.8378, "step": 12030 }, { "epoch": 0.6577686656415513, "grad_norm": 2.318696975708008, "learning_rate": 2.770608950937017e-05, "loss": 1.008, "step": 12031 }, { "epoch": 0.65782333845891, "grad_norm": 2.4810941219329834, "learning_rate": 2.7698165105223955e-05, "loss": 1.0759, "step": 12032 }, { "epoch": 0.6578780112762685, "grad_norm": 2.936530828475952, "learning_rate": 2.7690241400332108e-05, "loss": 1.0742, "step": 12033 }, { "epoch": 0.6579326840936272, "grad_norm": 2.458378314971924, "learning_rate": 2.768231839494308e-05, "loss": 1.0635, "step": 12034 }, { "epoch": 0.6579873569109859, "grad_norm": 3.123067617416382, "learning_rate": 2.7674396089305275e-05, "loss": 1.1691, "step": 12035 }, { "epoch": 0.6580420297283445, "grad_norm": 2.538848876953125, "learning_rate": 2.766647448366711e-05, "loss": 1.086, "step": 12036 }, { "epoch": 0.6580967025457031, "grad_norm": 2.598062038421631, "learning_rate": 2.7658553578276926e-05, "loss": 0.9453, "step": 12037 }, { "epoch": 0.6581513753630617, "grad_norm": 2.6212241649627686, "learning_rate": 2.7650633373383117e-05, "loss": 0.907, "step": 12038 }, { "epoch": 0.6582060481804203, "grad_norm": 2.5507395267486572, "learning_rate": 2.7642713869233994e-05, "loss": 1.0425, "step": 12039 }, { "epoch": 0.6582607209977789, "grad_norm": 7.072768211364746, "learning_rate": 2.763479506607787e-05, "loss": 0.9559, "step": 12040 }, { "epoch": 0.6583153938151375, "grad_norm": 2.8966710567474365, "learning_rate": 2.7626876964163027e-05, "loss": 1.0184, "step": 12041 }, { "epoch": 0.6583700666324962, "grad_norm": 2.9327433109283447, "learning_rate": 2.761895956373774e-05, "loss": 1.1933, "step": 12042 }, { "epoch": 0.6584247394498548, "grad_norm": 2.555039167404175, "learning_rate": 2.761104286505024e-05, "loss": 0.949, "step": 12043 }, { "epoch": 0.6584794122672134, "grad_norm": 2.6362216472625732, "learning_rate": 2.7603126868348756e-05, "loss": 0.9782, "step": 12044 }, { "epoch": 0.658534085084572, "grad_norm": 2.8005173206329346, "learning_rate": 2.7595211573881484e-05, "loss": 0.929, "step": 12045 }, { "epoch": 0.6585887579019306, "grad_norm": 3.312382221221924, "learning_rate": 2.7587296981896583e-05, "loss": 0.9936, "step": 12046 }, { "epoch": 0.6586434307192892, "grad_norm": 3.977504253387451, "learning_rate": 2.7579383092642242e-05, "loss": 1.2432, "step": 12047 }, { "epoch": 0.6586981035366479, "grad_norm": 2.809303045272827, "learning_rate": 2.7571469906366586e-05, "loss": 1.1046, "step": 12048 }, { "epoch": 0.6587527763540065, "grad_norm": 3.5577104091644287, "learning_rate": 2.7563557423317716e-05, "loss": 1.0702, "step": 12049 }, { "epoch": 0.6588074491713651, "grad_norm": 2.8248403072357178, "learning_rate": 2.7555645643743723e-05, "loss": 1.0101, "step": 12050 }, { "epoch": 0.6588621219887237, "grad_norm": 2.538443088531494, "learning_rate": 2.7547734567892674e-05, "loss": 0.946, "step": 12051 }, { "epoch": 0.6589167948060823, "grad_norm": 3.0676465034484863, "learning_rate": 2.7539824196012615e-05, "loss": 1.0355, "step": 12052 }, { "epoch": 0.6589714676234409, "grad_norm": 3.108776807785034, "learning_rate": 2.7531914528351564e-05, "loss": 1.171, "step": 12053 }, { "epoch": 0.6590261404407995, "grad_norm": 2.950096368789673, "learning_rate": 2.7524005565157536e-05, "loss": 0.9463, "step": 12054 }, { "epoch": 0.6590808132581583, "grad_norm": 2.996330976486206, "learning_rate": 2.751609730667849e-05, "loss": 1.0071, "step": 12055 }, { "epoch": 0.6591354860755169, "grad_norm": 2.898618221282959, "learning_rate": 2.7508189753162376e-05, "loss": 0.9788, "step": 12056 }, { "epoch": 0.6591901588928755, "grad_norm": 2.387190341949463, "learning_rate": 2.7500282904857165e-05, "loss": 1.1891, "step": 12057 }, { "epoch": 0.6592448317102341, "grad_norm": 3.0892927646636963, "learning_rate": 2.7492376762010747e-05, "loss": 0.9211, "step": 12058 }, { "epoch": 0.6592995045275927, "grad_norm": 2.9327166080474854, "learning_rate": 2.7484471324871015e-05, "loss": 0.9855, "step": 12059 }, { "epoch": 0.6593541773449513, "grad_norm": 2.880699396133423, "learning_rate": 2.7476566593685837e-05, "loss": 0.9361, "step": 12060 }, { "epoch": 0.6594088501623099, "grad_norm": 2.748349905014038, "learning_rate": 2.7468662568703053e-05, "loss": 1.0967, "step": 12061 }, { "epoch": 0.6594635229796686, "grad_norm": 2.174586057662964, "learning_rate": 2.7460759250170494e-05, "loss": 0.8606, "step": 12062 }, { "epoch": 0.6595181957970272, "grad_norm": 2.630542039871216, "learning_rate": 2.7452856638335954e-05, "loss": 0.9742, "step": 12063 }, { "epoch": 0.6595728686143858, "grad_norm": 2.3948209285736084, "learning_rate": 2.7444954733447225e-05, "loss": 0.8878, "step": 12064 }, { "epoch": 0.6596275414317444, "grad_norm": 3.231682300567627, "learning_rate": 2.743705353575205e-05, "loss": 1.0738, "step": 12065 }, { "epoch": 0.659682214249103, "grad_norm": 2.922814130783081, "learning_rate": 2.7429153045498158e-05, "loss": 1.1662, "step": 12066 }, { "epoch": 0.6597368870664616, "grad_norm": 2.8751633167266846, "learning_rate": 2.742125326293329e-05, "loss": 1.0588, "step": 12067 }, { "epoch": 0.6597915598838202, "grad_norm": 2.3623228073120117, "learning_rate": 2.741335418830512e-05, "loss": 1.0074, "step": 12068 }, { "epoch": 0.6598462327011789, "grad_norm": 2.605363368988037, "learning_rate": 2.7405455821861314e-05, "loss": 1.0098, "step": 12069 }, { "epoch": 0.6599009055185375, "grad_norm": 2.471242904663086, "learning_rate": 2.7397558163849523e-05, "loss": 0.8492, "step": 12070 }, { "epoch": 0.6599555783358961, "grad_norm": 3.039069652557373, "learning_rate": 2.7389661214517382e-05, "loss": 1.0091, "step": 12071 }, { "epoch": 0.6600102511532547, "grad_norm": 2.7059738636016846, "learning_rate": 2.7381764974112468e-05, "loss": 1.0913, "step": 12072 }, { "epoch": 0.6600649239706133, "grad_norm": 2.0858566761016846, "learning_rate": 2.7373869442882382e-05, "loss": 0.8207, "step": 12073 }, { "epoch": 0.6601195967879719, "grad_norm": 2.633859634399414, "learning_rate": 2.7365974621074665e-05, "loss": 1.1012, "step": 12074 }, { "epoch": 0.6601742696053307, "grad_norm": 2.6317455768585205, "learning_rate": 2.7358080508936867e-05, "loss": 0.9937, "step": 12075 }, { "epoch": 0.6602289424226893, "grad_norm": 3.7383968830108643, "learning_rate": 2.7350187106716474e-05, "loss": 0.7088, "step": 12076 }, { "epoch": 0.6602836152400479, "grad_norm": 2.5213239192962646, "learning_rate": 2.734229441466102e-05, "loss": 1.1162, "step": 12077 }, { "epoch": 0.6603382880574065, "grad_norm": 2.390933036804199, "learning_rate": 2.7334402433017936e-05, "loss": 0.8893, "step": 12078 }, { "epoch": 0.6603929608747651, "grad_norm": 3.4380483627319336, "learning_rate": 2.7326511162034696e-05, "loss": 1.0632, "step": 12079 }, { "epoch": 0.6604476336921237, "grad_norm": 2.199533462524414, "learning_rate": 2.7318620601958707e-05, "loss": 1.1076, "step": 12080 }, { "epoch": 0.6605023065094823, "grad_norm": 2.792722702026367, "learning_rate": 2.7310730753037374e-05, "loss": 1.0147, "step": 12081 }, { "epoch": 0.660556979326841, "grad_norm": 2.704129695892334, "learning_rate": 2.730284161551807e-05, "loss": 1.1319, "step": 12082 }, { "epoch": 0.6606116521441996, "grad_norm": 2.0242812633514404, "learning_rate": 2.7294953189648163e-05, "loss": 0.8909, "step": 12083 }, { "epoch": 0.6606663249615582, "grad_norm": 2.5586001873016357, "learning_rate": 2.728706547567499e-05, "loss": 1.1281, "step": 12084 }, { "epoch": 0.6607209977789168, "grad_norm": 3.057441473007202, "learning_rate": 2.7279178473845844e-05, "loss": 0.8871, "step": 12085 }, { "epoch": 0.6607756705962754, "grad_norm": 2.67756724357605, "learning_rate": 2.7271292184408037e-05, "loss": 0.9597, "step": 12086 }, { "epoch": 0.660830343413634, "grad_norm": 3.756412982940674, "learning_rate": 2.72634066076088e-05, "loss": 1.0166, "step": 12087 }, { "epoch": 0.6608850162309926, "grad_norm": 2.811707019805908, "learning_rate": 2.7255521743695423e-05, "loss": 0.8527, "step": 12088 }, { "epoch": 0.6609396890483513, "grad_norm": 2.4466354846954346, "learning_rate": 2.7247637592915116e-05, "loss": 1.0934, "step": 12089 }, { "epoch": 0.6609943618657099, "grad_norm": 2.680156707763672, "learning_rate": 2.7239754155515073e-05, "loss": 1.2679, "step": 12090 }, { "epoch": 0.6610490346830685, "grad_norm": 3.1350667476654053, "learning_rate": 2.723187143174247e-05, "loss": 1.0671, "step": 12091 }, { "epoch": 0.6611037075004271, "grad_norm": 3.1855430603027344, "learning_rate": 2.7223989421844477e-05, "loss": 0.9244, "step": 12092 }, { "epoch": 0.6611583803177857, "grad_norm": 2.7133376598358154, "learning_rate": 2.7216108126068207e-05, "loss": 0.8857, "step": 12093 }, { "epoch": 0.6612130531351443, "grad_norm": 2.2973275184631348, "learning_rate": 2.7208227544660785e-05, "loss": 0.7806, "step": 12094 }, { "epoch": 0.6612677259525029, "grad_norm": 2.4679486751556396, "learning_rate": 2.7200347677869297e-05, "loss": 0.8044, "step": 12095 }, { "epoch": 0.6613223987698617, "grad_norm": 2.951932907104492, "learning_rate": 2.7192468525940806e-05, "loss": 1.1311, "step": 12096 }, { "epoch": 0.6613770715872203, "grad_norm": 3.063937187194824, "learning_rate": 2.7184590089122354e-05, "loss": 0.9392, "step": 12097 }, { "epoch": 0.6614317444045789, "grad_norm": 2.4703798294067383, "learning_rate": 2.7176712367660973e-05, "loss": 0.7768, "step": 12098 }, { "epoch": 0.6614864172219375, "grad_norm": 2.3409719467163086, "learning_rate": 2.7168835361803658e-05, "loss": 1.0659, "step": 12099 }, { "epoch": 0.6615410900392961, "grad_norm": 2.5726468563079834, "learning_rate": 2.7160959071797353e-05, "loss": 1.1958, "step": 12100 }, { "epoch": 0.6615957628566547, "grad_norm": 2.7275593280792236, "learning_rate": 2.7153083497889066e-05, "loss": 1.1003, "step": 12101 }, { "epoch": 0.6616504356740134, "grad_norm": 3.8242874145507812, "learning_rate": 2.7145208640325708e-05, "loss": 1.0759, "step": 12102 }, { "epoch": 0.661705108491372, "grad_norm": 2.743986129760742, "learning_rate": 2.7137334499354184e-05, "loss": 0.9255, "step": 12103 }, { "epoch": 0.6617597813087306, "grad_norm": 2.3044209480285645, "learning_rate": 2.712946107522138e-05, "loss": 1.0386, "step": 12104 }, { "epoch": 0.6618144541260892, "grad_norm": 2.540036201477051, "learning_rate": 2.7121588368174165e-05, "loss": 0.9224, "step": 12105 }, { "epoch": 0.6618691269434478, "grad_norm": 2.3385140895843506, "learning_rate": 2.7113716378459374e-05, "loss": 1.033, "step": 12106 }, { "epoch": 0.6619237997608064, "grad_norm": 2.58774995803833, "learning_rate": 2.7105845106323835e-05, "loss": 0.8244, "step": 12107 }, { "epoch": 0.661978472578165, "grad_norm": 3.046797275543213, "learning_rate": 2.7097974552014332e-05, "loss": 0.8137, "step": 12108 }, { "epoch": 0.6620331453955237, "grad_norm": 2.542470693588257, "learning_rate": 2.7090104715777654e-05, "loss": 0.9401, "step": 12109 }, { "epoch": 0.6620878182128823, "grad_norm": 2.5069549083709717, "learning_rate": 2.708223559786054e-05, "loss": 0.9711, "step": 12110 }, { "epoch": 0.6621424910302409, "grad_norm": 2.584069013595581, "learning_rate": 2.7074367198509733e-05, "loss": 1.0925, "step": 12111 }, { "epoch": 0.6621971638475995, "grad_norm": 2.282742977142334, "learning_rate": 2.7066499517971926e-05, "loss": 0.9745, "step": 12112 }, { "epoch": 0.6622518366649581, "grad_norm": 2.462831735610962, "learning_rate": 2.7058632556493792e-05, "loss": 0.8635, "step": 12113 }, { "epoch": 0.6623065094823167, "grad_norm": 2.4703736305236816, "learning_rate": 2.705076631432203e-05, "loss": 0.9268, "step": 12114 }, { "epoch": 0.6623611822996753, "grad_norm": 2.4944543838500977, "learning_rate": 2.7042900791703256e-05, "loss": 0.9494, "step": 12115 }, { "epoch": 0.662415855117034, "grad_norm": 3.051347017288208, "learning_rate": 2.7035035988884095e-05, "loss": 0.8999, "step": 12116 }, { "epoch": 0.6624705279343927, "grad_norm": 3.1085565090179443, "learning_rate": 2.7027171906111125e-05, "loss": 1.1277, "step": 12117 }, { "epoch": 0.6625252007517513, "grad_norm": 2.265202522277832, "learning_rate": 2.701930854363094e-05, "loss": 0.8625, "step": 12118 }, { "epoch": 0.6625798735691099, "grad_norm": 2.9467320442199707, "learning_rate": 2.701144590169007e-05, "loss": 0.7588, "step": 12119 }, { "epoch": 0.6626345463864685, "grad_norm": 2.223480224609375, "learning_rate": 2.7003583980535054e-05, "loss": 0.8734, "step": 12120 }, { "epoch": 0.6626892192038271, "grad_norm": 2.641446113586426, "learning_rate": 2.699572278041238e-05, "loss": 1.0599, "step": 12121 }, { "epoch": 0.6627438920211857, "grad_norm": 2.6680328845977783, "learning_rate": 2.6987862301568546e-05, "loss": 1.0274, "step": 12122 }, { "epoch": 0.6627985648385444, "grad_norm": 2.1705362796783447, "learning_rate": 2.6980002544249993e-05, "loss": 0.9673, "step": 12123 }, { "epoch": 0.662853237655903, "grad_norm": 2.7265729904174805, "learning_rate": 2.6972143508703173e-05, "loss": 1.2332, "step": 12124 }, { "epoch": 0.6629079104732616, "grad_norm": 2.043795585632324, "learning_rate": 2.6964285195174478e-05, "loss": 0.8978, "step": 12125 }, { "epoch": 0.6629625832906202, "grad_norm": 2.680527925491333, "learning_rate": 2.695642760391033e-05, "loss": 0.9079, "step": 12126 }, { "epoch": 0.6630172561079788, "grad_norm": 2.457667589187622, "learning_rate": 2.6948570735157076e-05, "loss": 0.8961, "step": 12127 }, { "epoch": 0.6630719289253374, "grad_norm": 2.6986520290374756, "learning_rate": 2.6940714589161064e-05, "loss": 1.1138, "step": 12128 }, { "epoch": 0.663126601742696, "grad_norm": 2.567098379135132, "learning_rate": 2.6932859166168622e-05, "loss": 0.995, "step": 12129 }, { "epoch": 0.6631812745600547, "grad_norm": 2.335966110229492, "learning_rate": 2.692500446642604e-05, "loss": 1.1399, "step": 12130 }, { "epoch": 0.6632359473774133, "grad_norm": 2.3142247200012207, "learning_rate": 2.691715049017961e-05, "loss": 0.9301, "step": 12131 }, { "epoch": 0.6632906201947719, "grad_norm": 2.365985631942749, "learning_rate": 2.6909297237675566e-05, "loss": 0.9054, "step": 12132 }, { "epoch": 0.6633452930121305, "grad_norm": 3.747838258743286, "learning_rate": 2.690144470916016e-05, "loss": 0.957, "step": 12133 }, { "epoch": 0.6633999658294891, "grad_norm": 2.6087348461151123, "learning_rate": 2.689359290487959e-05, "loss": 1.0688, "step": 12134 }, { "epoch": 0.6634546386468477, "grad_norm": 3.1137685775756836, "learning_rate": 2.6885741825080023e-05, "loss": 1.0398, "step": 12135 }, { "epoch": 0.6635093114642064, "grad_norm": 2.5016233921051025, "learning_rate": 2.6877891470007667e-05, "loss": 0.9755, "step": 12136 }, { "epoch": 0.663563984281565, "grad_norm": 2.6123273372650146, "learning_rate": 2.687004183990864e-05, "loss": 0.9805, "step": 12137 }, { "epoch": 0.6636186570989236, "grad_norm": 2.500596523284912, "learning_rate": 2.6862192935029055e-05, "loss": 0.8244, "step": 12138 }, { "epoch": 0.6636733299162823, "grad_norm": 2.2560317516326904, "learning_rate": 2.6854344755615017e-05, "loss": 0.9783, "step": 12139 }, { "epoch": 0.6637280027336409, "grad_norm": 2.652940273284912, "learning_rate": 2.6846497301912598e-05, "loss": 1.0849, "step": 12140 }, { "epoch": 0.6637826755509995, "grad_norm": 2.3694050312042236, "learning_rate": 2.683865057416784e-05, "loss": 0.9608, "step": 12141 }, { "epoch": 0.6638373483683581, "grad_norm": 2.9512343406677246, "learning_rate": 2.6830804572626776e-05, "loss": 0.732, "step": 12142 }, { "epoch": 0.6638920211857168, "grad_norm": 3.3806233406066895, "learning_rate": 2.6822959297535412e-05, "loss": 0.9146, "step": 12143 }, { "epoch": 0.6639466940030754, "grad_norm": 2.952526330947876, "learning_rate": 2.6815114749139725e-05, "loss": 1.0666, "step": 12144 }, { "epoch": 0.664001366820434, "grad_norm": 2.913355827331543, "learning_rate": 2.6807270927685657e-05, "loss": 1.091, "step": 12145 }, { "epoch": 0.6640560396377926, "grad_norm": 2.0671417713165283, "learning_rate": 2.6799427833419176e-05, "loss": 0.9275, "step": 12146 }, { "epoch": 0.6641107124551512, "grad_norm": 2.9605319499969482, "learning_rate": 2.679158546658619e-05, "loss": 0.8664, "step": 12147 }, { "epoch": 0.6641653852725098, "grad_norm": 2.359484910964966, "learning_rate": 2.6783743827432585e-05, "loss": 1.0605, "step": 12148 }, { "epoch": 0.6642200580898684, "grad_norm": 3.2440547943115234, "learning_rate": 2.6775902916204217e-05, "loss": 1.1907, "step": 12149 }, { "epoch": 0.6642747309072271, "grad_norm": 3.045013904571533, "learning_rate": 2.6768062733146943e-05, "loss": 1.0754, "step": 12150 }, { "epoch": 0.6643294037245857, "grad_norm": 2.737485408782959, "learning_rate": 2.676022327850658e-05, "loss": 0.8168, "step": 12151 }, { "epoch": 0.6643840765419443, "grad_norm": 1.938084602355957, "learning_rate": 2.675238455252893e-05, "loss": 0.7519, "step": 12152 }, { "epoch": 0.6644387493593029, "grad_norm": 2.573995590209961, "learning_rate": 2.6744546555459772e-05, "loss": 1.0806, "step": 12153 }, { "epoch": 0.6644934221766615, "grad_norm": 2.592693567276001, "learning_rate": 2.6736709287544825e-05, "loss": 1.0846, "step": 12154 }, { "epoch": 0.6645480949940201, "grad_norm": 2.4971845149993896, "learning_rate": 2.6728872749029878e-05, "loss": 1.0473, "step": 12155 }, { "epoch": 0.6646027678113787, "grad_norm": 3.439608097076416, "learning_rate": 2.672103694016061e-05, "loss": 1.1072, "step": 12156 }, { "epoch": 0.6646574406287374, "grad_norm": 2.0449204444885254, "learning_rate": 2.6713201861182707e-05, "loss": 0.8975, "step": 12157 }, { "epoch": 0.664712113446096, "grad_norm": 2.9111557006835938, "learning_rate": 2.6705367512341827e-05, "loss": 0.9611, "step": 12158 }, { "epoch": 0.6647667862634546, "grad_norm": 5.648443698883057, "learning_rate": 2.669753389388362e-05, "loss": 1.1249, "step": 12159 }, { "epoch": 0.6648214590808132, "grad_norm": 2.3456313610076904, "learning_rate": 2.6689701006053693e-05, "loss": 0.9456, "step": 12160 }, { "epoch": 0.6648761318981719, "grad_norm": 3.77370023727417, "learning_rate": 2.6681868849097636e-05, "loss": 0.9381, "step": 12161 }, { "epoch": 0.6649308047155305, "grad_norm": 3.8832478523254395, "learning_rate": 2.667403742326103e-05, "loss": 1.0473, "step": 12162 }, { "epoch": 0.6649854775328892, "grad_norm": 2.4744811058044434, "learning_rate": 2.666620672878941e-05, "loss": 0.9196, "step": 12163 }, { "epoch": 0.6650401503502478, "grad_norm": 3.092015027999878, "learning_rate": 2.6658376765928295e-05, "loss": 1.0388, "step": 12164 }, { "epoch": 0.6650948231676064, "grad_norm": 2.5749993324279785, "learning_rate": 2.665054753492322e-05, "loss": 1.0177, "step": 12165 }, { "epoch": 0.665149495984965, "grad_norm": 2.5684518814086914, "learning_rate": 2.6642719036019636e-05, "loss": 1.0171, "step": 12166 }, { "epoch": 0.6652041688023236, "grad_norm": 4.928024768829346, "learning_rate": 2.6634891269463014e-05, "loss": 1.0549, "step": 12167 }, { "epoch": 0.6652588416196822, "grad_norm": 5.50245475769043, "learning_rate": 2.662706423549877e-05, "loss": 1.429, "step": 12168 }, { "epoch": 0.6653135144370408, "grad_norm": 2.848656415939331, "learning_rate": 2.6619237934372326e-05, "loss": 0.9348, "step": 12169 }, { "epoch": 0.6653681872543995, "grad_norm": 3.6458444595336914, "learning_rate": 2.6611412366329068e-05, "loss": 1.0865, "step": 12170 }, { "epoch": 0.6654228600717581, "grad_norm": 2.2439022064208984, "learning_rate": 2.660358753161435e-05, "loss": 1.0617, "step": 12171 }, { "epoch": 0.6654775328891167, "grad_norm": 2.176791191101074, "learning_rate": 2.6595763430473524e-05, "loss": 0.8488, "step": 12172 }, { "epoch": 0.6655322057064753, "grad_norm": 2.685589075088501, "learning_rate": 2.65879400631519e-05, "loss": 1.0278, "step": 12173 }, { "epoch": 0.6655868785238339, "grad_norm": 2.400214433670044, "learning_rate": 2.6580117429894757e-05, "loss": 0.9946, "step": 12174 }, { "epoch": 0.6656415513411925, "grad_norm": 4.501570701599121, "learning_rate": 2.657229553094741e-05, "loss": 1.0451, "step": 12175 }, { "epoch": 0.6656962241585511, "grad_norm": 3.8436691761016846, "learning_rate": 2.6564474366555082e-05, "loss": 1.1514, "step": 12176 }, { "epoch": 0.6657508969759098, "grad_norm": 2.8013997077941895, "learning_rate": 2.6556653936962995e-05, "loss": 0.9636, "step": 12177 }, { "epoch": 0.6658055697932684, "grad_norm": 2.813683271408081, "learning_rate": 2.654883424241636e-05, "loss": 0.956, "step": 12178 }, { "epoch": 0.665860242610627, "grad_norm": 2.196986436843872, "learning_rate": 2.6541015283160353e-05, "loss": 0.9617, "step": 12179 }, { "epoch": 0.6659149154279856, "grad_norm": 2.558891534805298, "learning_rate": 2.6533197059440128e-05, "loss": 1.0313, "step": 12180 }, { "epoch": 0.6659695882453442, "grad_norm": 3.533029794692993, "learning_rate": 2.6525379571500832e-05, "loss": 1.0024, "step": 12181 }, { "epoch": 0.6660242610627028, "grad_norm": 4.027921676635742, "learning_rate": 2.651756281958756e-05, "loss": 1.1505, "step": 12182 }, { "epoch": 0.6660789338800615, "grad_norm": 2.716588258743286, "learning_rate": 2.65097468039454e-05, "loss": 1.1008, "step": 12183 }, { "epoch": 0.6661336066974202, "grad_norm": 2.683274030685425, "learning_rate": 2.65019315248194e-05, "loss": 0.8609, "step": 12184 }, { "epoch": 0.6661882795147788, "grad_norm": 2.582347869873047, "learning_rate": 2.649411698245465e-05, "loss": 1.0828, "step": 12185 }, { "epoch": 0.6662429523321374, "grad_norm": 2.9391984939575195, "learning_rate": 2.6486303177096133e-05, "loss": 1.2012, "step": 12186 }, { "epoch": 0.666297625149496, "grad_norm": 2.80623722076416, "learning_rate": 2.647849010898885e-05, "loss": 1.1904, "step": 12187 }, { "epoch": 0.6663522979668546, "grad_norm": 3.003316879272461, "learning_rate": 2.6470677778377784e-05, "loss": 0.8952, "step": 12188 }, { "epoch": 0.6664069707842132, "grad_norm": 2.9346425533294678, "learning_rate": 2.6462866185507863e-05, "loss": 1.0616, "step": 12189 }, { "epoch": 0.6664616436015719, "grad_norm": 2.7167041301727295, "learning_rate": 2.6455055330624028e-05, "loss": 1.0576, "step": 12190 }, { "epoch": 0.6665163164189305, "grad_norm": 2.682445764541626, "learning_rate": 2.644724521397117e-05, "loss": 1.2974, "step": 12191 }, { "epoch": 0.6665709892362891, "grad_norm": 2.3651866912841797, "learning_rate": 2.6439435835794184e-05, "loss": 1.0477, "step": 12192 }, { "epoch": 0.6666256620536477, "grad_norm": 2.4053280353546143, "learning_rate": 2.6431627196337917e-05, "loss": 0.9206, "step": 12193 }, { "epoch": 0.6666803348710063, "grad_norm": 2.4128000736236572, "learning_rate": 2.6423819295847173e-05, "loss": 0.9075, "step": 12194 }, { "epoch": 0.6667350076883649, "grad_norm": 2.594255208969116, "learning_rate": 2.641601213456682e-05, "loss": 1.0016, "step": 12195 }, { "epoch": 0.6667896805057235, "grad_norm": 2.7705142498016357, "learning_rate": 2.6408205712741612e-05, "loss": 1.0921, "step": 12196 }, { "epoch": 0.6668443533230822, "grad_norm": 3.197054624557495, "learning_rate": 2.6400400030616316e-05, "loss": 1.0808, "step": 12197 }, { "epoch": 0.6668990261404408, "grad_norm": 2.588639974594116, "learning_rate": 2.6392595088435673e-05, "loss": 1.0256, "step": 12198 }, { "epoch": 0.6669536989577994, "grad_norm": 2.2103078365325928, "learning_rate": 2.63847908864444e-05, "loss": 1.1144, "step": 12199 }, { "epoch": 0.667008371775158, "grad_norm": 2.370826005935669, "learning_rate": 2.637698742488719e-05, "loss": 1.0239, "step": 12200 }, { "epoch": 0.6670630445925166, "grad_norm": 2.5350840091705322, "learning_rate": 2.6369184704008708e-05, "loss": 1.1324, "step": 12201 }, { "epoch": 0.6671177174098752, "grad_norm": 3.0819365978240967, "learning_rate": 2.6361382724053618e-05, "loss": 1.0339, "step": 12202 }, { "epoch": 0.6671723902272338, "grad_norm": 2.6090729236602783, "learning_rate": 2.6353581485266533e-05, "loss": 1.0749, "step": 12203 }, { "epoch": 0.6672270630445926, "grad_norm": 3.0511221885681152, "learning_rate": 2.6345780987892022e-05, "loss": 1.0222, "step": 12204 }, { "epoch": 0.6672817358619512, "grad_norm": 2.5928499698638916, "learning_rate": 2.6337981232174725e-05, "loss": 0.8098, "step": 12205 }, { "epoch": 0.6673364086793098, "grad_norm": 2.7456648349761963, "learning_rate": 2.6330182218359166e-05, "loss": 1.1208, "step": 12206 }, { "epoch": 0.6673910814966684, "grad_norm": 2.441781759262085, "learning_rate": 2.6322383946689878e-05, "loss": 1.0163, "step": 12207 }, { "epoch": 0.667445754314027, "grad_norm": 2.3689980506896973, "learning_rate": 2.6314586417411367e-05, "loss": 1.195, "step": 12208 }, { "epoch": 0.6675004271313856, "grad_norm": 2.9021685123443604, "learning_rate": 2.6306789630768112e-05, "loss": 1.0015, "step": 12209 }, { "epoch": 0.6675550999487442, "grad_norm": 2.7278428077697754, "learning_rate": 2.6298993587004587e-05, "loss": 1.1005, "step": 12210 }, { "epoch": 0.6676097727661029, "grad_norm": 2.3539953231811523, "learning_rate": 2.6291198286365225e-05, "loss": 1.1414, "step": 12211 }, { "epoch": 0.6676644455834615, "grad_norm": 2.810077667236328, "learning_rate": 2.6283403729094436e-05, "loss": 1.0672, "step": 12212 }, { "epoch": 0.6677191184008201, "grad_norm": 2.4309353828430176, "learning_rate": 2.6275609915436605e-05, "loss": 0.895, "step": 12213 }, { "epoch": 0.6677737912181787, "grad_norm": 2.5887839794158936, "learning_rate": 2.626781684563612e-05, "loss": 1.0195, "step": 12214 }, { "epoch": 0.6678284640355373, "grad_norm": 2.435805320739746, "learning_rate": 2.6260024519937322e-05, "loss": 1.0135, "step": 12215 }, { "epoch": 0.6678831368528959, "grad_norm": 3.1508588790893555, "learning_rate": 2.625223293858452e-05, "loss": 0.9915, "step": 12216 }, { "epoch": 0.6679378096702546, "grad_norm": 3.124706983566284, "learning_rate": 2.624444210182202e-05, "loss": 1.128, "step": 12217 }, { "epoch": 0.6679924824876132, "grad_norm": 2.2929482460021973, "learning_rate": 2.62366520098941e-05, "loss": 0.9701, "step": 12218 }, { "epoch": 0.6680471553049718, "grad_norm": 2.4455859661102295, "learning_rate": 2.6228862663045006e-05, "loss": 1.0293, "step": 12219 }, { "epoch": 0.6681018281223304, "grad_norm": 2.704460859298706, "learning_rate": 2.6221074061518967e-05, "loss": 1.1206, "step": 12220 }, { "epoch": 0.668156500939689, "grad_norm": 2.080909490585327, "learning_rate": 2.6213286205560195e-05, "loss": 0.8913, "step": 12221 }, { "epoch": 0.6682111737570476, "grad_norm": 2.409616470336914, "learning_rate": 2.6205499095412856e-05, "loss": 0.9963, "step": 12222 }, { "epoch": 0.6682658465744062, "grad_norm": 2.6312692165374756, "learning_rate": 2.6197712731321095e-05, "loss": 1.1084, "step": 12223 }, { "epoch": 0.668320519391765, "grad_norm": 2.394327163696289, "learning_rate": 2.6189927113529088e-05, "loss": 1.1212, "step": 12224 }, { "epoch": 0.6683751922091236, "grad_norm": 4.999292850494385, "learning_rate": 2.6182142242280933e-05, "loss": 1.1429, "step": 12225 }, { "epoch": 0.6684298650264822, "grad_norm": 2.6164352893829346, "learning_rate": 2.6174358117820707e-05, "loss": 0.9442, "step": 12226 }, { "epoch": 0.6684845378438408, "grad_norm": 2.5216972827911377, "learning_rate": 2.616657474039248e-05, "loss": 1.1603, "step": 12227 }, { "epoch": 0.6685392106611994, "grad_norm": 2.289999485015869, "learning_rate": 2.6158792110240287e-05, "loss": 1.0035, "step": 12228 }, { "epoch": 0.668593883478558, "grad_norm": 2.0596022605895996, "learning_rate": 2.6151010227608153e-05, "loss": 0.9109, "step": 12229 }, { "epoch": 0.6686485562959166, "grad_norm": 2.939802885055542, "learning_rate": 2.614322909274007e-05, "loss": 1.1405, "step": 12230 }, { "epoch": 0.6687032291132753, "grad_norm": 4.025731086730957, "learning_rate": 2.6135448705880004e-05, "loss": 0.9019, "step": 12231 }, { "epoch": 0.6687579019306339, "grad_norm": 2.1145224571228027, "learning_rate": 2.6127669067271908e-05, "loss": 0.9916, "step": 12232 }, { "epoch": 0.6688125747479925, "grad_norm": 2.6872265338897705, "learning_rate": 2.6119890177159678e-05, "loss": 0.9346, "step": 12233 }, { "epoch": 0.6688672475653511, "grad_norm": 2.772289276123047, "learning_rate": 2.6112112035787267e-05, "loss": 1.0691, "step": 12234 }, { "epoch": 0.6689219203827097, "grad_norm": 2.2201902866363525, "learning_rate": 2.6104334643398522e-05, "loss": 1.0603, "step": 12235 }, { "epoch": 0.6689765932000683, "grad_norm": 4.008410930633545, "learning_rate": 2.6096558000237297e-05, "loss": 1.06, "step": 12236 }, { "epoch": 0.6690312660174269, "grad_norm": 2.140869140625, "learning_rate": 2.6088782106547428e-05, "loss": 0.9541, "step": 12237 }, { "epoch": 0.6690859388347856, "grad_norm": 2.2848668098449707, "learning_rate": 2.6081006962572706e-05, "loss": 1.1548, "step": 12238 }, { "epoch": 0.6691406116521442, "grad_norm": 2.328343629837036, "learning_rate": 2.6073232568556938e-05, "loss": 0.9053, "step": 12239 }, { "epoch": 0.6691952844695028, "grad_norm": 2.700453519821167, "learning_rate": 2.6065458924743858e-05, "loss": 1.2494, "step": 12240 }, { "epoch": 0.6692499572868614, "grad_norm": 2.4615111351013184, "learning_rate": 2.6057686031377222e-05, "loss": 1.0253, "step": 12241 }, { "epoch": 0.66930463010422, "grad_norm": 2.787891149520874, "learning_rate": 2.604991388870073e-05, "loss": 0.8115, "step": 12242 }, { "epoch": 0.6693593029215786, "grad_norm": 2.3518903255462646, "learning_rate": 2.6042142496958056e-05, "loss": 1.0314, "step": 12243 }, { "epoch": 0.6694139757389374, "grad_norm": 3.208441972732544, "learning_rate": 2.6034371856392902e-05, "loss": 1.0125, "step": 12244 }, { "epoch": 0.669468648556296, "grad_norm": 1.9928171634674072, "learning_rate": 2.6026601967248886e-05, "loss": 0.9044, "step": 12245 }, { "epoch": 0.6695233213736546, "grad_norm": 2.3497135639190674, "learning_rate": 2.6018832829769636e-05, "loss": 1.0643, "step": 12246 }, { "epoch": 0.6695779941910132, "grad_norm": 2.87845778465271, "learning_rate": 2.6011064444198742e-05, "loss": 1.0566, "step": 12247 }, { "epoch": 0.6696326670083718, "grad_norm": 2.451493501663208, "learning_rate": 2.6003296810779776e-05, "loss": 0.8828, "step": 12248 }, { "epoch": 0.6696873398257304, "grad_norm": 3.112793207168579, "learning_rate": 2.599552992975628e-05, "loss": 1.1019, "step": 12249 }, { "epoch": 0.669742012643089, "grad_norm": 2.491610050201416, "learning_rate": 2.598776380137179e-05, "loss": 0.9811, "step": 12250 }, { "epoch": 0.6697966854604477, "grad_norm": 2.8478331565856934, "learning_rate": 2.597999842586979e-05, "loss": 1.1213, "step": 12251 }, { "epoch": 0.6698513582778063, "grad_norm": 3.1759798526763916, "learning_rate": 2.5972233803493762e-05, "loss": 1.2438, "step": 12252 }, { "epoch": 0.6699060310951649, "grad_norm": 3.01570463180542, "learning_rate": 2.5964469934487144e-05, "loss": 1.0917, "step": 12253 }, { "epoch": 0.6699607039125235, "grad_norm": 2.0471224784851074, "learning_rate": 2.59567068190934e-05, "loss": 0.8822, "step": 12254 }, { "epoch": 0.6700153767298821, "grad_norm": 2.7999770641326904, "learning_rate": 2.5948944457555924e-05, "loss": 0.9269, "step": 12255 }, { "epoch": 0.6700700495472407, "grad_norm": 2.6955881118774414, "learning_rate": 2.5941182850118084e-05, "loss": 1.0018, "step": 12256 }, { "epoch": 0.6701247223645993, "grad_norm": 2.468996286392212, "learning_rate": 2.5933421997023253e-05, "loss": 1.0541, "step": 12257 }, { "epoch": 0.670179395181958, "grad_norm": 2.64095401763916, "learning_rate": 2.5925661898514757e-05, "loss": 1.0838, "step": 12258 }, { "epoch": 0.6702340679993166, "grad_norm": 2.304887056350708, "learning_rate": 2.5917902554835905e-05, "loss": 0.7407, "step": 12259 }, { "epoch": 0.6702887408166752, "grad_norm": 2.446791410446167, "learning_rate": 2.5910143966229994e-05, "loss": 1.0313, "step": 12260 }, { "epoch": 0.6703434136340338, "grad_norm": 2.840925455093384, "learning_rate": 2.5902386132940282e-05, "loss": 0.8618, "step": 12261 }, { "epoch": 0.6703980864513924, "grad_norm": 4.037868499755859, "learning_rate": 2.5894629055209984e-05, "loss": 1.0924, "step": 12262 }, { "epoch": 0.670452759268751, "grad_norm": 2.2257418632507324, "learning_rate": 2.5886872733282363e-05, "loss": 1.0237, "step": 12263 }, { "epoch": 0.6705074320861096, "grad_norm": 2.37577748298645, "learning_rate": 2.587911716740059e-05, "loss": 1.0816, "step": 12264 }, { "epoch": 0.6705621049034683, "grad_norm": 3.021768808364868, "learning_rate": 2.587136235780784e-05, "loss": 1.0538, "step": 12265 }, { "epoch": 0.670616777720827, "grad_norm": 2.0841751098632812, "learning_rate": 2.5863608304747244e-05, "loss": 1.0002, "step": 12266 }, { "epoch": 0.6706714505381856, "grad_norm": 2.2577402591705322, "learning_rate": 2.5855855008461938e-05, "loss": 0.9599, "step": 12267 }, { "epoch": 0.6707261233555442, "grad_norm": 2.319687604904175, "learning_rate": 2.5848102469195012e-05, "loss": 1.1489, "step": 12268 }, { "epoch": 0.6707807961729028, "grad_norm": 2.6715598106384277, "learning_rate": 2.584035068718954e-05, "loss": 0.9211, "step": 12269 }, { "epoch": 0.6708354689902614, "grad_norm": 2.8724091053009033, "learning_rate": 2.5832599662688574e-05, "loss": 1.0103, "step": 12270 }, { "epoch": 0.6708901418076201, "grad_norm": 2.9304330348968506, "learning_rate": 2.582484939593514e-05, "loss": 1.1911, "step": 12271 }, { "epoch": 0.6709448146249787, "grad_norm": 2.9248220920562744, "learning_rate": 2.581709988717224e-05, "loss": 0.8567, "step": 12272 }, { "epoch": 0.6709994874423373, "grad_norm": 2.5359323024749756, "learning_rate": 2.5809351136642857e-05, "loss": 1.0268, "step": 12273 }, { "epoch": 0.6710541602596959, "grad_norm": 2.554508924484253, "learning_rate": 2.5801603144589925e-05, "loss": 0.9902, "step": 12274 }, { "epoch": 0.6711088330770545, "grad_norm": 2.7903354167938232, "learning_rate": 2.579385591125641e-05, "loss": 1.0807, "step": 12275 }, { "epoch": 0.6711635058944131, "grad_norm": 2.6855885982513428, "learning_rate": 2.5786109436885203e-05, "loss": 1.1919, "step": 12276 }, { "epoch": 0.6712181787117717, "grad_norm": 2.783773422241211, "learning_rate": 2.577836372171919e-05, "loss": 0.96, "step": 12277 }, { "epoch": 0.6712728515291304, "grad_norm": 4.236488342285156, "learning_rate": 2.577061876600123e-05, "loss": 1.1378, "step": 12278 }, { "epoch": 0.671327524346489, "grad_norm": 2.4340152740478516, "learning_rate": 2.576287456997416e-05, "loss": 0.7121, "step": 12279 }, { "epoch": 0.6713821971638476, "grad_norm": 2.7187018394470215, "learning_rate": 2.5755131133880782e-05, "loss": 1.0255, "step": 12280 }, { "epoch": 0.6714368699812062, "grad_norm": 2.258175849914551, "learning_rate": 2.5747388457963905e-05, "loss": 1.0307, "step": 12281 }, { "epoch": 0.6714915427985648, "grad_norm": 2.7641241550445557, "learning_rate": 2.573964654246628e-05, "loss": 1.0083, "step": 12282 }, { "epoch": 0.6715462156159234, "grad_norm": 2.4471817016601562, "learning_rate": 2.573190538763065e-05, "loss": 1.0769, "step": 12283 }, { "epoch": 0.671600888433282, "grad_norm": 2.0314173698425293, "learning_rate": 2.572416499369973e-05, "loss": 0.8606, "step": 12284 }, { "epoch": 0.6716555612506407, "grad_norm": 2.036238670349121, "learning_rate": 2.5716425360916217e-05, "loss": 0.9283, "step": 12285 }, { "epoch": 0.6717102340679993, "grad_norm": 2.2703168392181396, "learning_rate": 2.570868648952278e-05, "loss": 1.0413, "step": 12286 }, { "epoch": 0.671764906885358, "grad_norm": 2.7344839572906494, "learning_rate": 2.5700948379762046e-05, "loss": 1.1425, "step": 12287 }, { "epoch": 0.6718195797027166, "grad_norm": 2.779632329940796, "learning_rate": 2.569321103187667e-05, "loss": 1.0222, "step": 12288 }, { "epoch": 0.6718742525200752, "grad_norm": 3.2683072090148926, "learning_rate": 2.5685474446109237e-05, "loss": 1.2147, "step": 12289 }, { "epoch": 0.6719289253374338, "grad_norm": 2.787341594696045, "learning_rate": 2.567773862270232e-05, "loss": 0.9268, "step": 12290 }, { "epoch": 0.6719835981547924, "grad_norm": 2.4859886169433594, "learning_rate": 2.567000356189846e-05, "loss": 1.0729, "step": 12291 }, { "epoch": 0.6720382709721511, "grad_norm": 2.9681200981140137, "learning_rate": 2.566226926394019e-05, "loss": 1.1472, "step": 12292 }, { "epoch": 0.6720929437895097, "grad_norm": 2.248934507369995, "learning_rate": 2.565453572907002e-05, "loss": 1.0296, "step": 12293 }, { "epoch": 0.6721476166068683, "grad_norm": 2.460421085357666, "learning_rate": 2.5646802957530413e-05, "loss": 1.0206, "step": 12294 }, { "epoch": 0.6722022894242269, "grad_norm": 2.3288958072662354, "learning_rate": 2.5639070949563827e-05, "loss": 1.1157, "step": 12295 }, { "epoch": 0.6722569622415855, "grad_norm": 3.039437770843506, "learning_rate": 2.5631339705412704e-05, "loss": 1.2624, "step": 12296 }, { "epoch": 0.6723116350589441, "grad_norm": 3.2901694774627686, "learning_rate": 2.5623609225319435e-05, "loss": 1.2101, "step": 12297 }, { "epoch": 0.6723663078763028, "grad_norm": 2.414482355117798, "learning_rate": 2.5615879509526414e-05, "loss": 0.9935, "step": 12298 }, { "epoch": 0.6724209806936614, "grad_norm": 3.7520523071289062, "learning_rate": 2.5608150558275997e-05, "loss": 0.8977, "step": 12299 }, { "epoch": 0.67247565351102, "grad_norm": 2.835615396499634, "learning_rate": 2.560042237181049e-05, "loss": 0.9447, "step": 12300 }, { "epoch": 0.6725303263283786, "grad_norm": 3.2571423053741455, "learning_rate": 2.5592694950372254e-05, "loss": 1.2252, "step": 12301 }, { "epoch": 0.6725849991457372, "grad_norm": 2.575888156890869, "learning_rate": 2.5584968294203547e-05, "loss": 0.83, "step": 12302 }, { "epoch": 0.6726396719630958, "grad_norm": 2.18953013420105, "learning_rate": 2.5577242403546643e-05, "loss": 0.8955, "step": 12303 }, { "epoch": 0.6726943447804544, "grad_norm": 2.558992624282837, "learning_rate": 2.5569517278643763e-05, "loss": 1.1192, "step": 12304 }, { "epoch": 0.6727490175978131, "grad_norm": 2.6443958282470703, "learning_rate": 2.5561792919737137e-05, "loss": 1.0907, "step": 12305 }, { "epoch": 0.6728036904151717, "grad_norm": 2.9294698238372803, "learning_rate": 2.5554069327068954e-05, "loss": 1.2245, "step": 12306 }, { "epoch": 0.6728583632325303, "grad_norm": 3.024230480194092, "learning_rate": 2.554634650088137e-05, "loss": 1.087, "step": 12307 }, { "epoch": 0.672913036049889, "grad_norm": 2.9852206707000732, "learning_rate": 2.5538624441416535e-05, "loss": 1.2019, "step": 12308 }, { "epoch": 0.6729677088672475, "grad_norm": 2.2916202545166016, "learning_rate": 2.5530903148916562e-05, "loss": 0.9708, "step": 12309 }, { "epoch": 0.6730223816846062, "grad_norm": 2.24208402633667, "learning_rate": 2.552318262362356e-05, "loss": 1.0829, "step": 12310 }, { "epoch": 0.6730770545019648, "grad_norm": 3.9474101066589355, "learning_rate": 2.551546286577956e-05, "loss": 0.9711, "step": 12311 }, { "epoch": 0.6731317273193235, "grad_norm": 2.8721814155578613, "learning_rate": 2.5507743875626666e-05, "loss": 1.1889, "step": 12312 }, { "epoch": 0.6731864001366821, "grad_norm": 2.55472993850708, "learning_rate": 2.550002565340687e-05, "loss": 1.0541, "step": 12313 }, { "epoch": 0.6732410729540407, "grad_norm": 3.4001877307891846, "learning_rate": 2.549230819936216e-05, "loss": 0.8704, "step": 12314 }, { "epoch": 0.6732957457713993, "grad_norm": 2.1160645484924316, "learning_rate": 2.548459151373453e-05, "loss": 0.9867, "step": 12315 }, { "epoch": 0.6733504185887579, "grad_norm": 1.989133596420288, "learning_rate": 2.547687559676592e-05, "loss": 0.8355, "step": 12316 }, { "epoch": 0.6734050914061165, "grad_norm": 2.41538405418396, "learning_rate": 2.5469160448698252e-05, "loss": 1.0093, "step": 12317 }, { "epoch": 0.6734597642234751, "grad_norm": 2.317915916442871, "learning_rate": 2.5461446069773444e-05, "loss": 0.8962, "step": 12318 }, { "epoch": 0.6735144370408338, "grad_norm": 2.8856008052825928, "learning_rate": 2.5453732460233347e-05, "loss": 1.3014, "step": 12319 }, { "epoch": 0.6735691098581924, "grad_norm": 2.5062248706817627, "learning_rate": 2.5446019620319838e-05, "loss": 1.1383, "step": 12320 }, { "epoch": 0.673623782675551, "grad_norm": 2.90920090675354, "learning_rate": 2.543830755027472e-05, "loss": 1.1577, "step": 12321 }, { "epoch": 0.6736784554929096, "grad_norm": 2.1491966247558594, "learning_rate": 2.5430596250339835e-05, "loss": 1.0457, "step": 12322 }, { "epoch": 0.6737331283102682, "grad_norm": 2.365212917327881, "learning_rate": 2.542288572075694e-05, "loss": 1.0009, "step": 12323 }, { "epoch": 0.6737878011276268, "grad_norm": 2.3639745712280273, "learning_rate": 2.54151759617678e-05, "loss": 1.1394, "step": 12324 }, { "epoch": 0.6738424739449855, "grad_norm": 2.253744125366211, "learning_rate": 2.5407466973614148e-05, "loss": 0.8583, "step": 12325 }, { "epoch": 0.6738971467623441, "grad_norm": 2.829507350921631, "learning_rate": 2.5399758756537684e-05, "loss": 1.0682, "step": 12326 }, { "epoch": 0.6739518195797027, "grad_norm": 2.604891061782837, "learning_rate": 2.5392051310780095e-05, "loss": 1.0162, "step": 12327 }, { "epoch": 0.6740064923970613, "grad_norm": 2.5177483558654785, "learning_rate": 2.5384344636583045e-05, "loss": 0.8294, "step": 12328 }, { "epoch": 0.6740611652144199, "grad_norm": 2.713322877883911, "learning_rate": 2.5376638734188173e-05, "loss": 1.1123, "step": 12329 }, { "epoch": 0.6741158380317785, "grad_norm": 2.956040382385254, "learning_rate": 2.5368933603837087e-05, "loss": 0.922, "step": 12330 }, { "epoch": 0.6741705108491372, "grad_norm": 3.717933177947998, "learning_rate": 2.536122924577135e-05, "loss": 0.9325, "step": 12331 }, { "epoch": 0.6742251836664959, "grad_norm": 2.510637044906616, "learning_rate": 2.535352566023257e-05, "loss": 0.8844, "step": 12332 }, { "epoch": 0.6742798564838545, "grad_norm": 2.16003680229187, "learning_rate": 2.5345822847462265e-05, "loss": 0.9299, "step": 12333 }, { "epoch": 0.6743345293012131, "grad_norm": 3.187354803085327, "learning_rate": 2.5338120807701953e-05, "loss": 1.1412, "step": 12334 }, { "epoch": 0.6743892021185717, "grad_norm": 2.442673683166504, "learning_rate": 2.5330419541193117e-05, "loss": 1.0646, "step": 12335 }, { "epoch": 0.6744438749359303, "grad_norm": 2.888763427734375, "learning_rate": 2.5322719048177234e-05, "loss": 1.1183, "step": 12336 }, { "epoch": 0.6744985477532889, "grad_norm": 3.2310497760772705, "learning_rate": 2.531501932889574e-05, "loss": 1.0147, "step": 12337 }, { "epoch": 0.6745532205706475, "grad_norm": 2.8585307598114014, "learning_rate": 2.530732038359005e-05, "loss": 0.901, "step": 12338 }, { "epoch": 0.6746078933880062, "grad_norm": 2.411480665206909, "learning_rate": 2.529962221250156e-05, "loss": 0.9485, "step": 12339 }, { "epoch": 0.6746625662053648, "grad_norm": 2.532058000564575, "learning_rate": 2.5291924815871642e-05, "loss": 1.0408, "step": 12340 }, { "epoch": 0.6747172390227234, "grad_norm": 3.103410005569458, "learning_rate": 2.528422819394162e-05, "loss": 1.1159, "step": 12341 }, { "epoch": 0.674771911840082, "grad_norm": 2.667417287826538, "learning_rate": 2.527653234695286e-05, "loss": 1.1076, "step": 12342 }, { "epoch": 0.6748265846574406, "grad_norm": 3.001854419708252, "learning_rate": 2.5268837275146624e-05, "loss": 0.9483, "step": 12343 }, { "epoch": 0.6748812574747992, "grad_norm": 2.621840476989746, "learning_rate": 2.5261142978764195e-05, "loss": 1.1113, "step": 12344 }, { "epoch": 0.6749359302921578, "grad_norm": 3.6860241889953613, "learning_rate": 2.5253449458046817e-05, "loss": 1.096, "step": 12345 }, { "epoch": 0.6749906031095165, "grad_norm": 4.417140483856201, "learning_rate": 2.5245756713235726e-05, "loss": 0.9533, "step": 12346 }, { "epoch": 0.6750452759268751, "grad_norm": 2.9394705295562744, "learning_rate": 2.5238064744572098e-05, "loss": 1.1156, "step": 12347 }, { "epoch": 0.6750999487442337, "grad_norm": 3.3773915767669678, "learning_rate": 2.5230373552297128e-05, "loss": 1.2393, "step": 12348 }, { "epoch": 0.6751546215615923, "grad_norm": 2.6614468097686768, "learning_rate": 2.522268313665196e-05, "loss": 0.9496, "step": 12349 }, { "epoch": 0.6752092943789509, "grad_norm": 2.3741800785064697, "learning_rate": 2.5214993497877715e-05, "loss": 1.1244, "step": 12350 }, { "epoch": 0.6752639671963095, "grad_norm": 2.824147939682007, "learning_rate": 2.520730463621548e-05, "loss": 1.0787, "step": 12351 }, { "epoch": 0.6753186400136683, "grad_norm": 2.389281749725342, "learning_rate": 2.5199616551906376e-05, "loss": 1.1901, "step": 12352 }, { "epoch": 0.6753733128310269, "grad_norm": 2.729862928390503, "learning_rate": 2.5191929245191425e-05, "loss": 1.2486, "step": 12353 }, { "epoch": 0.6754279856483855, "grad_norm": 2.8372230529785156, "learning_rate": 2.5184242716311667e-05, "loss": 1.012, "step": 12354 }, { "epoch": 0.6754826584657441, "grad_norm": 2.670454740524292, "learning_rate": 2.51765569655081e-05, "loss": 1.0408, "step": 12355 }, { "epoch": 0.6755373312831027, "grad_norm": 2.628143787384033, "learning_rate": 2.5168871993021704e-05, "loss": 0.9472, "step": 12356 }, { "epoch": 0.6755920041004613, "grad_norm": 2.9739866256713867, "learning_rate": 2.5161187799093437e-05, "loss": 1.1522, "step": 12357 }, { "epoch": 0.6756466769178199, "grad_norm": 3.753770112991333, "learning_rate": 2.5153504383964233e-05, "loss": 1.2408, "step": 12358 }, { "epoch": 0.6757013497351786, "grad_norm": 2.0940752029418945, "learning_rate": 2.514582174787499e-05, "loss": 0.8752, "step": 12359 }, { "epoch": 0.6757560225525372, "grad_norm": 1.8771193027496338, "learning_rate": 2.5138139891066605e-05, "loss": 0.7937, "step": 12360 }, { "epoch": 0.6758106953698958, "grad_norm": 2.881742238998413, "learning_rate": 2.51304588137799e-05, "loss": 0.9357, "step": 12361 }, { "epoch": 0.6758653681872544, "grad_norm": 2.4721314907073975, "learning_rate": 2.5122778516255752e-05, "loss": 1.1336, "step": 12362 }, { "epoch": 0.675920041004613, "grad_norm": 2.4683098793029785, "learning_rate": 2.5115098998734953e-05, "loss": 0.8458, "step": 12363 }, { "epoch": 0.6759747138219716, "grad_norm": 2.660391092300415, "learning_rate": 2.5107420261458292e-05, "loss": 1.0902, "step": 12364 }, { "epoch": 0.6760293866393302, "grad_norm": 2.400022506713867, "learning_rate": 2.5099742304666517e-05, "loss": 1.0372, "step": 12365 }, { "epoch": 0.6760840594566889, "grad_norm": 2.450845241546631, "learning_rate": 2.5092065128600378e-05, "loss": 0.924, "step": 12366 }, { "epoch": 0.6761387322740475, "grad_norm": 2.1225085258483887, "learning_rate": 2.5084388733500575e-05, "loss": 1.1346, "step": 12367 }, { "epoch": 0.6761934050914061, "grad_norm": 3.7240824699401855, "learning_rate": 2.5076713119607804e-05, "loss": 1.0765, "step": 12368 }, { "epoch": 0.6762480779087647, "grad_norm": 3.4988973140716553, "learning_rate": 2.5069038287162716e-05, "loss": 1.1887, "step": 12369 }, { "epoch": 0.6763027507261233, "grad_norm": 2.950712203979492, "learning_rate": 2.506136423640594e-05, "loss": 1.0183, "step": 12370 }, { "epoch": 0.6763574235434819, "grad_norm": 2.8529157638549805, "learning_rate": 2.5053690967578116e-05, "loss": 0.9992, "step": 12371 }, { "epoch": 0.6764120963608405, "grad_norm": 3.156874179840088, "learning_rate": 2.5046018480919818e-05, "loss": 1.114, "step": 12372 }, { "epoch": 0.6764667691781993, "grad_norm": 2.5333175659179688, "learning_rate": 2.5038346776671617e-05, "loss": 0.8756, "step": 12373 }, { "epoch": 0.6765214419955579, "grad_norm": 2.195237159729004, "learning_rate": 2.5030675855074047e-05, "loss": 0.7999, "step": 12374 }, { "epoch": 0.6765761148129165, "grad_norm": 2.1630396842956543, "learning_rate": 2.502300571636762e-05, "loss": 0.8973, "step": 12375 }, { "epoch": 0.6766307876302751, "grad_norm": 3.799170732498169, "learning_rate": 2.5015336360792836e-05, "loss": 1.1247, "step": 12376 }, { "epoch": 0.6766854604476337, "grad_norm": 3.929232120513916, "learning_rate": 2.500766778859015e-05, "loss": 0.8197, "step": 12377 }, { "epoch": 0.6767401332649923, "grad_norm": 2.6028223037719727, "learning_rate": 2.500000000000001e-05, "loss": 0.9324, "step": 12378 }, { "epoch": 0.676794806082351, "grad_norm": 2.6902801990509033, "learning_rate": 2.499233299526283e-05, "loss": 0.9011, "step": 12379 }, { "epoch": 0.6768494788997096, "grad_norm": 3.0955700874328613, "learning_rate": 2.4984666774618988e-05, "loss": 0.9531, "step": 12380 }, { "epoch": 0.6769041517170682, "grad_norm": 2.802518844604492, "learning_rate": 2.497700133830888e-05, "loss": 1.0076, "step": 12381 }, { "epoch": 0.6769588245344268, "grad_norm": 2.3362138271331787, "learning_rate": 2.4969336686572835e-05, "loss": 0.9791, "step": 12382 }, { "epoch": 0.6770134973517854, "grad_norm": 2.373018264770508, "learning_rate": 2.4961672819651176e-05, "loss": 0.8966, "step": 12383 }, { "epoch": 0.677068170169144, "grad_norm": 3.2940988540649414, "learning_rate": 2.495400973778419e-05, "loss": 0.9751, "step": 12384 }, { "epoch": 0.6771228429865026, "grad_norm": 2.1533286571502686, "learning_rate": 2.4946347441212155e-05, "loss": 1.0769, "step": 12385 }, { "epoch": 0.6771775158038613, "grad_norm": 2.1330342292785645, "learning_rate": 2.4938685930175297e-05, "loss": 1.0271, "step": 12386 }, { "epoch": 0.6772321886212199, "grad_norm": 2.782688617706299, "learning_rate": 2.493102520491386e-05, "loss": 1.1022, "step": 12387 }, { "epoch": 0.6772868614385785, "grad_norm": 2.734428882598877, "learning_rate": 2.4923365265668025e-05, "loss": 1.0664, "step": 12388 }, { "epoch": 0.6773415342559371, "grad_norm": 3.2722818851470947, "learning_rate": 2.491570611267796e-05, "loss": 0.9586, "step": 12389 }, { "epoch": 0.6773962070732957, "grad_norm": 2.3761744499206543, "learning_rate": 2.4908047746183803e-05, "loss": 1.1633, "step": 12390 }, { "epoch": 0.6774508798906543, "grad_norm": 2.5738115310668945, "learning_rate": 2.4900390166425703e-05, "loss": 1.0587, "step": 12391 }, { "epoch": 0.6775055527080129, "grad_norm": 3.3735363483428955, "learning_rate": 2.4892733373643746e-05, "loss": 1.0862, "step": 12392 }, { "epoch": 0.6775602255253717, "grad_norm": 2.904623031616211, "learning_rate": 2.4885077368078e-05, "loss": 1.254, "step": 12393 }, { "epoch": 0.6776148983427303, "grad_norm": 2.4480948448181152, "learning_rate": 2.487742214996851e-05, "loss": 1.2204, "step": 12394 }, { "epoch": 0.6776695711600889, "grad_norm": 3.1328125, "learning_rate": 2.4869767719555305e-05, "loss": 1.2455, "step": 12395 }, { "epoch": 0.6777242439774475, "grad_norm": 2.5215795040130615, "learning_rate": 2.486211407707838e-05, "loss": 1.0441, "step": 12396 }, { "epoch": 0.6777789167948061, "grad_norm": 2.5327024459838867, "learning_rate": 2.4854461222777702e-05, "loss": 0.9156, "step": 12397 }, { "epoch": 0.6778335896121647, "grad_norm": 2.535919666290283, "learning_rate": 2.484680915689323e-05, "loss": 1.0729, "step": 12398 }, { "epoch": 0.6778882624295233, "grad_norm": 2.8720810413360596, "learning_rate": 2.4839157879664875e-05, "loss": 1.0358, "step": 12399 }, { "epoch": 0.677942935246882, "grad_norm": 2.5529627799987793, "learning_rate": 2.4831507391332532e-05, "loss": 1.1228, "step": 12400 }, { "epoch": 0.6779976080642406, "grad_norm": 3.0200417041778564, "learning_rate": 2.4823857692136104e-05, "loss": 0.9641, "step": 12401 }, { "epoch": 0.6780522808815992, "grad_norm": 2.2549471855163574, "learning_rate": 2.4816208782315425e-05, "loss": 0.9913, "step": 12402 }, { "epoch": 0.6781069536989578, "grad_norm": 2.4651882648468018, "learning_rate": 2.4808560662110312e-05, "loss": 1.0535, "step": 12403 }, { "epoch": 0.6781616265163164, "grad_norm": 3.8974246978759766, "learning_rate": 2.4800913331760576e-05, "loss": 1.0171, "step": 12404 }, { "epoch": 0.678216299333675, "grad_norm": 2.4447968006134033, "learning_rate": 2.4793266791505993e-05, "loss": 1.0885, "step": 12405 }, { "epoch": 0.6782709721510337, "grad_norm": 3.389918327331543, "learning_rate": 2.47856210415863e-05, "loss": 0.9526, "step": 12406 }, { "epoch": 0.6783256449683923, "grad_norm": 2.5894572734832764, "learning_rate": 2.4777976082241234e-05, "loss": 1.0152, "step": 12407 }, { "epoch": 0.6783803177857509, "grad_norm": 2.9223556518554688, "learning_rate": 2.4770331913710494e-05, "loss": 0.9345, "step": 12408 }, { "epoch": 0.6784349906031095, "grad_norm": 2.3106932640075684, "learning_rate": 2.4762688536233753e-05, "loss": 1.0995, "step": 12409 }, { "epoch": 0.6784896634204681, "grad_norm": 3.309239387512207, "learning_rate": 2.475504595005065e-05, "loss": 1.0588, "step": 12410 }, { "epoch": 0.6785443362378267, "grad_norm": 2.535458564758301, "learning_rate": 2.474740415540084e-05, "loss": 0.9925, "step": 12411 }, { "epoch": 0.6785990090551853, "grad_norm": 2.9277172088623047, "learning_rate": 2.4739763152523914e-05, "loss": 1.2231, "step": 12412 }, { "epoch": 0.678653681872544, "grad_norm": 2.0596232414245605, "learning_rate": 2.473212294165944e-05, "loss": 0.9657, "step": 12413 }, { "epoch": 0.6787083546899026, "grad_norm": 3.075716733932495, "learning_rate": 2.4724483523046982e-05, "loss": 0.9942, "step": 12414 }, { "epoch": 0.6787630275072613, "grad_norm": 2.3058316707611084, "learning_rate": 2.471684489692606e-05, "loss": 0.846, "step": 12415 }, { "epoch": 0.6788177003246199, "grad_norm": 2.4712443351745605, "learning_rate": 2.4709207063536178e-05, "loss": 1.1235, "step": 12416 }, { "epoch": 0.6788723731419785, "grad_norm": 2.272006034851074, "learning_rate": 2.470157002311681e-05, "loss": 0.9689, "step": 12417 }, { "epoch": 0.6789270459593371, "grad_norm": 2.811140537261963, "learning_rate": 2.4693933775907412e-05, "loss": 1.0394, "step": 12418 }, { "epoch": 0.6789817187766957, "grad_norm": 2.774385929107666, "learning_rate": 2.4686298322147395e-05, "loss": 1.018, "step": 12419 }, { "epoch": 0.6790363915940544, "grad_norm": 3.378063201904297, "learning_rate": 2.4678663662076195e-05, "loss": 0.9272, "step": 12420 }, { "epoch": 0.679091064411413, "grad_norm": 2.3519132137298584, "learning_rate": 2.4671029795933175e-05, "loss": 1.1993, "step": 12421 }, { "epoch": 0.6791457372287716, "grad_norm": 2.626681089401245, "learning_rate": 2.466339672395769e-05, "loss": 1.0621, "step": 12422 }, { "epoch": 0.6792004100461302, "grad_norm": 2.242798328399658, "learning_rate": 2.4655764446389057e-05, "loss": 0.9766, "step": 12423 }, { "epoch": 0.6792550828634888, "grad_norm": 2.531834363937378, "learning_rate": 2.464813296346659e-05, "loss": 1.0181, "step": 12424 }, { "epoch": 0.6793097556808474, "grad_norm": 2.73524808883667, "learning_rate": 2.4640502275429566e-05, "loss": 0.9151, "step": 12425 }, { "epoch": 0.679364428498206, "grad_norm": 2.7223715782165527, "learning_rate": 2.4632872382517242e-05, "loss": 0.848, "step": 12426 }, { "epoch": 0.6794191013155647, "grad_norm": 2.2883520126342773, "learning_rate": 2.4625243284968836e-05, "loss": 1.0322, "step": 12427 }, { "epoch": 0.6794737741329233, "grad_norm": 2.619699478149414, "learning_rate": 2.4617614983023553e-05, "loss": 1.1697, "step": 12428 }, { "epoch": 0.6795284469502819, "grad_norm": 2.9519925117492676, "learning_rate": 2.460998747692056e-05, "loss": 1.0338, "step": 12429 }, { "epoch": 0.6795831197676405, "grad_norm": 2.9255847930908203, "learning_rate": 2.4602360766899047e-05, "loss": 1.2711, "step": 12430 }, { "epoch": 0.6796377925849991, "grad_norm": 2.4679362773895264, "learning_rate": 2.4594734853198127e-05, "loss": 0.9374, "step": 12431 }, { "epoch": 0.6796924654023577, "grad_norm": 2.4051015377044678, "learning_rate": 2.458710973605689e-05, "loss": 1.0085, "step": 12432 }, { "epoch": 0.6797471382197164, "grad_norm": 2.617607831954956, "learning_rate": 2.4579485415714433e-05, "loss": 1.0532, "step": 12433 }, { "epoch": 0.679801811037075, "grad_norm": 2.435157299041748, "learning_rate": 2.457186189240979e-05, "loss": 0.9541, "step": 12434 }, { "epoch": 0.6798564838544336, "grad_norm": 2.7129299640655518, "learning_rate": 2.456423916638201e-05, "loss": 1.0694, "step": 12435 }, { "epoch": 0.6799111566717922, "grad_norm": 2.4859025478363037, "learning_rate": 2.4556617237870082e-05, "loss": 0.9939, "step": 12436 }, { "epoch": 0.6799658294891509, "grad_norm": 2.959392786026001, "learning_rate": 2.4548996107112992e-05, "loss": 1.1816, "step": 12437 }, { "epoch": 0.6800205023065095, "grad_norm": 2.616819143295288, "learning_rate": 2.4541375774349694e-05, "loss": 1.1511, "step": 12438 }, { "epoch": 0.6800751751238681, "grad_norm": 2.525036096572876, "learning_rate": 2.4533756239819095e-05, "loss": 1.014, "step": 12439 }, { "epoch": 0.6801298479412268, "grad_norm": 3.0394086837768555, "learning_rate": 2.4526137503760137e-05, "loss": 1.0771, "step": 12440 }, { "epoch": 0.6801845207585854, "grad_norm": 2.8139193058013916, "learning_rate": 2.4518519566411685e-05, "loss": 0.8376, "step": 12441 }, { "epoch": 0.680239193575944, "grad_norm": 3.359530210494995, "learning_rate": 2.4510902428012584e-05, "loss": 1.1324, "step": 12442 }, { "epoch": 0.6802938663933026, "grad_norm": 3.258964776992798, "learning_rate": 2.450328608880167e-05, "loss": 1.2038, "step": 12443 }, { "epoch": 0.6803485392106612, "grad_norm": 2.6548986434936523, "learning_rate": 2.449567054901774e-05, "loss": 1.0422, "step": 12444 }, { "epoch": 0.6804032120280198, "grad_norm": 2.5245134830474854, "learning_rate": 2.448805580889958e-05, "loss": 0.7842, "step": 12445 }, { "epoch": 0.6804578848453784, "grad_norm": 4.456421375274658, "learning_rate": 2.4480441868685934e-05, "loss": 1.1561, "step": 12446 }, { "epoch": 0.6805125576627371, "grad_norm": 2.5483434200286865, "learning_rate": 2.447282872861554e-05, "loss": 0.9327, "step": 12447 }, { "epoch": 0.6805672304800957, "grad_norm": 3.7578415870666504, "learning_rate": 2.44652163889271e-05, "loss": 1.0537, "step": 12448 }, { "epoch": 0.6806219032974543, "grad_norm": 2.645610809326172, "learning_rate": 2.445760484985926e-05, "loss": 0.953, "step": 12449 }, { "epoch": 0.6806765761148129, "grad_norm": 2.894163131713867, "learning_rate": 2.444999411165073e-05, "loss": 1.0504, "step": 12450 }, { "epoch": 0.6807312489321715, "grad_norm": 2.664027690887451, "learning_rate": 2.4442384174540112e-05, "loss": 1.0277, "step": 12451 }, { "epoch": 0.6807859217495301, "grad_norm": 2.815525770187378, "learning_rate": 2.4434775038766e-05, "loss": 1.1668, "step": 12452 }, { "epoch": 0.6808405945668887, "grad_norm": 2.7515344619750977, "learning_rate": 2.4427166704566985e-05, "loss": 1.0502, "step": 12453 }, { "epoch": 0.6808952673842474, "grad_norm": 3.0145907402038574, "learning_rate": 2.4419559172181615e-05, "loss": 1.1031, "step": 12454 }, { "epoch": 0.680949940201606, "grad_norm": 2.5242435932159424, "learning_rate": 2.4411952441848413e-05, "loss": 0.9745, "step": 12455 }, { "epoch": 0.6810046130189646, "grad_norm": 2.428819417953491, "learning_rate": 2.4404346513805888e-05, "loss": 1.2262, "step": 12456 }, { "epoch": 0.6810592858363232, "grad_norm": 2.5645008087158203, "learning_rate": 2.439674138829251e-05, "loss": 1.1188, "step": 12457 }, { "epoch": 0.6811139586536819, "grad_norm": 2.947828769683838, "learning_rate": 2.4389137065546734e-05, "loss": 1.1531, "step": 12458 }, { "epoch": 0.6811686314710405, "grad_norm": 2.1985132694244385, "learning_rate": 2.4381533545806988e-05, "loss": 0.9502, "step": 12459 }, { "epoch": 0.6812233042883991, "grad_norm": 3.507131338119507, "learning_rate": 2.4373930829311676e-05, "loss": 1.1229, "step": 12460 }, { "epoch": 0.6812779771057578, "grad_norm": 2.194375514984131, "learning_rate": 2.436632891629915e-05, "loss": 0.8104, "step": 12461 }, { "epoch": 0.6813326499231164, "grad_norm": 2.43066143989563, "learning_rate": 2.4358727807007803e-05, "loss": 1.1213, "step": 12462 }, { "epoch": 0.681387322740475, "grad_norm": 2.3564774990081787, "learning_rate": 2.4351127501675943e-05, "loss": 1.0932, "step": 12463 }, { "epoch": 0.6814419955578336, "grad_norm": 2.9604861736297607, "learning_rate": 2.4343528000541865e-05, "loss": 1.039, "step": 12464 }, { "epoch": 0.6814966683751922, "grad_norm": 3.0259017944335938, "learning_rate": 2.4335929303843852e-05, "loss": 1.1125, "step": 12465 }, { "epoch": 0.6815513411925508, "grad_norm": 2.648989200592041, "learning_rate": 2.432833141182015e-05, "loss": 0.8975, "step": 12466 }, { "epoch": 0.6816060140099095, "grad_norm": 3.268871784210205, "learning_rate": 2.432073432470898e-05, "loss": 0.9887, "step": 12467 }, { "epoch": 0.6816606868272681, "grad_norm": 2.551687002182007, "learning_rate": 2.4313138042748557e-05, "loss": 1.0163, "step": 12468 }, { "epoch": 0.6817153596446267, "grad_norm": 3.3467166423797607, "learning_rate": 2.4305542566177044e-05, "loss": 0.9186, "step": 12469 }, { "epoch": 0.6817700324619853, "grad_norm": 3.0145626068115234, "learning_rate": 2.4297947895232586e-05, "loss": 1.0653, "step": 12470 }, { "epoch": 0.6818247052793439, "grad_norm": 2.6724939346313477, "learning_rate": 2.4290354030153317e-05, "loss": 0.9523, "step": 12471 }, { "epoch": 0.6818793780967025, "grad_norm": 2.684685707092285, "learning_rate": 2.4282760971177333e-05, "loss": 1.0802, "step": 12472 }, { "epoch": 0.6819340509140611, "grad_norm": 3.3181779384613037, "learning_rate": 2.4275168718542708e-05, "loss": 1.2173, "step": 12473 }, { "epoch": 0.6819887237314198, "grad_norm": 2.4470248222351074, "learning_rate": 2.426757727248747e-05, "loss": 1.0617, "step": 12474 }, { "epoch": 0.6820433965487784, "grad_norm": 1.9331973791122437, "learning_rate": 2.4259986633249675e-05, "loss": 0.8771, "step": 12475 }, { "epoch": 0.682098069366137, "grad_norm": 2.5148396492004395, "learning_rate": 2.4252396801067316e-05, "loss": 1.0029, "step": 12476 }, { "epoch": 0.6821527421834956, "grad_norm": 2.142892837524414, "learning_rate": 2.424480777617835e-05, "loss": 0.9686, "step": 12477 }, { "epoch": 0.6822074150008542, "grad_norm": 3.0561587810516357, "learning_rate": 2.4237219558820738e-05, "loss": 0.9941, "step": 12478 }, { "epoch": 0.6822620878182128, "grad_norm": 2.5371923446655273, "learning_rate": 2.4229632149232396e-05, "loss": 1.0909, "step": 12479 }, { "epoch": 0.6823167606355715, "grad_norm": 2.2328147888183594, "learning_rate": 2.422204554765121e-05, "loss": 1.0897, "step": 12480 }, { "epoch": 0.6823714334529302, "grad_norm": 2.4774670600891113, "learning_rate": 2.4214459754315072e-05, "loss": 1.0669, "step": 12481 }, { "epoch": 0.6824261062702888, "grad_norm": 2.2219924926757812, "learning_rate": 2.4206874769461808e-05, "loss": 0.9617, "step": 12482 }, { "epoch": 0.6824807790876474, "grad_norm": 2.3492822647094727, "learning_rate": 2.419929059332925e-05, "loss": 0.9998, "step": 12483 }, { "epoch": 0.682535451905006, "grad_norm": 2.156297445297241, "learning_rate": 2.419170722615519e-05, "loss": 0.9665, "step": 12484 }, { "epoch": 0.6825901247223646, "grad_norm": 2.8159048557281494, "learning_rate": 2.41841246681774e-05, "loss": 1.1471, "step": 12485 }, { "epoch": 0.6826447975397232, "grad_norm": 3.5634145736694336, "learning_rate": 2.417654291963362e-05, "loss": 1.1558, "step": 12486 }, { "epoch": 0.6826994703570818, "grad_norm": 3.6054093837738037, "learning_rate": 2.4168961980761555e-05, "loss": 1.107, "step": 12487 }, { "epoch": 0.6827541431744405, "grad_norm": 2.3173885345458984, "learning_rate": 2.4161381851798938e-05, "loss": 1.0557, "step": 12488 }, { "epoch": 0.6828088159917991, "grad_norm": 2.7232301235198975, "learning_rate": 2.4153802532983405e-05, "loss": 1.0236, "step": 12489 }, { "epoch": 0.6828634888091577, "grad_norm": 3.0463461875915527, "learning_rate": 2.4146224024552617e-05, "loss": 0.86, "step": 12490 }, { "epoch": 0.6829181616265163, "grad_norm": 3.004004955291748, "learning_rate": 2.413864632674418e-05, "loss": 0.9045, "step": 12491 }, { "epoch": 0.6829728344438749, "grad_norm": 2.715135097503662, "learning_rate": 2.4131069439795683e-05, "loss": 1.1025, "step": 12492 }, { "epoch": 0.6830275072612335, "grad_norm": 2.7212514877319336, "learning_rate": 2.4123493363944705e-05, "loss": 1.1531, "step": 12493 }, { "epoch": 0.6830821800785922, "grad_norm": 2.3723788261413574, "learning_rate": 2.411591809942878e-05, "loss": 0.9215, "step": 12494 }, { "epoch": 0.6831368528959508, "grad_norm": 2.5293009281158447, "learning_rate": 2.4108343646485427e-05, "loss": 0.8755, "step": 12495 }, { "epoch": 0.6831915257133094, "grad_norm": 2.765866756439209, "learning_rate": 2.4100770005352126e-05, "loss": 0.9735, "step": 12496 }, { "epoch": 0.683246198530668, "grad_norm": 2.5461106300354004, "learning_rate": 2.4093197176266357e-05, "loss": 1.1002, "step": 12497 }, { "epoch": 0.6833008713480266, "grad_norm": 2.2607531547546387, "learning_rate": 2.408562515946553e-05, "loss": 0.9844, "step": 12498 }, { "epoch": 0.6833555441653852, "grad_norm": 2.2593421936035156, "learning_rate": 2.4078053955187095e-05, "loss": 1.1074, "step": 12499 }, { "epoch": 0.6834102169827438, "grad_norm": 2.545423746109009, "learning_rate": 2.4070483563668432e-05, "loss": 1.0873, "step": 12500 }, { "epoch": 0.6834648898001026, "grad_norm": 2.813816785812378, "learning_rate": 2.4062913985146896e-05, "loss": 1.1524, "step": 12501 }, { "epoch": 0.6835195626174612, "grad_norm": 2.60646390914917, "learning_rate": 2.4055345219859832e-05, "loss": 0.9977, "step": 12502 }, { "epoch": 0.6835742354348198, "grad_norm": 2.850405216217041, "learning_rate": 2.4047777268044543e-05, "loss": 1.0454, "step": 12503 }, { "epoch": 0.6836289082521784, "grad_norm": 2.9270894527435303, "learning_rate": 2.4040210129938318e-05, "loss": 1.0432, "step": 12504 }, { "epoch": 0.683683581069537, "grad_norm": 2.4206795692443848, "learning_rate": 2.4032643805778416e-05, "loss": 1.0903, "step": 12505 }, { "epoch": 0.6837382538868956, "grad_norm": 3.132258653640747, "learning_rate": 2.4025078295802077e-05, "loss": 1.0169, "step": 12506 }, { "epoch": 0.6837929267042542, "grad_norm": 2.1306402683258057, "learning_rate": 2.4017513600246517e-05, "loss": 0.7789, "step": 12507 }, { "epoch": 0.6838475995216129, "grad_norm": 4.337458610534668, "learning_rate": 2.4009949719348883e-05, "loss": 1.0856, "step": 12508 }, { "epoch": 0.6839022723389715, "grad_norm": 2.573580741882324, "learning_rate": 2.4002386653346386e-05, "loss": 0.9741, "step": 12509 }, { "epoch": 0.6839569451563301, "grad_norm": 3.2841835021972656, "learning_rate": 2.399482440247614e-05, "loss": 1.0421, "step": 12510 }, { "epoch": 0.6840116179736887, "grad_norm": 2.7050468921661377, "learning_rate": 2.3987262966975248e-05, "loss": 1.0527, "step": 12511 }, { "epoch": 0.6840662907910473, "grad_norm": 1.8948465585708618, "learning_rate": 2.3979702347080795e-05, "loss": 0.9081, "step": 12512 }, { "epoch": 0.6841209636084059, "grad_norm": 4.173888206481934, "learning_rate": 2.3972142543029836e-05, "loss": 0.9681, "step": 12513 }, { "epoch": 0.6841756364257645, "grad_norm": 2.013812780380249, "learning_rate": 2.39645835550594e-05, "loss": 0.9067, "step": 12514 }, { "epoch": 0.6842303092431232, "grad_norm": 2.3564858436584473, "learning_rate": 2.3957025383406495e-05, "loss": 0.8898, "step": 12515 }, { "epoch": 0.6842849820604818, "grad_norm": 2.080354690551758, "learning_rate": 2.3949468028308103e-05, "loss": 1.0138, "step": 12516 }, { "epoch": 0.6843396548778404, "grad_norm": 2.500095844268799, "learning_rate": 2.3941911490001173e-05, "loss": 0.7869, "step": 12517 }, { "epoch": 0.684394327695199, "grad_norm": 3.2991983890533447, "learning_rate": 2.3934355768722616e-05, "loss": 1.0984, "step": 12518 }, { "epoch": 0.6844490005125576, "grad_norm": 3.124401330947876, "learning_rate": 2.3926800864709376e-05, "loss": 1.0277, "step": 12519 }, { "epoch": 0.6845036733299162, "grad_norm": 2.425194501876831, "learning_rate": 2.3919246778198312e-05, "loss": 1.0318, "step": 12520 }, { "epoch": 0.684558346147275, "grad_norm": 2.5925452709198, "learning_rate": 2.391169350942627e-05, "loss": 1.0016, "step": 12521 }, { "epoch": 0.6846130189646336, "grad_norm": 3.0587151050567627, "learning_rate": 2.390414105863008e-05, "loss": 1.0183, "step": 12522 }, { "epoch": 0.6846676917819922, "grad_norm": 2.3460731506347656, "learning_rate": 2.3896589426046538e-05, "loss": 1.0455, "step": 12523 }, { "epoch": 0.6847223645993508, "grad_norm": 2.4901857376098633, "learning_rate": 2.388903861191243e-05, "loss": 0.9692, "step": 12524 }, { "epoch": 0.6847770374167094, "grad_norm": 2.8430469036102295, "learning_rate": 2.3881488616464493e-05, "loss": 0.9145, "step": 12525 }, { "epoch": 0.684831710234068, "grad_norm": 3.0498435497283936, "learning_rate": 2.387393943993946e-05, "loss": 1.0905, "step": 12526 }, { "epoch": 0.6848863830514266, "grad_norm": 2.727907419204712, "learning_rate": 2.3866391082573997e-05, "loss": 0.9211, "step": 12527 }, { "epoch": 0.6849410558687853, "grad_norm": 2.3594624996185303, "learning_rate": 2.385884354460483e-05, "loss": 0.9286, "step": 12528 }, { "epoch": 0.6849957286861439, "grad_norm": 3.2158422470092773, "learning_rate": 2.3851296826268577e-05, "loss": 0.9818, "step": 12529 }, { "epoch": 0.6850504015035025, "grad_norm": 2.4951658248901367, "learning_rate": 2.3843750927801855e-05, "loss": 1.0076, "step": 12530 }, { "epoch": 0.6851050743208611, "grad_norm": 2.3585662841796875, "learning_rate": 2.3836205849441266e-05, "loss": 1.1186, "step": 12531 }, { "epoch": 0.6851597471382197, "grad_norm": 2.3902840614318848, "learning_rate": 2.382866159142338e-05, "loss": 1.0477, "step": 12532 }, { "epoch": 0.6852144199555783, "grad_norm": 2.692687749862671, "learning_rate": 2.3821118153984732e-05, "loss": 1.13, "step": 12533 }, { "epoch": 0.6852690927729369, "grad_norm": 2.7185468673706055, "learning_rate": 2.3813575537361856e-05, "loss": 1.0124, "step": 12534 }, { "epoch": 0.6853237655902956, "grad_norm": 2.3226969242095947, "learning_rate": 2.3806033741791227e-05, "loss": 0.9668, "step": 12535 }, { "epoch": 0.6853784384076542, "grad_norm": 2.4121320247650146, "learning_rate": 2.3798492767509317e-05, "loss": 0.9815, "step": 12536 }, { "epoch": 0.6854331112250128, "grad_norm": 2.6295065879821777, "learning_rate": 2.3790952614752554e-05, "loss": 1.1176, "step": 12537 }, { "epoch": 0.6854877840423714, "grad_norm": 2.2965545654296875, "learning_rate": 2.3783413283757385e-05, "loss": 0.9868, "step": 12538 }, { "epoch": 0.68554245685973, "grad_norm": 2.5066068172454834, "learning_rate": 2.3775874774760175e-05, "loss": 1.0507, "step": 12539 }, { "epoch": 0.6855971296770886, "grad_norm": 2.968661308288574, "learning_rate": 2.37683370879973e-05, "loss": 0.9017, "step": 12540 }, { "epoch": 0.6856518024944472, "grad_norm": 2.627368927001953, "learning_rate": 2.376080022370509e-05, "loss": 1.1324, "step": 12541 }, { "epoch": 0.685706475311806, "grad_norm": 2.872601270675659, "learning_rate": 2.375326418211985e-05, "loss": 1.1332, "step": 12542 }, { "epoch": 0.6857611481291646, "grad_norm": 2.999735116958618, "learning_rate": 2.3745728963477882e-05, "loss": 0.9658, "step": 12543 }, { "epoch": 0.6858158209465232, "grad_norm": 3.7429418563842773, "learning_rate": 2.3738194568015432e-05, "loss": 1.0183, "step": 12544 }, { "epoch": 0.6858704937638818, "grad_norm": 2.8423709869384766, "learning_rate": 2.373066099596874e-05, "loss": 1.1195, "step": 12545 }, { "epoch": 0.6859251665812404, "grad_norm": 2.2599332332611084, "learning_rate": 2.3723128247574015e-05, "loss": 0.941, "step": 12546 }, { "epoch": 0.685979839398599, "grad_norm": 2.002310276031494, "learning_rate": 2.3715596323067425e-05, "loss": 0.9059, "step": 12547 }, { "epoch": 0.6860345122159577, "grad_norm": 3.005964756011963, "learning_rate": 2.370806522268515e-05, "loss": 1.1963, "step": 12548 }, { "epoch": 0.6860891850333163, "grad_norm": 3.2065718173980713, "learning_rate": 2.3700534946663315e-05, "loss": 1.1283, "step": 12549 }, { "epoch": 0.6861438578506749, "grad_norm": 2.241028070449829, "learning_rate": 2.3693005495238028e-05, "loss": 0.9347, "step": 12550 }, { "epoch": 0.6861985306680335, "grad_norm": 3.0798144340515137, "learning_rate": 2.3685476868645355e-05, "loss": 1.0854, "step": 12551 }, { "epoch": 0.6862532034853921, "grad_norm": 3.9636223316192627, "learning_rate": 2.3677949067121364e-05, "loss": 1.0872, "step": 12552 }, { "epoch": 0.6863078763027507, "grad_norm": 2.1847286224365234, "learning_rate": 2.367042209090207e-05, "loss": 0.9912, "step": 12553 }, { "epoch": 0.6863625491201093, "grad_norm": 2.212219715118408, "learning_rate": 2.3662895940223485e-05, "loss": 1.03, "step": 12554 }, { "epoch": 0.686417221937468, "grad_norm": 3.641014814376831, "learning_rate": 2.365537061532157e-05, "loss": 1.1251, "step": 12555 }, { "epoch": 0.6864718947548266, "grad_norm": 2.207946538925171, "learning_rate": 2.3647846116432292e-05, "loss": 0.9514, "step": 12556 }, { "epoch": 0.6865265675721852, "grad_norm": 2.622009754180908, "learning_rate": 2.364032244379155e-05, "loss": 1.0677, "step": 12557 }, { "epoch": 0.6865812403895438, "grad_norm": 2.103834867477417, "learning_rate": 2.3632799597635276e-05, "loss": 1.0851, "step": 12558 }, { "epoch": 0.6866359132069024, "grad_norm": 2.5778560638427734, "learning_rate": 2.362527757819933e-05, "loss": 0.9902, "step": 12559 }, { "epoch": 0.686690586024261, "grad_norm": 2.3894410133361816, "learning_rate": 2.361775638571955e-05, "loss": 0.9743, "step": 12560 }, { "epoch": 0.6867452588416196, "grad_norm": 2.3433163166046143, "learning_rate": 2.3610236020431758e-05, "loss": 0.8358, "step": 12561 }, { "epoch": 0.6867999316589783, "grad_norm": 2.6777641773223877, "learning_rate": 2.3602716482571757e-05, "loss": 1.0997, "step": 12562 }, { "epoch": 0.686854604476337, "grad_norm": 3.3191816806793213, "learning_rate": 2.359519777237531e-05, "loss": 1.1483, "step": 12563 }, { "epoch": 0.6869092772936956, "grad_norm": 4.358781814575195, "learning_rate": 2.3587679890078156e-05, "loss": 1.0242, "step": 12564 }, { "epoch": 0.6869639501110542, "grad_norm": 2.4262940883636475, "learning_rate": 2.3580162835916014e-05, "loss": 0.9222, "step": 12565 }, { "epoch": 0.6870186229284128, "grad_norm": 2.5840747356414795, "learning_rate": 2.3572646610124575e-05, "loss": 0.9048, "step": 12566 }, { "epoch": 0.6870732957457714, "grad_norm": 2.7970893383026123, "learning_rate": 2.356513121293949e-05, "loss": 1.0687, "step": 12567 }, { "epoch": 0.68712796856313, "grad_norm": 2.5979719161987305, "learning_rate": 2.3557616644596427e-05, "loss": 1.0283, "step": 12568 }, { "epoch": 0.6871826413804887, "grad_norm": 2.3256113529205322, "learning_rate": 2.3550102905330985e-05, "loss": 1.0057, "step": 12569 }, { "epoch": 0.6872373141978473, "grad_norm": 2.5474929809570312, "learning_rate": 2.354258999537875e-05, "loss": 0.9777, "step": 12570 }, { "epoch": 0.6872919870152059, "grad_norm": 3.542719841003418, "learning_rate": 2.3535077914975277e-05, "loss": 1.0351, "step": 12571 }, { "epoch": 0.6873466598325645, "grad_norm": 2.391545534133911, "learning_rate": 2.352756666435611e-05, "loss": 1.1653, "step": 12572 }, { "epoch": 0.6874013326499231, "grad_norm": 3.51374888420105, "learning_rate": 2.352005624375675e-05, "loss": 0.9404, "step": 12573 }, { "epoch": 0.6874560054672817, "grad_norm": 2.698169469833374, "learning_rate": 2.3512546653412682e-05, "loss": 1.1811, "step": 12574 }, { "epoch": 0.6875106782846404, "grad_norm": 2.880267858505249, "learning_rate": 2.3505037893559367e-05, "loss": 1.1582, "step": 12575 }, { "epoch": 0.687565351101999, "grad_norm": 2.958343267440796, "learning_rate": 2.3497529964432208e-05, "loss": 1.1902, "step": 12576 }, { "epoch": 0.6876200239193576, "grad_norm": 2.3976778984069824, "learning_rate": 2.349002286626666e-05, "loss": 0.9516, "step": 12577 }, { "epoch": 0.6876746967367162, "grad_norm": 2.0555288791656494, "learning_rate": 2.3482516599298065e-05, "loss": 0.8858, "step": 12578 }, { "epoch": 0.6877293695540748, "grad_norm": 2.3547935485839844, "learning_rate": 2.347501116376179e-05, "loss": 0.9965, "step": 12579 }, { "epoch": 0.6877840423714334, "grad_norm": 2.8308358192443848, "learning_rate": 2.3467506559893154e-05, "loss": 0.9968, "step": 12580 }, { "epoch": 0.687838715188792, "grad_norm": 3.0012125968933105, "learning_rate": 2.3460002787927464e-05, "loss": 0.9812, "step": 12581 }, { "epoch": 0.6878933880061507, "grad_norm": 2.8519558906555176, "learning_rate": 2.3452499848099985e-05, "loss": 1.1598, "step": 12582 }, { "epoch": 0.6879480608235093, "grad_norm": 2.57134747505188, "learning_rate": 2.3444997740645973e-05, "loss": 0.8729, "step": 12583 }, { "epoch": 0.688002733640868, "grad_norm": 2.7621114253997803, "learning_rate": 2.3437496465800646e-05, "loss": 1.1259, "step": 12584 }, { "epoch": 0.6880574064582266, "grad_norm": 2.066312313079834, "learning_rate": 2.34299960237992e-05, "loss": 0.8072, "step": 12585 }, { "epoch": 0.6881120792755852, "grad_norm": 2.2783570289611816, "learning_rate": 2.342249641487679e-05, "loss": 0.9592, "step": 12586 }, { "epoch": 0.6881667520929438, "grad_norm": 2.8852593898773193, "learning_rate": 2.3414997639268586e-05, "loss": 1.1717, "step": 12587 }, { "epoch": 0.6882214249103024, "grad_norm": 2.713148355484009, "learning_rate": 2.34074996972097e-05, "loss": 1.0968, "step": 12588 }, { "epoch": 0.6882760977276611, "grad_norm": 2.6421539783477783, "learning_rate": 2.340000258893522e-05, "loss": 1.1654, "step": 12589 }, { "epoch": 0.6883307705450197, "grad_norm": 3.0928759574890137, "learning_rate": 2.3392506314680207e-05, "loss": 1.1447, "step": 12590 }, { "epoch": 0.6883854433623783, "grad_norm": 2.385270833969116, "learning_rate": 2.3385010874679704e-05, "loss": 1.0562, "step": 12591 }, { "epoch": 0.6884401161797369, "grad_norm": 2.7442121505737305, "learning_rate": 2.3377516269168715e-05, "loss": 1.1961, "step": 12592 }, { "epoch": 0.6884947889970955, "grad_norm": 2.914600372314453, "learning_rate": 2.3370022498382238e-05, "loss": 0.9643, "step": 12593 }, { "epoch": 0.6885494618144541, "grad_norm": 2.464845657348633, "learning_rate": 2.336252956255523e-05, "loss": 0.9741, "step": 12594 }, { "epoch": 0.6886041346318127, "grad_norm": 2.6066129207611084, "learning_rate": 2.3355037461922625e-05, "loss": 1.0317, "step": 12595 }, { "epoch": 0.6886588074491714, "grad_norm": 2.943108320236206, "learning_rate": 2.334754619671931e-05, "loss": 1.1133, "step": 12596 }, { "epoch": 0.68871348026653, "grad_norm": 3.8171215057373047, "learning_rate": 2.3340055767180214e-05, "loss": 0.9222, "step": 12597 }, { "epoch": 0.6887681530838886, "grad_norm": 5.198548316955566, "learning_rate": 2.333256617354016e-05, "loss": 1.494, "step": 12598 }, { "epoch": 0.6888228259012472, "grad_norm": 3.000150680541992, "learning_rate": 2.3325077416033986e-05, "loss": 1.0953, "step": 12599 }, { "epoch": 0.6888774987186058, "grad_norm": 2.9203553199768066, "learning_rate": 2.331758949489649e-05, "loss": 0.8452, "step": 12600 }, { "epoch": 0.6889321715359644, "grad_norm": 2.216273307800293, "learning_rate": 2.331010241036246e-05, "loss": 0.8373, "step": 12601 }, { "epoch": 0.6889868443533231, "grad_norm": 2.376295804977417, "learning_rate": 2.3302616162666636e-05, "loss": 0.9891, "step": 12602 }, { "epoch": 0.6890415171706817, "grad_norm": 3.6823246479034424, "learning_rate": 2.3295130752043747e-05, "loss": 1.0235, "step": 12603 }, { "epoch": 0.6890961899880403, "grad_norm": 2.238354444503784, "learning_rate": 2.3287646178728495e-05, "loss": 0.9574, "step": 12604 }, { "epoch": 0.689150862805399, "grad_norm": 2.7708547115325928, "learning_rate": 2.3280162442955545e-05, "loss": 0.8888, "step": 12605 }, { "epoch": 0.6892055356227575, "grad_norm": 3.7001335620880127, "learning_rate": 2.3272679544959525e-05, "loss": 1.2228, "step": 12606 }, { "epoch": 0.6892602084401162, "grad_norm": 3.074371576309204, "learning_rate": 2.3265197484975098e-05, "loss": 1.1117, "step": 12607 }, { "epoch": 0.6893148812574748, "grad_norm": 2.6461009979248047, "learning_rate": 2.3257716263236833e-05, "loss": 1.1204, "step": 12608 }, { "epoch": 0.6893695540748335, "grad_norm": 2.3156697750091553, "learning_rate": 2.32502358799793e-05, "loss": 1.0321, "step": 12609 }, { "epoch": 0.6894242268921921, "grad_norm": 2.491529703140259, "learning_rate": 2.3242756335437045e-05, "loss": 1.0264, "step": 12610 }, { "epoch": 0.6894788997095507, "grad_norm": 2.514676094055176, "learning_rate": 2.3235277629844567e-05, "loss": 1.1135, "step": 12611 }, { "epoch": 0.6895335725269093, "grad_norm": 2.5938735008239746, "learning_rate": 2.322779976343637e-05, "loss": 0.9913, "step": 12612 }, { "epoch": 0.6895882453442679, "grad_norm": 3.073945999145508, "learning_rate": 2.322032273644691e-05, "loss": 1.0882, "step": 12613 }, { "epoch": 0.6896429181616265, "grad_norm": 2.468518018722534, "learning_rate": 2.3212846549110618e-05, "loss": 1.0812, "step": 12614 }, { "epoch": 0.6896975909789851, "grad_norm": 2.2855846881866455, "learning_rate": 2.3205371201661913e-05, "loss": 1.0229, "step": 12615 }, { "epoch": 0.6897522637963438, "grad_norm": 2.640982151031494, "learning_rate": 2.3197896694335153e-05, "loss": 0.8973, "step": 12616 }, { "epoch": 0.6898069366137024, "grad_norm": 3.3172476291656494, "learning_rate": 2.3190423027364728e-05, "loss": 0.9786, "step": 12617 }, { "epoch": 0.689861609431061, "grad_norm": 2.866981267929077, "learning_rate": 2.3182950200984958e-05, "loss": 1.0618, "step": 12618 }, { "epoch": 0.6899162822484196, "grad_norm": 2.812922477722168, "learning_rate": 2.3175478215430147e-05, "loss": 1.3657, "step": 12619 }, { "epoch": 0.6899709550657782, "grad_norm": 2.364445686340332, "learning_rate": 2.3168007070934562e-05, "loss": 1.0099, "step": 12620 }, { "epoch": 0.6900256278831368, "grad_norm": 2.277116060256958, "learning_rate": 2.3160536767732467e-05, "loss": 0.9143, "step": 12621 }, { "epoch": 0.6900803007004954, "grad_norm": 2.221538782119751, "learning_rate": 2.315306730605808e-05, "loss": 0.8824, "step": 12622 }, { "epoch": 0.6901349735178541, "grad_norm": 2.6578562259674072, "learning_rate": 2.3145598686145597e-05, "loss": 1.2198, "step": 12623 }, { "epoch": 0.6901896463352127, "grad_norm": 2.8607771396636963, "learning_rate": 2.3138130908229194e-05, "loss": 0.9664, "step": 12624 }, { "epoch": 0.6902443191525713, "grad_norm": 2.821418523788452, "learning_rate": 2.3130663972542997e-05, "loss": 1.0845, "step": 12625 }, { "epoch": 0.6902989919699299, "grad_norm": 2.3661251068115234, "learning_rate": 2.3123197879321163e-05, "loss": 0.8357, "step": 12626 }, { "epoch": 0.6903536647872885, "grad_norm": 1.9617817401885986, "learning_rate": 2.3115732628797765e-05, "loss": 0.9781, "step": 12627 }, { "epoch": 0.6904083376046471, "grad_norm": 2.5558347702026367, "learning_rate": 2.3108268221206875e-05, "loss": 0.8655, "step": 12628 }, { "epoch": 0.6904630104220059, "grad_norm": 2.5678629875183105, "learning_rate": 2.3100804656782522e-05, "loss": 1.1383, "step": 12629 }, { "epoch": 0.6905176832393645, "grad_norm": 2.175382137298584, "learning_rate": 2.3093341935758727e-05, "loss": 0.8998, "step": 12630 }, { "epoch": 0.6905723560567231, "grad_norm": 2.4261937141418457, "learning_rate": 2.3085880058369475e-05, "loss": 1.063, "step": 12631 }, { "epoch": 0.6906270288740817, "grad_norm": 3.3270998001098633, "learning_rate": 2.307841902484873e-05, "loss": 1.1277, "step": 12632 }, { "epoch": 0.6906817016914403, "grad_norm": 2.149839401245117, "learning_rate": 2.3070958835430424e-05, "loss": 0.8687, "step": 12633 }, { "epoch": 0.6907363745087989, "grad_norm": 2.4817636013031006, "learning_rate": 2.3063499490348462e-05, "loss": 0.8069, "step": 12634 }, { "epoch": 0.6907910473261575, "grad_norm": 2.837568998336792, "learning_rate": 2.305604098983671e-05, "loss": 1.197, "step": 12635 }, { "epoch": 0.6908457201435162, "grad_norm": 2.487238645553589, "learning_rate": 2.3048583334129055e-05, "loss": 0.956, "step": 12636 }, { "epoch": 0.6909003929608748, "grad_norm": 2.691133975982666, "learning_rate": 2.304112652345931e-05, "loss": 0.9571, "step": 12637 }, { "epoch": 0.6909550657782334, "grad_norm": 3.1934258937835693, "learning_rate": 2.3033670558061278e-05, "loss": 1.2977, "step": 12638 }, { "epoch": 0.691009738595592, "grad_norm": 2.6642894744873047, "learning_rate": 2.302621543816873e-05, "loss": 0.9302, "step": 12639 }, { "epoch": 0.6910644114129506, "grad_norm": 2.8873484134674072, "learning_rate": 2.3018761164015422e-05, "loss": 1.0196, "step": 12640 }, { "epoch": 0.6911190842303092, "grad_norm": 2.6015326976776123, "learning_rate": 2.3011307735835075e-05, "loss": 0.8944, "step": 12641 }, { "epoch": 0.6911737570476678, "grad_norm": 2.315153121948242, "learning_rate": 2.3003855153861375e-05, "loss": 0.9648, "step": 12642 }, { "epoch": 0.6912284298650265, "grad_norm": 2.66605544090271, "learning_rate": 2.2996403418328e-05, "loss": 0.8735, "step": 12643 }, { "epoch": 0.6912831026823851, "grad_norm": 2.168510913848877, "learning_rate": 2.2988952529468588e-05, "loss": 0.8112, "step": 12644 }, { "epoch": 0.6913377754997437, "grad_norm": 2.7343950271606445, "learning_rate": 2.2981502487516764e-05, "loss": 1.122, "step": 12645 }, { "epoch": 0.6913924483171023, "grad_norm": 2.1009061336517334, "learning_rate": 2.2974053292706105e-05, "loss": 0.8724, "step": 12646 }, { "epoch": 0.6914471211344609, "grad_norm": 2.746880292892456, "learning_rate": 2.296660494527018e-05, "loss": 0.9682, "step": 12647 }, { "epoch": 0.6915017939518195, "grad_norm": 2.868680715560913, "learning_rate": 2.295915744544251e-05, "loss": 1.1405, "step": 12648 }, { "epoch": 0.6915564667691781, "grad_norm": 3.6862564086914062, "learning_rate": 2.295171079345664e-05, "loss": 0.7859, "step": 12649 }, { "epoch": 0.6916111395865369, "grad_norm": 2.5076706409454346, "learning_rate": 2.294426498954603e-05, "loss": 1.1445, "step": 12650 }, { "epoch": 0.6916658124038955, "grad_norm": 3.1092514991760254, "learning_rate": 2.2936820033944136e-05, "loss": 0.8497, "step": 12651 }, { "epoch": 0.6917204852212541, "grad_norm": 2.740936279296875, "learning_rate": 2.2929375926884396e-05, "loss": 1.1688, "step": 12652 }, { "epoch": 0.6917751580386127, "grad_norm": 2.651374340057373, "learning_rate": 2.2921932668600204e-05, "loss": 1.0712, "step": 12653 }, { "epoch": 0.6918298308559713, "grad_norm": 2.8909850120544434, "learning_rate": 2.291449025932495e-05, "loss": 0.8608, "step": 12654 }, { "epoch": 0.6918845036733299, "grad_norm": 2.816999673843384, "learning_rate": 2.290704869929197e-05, "loss": 1.0694, "step": 12655 }, { "epoch": 0.6919391764906886, "grad_norm": 2.76155161857605, "learning_rate": 2.28996079887346e-05, "loss": 1.0198, "step": 12656 }, { "epoch": 0.6919938493080472, "grad_norm": 2.5856595039367676, "learning_rate": 2.2892168127886125e-05, "loss": 1.0526, "step": 12657 }, { "epoch": 0.6920485221254058, "grad_norm": 2.4060051441192627, "learning_rate": 2.2884729116979825e-05, "loss": 1.1609, "step": 12658 }, { "epoch": 0.6921031949427644, "grad_norm": 2.553886651992798, "learning_rate": 2.2877290956248936e-05, "loss": 1.015, "step": 12659 }, { "epoch": 0.692157867760123, "grad_norm": 2.484262704849243, "learning_rate": 2.2869853645926682e-05, "loss": 1.0274, "step": 12660 }, { "epoch": 0.6922125405774816, "grad_norm": 2.4718923568725586, "learning_rate": 2.2862417186246228e-05, "loss": 1.0144, "step": 12661 }, { "epoch": 0.6922672133948402, "grad_norm": 2.402182102203369, "learning_rate": 2.2854981577440777e-05, "loss": 1.0113, "step": 12662 }, { "epoch": 0.6923218862121989, "grad_norm": 2.715723991394043, "learning_rate": 2.2847546819743453e-05, "loss": 0.9212, "step": 12663 }, { "epoch": 0.6923765590295575, "grad_norm": 2.260871171951294, "learning_rate": 2.2840112913387358e-05, "loss": 0.9626, "step": 12664 }, { "epoch": 0.6924312318469161, "grad_norm": 3.4307467937469482, "learning_rate": 2.2832679858605584e-05, "loss": 1.0428, "step": 12665 }, { "epoch": 0.6924859046642747, "grad_norm": 2.1173460483551025, "learning_rate": 2.2825247655631177e-05, "loss": 1.0399, "step": 12666 }, { "epoch": 0.6925405774816333, "grad_norm": 2.5878939628601074, "learning_rate": 2.2817816304697176e-05, "loss": 1.0442, "step": 12667 }, { "epoch": 0.6925952502989919, "grad_norm": 2.0793113708496094, "learning_rate": 2.2810385806036583e-05, "loss": 0.7478, "step": 12668 }, { "epoch": 0.6926499231163505, "grad_norm": 2.7660794258117676, "learning_rate": 2.2802956159882373e-05, "loss": 1.055, "step": 12669 }, { "epoch": 0.6927045959337093, "grad_norm": 3.0883185863494873, "learning_rate": 2.2795527366467496e-05, "loss": 0.9841, "step": 12670 }, { "epoch": 0.6927592687510679, "grad_norm": 2.639946699142456, "learning_rate": 2.2788099426024874e-05, "loss": 1.0244, "step": 12671 }, { "epoch": 0.6928139415684265, "grad_norm": 2.185408353805542, "learning_rate": 2.2780672338787406e-05, "loss": 0.9859, "step": 12672 }, { "epoch": 0.6928686143857851, "grad_norm": 3.8110392093658447, "learning_rate": 2.2773246104987965e-05, "loss": 1.0121, "step": 12673 }, { "epoch": 0.6929232872031437, "grad_norm": 3.1139395236968994, "learning_rate": 2.276582072485937e-05, "loss": 1.0228, "step": 12674 }, { "epoch": 0.6929779600205023, "grad_norm": 3.282764434814453, "learning_rate": 2.2758396198634476e-05, "loss": 1.0087, "step": 12675 }, { "epoch": 0.6930326328378609, "grad_norm": 3.2233035564422607, "learning_rate": 2.275097252654605e-05, "loss": 1.2438, "step": 12676 }, { "epoch": 0.6930873056552196, "grad_norm": 3.086615562438965, "learning_rate": 2.274354970882686e-05, "loss": 0.8433, "step": 12677 }, { "epoch": 0.6931419784725782, "grad_norm": 2.7077488899230957, "learning_rate": 2.2736127745709644e-05, "loss": 1.09, "step": 12678 }, { "epoch": 0.6931966512899368, "grad_norm": 3.135850667953491, "learning_rate": 2.2728706637427104e-05, "loss": 0.9915, "step": 12679 }, { "epoch": 0.6932513241072954, "grad_norm": 2.2134108543395996, "learning_rate": 2.2721286384211926e-05, "loss": 1.0798, "step": 12680 }, { "epoch": 0.693305996924654, "grad_norm": 2.840503454208374, "learning_rate": 2.2713866986296768e-05, "loss": 0.9078, "step": 12681 }, { "epoch": 0.6933606697420126, "grad_norm": 2.7810001373291016, "learning_rate": 2.2706448443914258e-05, "loss": 0.9497, "step": 12682 }, { "epoch": 0.6934153425593713, "grad_norm": 2.6370139122009277, "learning_rate": 2.2699030757296992e-05, "loss": 1.1167, "step": 12683 }, { "epoch": 0.6934700153767299, "grad_norm": 2.5218820571899414, "learning_rate": 2.269161392667753e-05, "loss": 1.1077, "step": 12684 }, { "epoch": 0.6935246881940885, "grad_norm": 2.8146560192108154, "learning_rate": 2.2684197952288453e-05, "loss": 0.7312, "step": 12685 }, { "epoch": 0.6935793610114471, "grad_norm": 2.5385875701904297, "learning_rate": 2.2676782834362276e-05, "loss": 1.0523, "step": 12686 }, { "epoch": 0.6936340338288057, "grad_norm": 3.3538870811462402, "learning_rate": 2.2669368573131487e-05, "loss": 0.9449, "step": 12687 }, { "epoch": 0.6936887066461643, "grad_norm": 2.774348258972168, "learning_rate": 2.2661955168828548e-05, "loss": 1.0873, "step": 12688 }, { "epoch": 0.6937433794635229, "grad_norm": 2.3171803951263428, "learning_rate": 2.265454262168591e-05, "loss": 0.9228, "step": 12689 }, { "epoch": 0.6937980522808816, "grad_norm": 2.5339479446411133, "learning_rate": 2.2647130931935973e-05, "loss": 0.9855, "step": 12690 }, { "epoch": 0.6938527250982403, "grad_norm": 3.018153190612793, "learning_rate": 2.2639720099811134e-05, "loss": 1.0197, "step": 12691 }, { "epoch": 0.6939073979155989, "grad_norm": 2.2525994777679443, "learning_rate": 2.2632310125543755e-05, "loss": 0.9141, "step": 12692 }, { "epoch": 0.6939620707329575, "grad_norm": 2.984248399734497, "learning_rate": 2.262490100936617e-05, "loss": 1.0805, "step": 12693 }, { "epoch": 0.6940167435503161, "grad_norm": 2.151041030883789, "learning_rate": 2.261749275151065e-05, "loss": 0.9362, "step": 12694 }, { "epoch": 0.6940714163676747, "grad_norm": 2.3532567024230957, "learning_rate": 2.261008535220953e-05, "loss": 0.8229, "step": 12695 }, { "epoch": 0.6941260891850333, "grad_norm": 2.8248488903045654, "learning_rate": 2.2602678811695037e-05, "loss": 1.0058, "step": 12696 }, { "epoch": 0.694180762002392, "grad_norm": 2.5209758281707764, "learning_rate": 2.2595273130199403e-05, "loss": 0.9803, "step": 12697 }, { "epoch": 0.6942354348197506, "grad_norm": 3.908076047897339, "learning_rate": 2.2587868307954813e-05, "loss": 0.9747, "step": 12698 }, { "epoch": 0.6942901076371092, "grad_norm": 2.5614240169525146, "learning_rate": 2.2580464345193448e-05, "loss": 1.013, "step": 12699 }, { "epoch": 0.6943447804544678, "grad_norm": 3.851940393447876, "learning_rate": 2.2573061242147454e-05, "loss": 1.0888, "step": 12700 }, { "epoch": 0.6943994532718264, "grad_norm": 4.123527526855469, "learning_rate": 2.2565658999048946e-05, "loss": 0.9317, "step": 12701 }, { "epoch": 0.694454126089185, "grad_norm": 2.4459338188171387, "learning_rate": 2.2558257616130014e-05, "loss": 0.9885, "step": 12702 }, { "epoch": 0.6945087989065436, "grad_norm": 2.4631588459014893, "learning_rate": 2.2550857093622718e-05, "loss": 1.0188, "step": 12703 }, { "epoch": 0.6945634717239023, "grad_norm": 2.3298678398132324, "learning_rate": 2.254345743175909e-05, "loss": 0.9587, "step": 12704 }, { "epoch": 0.6946181445412609, "grad_norm": 2.233327627182007, "learning_rate": 2.2536058630771163e-05, "loss": 1.0095, "step": 12705 }, { "epoch": 0.6946728173586195, "grad_norm": 3.2848880290985107, "learning_rate": 2.2528660690890908e-05, "loss": 0.9624, "step": 12706 }, { "epoch": 0.6947274901759781, "grad_norm": 3.05550479888916, "learning_rate": 2.2521263612350275e-05, "loss": 1.1234, "step": 12707 }, { "epoch": 0.6947821629933367, "grad_norm": 2.7758593559265137, "learning_rate": 2.2513867395381198e-05, "loss": 1.0564, "step": 12708 }, { "epoch": 0.6948368358106953, "grad_norm": 3.7996633052825928, "learning_rate": 2.250647204021558e-05, "loss": 0.9078, "step": 12709 }, { "epoch": 0.694891508628054, "grad_norm": 2.6342804431915283, "learning_rate": 2.2499077547085296e-05, "loss": 0.7987, "step": 12710 }, { "epoch": 0.6949461814454126, "grad_norm": 3.091865301132202, "learning_rate": 2.2491683916222183e-05, "loss": 0.8855, "step": 12711 }, { "epoch": 0.6950008542627713, "grad_norm": 2.5293772220611572, "learning_rate": 2.2484291147858078e-05, "loss": 1.1664, "step": 12712 }, { "epoch": 0.6950555270801299, "grad_norm": 2.85190486907959, "learning_rate": 2.2476899242224764e-05, "loss": 0.903, "step": 12713 }, { "epoch": 0.6951101998974885, "grad_norm": 2.9972569942474365, "learning_rate": 2.2469508199553997e-05, "loss": 1.1136, "step": 12714 }, { "epoch": 0.6951648727148471, "grad_norm": 2.6244471073150635, "learning_rate": 2.2462118020077543e-05, "loss": 1.0234, "step": 12715 }, { "epoch": 0.6952195455322057, "grad_norm": 2.7424240112304688, "learning_rate": 2.2454728704027104e-05, "loss": 0.931, "step": 12716 }, { "epoch": 0.6952742183495644, "grad_norm": 2.382143259048462, "learning_rate": 2.2447340251634363e-05, "loss": 1.0584, "step": 12717 }, { "epoch": 0.695328891166923, "grad_norm": 2.691537380218506, "learning_rate": 2.2439952663130982e-05, "loss": 0.8489, "step": 12718 }, { "epoch": 0.6953835639842816, "grad_norm": 2.8141977787017822, "learning_rate": 2.2432565938748584e-05, "loss": 1.0047, "step": 12719 }, { "epoch": 0.6954382368016402, "grad_norm": 2.756681203842163, "learning_rate": 2.2425180078718782e-05, "loss": 0.9555, "step": 12720 }, { "epoch": 0.6954929096189988, "grad_norm": 3.0990734100341797, "learning_rate": 2.241779508327315e-05, "loss": 1.0013, "step": 12721 }, { "epoch": 0.6955475824363574, "grad_norm": 2.503868341445923, "learning_rate": 2.2410410952643237e-05, "loss": 0.9653, "step": 12722 }, { "epoch": 0.695602255253716, "grad_norm": 2.950181484222412, "learning_rate": 2.2403027687060563e-05, "loss": 1.1237, "step": 12723 }, { "epoch": 0.6956569280710747, "grad_norm": 2.5409042835235596, "learning_rate": 2.239564528675661e-05, "loss": 1.0761, "step": 12724 }, { "epoch": 0.6957116008884333, "grad_norm": 2.4821465015411377, "learning_rate": 2.238826375196289e-05, "loss": 0.9756, "step": 12725 }, { "epoch": 0.6957662737057919, "grad_norm": 2.602384328842163, "learning_rate": 2.238088308291081e-05, "loss": 1.0731, "step": 12726 }, { "epoch": 0.6958209465231505, "grad_norm": 2.3954856395721436, "learning_rate": 2.237350327983179e-05, "loss": 0.9872, "step": 12727 }, { "epoch": 0.6958756193405091, "grad_norm": 2.4963784217834473, "learning_rate": 2.2366124342957228e-05, "loss": 1.0202, "step": 12728 }, { "epoch": 0.6959302921578677, "grad_norm": 2.4741175174713135, "learning_rate": 2.2358746272518477e-05, "loss": 1.1646, "step": 12729 }, { "epoch": 0.6959849649752263, "grad_norm": 2.4544315338134766, "learning_rate": 2.2351369068746864e-05, "loss": 1.0122, "step": 12730 }, { "epoch": 0.696039637792585, "grad_norm": 2.2768688201904297, "learning_rate": 2.2343992731873698e-05, "loss": 0.9259, "step": 12731 }, { "epoch": 0.6960943106099436, "grad_norm": 2.286010980606079, "learning_rate": 2.2336617262130265e-05, "loss": 0.9344, "step": 12732 }, { "epoch": 0.6961489834273022, "grad_norm": 2.6752004623413086, "learning_rate": 2.232924265974779e-05, "loss": 1.0461, "step": 12733 }, { "epoch": 0.6962036562446609, "grad_norm": 2.919532060623169, "learning_rate": 2.2321868924957535e-05, "loss": 1.1218, "step": 12734 }, { "epoch": 0.6962583290620195, "grad_norm": 2.3011133670806885, "learning_rate": 2.231449605799068e-05, "loss": 0.7758, "step": 12735 }, { "epoch": 0.6963130018793781, "grad_norm": 2.850192070007324, "learning_rate": 2.2307124059078394e-05, "loss": 0.7387, "step": 12736 }, { "epoch": 0.6963676746967368, "grad_norm": 2.427144765853882, "learning_rate": 2.2299752928451816e-05, "loss": 0.9469, "step": 12737 }, { "epoch": 0.6964223475140954, "grad_norm": 2.8001291751861572, "learning_rate": 2.229238266634207e-05, "loss": 0.9287, "step": 12738 }, { "epoch": 0.696477020331454, "grad_norm": 2.2747340202331543, "learning_rate": 2.2285013272980243e-05, "loss": 1.0633, "step": 12739 }, { "epoch": 0.6965316931488126, "grad_norm": 2.7151694297790527, "learning_rate": 2.2277644748597387e-05, "loss": 0.9284, "step": 12740 }, { "epoch": 0.6965863659661712, "grad_norm": 2.4348440170288086, "learning_rate": 2.2270277093424542e-05, "loss": 1.0871, "step": 12741 }, { "epoch": 0.6966410387835298, "grad_norm": 4.3517045974731445, "learning_rate": 2.2262910307692715e-05, "loss": 1.2211, "step": 12742 }, { "epoch": 0.6966957116008884, "grad_norm": 2.553497791290283, "learning_rate": 2.225554439163286e-05, "loss": 1.1149, "step": 12743 }, { "epoch": 0.6967503844182471, "grad_norm": 2.9988999366760254, "learning_rate": 2.224817934547597e-05, "loss": 1.0056, "step": 12744 }, { "epoch": 0.6968050572356057, "grad_norm": 2.7340598106384277, "learning_rate": 2.2240815169452956e-05, "loss": 0.8079, "step": 12745 }, { "epoch": 0.6968597300529643, "grad_norm": 3.1419880390167236, "learning_rate": 2.2233451863794712e-05, "loss": 0.8347, "step": 12746 }, { "epoch": 0.6969144028703229, "grad_norm": 3.146704912185669, "learning_rate": 2.2226089428732107e-05, "loss": 1.0766, "step": 12747 }, { "epoch": 0.6969690756876815, "grad_norm": 3.0590498447418213, "learning_rate": 2.2218727864495977e-05, "loss": 1.0807, "step": 12748 }, { "epoch": 0.6970237485050401, "grad_norm": 2.905620813369751, "learning_rate": 2.2211367171317142e-05, "loss": 0.9666, "step": 12749 }, { "epoch": 0.6970784213223987, "grad_norm": 2.279930353164673, "learning_rate": 2.2204007349426402e-05, "loss": 0.9507, "step": 12750 }, { "epoch": 0.6971330941397574, "grad_norm": 2.458890676498413, "learning_rate": 2.2196648399054502e-05, "loss": 0.911, "step": 12751 }, { "epoch": 0.697187766957116, "grad_norm": 2.4117355346679688, "learning_rate": 2.218929032043218e-05, "loss": 1.1226, "step": 12752 }, { "epoch": 0.6972424397744746, "grad_norm": 2.9797070026397705, "learning_rate": 2.2181933113790127e-05, "loss": 1.1422, "step": 12753 }, { "epoch": 0.6972971125918332, "grad_norm": 2.8633031845092773, "learning_rate": 2.217457677935905e-05, "loss": 1.1652, "step": 12754 }, { "epoch": 0.6973517854091918, "grad_norm": 2.7802205085754395, "learning_rate": 2.2167221317369595e-05, "loss": 1.0392, "step": 12755 }, { "epoch": 0.6974064582265505, "grad_norm": 3.3254220485687256, "learning_rate": 2.2159866728052382e-05, "loss": 0.91, "step": 12756 }, { "epoch": 0.697461131043909, "grad_norm": 2.6587374210357666, "learning_rate": 2.2152513011638e-05, "loss": 0.9484, "step": 12757 }, { "epoch": 0.6975158038612678, "grad_norm": 3.2706222534179688, "learning_rate": 2.214516016835702e-05, "loss": 1.1046, "step": 12758 }, { "epoch": 0.6975704766786264, "grad_norm": 2.4504313468933105, "learning_rate": 2.213780819843999e-05, "loss": 0.9682, "step": 12759 }, { "epoch": 0.697625149495985, "grad_norm": 2.713257074356079, "learning_rate": 2.2130457102117418e-05, "loss": 0.9862, "step": 12760 }, { "epoch": 0.6976798223133436, "grad_norm": 2.197697877883911, "learning_rate": 2.2123106879619797e-05, "loss": 0.8376, "step": 12761 }, { "epoch": 0.6977344951307022, "grad_norm": 2.485894203186035, "learning_rate": 2.211575753117759e-05, "loss": 1.0368, "step": 12762 }, { "epoch": 0.6977891679480608, "grad_norm": 6.239354133605957, "learning_rate": 2.2108409057021202e-05, "loss": 1.1667, "step": 12763 }, { "epoch": 0.6978438407654194, "grad_norm": 3.8648149967193604, "learning_rate": 2.2101061457381072e-05, "loss": 1.0943, "step": 12764 }, { "epoch": 0.6978985135827781, "grad_norm": 3.0961179733276367, "learning_rate": 2.209371473248757e-05, "loss": 1.1744, "step": 12765 }, { "epoch": 0.6979531864001367, "grad_norm": 2.9730215072631836, "learning_rate": 2.208636888257104e-05, "loss": 1.1574, "step": 12766 }, { "epoch": 0.6980078592174953, "grad_norm": 2.774005889892578, "learning_rate": 2.2079023907861808e-05, "loss": 1.0024, "step": 12767 }, { "epoch": 0.6980625320348539, "grad_norm": 2.508789300918579, "learning_rate": 2.2071679808590167e-05, "loss": 0.9078, "step": 12768 }, { "epoch": 0.6981172048522125, "grad_norm": 2.332582712173462, "learning_rate": 2.2064336584986385e-05, "loss": 0.9495, "step": 12769 }, { "epoch": 0.6981718776695711, "grad_norm": 2.3115572929382324, "learning_rate": 2.2056994237280697e-05, "loss": 0.9937, "step": 12770 }, { "epoch": 0.6982265504869298, "grad_norm": 3.579118251800537, "learning_rate": 2.2049652765703326e-05, "loss": 1.2441, "step": 12771 }, { "epoch": 0.6982812233042884, "grad_norm": 4.045197486877441, "learning_rate": 2.2042312170484453e-05, "loss": 1.2178, "step": 12772 }, { "epoch": 0.698335896121647, "grad_norm": 2.304619789123535, "learning_rate": 2.2034972451854213e-05, "loss": 0.9853, "step": 12773 }, { "epoch": 0.6983905689390056, "grad_norm": 2.6045608520507812, "learning_rate": 2.202763361004278e-05, "loss": 1.0903, "step": 12774 }, { "epoch": 0.6984452417563642, "grad_norm": 2.748159408569336, "learning_rate": 2.2020295645280236e-05, "loss": 1.0405, "step": 12775 }, { "epoch": 0.6984999145737228, "grad_norm": 2.768920421600342, "learning_rate": 2.201295855779666e-05, "loss": 1.2392, "step": 12776 }, { "epoch": 0.6985545873910814, "grad_norm": 2.8066539764404297, "learning_rate": 2.2005622347822084e-05, "loss": 0.9809, "step": 12777 }, { "epoch": 0.6986092602084402, "grad_norm": 2.187250852584839, "learning_rate": 2.1998287015586548e-05, "loss": 0.8258, "step": 12778 }, { "epoch": 0.6986639330257988, "grad_norm": 2.7039361000061035, "learning_rate": 2.199095256132004e-05, "loss": 1.0506, "step": 12779 }, { "epoch": 0.6987186058431574, "grad_norm": 2.628802537918091, "learning_rate": 2.198361898525252e-05, "loss": 1.0553, "step": 12780 }, { "epoch": 0.698773278660516, "grad_norm": 4.075634956359863, "learning_rate": 2.197628628761393e-05, "loss": 0.9707, "step": 12781 }, { "epoch": 0.6988279514778746, "grad_norm": 2.9097564220428467, "learning_rate": 2.196895446863415e-05, "loss": 1.099, "step": 12782 }, { "epoch": 0.6988826242952332, "grad_norm": 2.399228096008301, "learning_rate": 2.1961623528543124e-05, "loss": 0.9706, "step": 12783 }, { "epoch": 0.6989372971125918, "grad_norm": 2.1231541633605957, "learning_rate": 2.1954293467570662e-05, "loss": 0.9426, "step": 12784 }, { "epoch": 0.6989919699299505, "grad_norm": 2.7664670944213867, "learning_rate": 2.1946964285946614e-05, "loss": 1.0975, "step": 12785 }, { "epoch": 0.6990466427473091, "grad_norm": 2.465397834777832, "learning_rate": 2.1939635983900764e-05, "loss": 1.0303, "step": 12786 }, { "epoch": 0.6991013155646677, "grad_norm": 2.646587371826172, "learning_rate": 2.1932308561662894e-05, "loss": 0.92, "step": 12787 }, { "epoch": 0.6991559883820263, "grad_norm": 2.878695487976074, "learning_rate": 2.1924982019462742e-05, "loss": 0.8782, "step": 12788 }, { "epoch": 0.6992106611993849, "grad_norm": 2.455801486968994, "learning_rate": 2.191765635753003e-05, "loss": 0.9658, "step": 12789 }, { "epoch": 0.6992653340167435, "grad_norm": 2.544664144515991, "learning_rate": 2.191033157609445e-05, "loss": 1.1054, "step": 12790 }, { "epoch": 0.6993200068341021, "grad_norm": 2.4304087162017822, "learning_rate": 2.1903007675385657e-05, "loss": 1.0488, "step": 12791 }, { "epoch": 0.6993746796514608, "grad_norm": 2.0343332290649414, "learning_rate": 2.189568465563327e-05, "loss": 0.9081, "step": 12792 }, { "epoch": 0.6994293524688194, "grad_norm": 3.0616984367370605, "learning_rate": 2.1888362517066934e-05, "loss": 1.047, "step": 12793 }, { "epoch": 0.699484025286178, "grad_norm": 2.729487895965576, "learning_rate": 2.1881041259916212e-05, "loss": 1.0079, "step": 12794 }, { "epoch": 0.6995386981035366, "grad_norm": 2.2196390628814697, "learning_rate": 2.187372088441065e-05, "loss": 0.9109, "step": 12795 }, { "epoch": 0.6995933709208952, "grad_norm": 2.115065097808838, "learning_rate": 2.1866401390779772e-05, "loss": 1.0091, "step": 12796 }, { "epoch": 0.6996480437382538, "grad_norm": 2.3476438522338867, "learning_rate": 2.1859082779253082e-05, "loss": 0.9946, "step": 12797 }, { "epoch": 0.6997027165556126, "grad_norm": 2.4571316242218018, "learning_rate": 2.185176505006004e-05, "loss": 0.9719, "step": 12798 }, { "epoch": 0.6997573893729712, "grad_norm": 3.076580762863159, "learning_rate": 2.184444820343009e-05, "loss": 1.1374, "step": 12799 }, { "epoch": 0.6998120621903298, "grad_norm": 3.0691683292388916, "learning_rate": 2.1837132239592646e-05, "loss": 0.9707, "step": 12800 }, { "epoch": 0.6998667350076884, "grad_norm": 2.925642490386963, "learning_rate": 2.1829817158777094e-05, "loss": 0.815, "step": 12801 }, { "epoch": 0.699921407825047, "grad_norm": 3.1126558780670166, "learning_rate": 2.182250296121277e-05, "loss": 0.7496, "step": 12802 }, { "epoch": 0.6999760806424056, "grad_norm": 3.1074249744415283, "learning_rate": 2.1815189647129046e-05, "loss": 0.9599, "step": 12803 }, { "epoch": 0.7000307534597642, "grad_norm": 3.4526031017303467, "learning_rate": 2.18078772167552e-05, "loss": 1.1577, "step": 12804 }, { "epoch": 0.7000854262771229, "grad_norm": 2.611168622970581, "learning_rate": 2.1800565670320516e-05, "loss": 0.9869, "step": 12805 }, { "epoch": 0.7001400990944815, "grad_norm": 2.3153247833251953, "learning_rate": 2.1793255008054237e-05, "loss": 0.9096, "step": 12806 }, { "epoch": 0.7001947719118401, "grad_norm": 2.8174216747283936, "learning_rate": 2.178594523018557e-05, "loss": 1.165, "step": 12807 }, { "epoch": 0.7002494447291987, "grad_norm": 3.0317928791046143, "learning_rate": 2.177863633694373e-05, "loss": 1.2278, "step": 12808 }, { "epoch": 0.7003041175465573, "grad_norm": 3.2709646224975586, "learning_rate": 2.1771328328557866e-05, "loss": 0.9737, "step": 12809 }, { "epoch": 0.7003587903639159, "grad_norm": 3.172633171081543, "learning_rate": 2.176402120525711e-05, "loss": 0.8892, "step": 12810 }, { "epoch": 0.7004134631812745, "grad_norm": 2.5540592670440674, "learning_rate": 2.1756714967270585e-05, "loss": 1.1199, "step": 12811 }, { "epoch": 0.7004681359986332, "grad_norm": 3.014749765396118, "learning_rate": 2.1749409614827342e-05, "loss": 0.9274, "step": 12812 }, { "epoch": 0.7005228088159918, "grad_norm": 2.620718240737915, "learning_rate": 2.174210514815647e-05, "loss": 1.1013, "step": 12813 }, { "epoch": 0.7005774816333504, "grad_norm": 2.5230071544647217, "learning_rate": 2.173480156748699e-05, "loss": 0.977, "step": 12814 }, { "epoch": 0.700632154450709, "grad_norm": 3.1707944869995117, "learning_rate": 2.172749887304788e-05, "loss": 1.0437, "step": 12815 }, { "epoch": 0.7006868272680676, "grad_norm": 3.0220165252685547, "learning_rate": 2.172019706506812e-05, "loss": 1.0831, "step": 12816 }, { "epoch": 0.7007415000854262, "grad_norm": 2.780973434448242, "learning_rate": 2.1712896143776656e-05, "loss": 1.0054, "step": 12817 }, { "epoch": 0.7007961729027848, "grad_norm": 3.2005982398986816, "learning_rate": 2.1705596109402393e-05, "loss": 1.149, "step": 12818 }, { "epoch": 0.7008508457201436, "grad_norm": 2.104093551635742, "learning_rate": 2.169829696217422e-05, "loss": 0.8586, "step": 12819 }, { "epoch": 0.7009055185375022, "grad_norm": 2.73643159866333, "learning_rate": 2.1690998702320998e-05, "loss": 1.2272, "step": 12820 }, { "epoch": 0.7009601913548608, "grad_norm": 2.1908724308013916, "learning_rate": 2.1683701330071548e-05, "loss": 1.0042, "step": 12821 }, { "epoch": 0.7010148641722194, "grad_norm": 3.13053822517395, "learning_rate": 2.1676404845654668e-05, "loss": 1.0427, "step": 12822 }, { "epoch": 0.701069536989578, "grad_norm": 2.6295175552368164, "learning_rate": 2.1669109249299164e-05, "loss": 1.0307, "step": 12823 }, { "epoch": 0.7011242098069366, "grad_norm": 2.845896005630493, "learning_rate": 2.166181454123376e-05, "loss": 1.2587, "step": 12824 }, { "epoch": 0.7011788826242953, "grad_norm": 2.4401443004608154, "learning_rate": 2.165452072168718e-05, "loss": 0.9094, "step": 12825 }, { "epoch": 0.7012335554416539, "grad_norm": 2.759427070617676, "learning_rate": 2.164722779088812e-05, "loss": 1.0941, "step": 12826 }, { "epoch": 0.7012882282590125, "grad_norm": 2.7783782482147217, "learning_rate": 2.1639935749065233e-05, "loss": 0.955, "step": 12827 }, { "epoch": 0.7013429010763711, "grad_norm": 2.321589469909668, "learning_rate": 2.1632644596447154e-05, "loss": 1.083, "step": 12828 }, { "epoch": 0.7013975738937297, "grad_norm": 2.4547674655914307, "learning_rate": 2.1625354333262503e-05, "loss": 0.9395, "step": 12829 }, { "epoch": 0.7014522467110883, "grad_norm": 2.4331774711608887, "learning_rate": 2.1618064959739853e-05, "loss": 0.9109, "step": 12830 }, { "epoch": 0.7015069195284469, "grad_norm": 3.649721145629883, "learning_rate": 2.1610776476107754e-05, "loss": 0.8801, "step": 12831 }, { "epoch": 0.7015615923458056, "grad_norm": 3.212219715118408, "learning_rate": 2.160348888259473e-05, "loss": 0.8635, "step": 12832 }, { "epoch": 0.7016162651631642, "grad_norm": 2.447260856628418, "learning_rate": 2.159620217942928e-05, "loss": 0.9904, "step": 12833 }, { "epoch": 0.7016709379805228, "grad_norm": 2.489508628845215, "learning_rate": 2.158891636683987e-05, "loss": 1.075, "step": 12834 }, { "epoch": 0.7017256107978814, "grad_norm": 2.2502260208129883, "learning_rate": 2.1581631445054924e-05, "loss": 0.9673, "step": 12835 }, { "epoch": 0.70178028361524, "grad_norm": 2.9815938472747803, "learning_rate": 2.1574347414302886e-05, "loss": 0.9111, "step": 12836 }, { "epoch": 0.7018349564325986, "grad_norm": 3.254917860031128, "learning_rate": 2.1567064274812132e-05, "loss": 1.0107, "step": 12837 }, { "epoch": 0.7018896292499572, "grad_norm": 2.4931859970092773, "learning_rate": 2.155978202681101e-05, "loss": 0.9413, "step": 12838 }, { "epoch": 0.701944302067316, "grad_norm": 1.9343799352645874, "learning_rate": 2.1552500670527846e-05, "loss": 0.7304, "step": 12839 }, { "epoch": 0.7019989748846746, "grad_norm": 3.2637622356414795, "learning_rate": 2.1545220206190946e-05, "loss": 1.0743, "step": 12840 }, { "epoch": 0.7020536477020332, "grad_norm": 2.0209200382232666, "learning_rate": 2.1537940634028585e-05, "loss": 0.986, "step": 12841 }, { "epoch": 0.7021083205193918, "grad_norm": 2.0992965698242188, "learning_rate": 2.1530661954269006e-05, "loss": 1.1311, "step": 12842 }, { "epoch": 0.7021629933367504, "grad_norm": 2.8838815689086914, "learning_rate": 2.152338416714042e-05, "loss": 0.9414, "step": 12843 }, { "epoch": 0.702217666154109, "grad_norm": 2.468585968017578, "learning_rate": 2.1516107272871018e-05, "loss": 1.0855, "step": 12844 }, { "epoch": 0.7022723389714676, "grad_norm": 2.957643508911133, "learning_rate": 2.1508831271688963e-05, "loss": 1.2501, "step": 12845 }, { "epoch": 0.7023270117888263, "grad_norm": 2.404787540435791, "learning_rate": 2.150155616382239e-05, "loss": 0.9413, "step": 12846 }, { "epoch": 0.7023816846061849, "grad_norm": 2.2932071685791016, "learning_rate": 2.1494281949499397e-05, "loss": 1.0556, "step": 12847 }, { "epoch": 0.7024363574235435, "grad_norm": 2.390286922454834, "learning_rate": 2.1487008628948047e-05, "loss": 1.0076, "step": 12848 }, { "epoch": 0.7024910302409021, "grad_norm": 2.5416054725646973, "learning_rate": 2.147973620239642e-05, "loss": 0.945, "step": 12849 }, { "epoch": 0.7025457030582607, "grad_norm": 2.9319369792938232, "learning_rate": 2.1472464670072524e-05, "loss": 1.1057, "step": 12850 }, { "epoch": 0.7026003758756193, "grad_norm": 2.536717653274536, "learning_rate": 2.146519403220435e-05, "loss": 0.9224, "step": 12851 }, { "epoch": 0.702655048692978, "grad_norm": 2.402155876159668, "learning_rate": 2.1457924289019858e-05, "loss": 0.9598, "step": 12852 }, { "epoch": 0.7027097215103366, "grad_norm": 3.933134078979492, "learning_rate": 2.1450655440747e-05, "loss": 1.1614, "step": 12853 }, { "epoch": 0.7027643943276952, "grad_norm": 2.9769914150238037, "learning_rate": 2.144338748761366e-05, "loss": 1.0784, "step": 12854 }, { "epoch": 0.7028190671450538, "grad_norm": 2.6229186058044434, "learning_rate": 2.1436120429847734e-05, "loss": 0.9319, "step": 12855 }, { "epoch": 0.7028737399624124, "grad_norm": 2.4067564010620117, "learning_rate": 2.1428854267677073e-05, "loss": 0.9722, "step": 12856 }, { "epoch": 0.702928412779771, "grad_norm": 2.8537838459014893, "learning_rate": 2.1421589001329494e-05, "loss": 1.1952, "step": 12857 }, { "epoch": 0.7029830855971296, "grad_norm": 2.702838659286499, "learning_rate": 2.1414324631032805e-05, "loss": 1.0528, "step": 12858 }, { "epoch": 0.7030377584144883, "grad_norm": 2.366044282913208, "learning_rate": 2.1407061157014762e-05, "loss": 0.9398, "step": 12859 }, { "epoch": 0.703092431231847, "grad_norm": 2.5406715869903564, "learning_rate": 2.139979857950311e-05, "loss": 1.0343, "step": 12860 }, { "epoch": 0.7031471040492056, "grad_norm": 2.448589324951172, "learning_rate": 2.1392536898725546e-05, "loss": 1.0134, "step": 12861 }, { "epoch": 0.7032017768665642, "grad_norm": 2.3517978191375732, "learning_rate": 2.1385276114909785e-05, "loss": 1.0207, "step": 12862 }, { "epoch": 0.7032564496839228, "grad_norm": 2.353336811065674, "learning_rate": 2.1378016228283465e-05, "loss": 1.1721, "step": 12863 }, { "epoch": 0.7033111225012814, "grad_norm": 2.8341333866119385, "learning_rate": 2.1370757239074214e-05, "loss": 1.1714, "step": 12864 }, { "epoch": 0.70336579531864, "grad_norm": 3.0007338523864746, "learning_rate": 2.136349914750963e-05, "loss": 1.0989, "step": 12865 }, { "epoch": 0.7034204681359987, "grad_norm": 3.0859551429748535, "learning_rate": 2.1356241953817286e-05, "loss": 1.0589, "step": 12866 }, { "epoch": 0.7034751409533573, "grad_norm": 2.869699239730835, "learning_rate": 2.1348985658224723e-05, "loss": 0.8831, "step": 12867 }, { "epoch": 0.7035298137707159, "grad_norm": 2.1673076152801514, "learning_rate": 2.1341730260959458e-05, "loss": 0.8904, "step": 12868 }, { "epoch": 0.7035844865880745, "grad_norm": 1.9656862020492554, "learning_rate": 2.1334475762248973e-05, "loss": 0.8463, "step": 12869 }, { "epoch": 0.7036391594054331, "grad_norm": 2.7034120559692383, "learning_rate": 2.132722216232073e-05, "loss": 1.19, "step": 12870 }, { "epoch": 0.7036938322227917, "grad_norm": 3.0611178874969482, "learning_rate": 2.131996946140215e-05, "loss": 1.0738, "step": 12871 }, { "epoch": 0.7037485050401503, "grad_norm": 2.907822608947754, "learning_rate": 2.1312717659720654e-05, "loss": 1.2785, "step": 12872 }, { "epoch": 0.703803177857509, "grad_norm": 2.6552536487579346, "learning_rate": 2.1305466757503606e-05, "loss": 1.04, "step": 12873 }, { "epoch": 0.7038578506748676, "grad_norm": 2.450998544692993, "learning_rate": 2.1298216754978358e-05, "loss": 1.1827, "step": 12874 }, { "epoch": 0.7039125234922262, "grad_norm": 2.52762508392334, "learning_rate": 2.1290967652372212e-05, "loss": 0.8976, "step": 12875 }, { "epoch": 0.7039671963095848, "grad_norm": 2.6567790508270264, "learning_rate": 2.1283719449912476e-05, "loss": 0.9027, "step": 12876 }, { "epoch": 0.7040218691269434, "grad_norm": 2.2797470092773438, "learning_rate": 2.1276472147826394e-05, "loss": 0.9906, "step": 12877 }, { "epoch": 0.704076541944302, "grad_norm": 2.386249303817749, "learning_rate": 2.126922574634121e-05, "loss": 0.9882, "step": 12878 }, { "epoch": 0.7041312147616607, "grad_norm": 3.1851139068603516, "learning_rate": 2.126198024568412e-05, "loss": 1.097, "step": 12879 }, { "epoch": 0.7041858875790193, "grad_norm": 3.1625595092773438, "learning_rate": 2.1254735646082306e-05, "loss": 1.0188, "step": 12880 }, { "epoch": 0.704240560396378, "grad_norm": 2.573472023010254, "learning_rate": 2.1247491947762903e-05, "loss": 0.9657, "step": 12881 }, { "epoch": 0.7042952332137365, "grad_norm": 2.036442995071411, "learning_rate": 2.1240249150953056e-05, "loss": 0.9081, "step": 12882 }, { "epoch": 0.7043499060310952, "grad_norm": 2.132127523422241, "learning_rate": 2.1233007255879845e-05, "loss": 1.0159, "step": 12883 }, { "epoch": 0.7044045788484538, "grad_norm": 2.9679460525512695, "learning_rate": 2.122576626277033e-05, "loss": 1.0333, "step": 12884 }, { "epoch": 0.7044592516658124, "grad_norm": 3.3968071937561035, "learning_rate": 2.1218526171851545e-05, "loss": 1.2899, "step": 12885 }, { "epoch": 0.7045139244831711, "grad_norm": 2.3488030433654785, "learning_rate": 2.1211286983350503e-05, "loss": 1.148, "step": 12886 }, { "epoch": 0.7045685973005297, "grad_norm": 2.735295295715332, "learning_rate": 2.1204048697494177e-05, "loss": 0.8297, "step": 12887 }, { "epoch": 0.7046232701178883, "grad_norm": 2.768148899078369, "learning_rate": 2.1196811314509517e-05, "loss": 0.91, "step": 12888 }, { "epoch": 0.7046779429352469, "grad_norm": 2.8746912479400635, "learning_rate": 2.118957483462345e-05, "loss": 1.1588, "step": 12889 }, { "epoch": 0.7047326157526055, "grad_norm": 2.8821613788604736, "learning_rate": 2.1182339258062843e-05, "loss": 0.8923, "step": 12890 }, { "epoch": 0.7047872885699641, "grad_norm": 2.969954013824463, "learning_rate": 2.1175104585054606e-05, "loss": 0.9636, "step": 12891 }, { "epoch": 0.7048419613873227, "grad_norm": 2.901960849761963, "learning_rate": 2.1167870815825545e-05, "loss": 0.9599, "step": 12892 }, { "epoch": 0.7048966342046814, "grad_norm": 2.4681766033172607, "learning_rate": 2.1160637950602484e-05, "loss": 1.0457, "step": 12893 }, { "epoch": 0.70495130702204, "grad_norm": 2.4694743156433105, "learning_rate": 2.11534059896122e-05, "loss": 1.2198, "step": 12894 }, { "epoch": 0.7050059798393986, "grad_norm": 2.660440444946289, "learning_rate": 2.1146174933081435e-05, "loss": 1.1949, "step": 12895 }, { "epoch": 0.7050606526567572, "grad_norm": 3.0775976181030273, "learning_rate": 2.1138944781236918e-05, "loss": 1.0103, "step": 12896 }, { "epoch": 0.7051153254741158, "grad_norm": 2.8536880016326904, "learning_rate": 2.113171553430535e-05, "loss": 1.1488, "step": 12897 }, { "epoch": 0.7051699982914744, "grad_norm": 2.4894356727600098, "learning_rate": 2.1124487192513386e-05, "loss": 1.1464, "step": 12898 }, { "epoch": 0.705224671108833, "grad_norm": 2.1471807956695557, "learning_rate": 2.1117259756087677e-05, "loss": 0.8398, "step": 12899 }, { "epoch": 0.7052793439261917, "grad_norm": 2.4444870948791504, "learning_rate": 2.1110033225254805e-05, "loss": 1.0143, "step": 12900 }, { "epoch": 0.7053340167435503, "grad_norm": 2.6528127193450928, "learning_rate": 2.1102807600241387e-05, "loss": 1.1858, "step": 12901 }, { "epoch": 0.7053886895609089, "grad_norm": 2.9057836532592773, "learning_rate": 2.109558288127397e-05, "loss": 1.0098, "step": 12902 }, { "epoch": 0.7054433623782675, "grad_norm": 2.7795121669769287, "learning_rate": 2.108835906857906e-05, "loss": 1.0823, "step": 12903 }, { "epoch": 0.7054980351956261, "grad_norm": 2.4294755458831787, "learning_rate": 2.108113616238317e-05, "loss": 0.9254, "step": 12904 }, { "epoch": 0.7055527080129848, "grad_norm": 2.933898687362671, "learning_rate": 2.107391416291276e-05, "loss": 1.2209, "step": 12905 }, { "epoch": 0.7056073808303435, "grad_norm": 2.156920909881592, "learning_rate": 2.1066693070394273e-05, "loss": 0.9567, "step": 12906 }, { "epoch": 0.7056620536477021, "grad_norm": 2.3620495796203613, "learning_rate": 2.1059472885054116e-05, "loss": 1.2297, "step": 12907 }, { "epoch": 0.7057167264650607, "grad_norm": 2.2835135459899902, "learning_rate": 2.1052253607118678e-05, "loss": 1.0059, "step": 12908 }, { "epoch": 0.7057713992824193, "grad_norm": 3.443518877029419, "learning_rate": 2.1045035236814303e-05, "loss": 1.0685, "step": 12909 }, { "epoch": 0.7058260720997779, "grad_norm": 2.9411098957061768, "learning_rate": 2.103781777436731e-05, "loss": 1.1599, "step": 12910 }, { "epoch": 0.7058807449171365, "grad_norm": 2.359004259109497, "learning_rate": 2.103060122000402e-05, "loss": 1.1792, "step": 12911 }, { "epoch": 0.7059354177344951, "grad_norm": 2.656282663345337, "learning_rate": 2.1023385573950692e-05, "loss": 0.9182, "step": 12912 }, { "epoch": 0.7059900905518538, "grad_norm": 2.262634754180908, "learning_rate": 2.101617083643357e-05, "loss": 0.9238, "step": 12913 }, { "epoch": 0.7060447633692124, "grad_norm": 2.9555959701538086, "learning_rate": 2.1008957007678852e-05, "loss": 1.1983, "step": 12914 }, { "epoch": 0.706099436186571, "grad_norm": 2.67622709274292, "learning_rate": 2.1001744087912733e-05, "loss": 1.007, "step": 12915 }, { "epoch": 0.7061541090039296, "grad_norm": 2.8790767192840576, "learning_rate": 2.0994532077361367e-05, "loss": 1.0495, "step": 12916 }, { "epoch": 0.7062087818212882, "grad_norm": 2.6555469036102295, "learning_rate": 2.0987320976250872e-05, "loss": 1.0953, "step": 12917 }, { "epoch": 0.7062634546386468, "grad_norm": 2.9926342964172363, "learning_rate": 2.0980110784807356e-05, "loss": 0.7771, "step": 12918 }, { "epoch": 0.7063181274560054, "grad_norm": 2.8099515438079834, "learning_rate": 2.097290150325688e-05, "loss": 1.0538, "step": 12919 }, { "epoch": 0.7063728002733641, "grad_norm": 2.2947022914886475, "learning_rate": 2.096569313182547e-05, "loss": 1.0199, "step": 12920 }, { "epoch": 0.7064274730907227, "grad_norm": 2.5088655948638916, "learning_rate": 2.0958485670739175e-05, "loss": 1.0472, "step": 12921 }, { "epoch": 0.7064821459080813, "grad_norm": 2.493607521057129, "learning_rate": 2.0951279120223967e-05, "loss": 0.8279, "step": 12922 }, { "epoch": 0.7065368187254399, "grad_norm": 2.542738676071167, "learning_rate": 2.0944073480505783e-05, "loss": 1.0477, "step": 12923 }, { "epoch": 0.7065914915427985, "grad_norm": 2.1191086769104004, "learning_rate": 2.0936868751810562e-05, "loss": 0.9086, "step": 12924 }, { "epoch": 0.7066461643601571, "grad_norm": 2.343430757522583, "learning_rate": 2.0929664934364208e-05, "loss": 0.8121, "step": 12925 }, { "epoch": 0.7067008371775158, "grad_norm": 2.420703649520874, "learning_rate": 2.0922462028392576e-05, "loss": 0.8712, "step": 12926 }, { "epoch": 0.7067555099948745, "grad_norm": 3.006709575653076, "learning_rate": 2.091526003412151e-05, "loss": 0.7643, "step": 12927 }, { "epoch": 0.7068101828122331, "grad_norm": 2.9959733486175537, "learning_rate": 2.090805895177683e-05, "loss": 1.2541, "step": 12928 }, { "epoch": 0.7068648556295917, "grad_norm": 3.325674057006836, "learning_rate": 2.0900858781584314e-05, "loss": 0.8584, "step": 12929 }, { "epoch": 0.7069195284469503, "grad_norm": 3.4345290660858154, "learning_rate": 2.0893659523769705e-05, "loss": 1.1244, "step": 12930 }, { "epoch": 0.7069742012643089, "grad_norm": 2.2240123748779297, "learning_rate": 2.0886461178558754e-05, "loss": 1.0025, "step": 12931 }, { "epoch": 0.7070288740816675, "grad_norm": 2.785217523574829, "learning_rate": 2.0879263746177148e-05, "loss": 1.0592, "step": 12932 }, { "epoch": 0.7070835468990262, "grad_norm": 2.540945053100586, "learning_rate": 2.0872067226850557e-05, "loss": 0.9823, "step": 12933 }, { "epoch": 0.7071382197163848, "grad_norm": 2.743664264678955, "learning_rate": 2.086487162080462e-05, "loss": 0.9611, "step": 12934 }, { "epoch": 0.7071928925337434, "grad_norm": 2.750447988510132, "learning_rate": 2.0857676928264948e-05, "loss": 1.1049, "step": 12935 }, { "epoch": 0.707247565351102, "grad_norm": 2.343214750289917, "learning_rate": 2.0850483149457124e-05, "loss": 1.0202, "step": 12936 }, { "epoch": 0.7073022381684606, "grad_norm": 2.176316261291504, "learning_rate": 2.0843290284606702e-05, "loss": 0.8843, "step": 12937 }, { "epoch": 0.7073569109858192, "grad_norm": 2.8295884132385254, "learning_rate": 2.0836098333939212e-05, "loss": 0.9435, "step": 12938 }, { "epoch": 0.7074115838031778, "grad_norm": 2.3086965084075928, "learning_rate": 2.0828907297680133e-05, "loss": 1.0742, "step": 12939 }, { "epoch": 0.7074662566205365, "grad_norm": 2.7980968952178955, "learning_rate": 2.0821717176054965e-05, "loss": 0.7904, "step": 12940 }, { "epoch": 0.7075209294378951, "grad_norm": 2.709848403930664, "learning_rate": 2.0814527969289132e-05, "loss": 1.0081, "step": 12941 }, { "epoch": 0.7075756022552537, "grad_norm": 2.9623703956604004, "learning_rate": 2.0807339677608045e-05, "loss": 0.9386, "step": 12942 }, { "epoch": 0.7076302750726123, "grad_norm": 2.3556182384490967, "learning_rate": 2.0800152301237093e-05, "loss": 0.8743, "step": 12943 }, { "epoch": 0.7076849478899709, "grad_norm": 2.698474645614624, "learning_rate": 2.0792965840401618e-05, "loss": 1.0659, "step": 12944 }, { "epoch": 0.7077396207073295, "grad_norm": 3.510077714920044, "learning_rate": 2.078578029532695e-05, "loss": 1.0274, "step": 12945 }, { "epoch": 0.7077942935246881, "grad_norm": 2.863795518875122, "learning_rate": 2.0778595666238387e-05, "loss": 1.107, "step": 12946 }, { "epoch": 0.7078489663420469, "grad_norm": 2.7847113609313965, "learning_rate": 2.07714119533612e-05, "loss": 1.201, "step": 12947 }, { "epoch": 0.7079036391594055, "grad_norm": 2.7722926139831543, "learning_rate": 2.0764229156920622e-05, "loss": 0.9897, "step": 12948 }, { "epoch": 0.7079583119767641, "grad_norm": 2.267101764678955, "learning_rate": 2.0757047277141845e-05, "loss": 1.0608, "step": 12949 }, { "epoch": 0.7080129847941227, "grad_norm": 2.6096906661987305, "learning_rate": 2.0749866314250094e-05, "loss": 1.0385, "step": 12950 }, { "epoch": 0.7080676576114813, "grad_norm": 2.355436325073242, "learning_rate": 2.0742686268470497e-05, "loss": 1.1253, "step": 12951 }, { "epoch": 0.7081223304288399, "grad_norm": 2.8157782554626465, "learning_rate": 2.0735507140028177e-05, "loss": 0.9583, "step": 12952 }, { "epoch": 0.7081770032461985, "grad_norm": 3.8016324043273926, "learning_rate": 2.0728328929148234e-05, "loss": 0.9481, "step": 12953 }, { "epoch": 0.7082316760635572, "grad_norm": 2.729966402053833, "learning_rate": 2.072115163605573e-05, "loss": 1.225, "step": 12954 }, { "epoch": 0.7082863488809158, "grad_norm": 3.033608913421631, "learning_rate": 2.071397526097571e-05, "loss": 1.0831, "step": 12955 }, { "epoch": 0.7083410216982744, "grad_norm": 3.1120944023132324, "learning_rate": 2.0706799804133175e-05, "loss": 1.0308, "step": 12956 }, { "epoch": 0.708395694515633, "grad_norm": 2.5011651515960693, "learning_rate": 2.069962526575311e-05, "loss": 1.0966, "step": 12957 }, { "epoch": 0.7084503673329916, "grad_norm": 4.5902299880981445, "learning_rate": 2.0692451646060464e-05, "loss": 1.1426, "step": 12958 }, { "epoch": 0.7085050401503502, "grad_norm": 2.832130193710327, "learning_rate": 2.0685278945280136e-05, "loss": 0.9654, "step": 12959 }, { "epoch": 0.7085597129677089, "grad_norm": 2.629133939743042, "learning_rate": 2.0678107163637065e-05, "loss": 0.8453, "step": 12960 }, { "epoch": 0.7086143857850675, "grad_norm": 3.009580373764038, "learning_rate": 2.06709363013561e-05, "loss": 0.7911, "step": 12961 }, { "epoch": 0.7086690586024261, "grad_norm": 3.0457491874694824, "learning_rate": 2.066376635866207e-05, "loss": 0.7793, "step": 12962 }, { "epoch": 0.7087237314197847, "grad_norm": 2.9554312229156494, "learning_rate": 2.065659733577978e-05, "loss": 1.0172, "step": 12963 }, { "epoch": 0.7087784042371433, "grad_norm": 2.2933287620544434, "learning_rate": 2.0649429232934015e-05, "loss": 0.9681, "step": 12964 }, { "epoch": 0.7088330770545019, "grad_norm": 2.1884775161743164, "learning_rate": 2.064226205034952e-05, "loss": 0.8863, "step": 12965 }, { "epoch": 0.7088877498718605, "grad_norm": 2.4976489543914795, "learning_rate": 2.063509578825102e-05, "loss": 0.8904, "step": 12966 }, { "epoch": 0.7089424226892193, "grad_norm": 2.2133281230926514, "learning_rate": 2.0627930446863204e-05, "loss": 0.73, "step": 12967 }, { "epoch": 0.7089970955065779, "grad_norm": 3.2206673622131348, "learning_rate": 2.0620766026410732e-05, "loss": 1.2944, "step": 12968 }, { "epoch": 0.7090517683239365, "grad_norm": 3.160167932510376, "learning_rate": 2.0613602527118226e-05, "loss": 1.0875, "step": 12969 }, { "epoch": 0.7091064411412951, "grad_norm": 4.1169939041137695, "learning_rate": 2.060643994921032e-05, "loss": 1.035, "step": 12970 }, { "epoch": 0.7091611139586537, "grad_norm": 2.8154804706573486, "learning_rate": 2.0599278292911584e-05, "loss": 1.0015, "step": 12971 }, { "epoch": 0.7092157867760123, "grad_norm": 3.2838668823242188, "learning_rate": 2.0592117558446554e-05, "loss": 0.9974, "step": 12972 }, { "epoch": 0.7092704595933709, "grad_norm": 2.987652540206909, "learning_rate": 2.0584957746039758e-05, "loss": 0.939, "step": 12973 }, { "epoch": 0.7093251324107296, "grad_norm": 2.6340441703796387, "learning_rate": 2.0577798855915676e-05, "loss": 1.0737, "step": 12974 }, { "epoch": 0.7093798052280882, "grad_norm": 4.064855575561523, "learning_rate": 2.0570640888298775e-05, "loss": 0.9091, "step": 12975 }, { "epoch": 0.7094344780454468, "grad_norm": 3.6732358932495117, "learning_rate": 2.0563483843413485e-05, "loss": 0.9076, "step": 12976 }, { "epoch": 0.7094891508628054, "grad_norm": 2.8794233798980713, "learning_rate": 2.0556327721484208e-05, "loss": 1.0211, "step": 12977 }, { "epoch": 0.709543823680164, "grad_norm": 2.4235548973083496, "learning_rate": 2.0549172522735318e-05, "loss": 0.9244, "step": 12978 }, { "epoch": 0.7095984964975226, "grad_norm": 2.5998682975769043, "learning_rate": 2.054201824739114e-05, "loss": 0.9239, "step": 12979 }, { "epoch": 0.7096531693148812, "grad_norm": 2.4556167125701904, "learning_rate": 2.0534864895676037e-05, "loss": 0.9632, "step": 12980 }, { "epoch": 0.7097078421322399, "grad_norm": 2.8562428951263428, "learning_rate": 2.0527712467814263e-05, "loss": 1.1871, "step": 12981 }, { "epoch": 0.7097625149495985, "grad_norm": 2.555192708969116, "learning_rate": 2.0520560964030083e-05, "loss": 0.9531, "step": 12982 }, { "epoch": 0.7098171877669571, "grad_norm": 2.7812247276306152, "learning_rate": 2.0513410384547727e-05, "loss": 1.0354, "step": 12983 }, { "epoch": 0.7098718605843157, "grad_norm": 2.8864500522613525, "learning_rate": 2.0506260729591397e-05, "loss": 1.0486, "step": 12984 }, { "epoch": 0.7099265334016743, "grad_norm": 4.159646034240723, "learning_rate": 2.0499111999385255e-05, "loss": 1.2016, "step": 12985 }, { "epoch": 0.7099812062190329, "grad_norm": 2.3451220989227295, "learning_rate": 2.0491964194153458e-05, "loss": 1.0971, "step": 12986 }, { "epoch": 0.7100358790363916, "grad_norm": 2.365543842315674, "learning_rate": 2.0484817314120102e-05, "loss": 0.8828, "step": 12987 }, { "epoch": 0.7100905518537503, "grad_norm": 2.4999475479125977, "learning_rate": 2.0477671359509283e-05, "loss": 0.91, "step": 12988 }, { "epoch": 0.7101452246711089, "grad_norm": 3.474247694015503, "learning_rate": 2.047052633054503e-05, "loss": 1.0736, "step": 12989 }, { "epoch": 0.7101998974884675, "grad_norm": 2.693411111831665, "learning_rate": 2.0463382227451415e-05, "loss": 0.8694, "step": 12990 }, { "epoch": 0.7102545703058261, "grad_norm": 2.2328732013702393, "learning_rate": 2.045623905045241e-05, "loss": 0.7086, "step": 12991 }, { "epoch": 0.7103092431231847, "grad_norm": 2.9220778942108154, "learning_rate": 2.0449096799771984e-05, "loss": 1.1383, "step": 12992 }, { "epoch": 0.7103639159405433, "grad_norm": 2.755577325820923, "learning_rate": 2.0441955475634077e-05, "loss": 1.1199, "step": 12993 }, { "epoch": 0.710418588757902, "grad_norm": 2.0983026027679443, "learning_rate": 2.0434815078262603e-05, "loss": 1.0608, "step": 12994 }, { "epoch": 0.7104732615752606, "grad_norm": 2.8807921409606934, "learning_rate": 2.042767560788143e-05, "loss": 0.9289, "step": 12995 }, { "epoch": 0.7105279343926192, "grad_norm": 2.7764415740966797, "learning_rate": 2.0420537064714425e-05, "loss": 1.1791, "step": 12996 }, { "epoch": 0.7105826072099778, "grad_norm": 2.9338345527648926, "learning_rate": 2.0413399448985403e-05, "loss": 0.9149, "step": 12997 }, { "epoch": 0.7106372800273364, "grad_norm": 2.511080503463745, "learning_rate": 2.0406262760918137e-05, "loss": 1.0242, "step": 12998 }, { "epoch": 0.710691952844695, "grad_norm": 2.572181463241577, "learning_rate": 2.0399127000736434e-05, "loss": 0.9171, "step": 12999 }, { "epoch": 0.7107466256620536, "grad_norm": 2.302682638168335, "learning_rate": 2.0391992168664008e-05, "loss": 1.0599, "step": 13000 }, { "epoch": 0.7108012984794123, "grad_norm": 2.343639612197876, "learning_rate": 2.0384858264924567e-05, "loss": 0.9503, "step": 13001 }, { "epoch": 0.7108559712967709, "grad_norm": 2.775996446609497, "learning_rate": 2.037772528974179e-05, "loss": 1.026, "step": 13002 }, { "epoch": 0.7109106441141295, "grad_norm": 2.9008822441101074, "learning_rate": 2.037059324333932e-05, "loss": 1.1896, "step": 13003 }, { "epoch": 0.7109653169314881, "grad_norm": 2.339043378829956, "learning_rate": 2.0363462125940774e-05, "loss": 0.9098, "step": 13004 }, { "epoch": 0.7110199897488467, "grad_norm": 2.5461485385894775, "learning_rate": 2.035633193776975e-05, "loss": 1.0782, "step": 13005 }, { "epoch": 0.7110746625662053, "grad_norm": 3.344564199447632, "learning_rate": 2.0349202679049807e-05, "loss": 1.1271, "step": 13006 }, { "epoch": 0.7111293353835639, "grad_norm": 2.531566858291626, "learning_rate": 2.0342074350004475e-05, "loss": 1.1151, "step": 13007 }, { "epoch": 0.7111840082009226, "grad_norm": 2.1723899841308594, "learning_rate": 2.0334946950857252e-05, "loss": 1.0333, "step": 13008 }, { "epoch": 0.7112386810182812, "grad_norm": 2.4801275730133057, "learning_rate": 2.03278204818316e-05, "loss": 0.9328, "step": 13009 }, { "epoch": 0.7112933538356399, "grad_norm": 2.4109573364257812, "learning_rate": 2.0320694943150997e-05, "loss": 1.0039, "step": 13010 }, { "epoch": 0.7113480266529985, "grad_norm": 3.1384685039520264, "learning_rate": 2.031357033503884e-05, "loss": 0.9517, "step": 13011 }, { "epoch": 0.7114026994703571, "grad_norm": 2.577094316482544, "learning_rate": 2.0306446657718514e-05, "loss": 1.3407, "step": 13012 }, { "epoch": 0.7114573722877157, "grad_norm": 2.7509803771972656, "learning_rate": 2.0299323911413377e-05, "loss": 1.048, "step": 13013 }, { "epoch": 0.7115120451050744, "grad_norm": 2.644674301147461, "learning_rate": 2.0292202096346753e-05, "loss": 0.9884, "step": 13014 }, { "epoch": 0.711566717922433, "grad_norm": 3.6238861083984375, "learning_rate": 2.0285081212741945e-05, "loss": 1.0687, "step": 13015 }, { "epoch": 0.7116213907397916, "grad_norm": 3.1207950115203857, "learning_rate": 2.0277961260822222e-05, "loss": 1.0137, "step": 13016 }, { "epoch": 0.7116760635571502, "grad_norm": 2.487736701965332, "learning_rate": 2.0270842240810817e-05, "loss": 1.1065, "step": 13017 }, { "epoch": 0.7117307363745088, "grad_norm": 2.7813916206359863, "learning_rate": 2.0263724152930948e-05, "loss": 1.0455, "step": 13018 }, { "epoch": 0.7117854091918674, "grad_norm": 2.6746654510498047, "learning_rate": 2.025660699740579e-05, "loss": 1.0367, "step": 13019 }, { "epoch": 0.711840082009226, "grad_norm": 2.883726119995117, "learning_rate": 2.0249490774458503e-05, "loss": 0.9782, "step": 13020 }, { "epoch": 0.7118947548265847, "grad_norm": 2.349658250808716, "learning_rate": 2.0242375484312205e-05, "loss": 1.0824, "step": 13021 }, { "epoch": 0.7119494276439433, "grad_norm": 2.734553575515747, "learning_rate": 2.023526112718997e-05, "loss": 0.8033, "step": 13022 }, { "epoch": 0.7120041004613019, "grad_norm": 3.6012487411499023, "learning_rate": 2.0228147703314904e-05, "loss": 0.8844, "step": 13023 }, { "epoch": 0.7120587732786605, "grad_norm": 4.776065349578857, "learning_rate": 2.0221035212910016e-05, "loss": 0.919, "step": 13024 }, { "epoch": 0.7121134460960191, "grad_norm": 2.6252124309539795, "learning_rate": 2.0213923656198324e-05, "loss": 1.0189, "step": 13025 }, { "epoch": 0.7121681189133777, "grad_norm": 3.01171612739563, "learning_rate": 2.0206813033402795e-05, "loss": 1.0114, "step": 13026 }, { "epoch": 0.7122227917307363, "grad_norm": 2.660158395767212, "learning_rate": 2.0199703344746374e-05, "loss": 0.9402, "step": 13027 }, { "epoch": 0.712277464548095, "grad_norm": 3.065377950668335, "learning_rate": 2.0192594590451984e-05, "loss": 0.9333, "step": 13028 }, { "epoch": 0.7123321373654536, "grad_norm": 2.523102045059204, "learning_rate": 2.0185486770742516e-05, "loss": 1.0319, "step": 13029 }, { "epoch": 0.7123868101828122, "grad_norm": 2.3675055503845215, "learning_rate": 2.0178379885840825e-05, "loss": 1.0491, "step": 13030 }, { "epoch": 0.7124414830001708, "grad_norm": 2.0836658477783203, "learning_rate": 2.0171273935969747e-05, "loss": 0.9086, "step": 13031 }, { "epoch": 0.7124961558175295, "grad_norm": 2.9225401878356934, "learning_rate": 2.0164168921352077e-05, "loss": 1.148, "step": 13032 }, { "epoch": 0.7125508286348881, "grad_norm": 4.097594738006592, "learning_rate": 2.0157064842210587e-05, "loss": 1.1288, "step": 13033 }, { "epoch": 0.7126055014522467, "grad_norm": 2.69616961479187, "learning_rate": 2.0149961698768017e-05, "loss": 1.1606, "step": 13034 }, { "epoch": 0.7126601742696054, "grad_norm": 2.754666328430176, "learning_rate": 2.014285949124707e-05, "loss": 1.0388, "step": 13035 }, { "epoch": 0.712714847086964, "grad_norm": 3.36199688911438, "learning_rate": 2.013575821987046e-05, "loss": 1.049, "step": 13036 }, { "epoch": 0.7127695199043226, "grad_norm": 2.08490252494812, "learning_rate": 2.012865788486082e-05, "loss": 0.8901, "step": 13037 }, { "epoch": 0.7128241927216812, "grad_norm": 2.7001333236694336, "learning_rate": 2.0121558486440785e-05, "loss": 1.1398, "step": 13038 }, { "epoch": 0.7128788655390398, "grad_norm": 3.009451389312744, "learning_rate": 2.011446002483294e-05, "loss": 1.0957, "step": 13039 }, { "epoch": 0.7129335383563984, "grad_norm": 2.392313241958618, "learning_rate": 2.0107362500259853e-05, "loss": 0.8851, "step": 13040 }, { "epoch": 0.7129882111737571, "grad_norm": 2.86203670501709, "learning_rate": 2.010026591294406e-05, "loss": 1.0966, "step": 13041 }, { "epoch": 0.7130428839911157, "grad_norm": 3.184058666229248, "learning_rate": 2.0093170263108075e-05, "loss": 1.17, "step": 13042 }, { "epoch": 0.7130975568084743, "grad_norm": 2.505202293395996, "learning_rate": 2.0086075550974372e-05, "loss": 0.9288, "step": 13043 }, { "epoch": 0.7131522296258329, "grad_norm": 2.451733350753784, "learning_rate": 2.0078981776765398e-05, "loss": 0.903, "step": 13044 }, { "epoch": 0.7132069024431915, "grad_norm": 2.3501508235931396, "learning_rate": 2.0071888940703577e-05, "loss": 1.1364, "step": 13045 }, { "epoch": 0.7132615752605501, "grad_norm": 1.9574286937713623, "learning_rate": 2.0064797043011286e-05, "loss": 1.0242, "step": 13046 }, { "epoch": 0.7133162480779087, "grad_norm": 2.290630340576172, "learning_rate": 2.005770608391088e-05, "loss": 1.0286, "step": 13047 }, { "epoch": 0.7133709208952674, "grad_norm": 3.1832146644592285, "learning_rate": 2.0050616063624722e-05, "loss": 0.7872, "step": 13048 }, { "epoch": 0.713425593712626, "grad_norm": 3.38427472114563, "learning_rate": 2.0043526982375094e-05, "loss": 1.1746, "step": 13049 }, { "epoch": 0.7134802665299846, "grad_norm": 3.9473443031311035, "learning_rate": 2.0036438840384268e-05, "loss": 0.9198, "step": 13050 }, { "epoch": 0.7135349393473432, "grad_norm": 2.1816937923431396, "learning_rate": 2.0029351637874493e-05, "loss": 1.0252, "step": 13051 }, { "epoch": 0.7135896121647018, "grad_norm": 2.6863136291503906, "learning_rate": 2.0022265375067972e-05, "loss": 1.0577, "step": 13052 }, { "epoch": 0.7136442849820605, "grad_norm": 2.4978554248809814, "learning_rate": 2.0015180052186892e-05, "loss": 1.1731, "step": 13053 }, { "epoch": 0.713698957799419, "grad_norm": 2.505112409591675, "learning_rate": 2.0008095669453407e-05, "loss": 1.1259, "step": 13054 }, { "epoch": 0.7137536306167778, "grad_norm": 3.7817249298095703, "learning_rate": 2.0001012227089645e-05, "loss": 0.9726, "step": 13055 }, { "epoch": 0.7138083034341364, "grad_norm": 3.3198447227478027, "learning_rate": 1.9993929725317695e-05, "loss": 1.1585, "step": 13056 }, { "epoch": 0.713862976251495, "grad_norm": 2.2222015857696533, "learning_rate": 1.9986848164359613e-05, "loss": 0.8246, "step": 13057 }, { "epoch": 0.7139176490688536, "grad_norm": 2.9789958000183105, "learning_rate": 1.9979767544437462e-05, "loss": 1.0667, "step": 13058 }, { "epoch": 0.7139723218862122, "grad_norm": 2.8637211322784424, "learning_rate": 1.9972687865773237e-05, "loss": 1.1859, "step": 13059 }, { "epoch": 0.7140269947035708, "grad_norm": 3.2845399379730225, "learning_rate": 1.9965609128588914e-05, "loss": 1.008, "step": 13060 }, { "epoch": 0.7140816675209294, "grad_norm": 2.3202908039093018, "learning_rate": 1.9958531333106434e-05, "loss": 0.89, "step": 13061 }, { "epoch": 0.7141363403382881, "grad_norm": 2.50687313079834, "learning_rate": 1.9951454479547728e-05, "loss": 1.0495, "step": 13062 }, { "epoch": 0.7141910131556467, "grad_norm": 2.5278711318969727, "learning_rate": 1.994437856813467e-05, "loss": 0.786, "step": 13063 }, { "epoch": 0.7142456859730053, "grad_norm": 2.5533554553985596, "learning_rate": 1.993730359908913e-05, "loss": 0.9355, "step": 13064 }, { "epoch": 0.7143003587903639, "grad_norm": 2.7375760078430176, "learning_rate": 1.993022957263293e-05, "loss": 0.9599, "step": 13065 }, { "epoch": 0.7143550316077225, "grad_norm": 2.926734447479248, "learning_rate": 1.9923156488987877e-05, "loss": 0.9909, "step": 13066 }, { "epoch": 0.7144097044250811, "grad_norm": 3.015712022781372, "learning_rate": 1.9916084348375713e-05, "loss": 1.0696, "step": 13067 }, { "epoch": 0.7144643772424398, "grad_norm": 2.9609577655792236, "learning_rate": 1.990901315101823e-05, "loss": 0.8821, "step": 13068 }, { "epoch": 0.7145190500597984, "grad_norm": 3.1204631328582764, "learning_rate": 1.9901942897137106e-05, "loss": 1.1586, "step": 13069 }, { "epoch": 0.714573722877157, "grad_norm": 3.439385414123535, "learning_rate": 1.9894873586954033e-05, "loss": 1.2382, "step": 13070 }, { "epoch": 0.7146283956945156, "grad_norm": 2.8616256713867188, "learning_rate": 1.9887805220690653e-05, "loss": 1.0047, "step": 13071 }, { "epoch": 0.7146830685118742, "grad_norm": 2.465494155883789, "learning_rate": 1.98807377985686e-05, "loss": 1.0421, "step": 13072 }, { "epoch": 0.7147377413292328, "grad_norm": 2.8764584064483643, "learning_rate": 1.9873671320809463e-05, "loss": 1.1374, "step": 13073 }, { "epoch": 0.7147924141465914, "grad_norm": 2.367800235748291, "learning_rate": 1.9866605787634797e-05, "loss": 0.9783, "step": 13074 }, { "epoch": 0.7148470869639502, "grad_norm": 2.655637264251709, "learning_rate": 1.9859541199266145e-05, "loss": 1.0937, "step": 13075 }, { "epoch": 0.7149017597813088, "grad_norm": 4.034111022949219, "learning_rate": 1.985247755592501e-05, "loss": 1.0937, "step": 13076 }, { "epoch": 0.7149564325986674, "grad_norm": 3.6208882331848145, "learning_rate": 1.984541485783284e-05, "loss": 1.0802, "step": 13077 }, { "epoch": 0.715011105416026, "grad_norm": 3.1767754554748535, "learning_rate": 1.9838353105211126e-05, "loss": 1.2013, "step": 13078 }, { "epoch": 0.7150657782333846, "grad_norm": 2.87654709815979, "learning_rate": 1.9831292298281262e-05, "loss": 0.9439, "step": 13079 }, { "epoch": 0.7151204510507432, "grad_norm": 2.4725522994995117, "learning_rate": 1.9824232437264628e-05, "loss": 1.0308, "step": 13080 }, { "epoch": 0.7151751238681018, "grad_norm": 2.967433452606201, "learning_rate": 1.9817173522382586e-05, "loss": 1.1107, "step": 13081 }, { "epoch": 0.7152297966854605, "grad_norm": 2.5790328979492188, "learning_rate": 1.9810115553856463e-05, "loss": 0.9918, "step": 13082 }, { "epoch": 0.7152844695028191, "grad_norm": 3.2861788272857666, "learning_rate": 1.9803058531907548e-05, "loss": 1.0635, "step": 13083 }, { "epoch": 0.7153391423201777, "grad_norm": 2.31318736076355, "learning_rate": 1.9796002456757116e-05, "loss": 1.0405, "step": 13084 }, { "epoch": 0.7153938151375363, "grad_norm": 2.3617327213287354, "learning_rate": 1.9788947328626396e-05, "loss": 1.113, "step": 13085 }, { "epoch": 0.7154484879548949, "grad_norm": 4.383198261260986, "learning_rate": 1.9781893147736602e-05, "loss": 1.1163, "step": 13086 }, { "epoch": 0.7155031607722535, "grad_norm": 2.652508020401001, "learning_rate": 1.977483991430889e-05, "loss": 0.8033, "step": 13087 }, { "epoch": 0.7155578335896121, "grad_norm": 2.7513699531555176, "learning_rate": 1.9767787628564443e-05, "loss": 0.9948, "step": 13088 }, { "epoch": 0.7156125064069708, "grad_norm": 2.4860401153564453, "learning_rate": 1.9760736290724368e-05, "loss": 0.8186, "step": 13089 }, { "epoch": 0.7156671792243294, "grad_norm": 2.722705125808716, "learning_rate": 1.9753685901009745e-05, "loss": 1.0026, "step": 13090 }, { "epoch": 0.715721852041688, "grad_norm": 2.674516201019287, "learning_rate": 1.9746636459641636e-05, "loss": 0.9087, "step": 13091 }, { "epoch": 0.7157765248590466, "grad_norm": 2.723752498626709, "learning_rate": 1.9739587966841073e-05, "loss": 1.1599, "step": 13092 }, { "epoch": 0.7158311976764052, "grad_norm": 3.596423625946045, "learning_rate": 1.9732540422829053e-05, "loss": 0.9997, "step": 13093 }, { "epoch": 0.7158858704937638, "grad_norm": 2.257920503616333, "learning_rate": 1.972549382782654e-05, "loss": 0.8432, "step": 13094 }, { "epoch": 0.7159405433111224, "grad_norm": 2.5009467601776123, "learning_rate": 1.9718448182054488e-05, "loss": 0.8665, "step": 13095 }, { "epoch": 0.7159952161284812, "grad_norm": 2.406541347503662, "learning_rate": 1.971140348573377e-05, "loss": 0.9275, "step": 13096 }, { "epoch": 0.7160498889458398, "grad_norm": 2.2786691188812256, "learning_rate": 1.9704359739085322e-05, "loss": 1.0369, "step": 13097 }, { "epoch": 0.7161045617631984, "grad_norm": 2.594749927520752, "learning_rate": 1.9697316942329957e-05, "loss": 1.0061, "step": 13098 }, { "epoch": 0.716159234580557, "grad_norm": 2.516812562942505, "learning_rate": 1.969027509568851e-05, "loss": 0.813, "step": 13099 }, { "epoch": 0.7162139073979156, "grad_norm": 1.927990198135376, "learning_rate": 1.968323419938177e-05, "loss": 0.8771, "step": 13100 }, { "epoch": 0.7162685802152742, "grad_norm": 2.4646353721618652, "learning_rate": 1.967619425363049e-05, "loss": 0.9995, "step": 13101 }, { "epoch": 0.7163232530326329, "grad_norm": 2.979707956314087, "learning_rate": 1.9669155258655407e-05, "loss": 0.9441, "step": 13102 }, { "epoch": 0.7163779258499915, "grad_norm": 2.3479859828948975, "learning_rate": 1.9662117214677227e-05, "loss": 1.0259, "step": 13103 }, { "epoch": 0.7164325986673501, "grad_norm": 2.729787826538086, "learning_rate": 1.9655080121916613e-05, "loss": 0.9199, "step": 13104 }, { "epoch": 0.7164872714847087, "grad_norm": 2.2676773071289062, "learning_rate": 1.9648043980594217e-05, "loss": 0.9458, "step": 13105 }, { "epoch": 0.7165419443020673, "grad_norm": 2.637509346008301, "learning_rate": 1.964100879093062e-05, "loss": 0.9414, "step": 13106 }, { "epoch": 0.7165966171194259, "grad_norm": 2.760664224624634, "learning_rate": 1.9633974553146444e-05, "loss": 1.1216, "step": 13107 }, { "epoch": 0.7166512899367845, "grad_norm": 2.5311660766601562, "learning_rate": 1.9626941267462236e-05, "loss": 0.9708, "step": 13108 }, { "epoch": 0.7167059627541432, "grad_norm": 3.0335540771484375, "learning_rate": 1.9619908934098502e-05, "loss": 1.1422, "step": 13109 }, { "epoch": 0.7167606355715018, "grad_norm": 2.2666690349578857, "learning_rate": 1.9612877553275738e-05, "loss": 0.8885, "step": 13110 }, { "epoch": 0.7168153083888604, "grad_norm": 2.366438627243042, "learning_rate": 1.9605847125214417e-05, "loss": 1.0553, "step": 13111 }, { "epoch": 0.716869981206219, "grad_norm": 4.382397174835205, "learning_rate": 1.959881765013496e-05, "loss": 0.9439, "step": 13112 }, { "epoch": 0.7169246540235776, "grad_norm": 3.1416866779327393, "learning_rate": 1.9591789128257777e-05, "loss": 1.1231, "step": 13113 }, { "epoch": 0.7169793268409362, "grad_norm": 2.3448357582092285, "learning_rate": 1.9584761559803237e-05, "loss": 1.0352, "step": 13114 }, { "epoch": 0.7170339996582948, "grad_norm": 2.4032883644104004, "learning_rate": 1.9577734944991688e-05, "loss": 1.087, "step": 13115 }, { "epoch": 0.7170886724756536, "grad_norm": 3.6829113960266113, "learning_rate": 1.9570709284043426e-05, "loss": 1.0189, "step": 13116 }, { "epoch": 0.7171433452930122, "grad_norm": 2.433093309402466, "learning_rate": 1.956368457717876e-05, "loss": 1.0728, "step": 13117 }, { "epoch": 0.7171980181103708, "grad_norm": 2.531810760498047, "learning_rate": 1.9556660824617934e-05, "loss": 1.2108, "step": 13118 }, { "epoch": 0.7172526909277294, "grad_norm": 2.8859050273895264, "learning_rate": 1.9549638026581175e-05, "loss": 0.9969, "step": 13119 }, { "epoch": 0.717307363745088, "grad_norm": 3.8214075565338135, "learning_rate": 1.9542616183288665e-05, "loss": 1.1378, "step": 13120 }, { "epoch": 0.7173620365624466, "grad_norm": 3.2395942211151123, "learning_rate": 1.9535595294960575e-05, "loss": 0.9793, "step": 13121 }, { "epoch": 0.7174167093798052, "grad_norm": 2.3962631225585938, "learning_rate": 1.952857536181704e-05, "loss": 1.0357, "step": 13122 }, { "epoch": 0.7174713821971639, "grad_norm": 2.3583757877349854, "learning_rate": 1.952155638407816e-05, "loss": 0.9744, "step": 13123 }, { "epoch": 0.7175260550145225, "grad_norm": 2.1371867656707764, "learning_rate": 1.9514538361964014e-05, "loss": 0.9118, "step": 13124 }, { "epoch": 0.7175807278318811, "grad_norm": 2.3920483589172363, "learning_rate": 1.950752129569464e-05, "loss": 0.8918, "step": 13125 }, { "epoch": 0.7176354006492397, "grad_norm": 2.3434596061706543, "learning_rate": 1.9500505185490042e-05, "loss": 1.0376, "step": 13126 }, { "epoch": 0.7176900734665983, "grad_norm": 2.378005027770996, "learning_rate": 1.9493490031570227e-05, "loss": 1.1349, "step": 13127 }, { "epoch": 0.7177447462839569, "grad_norm": 2.6968421936035156, "learning_rate": 1.9486475834155145e-05, "loss": 0.9379, "step": 13128 }, { "epoch": 0.7177994191013156, "grad_norm": 3.2149081230163574, "learning_rate": 1.9479462593464708e-05, "loss": 1.1021, "step": 13129 }, { "epoch": 0.7178540919186742, "grad_norm": 2.7431252002716064, "learning_rate": 1.9472450309718814e-05, "loss": 1.0235, "step": 13130 }, { "epoch": 0.7179087647360328, "grad_norm": 2.0457091331481934, "learning_rate": 1.9465438983137334e-05, "loss": 0.9791, "step": 13131 }, { "epoch": 0.7179634375533914, "grad_norm": 2.8715569972991943, "learning_rate": 1.9458428613940095e-05, "loss": 0.9648, "step": 13132 }, { "epoch": 0.71801811037075, "grad_norm": 2.4275851249694824, "learning_rate": 1.9451419202346898e-05, "loss": 0.7901, "step": 13133 }, { "epoch": 0.7180727831881086, "grad_norm": 2.6776251792907715, "learning_rate": 1.944441074857753e-05, "loss": 1.0601, "step": 13134 }, { "epoch": 0.7181274560054672, "grad_norm": 2.1373989582061768, "learning_rate": 1.9437403252851714e-05, "loss": 1.037, "step": 13135 }, { "epoch": 0.718182128822826, "grad_norm": 2.3785555362701416, "learning_rate": 1.9430396715389172e-05, "loss": 0.9745, "step": 13136 }, { "epoch": 0.7182368016401846, "grad_norm": 2.768315315246582, "learning_rate": 1.94233911364096e-05, "loss": 1.1716, "step": 13137 }, { "epoch": 0.7182914744575432, "grad_norm": 3.1470916271209717, "learning_rate": 1.9416386516132646e-05, "loss": 0.9448, "step": 13138 }, { "epoch": 0.7183461472749018, "grad_norm": 3.07698917388916, "learning_rate": 1.940938285477793e-05, "loss": 1.1526, "step": 13139 }, { "epoch": 0.7184008200922604, "grad_norm": 2.6616814136505127, "learning_rate": 1.9402380152565048e-05, "loss": 0.8482, "step": 13140 }, { "epoch": 0.718455492909619, "grad_norm": 2.7486941814422607, "learning_rate": 1.9395378409713567e-05, "loss": 0.9498, "step": 13141 }, { "epoch": 0.7185101657269776, "grad_norm": 2.3833463191986084, "learning_rate": 1.938837762644301e-05, "loss": 1.0275, "step": 13142 }, { "epoch": 0.7185648385443363, "grad_norm": 2.310575485229492, "learning_rate": 1.938137780297289e-05, "loss": 1.1387, "step": 13143 }, { "epoch": 0.7186195113616949, "grad_norm": 2.3497138023376465, "learning_rate": 1.937437893952267e-05, "loss": 0.9575, "step": 13144 }, { "epoch": 0.7186741841790535, "grad_norm": 2.4901771545410156, "learning_rate": 1.9367381036311806e-05, "loss": 1.005, "step": 13145 }, { "epoch": 0.7187288569964121, "grad_norm": 4.0358686447143555, "learning_rate": 1.9360384093559686e-05, "loss": 1.1044, "step": 13146 }, { "epoch": 0.7187835298137707, "grad_norm": 2.3924732208251953, "learning_rate": 1.9353388111485725e-05, "loss": 0.8759, "step": 13147 }, { "epoch": 0.7188382026311293, "grad_norm": 2.4145123958587646, "learning_rate": 1.9346393090309266e-05, "loss": 1.1642, "step": 13148 }, { "epoch": 0.7188928754484879, "grad_norm": 2.528066873550415, "learning_rate": 1.9339399030249634e-05, "loss": 1.0597, "step": 13149 }, { "epoch": 0.7189475482658466, "grad_norm": 2.618722438812256, "learning_rate": 1.933240593152611e-05, "loss": 0.9903, "step": 13150 }, { "epoch": 0.7190022210832052, "grad_norm": 2.6997835636138916, "learning_rate": 1.932541379435796e-05, "loss": 0.9153, "step": 13151 }, { "epoch": 0.7190568939005638, "grad_norm": 3.164957284927368, "learning_rate": 1.931842261896442e-05, "loss": 0.9886, "step": 13152 }, { "epoch": 0.7191115667179224, "grad_norm": 3.4121906757354736, "learning_rate": 1.9311432405564695e-05, "loss": 0.9941, "step": 13153 }, { "epoch": 0.719166239535281, "grad_norm": 3.8091342449188232, "learning_rate": 1.9304443154377954e-05, "loss": 0.8333, "step": 13154 }, { "epoch": 0.7192209123526396, "grad_norm": 2.744696617126465, "learning_rate": 1.9297454865623315e-05, "loss": 1.1319, "step": 13155 }, { "epoch": 0.7192755851699983, "grad_norm": 2.586902618408203, "learning_rate": 1.929046753951993e-05, "loss": 0.9389, "step": 13156 }, { "epoch": 0.719330257987357, "grad_norm": 2.4668192863464355, "learning_rate": 1.9283481176286866e-05, "loss": 1.1627, "step": 13157 }, { "epoch": 0.7193849308047155, "grad_norm": 2.599684000015259, "learning_rate": 1.927649577614317e-05, "loss": 1.0026, "step": 13158 }, { "epoch": 0.7194396036220742, "grad_norm": 2.412224054336548, "learning_rate": 1.9269511339307862e-05, "loss": 0.9912, "step": 13159 }, { "epoch": 0.7194942764394328, "grad_norm": 2.876762628555298, "learning_rate": 1.9262527865999934e-05, "loss": 1.0967, "step": 13160 }, { "epoch": 0.7195489492567914, "grad_norm": 2.6116907596588135, "learning_rate": 1.9255545356438354e-05, "loss": 1.092, "step": 13161 }, { "epoch": 0.71960362207415, "grad_norm": 2.5369796752929688, "learning_rate": 1.924856381084204e-05, "loss": 0.8744, "step": 13162 }, { "epoch": 0.7196582948915087, "grad_norm": 2.845916509628296, "learning_rate": 1.9241583229429898e-05, "loss": 1.0174, "step": 13163 }, { "epoch": 0.7197129677088673, "grad_norm": 2.4052858352661133, "learning_rate": 1.9234603612420805e-05, "loss": 0.9368, "step": 13164 }, { "epoch": 0.7197676405262259, "grad_norm": 3.0002968311309814, "learning_rate": 1.9227624960033567e-05, "loss": 1.042, "step": 13165 }, { "epoch": 0.7198223133435845, "grad_norm": 3.0839033126831055, "learning_rate": 1.9220647272487045e-05, "loss": 0.8348, "step": 13166 }, { "epoch": 0.7198769861609431, "grad_norm": 2.3856160640716553, "learning_rate": 1.921367054999999e-05, "loss": 1.131, "step": 13167 }, { "epoch": 0.7199316589783017, "grad_norm": 2.6177892684936523, "learning_rate": 1.9206694792791157e-05, "loss": 0.9453, "step": 13168 }, { "epoch": 0.7199863317956603, "grad_norm": 2.657552480697632, "learning_rate": 1.9199720001079262e-05, "loss": 1.0657, "step": 13169 }, { "epoch": 0.720041004613019, "grad_norm": 2.334929943084717, "learning_rate": 1.9192746175082994e-05, "loss": 1.0994, "step": 13170 }, { "epoch": 0.7200956774303776, "grad_norm": 3.129288911819458, "learning_rate": 1.918577331502101e-05, "loss": 0.9249, "step": 13171 }, { "epoch": 0.7201503502477362, "grad_norm": 3.28945255279541, "learning_rate": 1.9178801421111943e-05, "loss": 0.8799, "step": 13172 }, { "epoch": 0.7202050230650948, "grad_norm": 3.2076432704925537, "learning_rate": 1.9171830493574376e-05, "loss": 1.0096, "step": 13173 }, { "epoch": 0.7202596958824534, "grad_norm": 2.330111026763916, "learning_rate": 1.9164860532626895e-05, "loss": 0.9153, "step": 13174 }, { "epoch": 0.720314368699812, "grad_norm": 2.806791305541992, "learning_rate": 1.915789153848801e-05, "loss": 1.158, "step": 13175 }, { "epoch": 0.7203690415171706, "grad_norm": 2.497300148010254, "learning_rate": 1.9150923511376263e-05, "loss": 0.7722, "step": 13176 }, { "epoch": 0.7204237143345293, "grad_norm": 2.591094493865967, "learning_rate": 1.9143956451510114e-05, "loss": 0.9828, "step": 13177 }, { "epoch": 0.720478387151888, "grad_norm": 2.8949966430664062, "learning_rate": 1.913699035910801e-05, "loss": 1.1109, "step": 13178 }, { "epoch": 0.7205330599692465, "grad_norm": 2.074528932571411, "learning_rate": 1.9130025234388362e-05, "loss": 0.8101, "step": 13179 }, { "epoch": 0.7205877327866052, "grad_norm": 2.824284315109253, "learning_rate": 1.912306107756956e-05, "loss": 0.9723, "step": 13180 }, { "epoch": 0.7206424056039638, "grad_norm": 2.7409591674804688, "learning_rate": 1.911609788886996e-05, "loss": 1.0074, "step": 13181 }, { "epoch": 0.7206970784213224, "grad_norm": 2.3808035850524902, "learning_rate": 1.9109135668507884e-05, "loss": 1.0873, "step": 13182 }, { "epoch": 0.7207517512386811, "grad_norm": 2.113053798675537, "learning_rate": 1.9102174416701623e-05, "loss": 0.9298, "step": 13183 }, { "epoch": 0.7208064240560397, "grad_norm": 2.774240255355835, "learning_rate": 1.9095214133669447e-05, "loss": 1.1813, "step": 13184 }, { "epoch": 0.7208610968733983, "grad_norm": 2.2523889541625977, "learning_rate": 1.908825481962957e-05, "loss": 0.8084, "step": 13185 }, { "epoch": 0.7209157696907569, "grad_norm": 2.954360246658325, "learning_rate": 1.908129647480023e-05, "loss": 1.0165, "step": 13186 }, { "epoch": 0.7209704425081155, "grad_norm": 2.777467966079712, "learning_rate": 1.9074339099399585e-05, "loss": 1.061, "step": 13187 }, { "epoch": 0.7210251153254741, "grad_norm": 2.8078041076660156, "learning_rate": 1.9067382693645767e-05, "loss": 0.9506, "step": 13188 }, { "epoch": 0.7210797881428327, "grad_norm": 2.5602991580963135, "learning_rate": 1.90604272577569e-05, "loss": 1.244, "step": 13189 }, { "epoch": 0.7211344609601914, "grad_norm": 2.680001974105835, "learning_rate": 1.9053472791951065e-05, "loss": 0.9329, "step": 13190 }, { "epoch": 0.72118913377755, "grad_norm": 2.1441843509674072, "learning_rate": 1.9046519296446302e-05, "loss": 0.9542, "step": 13191 }, { "epoch": 0.7212438065949086, "grad_norm": 2.1865930557250977, "learning_rate": 1.9039566771460644e-05, "loss": 0.7542, "step": 13192 }, { "epoch": 0.7212984794122672, "grad_norm": 3.616717576980591, "learning_rate": 1.9032615217212074e-05, "loss": 1.049, "step": 13193 }, { "epoch": 0.7213531522296258, "grad_norm": 3.307795763015747, "learning_rate": 1.9025664633918554e-05, "loss": 1.1143, "step": 13194 }, { "epoch": 0.7214078250469844, "grad_norm": 2.1458840370178223, "learning_rate": 1.9018715021798012e-05, "loss": 1.0493, "step": 13195 }, { "epoch": 0.721462497864343, "grad_norm": 2.5099587440490723, "learning_rate": 1.901176638106833e-05, "loss": 0.9375, "step": 13196 }, { "epoch": 0.7215171706817017, "grad_norm": 2.927013874053955, "learning_rate": 1.9004818711947415e-05, "loss": 1.1396, "step": 13197 }, { "epoch": 0.7215718434990603, "grad_norm": 3.2371485233306885, "learning_rate": 1.8997872014653084e-05, "loss": 0.9584, "step": 13198 }, { "epoch": 0.7216265163164189, "grad_norm": 2.7286055088043213, "learning_rate": 1.8990926289403148e-05, "loss": 1.2198, "step": 13199 }, { "epoch": 0.7216811891337775, "grad_norm": 2.906553268432617, "learning_rate": 1.898398153641538e-05, "loss": 0.9671, "step": 13200 }, { "epoch": 0.7217358619511361, "grad_norm": 3.095320701599121, "learning_rate": 1.897703775590753e-05, "loss": 0.9144, "step": 13201 }, { "epoch": 0.7217905347684948, "grad_norm": 2.504882335662842, "learning_rate": 1.8970094948097307e-05, "loss": 0.8824, "step": 13202 }, { "epoch": 0.7218452075858534, "grad_norm": 2.6431758403778076, "learning_rate": 1.8963153113202402e-05, "loss": 1.0744, "step": 13203 }, { "epoch": 0.7218998804032121, "grad_norm": 2.346872568130493, "learning_rate": 1.8956212251440476e-05, "loss": 0.9854, "step": 13204 }, { "epoch": 0.7219545532205707, "grad_norm": 2.715441942214966, "learning_rate": 1.894927236302914e-05, "loss": 1.09, "step": 13205 }, { "epoch": 0.7220092260379293, "grad_norm": 2.5303125381469727, "learning_rate": 1.8942333448186e-05, "loss": 1.1512, "step": 13206 }, { "epoch": 0.7220638988552879, "grad_norm": 2.1633517742156982, "learning_rate": 1.893539550712862e-05, "loss": 0.9226, "step": 13207 }, { "epoch": 0.7221185716726465, "grad_norm": 3.035252809524536, "learning_rate": 1.8928458540074525e-05, "loss": 1.1484, "step": 13208 }, { "epoch": 0.7221732444900051, "grad_norm": 3.4229931831359863, "learning_rate": 1.89215225472412e-05, "loss": 1.1383, "step": 13209 }, { "epoch": 0.7222279173073638, "grad_norm": 2.5256905555725098, "learning_rate": 1.8914587528846157e-05, "loss": 0.9113, "step": 13210 }, { "epoch": 0.7222825901247224, "grad_norm": 2.715045213699341, "learning_rate": 1.8907653485106818e-05, "loss": 0.8295, "step": 13211 }, { "epoch": 0.722337262942081, "grad_norm": 2.9072418212890625, "learning_rate": 1.890072041624059e-05, "loss": 0.9926, "step": 13212 }, { "epoch": 0.7223919357594396, "grad_norm": 4.155877113342285, "learning_rate": 1.8893788322464866e-05, "loss": 1.1946, "step": 13213 }, { "epoch": 0.7224466085767982, "grad_norm": 3.0975630283355713, "learning_rate": 1.8886857203996982e-05, "loss": 1.1538, "step": 13214 }, { "epoch": 0.7225012813941568, "grad_norm": 3.4346773624420166, "learning_rate": 1.887992706105426e-05, "loss": 1.0529, "step": 13215 }, { "epoch": 0.7225559542115154, "grad_norm": 2.74875545501709, "learning_rate": 1.8872997893853993e-05, "loss": 1.1571, "step": 13216 }, { "epoch": 0.7226106270288741, "grad_norm": 2.2412219047546387, "learning_rate": 1.8866069702613437e-05, "loss": 1.0556, "step": 13217 }, { "epoch": 0.7226652998462327, "grad_norm": 2.8085992336273193, "learning_rate": 1.885914248754982e-05, "loss": 0.9009, "step": 13218 }, { "epoch": 0.7227199726635913, "grad_norm": 3.9162075519561768, "learning_rate": 1.8852216248880333e-05, "loss": 0.8952, "step": 13219 }, { "epoch": 0.7227746454809499, "grad_norm": 2.0843727588653564, "learning_rate": 1.8845290986822152e-05, "loss": 1.005, "step": 13220 }, { "epoch": 0.7228293182983085, "grad_norm": 2.1332783699035645, "learning_rate": 1.8838366701592402e-05, "loss": 1.0935, "step": 13221 }, { "epoch": 0.7228839911156671, "grad_norm": 4.116275310516357, "learning_rate": 1.8831443393408178e-05, "loss": 1.1395, "step": 13222 }, { "epoch": 0.7229386639330257, "grad_norm": 2.439242124557495, "learning_rate": 1.882452106248659e-05, "loss": 0.992, "step": 13223 }, { "epoch": 0.7229933367503845, "grad_norm": 2.2224056720733643, "learning_rate": 1.8817599709044654e-05, "loss": 0.9638, "step": 13224 }, { "epoch": 0.7230480095677431, "grad_norm": 2.1167783737182617, "learning_rate": 1.8810679333299393e-05, "loss": 0.8389, "step": 13225 }, { "epoch": 0.7231026823851017, "grad_norm": 3.724138021469116, "learning_rate": 1.8803759935467784e-05, "loss": 0.9511, "step": 13226 }, { "epoch": 0.7231573552024603, "grad_norm": 2.9451165199279785, "learning_rate": 1.8796841515766783e-05, "loss": 1.0941, "step": 13227 }, { "epoch": 0.7232120280198189, "grad_norm": 2.3164262771606445, "learning_rate": 1.8789924074413305e-05, "loss": 1.1582, "step": 13228 }, { "epoch": 0.7232667008371775, "grad_norm": 2.643362283706665, "learning_rate": 1.8783007611624248e-05, "loss": 1.2327, "step": 13229 }, { "epoch": 0.7233213736545361, "grad_norm": 3.268071413040161, "learning_rate": 1.8776092127616467e-05, "loss": 0.8954, "step": 13230 }, { "epoch": 0.7233760464718948, "grad_norm": 3.0899040699005127, "learning_rate": 1.8769177622606794e-05, "loss": 1.1333, "step": 13231 }, { "epoch": 0.7234307192892534, "grad_norm": 2.7050845623016357, "learning_rate": 1.876226409681202e-05, "loss": 1.0862, "step": 13232 }, { "epoch": 0.723485392106612, "grad_norm": 2.6851587295532227, "learning_rate": 1.8755351550448917e-05, "loss": 0.9394, "step": 13233 }, { "epoch": 0.7235400649239706, "grad_norm": 2.554981231689453, "learning_rate": 1.8748439983734207e-05, "loss": 0.9987, "step": 13234 }, { "epoch": 0.7235947377413292, "grad_norm": 2.9931459426879883, "learning_rate": 1.874152939688463e-05, "loss": 0.9656, "step": 13235 }, { "epoch": 0.7236494105586878, "grad_norm": 3.0803914070129395, "learning_rate": 1.8734619790116837e-05, "loss": 1.0097, "step": 13236 }, { "epoch": 0.7237040833760465, "grad_norm": 2.6034421920776367, "learning_rate": 1.8727711163647477e-05, "loss": 1.0826, "step": 13237 }, { "epoch": 0.7237587561934051, "grad_norm": 2.6612548828125, "learning_rate": 1.8720803517693168e-05, "loss": 0.801, "step": 13238 }, { "epoch": 0.7238134290107637, "grad_norm": 2.5795066356658936, "learning_rate": 1.8713896852470492e-05, "loss": 1.0524, "step": 13239 }, { "epoch": 0.7238681018281223, "grad_norm": 2.6971993446350098, "learning_rate": 1.870699116819599e-05, "loss": 1.0999, "step": 13240 }, { "epoch": 0.7239227746454809, "grad_norm": 2.3825690746307373, "learning_rate": 1.8700086465086204e-05, "loss": 1.0229, "step": 13241 }, { "epoch": 0.7239774474628395, "grad_norm": 2.578674077987671, "learning_rate": 1.8693182743357612e-05, "loss": 0.9877, "step": 13242 }, { "epoch": 0.7240321202801981, "grad_norm": 3.384392738342285, "learning_rate": 1.8686280003226673e-05, "loss": 1.1507, "step": 13243 }, { "epoch": 0.7240867930975569, "grad_norm": 2.699976682662964, "learning_rate": 1.86793782449098e-05, "loss": 0.8633, "step": 13244 }, { "epoch": 0.7241414659149155, "grad_norm": 2.3429765701293945, "learning_rate": 1.8672477468623433e-05, "loss": 0.9272, "step": 13245 }, { "epoch": 0.7241961387322741, "grad_norm": 2.2280309200286865, "learning_rate": 1.8665577674583917e-05, "loss": 0.9941, "step": 13246 }, { "epoch": 0.7242508115496327, "grad_norm": 2.643648386001587, "learning_rate": 1.865867886300759e-05, "loss": 1.1949, "step": 13247 }, { "epoch": 0.7243054843669913, "grad_norm": 3.4207513332366943, "learning_rate": 1.8651781034110753e-05, "loss": 1.1988, "step": 13248 }, { "epoch": 0.7243601571843499, "grad_norm": 3.064027786254883, "learning_rate": 1.864488418810969e-05, "loss": 1.1052, "step": 13249 }, { "epoch": 0.7244148300017085, "grad_norm": 2.586951732635498, "learning_rate": 1.863798832522064e-05, "loss": 0.954, "step": 13250 }, { "epoch": 0.7244695028190672, "grad_norm": 2.5602729320526123, "learning_rate": 1.863109344565982e-05, "loss": 0.9973, "step": 13251 }, { "epoch": 0.7245241756364258, "grad_norm": 3.1250650882720947, "learning_rate": 1.8624199549643407e-05, "loss": 0.8419, "step": 13252 }, { "epoch": 0.7245788484537844, "grad_norm": 2.767137050628662, "learning_rate": 1.8617306637387545e-05, "loss": 1.1379, "step": 13253 }, { "epoch": 0.724633521271143, "grad_norm": 2.5987932682037354, "learning_rate": 1.8610414709108383e-05, "loss": 1.0766, "step": 13254 }, { "epoch": 0.7246881940885016, "grad_norm": 2.738588333129883, "learning_rate": 1.8603523765021996e-05, "loss": 1.093, "step": 13255 }, { "epoch": 0.7247428669058602, "grad_norm": 2.5100107192993164, "learning_rate": 1.8596633805344443e-05, "loss": 1.0031, "step": 13256 }, { "epoch": 0.7247975397232188, "grad_norm": 2.73599910736084, "learning_rate": 1.858974483029175e-05, "loss": 1.0834, "step": 13257 }, { "epoch": 0.7248522125405775, "grad_norm": 3.2933785915374756, "learning_rate": 1.8582856840079922e-05, "loss": 1.0242, "step": 13258 }, { "epoch": 0.7249068853579361, "grad_norm": 2.5659072399139404, "learning_rate": 1.8575969834924918e-05, "loss": 1.0607, "step": 13259 }, { "epoch": 0.7249615581752947, "grad_norm": 4.06325101852417, "learning_rate": 1.8569083815042676e-05, "loss": 1.0677, "step": 13260 }, { "epoch": 0.7250162309926533, "grad_norm": 3.171947479248047, "learning_rate": 1.856219878064911e-05, "loss": 0.9194, "step": 13261 }, { "epoch": 0.7250709038100119, "grad_norm": 3.1381309032440186, "learning_rate": 1.8555314731960076e-05, "loss": 1.062, "step": 13262 }, { "epoch": 0.7251255766273705, "grad_norm": 2.703033685684204, "learning_rate": 1.854843166919142e-05, "loss": 0.9515, "step": 13263 }, { "epoch": 0.7251802494447293, "grad_norm": 3.92826771736145, "learning_rate": 1.8541549592558977e-05, "loss": 1.1012, "step": 13264 }, { "epoch": 0.7252349222620879, "grad_norm": 2.1585707664489746, "learning_rate": 1.8534668502278513e-05, "loss": 0.8328, "step": 13265 }, { "epoch": 0.7252895950794465, "grad_norm": 2.8574776649475098, "learning_rate": 1.8527788398565776e-05, "loss": 0.9949, "step": 13266 }, { "epoch": 0.7253442678968051, "grad_norm": 2.5478224754333496, "learning_rate": 1.8520909281636495e-05, "loss": 1.0745, "step": 13267 }, { "epoch": 0.7253989407141637, "grad_norm": 2.196737289428711, "learning_rate": 1.8514031151706346e-05, "loss": 0.8649, "step": 13268 }, { "epoch": 0.7254536135315223, "grad_norm": 2.423264980316162, "learning_rate": 1.8507154008990996e-05, "loss": 1.0149, "step": 13269 }, { "epoch": 0.7255082863488809, "grad_norm": 2.596264362335205, "learning_rate": 1.8500277853706073e-05, "loss": 1.0259, "step": 13270 }, { "epoch": 0.7255629591662396, "grad_norm": 2.886505126953125, "learning_rate": 1.8493402686067163e-05, "loss": 1.1542, "step": 13271 }, { "epoch": 0.7256176319835982, "grad_norm": 2.490129232406616, "learning_rate": 1.848652850628984e-05, "loss": 1.0742, "step": 13272 }, { "epoch": 0.7256723048009568, "grad_norm": 2.336700677871704, "learning_rate": 1.8479655314589618e-05, "loss": 1.0693, "step": 13273 }, { "epoch": 0.7257269776183154, "grad_norm": 2.503716468811035, "learning_rate": 1.847278311118203e-05, "loss": 0.9988, "step": 13274 }, { "epoch": 0.725781650435674, "grad_norm": 2.6347475051879883, "learning_rate": 1.8465911896282535e-05, "loss": 1.0252, "step": 13275 }, { "epoch": 0.7258363232530326, "grad_norm": 2.4728643894195557, "learning_rate": 1.8459041670106575e-05, "loss": 0.9926, "step": 13276 }, { "epoch": 0.7258909960703912, "grad_norm": 3.0699636936187744, "learning_rate": 1.8452172432869553e-05, "loss": 1.0874, "step": 13277 }, { "epoch": 0.7259456688877499, "grad_norm": 3.076063871383667, "learning_rate": 1.844530418478686e-05, "loss": 1.1293, "step": 13278 }, { "epoch": 0.7260003417051085, "grad_norm": 2.709651231765747, "learning_rate": 1.843843692607383e-05, "loss": 1.1165, "step": 13279 }, { "epoch": 0.7260550145224671, "grad_norm": 2.4465107917785645, "learning_rate": 1.843157065694579e-05, "loss": 1.0169, "step": 13280 }, { "epoch": 0.7261096873398257, "grad_norm": 2.1843855381011963, "learning_rate": 1.8424705377618022e-05, "loss": 1.0241, "step": 13281 }, { "epoch": 0.7261643601571843, "grad_norm": 2.3323919773101807, "learning_rate": 1.841784108830578e-05, "loss": 1.1141, "step": 13282 }, { "epoch": 0.7262190329745429, "grad_norm": 2.8133187294006348, "learning_rate": 1.8410977789224278e-05, "loss": 0.8732, "step": 13283 }, { "epoch": 0.7262737057919015, "grad_norm": 2.705472707748413, "learning_rate": 1.840411548058873e-05, "loss": 1.1677, "step": 13284 }, { "epoch": 0.7263283786092603, "grad_norm": 2.5063371658325195, "learning_rate": 1.8397254162614285e-05, "loss": 0.9767, "step": 13285 }, { "epoch": 0.7263830514266189, "grad_norm": 2.243039608001709, "learning_rate": 1.8390393835516078e-05, "loss": 1.0456, "step": 13286 }, { "epoch": 0.7264377242439775, "grad_norm": 2.571035861968994, "learning_rate": 1.8383534499509208e-05, "loss": 1.083, "step": 13287 }, { "epoch": 0.7264923970613361, "grad_norm": 2.8856492042541504, "learning_rate": 1.8376676154808743e-05, "loss": 0.999, "step": 13288 }, { "epoch": 0.7265470698786947, "grad_norm": 2.844303846359253, "learning_rate": 1.836981880162972e-05, "loss": 1.0298, "step": 13289 }, { "epoch": 0.7266017426960533, "grad_norm": 2.2882771492004395, "learning_rate": 1.8362962440187135e-05, "loss": 0.8037, "step": 13290 }, { "epoch": 0.726656415513412, "grad_norm": 2.7179713249206543, "learning_rate": 1.8356107070695983e-05, "loss": 0.9505, "step": 13291 }, { "epoch": 0.7267110883307706, "grad_norm": 2.505188226699829, "learning_rate": 1.8349252693371195e-05, "loss": 1.0443, "step": 13292 }, { "epoch": 0.7267657611481292, "grad_norm": 2.7823808193206787, "learning_rate": 1.8342399308427667e-05, "loss": 1.0644, "step": 13293 }, { "epoch": 0.7268204339654878, "grad_norm": 2.7123606204986572, "learning_rate": 1.8335546916080315e-05, "loss": 0.9614, "step": 13294 }, { "epoch": 0.7268751067828464, "grad_norm": 2.554856300354004, "learning_rate": 1.832869551654398e-05, "loss": 0.909, "step": 13295 }, { "epoch": 0.726929779600205, "grad_norm": 2.5462024211883545, "learning_rate": 1.8321845110033474e-05, "loss": 1.1023, "step": 13296 }, { "epoch": 0.7269844524175636, "grad_norm": 2.126784086227417, "learning_rate": 1.8314995696763586e-05, "loss": 0.9264, "step": 13297 }, { "epoch": 0.7270391252349223, "grad_norm": 2.354419231414795, "learning_rate": 1.8308147276949084e-05, "loss": 1.0789, "step": 13298 }, { "epoch": 0.7270937980522809, "grad_norm": 2.003803014755249, "learning_rate": 1.8301299850804678e-05, "loss": 0.8372, "step": 13299 }, { "epoch": 0.7271484708696395, "grad_norm": 2.98467755317688, "learning_rate": 1.8294453418545072e-05, "loss": 1.0518, "step": 13300 }, { "epoch": 0.7272031436869981, "grad_norm": 2.7371714115142822, "learning_rate": 1.828760798038493e-05, "loss": 0.9571, "step": 13301 }, { "epoch": 0.7272578165043567, "grad_norm": 2.678985595703125, "learning_rate": 1.828076353653888e-05, "loss": 1.0031, "step": 13302 }, { "epoch": 0.7273124893217153, "grad_norm": 2.608912229537964, "learning_rate": 1.8273920087221513e-05, "loss": 0.9529, "step": 13303 }, { "epoch": 0.7273671621390739, "grad_norm": 2.6354880332946777, "learning_rate": 1.8267077632647428e-05, "loss": 0.9765, "step": 13304 }, { "epoch": 0.7274218349564326, "grad_norm": 2.630782127380371, "learning_rate": 1.8260236173031152e-05, "loss": 0.9573, "step": 13305 }, { "epoch": 0.7274765077737912, "grad_norm": 2.485555410385132, "learning_rate": 1.825339570858719e-05, "loss": 0.9461, "step": 13306 }, { "epoch": 0.7275311805911499, "grad_norm": 2.657470226287842, "learning_rate": 1.8246556239530017e-05, "loss": 1.0361, "step": 13307 }, { "epoch": 0.7275858534085085, "grad_norm": 2.3468029499053955, "learning_rate": 1.8239717766074078e-05, "loss": 0.8771, "step": 13308 }, { "epoch": 0.7276405262258671, "grad_norm": 2.6369833946228027, "learning_rate": 1.823288028843379e-05, "loss": 1.1786, "step": 13309 }, { "epoch": 0.7276951990432257, "grad_norm": 4.241086483001709, "learning_rate": 1.822604380682354e-05, "loss": 1.3643, "step": 13310 }, { "epoch": 0.7277498718605843, "grad_norm": 2.621633768081665, "learning_rate": 1.821920832145767e-05, "loss": 1.0145, "step": 13311 }, { "epoch": 0.727804544677943, "grad_norm": 2.1846847534179688, "learning_rate": 1.8212373832550488e-05, "loss": 1.0119, "step": 13312 }, { "epoch": 0.7278592174953016, "grad_norm": 2.3945112228393555, "learning_rate": 1.8205540340316323e-05, "loss": 1.0157, "step": 13313 }, { "epoch": 0.7279138903126602, "grad_norm": 3.054967164993286, "learning_rate": 1.8198707844969414e-05, "loss": 1.0046, "step": 13314 }, { "epoch": 0.7279685631300188, "grad_norm": 2.687509298324585, "learning_rate": 1.819187634672398e-05, "loss": 0.9296, "step": 13315 }, { "epoch": 0.7280232359473774, "grad_norm": 2.3095152378082275, "learning_rate": 1.8185045845794225e-05, "loss": 1.0593, "step": 13316 }, { "epoch": 0.728077908764736, "grad_norm": 2.8969266414642334, "learning_rate": 1.817821634239431e-05, "loss": 1.0787, "step": 13317 }, { "epoch": 0.7281325815820947, "grad_norm": 2.4817728996276855, "learning_rate": 1.8171387836738368e-05, "loss": 1.0582, "step": 13318 }, { "epoch": 0.7281872543994533, "grad_norm": 3.0653750896453857, "learning_rate": 1.8164560329040502e-05, "loss": 0.8764, "step": 13319 }, { "epoch": 0.7282419272168119, "grad_norm": 2.414740800857544, "learning_rate": 1.8157733819514782e-05, "loss": 0.7943, "step": 13320 }, { "epoch": 0.7282966000341705, "grad_norm": 3.673865795135498, "learning_rate": 1.8150908308375248e-05, "loss": 1.041, "step": 13321 }, { "epoch": 0.7283512728515291, "grad_norm": 3.043304920196533, "learning_rate": 1.8144083795835885e-05, "loss": 0.9839, "step": 13322 }, { "epoch": 0.7284059456688877, "grad_norm": 2.20328688621521, "learning_rate": 1.8137260282110714e-05, "loss": 0.9636, "step": 13323 }, { "epoch": 0.7284606184862463, "grad_norm": 2.7996411323547363, "learning_rate": 1.8130437767413656e-05, "loss": 1.0003, "step": 13324 }, { "epoch": 0.728515291303605, "grad_norm": 2.655442714691162, "learning_rate": 1.8123616251958625e-05, "loss": 0.8448, "step": 13325 }, { "epoch": 0.7285699641209636, "grad_norm": 2.9348411560058594, "learning_rate": 1.8116795735959506e-05, "loss": 1.1582, "step": 13326 }, { "epoch": 0.7286246369383222, "grad_norm": 3.335094928741455, "learning_rate": 1.810997621963015e-05, "loss": 1.2506, "step": 13327 }, { "epoch": 0.7286793097556808, "grad_norm": 2.5713140964508057, "learning_rate": 1.8103157703184376e-05, "loss": 0.8501, "step": 13328 }, { "epoch": 0.7287339825730395, "grad_norm": 2.7603046894073486, "learning_rate": 1.8096340186835974e-05, "loss": 0.9824, "step": 13329 }, { "epoch": 0.728788655390398, "grad_norm": 2.673360586166382, "learning_rate": 1.8089523670798696e-05, "loss": 1.002, "step": 13330 }, { "epoch": 0.7288433282077567, "grad_norm": 2.7798640727996826, "learning_rate": 1.8082708155286277e-05, "loss": 1.2248, "step": 13331 }, { "epoch": 0.7288980010251154, "grad_norm": 2.861891269683838, "learning_rate": 1.8075893640512388e-05, "loss": 0.9906, "step": 13332 }, { "epoch": 0.728952673842474, "grad_norm": 2.3161606788635254, "learning_rate": 1.806908012669073e-05, "loss": 0.9781, "step": 13333 }, { "epoch": 0.7290073466598326, "grad_norm": 2.4252521991729736, "learning_rate": 1.806226761403491e-05, "loss": 0.9505, "step": 13334 }, { "epoch": 0.7290620194771912, "grad_norm": 2.78179931640625, "learning_rate": 1.805545610275854e-05, "loss": 0.9459, "step": 13335 }, { "epoch": 0.7291166922945498, "grad_norm": 2.4602904319763184, "learning_rate": 1.8048645593075175e-05, "loss": 1.1243, "step": 13336 }, { "epoch": 0.7291713651119084, "grad_norm": 2.5648088455200195, "learning_rate": 1.8041836085198364e-05, "loss": 0.911, "step": 13337 }, { "epoch": 0.729226037929267, "grad_norm": 2.9662537574768066, "learning_rate": 1.8035027579341608e-05, "loss": 1.1062, "step": 13338 }, { "epoch": 0.7292807107466257, "grad_norm": 3.056739330291748, "learning_rate": 1.8028220075718382e-05, "loss": 1.008, "step": 13339 }, { "epoch": 0.7293353835639843, "grad_norm": 2.4202511310577393, "learning_rate": 1.8021413574542135e-05, "loss": 0.9634, "step": 13340 }, { "epoch": 0.7293900563813429, "grad_norm": 2.7389378547668457, "learning_rate": 1.8014608076026273e-05, "loss": 0.8813, "step": 13341 }, { "epoch": 0.7294447291987015, "grad_norm": 2.6643612384796143, "learning_rate": 1.800780358038416e-05, "loss": 1.1675, "step": 13342 }, { "epoch": 0.7294994020160601, "grad_norm": 2.4853949546813965, "learning_rate": 1.8001000087829178e-05, "loss": 1.0706, "step": 13343 }, { "epoch": 0.7295540748334187, "grad_norm": 2.757473945617676, "learning_rate": 1.7994197598574626e-05, "loss": 1.0332, "step": 13344 }, { "epoch": 0.7296087476507774, "grad_norm": 2.6291592121124268, "learning_rate": 1.79873961128338e-05, "loss": 0.8623, "step": 13345 }, { "epoch": 0.729663420468136, "grad_norm": 2.8601534366607666, "learning_rate": 1.7980595630819942e-05, "loss": 0.8774, "step": 13346 }, { "epoch": 0.7297180932854946, "grad_norm": 3.383178234100342, "learning_rate": 1.797379615274628e-05, "loss": 1.007, "step": 13347 }, { "epoch": 0.7297727661028532, "grad_norm": 2.6744322776794434, "learning_rate": 1.7966997678826008e-05, "loss": 1.348, "step": 13348 }, { "epoch": 0.7298274389202118, "grad_norm": 3.054065465927124, "learning_rate": 1.7960200209272288e-05, "loss": 0.9601, "step": 13349 }, { "epoch": 0.7298821117375704, "grad_norm": 2.7055137157440186, "learning_rate": 1.795340374429824e-05, "loss": 1.0079, "step": 13350 }, { "epoch": 0.729936784554929, "grad_norm": 3.4284167289733887, "learning_rate": 1.7946608284116972e-05, "loss": 1.0187, "step": 13351 }, { "epoch": 0.7299914573722878, "grad_norm": 2.347721815109253, "learning_rate": 1.7939813828941522e-05, "loss": 0.8618, "step": 13352 }, { "epoch": 0.7300461301896464, "grad_norm": 2.754229784011841, "learning_rate": 1.7933020378984967e-05, "loss": 0.7991, "step": 13353 }, { "epoch": 0.730100803007005, "grad_norm": 2.4036810398101807, "learning_rate": 1.792622793446028e-05, "loss": 1.0994, "step": 13354 }, { "epoch": 0.7301554758243636, "grad_norm": 2.9665982723236084, "learning_rate": 1.791943649558045e-05, "loss": 1.0868, "step": 13355 }, { "epoch": 0.7302101486417222, "grad_norm": 2.7931716442108154, "learning_rate": 1.791264606255841e-05, "loss": 1.0217, "step": 13356 }, { "epoch": 0.7302648214590808, "grad_norm": 2.287790060043335, "learning_rate": 1.790585663560706e-05, "loss": 0.8395, "step": 13357 }, { "epoch": 0.7303194942764394, "grad_norm": 3.1809210777282715, "learning_rate": 1.789906821493928e-05, "loss": 0.9286, "step": 13358 }, { "epoch": 0.7303741670937981, "grad_norm": 2.626770257949829, "learning_rate": 1.789228080076792e-05, "loss": 1.0876, "step": 13359 }, { "epoch": 0.7304288399111567, "grad_norm": 2.6076295375823975, "learning_rate": 1.788549439330579e-05, "loss": 1.1141, "step": 13360 }, { "epoch": 0.7304835127285153, "grad_norm": 2.158210515975952, "learning_rate": 1.787870899276565e-05, "loss": 0.8984, "step": 13361 }, { "epoch": 0.7305381855458739, "grad_norm": 2.2852649688720703, "learning_rate": 1.7871924599360296e-05, "loss": 0.9364, "step": 13362 }, { "epoch": 0.7305928583632325, "grad_norm": 2.6636812686920166, "learning_rate": 1.7865141213302424e-05, "loss": 1.1202, "step": 13363 }, { "epoch": 0.7306475311805911, "grad_norm": 2.999147415161133, "learning_rate": 1.7858358834804716e-05, "loss": 1.056, "step": 13364 }, { "epoch": 0.7307022039979497, "grad_norm": 3.1896941661834717, "learning_rate": 1.7851577464079832e-05, "loss": 1.2005, "step": 13365 }, { "epoch": 0.7307568768153084, "grad_norm": 2.4280107021331787, "learning_rate": 1.7844797101340398e-05, "loss": 1.0163, "step": 13366 }, { "epoch": 0.730811549632667, "grad_norm": 4.298771381378174, "learning_rate": 1.7838017746799003e-05, "loss": 0.8752, "step": 13367 }, { "epoch": 0.7308662224500256, "grad_norm": 2.8306760787963867, "learning_rate": 1.783123940066821e-05, "loss": 0.8359, "step": 13368 }, { "epoch": 0.7309208952673842, "grad_norm": 2.650146484375, "learning_rate": 1.7824462063160548e-05, "loss": 1.006, "step": 13369 }, { "epoch": 0.7309755680847428, "grad_norm": 2.369266986846924, "learning_rate": 1.7817685734488502e-05, "loss": 1.0387, "step": 13370 }, { "epoch": 0.7310302409021014, "grad_norm": 2.881565809249878, "learning_rate": 1.7810910414864547e-05, "loss": 0.9577, "step": 13371 }, { "epoch": 0.7310849137194602, "grad_norm": 2.733555555343628, "learning_rate": 1.7804136104501124e-05, "loss": 1.0683, "step": 13372 }, { "epoch": 0.7311395865368188, "grad_norm": 3.058502197265625, "learning_rate": 1.7797362803610633e-05, "loss": 0.9222, "step": 13373 }, { "epoch": 0.7311942593541774, "grad_norm": 2.6692895889282227, "learning_rate": 1.7790590512405447e-05, "loss": 1.0795, "step": 13374 }, { "epoch": 0.731248932171536, "grad_norm": 2.5517568588256836, "learning_rate": 1.77838192310979e-05, "loss": 0.9853, "step": 13375 }, { "epoch": 0.7313036049888946, "grad_norm": 5.201426982879639, "learning_rate": 1.7777048959900298e-05, "loss": 1.0329, "step": 13376 }, { "epoch": 0.7313582778062532, "grad_norm": 2.7986574172973633, "learning_rate": 1.777027969902492e-05, "loss": 0.902, "step": 13377 }, { "epoch": 0.7314129506236118, "grad_norm": 2.513498306274414, "learning_rate": 1.776351144868401e-05, "loss": 1.0579, "step": 13378 }, { "epoch": 0.7314676234409705, "grad_norm": 4.028186321258545, "learning_rate": 1.7756744209089777e-05, "loss": 1.1786, "step": 13379 }, { "epoch": 0.7315222962583291, "grad_norm": 2.5825142860412598, "learning_rate": 1.7749977980454407e-05, "loss": 0.9534, "step": 13380 }, { "epoch": 0.7315769690756877, "grad_norm": 3.118117094039917, "learning_rate": 1.7743212762990046e-05, "loss": 0.7885, "step": 13381 }, { "epoch": 0.7316316418930463, "grad_norm": 2.53943133354187, "learning_rate": 1.7736448556908814e-05, "loss": 1.0525, "step": 13382 }, { "epoch": 0.7316863147104049, "grad_norm": 2.6646206378936768, "learning_rate": 1.7729685362422775e-05, "loss": 1.1693, "step": 13383 }, { "epoch": 0.7317409875277635, "grad_norm": 3.351536273956299, "learning_rate": 1.7722923179744022e-05, "loss": 0.9874, "step": 13384 }, { "epoch": 0.7317956603451221, "grad_norm": 2.197678804397583, "learning_rate": 1.7716162009084558e-05, "loss": 0.9728, "step": 13385 }, { "epoch": 0.7318503331624808, "grad_norm": 3.8749794960021973, "learning_rate": 1.7709401850656378e-05, "loss": 1.172, "step": 13386 }, { "epoch": 0.7319050059798394, "grad_norm": 2.3107028007507324, "learning_rate": 1.770264270467143e-05, "loss": 1.0542, "step": 13387 }, { "epoch": 0.731959678797198, "grad_norm": 3.177173614501953, "learning_rate": 1.7695884571341647e-05, "loss": 1.1286, "step": 13388 }, { "epoch": 0.7320143516145566, "grad_norm": 2.5552475452423096, "learning_rate": 1.7689127450878935e-05, "loss": 1.1357, "step": 13389 }, { "epoch": 0.7320690244319152, "grad_norm": 2.6718149185180664, "learning_rate": 1.7682371343495136e-05, "loss": 1.0341, "step": 13390 }, { "epoch": 0.7321236972492738, "grad_norm": 2.9457812309265137, "learning_rate": 1.76756162494021e-05, "loss": 1.2087, "step": 13391 }, { "epoch": 0.7321783700666324, "grad_norm": 2.9211692810058594, "learning_rate": 1.766886216881162e-05, "loss": 1.023, "step": 13392 }, { "epoch": 0.7322330428839912, "grad_norm": 4.186037540435791, "learning_rate": 1.7662109101935458e-05, "loss": 1.1524, "step": 13393 }, { "epoch": 0.7322877157013498, "grad_norm": 2.97879695892334, "learning_rate": 1.7655357048985365e-05, "loss": 0.9126, "step": 13394 }, { "epoch": 0.7323423885187084, "grad_norm": 2.84668231010437, "learning_rate": 1.7648606010173034e-05, "loss": 1.0432, "step": 13395 }, { "epoch": 0.732397061336067, "grad_norm": 2.711557388305664, "learning_rate": 1.7641855985710125e-05, "loss": 1.2023, "step": 13396 }, { "epoch": 0.7324517341534256, "grad_norm": 2.63413143157959, "learning_rate": 1.7635106975808315e-05, "loss": 1.0452, "step": 13397 }, { "epoch": 0.7325064069707842, "grad_norm": 2.5392911434173584, "learning_rate": 1.762835898067919e-05, "loss": 0.9892, "step": 13398 }, { "epoch": 0.7325610797881429, "grad_norm": 2.740419864654541, "learning_rate": 1.7621612000534332e-05, "loss": 1.1165, "step": 13399 }, { "epoch": 0.7326157526055015, "grad_norm": 3.006603956222534, "learning_rate": 1.7614866035585287e-05, "loss": 0.9036, "step": 13400 }, { "epoch": 0.7326704254228601, "grad_norm": 3.689149856567383, "learning_rate": 1.7608121086043568e-05, "loss": 1.1207, "step": 13401 }, { "epoch": 0.7327250982402187, "grad_norm": 2.4583232402801514, "learning_rate": 1.7601377152120657e-05, "loss": 0.9608, "step": 13402 }, { "epoch": 0.7327797710575773, "grad_norm": 2.7097327709198, "learning_rate": 1.7594634234028002e-05, "loss": 0.9009, "step": 13403 }, { "epoch": 0.7328344438749359, "grad_norm": 3.2427682876586914, "learning_rate": 1.7587892331977023e-05, "loss": 0.9941, "step": 13404 }, { "epoch": 0.7328891166922945, "grad_norm": 2.906022548675537, "learning_rate": 1.7581151446179107e-05, "loss": 1.0058, "step": 13405 }, { "epoch": 0.7329437895096532, "grad_norm": 2.360671043395996, "learning_rate": 1.7574411576845608e-05, "loss": 0.9405, "step": 13406 }, { "epoch": 0.7329984623270118, "grad_norm": 2.5986475944519043, "learning_rate": 1.756767272418785e-05, "loss": 0.7813, "step": 13407 }, { "epoch": 0.7330531351443704, "grad_norm": 2.967244863510132, "learning_rate": 1.7560934888417123e-05, "loss": 1.1495, "step": 13408 }, { "epoch": 0.733107807961729, "grad_norm": 2.4784257411956787, "learning_rate": 1.7554198069744666e-05, "loss": 0.9684, "step": 13409 }, { "epoch": 0.7331624807790876, "grad_norm": 2.518152952194214, "learning_rate": 1.7547462268381743e-05, "loss": 1.1864, "step": 13410 }, { "epoch": 0.7332171535964462, "grad_norm": 3.2724578380584717, "learning_rate": 1.7540727484539533e-05, "loss": 1.0582, "step": 13411 }, { "epoch": 0.7332718264138048, "grad_norm": 3.2730844020843506, "learning_rate": 1.753399371842919e-05, "loss": 1.1862, "step": 13412 }, { "epoch": 0.7333264992311636, "grad_norm": 3.4399876594543457, "learning_rate": 1.7527260970261867e-05, "loss": 1.0257, "step": 13413 }, { "epoch": 0.7333811720485222, "grad_norm": 5.190759658813477, "learning_rate": 1.752052924024864e-05, "loss": 1.2615, "step": 13414 }, { "epoch": 0.7334358448658808, "grad_norm": 2.5566954612731934, "learning_rate": 1.7513798528600583e-05, "loss": 1.0893, "step": 13415 }, { "epoch": 0.7334905176832394, "grad_norm": 2.589362621307373, "learning_rate": 1.750706883552874e-05, "loss": 1.0204, "step": 13416 }, { "epoch": 0.733545190500598, "grad_norm": 2.7090673446655273, "learning_rate": 1.750034016124411e-05, "loss": 0.9566, "step": 13417 }, { "epoch": 0.7335998633179566, "grad_norm": 2.362882137298584, "learning_rate": 1.7493612505957656e-05, "loss": 0.9712, "step": 13418 }, { "epoch": 0.7336545361353152, "grad_norm": 2.8067002296447754, "learning_rate": 1.7486885869880332e-05, "loss": 1.0906, "step": 13419 }, { "epoch": 0.7337092089526739, "grad_norm": 2.453381299972534, "learning_rate": 1.748016025322302e-05, "loss": 0.9326, "step": 13420 }, { "epoch": 0.7337638817700325, "grad_norm": 3.2722554206848145, "learning_rate": 1.7473435656196634e-05, "loss": 1.0867, "step": 13421 }, { "epoch": 0.7338185545873911, "grad_norm": 2.3443751335144043, "learning_rate": 1.7466712079012e-05, "loss": 1.0069, "step": 13422 }, { "epoch": 0.7338732274047497, "grad_norm": 2.473886251449585, "learning_rate": 1.745998952187992e-05, "loss": 1.0086, "step": 13423 }, { "epoch": 0.7339279002221083, "grad_norm": 2.4220938682556152, "learning_rate": 1.745326798501119e-05, "loss": 1.1155, "step": 13424 }, { "epoch": 0.7339825730394669, "grad_norm": 2.687345266342163, "learning_rate": 1.7446547468616548e-05, "loss": 1.1803, "step": 13425 }, { "epoch": 0.7340372458568255, "grad_norm": 2.388594150543213, "learning_rate": 1.7439827972906715e-05, "loss": 1.0075, "step": 13426 }, { "epoch": 0.7340919186741842, "grad_norm": 2.1119651794433594, "learning_rate": 1.7433109498092363e-05, "loss": 1.0102, "step": 13427 }, { "epoch": 0.7341465914915428, "grad_norm": 2.43290638923645, "learning_rate": 1.742639204438416e-05, "loss": 0.9879, "step": 13428 }, { "epoch": 0.7342012643089014, "grad_norm": 3.06787109375, "learning_rate": 1.741967561199272e-05, "loss": 1.089, "step": 13429 }, { "epoch": 0.73425593712626, "grad_norm": 2.489150047302246, "learning_rate": 1.741296020112861e-05, "loss": 0.8247, "step": 13430 }, { "epoch": 0.7343106099436186, "grad_norm": 2.474410057067871, "learning_rate": 1.740624581200242e-05, "loss": 1.1083, "step": 13431 }, { "epoch": 0.7343652827609772, "grad_norm": 2.3651175498962402, "learning_rate": 1.7399532444824657e-05, "loss": 1.0768, "step": 13432 }, { "epoch": 0.734419955578336, "grad_norm": 3.2795684337615967, "learning_rate": 1.7392820099805816e-05, "loss": 0.9817, "step": 13433 }, { "epoch": 0.7344746283956946, "grad_norm": 1.9685912132263184, "learning_rate": 1.7386108777156363e-05, "loss": 0.8412, "step": 13434 }, { "epoch": 0.7345293012130532, "grad_norm": 2.5174529552459717, "learning_rate": 1.7379398477086713e-05, "loss": 1.0919, "step": 13435 }, { "epoch": 0.7345839740304118, "grad_norm": 4.550227165222168, "learning_rate": 1.7372689199807263e-05, "loss": 1.3439, "step": 13436 }, { "epoch": 0.7346386468477704, "grad_norm": 2.5740859508514404, "learning_rate": 1.7365980945528383e-05, "loss": 0.8761, "step": 13437 }, { "epoch": 0.734693319665129, "grad_norm": 2.227073907852173, "learning_rate": 1.73592737144604e-05, "loss": 1.0405, "step": 13438 }, { "epoch": 0.7347479924824876, "grad_norm": 2.0031511783599854, "learning_rate": 1.7352567506813616e-05, "loss": 0.8989, "step": 13439 }, { "epoch": 0.7348026652998463, "grad_norm": 2.7261111736297607, "learning_rate": 1.7345862322798278e-05, "loss": 1.1577, "step": 13440 }, { "epoch": 0.7348573381172049, "grad_norm": 2.4604039192199707, "learning_rate": 1.7339158162624658e-05, "loss": 0.9846, "step": 13441 }, { "epoch": 0.7349120109345635, "grad_norm": 2.832409620285034, "learning_rate": 1.7332455026502943e-05, "loss": 1.1664, "step": 13442 }, { "epoch": 0.7349666837519221, "grad_norm": 1.8008326292037964, "learning_rate": 1.73257529146433e-05, "loss": 0.8437, "step": 13443 }, { "epoch": 0.7350213565692807, "grad_norm": 3.1282031536102295, "learning_rate": 1.731905182725587e-05, "loss": 0.8773, "step": 13444 }, { "epoch": 0.7350760293866393, "grad_norm": 2.628647565841675, "learning_rate": 1.731235176455076e-05, "loss": 0.8348, "step": 13445 }, { "epoch": 0.7351307022039979, "grad_norm": 2.6856818199157715, "learning_rate": 1.730565272673804e-05, "loss": 0.9608, "step": 13446 }, { "epoch": 0.7351853750213566, "grad_norm": 2.807981014251709, "learning_rate": 1.7298954714027764e-05, "loss": 1.0507, "step": 13447 }, { "epoch": 0.7352400478387152, "grad_norm": 2.134700059890747, "learning_rate": 1.729225772662993e-05, "loss": 0.9979, "step": 13448 }, { "epoch": 0.7352947206560738, "grad_norm": 2.543099880218506, "learning_rate": 1.728556176475452e-05, "loss": 0.9458, "step": 13449 }, { "epoch": 0.7353493934734324, "grad_norm": 2.865786552429199, "learning_rate": 1.7278866828611467e-05, "loss": 0.9613, "step": 13450 }, { "epoch": 0.735404066290791, "grad_norm": 2.353257179260254, "learning_rate": 1.7272172918410717e-05, "loss": 1.0127, "step": 13451 }, { "epoch": 0.7354587391081496, "grad_norm": 2.4515750408172607, "learning_rate": 1.726548003436213e-05, "loss": 0.9395, "step": 13452 }, { "epoch": 0.7355134119255082, "grad_norm": 2.1536340713500977, "learning_rate": 1.7258788176675554e-05, "loss": 0.759, "step": 13453 }, { "epoch": 0.735568084742867, "grad_norm": 2.5961358547210693, "learning_rate": 1.725209734556082e-05, "loss": 1.0383, "step": 13454 }, { "epoch": 0.7356227575602255, "grad_norm": 2.0199992656707764, "learning_rate": 1.72454075412277e-05, "loss": 0.9349, "step": 13455 }, { "epoch": 0.7356774303775842, "grad_norm": 2.5477824211120605, "learning_rate": 1.7238718763885954e-05, "loss": 1.0139, "step": 13456 }, { "epoch": 0.7357321031949428, "grad_norm": 3.050642251968384, "learning_rate": 1.7232031013745297e-05, "loss": 1.1441, "step": 13457 }, { "epoch": 0.7357867760123014, "grad_norm": 3.472891092300415, "learning_rate": 1.722534429101542e-05, "loss": 1.0932, "step": 13458 }, { "epoch": 0.73584144882966, "grad_norm": 2.8448328971862793, "learning_rate": 1.7218658595905978e-05, "loss": 1.1137, "step": 13459 }, { "epoch": 0.7358961216470187, "grad_norm": 2.470618963241577, "learning_rate": 1.7211973928626584e-05, "loss": 1.0226, "step": 13460 }, { "epoch": 0.7359507944643773, "grad_norm": 2.2175028324127197, "learning_rate": 1.720529028938686e-05, "loss": 0.9584, "step": 13461 }, { "epoch": 0.7360054672817359, "grad_norm": 3.0458779335021973, "learning_rate": 1.7198607678396345e-05, "loss": 0.9928, "step": 13462 }, { "epoch": 0.7360601400990945, "grad_norm": 2.7862939834594727, "learning_rate": 1.7191926095864568e-05, "loss": 1.0457, "step": 13463 }, { "epoch": 0.7361148129164531, "grad_norm": 3.8227531909942627, "learning_rate": 1.7185245542001034e-05, "loss": 0.8144, "step": 13464 }, { "epoch": 0.7361694857338117, "grad_norm": 2.8803415298461914, "learning_rate": 1.717856601701519e-05, "loss": 0.8329, "step": 13465 }, { "epoch": 0.7362241585511703, "grad_norm": 2.0129618644714355, "learning_rate": 1.7171887521116477e-05, "loss": 0.8501, "step": 13466 }, { "epoch": 0.736278831368529, "grad_norm": 2.564380645751953, "learning_rate": 1.7165210054514285e-05, "loss": 1.0003, "step": 13467 }, { "epoch": 0.7363335041858876, "grad_norm": 2.4575252532958984, "learning_rate": 1.7158533617417994e-05, "loss": 1.0599, "step": 13468 }, { "epoch": 0.7363881770032462, "grad_norm": 2.66782808303833, "learning_rate": 1.715185821003691e-05, "loss": 1.0851, "step": 13469 }, { "epoch": 0.7364428498206048, "grad_norm": 2.35630464553833, "learning_rate": 1.7145183832580363e-05, "loss": 0.8916, "step": 13470 }, { "epoch": 0.7364975226379634, "grad_norm": 3.8086323738098145, "learning_rate": 1.7138510485257626e-05, "loss": 0.986, "step": 13471 }, { "epoch": 0.736552195455322, "grad_norm": 2.5560150146484375, "learning_rate": 1.7131838168277913e-05, "loss": 0.9469, "step": 13472 }, { "epoch": 0.7366068682726806, "grad_norm": 2.505723237991333, "learning_rate": 1.712516688185044e-05, "loss": 0.7868, "step": 13473 }, { "epoch": 0.7366615410900393, "grad_norm": 2.7038347721099854, "learning_rate": 1.711849662618438e-05, "loss": 1.0468, "step": 13474 }, { "epoch": 0.7367162139073979, "grad_norm": 2.4715449810028076, "learning_rate": 1.711182740148888e-05, "loss": 0.957, "step": 13475 }, { "epoch": 0.7367708867247565, "grad_norm": 3.085876703262329, "learning_rate": 1.7105159207973027e-05, "loss": 1.1694, "step": 13476 }, { "epoch": 0.7368255595421151, "grad_norm": 3.411160945892334, "learning_rate": 1.709849204584591e-05, "loss": 0.9658, "step": 13477 }, { "epoch": 0.7368802323594738, "grad_norm": 2.3381447792053223, "learning_rate": 1.7091825915316572e-05, "loss": 0.915, "step": 13478 }, { "epoch": 0.7369349051768324, "grad_norm": 2.927572727203369, "learning_rate": 1.7085160816594003e-05, "loss": 0.9754, "step": 13479 }, { "epoch": 0.736989577994191, "grad_norm": 2.6808054447174072, "learning_rate": 1.7078496749887218e-05, "loss": 0.8262, "step": 13480 }, { "epoch": 0.7370442508115497, "grad_norm": 2.6391348838806152, "learning_rate": 1.7071833715405144e-05, "loss": 0.9114, "step": 13481 }, { "epoch": 0.7370989236289083, "grad_norm": 3.0007286071777344, "learning_rate": 1.7065171713356692e-05, "loss": 1.2435, "step": 13482 }, { "epoch": 0.7371535964462669, "grad_norm": 2.2076828479766846, "learning_rate": 1.7058510743950752e-05, "loss": 0.91, "step": 13483 }, { "epoch": 0.7372082692636255, "grad_norm": 2.737650156021118, "learning_rate": 1.7051850807396168e-05, "loss": 0.9875, "step": 13484 }, { "epoch": 0.7372629420809841, "grad_norm": 2.8905320167541504, "learning_rate": 1.7045191903901753e-05, "loss": 1.1779, "step": 13485 }, { "epoch": 0.7373176148983427, "grad_norm": 2.3092544078826904, "learning_rate": 1.7038534033676295e-05, "loss": 1.0648, "step": 13486 }, { "epoch": 0.7373722877157014, "grad_norm": 2.1126270294189453, "learning_rate": 1.7031877196928542e-05, "loss": 0.9315, "step": 13487 }, { "epoch": 0.73742696053306, "grad_norm": 3.1332499980926514, "learning_rate": 1.702522139386722e-05, "loss": 0.9086, "step": 13488 }, { "epoch": 0.7374816333504186, "grad_norm": 2.8474907875061035, "learning_rate": 1.7018566624700992e-05, "loss": 1.0478, "step": 13489 }, { "epoch": 0.7375363061677772, "grad_norm": 1.975326657295227, "learning_rate": 1.7011912889638547e-05, "loss": 0.8998, "step": 13490 }, { "epoch": 0.7375909789851358, "grad_norm": 4.605235576629639, "learning_rate": 1.7005260188888498e-05, "loss": 0.9868, "step": 13491 }, { "epoch": 0.7376456518024944, "grad_norm": 3.2955338954925537, "learning_rate": 1.6998608522659426e-05, "loss": 0.9172, "step": 13492 }, { "epoch": 0.737700324619853, "grad_norm": 2.2604339122772217, "learning_rate": 1.6991957891159893e-05, "loss": 0.8868, "step": 13493 }, { "epoch": 0.7377549974372117, "grad_norm": 2.645458221435547, "learning_rate": 1.6985308294598418e-05, "loss": 0.8826, "step": 13494 }, { "epoch": 0.7378096702545703, "grad_norm": 2.369835376739502, "learning_rate": 1.6978659733183495e-05, "loss": 1.0059, "step": 13495 }, { "epoch": 0.7378643430719289, "grad_norm": 3.2291479110717773, "learning_rate": 1.697201220712359e-05, "loss": 1.049, "step": 13496 }, { "epoch": 0.7379190158892875, "grad_norm": 2.9865975379943848, "learning_rate": 1.6965365716627125e-05, "loss": 0.9994, "step": 13497 }, { "epoch": 0.7379736887066461, "grad_norm": 2.4879465103149414, "learning_rate": 1.6958720261902495e-05, "loss": 1.1546, "step": 13498 }, { "epoch": 0.7380283615240048, "grad_norm": 2.4251723289489746, "learning_rate": 1.6952075843158044e-05, "loss": 0.981, "step": 13499 }, { "epoch": 0.7380830343413634, "grad_norm": 2.1156165599823, "learning_rate": 1.694543246060214e-05, "loss": 0.9057, "step": 13500 }, { "epoch": 0.7381377071587221, "grad_norm": 2.8444643020629883, "learning_rate": 1.693879011444306e-05, "loss": 1.2076, "step": 13501 }, { "epoch": 0.7381923799760807, "grad_norm": 3.3338875770568848, "learning_rate": 1.6932148804889068e-05, "loss": 1.0358, "step": 13502 }, { "epoch": 0.7382470527934393, "grad_norm": 2.1900298595428467, "learning_rate": 1.6925508532148403e-05, "loss": 0.9365, "step": 13503 }, { "epoch": 0.7383017256107979, "grad_norm": 2.3048558235168457, "learning_rate": 1.6918869296429256e-05, "loss": 1.0116, "step": 13504 }, { "epoch": 0.7383563984281565, "grad_norm": 3.111403465270996, "learning_rate": 1.6912231097939806e-05, "loss": 1.0414, "step": 13505 }, { "epoch": 0.7384110712455151, "grad_norm": 2.3422482013702393, "learning_rate": 1.6905593936888175e-05, "loss": 0.9855, "step": 13506 }, { "epoch": 0.7384657440628737, "grad_norm": 2.666698932647705, "learning_rate": 1.6898957813482475e-05, "loss": 1.0073, "step": 13507 }, { "epoch": 0.7385204168802324, "grad_norm": 2.7504305839538574, "learning_rate": 1.689232272793077e-05, "loss": 1.0637, "step": 13508 }, { "epoch": 0.738575089697591, "grad_norm": 2.868896484375, "learning_rate": 1.688568868044108e-05, "loss": 1.1133, "step": 13509 }, { "epoch": 0.7386297625149496, "grad_norm": 2.5644655227661133, "learning_rate": 1.687905567122145e-05, "loss": 1.1489, "step": 13510 }, { "epoch": 0.7386844353323082, "grad_norm": 2.6957552433013916, "learning_rate": 1.687242370047983e-05, "loss": 0.8793, "step": 13511 }, { "epoch": 0.7387391081496668, "grad_norm": 2.3032736778259277, "learning_rate": 1.686579276842416e-05, "loss": 1.0306, "step": 13512 }, { "epoch": 0.7387937809670254, "grad_norm": 2.4544272422790527, "learning_rate": 1.6859162875262345e-05, "loss": 0.9654, "step": 13513 }, { "epoch": 0.7388484537843841, "grad_norm": 2.283972978591919, "learning_rate": 1.6852534021202266e-05, "loss": 1.0073, "step": 13514 }, { "epoch": 0.7389031266017427, "grad_norm": 2.359825611114502, "learning_rate": 1.6845906206451755e-05, "loss": 0.9909, "step": 13515 }, { "epoch": 0.7389577994191013, "grad_norm": 2.958374261856079, "learning_rate": 1.6839279431218635e-05, "loss": 1.025, "step": 13516 }, { "epoch": 0.7390124722364599, "grad_norm": 2.91914701461792, "learning_rate": 1.683265369571067e-05, "loss": 1.0406, "step": 13517 }, { "epoch": 0.7390671450538185, "grad_norm": 3.3668336868286133, "learning_rate": 1.6826029000135597e-05, "loss": 0.9162, "step": 13518 }, { "epoch": 0.7391218178711771, "grad_norm": 2.8264718055725098, "learning_rate": 1.681940534470115e-05, "loss": 1.1302, "step": 13519 }, { "epoch": 0.7391764906885357, "grad_norm": 2.821486711502075, "learning_rate": 1.6812782729615e-05, "loss": 1.1219, "step": 13520 }, { "epoch": 0.7392311635058945, "grad_norm": 2.5906906127929688, "learning_rate": 1.6806161155084792e-05, "loss": 1.0459, "step": 13521 }, { "epoch": 0.7392858363232531, "grad_norm": 2.3464813232421875, "learning_rate": 1.679954062131814e-05, "loss": 0.8695, "step": 13522 }, { "epoch": 0.7393405091406117, "grad_norm": 3.915419101715088, "learning_rate": 1.679292112852262e-05, "loss": 1.1476, "step": 13523 }, { "epoch": 0.7393951819579703, "grad_norm": 2.4175939559936523, "learning_rate": 1.6786302676905785e-05, "loss": 0.9375, "step": 13524 }, { "epoch": 0.7394498547753289, "grad_norm": 5.308860778808594, "learning_rate": 1.677968526667515e-05, "loss": 1.0772, "step": 13525 }, { "epoch": 0.7395045275926875, "grad_norm": 3.430893898010254, "learning_rate": 1.6773068898038198e-05, "loss": 1.0259, "step": 13526 }, { "epoch": 0.7395592004100461, "grad_norm": 3.303941249847412, "learning_rate": 1.6766453571202378e-05, "loss": 1.0315, "step": 13527 }, { "epoch": 0.7396138732274048, "grad_norm": 2.6569619178771973, "learning_rate": 1.675983928637509e-05, "loss": 1.0697, "step": 13528 }, { "epoch": 0.7396685460447634, "grad_norm": 2.375483274459839, "learning_rate": 1.6753226043763755e-05, "loss": 1.0388, "step": 13529 }, { "epoch": 0.739723218862122, "grad_norm": 2.9303476810455322, "learning_rate": 1.674661384357571e-05, "loss": 1.0769, "step": 13530 }, { "epoch": 0.7397778916794806, "grad_norm": 2.4599878787994385, "learning_rate": 1.674000268601827e-05, "loss": 0.9407, "step": 13531 }, { "epoch": 0.7398325644968392, "grad_norm": 2.776750087738037, "learning_rate": 1.6733392571298728e-05, "loss": 0.9317, "step": 13532 }, { "epoch": 0.7398872373141978, "grad_norm": 2.2558324337005615, "learning_rate": 1.6726783499624333e-05, "loss": 0.8849, "step": 13533 }, { "epoch": 0.7399419101315564, "grad_norm": 3.104018211364746, "learning_rate": 1.672017547120231e-05, "loss": 1.1298, "step": 13534 }, { "epoch": 0.7399965829489151, "grad_norm": 3.308168649673462, "learning_rate": 1.6713568486239844e-05, "loss": 1.1887, "step": 13535 }, { "epoch": 0.7400512557662737, "grad_norm": 2.5340161323547363, "learning_rate": 1.67069625449441e-05, "loss": 0.9861, "step": 13536 }, { "epoch": 0.7401059285836323, "grad_norm": 3.752514123916626, "learning_rate": 1.6700357647522193e-05, "loss": 1.0572, "step": 13537 }, { "epoch": 0.7401606014009909, "grad_norm": 2.8956522941589355, "learning_rate": 1.6693753794181192e-05, "loss": 1.169, "step": 13538 }, { "epoch": 0.7402152742183495, "grad_norm": 2.470950126647949, "learning_rate": 1.6687150985128203e-05, "loss": 1.1036, "step": 13539 }, { "epoch": 0.7402699470357081, "grad_norm": 2.6959574222564697, "learning_rate": 1.6680549220570223e-05, "loss": 1.0799, "step": 13540 }, { "epoch": 0.7403246198530669, "grad_norm": 4.200050354003906, "learning_rate": 1.6673948500714254e-05, "loss": 1.0609, "step": 13541 }, { "epoch": 0.7403792926704255, "grad_norm": 2.4017691612243652, "learning_rate": 1.6667348825767247e-05, "loss": 0.9346, "step": 13542 }, { "epoch": 0.7404339654877841, "grad_norm": 2.7933242321014404, "learning_rate": 1.6660750195936137e-05, "loss": 1.1185, "step": 13543 }, { "epoch": 0.7404886383051427, "grad_norm": 2.60417103767395, "learning_rate": 1.6654152611427808e-05, "loss": 0.9748, "step": 13544 }, { "epoch": 0.7405433111225013, "grad_norm": 3.382577419281006, "learning_rate": 1.6647556072449126e-05, "loss": 1.1614, "step": 13545 }, { "epoch": 0.7405979839398599, "grad_norm": 3.669703960418701, "learning_rate": 1.6640960579206926e-05, "loss": 1.0159, "step": 13546 }, { "epoch": 0.7406526567572185, "grad_norm": 3.8323235511779785, "learning_rate": 1.6634366131907995e-05, "loss": 0.9637, "step": 13547 }, { "epoch": 0.7407073295745772, "grad_norm": 2.44990873336792, "learning_rate": 1.6627772730759088e-05, "loss": 0.9727, "step": 13548 }, { "epoch": 0.7407620023919358, "grad_norm": 2.8017003536224365, "learning_rate": 1.662118037596696e-05, "loss": 0.7467, "step": 13549 }, { "epoch": 0.7408166752092944, "grad_norm": 2.8464958667755127, "learning_rate": 1.66145890677383e-05, "loss": 1.1778, "step": 13550 }, { "epoch": 0.740871348026653, "grad_norm": 2.4384028911590576, "learning_rate": 1.660799880627976e-05, "loss": 1.0828, "step": 13551 }, { "epoch": 0.7409260208440116, "grad_norm": 3.349210739135742, "learning_rate": 1.660140959179799e-05, "loss": 1.0115, "step": 13552 }, { "epoch": 0.7409806936613702, "grad_norm": 2.7372825145721436, "learning_rate": 1.6594821424499574e-05, "loss": 0.9634, "step": 13553 }, { "epoch": 0.7410353664787288, "grad_norm": 2.9902446269989014, "learning_rate": 1.6588234304591084e-05, "loss": 1.1753, "step": 13554 }, { "epoch": 0.7410900392960875, "grad_norm": 2.9967691898345947, "learning_rate": 1.6581648232279052e-05, "loss": 0.9331, "step": 13555 }, { "epoch": 0.7411447121134461, "grad_norm": 2.365565061569214, "learning_rate": 1.657506320776998e-05, "loss": 0.9793, "step": 13556 }, { "epoch": 0.7411993849308047, "grad_norm": 11.725977897644043, "learning_rate": 1.6568479231270334e-05, "loss": 0.9243, "step": 13557 }, { "epoch": 0.7412540577481633, "grad_norm": 2.593470335006714, "learning_rate": 1.656189630298653e-05, "loss": 1.0552, "step": 13558 }, { "epoch": 0.7413087305655219, "grad_norm": 2.885096311569214, "learning_rate": 1.655531442312501e-05, "loss": 0.9349, "step": 13559 }, { "epoch": 0.7413634033828805, "grad_norm": 2.2273921966552734, "learning_rate": 1.6548733591892122e-05, "loss": 0.8767, "step": 13560 }, { "epoch": 0.7414180762002391, "grad_norm": 2.5620856285095215, "learning_rate": 1.65421538094942e-05, "loss": 1.1093, "step": 13561 }, { "epoch": 0.7414727490175979, "grad_norm": 3.4551751613616943, "learning_rate": 1.6535575076137555e-05, "loss": 1.1089, "step": 13562 }, { "epoch": 0.7415274218349565, "grad_norm": 2.9279263019561768, "learning_rate": 1.6528997392028446e-05, "loss": 0.9668, "step": 13563 }, { "epoch": 0.7415820946523151, "grad_norm": 2.315009832382202, "learning_rate": 1.6522420757373118e-05, "loss": 0.9517, "step": 13564 }, { "epoch": 0.7416367674696737, "grad_norm": 3.0003020763397217, "learning_rate": 1.651584517237778e-05, "loss": 0.907, "step": 13565 }, { "epoch": 0.7416914402870323, "grad_norm": 2.1818809509277344, "learning_rate": 1.650927063724859e-05, "loss": 0.9724, "step": 13566 }, { "epoch": 0.7417461131043909, "grad_norm": 2.334299087524414, "learning_rate": 1.6502697152191704e-05, "loss": 0.9428, "step": 13567 }, { "epoch": 0.7418007859217496, "grad_norm": 2.5200281143188477, "learning_rate": 1.6496124717413215e-05, "loss": 0.966, "step": 13568 }, { "epoch": 0.7418554587391082, "grad_norm": 2.4079132080078125, "learning_rate": 1.6489553333119197e-05, "loss": 1.0886, "step": 13569 }, { "epoch": 0.7419101315564668, "grad_norm": 2.7993693351745605, "learning_rate": 1.6482982999515678e-05, "loss": 1.0371, "step": 13570 }, { "epoch": 0.7419648043738254, "grad_norm": 2.743403434753418, "learning_rate": 1.6476413716808692e-05, "loss": 1.15, "step": 13571 }, { "epoch": 0.742019477191184, "grad_norm": 2.221224308013916, "learning_rate": 1.6469845485204205e-05, "loss": 0.9017, "step": 13572 }, { "epoch": 0.7420741500085426, "grad_norm": 2.147552967071533, "learning_rate": 1.6463278304908153e-05, "loss": 0.9629, "step": 13573 }, { "epoch": 0.7421288228259012, "grad_norm": 2.2423901557922363, "learning_rate": 1.6456712176126445e-05, "loss": 0.9472, "step": 13574 }, { "epoch": 0.7421834956432599, "grad_norm": 2.247671365737915, "learning_rate": 1.6450147099064954e-05, "loss": 0.9732, "step": 13575 }, { "epoch": 0.7422381684606185, "grad_norm": 2.185407876968384, "learning_rate": 1.6443583073929523e-05, "loss": 1.0194, "step": 13576 }, { "epoch": 0.7422928412779771, "grad_norm": 2.9383466243743896, "learning_rate": 1.6437020100925965e-05, "loss": 1.2062, "step": 13577 }, { "epoch": 0.7423475140953357, "grad_norm": 2.531588315963745, "learning_rate": 1.6430458180260056e-05, "loss": 1.0723, "step": 13578 }, { "epoch": 0.7424021869126943, "grad_norm": 2.476625919342041, "learning_rate": 1.642389731213754e-05, "loss": 0.9871, "step": 13579 }, { "epoch": 0.7424568597300529, "grad_norm": 2.487555503845215, "learning_rate": 1.6417337496764113e-05, "loss": 0.9172, "step": 13580 }, { "epoch": 0.7425115325474115, "grad_norm": 3.0444176197052, "learning_rate": 1.641077873434547e-05, "loss": 0.9704, "step": 13581 }, { "epoch": 0.7425662053647702, "grad_norm": 2.3953452110290527, "learning_rate": 1.6404221025087248e-05, "loss": 1.1311, "step": 13582 }, { "epoch": 0.7426208781821289, "grad_norm": 2.322822332382202, "learning_rate": 1.6397664369195043e-05, "loss": 0.9259, "step": 13583 }, { "epoch": 0.7426755509994875, "grad_norm": 2.1678712368011475, "learning_rate": 1.6391108766874464e-05, "loss": 0.8901, "step": 13584 }, { "epoch": 0.7427302238168461, "grad_norm": 2.190922260284424, "learning_rate": 1.638455421833104e-05, "loss": 0.9992, "step": 13585 }, { "epoch": 0.7427848966342047, "grad_norm": 2.108095407485962, "learning_rate": 1.6378000723770288e-05, "loss": 0.9527, "step": 13586 }, { "epoch": 0.7428395694515633, "grad_norm": 2.303877592086792, "learning_rate": 1.6371448283397676e-05, "loss": 1.0786, "step": 13587 }, { "epoch": 0.7428942422689219, "grad_norm": 2.8591244220733643, "learning_rate": 1.6364896897418664e-05, "loss": 1.0572, "step": 13588 }, { "epoch": 0.7429489150862806, "grad_norm": 2.811589002609253, "learning_rate": 1.6358346566038655e-05, "loss": 1.0973, "step": 13589 }, { "epoch": 0.7430035879036392, "grad_norm": 2.815425395965576, "learning_rate": 1.6351797289463034e-05, "loss": 1.0125, "step": 13590 }, { "epoch": 0.7430582607209978, "grad_norm": 2.6956348419189453, "learning_rate": 1.6345249067897146e-05, "loss": 1.0591, "step": 13591 }, { "epoch": 0.7431129335383564, "grad_norm": 2.2065372467041016, "learning_rate": 1.6338701901546307e-05, "loss": 0.9464, "step": 13592 }, { "epoch": 0.743167606355715, "grad_norm": 2.510150671005249, "learning_rate": 1.633215579061579e-05, "loss": 1.0584, "step": 13593 }, { "epoch": 0.7432222791730736, "grad_norm": 2.497263193130493, "learning_rate": 1.632561073531085e-05, "loss": 0.9523, "step": 13594 }, { "epoch": 0.7432769519904323, "grad_norm": 3.269714117050171, "learning_rate": 1.6319066735836696e-05, "loss": 1.2194, "step": 13595 }, { "epoch": 0.7433316248077909, "grad_norm": 2.2402267456054688, "learning_rate": 1.63125237923985e-05, "loss": 1.0155, "step": 13596 }, { "epoch": 0.7433862976251495, "grad_norm": 2.484062910079956, "learning_rate": 1.6305981905201435e-05, "loss": 1.0184, "step": 13597 }, { "epoch": 0.7434409704425081, "grad_norm": 3.439157009124756, "learning_rate": 1.6299441074450605e-05, "loss": 0.9046, "step": 13598 }, { "epoch": 0.7434956432598667, "grad_norm": 2.0614326000213623, "learning_rate": 1.6292901300351094e-05, "loss": 0.905, "step": 13599 }, { "epoch": 0.7435503160772253, "grad_norm": 2.3215107917785645, "learning_rate": 1.6286362583107943e-05, "loss": 0.9111, "step": 13600 }, { "epoch": 0.7436049888945839, "grad_norm": 3.900709629058838, "learning_rate": 1.6279824922926173e-05, "loss": 1.1538, "step": 13601 }, { "epoch": 0.7436596617119426, "grad_norm": 2.332212209701538, "learning_rate": 1.627328832001077e-05, "loss": 0.9708, "step": 13602 }, { "epoch": 0.7437143345293012, "grad_norm": 2.5085246562957764, "learning_rate": 1.626675277456668e-05, "loss": 0.9965, "step": 13603 }, { "epoch": 0.7437690073466598, "grad_norm": 2.5813589096069336, "learning_rate": 1.6260218286798813e-05, "loss": 0.8077, "step": 13604 }, { "epoch": 0.7438236801640185, "grad_norm": 2.5683233737945557, "learning_rate": 1.625368485691206e-05, "loss": 1.0556, "step": 13605 }, { "epoch": 0.7438783529813771, "grad_norm": 2.9296767711639404, "learning_rate": 1.6247152485111267e-05, "loss": 1.0801, "step": 13606 }, { "epoch": 0.7439330257987357, "grad_norm": 2.407926082611084, "learning_rate": 1.624062117160124e-05, "loss": 1.0285, "step": 13607 }, { "epoch": 0.7439876986160943, "grad_norm": 2.652005434036255, "learning_rate": 1.623409091658679e-05, "loss": 1.1079, "step": 13608 }, { "epoch": 0.744042371433453, "grad_norm": 2.1531574726104736, "learning_rate": 1.622756172027265e-05, "loss": 0.8196, "step": 13609 }, { "epoch": 0.7440970442508116, "grad_norm": 2.6320996284484863, "learning_rate": 1.6221033582863544e-05, "loss": 0.9329, "step": 13610 }, { "epoch": 0.7441517170681702, "grad_norm": 2.6350317001342773, "learning_rate": 1.621450650456415e-05, "loss": 0.9699, "step": 13611 }, { "epoch": 0.7442063898855288, "grad_norm": 2.406200647354126, "learning_rate": 1.6207980485579116e-05, "loss": 1.0809, "step": 13612 }, { "epoch": 0.7442610627028874, "grad_norm": 2.2670552730560303, "learning_rate": 1.620145552611307e-05, "loss": 1.0608, "step": 13613 }, { "epoch": 0.744315735520246, "grad_norm": 2.3390543460845947, "learning_rate": 1.6194931626370586e-05, "loss": 1.0504, "step": 13614 }, { "epoch": 0.7443704083376046, "grad_norm": 2.8658833503723145, "learning_rate": 1.618840878655622e-05, "loss": 1.1071, "step": 13615 }, { "epoch": 0.7444250811549633, "grad_norm": 2.333585739135742, "learning_rate": 1.6181887006874485e-05, "loss": 1.0418, "step": 13616 }, { "epoch": 0.7444797539723219, "grad_norm": 3.087285280227661, "learning_rate": 1.617536628752986e-05, "loss": 1.1465, "step": 13617 }, { "epoch": 0.7445344267896805, "grad_norm": 2.9812681674957275, "learning_rate": 1.616884662872682e-05, "loss": 1.1186, "step": 13618 }, { "epoch": 0.7445890996070391, "grad_norm": 2.478816032409668, "learning_rate": 1.616232803066977e-05, "loss": 0.9464, "step": 13619 }, { "epoch": 0.7446437724243977, "grad_norm": 2.3934006690979004, "learning_rate": 1.6155810493563096e-05, "loss": 1.0309, "step": 13620 }, { "epoch": 0.7446984452417563, "grad_norm": 2.5535497665405273, "learning_rate": 1.6149294017611148e-05, "loss": 1.0802, "step": 13621 }, { "epoch": 0.744753118059115, "grad_norm": 2.644432783126831, "learning_rate": 1.6142778603018243e-05, "loss": 1.0965, "step": 13622 }, { "epoch": 0.7448077908764736, "grad_norm": 2.8627312183380127, "learning_rate": 1.613626424998867e-05, "loss": 0.9603, "step": 13623 }, { "epoch": 0.7448624636938322, "grad_norm": 2.5009968280792236, "learning_rate": 1.6129750958726675e-05, "loss": 1.0883, "step": 13624 }, { "epoch": 0.7449171365111908, "grad_norm": 3.0906999111175537, "learning_rate": 1.612323872943648e-05, "loss": 1.0165, "step": 13625 }, { "epoch": 0.7449718093285495, "grad_norm": 2.953054189682007, "learning_rate": 1.6116727562322255e-05, "loss": 0.9285, "step": 13626 }, { "epoch": 0.745026482145908, "grad_norm": 2.359240770339966, "learning_rate": 1.6110217457588178e-05, "loss": 0.9402, "step": 13627 }, { "epoch": 0.7450811549632667, "grad_norm": 2.5462045669555664, "learning_rate": 1.6103708415438363e-05, "loss": 1.0041, "step": 13628 }, { "epoch": 0.7451358277806254, "grad_norm": 2.522488832473755, "learning_rate": 1.6097200436076887e-05, "loss": 1.1118, "step": 13629 }, { "epoch": 0.745190500597984, "grad_norm": 2.438720226287842, "learning_rate": 1.60906935197078e-05, "loss": 0.996, "step": 13630 }, { "epoch": 0.7452451734153426, "grad_norm": 3.1414928436279297, "learning_rate": 1.6084187666535127e-05, "loss": 1.0256, "step": 13631 }, { "epoch": 0.7452998462327012, "grad_norm": 2.4603030681610107, "learning_rate": 1.6077682876762856e-05, "loss": 1.0423, "step": 13632 }, { "epoch": 0.7453545190500598, "grad_norm": 2.3587136268615723, "learning_rate": 1.607117915059493e-05, "loss": 1.244, "step": 13633 }, { "epoch": 0.7454091918674184, "grad_norm": 2.5863101482391357, "learning_rate": 1.606467648823527e-05, "loss": 0.8223, "step": 13634 }, { "epoch": 0.745463864684777, "grad_norm": 2.800921678543091, "learning_rate": 1.6058174889887763e-05, "loss": 0.9756, "step": 13635 }, { "epoch": 0.7455185375021357, "grad_norm": 2.514113187789917, "learning_rate": 1.605167435575624e-05, "loss": 1.0469, "step": 13636 }, { "epoch": 0.7455732103194943, "grad_norm": 3.1971139907836914, "learning_rate": 1.6045174886044556e-05, "loss": 0.9536, "step": 13637 }, { "epoch": 0.7456278831368529, "grad_norm": 3.243492841720581, "learning_rate": 1.603867648095649e-05, "loss": 0.945, "step": 13638 }, { "epoch": 0.7456825559542115, "grad_norm": 1.9049705266952515, "learning_rate": 1.6032179140695775e-05, "loss": 0.8371, "step": 13639 }, { "epoch": 0.7457372287715701, "grad_norm": 2.648012399673462, "learning_rate": 1.6025682865466135e-05, "loss": 0.9778, "step": 13640 }, { "epoch": 0.7457919015889287, "grad_norm": 2.2134783267974854, "learning_rate": 1.6019187655471268e-05, "loss": 1.0042, "step": 13641 }, { "epoch": 0.7458465744062873, "grad_norm": 3.2746517658233643, "learning_rate": 1.6012693510914804e-05, "loss": 1.0251, "step": 13642 }, { "epoch": 0.745901247223646, "grad_norm": 3.102330446243286, "learning_rate": 1.6006200432000385e-05, "loss": 0.9305, "step": 13643 }, { "epoch": 0.7459559200410046, "grad_norm": 2.689472198486328, "learning_rate": 1.5999708418931576e-05, "loss": 1.0992, "step": 13644 }, { "epoch": 0.7460105928583632, "grad_norm": 2.97218918800354, "learning_rate": 1.5993217471911936e-05, "loss": 0.9793, "step": 13645 }, { "epoch": 0.7460652656757218, "grad_norm": 2.8465566635131836, "learning_rate": 1.5986727591144973e-05, "loss": 1.0551, "step": 13646 }, { "epoch": 0.7461199384930804, "grad_norm": 2.7044801712036133, "learning_rate": 1.5980238776834194e-05, "loss": 1.0792, "step": 13647 }, { "epoch": 0.746174611310439, "grad_norm": 2.679145336151123, "learning_rate": 1.597375102918303e-05, "loss": 1.0884, "step": 13648 }, { "epoch": 0.7462292841277978, "grad_norm": 3.394447088241577, "learning_rate": 1.5967264348394918e-05, "loss": 0.9936, "step": 13649 }, { "epoch": 0.7462839569451564, "grad_norm": 2.5425004959106445, "learning_rate": 1.5960778734673225e-05, "loss": 1.0213, "step": 13650 }, { "epoch": 0.746338629762515, "grad_norm": 3.767387866973877, "learning_rate": 1.595429418822131e-05, "loss": 1.1005, "step": 13651 }, { "epoch": 0.7463933025798736, "grad_norm": 2.5625011920928955, "learning_rate": 1.5947810709242477e-05, "loss": 0.9262, "step": 13652 }, { "epoch": 0.7464479753972322, "grad_norm": 2.6253843307495117, "learning_rate": 1.5941328297940027e-05, "loss": 0.841, "step": 13653 }, { "epoch": 0.7465026482145908, "grad_norm": 3.3909876346588135, "learning_rate": 1.59348469545172e-05, "loss": 1.2061, "step": 13654 }, { "epoch": 0.7465573210319494, "grad_norm": 2.7748467922210693, "learning_rate": 1.5928366679177226e-05, "loss": 1.1454, "step": 13655 }, { "epoch": 0.7466119938493081, "grad_norm": 2.7177469730377197, "learning_rate": 1.5921887472123255e-05, "loss": 1.1093, "step": 13656 }, { "epoch": 0.7466666666666667, "grad_norm": 2.765305757522583, "learning_rate": 1.5915409333558473e-05, "loss": 0.7219, "step": 13657 }, { "epoch": 0.7467213394840253, "grad_norm": 2.2002971172332764, "learning_rate": 1.590893226368599e-05, "loss": 0.9018, "step": 13658 }, { "epoch": 0.7467760123013839, "grad_norm": 2.4290997982025146, "learning_rate": 1.5902456262708877e-05, "loss": 1.0495, "step": 13659 }, { "epoch": 0.7468306851187425, "grad_norm": 2.864657402038574, "learning_rate": 1.589598133083019e-05, "loss": 1.0688, "step": 13660 }, { "epoch": 0.7468853579361011, "grad_norm": 2.389864683151245, "learning_rate": 1.5889507468252946e-05, "loss": 0.9348, "step": 13661 }, { "epoch": 0.7469400307534597, "grad_norm": 4.438469886779785, "learning_rate": 1.588303467518012e-05, "loss": 0.8765, "step": 13662 }, { "epoch": 0.7469947035708184, "grad_norm": 2.647409200668335, "learning_rate": 1.5876562951814666e-05, "loss": 0.9822, "step": 13663 }, { "epoch": 0.747049376388177, "grad_norm": 2.3797171115875244, "learning_rate": 1.5870092298359502e-05, "loss": 1.1102, "step": 13664 }, { "epoch": 0.7471040492055356, "grad_norm": 2.9651267528533936, "learning_rate": 1.58636227150175e-05, "loss": 1.027, "step": 13665 }, { "epoch": 0.7471587220228942, "grad_norm": 3.1770827770233154, "learning_rate": 1.5857154201991502e-05, "loss": 0.9833, "step": 13666 }, { "epoch": 0.7472133948402528, "grad_norm": 3.299187421798706, "learning_rate": 1.5850686759484356e-05, "loss": 1.0785, "step": 13667 }, { "epoch": 0.7472680676576114, "grad_norm": 2.5221095085144043, "learning_rate": 1.5844220387698816e-05, "loss": 0.816, "step": 13668 }, { "epoch": 0.74732274047497, "grad_norm": 3.3017706871032715, "learning_rate": 1.5837755086837634e-05, "loss": 0.9811, "step": 13669 }, { "epoch": 0.7473774132923288, "grad_norm": 2.671339511871338, "learning_rate": 1.5831290857103527e-05, "loss": 1.0746, "step": 13670 }, { "epoch": 0.7474320861096874, "grad_norm": 2.287787914276123, "learning_rate": 1.5824827698699174e-05, "loss": 0.9433, "step": 13671 }, { "epoch": 0.747486758927046, "grad_norm": 2.9895784854888916, "learning_rate": 1.5818365611827217e-05, "loss": 1.0403, "step": 13672 }, { "epoch": 0.7475414317444046, "grad_norm": 2.356179714202881, "learning_rate": 1.581190459669028e-05, "loss": 0.8803, "step": 13673 }, { "epoch": 0.7475961045617632, "grad_norm": 2.876831531524658, "learning_rate": 1.580544465349093e-05, "loss": 0.9572, "step": 13674 }, { "epoch": 0.7476507773791218, "grad_norm": 2.067479133605957, "learning_rate": 1.57989857824317e-05, "loss": 0.9046, "step": 13675 }, { "epoch": 0.7477054501964805, "grad_norm": 2.634136438369751, "learning_rate": 1.579252798371514e-05, "loss": 1.0187, "step": 13676 }, { "epoch": 0.7477601230138391, "grad_norm": 2.2361278533935547, "learning_rate": 1.578607125754371e-05, "loss": 1.0699, "step": 13677 }, { "epoch": 0.7478147958311977, "grad_norm": 2.6253905296325684, "learning_rate": 1.577961560411985e-05, "loss": 1.0649, "step": 13678 }, { "epoch": 0.7478694686485563, "grad_norm": 3.0251200199127197, "learning_rate": 1.577316102364598e-05, "loss": 1.1716, "step": 13679 }, { "epoch": 0.7479241414659149, "grad_norm": 3.087291717529297, "learning_rate": 1.576670751632447e-05, "loss": 1.154, "step": 13680 }, { "epoch": 0.7479788142832735, "grad_norm": 2.0995359420776367, "learning_rate": 1.576025508235766e-05, "loss": 0.8807, "step": 13681 }, { "epoch": 0.7480334871006321, "grad_norm": 2.310990333557129, "learning_rate": 1.5753803721947875e-05, "loss": 1.064, "step": 13682 }, { "epoch": 0.7480881599179908, "grad_norm": 2.931558609008789, "learning_rate": 1.5747353435297386e-05, "loss": 1.0329, "step": 13683 }, { "epoch": 0.7481428327353494, "grad_norm": 4.1635355949401855, "learning_rate": 1.5740904222608425e-05, "loss": 1.0282, "step": 13684 }, { "epoch": 0.748197505552708, "grad_norm": 2.515841245651245, "learning_rate": 1.5734456084083205e-05, "loss": 1.0777, "step": 13685 }, { "epoch": 0.7482521783700666, "grad_norm": 2.9964826107025146, "learning_rate": 1.5728009019923916e-05, "loss": 1.0855, "step": 13686 }, { "epoch": 0.7483068511874252, "grad_norm": 2.456324815750122, "learning_rate": 1.572156303033269e-05, "loss": 1.0418, "step": 13687 }, { "epoch": 0.7483615240047838, "grad_norm": 2.637317180633545, "learning_rate": 1.571511811551164e-05, "loss": 1.1332, "step": 13688 }, { "epoch": 0.7484161968221424, "grad_norm": 3.0629265308380127, "learning_rate": 1.5708674275662837e-05, "loss": 1.1023, "step": 13689 }, { "epoch": 0.7484708696395012, "grad_norm": 3.038931131362915, "learning_rate": 1.5702231510988324e-05, "loss": 1.2645, "step": 13690 }, { "epoch": 0.7485255424568598, "grad_norm": 2.28017520904541, "learning_rate": 1.5695789821690104e-05, "loss": 0.9232, "step": 13691 }, { "epoch": 0.7485802152742184, "grad_norm": 3.161076068878174, "learning_rate": 1.568934920797015e-05, "loss": 1.0994, "step": 13692 }, { "epoch": 0.748634888091577, "grad_norm": 2.548067092895508, "learning_rate": 1.5682909670030403e-05, "loss": 0.9355, "step": 13693 }, { "epoch": 0.7486895609089356, "grad_norm": 2.5336945056915283, "learning_rate": 1.5676471208072778e-05, "loss": 1.199, "step": 13694 }, { "epoch": 0.7487442337262942, "grad_norm": 2.429910659790039, "learning_rate": 1.567003382229912e-05, "loss": 1.014, "step": 13695 }, { "epoch": 0.7487989065436528, "grad_norm": 2.7263107299804688, "learning_rate": 1.5663597512911303e-05, "loss": 0.9583, "step": 13696 }, { "epoch": 0.7488535793610115, "grad_norm": 2.653622627258301, "learning_rate": 1.5657162280111115e-05, "loss": 1.0304, "step": 13697 }, { "epoch": 0.7489082521783701, "grad_norm": 2.6253695487976074, "learning_rate": 1.5650728124100328e-05, "loss": 1.1366, "step": 13698 }, { "epoch": 0.7489629249957287, "grad_norm": 2.3037378787994385, "learning_rate": 1.564429504508068e-05, "loss": 0.8488, "step": 13699 }, { "epoch": 0.7490175978130873, "grad_norm": 2.727385997772217, "learning_rate": 1.5637863043253877e-05, "loss": 1.031, "step": 13700 }, { "epoch": 0.7490722706304459, "grad_norm": 2.4166977405548096, "learning_rate": 1.563143211882158e-05, "loss": 1.2168, "step": 13701 }, { "epoch": 0.7491269434478045, "grad_norm": 2.37668776512146, "learning_rate": 1.5625002271985433e-05, "loss": 1.0296, "step": 13702 }, { "epoch": 0.7491816162651632, "grad_norm": 2.5500338077545166, "learning_rate": 1.561857350294704e-05, "loss": 0.869, "step": 13703 }, { "epoch": 0.7492362890825218, "grad_norm": 2.7659201622009277, "learning_rate": 1.5612145811907964e-05, "loss": 0.9245, "step": 13704 }, { "epoch": 0.7492909618998804, "grad_norm": 2.3526370525360107, "learning_rate": 1.5605719199069718e-05, "loss": 1.1586, "step": 13705 }, { "epoch": 0.749345634717239, "grad_norm": 2.405149221420288, "learning_rate": 1.5599293664633847e-05, "loss": 0.9796, "step": 13706 }, { "epoch": 0.7494003075345976, "grad_norm": 2.6011006832122803, "learning_rate": 1.5592869208801797e-05, "loss": 0.9236, "step": 13707 }, { "epoch": 0.7494549803519562, "grad_norm": 3.146341562271118, "learning_rate": 1.5586445831774997e-05, "loss": 1.0145, "step": 13708 }, { "epoch": 0.7495096531693148, "grad_norm": 2.524829626083374, "learning_rate": 1.5580023533754857e-05, "loss": 0.8914, "step": 13709 }, { "epoch": 0.7495643259866736, "grad_norm": 2.3751327991485596, "learning_rate": 1.557360231494273e-05, "loss": 0.8883, "step": 13710 }, { "epoch": 0.7496189988040322, "grad_norm": 2.9230704307556152, "learning_rate": 1.556718217553995e-05, "loss": 1.1785, "step": 13711 }, { "epoch": 0.7496736716213908, "grad_norm": 3.171186923980713, "learning_rate": 1.556076311574783e-05, "loss": 0.9251, "step": 13712 }, { "epoch": 0.7497283444387494, "grad_norm": 3.2046635150909424, "learning_rate": 1.5554345135767612e-05, "loss": 0.8519, "step": 13713 }, { "epoch": 0.749783017256108, "grad_norm": 2.2906951904296875, "learning_rate": 1.5547928235800536e-05, "loss": 0.9803, "step": 13714 }, { "epoch": 0.7498376900734666, "grad_norm": 2.327101230621338, "learning_rate": 1.5541512416047787e-05, "loss": 1.0763, "step": 13715 }, { "epoch": 0.7498923628908252, "grad_norm": 1.860809326171875, "learning_rate": 1.5535097676710554e-05, "loss": 0.7749, "step": 13716 }, { "epoch": 0.7499470357081839, "grad_norm": 2.6093978881835938, "learning_rate": 1.552868401798995e-05, "loss": 1.1309, "step": 13717 }, { "epoch": 0.7500017085255425, "grad_norm": 3.1744062900543213, "learning_rate": 1.552227144008706e-05, "loss": 1.1441, "step": 13718 }, { "epoch": 0.7500563813429011, "grad_norm": 3.112637519836426, "learning_rate": 1.5515859943202964e-05, "loss": 1.1809, "step": 13719 }, { "epoch": 0.7501110541602597, "grad_norm": 2.302283525466919, "learning_rate": 1.5509449527538677e-05, "loss": 1.0522, "step": 13720 }, { "epoch": 0.7501657269776183, "grad_norm": 3.3545103073120117, "learning_rate": 1.55030401932952e-05, "loss": 0.9137, "step": 13721 }, { "epoch": 0.7502203997949769, "grad_norm": 2.4731898307800293, "learning_rate": 1.5496631940673478e-05, "loss": 1.0181, "step": 13722 }, { "epoch": 0.7502750726123355, "grad_norm": 2.9164187908172607, "learning_rate": 1.549022476987445e-05, "loss": 1.0214, "step": 13723 }, { "epoch": 0.7503297454296942, "grad_norm": 3.294419527053833, "learning_rate": 1.5483818681098998e-05, "loss": 1.1067, "step": 13724 }, { "epoch": 0.7503844182470528, "grad_norm": 3.282343626022339, "learning_rate": 1.547741367454797e-05, "loss": 0.9776, "step": 13725 }, { "epoch": 0.7504390910644114, "grad_norm": 3.0736026763916016, "learning_rate": 1.5471009750422215e-05, "loss": 0.9081, "step": 13726 }, { "epoch": 0.75049376388177, "grad_norm": 3.762387990951538, "learning_rate": 1.5464606908922515e-05, "loss": 1.0229, "step": 13727 }, { "epoch": 0.7505484366991286, "grad_norm": 2.6389031410217285, "learning_rate": 1.5458205150249615e-05, "loss": 0.8238, "step": 13728 }, { "epoch": 0.7506031095164872, "grad_norm": 2.628594398498535, "learning_rate": 1.5451804474604244e-05, "loss": 1.0852, "step": 13729 }, { "epoch": 0.7506577823338458, "grad_norm": 3.2856125831604004, "learning_rate": 1.5445404882187085e-05, "loss": 0.9471, "step": 13730 }, { "epoch": 0.7507124551512045, "grad_norm": 2.309971570968628, "learning_rate": 1.5439006373198795e-05, "loss": 0.9789, "step": 13731 }, { "epoch": 0.7507671279685632, "grad_norm": 3.657557964324951, "learning_rate": 1.5432608947839992e-05, "loss": 1.1329, "step": 13732 }, { "epoch": 0.7508218007859218, "grad_norm": 2.7885587215423584, "learning_rate": 1.5426212606311263e-05, "loss": 0.9189, "step": 13733 }, { "epoch": 0.7508764736032804, "grad_norm": 2.519517421722412, "learning_rate": 1.5419817348813136e-05, "loss": 1.1284, "step": 13734 }, { "epoch": 0.750931146420639, "grad_norm": 2.342937707901001, "learning_rate": 1.5413423175546176e-05, "loss": 0.9972, "step": 13735 }, { "epoch": 0.7509858192379976, "grad_norm": 2.7353498935699463, "learning_rate": 1.540703008671084e-05, "loss": 1.0349, "step": 13736 }, { "epoch": 0.7510404920553563, "grad_norm": 2.7928450107574463, "learning_rate": 1.540063808250758e-05, "loss": 0.9861, "step": 13737 }, { "epoch": 0.7510951648727149, "grad_norm": 2.6896603107452393, "learning_rate": 1.5394247163136805e-05, "loss": 1.0174, "step": 13738 }, { "epoch": 0.7511498376900735, "grad_norm": 3.1313514709472656, "learning_rate": 1.538785732879891e-05, "loss": 1.0464, "step": 13739 }, { "epoch": 0.7512045105074321, "grad_norm": 2.3843460083007812, "learning_rate": 1.538146857969423e-05, "loss": 0.9312, "step": 13740 }, { "epoch": 0.7512591833247907, "grad_norm": 2.254762649536133, "learning_rate": 1.537508091602309e-05, "loss": 0.827, "step": 13741 }, { "epoch": 0.7513138561421493, "grad_norm": 3.093052864074707, "learning_rate": 1.5368694337985757e-05, "loss": 1.2032, "step": 13742 }, { "epoch": 0.7513685289595079, "grad_norm": 3.170858383178711, "learning_rate": 1.5362308845782485e-05, "loss": 1.0023, "step": 13743 }, { "epoch": 0.7514232017768666, "grad_norm": 2.5611677169799805, "learning_rate": 1.5355924439613473e-05, "loss": 1.0477, "step": 13744 }, { "epoch": 0.7514778745942252, "grad_norm": 2.7477810382843018, "learning_rate": 1.5349541119678916e-05, "loss": 1.06, "step": 13745 }, { "epoch": 0.7515325474115838, "grad_norm": 3.0282485485076904, "learning_rate": 1.534315888617896e-05, "loss": 0.8946, "step": 13746 }, { "epoch": 0.7515872202289424, "grad_norm": 2.3020436763763428, "learning_rate": 1.5336777739313703e-05, "loss": 0.9854, "step": 13747 }, { "epoch": 0.751641893046301, "grad_norm": 2.616060495376587, "learning_rate": 1.5330397679283215e-05, "loss": 0.9469, "step": 13748 }, { "epoch": 0.7516965658636596, "grad_norm": 2.962458372116089, "learning_rate": 1.532401870628755e-05, "loss": 1.0091, "step": 13749 }, { "epoch": 0.7517512386810182, "grad_norm": 3.07747483253479, "learning_rate": 1.5317640820526708e-05, "loss": 0.9776, "step": 13750 }, { "epoch": 0.7518059114983769, "grad_norm": 2.3753862380981445, "learning_rate": 1.531126402220066e-05, "loss": 1.0209, "step": 13751 }, { "epoch": 0.7518605843157355, "grad_norm": 3.534719944000244, "learning_rate": 1.5304888311509353e-05, "loss": 1.0381, "step": 13752 }, { "epoch": 0.7519152571330942, "grad_norm": 3.722872257232666, "learning_rate": 1.529851368865269e-05, "loss": 1.1189, "step": 13753 }, { "epoch": 0.7519699299504528, "grad_norm": 2.412022113800049, "learning_rate": 1.529214015383053e-05, "loss": 1.0596, "step": 13754 }, { "epoch": 0.7520246027678114, "grad_norm": 2.4703586101531982, "learning_rate": 1.528576770724272e-05, "loss": 0.8372, "step": 13755 }, { "epoch": 0.75207927558517, "grad_norm": 2.56915545463562, "learning_rate": 1.5279396349089065e-05, "loss": 1.1035, "step": 13756 }, { "epoch": 0.7521339484025286, "grad_norm": 2.330784797668457, "learning_rate": 1.5273026079569308e-05, "loss": 0.9634, "step": 13757 }, { "epoch": 0.7521886212198873, "grad_norm": 2.351229429244995, "learning_rate": 1.526665689888322e-05, "loss": 0.8953, "step": 13758 }, { "epoch": 0.7522432940372459, "grad_norm": 2.305488109588623, "learning_rate": 1.5260288807230487e-05, "loss": 0.9026, "step": 13759 }, { "epoch": 0.7522979668546045, "grad_norm": 2.731138229370117, "learning_rate": 1.5253921804810773e-05, "loss": 0.9264, "step": 13760 }, { "epoch": 0.7523526396719631, "grad_norm": 2.4010040760040283, "learning_rate": 1.5247555891823712e-05, "loss": 1.2059, "step": 13761 }, { "epoch": 0.7524073124893217, "grad_norm": 1.997403860092163, "learning_rate": 1.5241191068468896e-05, "loss": 0.924, "step": 13762 }, { "epoch": 0.7524619853066803, "grad_norm": 2.576483964920044, "learning_rate": 1.5234827334945895e-05, "loss": 1.0405, "step": 13763 }, { "epoch": 0.752516658124039, "grad_norm": 2.6446032524108887, "learning_rate": 1.522846469145423e-05, "loss": 0.869, "step": 13764 }, { "epoch": 0.7525713309413976, "grad_norm": 2.2436065673828125, "learning_rate": 1.5222103138193406e-05, "loss": 0.9247, "step": 13765 }, { "epoch": 0.7526260037587562, "grad_norm": 2.9633448123931885, "learning_rate": 1.5215742675362876e-05, "loss": 0.9878, "step": 13766 }, { "epoch": 0.7526806765761148, "grad_norm": 2.835598945617676, "learning_rate": 1.5209383303162073e-05, "loss": 1.0498, "step": 13767 }, { "epoch": 0.7527353493934734, "grad_norm": 2.3414018154144287, "learning_rate": 1.5203025021790385e-05, "loss": 1.0524, "step": 13768 }, { "epoch": 0.752790022210832, "grad_norm": 2.858172655105591, "learning_rate": 1.519666783144717e-05, "loss": 1.0304, "step": 13769 }, { "epoch": 0.7528446950281906, "grad_norm": 2.329643964767456, "learning_rate": 1.5190311732331736e-05, "loss": 1.11, "step": 13770 }, { "epoch": 0.7528993678455493, "grad_norm": 2.6795647144317627, "learning_rate": 1.518395672464341e-05, "loss": 0.9819, "step": 13771 }, { "epoch": 0.7529540406629079, "grad_norm": 2.617692470550537, "learning_rate": 1.5177602808581426e-05, "loss": 1.018, "step": 13772 }, { "epoch": 0.7530087134802665, "grad_norm": 3.1776320934295654, "learning_rate": 1.517124998434501e-05, "loss": 1.0586, "step": 13773 }, { "epoch": 0.7530633862976251, "grad_norm": 2.4237136840820312, "learning_rate": 1.5164898252133342e-05, "loss": 1.1536, "step": 13774 }, { "epoch": 0.7531180591149838, "grad_norm": 2.685262680053711, "learning_rate": 1.5158547612145586e-05, "loss": 0.8687, "step": 13775 }, { "epoch": 0.7531727319323424, "grad_norm": 3.6129586696624756, "learning_rate": 1.5152198064580853e-05, "loss": 1.0168, "step": 13776 }, { "epoch": 0.753227404749701, "grad_norm": 4.261623382568359, "learning_rate": 1.5145849609638224e-05, "loss": 1.0689, "step": 13777 }, { "epoch": 0.7532820775670597, "grad_norm": 2.1571764945983887, "learning_rate": 1.5139502247516758e-05, "loss": 0.9007, "step": 13778 }, { "epoch": 0.7533367503844183, "grad_norm": 2.0824148654937744, "learning_rate": 1.513315597841547e-05, "loss": 0.9957, "step": 13779 }, { "epoch": 0.7533914232017769, "grad_norm": 2.710608959197998, "learning_rate": 1.512681080253333e-05, "loss": 1.0264, "step": 13780 }, { "epoch": 0.7534460960191355, "grad_norm": 2.4596025943756104, "learning_rate": 1.5120466720069304e-05, "loss": 1.0316, "step": 13781 }, { "epoch": 0.7535007688364941, "grad_norm": 3.299903631210327, "learning_rate": 1.511412373122229e-05, "loss": 0.9443, "step": 13782 }, { "epoch": 0.7535554416538527, "grad_norm": 2.258500814437866, "learning_rate": 1.5107781836191154e-05, "loss": 1.1448, "step": 13783 }, { "epoch": 0.7536101144712113, "grad_norm": 3.1334431171417236, "learning_rate": 1.510144103517478e-05, "loss": 1.1691, "step": 13784 }, { "epoch": 0.75366478728857, "grad_norm": 2.9880402088165283, "learning_rate": 1.5095101328371953e-05, "loss": 1.0568, "step": 13785 }, { "epoch": 0.7537194601059286, "grad_norm": 3.0421671867370605, "learning_rate": 1.5088762715981458e-05, "loss": 1.0608, "step": 13786 }, { "epoch": 0.7537741329232872, "grad_norm": 3.821805000305176, "learning_rate": 1.5082425198202027e-05, "loss": 1.1664, "step": 13787 }, { "epoch": 0.7538288057406458, "grad_norm": 3.0443921089172363, "learning_rate": 1.5076088775232372e-05, "loss": 1.0673, "step": 13788 }, { "epoch": 0.7538834785580044, "grad_norm": 2.5022451877593994, "learning_rate": 1.5069753447271168e-05, "loss": 1.0051, "step": 13789 }, { "epoch": 0.753938151375363, "grad_norm": 2.7983431816101074, "learning_rate": 1.5063419214517044e-05, "loss": 0.8949, "step": 13790 }, { "epoch": 0.7539928241927217, "grad_norm": 2.3760759830474854, "learning_rate": 1.505708607716862e-05, "loss": 1.1153, "step": 13791 }, { "epoch": 0.7540474970100803, "grad_norm": 2.363950729370117, "learning_rate": 1.5050754035424452e-05, "loss": 1.0743, "step": 13792 }, { "epoch": 0.7541021698274389, "grad_norm": 2.8788578510284424, "learning_rate": 1.5044423089483067e-05, "loss": 1.0096, "step": 13793 }, { "epoch": 0.7541568426447975, "grad_norm": 2.3657846450805664, "learning_rate": 1.5038093239543e-05, "loss": 0.8137, "step": 13794 }, { "epoch": 0.7542115154621561, "grad_norm": 2.3414242267608643, "learning_rate": 1.5031764485802696e-05, "loss": 1.1768, "step": 13795 }, { "epoch": 0.7542661882795147, "grad_norm": 2.913315534591675, "learning_rate": 1.5025436828460588e-05, "loss": 1.19, "step": 13796 }, { "epoch": 0.7543208610968734, "grad_norm": 2.2482876777648926, "learning_rate": 1.5019110267715075e-05, "loss": 0.9353, "step": 13797 }, { "epoch": 0.7543755339142321, "grad_norm": 3.0149898529052734, "learning_rate": 1.5012784803764523e-05, "loss": 1.0817, "step": 13798 }, { "epoch": 0.7544302067315907, "grad_norm": 2.493788480758667, "learning_rate": 1.5006460436807257e-05, "loss": 0.9854, "step": 13799 }, { "epoch": 0.7544848795489493, "grad_norm": 5.995829105377197, "learning_rate": 1.5000137167041579e-05, "loss": 0.8615, "step": 13800 }, { "epoch": 0.7545395523663079, "grad_norm": 2.671525239944458, "learning_rate": 1.4993814994665745e-05, "loss": 1.0475, "step": 13801 }, { "epoch": 0.7545942251836665, "grad_norm": 2.6728312969207764, "learning_rate": 1.4987493919877976e-05, "loss": 1.0773, "step": 13802 }, { "epoch": 0.7546488980010251, "grad_norm": 2.7256550788879395, "learning_rate": 1.498117394287646e-05, "loss": 0.9925, "step": 13803 }, { "epoch": 0.7547035708183837, "grad_norm": 2.6848130226135254, "learning_rate": 1.4974855063859377e-05, "loss": 1.0995, "step": 13804 }, { "epoch": 0.7547582436357424, "grad_norm": 3.356513261795044, "learning_rate": 1.4968537283024836e-05, "loss": 1.068, "step": 13805 }, { "epoch": 0.754812916453101, "grad_norm": 2.2043514251708984, "learning_rate": 1.4962220600570925e-05, "loss": 1.0714, "step": 13806 }, { "epoch": 0.7548675892704596, "grad_norm": 2.3694396018981934, "learning_rate": 1.4955905016695704e-05, "loss": 1.0114, "step": 13807 }, { "epoch": 0.7549222620878182, "grad_norm": 2.507178544998169, "learning_rate": 1.4949590531597179e-05, "loss": 0.996, "step": 13808 }, { "epoch": 0.7549769349051768, "grad_norm": 2.8392446041107178, "learning_rate": 1.494327714547335e-05, "loss": 0.9979, "step": 13809 }, { "epoch": 0.7550316077225354, "grad_norm": 2.977579116821289, "learning_rate": 1.4936964858522162e-05, "loss": 0.9922, "step": 13810 }, { "epoch": 0.755086280539894, "grad_norm": 2.7333648204803467, "learning_rate": 1.4930653670941525e-05, "loss": 1.1422, "step": 13811 }, { "epoch": 0.7551409533572527, "grad_norm": 2.751213788986206, "learning_rate": 1.492434358292933e-05, "loss": 1.0556, "step": 13812 }, { "epoch": 0.7551956261746113, "grad_norm": 4.159448146820068, "learning_rate": 1.49180345946834e-05, "loss": 1.094, "step": 13813 }, { "epoch": 0.7552502989919699, "grad_norm": 2.486954689025879, "learning_rate": 1.4911726706401591e-05, "loss": 1.1316, "step": 13814 }, { "epoch": 0.7553049718093285, "grad_norm": 2.954690933227539, "learning_rate": 1.4905419918281654e-05, "loss": 0.893, "step": 13815 }, { "epoch": 0.7553596446266871, "grad_norm": 2.9226043224334717, "learning_rate": 1.4899114230521339e-05, "loss": 1.0179, "step": 13816 }, { "epoch": 0.7554143174440457, "grad_norm": 2.4943625926971436, "learning_rate": 1.4892809643318351e-05, "loss": 0.9098, "step": 13817 }, { "epoch": 0.7554689902614045, "grad_norm": 2.937697410583496, "learning_rate": 1.4886506156870367e-05, "loss": 1.0945, "step": 13818 }, { "epoch": 0.7555236630787631, "grad_norm": 2.723310708999634, "learning_rate": 1.488020377137503e-05, "loss": 0.8711, "step": 13819 }, { "epoch": 0.7555783358961217, "grad_norm": 2.113034963607788, "learning_rate": 1.4873902487029939e-05, "loss": 0.8838, "step": 13820 }, { "epoch": 0.7556330087134803, "grad_norm": 2.453701972961426, "learning_rate": 1.4867602304032675e-05, "loss": 1.0389, "step": 13821 }, { "epoch": 0.7556876815308389, "grad_norm": 3.087524890899658, "learning_rate": 1.486130322258077e-05, "loss": 1.0246, "step": 13822 }, { "epoch": 0.7557423543481975, "grad_norm": 2.2181131839752197, "learning_rate": 1.4855005242871706e-05, "loss": 0.9555, "step": 13823 }, { "epoch": 0.7557970271655561, "grad_norm": 3.429703712463379, "learning_rate": 1.4848708365102982e-05, "loss": 1.2144, "step": 13824 }, { "epoch": 0.7558516999829148, "grad_norm": 3.3057734966278076, "learning_rate": 1.4842412589472027e-05, "loss": 1.1541, "step": 13825 }, { "epoch": 0.7559063728002734, "grad_norm": 2.8373947143554688, "learning_rate": 1.4836117916176223e-05, "loss": 1.0304, "step": 13826 }, { "epoch": 0.755961045617632, "grad_norm": 3.02575945854187, "learning_rate": 1.4829824345412947e-05, "loss": 0.9487, "step": 13827 }, { "epoch": 0.7560157184349906, "grad_norm": 2.9373891353607178, "learning_rate": 1.4823531877379527e-05, "loss": 1.2106, "step": 13828 }, { "epoch": 0.7560703912523492, "grad_norm": 2.913529872894287, "learning_rate": 1.481724051227325e-05, "loss": 0.9862, "step": 13829 }, { "epoch": 0.7561250640697078, "grad_norm": 2.608541488647461, "learning_rate": 1.4810950250291378e-05, "loss": 1.1451, "step": 13830 }, { "epoch": 0.7561797368870664, "grad_norm": 2.9068803787231445, "learning_rate": 1.4804661091631144e-05, "loss": 0.9545, "step": 13831 }, { "epoch": 0.7562344097044251, "grad_norm": 2.539964437484741, "learning_rate": 1.479837303648972e-05, "loss": 1.2251, "step": 13832 }, { "epoch": 0.7562890825217837, "grad_norm": 2.150078058242798, "learning_rate": 1.4792086085064289e-05, "loss": 0.8736, "step": 13833 }, { "epoch": 0.7563437553391423, "grad_norm": 2.4189743995666504, "learning_rate": 1.478580023755196e-05, "loss": 0.9629, "step": 13834 }, { "epoch": 0.7563984281565009, "grad_norm": 2.017184019088745, "learning_rate": 1.4779515494149827e-05, "loss": 0.7221, "step": 13835 }, { "epoch": 0.7564531009738595, "grad_norm": 2.3191378116607666, "learning_rate": 1.4773231855054931e-05, "loss": 0.8189, "step": 13836 }, { "epoch": 0.7565077737912181, "grad_norm": 2.7308781147003174, "learning_rate": 1.4766949320464295e-05, "loss": 1.0888, "step": 13837 }, { "epoch": 0.7565624466085767, "grad_norm": 2.437636613845825, "learning_rate": 1.4760667890574903e-05, "loss": 0.8129, "step": 13838 }, { "epoch": 0.7566171194259355, "grad_norm": 4.08992862701416, "learning_rate": 1.4754387565583704e-05, "loss": 0.9737, "step": 13839 }, { "epoch": 0.7566717922432941, "grad_norm": 2.799089193344116, "learning_rate": 1.474810834568761e-05, "loss": 1.0131, "step": 13840 }, { "epoch": 0.7567264650606527, "grad_norm": 2.56410813331604, "learning_rate": 1.4741830231083504e-05, "loss": 0.9824, "step": 13841 }, { "epoch": 0.7567811378780113, "grad_norm": 2.399125337600708, "learning_rate": 1.4735553221968212e-05, "loss": 0.9159, "step": 13842 }, { "epoch": 0.7568358106953699, "grad_norm": 2.822639226913452, "learning_rate": 1.4729277318538581e-05, "loss": 1.1065, "step": 13843 }, { "epoch": 0.7568904835127285, "grad_norm": 2.4552836418151855, "learning_rate": 1.4723002520991358e-05, "loss": 0.8286, "step": 13844 }, { "epoch": 0.7569451563300872, "grad_norm": 2.6560118198394775, "learning_rate": 1.4716728829523296e-05, "loss": 1.0552, "step": 13845 }, { "epoch": 0.7569998291474458, "grad_norm": 2.411102056503296, "learning_rate": 1.47104562443311e-05, "loss": 1.1042, "step": 13846 }, { "epoch": 0.7570545019648044, "grad_norm": 3.0674889087677, "learning_rate": 1.4704184765611434e-05, "loss": 1.1471, "step": 13847 }, { "epoch": 0.757109174782163, "grad_norm": 2.3766045570373535, "learning_rate": 1.469791439356094e-05, "loss": 1.1378, "step": 13848 }, { "epoch": 0.7571638475995216, "grad_norm": 2.5804994106292725, "learning_rate": 1.4691645128376218e-05, "loss": 1.0523, "step": 13849 }, { "epoch": 0.7572185204168802, "grad_norm": 2.775123357772827, "learning_rate": 1.468537697025384e-05, "loss": 1.0227, "step": 13850 }, { "epoch": 0.7572731932342388, "grad_norm": 2.4533956050872803, "learning_rate": 1.4679109919390333e-05, "loss": 0.901, "step": 13851 }, { "epoch": 0.7573278660515975, "grad_norm": 2.277006149291992, "learning_rate": 1.467284397598218e-05, "loss": 0.9439, "step": 13852 }, { "epoch": 0.7573825388689561, "grad_norm": 2.824005603790283, "learning_rate": 1.4666579140225878e-05, "loss": 1.0838, "step": 13853 }, { "epoch": 0.7574372116863147, "grad_norm": 3.521512985229492, "learning_rate": 1.4660315412317838e-05, "loss": 1.0228, "step": 13854 }, { "epoch": 0.7574918845036733, "grad_norm": 2.3692357540130615, "learning_rate": 1.4654052792454448e-05, "loss": 1.086, "step": 13855 }, { "epoch": 0.7575465573210319, "grad_norm": 2.7241148948669434, "learning_rate": 1.4647791280832079e-05, "loss": 0.9732, "step": 13856 }, { "epoch": 0.7576012301383905, "grad_norm": 2.709139108657837, "learning_rate": 1.4641530877647048e-05, "loss": 1.011, "step": 13857 }, { "epoch": 0.7576559029557491, "grad_norm": 2.78713321685791, "learning_rate": 1.4635271583095644e-05, "loss": 0.8551, "step": 13858 }, { "epoch": 0.7577105757731079, "grad_norm": 2.8288650512695312, "learning_rate": 1.4629013397374125e-05, "loss": 0.8603, "step": 13859 }, { "epoch": 0.7577652485904665, "grad_norm": 3.3145382404327393, "learning_rate": 1.462275632067871e-05, "loss": 1.1803, "step": 13860 }, { "epoch": 0.7578199214078251, "grad_norm": 2.995844841003418, "learning_rate": 1.4616500353205581e-05, "loss": 0.989, "step": 13861 }, { "epoch": 0.7578745942251837, "grad_norm": 2.2727649211883545, "learning_rate": 1.4610245495150876e-05, "loss": 1.0661, "step": 13862 }, { "epoch": 0.7579292670425423, "grad_norm": 2.4853696823120117, "learning_rate": 1.4603991746710737e-05, "loss": 1.092, "step": 13863 }, { "epoch": 0.7579839398599009, "grad_norm": 2.6337790489196777, "learning_rate": 1.4597739108081237e-05, "loss": 1.1689, "step": 13864 }, { "epoch": 0.7580386126772595, "grad_norm": 2.252255439758301, "learning_rate": 1.4591487579458412e-05, "loss": 0.8483, "step": 13865 }, { "epoch": 0.7580932854946182, "grad_norm": 2.6118688583374023, "learning_rate": 1.4585237161038283e-05, "loss": 1.069, "step": 13866 }, { "epoch": 0.7581479583119768, "grad_norm": 5.0295562744140625, "learning_rate": 1.4578987853016823e-05, "loss": 1.0011, "step": 13867 }, { "epoch": 0.7582026311293354, "grad_norm": 2.4759104251861572, "learning_rate": 1.4572739655589973e-05, "loss": 1.0885, "step": 13868 }, { "epoch": 0.758257303946694, "grad_norm": 2.7937259674072266, "learning_rate": 1.4566492568953643e-05, "loss": 1.1243, "step": 13869 }, { "epoch": 0.7583119767640526, "grad_norm": 3.448448657989502, "learning_rate": 1.4560246593303695e-05, "loss": 0.8344, "step": 13870 }, { "epoch": 0.7583666495814112, "grad_norm": 3.175464630126953, "learning_rate": 1.4554001728835975e-05, "loss": 1.0983, "step": 13871 }, { "epoch": 0.7584213223987699, "grad_norm": 6.244600772857666, "learning_rate": 1.4547757975746269e-05, "loss": 1.1231, "step": 13872 }, { "epoch": 0.7584759952161285, "grad_norm": 2.3896350860595703, "learning_rate": 1.454151533423037e-05, "loss": 0.844, "step": 13873 }, { "epoch": 0.7585306680334871, "grad_norm": 3.479240655899048, "learning_rate": 1.4535273804484001e-05, "loss": 1.1035, "step": 13874 }, { "epoch": 0.7585853408508457, "grad_norm": 2.3179800510406494, "learning_rate": 1.4529033386702856e-05, "loss": 0.8017, "step": 13875 }, { "epoch": 0.7586400136682043, "grad_norm": 2.407397508621216, "learning_rate": 1.4522794081082598e-05, "loss": 0.9487, "step": 13876 }, { "epoch": 0.7586946864855629, "grad_norm": 3.3143861293792725, "learning_rate": 1.4516555887818855e-05, "loss": 0.916, "step": 13877 }, { "epoch": 0.7587493593029215, "grad_norm": 2.0185630321502686, "learning_rate": 1.4510318807107226e-05, "loss": 0.7837, "step": 13878 }, { "epoch": 0.7588040321202802, "grad_norm": 2.7278478145599365, "learning_rate": 1.4504082839143262e-05, "loss": 0.873, "step": 13879 }, { "epoch": 0.7588587049376389, "grad_norm": 4.625039577484131, "learning_rate": 1.4497847984122486e-05, "loss": 1.2097, "step": 13880 }, { "epoch": 0.7589133777549975, "grad_norm": 2.373426675796509, "learning_rate": 1.4491614242240391e-05, "loss": 0.9837, "step": 13881 }, { "epoch": 0.7589680505723561, "grad_norm": 2.395942211151123, "learning_rate": 1.448538161369241e-05, "loss": 1.0086, "step": 13882 }, { "epoch": 0.7590227233897147, "grad_norm": 2.5173652172088623, "learning_rate": 1.4479150098674006e-05, "loss": 0.9544, "step": 13883 }, { "epoch": 0.7590773962070733, "grad_norm": 2.4088785648345947, "learning_rate": 1.4472919697380527e-05, "loss": 0.9945, "step": 13884 }, { "epoch": 0.7591320690244319, "grad_norm": 2.6577165126800537, "learning_rate": 1.4466690410007332e-05, "loss": 0.842, "step": 13885 }, { "epoch": 0.7591867418417906, "grad_norm": 2.974480390548706, "learning_rate": 1.4460462236749733e-05, "loss": 1.0845, "step": 13886 }, { "epoch": 0.7592414146591492, "grad_norm": 2.8575828075408936, "learning_rate": 1.4454235177803016e-05, "loss": 0.9903, "step": 13887 }, { "epoch": 0.7592960874765078, "grad_norm": 5.795757293701172, "learning_rate": 1.4448009233362414e-05, "loss": 1.2554, "step": 13888 }, { "epoch": 0.7593507602938664, "grad_norm": 3.020311117172241, "learning_rate": 1.4441784403623143e-05, "loss": 1.0457, "step": 13889 }, { "epoch": 0.759405433111225, "grad_norm": 2.8140456676483154, "learning_rate": 1.4435560688780376e-05, "loss": 0.9993, "step": 13890 }, { "epoch": 0.7594601059285836, "grad_norm": 2.5125038623809814, "learning_rate": 1.4429338089029232e-05, "loss": 1.0365, "step": 13891 }, { "epoch": 0.7595147787459422, "grad_norm": 2.6687676906585693, "learning_rate": 1.4423116604564851e-05, "loss": 0.9041, "step": 13892 }, { "epoch": 0.7595694515633009, "grad_norm": 2.5287647247314453, "learning_rate": 1.4416896235582283e-05, "loss": 0.8001, "step": 13893 }, { "epoch": 0.7596241243806595, "grad_norm": 2.600055694580078, "learning_rate": 1.4410676982276572e-05, "loss": 0.9443, "step": 13894 }, { "epoch": 0.7596787971980181, "grad_norm": 2.5716171264648438, "learning_rate": 1.4404458844842706e-05, "loss": 0.9668, "step": 13895 }, { "epoch": 0.7597334700153767, "grad_norm": 2.364652633666992, "learning_rate": 1.439824182347565e-05, "loss": 1.0325, "step": 13896 }, { "epoch": 0.7597881428327353, "grad_norm": 2.4407594203948975, "learning_rate": 1.4392025918370339e-05, "loss": 1.0006, "step": 13897 }, { "epoch": 0.7598428156500939, "grad_norm": 2.868475914001465, "learning_rate": 1.4385811129721667e-05, "loss": 1.0059, "step": 13898 }, { "epoch": 0.7598974884674526, "grad_norm": 2.649587631225586, "learning_rate": 1.4379597457724486e-05, "loss": 1.0975, "step": 13899 }, { "epoch": 0.7599521612848112, "grad_norm": 2.9589762687683105, "learning_rate": 1.4373384902573628e-05, "loss": 1.0098, "step": 13900 }, { "epoch": 0.7600068341021698, "grad_norm": 2.843452215194702, "learning_rate": 1.4367173464463862e-05, "loss": 1.1458, "step": 13901 }, { "epoch": 0.7600615069195285, "grad_norm": 2.9351723194122314, "learning_rate": 1.4360963143589973e-05, "loss": 0.8954, "step": 13902 }, { "epoch": 0.760116179736887, "grad_norm": 2.852999448776245, "learning_rate": 1.4354753940146671e-05, "loss": 1.1409, "step": 13903 }, { "epoch": 0.7601708525542457, "grad_norm": 2.4131743907928467, "learning_rate": 1.4348545854328631e-05, "loss": 1.1021, "step": 13904 }, { "epoch": 0.7602255253716043, "grad_norm": 2.380025625228882, "learning_rate": 1.434233888633051e-05, "loss": 1.1696, "step": 13905 }, { "epoch": 0.760280198188963, "grad_norm": 2.882643222808838, "learning_rate": 1.4336133036346916e-05, "loss": 1.1847, "step": 13906 }, { "epoch": 0.7603348710063216, "grad_norm": 2.854652166366577, "learning_rate": 1.4329928304572432e-05, "loss": 0.8762, "step": 13907 }, { "epoch": 0.7603895438236802, "grad_norm": 2.337059259414673, "learning_rate": 1.4323724691201596e-05, "loss": 0.9328, "step": 13908 }, { "epoch": 0.7604442166410388, "grad_norm": 2.582915782928467, "learning_rate": 1.431752219642893e-05, "loss": 1.1028, "step": 13909 }, { "epoch": 0.7604988894583974, "grad_norm": 2.4900546073913574, "learning_rate": 1.4311320820448892e-05, "loss": 1.0735, "step": 13910 }, { "epoch": 0.760553562275756, "grad_norm": 2.599689483642578, "learning_rate": 1.4305120563455914e-05, "loss": 1.213, "step": 13911 }, { "epoch": 0.7606082350931146, "grad_norm": 2.8148136138916016, "learning_rate": 1.4298921425644429e-05, "loss": 1.139, "step": 13912 }, { "epoch": 0.7606629079104733, "grad_norm": 3.3963375091552734, "learning_rate": 1.4292723407208786e-05, "loss": 1.1501, "step": 13913 }, { "epoch": 0.7607175807278319, "grad_norm": 2.4190804958343506, "learning_rate": 1.4286526508343329e-05, "loss": 0.9933, "step": 13914 }, { "epoch": 0.7607722535451905, "grad_norm": 3.352792263031006, "learning_rate": 1.4280330729242347e-05, "loss": 1.276, "step": 13915 }, { "epoch": 0.7608269263625491, "grad_norm": 2.4749679565429688, "learning_rate": 1.4274136070100102e-05, "loss": 0.8986, "step": 13916 }, { "epoch": 0.7608815991799077, "grad_norm": 3.394331932067871, "learning_rate": 1.4267942531110828e-05, "loss": 1.0904, "step": 13917 }, { "epoch": 0.7609362719972663, "grad_norm": 2.6163742542266846, "learning_rate": 1.4261750112468719e-05, "loss": 0.9098, "step": 13918 }, { "epoch": 0.7609909448146249, "grad_norm": 2.3865067958831787, "learning_rate": 1.4255558814367926e-05, "loss": 0.8325, "step": 13919 }, { "epoch": 0.7610456176319836, "grad_norm": 2.5565621852874756, "learning_rate": 1.4249368637002575e-05, "loss": 1.1768, "step": 13920 }, { "epoch": 0.7611002904493422, "grad_norm": 2.515143871307373, "learning_rate": 1.424317958056674e-05, "loss": 1.1852, "step": 13921 }, { "epoch": 0.7611549632667008, "grad_norm": 2.603386402130127, "learning_rate": 1.42369916452545e-05, "loss": 0.8963, "step": 13922 }, { "epoch": 0.7612096360840594, "grad_norm": 2.2795424461364746, "learning_rate": 1.4230804831259864e-05, "loss": 0.9363, "step": 13923 }, { "epoch": 0.761264308901418, "grad_norm": 2.037750482559204, "learning_rate": 1.4224619138776807e-05, "loss": 0.7807, "step": 13924 }, { "epoch": 0.7613189817187767, "grad_norm": 2.2104363441467285, "learning_rate": 1.4218434567999278e-05, "loss": 0.9936, "step": 13925 }, { "epoch": 0.7613736545361354, "grad_norm": 2.570457935333252, "learning_rate": 1.421225111912119e-05, "loss": 1.0377, "step": 13926 }, { "epoch": 0.761428327353494, "grad_norm": 4.410375595092773, "learning_rate": 1.4206068792336418e-05, "loss": 1.1157, "step": 13927 }, { "epoch": 0.7614830001708526, "grad_norm": 2.8602867126464844, "learning_rate": 1.4199887587838806e-05, "loss": 1.2166, "step": 13928 }, { "epoch": 0.7615376729882112, "grad_norm": 2.8221139907836914, "learning_rate": 1.4193707505822157e-05, "loss": 1.006, "step": 13929 }, { "epoch": 0.7615923458055698, "grad_norm": 3.663313627243042, "learning_rate": 1.4187528546480239e-05, "loss": 1.1837, "step": 13930 }, { "epoch": 0.7616470186229284, "grad_norm": 3.5057477951049805, "learning_rate": 1.4181350710006785e-05, "loss": 1.2444, "step": 13931 }, { "epoch": 0.761701691440287, "grad_norm": 2.8793952465057373, "learning_rate": 1.4175173996595514e-05, "loss": 1.0522, "step": 13932 }, { "epoch": 0.7617563642576457, "grad_norm": 2.6981873512268066, "learning_rate": 1.4168998406440082e-05, "loss": 0.9594, "step": 13933 }, { "epoch": 0.7618110370750043, "grad_norm": 2.928870439529419, "learning_rate": 1.4162823939734116e-05, "loss": 1.0579, "step": 13934 }, { "epoch": 0.7618657098923629, "grad_norm": 2.4800240993499756, "learning_rate": 1.4156650596671212e-05, "loss": 0.9709, "step": 13935 }, { "epoch": 0.7619203827097215, "grad_norm": 3.1607398986816406, "learning_rate": 1.4150478377444931e-05, "loss": 1.1202, "step": 13936 }, { "epoch": 0.7619750555270801, "grad_norm": 2.6219136714935303, "learning_rate": 1.4144307282248798e-05, "loss": 1.0506, "step": 13937 }, { "epoch": 0.7620297283444387, "grad_norm": 2.174367666244507, "learning_rate": 1.4138137311276294e-05, "loss": 0.8865, "step": 13938 }, { "epoch": 0.7620844011617973, "grad_norm": 2.4139466285705566, "learning_rate": 1.413196846472089e-05, "loss": 1.0751, "step": 13939 }, { "epoch": 0.762139073979156, "grad_norm": 2.483908176422119, "learning_rate": 1.4125800742775985e-05, "loss": 1.13, "step": 13940 }, { "epoch": 0.7621937467965146, "grad_norm": 3.1919143199920654, "learning_rate": 1.411963414563498e-05, "loss": 1.1537, "step": 13941 }, { "epoch": 0.7622484196138732, "grad_norm": 2.5675668716430664, "learning_rate": 1.4113468673491215e-05, "loss": 1.1878, "step": 13942 }, { "epoch": 0.7623030924312318, "grad_norm": 3.3264200687408447, "learning_rate": 1.4107304326538002e-05, "loss": 1.0205, "step": 13943 }, { "epoch": 0.7623577652485904, "grad_norm": 2.91581392288208, "learning_rate": 1.4101141104968602e-05, "loss": 1.221, "step": 13944 }, { "epoch": 0.762412438065949, "grad_norm": 2.8131520748138428, "learning_rate": 1.4094979008976288e-05, "loss": 0.8619, "step": 13945 }, { "epoch": 0.7624671108833077, "grad_norm": 2.8515093326568604, "learning_rate": 1.4088818038754258e-05, "loss": 1.0144, "step": 13946 }, { "epoch": 0.7625217837006664, "grad_norm": 2.386162757873535, "learning_rate": 1.4082658194495685e-05, "loss": 0.7922, "step": 13947 }, { "epoch": 0.762576456518025, "grad_norm": 2.5248565673828125, "learning_rate": 1.4076499476393695e-05, "loss": 1.1238, "step": 13948 }, { "epoch": 0.7626311293353836, "grad_norm": 2.531343698501587, "learning_rate": 1.4070341884641397e-05, "loss": 0.8911, "step": 13949 }, { "epoch": 0.7626858021527422, "grad_norm": 2.3794009685516357, "learning_rate": 1.4064185419431853e-05, "loss": 1.0329, "step": 13950 }, { "epoch": 0.7627404749701008, "grad_norm": 2.815375328063965, "learning_rate": 1.4058030080958095e-05, "loss": 1.0534, "step": 13951 }, { "epoch": 0.7627951477874594, "grad_norm": 3.3699145317077637, "learning_rate": 1.4051875869413123e-05, "loss": 0.9636, "step": 13952 }, { "epoch": 0.7628498206048181, "grad_norm": 3.262012481689453, "learning_rate": 1.404572278498989e-05, "loss": 0.9433, "step": 13953 }, { "epoch": 0.7629044934221767, "grad_norm": 2.7326669692993164, "learning_rate": 1.403957082788132e-05, "loss": 1.1707, "step": 13954 }, { "epoch": 0.7629591662395353, "grad_norm": 2.2010087966918945, "learning_rate": 1.4033419998280306e-05, "loss": 0.8474, "step": 13955 }, { "epoch": 0.7630138390568939, "grad_norm": 2.840094804763794, "learning_rate": 1.4027270296379701e-05, "loss": 0.9487, "step": 13956 }, { "epoch": 0.7630685118742525, "grad_norm": 2.7543728351593018, "learning_rate": 1.4021121722372311e-05, "loss": 0.9771, "step": 13957 }, { "epoch": 0.7631231846916111, "grad_norm": 2.765791893005371, "learning_rate": 1.4014974276450948e-05, "loss": 1.0876, "step": 13958 }, { "epoch": 0.7631778575089697, "grad_norm": 2.4361929893493652, "learning_rate": 1.4008827958808341e-05, "loss": 1.0129, "step": 13959 }, { "epoch": 0.7632325303263284, "grad_norm": 4.013681411743164, "learning_rate": 1.4002682769637204e-05, "loss": 1.0913, "step": 13960 }, { "epoch": 0.763287203143687, "grad_norm": 2.296781539916992, "learning_rate": 1.3996538709130213e-05, "loss": 0.8363, "step": 13961 }, { "epoch": 0.7633418759610456, "grad_norm": 2.632270336151123, "learning_rate": 1.3990395777480015e-05, "loss": 0.849, "step": 13962 }, { "epoch": 0.7633965487784042, "grad_norm": 4.206075668334961, "learning_rate": 1.3984253974879209e-05, "loss": 1.1419, "step": 13963 }, { "epoch": 0.7634512215957628, "grad_norm": 2.290482997894287, "learning_rate": 1.3978113301520368e-05, "loss": 0.9089, "step": 13964 }, { "epoch": 0.7635058944131214, "grad_norm": 2.8412249088287354, "learning_rate": 1.3971973757596035e-05, "loss": 0.9885, "step": 13965 }, { "epoch": 0.76356056723048, "grad_norm": 2.920093297958374, "learning_rate": 1.39658353432987e-05, "loss": 1.152, "step": 13966 }, { "epoch": 0.7636152400478388, "grad_norm": 2.5233466625213623, "learning_rate": 1.395969805882083e-05, "loss": 1.1277, "step": 13967 }, { "epoch": 0.7636699128651974, "grad_norm": 2.627316951751709, "learning_rate": 1.3953561904354856e-05, "loss": 0.8932, "step": 13968 }, { "epoch": 0.763724585682556, "grad_norm": 2.148751974105835, "learning_rate": 1.3947426880093173e-05, "loss": 0.9226, "step": 13969 }, { "epoch": 0.7637792584999146, "grad_norm": 3.103487253189087, "learning_rate": 1.394129298622812e-05, "loss": 1.1843, "step": 13970 }, { "epoch": 0.7638339313172732, "grad_norm": 2.9379608631134033, "learning_rate": 1.3935160222952054e-05, "loss": 0.9131, "step": 13971 }, { "epoch": 0.7638886041346318, "grad_norm": 2.3476593494415283, "learning_rate": 1.3929028590457243e-05, "loss": 1.1072, "step": 13972 }, { "epoch": 0.7639432769519904, "grad_norm": 2.390026569366455, "learning_rate": 1.3922898088935943e-05, "loss": 0.9651, "step": 13973 }, { "epoch": 0.7639979497693491, "grad_norm": 2.336095094680786, "learning_rate": 1.391676871858037e-05, "loss": 0.7138, "step": 13974 }, { "epoch": 0.7640526225867077, "grad_norm": 2.537560224533081, "learning_rate": 1.3910640479582704e-05, "loss": 0.9164, "step": 13975 }, { "epoch": 0.7641072954040663, "grad_norm": 2.278015375137329, "learning_rate": 1.3904513372135092e-05, "loss": 1.0782, "step": 13976 }, { "epoch": 0.7641619682214249, "grad_norm": 1.9491338729858398, "learning_rate": 1.389838739642964e-05, "loss": 0.7371, "step": 13977 }, { "epoch": 0.7642166410387835, "grad_norm": 2.5267326831817627, "learning_rate": 1.3892262552658425e-05, "loss": 0.9737, "step": 13978 }, { "epoch": 0.7642713138561421, "grad_norm": 2.1642963886260986, "learning_rate": 1.3886138841013485e-05, "loss": 0.9539, "step": 13979 }, { "epoch": 0.7643259866735008, "grad_norm": 2.369743824005127, "learning_rate": 1.3880016261686812e-05, "loss": 0.9817, "step": 13980 }, { "epoch": 0.7643806594908594, "grad_norm": 2.026423692703247, "learning_rate": 1.3873894814870403e-05, "loss": 1.0454, "step": 13981 }, { "epoch": 0.764435332308218, "grad_norm": 3.1459672451019287, "learning_rate": 1.386777450075617e-05, "loss": 1.14, "step": 13982 }, { "epoch": 0.7644900051255766, "grad_norm": 3.9848461151123047, "learning_rate": 1.386165531953602e-05, "loss": 1.0677, "step": 13983 }, { "epoch": 0.7645446779429352, "grad_norm": 2.453705072402954, "learning_rate": 1.3855537271401809e-05, "loss": 0.9539, "step": 13984 }, { "epoch": 0.7645993507602938, "grad_norm": 2.419663429260254, "learning_rate": 1.3849420356545356e-05, "loss": 1.0094, "step": 13985 }, { "epoch": 0.7646540235776524, "grad_norm": 2.9864275455474854, "learning_rate": 1.3843304575158467e-05, "loss": 1.1424, "step": 13986 }, { "epoch": 0.7647086963950112, "grad_norm": 3.023198366165161, "learning_rate": 1.3837189927432881e-05, "loss": 1.1347, "step": 13987 }, { "epoch": 0.7647633692123698, "grad_norm": 2.469236135482788, "learning_rate": 1.383107641356033e-05, "loss": 1.0838, "step": 13988 }, { "epoch": 0.7648180420297284, "grad_norm": 2.3820459842681885, "learning_rate": 1.3824964033732474e-05, "loss": 0.9596, "step": 13989 }, { "epoch": 0.764872714847087, "grad_norm": 2.6902360916137695, "learning_rate": 1.3818852788140996e-05, "loss": 1.0093, "step": 13990 }, { "epoch": 0.7649273876644456, "grad_norm": 2.454867124557495, "learning_rate": 1.3812742676977497e-05, "loss": 1.1064, "step": 13991 }, { "epoch": 0.7649820604818042, "grad_norm": 3.1443161964416504, "learning_rate": 1.3806633700433546e-05, "loss": 1.0649, "step": 13992 }, { "epoch": 0.7650367332991628, "grad_norm": 2.4855806827545166, "learning_rate": 1.3800525858700687e-05, "loss": 0.873, "step": 13993 }, { "epoch": 0.7650914061165215, "grad_norm": 2.226555824279785, "learning_rate": 1.3794419151970428e-05, "loss": 0.9665, "step": 13994 }, { "epoch": 0.7651460789338801, "grad_norm": 2.552560806274414, "learning_rate": 1.3788313580434242e-05, "loss": 1.0606, "step": 13995 }, { "epoch": 0.7652007517512387, "grad_norm": 3.3494205474853516, "learning_rate": 1.378220914428356e-05, "loss": 0.8906, "step": 13996 }, { "epoch": 0.7652554245685973, "grad_norm": 3.415768623352051, "learning_rate": 1.377610584370978e-05, "loss": 1.189, "step": 13997 }, { "epoch": 0.7653100973859559, "grad_norm": 3.083601713180542, "learning_rate": 1.3770003678904265e-05, "loss": 1.2576, "step": 13998 }, { "epoch": 0.7653647702033145, "grad_norm": 2.0896565914154053, "learning_rate": 1.376390265005833e-05, "loss": 0.8774, "step": 13999 }, { "epoch": 0.7654194430206731, "grad_norm": 2.1611976623535156, "learning_rate": 1.3757802757363303e-05, "loss": 0.7717, "step": 14000 }, { "epoch": 0.7654741158380318, "grad_norm": 2.575249671936035, "learning_rate": 1.3751704001010419e-05, "loss": 1.174, "step": 14001 }, { "epoch": 0.7655287886553904, "grad_norm": 2.479749917984009, "learning_rate": 1.37456063811909e-05, "loss": 0.9764, "step": 14002 }, { "epoch": 0.765583461472749, "grad_norm": 2.7539167404174805, "learning_rate": 1.3739509898095931e-05, "loss": 1.0565, "step": 14003 }, { "epoch": 0.7656381342901076, "grad_norm": 2.1908349990844727, "learning_rate": 1.3733414551916668e-05, "loss": 0.9279, "step": 14004 }, { "epoch": 0.7656928071074662, "grad_norm": 2.835941791534424, "learning_rate": 1.3727320342844213e-05, "loss": 0.9909, "step": 14005 }, { "epoch": 0.7657474799248248, "grad_norm": 2.6789841651916504, "learning_rate": 1.372122727106966e-05, "loss": 1.1139, "step": 14006 }, { "epoch": 0.7658021527421836, "grad_norm": 2.3818368911743164, "learning_rate": 1.3715135336784035e-05, "loss": 0.9959, "step": 14007 }, { "epoch": 0.7658568255595422, "grad_norm": 2.728410243988037, "learning_rate": 1.3709044540178356e-05, "loss": 1.2173, "step": 14008 }, { "epoch": 0.7659114983769008, "grad_norm": 2.7764949798583984, "learning_rate": 1.3702954881443581e-05, "loss": 1.0167, "step": 14009 }, { "epoch": 0.7659661711942594, "grad_norm": 2.185671091079712, "learning_rate": 1.3696866360770671e-05, "loss": 0.973, "step": 14010 }, { "epoch": 0.766020844011618, "grad_norm": 3.0764238834381104, "learning_rate": 1.3690778978350516e-05, "loss": 1.1115, "step": 14011 }, { "epoch": 0.7660755168289766, "grad_norm": 2.05844783782959, "learning_rate": 1.3684692734373972e-05, "loss": 1.0948, "step": 14012 }, { "epoch": 0.7661301896463352, "grad_norm": 2.5946295261383057, "learning_rate": 1.3678607629031875e-05, "loss": 0.7589, "step": 14013 }, { "epoch": 0.7661848624636939, "grad_norm": 2.9506454467773438, "learning_rate": 1.3672523662515013e-05, "loss": 1.0396, "step": 14014 }, { "epoch": 0.7662395352810525, "grad_norm": 2.392972469329834, "learning_rate": 1.3666440835014149e-05, "loss": 0.9868, "step": 14015 }, { "epoch": 0.7662942080984111, "grad_norm": 2.3047313690185547, "learning_rate": 1.3660359146720003e-05, "loss": 1.098, "step": 14016 }, { "epoch": 0.7663488809157697, "grad_norm": 2.56172776222229, "learning_rate": 1.3654278597823256e-05, "loss": 1.1776, "step": 14017 }, { "epoch": 0.7664035537331283, "grad_norm": 2.5841245651245117, "learning_rate": 1.3648199188514565e-05, "loss": 0.8132, "step": 14018 }, { "epoch": 0.7664582265504869, "grad_norm": 2.7783403396606445, "learning_rate": 1.364212091898453e-05, "loss": 1.0086, "step": 14019 }, { "epoch": 0.7665128993678455, "grad_norm": 2.7862167358398438, "learning_rate": 1.3636043789423752e-05, "loss": 1.0701, "step": 14020 }, { "epoch": 0.7665675721852042, "grad_norm": 2.7270286083221436, "learning_rate": 1.3629967800022764e-05, "loss": 1.0946, "step": 14021 }, { "epoch": 0.7666222450025628, "grad_norm": 2.8764219284057617, "learning_rate": 1.3623892950972079e-05, "loss": 1.0829, "step": 14022 }, { "epoch": 0.7666769178199214, "grad_norm": 2.850161075592041, "learning_rate": 1.3617819242462153e-05, "loss": 0.9626, "step": 14023 }, { "epoch": 0.76673159063728, "grad_norm": 2.431230306625366, "learning_rate": 1.3611746674683435e-05, "loss": 0.9719, "step": 14024 }, { "epoch": 0.7667862634546386, "grad_norm": 3.7650816440582275, "learning_rate": 1.3605675247826322e-05, "loss": 1.2039, "step": 14025 }, { "epoch": 0.7668409362719972, "grad_norm": 2.161651372909546, "learning_rate": 1.359960496208118e-05, "loss": 0.8891, "step": 14026 }, { "epoch": 0.7668956090893558, "grad_norm": 2.367830514907837, "learning_rate": 1.3593535817638331e-05, "loss": 0.7129, "step": 14027 }, { "epoch": 0.7669502819067145, "grad_norm": 2.7562432289123535, "learning_rate": 1.3587467814688076e-05, "loss": 1.0069, "step": 14028 }, { "epoch": 0.7670049547240732, "grad_norm": 3.1551754474639893, "learning_rate": 1.3581400953420648e-05, "loss": 0.8613, "step": 14029 }, { "epoch": 0.7670596275414318, "grad_norm": 2.7708892822265625, "learning_rate": 1.3575335234026304e-05, "loss": 1.0152, "step": 14030 }, { "epoch": 0.7671143003587904, "grad_norm": 2.205470323562622, "learning_rate": 1.3569270656695215e-05, "loss": 0.9365, "step": 14031 }, { "epoch": 0.767168973176149, "grad_norm": 2.3799355030059814, "learning_rate": 1.3563207221617524e-05, "loss": 1.0017, "step": 14032 }, { "epoch": 0.7672236459935076, "grad_norm": 2.296449899673462, "learning_rate": 1.3557144928983356e-05, "loss": 0.992, "step": 14033 }, { "epoch": 0.7672783188108663, "grad_norm": 2.6208577156066895, "learning_rate": 1.3551083778982776e-05, "loss": 0.9157, "step": 14034 }, { "epoch": 0.7673329916282249, "grad_norm": 2.1091256141662598, "learning_rate": 1.3545023771805831e-05, "loss": 0.8993, "step": 14035 }, { "epoch": 0.7673876644455835, "grad_norm": 1.9896224737167358, "learning_rate": 1.3538964907642532e-05, "loss": 1.0296, "step": 14036 }, { "epoch": 0.7674423372629421, "grad_norm": 2.57271671295166, "learning_rate": 1.3532907186682848e-05, "loss": 0.9688, "step": 14037 }, { "epoch": 0.7674970100803007, "grad_norm": 2.917086124420166, "learning_rate": 1.3526850609116704e-05, "loss": 0.9338, "step": 14038 }, { "epoch": 0.7675516828976593, "grad_norm": 2.2523691654205322, "learning_rate": 1.3520795175133993e-05, "loss": 1.0397, "step": 14039 }, { "epoch": 0.7676063557150179, "grad_norm": 2.3717010021209717, "learning_rate": 1.3514740884924604e-05, "loss": 0.9198, "step": 14040 }, { "epoch": 0.7676610285323766, "grad_norm": 2.9532599449157715, "learning_rate": 1.3508687738678356e-05, "loss": 0.8893, "step": 14041 }, { "epoch": 0.7677157013497352, "grad_norm": 2.9408931732177734, "learning_rate": 1.3502635736585029e-05, "loss": 0.9333, "step": 14042 }, { "epoch": 0.7677703741670938, "grad_norm": 3.4959986209869385, "learning_rate": 1.3496584878834384e-05, "loss": 1.1002, "step": 14043 }, { "epoch": 0.7678250469844524, "grad_norm": 2.988168478012085, "learning_rate": 1.3490535165616142e-05, "loss": 1.1096, "step": 14044 }, { "epoch": 0.767879719801811, "grad_norm": 2.265249252319336, "learning_rate": 1.3484486597119984e-05, "loss": 1.0457, "step": 14045 }, { "epoch": 0.7679343926191696, "grad_norm": 2.3100788593292236, "learning_rate": 1.3478439173535556e-05, "loss": 1.0701, "step": 14046 }, { "epoch": 0.7679890654365282, "grad_norm": 3.045563220977783, "learning_rate": 1.3472392895052471e-05, "loss": 0.8767, "step": 14047 }, { "epoch": 0.7680437382538869, "grad_norm": 2.428858757019043, "learning_rate": 1.3466347761860293e-05, "loss": 1.015, "step": 14048 }, { "epoch": 0.7680984110712455, "grad_norm": 3.0974910259246826, "learning_rate": 1.3460303774148587e-05, "loss": 1.0857, "step": 14049 }, { "epoch": 0.7681530838886041, "grad_norm": 2.8438851833343506, "learning_rate": 1.3454260932106844e-05, "loss": 1.0775, "step": 14050 }, { "epoch": 0.7682077567059628, "grad_norm": 2.523676872253418, "learning_rate": 1.344821923592453e-05, "loss": 0.8891, "step": 14051 }, { "epoch": 0.7682624295233214, "grad_norm": 3.169914960861206, "learning_rate": 1.3442178685791084e-05, "loss": 1.106, "step": 14052 }, { "epoch": 0.76831710234068, "grad_norm": 2.48053240776062, "learning_rate": 1.3436139281895894e-05, "loss": 1.0081, "step": 14053 }, { "epoch": 0.7683717751580386, "grad_norm": 2.958273410797119, "learning_rate": 1.3430101024428327e-05, "loss": 0.9953, "step": 14054 }, { "epoch": 0.7684264479753973, "grad_norm": 2.935276985168457, "learning_rate": 1.34240639135777e-05, "loss": 1.0236, "step": 14055 }, { "epoch": 0.7684811207927559, "grad_norm": 3.6085829734802246, "learning_rate": 1.3418027949533302e-05, "loss": 0.8464, "step": 14056 }, { "epoch": 0.7685357936101145, "grad_norm": 2.6292688846588135, "learning_rate": 1.341199313248439e-05, "loss": 0.8908, "step": 14057 }, { "epoch": 0.7685904664274731, "grad_norm": 2.3930580615997314, "learning_rate": 1.3405959462620166e-05, "loss": 0.8748, "step": 14058 }, { "epoch": 0.7686451392448317, "grad_norm": 3.2000064849853516, "learning_rate": 1.3399926940129837e-05, "loss": 1.0594, "step": 14059 }, { "epoch": 0.7686998120621903, "grad_norm": 2.7435896396636963, "learning_rate": 1.3393895565202536e-05, "loss": 1.0593, "step": 14060 }, { "epoch": 0.7687544848795489, "grad_norm": 2.24101185798645, "learning_rate": 1.3387865338027361e-05, "loss": 1.1119, "step": 14061 }, { "epoch": 0.7688091576969076, "grad_norm": 2.2149908542633057, "learning_rate": 1.3381836258793402e-05, "loss": 1.0671, "step": 14062 }, { "epoch": 0.7688638305142662, "grad_norm": 2.89339017868042, "learning_rate": 1.3375808327689676e-05, "loss": 1.1431, "step": 14063 }, { "epoch": 0.7689185033316248, "grad_norm": 2.19675350189209, "learning_rate": 1.3369781544905197e-05, "loss": 0.9926, "step": 14064 }, { "epoch": 0.7689731761489834, "grad_norm": 2.9441776275634766, "learning_rate": 1.3363755910628927e-05, "loss": 1.0982, "step": 14065 }, { "epoch": 0.769027848966342, "grad_norm": 2.2773094177246094, "learning_rate": 1.335773142504979e-05, "loss": 1.0563, "step": 14066 }, { "epoch": 0.7690825217837006, "grad_norm": 3.474194049835205, "learning_rate": 1.3351708088356685e-05, "loss": 1.1689, "step": 14067 }, { "epoch": 0.7691371946010593, "grad_norm": 3.57145357131958, "learning_rate": 1.3345685900738452e-05, "loss": 1.1678, "step": 14068 }, { "epoch": 0.7691918674184179, "grad_norm": 2.59653639793396, "learning_rate": 1.3339664862383932e-05, "loss": 1.2003, "step": 14069 }, { "epoch": 0.7692465402357765, "grad_norm": 2.7563655376434326, "learning_rate": 1.3333644973481908e-05, "loss": 1.2475, "step": 14070 }, { "epoch": 0.7693012130531351, "grad_norm": 3.4063470363616943, "learning_rate": 1.3327626234221119e-05, "loss": 1.0851, "step": 14071 }, { "epoch": 0.7693558858704937, "grad_norm": 2.868192195892334, "learning_rate": 1.3321608644790278e-05, "loss": 0.9398, "step": 14072 }, { "epoch": 0.7694105586878524, "grad_norm": 2.0740225315093994, "learning_rate": 1.331559220537807e-05, "loss": 0.9566, "step": 14073 }, { "epoch": 0.769465231505211, "grad_norm": 2.281644821166992, "learning_rate": 1.3309576916173123e-05, "loss": 0.9987, "step": 14074 }, { "epoch": 0.7695199043225697, "grad_norm": 1.986656665802002, "learning_rate": 1.3303562777364049e-05, "loss": 0.9921, "step": 14075 }, { "epoch": 0.7695745771399283, "grad_norm": 4.053314208984375, "learning_rate": 1.3297549789139413e-05, "loss": 1.0383, "step": 14076 }, { "epoch": 0.7696292499572869, "grad_norm": 2.5462167263031006, "learning_rate": 1.329153795168775e-05, "loss": 1.0843, "step": 14077 }, { "epoch": 0.7696839227746455, "grad_norm": 2.1784462928771973, "learning_rate": 1.3285527265197534e-05, "loss": 0.8974, "step": 14078 }, { "epoch": 0.7697385955920041, "grad_norm": 2.5314910411834717, "learning_rate": 1.327951772985726e-05, "loss": 0.9597, "step": 14079 }, { "epoch": 0.7697932684093627, "grad_norm": 3.55694842338562, "learning_rate": 1.327350934585534e-05, "loss": 0.9737, "step": 14080 }, { "epoch": 0.7698479412267213, "grad_norm": 2.399404287338257, "learning_rate": 1.3267502113380154e-05, "loss": 1.0224, "step": 14081 }, { "epoch": 0.76990261404408, "grad_norm": 2.827826499938965, "learning_rate": 1.3261496032620058e-05, "loss": 0.8967, "step": 14082 }, { "epoch": 0.7699572868614386, "grad_norm": 2.539834976196289, "learning_rate": 1.3255491103763368e-05, "loss": 0.94, "step": 14083 }, { "epoch": 0.7700119596787972, "grad_norm": 2.839069128036499, "learning_rate": 1.324948732699836e-05, "loss": 0.9056, "step": 14084 }, { "epoch": 0.7700666324961558, "grad_norm": 3.447113037109375, "learning_rate": 1.3243484702513276e-05, "loss": 1.1039, "step": 14085 }, { "epoch": 0.7701213053135144, "grad_norm": 2.4861059188842773, "learning_rate": 1.3237483230496329e-05, "loss": 0.8996, "step": 14086 }, { "epoch": 0.770175978130873, "grad_norm": 2.7443196773529053, "learning_rate": 1.323148291113569e-05, "loss": 0.9274, "step": 14087 }, { "epoch": 0.7702306509482316, "grad_norm": 2.1349122524261475, "learning_rate": 1.3225483744619472e-05, "loss": 1.0095, "step": 14088 }, { "epoch": 0.7702853237655903, "grad_norm": 2.303983449935913, "learning_rate": 1.3219485731135806e-05, "loss": 0.9104, "step": 14089 }, { "epoch": 0.7703399965829489, "grad_norm": 2.8385684490203857, "learning_rate": 1.3213488870872737e-05, "loss": 1.0687, "step": 14090 }, { "epoch": 0.7703946694003075, "grad_norm": 2.8152976036071777, "learning_rate": 1.3207493164018297e-05, "loss": 0.9761, "step": 14091 }, { "epoch": 0.7704493422176661, "grad_norm": 3.8429758548736572, "learning_rate": 1.3201498610760476e-05, "loss": 1.0889, "step": 14092 }, { "epoch": 0.7705040150350247, "grad_norm": 2.1713054180145264, "learning_rate": 1.3195505211287229e-05, "loss": 0.9939, "step": 14093 }, { "epoch": 0.7705586878523834, "grad_norm": 2.546319007873535, "learning_rate": 1.3189512965786466e-05, "loss": 0.9562, "step": 14094 }, { "epoch": 0.7706133606697421, "grad_norm": 2.353167772293091, "learning_rate": 1.318352187444607e-05, "loss": 1.1088, "step": 14095 }, { "epoch": 0.7706680334871007, "grad_norm": 4.703633785247803, "learning_rate": 1.3177531937453896e-05, "loss": 0.9899, "step": 14096 }, { "epoch": 0.7707227063044593, "grad_norm": 2.32779860496521, "learning_rate": 1.3171543154997729e-05, "loss": 0.9996, "step": 14097 }, { "epoch": 0.7707773791218179, "grad_norm": 2.624629497528076, "learning_rate": 1.3165555527265372e-05, "loss": 1.2023, "step": 14098 }, { "epoch": 0.7708320519391765, "grad_norm": 2.93255615234375, "learning_rate": 1.3159569054444547e-05, "loss": 1.0394, "step": 14099 }, { "epoch": 0.7708867247565351, "grad_norm": 2.887793779373169, "learning_rate": 1.3153583736722963e-05, "loss": 1.2422, "step": 14100 }, { "epoch": 0.7709413975738937, "grad_norm": 2.977325201034546, "learning_rate": 1.3147599574288277e-05, "loss": 1.2075, "step": 14101 }, { "epoch": 0.7709960703912524, "grad_norm": 2.33796763420105, "learning_rate": 1.314161656732812e-05, "loss": 0.9366, "step": 14102 }, { "epoch": 0.771050743208611, "grad_norm": 2.5270068645477295, "learning_rate": 1.3135634716030076e-05, "loss": 1.0627, "step": 14103 }, { "epoch": 0.7711054160259696, "grad_norm": 2.470066547393799, "learning_rate": 1.3129654020581711e-05, "loss": 1.0347, "step": 14104 }, { "epoch": 0.7711600888433282, "grad_norm": 2.483599901199341, "learning_rate": 1.3123674481170545e-05, "loss": 1.1055, "step": 14105 }, { "epoch": 0.7712147616606868, "grad_norm": 3.1909914016723633, "learning_rate": 1.311769609798405e-05, "loss": 1.2179, "step": 14106 }, { "epoch": 0.7712694344780454, "grad_norm": 3.856968641281128, "learning_rate": 1.3111718871209666e-05, "loss": 0.9608, "step": 14107 }, { "epoch": 0.771324107295404, "grad_norm": 2.595964193344116, "learning_rate": 1.3105742801034832e-05, "loss": 1.2067, "step": 14108 }, { "epoch": 0.7713787801127627, "grad_norm": 1.9497746229171753, "learning_rate": 1.3099767887646907e-05, "loss": 0.8754, "step": 14109 }, { "epoch": 0.7714334529301213, "grad_norm": 2.347907304763794, "learning_rate": 1.3093794131233234e-05, "loss": 0.8644, "step": 14110 }, { "epoch": 0.7714881257474799, "grad_norm": 2.915674924850464, "learning_rate": 1.3087821531981109e-05, "loss": 0.9309, "step": 14111 }, { "epoch": 0.7715427985648385, "grad_norm": 2.6876161098480225, "learning_rate": 1.3081850090077796e-05, "loss": 1.193, "step": 14112 }, { "epoch": 0.7715974713821971, "grad_norm": 2.4792158603668213, "learning_rate": 1.3075879805710534e-05, "loss": 0.9476, "step": 14113 }, { "epoch": 0.7716521441995557, "grad_norm": 2.7471187114715576, "learning_rate": 1.3069910679066504e-05, "loss": 1.0674, "step": 14114 }, { "epoch": 0.7717068170169143, "grad_norm": 2.985450267791748, "learning_rate": 1.3063942710332867e-05, "loss": 1.1512, "step": 14115 }, { "epoch": 0.7717614898342731, "grad_norm": 3.5876994132995605, "learning_rate": 1.305797589969675e-05, "loss": 0.9371, "step": 14116 }, { "epoch": 0.7718161626516317, "grad_norm": 2.37509822845459, "learning_rate": 1.3052010247345225e-05, "loss": 1.0266, "step": 14117 }, { "epoch": 0.7718708354689903, "grad_norm": 2.7509617805480957, "learning_rate": 1.3046045753465336e-05, "loss": 1.2116, "step": 14118 }, { "epoch": 0.7719255082863489, "grad_norm": 2.8825037479400635, "learning_rate": 1.304008241824412e-05, "loss": 1.0412, "step": 14119 }, { "epoch": 0.7719801811037075, "grad_norm": 2.6816375255584717, "learning_rate": 1.3034120241868536e-05, "loss": 1.1498, "step": 14120 }, { "epoch": 0.7720348539210661, "grad_norm": 2.4346652030944824, "learning_rate": 1.3028159224525527e-05, "loss": 1.2961, "step": 14121 }, { "epoch": 0.7720895267384248, "grad_norm": 2.0547688007354736, "learning_rate": 1.3022199366401988e-05, "loss": 0.9026, "step": 14122 }, { "epoch": 0.7721441995557834, "grad_norm": 2.435445547103882, "learning_rate": 1.3016240667684793e-05, "loss": 1.0488, "step": 14123 }, { "epoch": 0.772198872373142, "grad_norm": 2.6348538398742676, "learning_rate": 1.3010283128560763e-05, "loss": 1.0179, "step": 14124 }, { "epoch": 0.7722535451905006, "grad_norm": 2.5259861946105957, "learning_rate": 1.30043267492167e-05, "loss": 0.8679, "step": 14125 }, { "epoch": 0.7723082180078592, "grad_norm": 3.9306066036224365, "learning_rate": 1.2998371529839359e-05, "loss": 1.1925, "step": 14126 }, { "epoch": 0.7723628908252178, "grad_norm": 2.6490440368652344, "learning_rate": 1.2992417470615459e-05, "loss": 0.897, "step": 14127 }, { "epoch": 0.7724175636425764, "grad_norm": 2.9525883197784424, "learning_rate": 1.2986464571731683e-05, "loss": 0.9603, "step": 14128 }, { "epoch": 0.7724722364599351, "grad_norm": 2.5102672576904297, "learning_rate": 1.298051283337468e-05, "loss": 0.9767, "step": 14129 }, { "epoch": 0.7725269092772937, "grad_norm": 2.5278310775756836, "learning_rate": 1.297456225573106e-05, "loss": 0.9914, "step": 14130 }, { "epoch": 0.7725815820946523, "grad_norm": 2.6740047931671143, "learning_rate": 1.2968612838987387e-05, "loss": 0.9962, "step": 14131 }, { "epoch": 0.7726362549120109, "grad_norm": 2.4294416904449463, "learning_rate": 1.296266458333023e-05, "loss": 0.9025, "step": 14132 }, { "epoch": 0.7726909277293695, "grad_norm": 2.896888256072998, "learning_rate": 1.2956717488946075e-05, "loss": 0.8128, "step": 14133 }, { "epoch": 0.7727456005467281, "grad_norm": 2.2721681594848633, "learning_rate": 1.2950771556021379e-05, "loss": 0.9533, "step": 14134 }, { "epoch": 0.7728002733640867, "grad_norm": 2.678513765335083, "learning_rate": 1.2944826784742586e-05, "loss": 1.0486, "step": 14135 }, { "epoch": 0.7728549461814455, "grad_norm": 2.3453524112701416, "learning_rate": 1.293888317529608e-05, "loss": 1.0972, "step": 14136 }, { "epoch": 0.7729096189988041, "grad_norm": 2.30438494682312, "learning_rate": 1.2932940727868221e-05, "loss": 0.9151, "step": 14137 }, { "epoch": 0.7729642918161627, "grad_norm": 3.7824621200561523, "learning_rate": 1.2926999442645326e-05, "loss": 0.7963, "step": 14138 }, { "epoch": 0.7730189646335213, "grad_norm": 2.5715298652648926, "learning_rate": 1.2921059319813688e-05, "loss": 0.9352, "step": 14139 }, { "epoch": 0.7730736374508799, "grad_norm": 2.6740877628326416, "learning_rate": 1.291512035955954e-05, "loss": 0.9247, "step": 14140 }, { "epoch": 0.7731283102682385, "grad_norm": 2.9978339672088623, "learning_rate": 1.2909182562069106e-05, "loss": 1.2688, "step": 14141 }, { "epoch": 0.7731829830855971, "grad_norm": 3.5863492488861084, "learning_rate": 1.2903245927528552e-05, "loss": 1.0726, "step": 14142 }, { "epoch": 0.7732376559029558, "grad_norm": 3.071641445159912, "learning_rate": 1.2897310456124018e-05, "loss": 0.7458, "step": 14143 }, { "epoch": 0.7732923287203144, "grad_norm": 2.3015222549438477, "learning_rate": 1.289137614804159e-05, "loss": 1.0184, "step": 14144 }, { "epoch": 0.773347001537673, "grad_norm": 2.9260165691375732, "learning_rate": 1.2885443003467368e-05, "loss": 1.051, "step": 14145 }, { "epoch": 0.7734016743550316, "grad_norm": 2.474536895751953, "learning_rate": 1.2879511022587354e-05, "loss": 0.8592, "step": 14146 }, { "epoch": 0.7734563471723902, "grad_norm": 2.1978261470794678, "learning_rate": 1.2873580205587555e-05, "loss": 0.9338, "step": 14147 }, { "epoch": 0.7735110199897488, "grad_norm": 3.208782196044922, "learning_rate": 1.2867650552653914e-05, "loss": 1.1764, "step": 14148 }, { "epoch": 0.7735656928071075, "grad_norm": 2.1831109523773193, "learning_rate": 1.286172206397236e-05, "loss": 0.9988, "step": 14149 }, { "epoch": 0.7736203656244661, "grad_norm": 2.2812464237213135, "learning_rate": 1.2855794739728772e-05, "loss": 0.8811, "step": 14150 }, { "epoch": 0.7736750384418247, "grad_norm": 2.4823129177093506, "learning_rate": 1.2849868580108987e-05, "loss": 1.0074, "step": 14151 }, { "epoch": 0.7737297112591833, "grad_norm": 3.2209761142730713, "learning_rate": 1.2843943585298828e-05, "loss": 0.8068, "step": 14152 }, { "epoch": 0.7737843840765419, "grad_norm": 3.0931761264801025, "learning_rate": 1.283801975548406e-05, "loss": 0.8968, "step": 14153 }, { "epoch": 0.7738390568939005, "grad_norm": 2.7456727027893066, "learning_rate": 1.2832097090850425e-05, "loss": 0.8569, "step": 14154 }, { "epoch": 0.7738937297112591, "grad_norm": 2.37078595161438, "learning_rate": 1.2826175591583617e-05, "loss": 1.0136, "step": 14155 }, { "epoch": 0.7739484025286179, "grad_norm": 2.5690863132476807, "learning_rate": 1.2820255257869291e-05, "loss": 0.967, "step": 14156 }, { "epoch": 0.7740030753459765, "grad_norm": 3.3174755573272705, "learning_rate": 1.2814336089893091e-05, "loss": 1.1364, "step": 14157 }, { "epoch": 0.7740577481633351, "grad_norm": 2.6681478023529053, "learning_rate": 1.2808418087840607e-05, "loss": 0.9918, "step": 14158 }, { "epoch": 0.7741124209806937, "grad_norm": 2.503267288208008, "learning_rate": 1.2802501251897386e-05, "loss": 1.0066, "step": 14159 }, { "epoch": 0.7741670937980523, "grad_norm": 3.073838949203491, "learning_rate": 1.2796585582248948e-05, "loss": 0.9302, "step": 14160 }, { "epoch": 0.7742217666154109, "grad_norm": 2.231832981109619, "learning_rate": 1.2790671079080773e-05, "loss": 1.0395, "step": 14161 }, { "epoch": 0.7742764394327695, "grad_norm": 2.698711633682251, "learning_rate": 1.2784757742578302e-05, "loss": 0.9213, "step": 14162 }, { "epoch": 0.7743311122501282, "grad_norm": 2.5155365467071533, "learning_rate": 1.277884557292694e-05, "loss": 0.9679, "step": 14163 }, { "epoch": 0.7743857850674868, "grad_norm": 3.220533847808838, "learning_rate": 1.2772934570312068e-05, "loss": 1.0797, "step": 14164 }, { "epoch": 0.7744404578848454, "grad_norm": 2.300043821334839, "learning_rate": 1.2767024734919008e-05, "loss": 1.1261, "step": 14165 }, { "epoch": 0.774495130702204, "grad_norm": 3.5064620971679688, "learning_rate": 1.2761116066933054e-05, "loss": 1.0778, "step": 14166 }, { "epoch": 0.7745498035195626, "grad_norm": 2.7861337661743164, "learning_rate": 1.2755208566539489e-05, "loss": 1.09, "step": 14167 }, { "epoch": 0.7746044763369212, "grad_norm": 3.112344741821289, "learning_rate": 1.2749302233923528e-05, "loss": 1.1701, "step": 14168 }, { "epoch": 0.7746591491542798, "grad_norm": 2.3445794582366943, "learning_rate": 1.2743397069270357e-05, "loss": 1.0179, "step": 14169 }, { "epoch": 0.7747138219716385, "grad_norm": 2.5174291133880615, "learning_rate": 1.2737493072765128e-05, "loss": 1.0046, "step": 14170 }, { "epoch": 0.7747684947889971, "grad_norm": 2.0711724758148193, "learning_rate": 1.273159024459295e-05, "loss": 0.9253, "step": 14171 }, { "epoch": 0.7748231676063557, "grad_norm": 3.13870906829834, "learning_rate": 1.2725688584938905e-05, "loss": 1.0722, "step": 14172 }, { "epoch": 0.7748778404237143, "grad_norm": 3.1472957134246826, "learning_rate": 1.2719788093988038e-05, "loss": 1.1004, "step": 14173 }, { "epoch": 0.7749325132410729, "grad_norm": 2.697669744491577, "learning_rate": 1.2713888771925347e-05, "loss": 1.0888, "step": 14174 }, { "epoch": 0.7749871860584315, "grad_norm": 2.175327777862549, "learning_rate": 1.2707990618935806e-05, "loss": 0.9518, "step": 14175 }, { "epoch": 0.7750418588757902, "grad_norm": 2.668721914291382, "learning_rate": 1.2702093635204326e-05, "loss": 0.9784, "step": 14176 }, { "epoch": 0.7750965316931488, "grad_norm": 2.4207677841186523, "learning_rate": 1.2696197820915839e-05, "loss": 1.0014, "step": 14177 }, { "epoch": 0.7751512045105075, "grad_norm": 3.0596325397491455, "learning_rate": 1.269030317625518e-05, "loss": 1.0535, "step": 14178 }, { "epoch": 0.775205877327866, "grad_norm": 2.4352669715881348, "learning_rate": 1.2684409701407173e-05, "loss": 1.0648, "step": 14179 }, { "epoch": 0.7752605501452247, "grad_norm": 2.181002616882324, "learning_rate": 1.2678517396556605e-05, "loss": 0.9039, "step": 14180 }, { "epoch": 0.7753152229625833, "grad_norm": 2.471205949783325, "learning_rate": 1.267262626188822e-05, "loss": 1.1634, "step": 14181 }, { "epoch": 0.7753698957799419, "grad_norm": 2.221444845199585, "learning_rate": 1.2666736297586734e-05, "loss": 0.9385, "step": 14182 }, { "epoch": 0.7754245685973006, "grad_norm": 2.296884536743164, "learning_rate": 1.266084750383682e-05, "loss": 0.979, "step": 14183 }, { "epoch": 0.7754792414146592, "grad_norm": 2.3345508575439453, "learning_rate": 1.2654959880823119e-05, "loss": 1.1859, "step": 14184 }, { "epoch": 0.7755339142320178, "grad_norm": 2.8764328956604004, "learning_rate": 1.2649073428730224e-05, "loss": 1.146, "step": 14185 }, { "epoch": 0.7755885870493764, "grad_norm": 2.301928997039795, "learning_rate": 1.264318814774269e-05, "loss": 0.9396, "step": 14186 }, { "epoch": 0.775643259866735, "grad_norm": 2.5097291469573975, "learning_rate": 1.2637304038045079e-05, "loss": 1.1075, "step": 14187 }, { "epoch": 0.7756979326840936, "grad_norm": 2.1021358966827393, "learning_rate": 1.2631421099821855e-05, "loss": 0.9689, "step": 14188 }, { "epoch": 0.7757526055014522, "grad_norm": 3.2524712085723877, "learning_rate": 1.262553933325748e-05, "loss": 1.0058, "step": 14189 }, { "epoch": 0.7758072783188109, "grad_norm": 2.439317464828491, "learning_rate": 1.2619658738536372e-05, "loss": 0.8381, "step": 14190 }, { "epoch": 0.7758619511361695, "grad_norm": 2.624206304550171, "learning_rate": 1.2613779315842916e-05, "loss": 1.1278, "step": 14191 }, { "epoch": 0.7759166239535281, "grad_norm": 2.4121522903442383, "learning_rate": 1.2607901065361444e-05, "loss": 0.8869, "step": 14192 }, { "epoch": 0.7759712967708867, "grad_norm": 2.7034876346588135, "learning_rate": 1.2602023987276274e-05, "loss": 0.9151, "step": 14193 }, { "epoch": 0.7760259695882453, "grad_norm": 2.30360746383667, "learning_rate": 1.2596148081771676e-05, "loss": 0.9426, "step": 14194 }, { "epoch": 0.7760806424056039, "grad_norm": 2.5167315006256104, "learning_rate": 1.2590273349031872e-05, "loss": 1.0668, "step": 14195 }, { "epoch": 0.7761353152229625, "grad_norm": 2.9563591480255127, "learning_rate": 1.2584399789241058e-05, "loss": 0.8606, "step": 14196 }, { "epoch": 0.7761899880403212, "grad_norm": 2.979649543762207, "learning_rate": 1.2578527402583424e-05, "loss": 0.9557, "step": 14197 }, { "epoch": 0.7762446608576798, "grad_norm": 3.5225071907043457, "learning_rate": 1.2572656189243065e-05, "loss": 1.1054, "step": 14198 }, { "epoch": 0.7762993336750384, "grad_norm": 2.820856809616089, "learning_rate": 1.256678614940408e-05, "loss": 1.0217, "step": 14199 }, { "epoch": 0.776354006492397, "grad_norm": 2.3688673973083496, "learning_rate": 1.2560917283250518e-05, "loss": 0.916, "step": 14200 }, { "epoch": 0.7764086793097557, "grad_norm": 3.568598747253418, "learning_rate": 1.2555049590966383e-05, "loss": 1.1341, "step": 14201 }, { "epoch": 0.7764633521271143, "grad_norm": 2.600299835205078, "learning_rate": 1.2549183072735665e-05, "loss": 0.9507, "step": 14202 }, { "epoch": 0.776518024944473, "grad_norm": 2.6328537464141846, "learning_rate": 1.2543317728742293e-05, "loss": 1.0008, "step": 14203 }, { "epoch": 0.7765726977618316, "grad_norm": 2.733224868774414, "learning_rate": 1.2537453559170175e-05, "loss": 1.1052, "step": 14204 }, { "epoch": 0.7766273705791902, "grad_norm": 2.4219813346862793, "learning_rate": 1.2531590564203155e-05, "loss": 0.8347, "step": 14205 }, { "epoch": 0.7766820433965488, "grad_norm": 2.447277784347534, "learning_rate": 1.25257287440251e-05, "loss": 1.0307, "step": 14206 }, { "epoch": 0.7767367162139074, "grad_norm": 2.8740603923797607, "learning_rate": 1.2519868098819788e-05, "loss": 1.0888, "step": 14207 }, { "epoch": 0.776791389031266, "grad_norm": 2.4255290031433105, "learning_rate": 1.2514008628770962e-05, "loss": 0.9701, "step": 14208 }, { "epoch": 0.7768460618486246, "grad_norm": 3.154386043548584, "learning_rate": 1.2508150334062357e-05, "loss": 0.8867, "step": 14209 }, { "epoch": 0.7769007346659833, "grad_norm": 2.4732022285461426, "learning_rate": 1.2502293214877642e-05, "loss": 0.9671, "step": 14210 }, { "epoch": 0.7769554074833419, "grad_norm": 3.4769017696380615, "learning_rate": 1.2496437271400468e-05, "loss": 1.1366, "step": 14211 }, { "epoch": 0.7770100803007005, "grad_norm": 2.9095497131347656, "learning_rate": 1.2490582503814441e-05, "loss": 0.8109, "step": 14212 }, { "epoch": 0.7770647531180591, "grad_norm": 2.7463326454162598, "learning_rate": 1.2484728912303128e-05, "loss": 1.0008, "step": 14213 }, { "epoch": 0.7771194259354177, "grad_norm": 2.1142590045928955, "learning_rate": 1.2478876497050073e-05, "loss": 1.0677, "step": 14214 }, { "epoch": 0.7771740987527763, "grad_norm": 3.037248134613037, "learning_rate": 1.2473025258238752e-05, "loss": 0.9463, "step": 14215 }, { "epoch": 0.7772287715701349, "grad_norm": 2.6482901573181152, "learning_rate": 1.246717519605266e-05, "loss": 1.0654, "step": 14216 }, { "epoch": 0.7772834443874936, "grad_norm": 2.371907949447632, "learning_rate": 1.2461326310675198e-05, "loss": 1.1454, "step": 14217 }, { "epoch": 0.7773381172048522, "grad_norm": 3.4677586555480957, "learning_rate": 1.2455478602289754e-05, "loss": 0.9954, "step": 14218 }, { "epoch": 0.7773927900222108, "grad_norm": 3.3765716552734375, "learning_rate": 1.2449632071079687e-05, "loss": 0.9935, "step": 14219 }, { "epoch": 0.7774474628395694, "grad_norm": 3.366795539855957, "learning_rate": 1.24437867172283e-05, "loss": 1.103, "step": 14220 }, { "epoch": 0.777502135656928, "grad_norm": 5.282108306884766, "learning_rate": 1.2437942540918867e-05, "loss": 1.2092, "step": 14221 }, { "epoch": 0.7775568084742867, "grad_norm": 2.5586583614349365, "learning_rate": 1.2432099542334642e-05, "loss": 1.1071, "step": 14222 }, { "epoch": 0.7776114812916453, "grad_norm": 2.6529593467712402, "learning_rate": 1.2426257721658807e-05, "loss": 0.9547, "step": 14223 }, { "epoch": 0.777666154109004, "grad_norm": 3.1547141075134277, "learning_rate": 1.2420417079074543e-05, "loss": 0.9288, "step": 14224 }, { "epoch": 0.7777208269263626, "grad_norm": 2.5918540954589844, "learning_rate": 1.2414577614764961e-05, "loss": 0.9505, "step": 14225 }, { "epoch": 0.7777754997437212, "grad_norm": 3.2766401767730713, "learning_rate": 1.2408739328913172e-05, "loss": 0.9601, "step": 14226 }, { "epoch": 0.7778301725610798, "grad_norm": 3.261046886444092, "learning_rate": 1.2402902221702222e-05, "loss": 1.0181, "step": 14227 }, { "epoch": 0.7778848453784384, "grad_norm": 2.4029428958892822, "learning_rate": 1.2397066293315135e-05, "loss": 0.8913, "step": 14228 }, { "epoch": 0.777939518195797, "grad_norm": 3.012624979019165, "learning_rate": 1.2391231543934878e-05, "loss": 1.15, "step": 14229 }, { "epoch": 0.7779941910131557, "grad_norm": 3.7176852226257324, "learning_rate": 1.2385397973744406e-05, "loss": 0.847, "step": 14230 }, { "epoch": 0.7780488638305143, "grad_norm": 5.812772750854492, "learning_rate": 1.2379565582926616e-05, "loss": 1.1765, "step": 14231 }, { "epoch": 0.7781035366478729, "grad_norm": 2.335371971130371, "learning_rate": 1.2373734371664386e-05, "loss": 0.9201, "step": 14232 }, { "epoch": 0.7781582094652315, "grad_norm": 3.176830291748047, "learning_rate": 1.2367904340140545e-05, "loss": 0.9456, "step": 14233 }, { "epoch": 0.7782128822825901, "grad_norm": 3.9991066455841064, "learning_rate": 1.2362075488537883e-05, "loss": 0.9906, "step": 14234 }, { "epoch": 0.7782675550999487, "grad_norm": 2.39975905418396, "learning_rate": 1.2356247817039157e-05, "loss": 1.0616, "step": 14235 }, { "epoch": 0.7783222279173073, "grad_norm": 2.3886520862579346, "learning_rate": 1.2350421325827105e-05, "loss": 1.033, "step": 14236 }, { "epoch": 0.778376900734666, "grad_norm": 2.4292829036712646, "learning_rate": 1.2344596015084403e-05, "loss": 1.1131, "step": 14237 }, { "epoch": 0.7784315735520246, "grad_norm": 2.028297185897827, "learning_rate": 1.2338771884993695e-05, "loss": 1.0899, "step": 14238 }, { "epoch": 0.7784862463693832, "grad_norm": 3.0904722213745117, "learning_rate": 1.2332948935737593e-05, "loss": 1.1601, "step": 14239 }, { "epoch": 0.7785409191867418, "grad_norm": 2.8887529373168945, "learning_rate": 1.2327127167498675e-05, "loss": 1.1849, "step": 14240 }, { "epoch": 0.7785955920041004, "grad_norm": 2.3615059852600098, "learning_rate": 1.2321306580459468e-05, "loss": 0.8407, "step": 14241 }, { "epoch": 0.778650264821459, "grad_norm": 2.8297224044799805, "learning_rate": 1.2315487174802481e-05, "loss": 1.1557, "step": 14242 }, { "epoch": 0.7787049376388177, "grad_norm": 2.5859527587890625, "learning_rate": 1.2309668950710174e-05, "loss": 0.9336, "step": 14243 }, { "epoch": 0.7787596104561764, "grad_norm": 2.8321096897125244, "learning_rate": 1.2303851908364967e-05, "loss": 0.985, "step": 14244 }, { "epoch": 0.778814283273535, "grad_norm": 2.1536428928375244, "learning_rate": 1.2298036047949236e-05, "loss": 1.0762, "step": 14245 }, { "epoch": 0.7788689560908936, "grad_norm": 2.8155789375305176, "learning_rate": 1.2292221369645363e-05, "loss": 0.9603, "step": 14246 }, { "epoch": 0.7789236289082522, "grad_norm": 2.9844558238983154, "learning_rate": 1.2286407873635647e-05, "loss": 1.0441, "step": 14247 }, { "epoch": 0.7789783017256108, "grad_norm": 2.260105848312378, "learning_rate": 1.228059556010237e-05, "loss": 1.015, "step": 14248 }, { "epoch": 0.7790329745429694, "grad_norm": 2.963428258895874, "learning_rate": 1.2274784429227759e-05, "loss": 1.0894, "step": 14249 }, { "epoch": 0.779087647360328, "grad_norm": 2.3327176570892334, "learning_rate": 1.2268974481194028e-05, "loss": 0.8269, "step": 14250 }, { "epoch": 0.7791423201776867, "grad_norm": 2.6900041103363037, "learning_rate": 1.2263165716183344e-05, "loss": 0.9783, "step": 14251 }, { "epoch": 0.7791969929950453, "grad_norm": 2.236931085586548, "learning_rate": 1.2257358134377827e-05, "loss": 1.1496, "step": 14252 }, { "epoch": 0.7792516658124039, "grad_norm": 2.7468862533569336, "learning_rate": 1.2251551735959576e-05, "loss": 1.0099, "step": 14253 }, { "epoch": 0.7793063386297625, "grad_norm": 3.2401537895202637, "learning_rate": 1.2245746521110623e-05, "loss": 1.0926, "step": 14254 }, { "epoch": 0.7793610114471211, "grad_norm": 3.3264291286468506, "learning_rate": 1.2239942490013023e-05, "loss": 1.1885, "step": 14255 }, { "epoch": 0.7794156842644797, "grad_norm": 2.8062350749969482, "learning_rate": 1.2234139642848735e-05, "loss": 0.9159, "step": 14256 }, { "epoch": 0.7794703570818384, "grad_norm": 2.5966224670410156, "learning_rate": 1.222833797979971e-05, "loss": 0.9385, "step": 14257 }, { "epoch": 0.779525029899197, "grad_norm": 2.5349366664886475, "learning_rate": 1.2222537501047849e-05, "loss": 0.9119, "step": 14258 }, { "epoch": 0.7795797027165556, "grad_norm": 3.12762451171875, "learning_rate": 1.2216738206775018e-05, "loss": 1.0479, "step": 14259 }, { "epoch": 0.7796343755339142, "grad_norm": 2.012960195541382, "learning_rate": 1.2210940097163054e-05, "loss": 1.0481, "step": 14260 }, { "epoch": 0.7796890483512728, "grad_norm": 3.438400983810425, "learning_rate": 1.2205143172393746e-05, "loss": 1.0637, "step": 14261 }, { "epoch": 0.7797437211686314, "grad_norm": 5.236997127532959, "learning_rate": 1.2199347432648861e-05, "loss": 1.2232, "step": 14262 }, { "epoch": 0.77979839398599, "grad_norm": 2.1350207328796387, "learning_rate": 1.219355287811011e-05, "loss": 0.7541, "step": 14263 }, { "epoch": 0.7798530668033488, "grad_norm": 3.0262317657470703, "learning_rate": 1.2187759508959162e-05, "loss": 1.1748, "step": 14264 }, { "epoch": 0.7799077396207074, "grad_norm": 3.944502830505371, "learning_rate": 1.2181967325377703e-05, "loss": 0.9102, "step": 14265 }, { "epoch": 0.779962412438066, "grad_norm": 3.110933303833008, "learning_rate": 1.2176176327547312e-05, "loss": 0.9405, "step": 14266 }, { "epoch": 0.7800170852554246, "grad_norm": 2.385761022567749, "learning_rate": 1.2170386515649568e-05, "loss": 0.8297, "step": 14267 }, { "epoch": 0.7800717580727832, "grad_norm": 2.5984997749328613, "learning_rate": 1.2164597889866008e-05, "loss": 0.8496, "step": 14268 }, { "epoch": 0.7801264308901418, "grad_norm": 2.768176555633545, "learning_rate": 1.2158810450378128e-05, "loss": 1.1136, "step": 14269 }, { "epoch": 0.7801811037075004, "grad_norm": 2.9485933780670166, "learning_rate": 1.2153024197367385e-05, "loss": 1.0892, "step": 14270 }, { "epoch": 0.7802357765248591, "grad_norm": 3.002471685409546, "learning_rate": 1.2147239131015203e-05, "loss": 1.0536, "step": 14271 }, { "epoch": 0.7802904493422177, "grad_norm": 2.5011394023895264, "learning_rate": 1.214145525150297e-05, "loss": 1.0641, "step": 14272 }, { "epoch": 0.7803451221595763, "grad_norm": 2.2702183723449707, "learning_rate": 1.2135672559012034e-05, "loss": 0.9443, "step": 14273 }, { "epoch": 0.7803997949769349, "grad_norm": 3.02376127243042, "learning_rate": 1.2129891053723686e-05, "loss": 1.0688, "step": 14274 }, { "epoch": 0.7804544677942935, "grad_norm": 2.8832361698150635, "learning_rate": 1.2124110735819238e-05, "loss": 0.881, "step": 14275 }, { "epoch": 0.7805091406116521, "grad_norm": 4.050958633422852, "learning_rate": 1.2118331605479905e-05, "loss": 0.9478, "step": 14276 }, { "epoch": 0.7805638134290107, "grad_norm": 2.3297173976898193, "learning_rate": 1.2112553662886888e-05, "loss": 0.9413, "step": 14277 }, { "epoch": 0.7806184862463694, "grad_norm": 2.4005184173583984, "learning_rate": 1.210677690822135e-05, "loss": 0.851, "step": 14278 }, { "epoch": 0.780673159063728, "grad_norm": 2.219341278076172, "learning_rate": 1.210100134166442e-05, "loss": 0.7547, "step": 14279 }, { "epoch": 0.7807278318810866, "grad_norm": 3.8426074981689453, "learning_rate": 1.2095226963397183e-05, "loss": 1.0007, "step": 14280 }, { "epoch": 0.7807825046984452, "grad_norm": 2.667133331298828, "learning_rate": 1.2089453773600684e-05, "loss": 1.035, "step": 14281 }, { "epoch": 0.7808371775158038, "grad_norm": 2.7754311561584473, "learning_rate": 1.2083681772455946e-05, "loss": 1.1013, "step": 14282 }, { "epoch": 0.7808918503331624, "grad_norm": 3.13974666595459, "learning_rate": 1.207791096014394e-05, "loss": 1.1969, "step": 14283 }, { "epoch": 0.7809465231505212, "grad_norm": 2.918792247772217, "learning_rate": 1.2072141336845589e-05, "loss": 0.974, "step": 14284 }, { "epoch": 0.7810011959678798, "grad_norm": 3.1454949378967285, "learning_rate": 1.2066372902741823e-05, "loss": 1.0947, "step": 14285 }, { "epoch": 0.7810558687852384, "grad_norm": 2.7961647510528564, "learning_rate": 1.2060605658013496e-05, "loss": 0.9226, "step": 14286 }, { "epoch": 0.781110541602597, "grad_norm": 1.9417601823806763, "learning_rate": 1.2054839602841428e-05, "loss": 0.9719, "step": 14287 }, { "epoch": 0.7811652144199556, "grad_norm": 2.4315335750579834, "learning_rate": 1.2049074737406418e-05, "loss": 1.0362, "step": 14288 }, { "epoch": 0.7812198872373142, "grad_norm": 3.2507734298706055, "learning_rate": 1.2043311061889212e-05, "loss": 1.0984, "step": 14289 }, { "epoch": 0.7812745600546728, "grad_norm": 2.5504653453826904, "learning_rate": 1.2037548576470525e-05, "loss": 0.9937, "step": 14290 }, { "epoch": 0.7813292328720315, "grad_norm": 3.9796667098999023, "learning_rate": 1.2031787281331036e-05, "loss": 1.1035, "step": 14291 }, { "epoch": 0.7813839056893901, "grad_norm": 2.8110220432281494, "learning_rate": 1.202602717665139e-05, "loss": 1.0965, "step": 14292 }, { "epoch": 0.7814385785067487, "grad_norm": 2.382028341293335, "learning_rate": 1.2020268262612177e-05, "loss": 1.0416, "step": 14293 }, { "epoch": 0.7814932513241073, "grad_norm": 2.749891757965088, "learning_rate": 1.2014510539393964e-05, "loss": 0.9018, "step": 14294 }, { "epoch": 0.7815479241414659, "grad_norm": 2.3427412509918213, "learning_rate": 1.2008754007177298e-05, "loss": 1.0075, "step": 14295 }, { "epoch": 0.7816025969588245, "grad_norm": 2.896531343460083, "learning_rate": 1.2002998666142656e-05, "loss": 0.9493, "step": 14296 }, { "epoch": 0.7816572697761831, "grad_norm": 2.725443124771118, "learning_rate": 1.1997244516470496e-05, "loss": 0.9303, "step": 14297 }, { "epoch": 0.7817119425935418, "grad_norm": 2.698646068572998, "learning_rate": 1.1991491558341228e-05, "loss": 0.9574, "step": 14298 }, { "epoch": 0.7817666154109004, "grad_norm": 2.500046491622925, "learning_rate": 1.198573979193524e-05, "loss": 0.8502, "step": 14299 }, { "epoch": 0.781821288228259, "grad_norm": 2.618896007537842, "learning_rate": 1.1979989217432868e-05, "loss": 0.9059, "step": 14300 }, { "epoch": 0.7818759610456176, "grad_norm": 2.990793466567993, "learning_rate": 1.1974239835014417e-05, "loss": 1.2215, "step": 14301 }, { "epoch": 0.7819306338629762, "grad_norm": 3.748758554458618, "learning_rate": 1.1968491644860153e-05, "loss": 0.9915, "step": 14302 }, { "epoch": 0.7819853066803348, "grad_norm": 3.2244017124176025, "learning_rate": 1.1962744647150304e-05, "loss": 1.2042, "step": 14303 }, { "epoch": 0.7820399794976934, "grad_norm": 2.223947286605835, "learning_rate": 1.1956998842065066e-05, "loss": 0.8974, "step": 14304 }, { "epoch": 0.7820946523150522, "grad_norm": 3.097116708755493, "learning_rate": 1.1951254229784581e-05, "loss": 1.0197, "step": 14305 }, { "epoch": 0.7821493251324108, "grad_norm": 2.7232484817504883, "learning_rate": 1.1945510810488986e-05, "loss": 1.013, "step": 14306 }, { "epoch": 0.7822039979497694, "grad_norm": 2.629509449005127, "learning_rate": 1.1939768584358352e-05, "loss": 0.7858, "step": 14307 }, { "epoch": 0.782258670767128, "grad_norm": 2.9773430824279785, "learning_rate": 1.1934027551572724e-05, "loss": 0.9117, "step": 14308 }, { "epoch": 0.7823133435844866, "grad_norm": 3.008823871612549, "learning_rate": 1.1928287712312103e-05, "loss": 1.1723, "step": 14309 }, { "epoch": 0.7823680164018452, "grad_norm": 2.946367025375366, "learning_rate": 1.1922549066756461e-05, "loss": 1.1291, "step": 14310 }, { "epoch": 0.7824226892192039, "grad_norm": 2.710866928100586, "learning_rate": 1.1916811615085722e-05, "loss": 1.0374, "step": 14311 }, { "epoch": 0.7824773620365625, "grad_norm": 2.993502140045166, "learning_rate": 1.1911075357479778e-05, "loss": 0.9413, "step": 14312 }, { "epoch": 0.7825320348539211, "grad_norm": 2.780651092529297, "learning_rate": 1.1905340294118495e-05, "loss": 0.7811, "step": 14313 }, { "epoch": 0.7825867076712797, "grad_norm": 2.904304027557373, "learning_rate": 1.1899606425181681e-05, "loss": 0.9418, "step": 14314 }, { "epoch": 0.7826413804886383, "grad_norm": 2.694700241088867, "learning_rate": 1.1893873750849121e-05, "loss": 0.9514, "step": 14315 }, { "epoch": 0.7826960533059969, "grad_norm": 2.668443441390991, "learning_rate": 1.1888142271300556e-05, "loss": 1.1396, "step": 14316 }, { "epoch": 0.7827507261233555, "grad_norm": 2.187182664871216, "learning_rate": 1.1882411986715692e-05, "loss": 0.8917, "step": 14317 }, { "epoch": 0.7828053989407142, "grad_norm": 2.3141915798187256, "learning_rate": 1.1876682897274178e-05, "loss": 0.9326, "step": 14318 }, { "epoch": 0.7828600717580728, "grad_norm": 3.6086108684539795, "learning_rate": 1.1870955003155681e-05, "loss": 1.1172, "step": 14319 }, { "epoch": 0.7829147445754314, "grad_norm": 3.9852781295776367, "learning_rate": 1.1865228304539777e-05, "loss": 0.9156, "step": 14320 }, { "epoch": 0.78296941739279, "grad_norm": 2.82025146484375, "learning_rate": 1.1859502801606026e-05, "loss": 0.8765, "step": 14321 }, { "epoch": 0.7830240902101486, "grad_norm": 3.0632998943328857, "learning_rate": 1.1853778494533935e-05, "loss": 1.1042, "step": 14322 }, { "epoch": 0.7830787630275072, "grad_norm": 2.776771306991577, "learning_rate": 1.1848055383502992e-05, "loss": 0.9521, "step": 14323 }, { "epoch": 0.7831334358448658, "grad_norm": 4.1304426193237305, "learning_rate": 1.184233346869264e-05, "loss": 0.8318, "step": 14324 }, { "epoch": 0.7831881086622245, "grad_norm": 2.6190474033355713, "learning_rate": 1.1836612750282278e-05, "loss": 1.2755, "step": 14325 }, { "epoch": 0.7832427814795831, "grad_norm": 2.31719970703125, "learning_rate": 1.1830893228451284e-05, "loss": 0.8751, "step": 14326 }, { "epoch": 0.7832974542969418, "grad_norm": 3.0508618354797363, "learning_rate": 1.1825174903378989e-05, "loss": 0.8509, "step": 14327 }, { "epoch": 0.7833521271143004, "grad_norm": 2.8911125659942627, "learning_rate": 1.1819457775244674e-05, "loss": 1.2376, "step": 14328 }, { "epoch": 0.783406799931659, "grad_norm": 2.605196952819824, "learning_rate": 1.1813741844227605e-05, "loss": 1.0907, "step": 14329 }, { "epoch": 0.7834614727490176, "grad_norm": 2.0063865184783936, "learning_rate": 1.1808027110506991e-05, "loss": 0.9994, "step": 14330 }, { "epoch": 0.7835161455663762, "grad_norm": 2.2086639404296875, "learning_rate": 1.1802313574262014e-05, "loss": 0.9621, "step": 14331 }, { "epoch": 0.7835708183837349, "grad_norm": 2.7246341705322266, "learning_rate": 1.1796601235671828e-05, "loss": 0.9999, "step": 14332 }, { "epoch": 0.7836254912010935, "grad_norm": 2.1897342205047607, "learning_rate": 1.1790890094915536e-05, "loss": 1.0122, "step": 14333 }, { "epoch": 0.7836801640184521, "grad_norm": 3.1242315769195557, "learning_rate": 1.1785180152172192e-05, "loss": 1.0322, "step": 14334 }, { "epoch": 0.7837348368358107, "grad_norm": 3.4312424659729004, "learning_rate": 1.1779471407620845e-05, "loss": 1.0094, "step": 14335 }, { "epoch": 0.7837895096531693, "grad_norm": 2.5712151527404785, "learning_rate": 1.1773763861440474e-05, "loss": 0.9257, "step": 14336 }, { "epoch": 0.7838441824705279, "grad_norm": 3.311643362045288, "learning_rate": 1.1768057513810037e-05, "loss": 0.864, "step": 14337 }, { "epoch": 0.7838988552878866, "grad_norm": 2.9890379905700684, "learning_rate": 1.1762352364908458e-05, "loss": 0.9747, "step": 14338 }, { "epoch": 0.7839535281052452, "grad_norm": 2.6262269020080566, "learning_rate": 1.1756648414914607e-05, "loss": 1.0898, "step": 14339 }, { "epoch": 0.7840082009226038, "grad_norm": 2.5010857582092285, "learning_rate": 1.175094566400733e-05, "loss": 1.0351, "step": 14340 }, { "epoch": 0.7840628737399624, "grad_norm": 2.469552755355835, "learning_rate": 1.1745244112365433e-05, "loss": 1.1228, "step": 14341 }, { "epoch": 0.784117546557321, "grad_norm": 2.218506336212158, "learning_rate": 1.1739543760167687e-05, "loss": 1.1393, "step": 14342 }, { "epoch": 0.7841722193746796, "grad_norm": 2.4405441284179688, "learning_rate": 1.1733844607592798e-05, "loss": 1.0068, "step": 14343 }, { "epoch": 0.7842268921920382, "grad_norm": 2.6382620334625244, "learning_rate": 1.1728146654819494e-05, "loss": 0.9333, "step": 14344 }, { "epoch": 0.7842815650093969, "grad_norm": 3.027735710144043, "learning_rate": 1.1722449902026411e-05, "loss": 1.0998, "step": 14345 }, { "epoch": 0.7843362378267555, "grad_norm": 2.806788206100464, "learning_rate": 1.1716754349392167e-05, "loss": 0.9904, "step": 14346 }, { "epoch": 0.7843909106441141, "grad_norm": 2.2473037242889404, "learning_rate": 1.1711059997095342e-05, "loss": 0.9082, "step": 14347 }, { "epoch": 0.7844455834614728, "grad_norm": 2.364161729812622, "learning_rate": 1.1705366845314475e-05, "loss": 1.0611, "step": 14348 }, { "epoch": 0.7845002562788314, "grad_norm": 2.642594575881958, "learning_rate": 1.1699674894228074e-05, "loss": 1.0069, "step": 14349 }, { "epoch": 0.78455492909619, "grad_norm": 2.319812297821045, "learning_rate": 1.1693984144014596e-05, "loss": 1.0893, "step": 14350 }, { "epoch": 0.7846096019135486, "grad_norm": 2.5401718616485596, "learning_rate": 1.1688294594852484e-05, "loss": 1.1243, "step": 14351 }, { "epoch": 0.7846642747309073, "grad_norm": 2.3339438438415527, "learning_rate": 1.1682606246920113e-05, "loss": 0.9701, "step": 14352 }, { "epoch": 0.7847189475482659, "grad_norm": 2.370710849761963, "learning_rate": 1.1676919100395834e-05, "loss": 1.1193, "step": 14353 }, { "epoch": 0.7847736203656245, "grad_norm": 3.1928703784942627, "learning_rate": 1.167123315545799e-05, "loss": 1.0902, "step": 14354 }, { "epoch": 0.7848282931829831, "grad_norm": 2.5443837642669678, "learning_rate": 1.1665548412284832e-05, "loss": 0.9243, "step": 14355 }, { "epoch": 0.7848829660003417, "grad_norm": 3.0031380653381348, "learning_rate": 1.1659864871054615e-05, "loss": 0.8491, "step": 14356 }, { "epoch": 0.7849376388177003, "grad_norm": 2.825805425643921, "learning_rate": 1.1654182531945534e-05, "loss": 0.9602, "step": 14357 }, { "epoch": 0.7849923116350589, "grad_norm": 3.5007755756378174, "learning_rate": 1.1648501395135759e-05, "loss": 1.2364, "step": 14358 }, { "epoch": 0.7850469844524176, "grad_norm": 2.449169874191284, "learning_rate": 1.1642821460803405e-05, "loss": 1.0911, "step": 14359 }, { "epoch": 0.7851016572697762, "grad_norm": 2.19742751121521, "learning_rate": 1.1637142729126577e-05, "loss": 1.0181, "step": 14360 }, { "epoch": 0.7851563300871348, "grad_norm": 2.256869316101074, "learning_rate": 1.1631465200283315e-05, "loss": 0.9429, "step": 14361 }, { "epoch": 0.7852110029044934, "grad_norm": 2.519221782684326, "learning_rate": 1.1625788874451626e-05, "loss": 0.8611, "step": 14362 }, { "epoch": 0.785265675721852, "grad_norm": 2.7353110313415527, "learning_rate": 1.1620113751809508e-05, "loss": 0.9387, "step": 14363 }, { "epoch": 0.7853203485392106, "grad_norm": 3.045177698135376, "learning_rate": 1.1614439832534891e-05, "loss": 0.9696, "step": 14364 }, { "epoch": 0.7853750213565693, "grad_norm": 2.291332721710205, "learning_rate": 1.1608767116805675e-05, "loss": 1.0146, "step": 14365 }, { "epoch": 0.7854296941739279, "grad_norm": 2.4907147884368896, "learning_rate": 1.1603095604799719e-05, "loss": 0.8293, "step": 14366 }, { "epoch": 0.7854843669912865, "grad_norm": 2.7572805881500244, "learning_rate": 1.1597425296694852e-05, "loss": 0.9041, "step": 14367 }, { "epoch": 0.7855390398086451, "grad_norm": 3.2325820922851562, "learning_rate": 1.1591756192668863e-05, "loss": 1.0397, "step": 14368 }, { "epoch": 0.7855937126260037, "grad_norm": 2.285101890563965, "learning_rate": 1.1586088292899493e-05, "loss": 1.0416, "step": 14369 }, { "epoch": 0.7856483854433624, "grad_norm": 3.1816437244415283, "learning_rate": 1.1580421597564467e-05, "loss": 1.0215, "step": 14370 }, { "epoch": 0.785703058260721, "grad_norm": 2.351705551147461, "learning_rate": 1.1574756106841444e-05, "loss": 1.0003, "step": 14371 }, { "epoch": 0.7857577310780797, "grad_norm": 3.1023809909820557, "learning_rate": 1.1569091820908062e-05, "loss": 1.0004, "step": 14372 }, { "epoch": 0.7858124038954383, "grad_norm": 3.2034363746643066, "learning_rate": 1.156342873994194e-05, "loss": 1.1594, "step": 14373 }, { "epoch": 0.7858670767127969, "grad_norm": 2.715543508529663, "learning_rate": 1.1557766864120622e-05, "loss": 1.154, "step": 14374 }, { "epoch": 0.7859217495301555, "grad_norm": 2.5486230850219727, "learning_rate": 1.1552106193621637e-05, "loss": 1.196, "step": 14375 }, { "epoch": 0.7859764223475141, "grad_norm": 2.6899499893188477, "learning_rate": 1.1546446728622462e-05, "loss": 0.9362, "step": 14376 }, { "epoch": 0.7860310951648727, "grad_norm": 2.935373306274414, "learning_rate": 1.1540788469300556e-05, "loss": 1.0884, "step": 14377 }, { "epoch": 0.7860857679822313, "grad_norm": 2.54411244392395, "learning_rate": 1.1535131415833323e-05, "loss": 1.0302, "step": 14378 }, { "epoch": 0.78614044079959, "grad_norm": 2.232530117034912, "learning_rate": 1.1529475568398134e-05, "loss": 1.1008, "step": 14379 }, { "epoch": 0.7861951136169486, "grad_norm": 2.131760835647583, "learning_rate": 1.1523820927172325e-05, "loss": 1.0443, "step": 14380 }, { "epoch": 0.7862497864343072, "grad_norm": 3.4363222122192383, "learning_rate": 1.1518167492333187e-05, "loss": 1.1193, "step": 14381 }, { "epoch": 0.7863044592516658, "grad_norm": 2.582440137863159, "learning_rate": 1.1512515264057977e-05, "loss": 0.9888, "step": 14382 }, { "epoch": 0.7863591320690244, "grad_norm": 3.6039130687713623, "learning_rate": 1.1506864242523928e-05, "loss": 1.2408, "step": 14383 }, { "epoch": 0.786413804886383, "grad_norm": 3.224461793899536, "learning_rate": 1.1501214427908218e-05, "loss": 0.908, "step": 14384 }, { "epoch": 0.7864684777037416, "grad_norm": 2.7981081008911133, "learning_rate": 1.1495565820387994e-05, "loss": 1.0747, "step": 14385 }, { "epoch": 0.7865231505211003, "grad_norm": 3.419074535369873, "learning_rate": 1.1489918420140355e-05, "loss": 1.1736, "step": 14386 }, { "epoch": 0.7865778233384589, "grad_norm": 2.49194073677063, "learning_rate": 1.148427222734238e-05, "loss": 0.9532, "step": 14387 }, { "epoch": 0.7866324961558175, "grad_norm": 2.519834518432617, "learning_rate": 1.1478627242171091e-05, "loss": 1.0959, "step": 14388 }, { "epoch": 0.7866871689731761, "grad_norm": 2.6578192710876465, "learning_rate": 1.1472983464803489e-05, "loss": 0.9406, "step": 14389 }, { "epoch": 0.7867418417905347, "grad_norm": 2.6021318435668945, "learning_rate": 1.1467340895416523e-05, "loss": 1.0959, "step": 14390 }, { "epoch": 0.7867965146078933, "grad_norm": 2.576326847076416, "learning_rate": 1.1461699534187115e-05, "loss": 0.9231, "step": 14391 }, { "epoch": 0.786851187425252, "grad_norm": 2.5347542762756348, "learning_rate": 1.1456059381292128e-05, "loss": 1.186, "step": 14392 }, { "epoch": 0.7869058602426107, "grad_norm": 2.4445648193359375, "learning_rate": 1.1450420436908432e-05, "loss": 1.0624, "step": 14393 }, { "epoch": 0.7869605330599693, "grad_norm": 2.6685128211975098, "learning_rate": 1.1444782701212825e-05, "loss": 1.0994, "step": 14394 }, { "epoch": 0.7870152058773279, "grad_norm": 2.829876184463501, "learning_rate": 1.1439146174382066e-05, "loss": 1.0612, "step": 14395 }, { "epoch": 0.7870698786946865, "grad_norm": 2.8097550868988037, "learning_rate": 1.1433510856592884e-05, "loss": 0.9593, "step": 14396 }, { "epoch": 0.7871245515120451, "grad_norm": 3.0460641384124756, "learning_rate": 1.142787674802197e-05, "loss": 1.0197, "step": 14397 }, { "epoch": 0.7871792243294037, "grad_norm": 2.5617196559906006, "learning_rate": 1.1422243848845975e-05, "loss": 1.1335, "step": 14398 }, { "epoch": 0.7872338971467624, "grad_norm": 2.612793445587158, "learning_rate": 1.141661215924152e-05, "loss": 1.0405, "step": 14399 }, { "epoch": 0.787288569964121, "grad_norm": 2.92124080657959, "learning_rate": 1.1410981679385169e-05, "loss": 1.0262, "step": 14400 }, { "epoch": 0.7873432427814796, "grad_norm": 4.507497310638428, "learning_rate": 1.1405352409453473e-05, "loss": 1.2804, "step": 14401 }, { "epoch": 0.7873979155988382, "grad_norm": 2.799243688583374, "learning_rate": 1.1399724349622914e-05, "loss": 1.1313, "step": 14402 }, { "epoch": 0.7874525884161968, "grad_norm": 2.268472194671631, "learning_rate": 1.1394097500069983e-05, "loss": 0.9734, "step": 14403 }, { "epoch": 0.7875072612335554, "grad_norm": 2.3922641277313232, "learning_rate": 1.1388471860971095e-05, "loss": 0.9861, "step": 14404 }, { "epoch": 0.787561934050914, "grad_norm": 2.3108694553375244, "learning_rate": 1.138284743250263e-05, "loss": 0.9721, "step": 14405 }, { "epoch": 0.7876166068682727, "grad_norm": 2.4600064754486084, "learning_rate": 1.1377224214840938e-05, "loss": 0.9048, "step": 14406 }, { "epoch": 0.7876712796856313, "grad_norm": 2.2181901931762695, "learning_rate": 1.1371602208162335e-05, "loss": 0.8846, "step": 14407 }, { "epoch": 0.7877259525029899, "grad_norm": 2.8898019790649414, "learning_rate": 1.136598141264309e-05, "loss": 1.0187, "step": 14408 }, { "epoch": 0.7877806253203485, "grad_norm": 2.8248002529144287, "learning_rate": 1.1360361828459436e-05, "loss": 0.9276, "step": 14409 }, { "epoch": 0.7878352981377071, "grad_norm": 2.4413208961486816, "learning_rate": 1.1354743455787581e-05, "loss": 0.8984, "step": 14410 }, { "epoch": 0.7878899709550657, "grad_norm": 2.813363790512085, "learning_rate": 1.1349126294803658e-05, "loss": 0.9115, "step": 14411 }, { "epoch": 0.7879446437724243, "grad_norm": 2.370694637298584, "learning_rate": 1.1343510345683822e-05, "loss": 1.2114, "step": 14412 }, { "epoch": 0.7879993165897831, "grad_norm": 2.9598422050476074, "learning_rate": 1.1337895608604138e-05, "loss": 1.1803, "step": 14413 }, { "epoch": 0.7880539894071417, "grad_norm": 2.2933030128479004, "learning_rate": 1.1332282083740653e-05, "loss": 1.0802, "step": 14414 }, { "epoch": 0.7881086622245003, "grad_norm": 2.4455111026763916, "learning_rate": 1.1326669771269382e-05, "loss": 0.9676, "step": 14415 }, { "epoch": 0.7881633350418589, "grad_norm": 3.0172500610351562, "learning_rate": 1.132105867136628e-05, "loss": 0.9601, "step": 14416 }, { "epoch": 0.7882180078592175, "grad_norm": 2.322958469390869, "learning_rate": 1.1315448784207288e-05, "loss": 0.9754, "step": 14417 }, { "epoch": 0.7882726806765761, "grad_norm": 2.547889471054077, "learning_rate": 1.1309840109968294e-05, "loss": 1.0037, "step": 14418 }, { "epoch": 0.7883273534939347, "grad_norm": 4.106093883514404, "learning_rate": 1.1304232648825157e-05, "loss": 1.197, "step": 14419 }, { "epoch": 0.7883820263112934, "grad_norm": 4.2771711349487305, "learning_rate": 1.1298626400953693e-05, "loss": 1.1249, "step": 14420 }, { "epoch": 0.788436699128652, "grad_norm": 2.50081205368042, "learning_rate": 1.1293021366529672e-05, "loss": 1.0779, "step": 14421 }, { "epoch": 0.7884913719460106, "grad_norm": 2.8228464126586914, "learning_rate": 1.1287417545728852e-05, "loss": 0.9532, "step": 14422 }, { "epoch": 0.7885460447633692, "grad_norm": 2.307018756866455, "learning_rate": 1.1281814938726926e-05, "loss": 1.0418, "step": 14423 }, { "epoch": 0.7886007175807278, "grad_norm": 2.0854570865631104, "learning_rate": 1.127621354569956e-05, "loss": 0.8954, "step": 14424 }, { "epoch": 0.7886553903980864, "grad_norm": 3.3360564708709717, "learning_rate": 1.127061336682238e-05, "loss": 0.976, "step": 14425 }, { "epoch": 0.7887100632154451, "grad_norm": 2.539268732070923, "learning_rate": 1.1265014402270974e-05, "loss": 1.0327, "step": 14426 }, { "epoch": 0.7887647360328037, "grad_norm": 2.7825889587402344, "learning_rate": 1.1259416652220895e-05, "loss": 1.0454, "step": 14427 }, { "epoch": 0.7888194088501623, "grad_norm": 2.371199131011963, "learning_rate": 1.1253820116847658e-05, "loss": 0.9707, "step": 14428 }, { "epoch": 0.7888740816675209, "grad_norm": 2.480726957321167, "learning_rate": 1.1248224796326728e-05, "loss": 1.201, "step": 14429 }, { "epoch": 0.7889287544848795, "grad_norm": 2.872257709503174, "learning_rate": 1.124263069083355e-05, "loss": 1.2605, "step": 14430 }, { "epoch": 0.7889834273022381, "grad_norm": 3.0205326080322266, "learning_rate": 1.1237037800543509e-05, "loss": 0.9928, "step": 14431 }, { "epoch": 0.7890381001195967, "grad_norm": 2.6951792240142822, "learning_rate": 1.1231446125631984e-05, "loss": 1.0057, "step": 14432 }, { "epoch": 0.7890927729369555, "grad_norm": 2.2214179039001465, "learning_rate": 1.1225855666274292e-05, "loss": 0.9034, "step": 14433 }, { "epoch": 0.7891474457543141, "grad_norm": 2.4234189987182617, "learning_rate": 1.1220266422645714e-05, "loss": 1.076, "step": 14434 }, { "epoch": 0.7892021185716727, "grad_norm": 3.1236464977264404, "learning_rate": 1.1214678394921491e-05, "loss": 1.2028, "step": 14435 }, { "epoch": 0.7892567913890313, "grad_norm": 10.89686107635498, "learning_rate": 1.1209091583276838e-05, "loss": 0.8462, "step": 14436 }, { "epoch": 0.7893114642063899, "grad_norm": 2.7754251956939697, "learning_rate": 1.1203505987886919e-05, "loss": 1.1014, "step": 14437 }, { "epoch": 0.7893661370237485, "grad_norm": 2.5618817806243896, "learning_rate": 1.1197921608926876e-05, "loss": 0.7957, "step": 14438 }, { "epoch": 0.7894208098411071, "grad_norm": 2.96242356300354, "learning_rate": 1.1192338446571787e-05, "loss": 1.0231, "step": 14439 }, { "epoch": 0.7894754826584658, "grad_norm": 3.169785261154175, "learning_rate": 1.1186756500996714e-05, "loss": 1.1388, "step": 14440 }, { "epoch": 0.7895301554758244, "grad_norm": 2.540795087814331, "learning_rate": 1.1181175772376662e-05, "loss": 0.9584, "step": 14441 }, { "epoch": 0.789584828293183, "grad_norm": 2.407414436340332, "learning_rate": 1.117559626088664e-05, "loss": 0.9668, "step": 14442 }, { "epoch": 0.7896395011105416, "grad_norm": 2.6079776287078857, "learning_rate": 1.1170017966701562e-05, "loss": 1.0782, "step": 14443 }, { "epoch": 0.7896941739279002, "grad_norm": 2.8125829696655273, "learning_rate": 1.1164440889996348e-05, "loss": 0.967, "step": 14444 }, { "epoch": 0.7897488467452588, "grad_norm": 3.0257949829101562, "learning_rate": 1.1158865030945847e-05, "loss": 1.0614, "step": 14445 }, { "epoch": 0.7898035195626174, "grad_norm": 2.699274778366089, "learning_rate": 1.1153290389724897e-05, "loss": 0.7728, "step": 14446 }, { "epoch": 0.7898581923799761, "grad_norm": 2.9300377368927, "learning_rate": 1.1147716966508282e-05, "loss": 0.8802, "step": 14447 }, { "epoch": 0.7899128651973347, "grad_norm": 2.544724702835083, "learning_rate": 1.1142144761470746e-05, "loss": 0.949, "step": 14448 }, { "epoch": 0.7899675380146933, "grad_norm": 2.5961954593658447, "learning_rate": 1.1136573774787007e-05, "loss": 1.028, "step": 14449 }, { "epoch": 0.7900222108320519, "grad_norm": 2.2956180572509766, "learning_rate": 1.1131004006631734e-05, "loss": 1.0021, "step": 14450 }, { "epoch": 0.7900768836494105, "grad_norm": 2.540937900543213, "learning_rate": 1.1125435457179556e-05, "loss": 0.9656, "step": 14451 }, { "epoch": 0.7901315564667691, "grad_norm": 2.161816120147705, "learning_rate": 1.1119868126605087e-05, "loss": 0.8456, "step": 14452 }, { "epoch": 0.7901862292841279, "grad_norm": 2.518540143966675, "learning_rate": 1.1114302015082879e-05, "loss": 0.8945, "step": 14453 }, { "epoch": 0.7902409021014865, "grad_norm": 2.2946221828460693, "learning_rate": 1.1108737122787455e-05, "loss": 0.8889, "step": 14454 }, { "epoch": 0.7902955749188451, "grad_norm": 2.415545701980591, "learning_rate": 1.110317344989329e-05, "loss": 1.0546, "step": 14455 }, { "epoch": 0.7903502477362037, "grad_norm": 3.103342294692993, "learning_rate": 1.1097610996574831e-05, "loss": 0.9445, "step": 14456 }, { "epoch": 0.7904049205535623, "grad_norm": 2.4588301181793213, "learning_rate": 1.1092049763006485e-05, "loss": 1.0228, "step": 14457 }, { "epoch": 0.7904595933709209, "grad_norm": 2.8194026947021484, "learning_rate": 1.1086489749362616e-05, "loss": 1.0208, "step": 14458 }, { "epoch": 0.7905142661882795, "grad_norm": 2.988203525543213, "learning_rate": 1.108093095581756e-05, "loss": 1.1914, "step": 14459 }, { "epoch": 0.7905689390056382, "grad_norm": 2.944692373275757, "learning_rate": 1.10753733825456e-05, "loss": 1.055, "step": 14460 }, { "epoch": 0.7906236118229968, "grad_norm": 2.700488328933716, "learning_rate": 1.106981702972098e-05, "loss": 0.9296, "step": 14461 }, { "epoch": 0.7906782846403554, "grad_norm": 2.857638120651245, "learning_rate": 1.106426189751794e-05, "loss": 1.0536, "step": 14462 }, { "epoch": 0.790732957457714, "grad_norm": 2.253323554992676, "learning_rate": 1.105870798611065e-05, "loss": 1.1328, "step": 14463 }, { "epoch": 0.7907876302750726, "grad_norm": 2.0775763988494873, "learning_rate": 1.1053155295673235e-05, "loss": 0.9884, "step": 14464 }, { "epoch": 0.7908423030924312, "grad_norm": 2.9139010906219482, "learning_rate": 1.1047603826379805e-05, "loss": 1.1045, "step": 14465 }, { "epoch": 0.7908969759097898, "grad_norm": 2.543663263320923, "learning_rate": 1.1042053578404416e-05, "loss": 1.1203, "step": 14466 }, { "epoch": 0.7909516487271485, "grad_norm": 2.914594888687134, "learning_rate": 1.1036504551921096e-05, "loss": 1.0446, "step": 14467 }, { "epoch": 0.7910063215445071, "grad_norm": 2.888427495956421, "learning_rate": 1.1030956747103822e-05, "loss": 1.1016, "step": 14468 }, { "epoch": 0.7910609943618657, "grad_norm": 2.9080071449279785, "learning_rate": 1.1025410164126549e-05, "loss": 0.9517, "step": 14469 }, { "epoch": 0.7911156671792243, "grad_norm": 2.692763328552246, "learning_rate": 1.1019864803163165e-05, "loss": 1.0586, "step": 14470 }, { "epoch": 0.7911703399965829, "grad_norm": 2.330894708633423, "learning_rate": 1.1014320664387574e-05, "loss": 1.0549, "step": 14471 }, { "epoch": 0.7912250128139415, "grad_norm": 4.505273818969727, "learning_rate": 1.1008777747973587e-05, "loss": 1.1578, "step": 14472 }, { "epoch": 0.7912796856313001, "grad_norm": 2.361090898513794, "learning_rate": 1.1003236054095e-05, "loss": 0.881, "step": 14473 }, { "epoch": 0.7913343584486588, "grad_norm": 2.3257150650024414, "learning_rate": 1.0997695582925572e-05, "loss": 1.0612, "step": 14474 }, { "epoch": 0.7913890312660175, "grad_norm": 2.2999260425567627, "learning_rate": 1.0992156334639015e-05, "loss": 1.1092, "step": 14475 }, { "epoch": 0.791443704083376, "grad_norm": 2.5801024436950684, "learning_rate": 1.0986618309409003e-05, "loss": 1.0032, "step": 14476 }, { "epoch": 0.7914983769007347, "grad_norm": 3.0979039669036865, "learning_rate": 1.0981081507409185e-05, "loss": 1.1839, "step": 14477 }, { "epoch": 0.7915530497180933, "grad_norm": 3.2363264560699463, "learning_rate": 1.0975545928813158e-05, "loss": 1.0428, "step": 14478 }, { "epoch": 0.7916077225354519, "grad_norm": 2.3314082622528076, "learning_rate": 1.0970011573794486e-05, "loss": 0.9452, "step": 14479 }, { "epoch": 0.7916623953528106, "grad_norm": 2.4360928535461426, "learning_rate": 1.0964478442526676e-05, "loss": 0.8647, "step": 14480 }, { "epoch": 0.7917170681701692, "grad_norm": 2.987016201019287, "learning_rate": 1.0958946535183251e-05, "loss": 1.0267, "step": 14481 }, { "epoch": 0.7917717409875278, "grad_norm": 2.2317287921905518, "learning_rate": 1.0953415851937638e-05, "loss": 0.9208, "step": 14482 }, { "epoch": 0.7918264138048864, "grad_norm": 2.6234517097473145, "learning_rate": 1.0947886392963247e-05, "loss": 0.96, "step": 14483 }, { "epoch": 0.791881086622245, "grad_norm": 2.4511327743530273, "learning_rate": 1.0942358158433453e-05, "loss": 0.9141, "step": 14484 }, { "epoch": 0.7919357594396036, "grad_norm": 3.361917018890381, "learning_rate": 1.0936831148521588e-05, "loss": 1.2397, "step": 14485 }, { "epoch": 0.7919904322569622, "grad_norm": 3.241757392883301, "learning_rate": 1.093130536340094e-05, "loss": 0.9489, "step": 14486 }, { "epoch": 0.7920451050743209, "grad_norm": 2.7625789642333984, "learning_rate": 1.0925780803244773e-05, "loss": 1.1175, "step": 14487 }, { "epoch": 0.7920997778916795, "grad_norm": 3.3179774284362793, "learning_rate": 1.0920257468226308e-05, "loss": 0.7566, "step": 14488 }, { "epoch": 0.7921544507090381, "grad_norm": 2.3944694995880127, "learning_rate": 1.0914735358518712e-05, "loss": 1.1322, "step": 14489 }, { "epoch": 0.7922091235263967, "grad_norm": 4.424141883850098, "learning_rate": 1.0909214474295137e-05, "loss": 1.1214, "step": 14490 }, { "epoch": 0.7922637963437553, "grad_norm": 2.035337209701538, "learning_rate": 1.0903694815728677e-05, "loss": 0.9272, "step": 14491 }, { "epoch": 0.7923184691611139, "grad_norm": 2.594921350479126, "learning_rate": 1.0898176382992387e-05, "loss": 1.0234, "step": 14492 }, { "epoch": 0.7923731419784725, "grad_norm": 2.392840623855591, "learning_rate": 1.0892659176259323e-05, "loss": 0.9766, "step": 14493 }, { "epoch": 0.7924278147958312, "grad_norm": 3.1466386318206787, "learning_rate": 1.0887143195702448e-05, "loss": 1.0447, "step": 14494 }, { "epoch": 0.7924824876131898, "grad_norm": 2.441005229949951, "learning_rate": 1.0881628441494723e-05, "loss": 1.1223, "step": 14495 }, { "epoch": 0.7925371604305484, "grad_norm": 2.040827989578247, "learning_rate": 1.087611491380905e-05, "loss": 0.9879, "step": 14496 }, { "epoch": 0.792591833247907, "grad_norm": 2.846754789352417, "learning_rate": 1.0870602612818304e-05, "loss": 1.1629, "step": 14497 }, { "epoch": 0.7926465060652657, "grad_norm": 2.333137035369873, "learning_rate": 1.0865091538695322e-05, "loss": 1.1534, "step": 14498 }, { "epoch": 0.7927011788826243, "grad_norm": 2.556417465209961, "learning_rate": 1.0859581691612891e-05, "loss": 1.0104, "step": 14499 }, { "epoch": 0.7927558516999829, "grad_norm": 2.9408657550811768, "learning_rate": 1.085407307174377e-05, "loss": 0.8127, "step": 14500 }, { "epoch": 0.7928105245173416, "grad_norm": 3.0947659015655518, "learning_rate": 1.084856567926068e-05, "loss": 0.9966, "step": 14501 }, { "epoch": 0.7928651973347002, "grad_norm": 2.6031627655029297, "learning_rate": 1.0843059514336296e-05, "loss": 0.7133, "step": 14502 }, { "epoch": 0.7929198701520588, "grad_norm": 3.0601370334625244, "learning_rate": 1.0837554577143266e-05, "loss": 1.0516, "step": 14503 }, { "epoch": 0.7929745429694174, "grad_norm": 2.2444825172424316, "learning_rate": 1.0832050867854182e-05, "loss": 1.0079, "step": 14504 }, { "epoch": 0.793029215786776, "grad_norm": 2.885132312774658, "learning_rate": 1.0826548386641606e-05, "loss": 1.2273, "step": 14505 }, { "epoch": 0.7930838886041346, "grad_norm": 2.3928067684173584, "learning_rate": 1.0821047133678081e-05, "loss": 1.0007, "step": 14506 }, { "epoch": 0.7931385614214933, "grad_norm": 2.387742519378662, "learning_rate": 1.0815547109136082e-05, "loss": 0.9967, "step": 14507 }, { "epoch": 0.7931932342388519, "grad_norm": 2.4718332290649414, "learning_rate": 1.0810048313188065e-05, "loss": 1.0594, "step": 14508 }, { "epoch": 0.7932479070562105, "grad_norm": 2.832437515258789, "learning_rate": 1.0804550746006431e-05, "loss": 0.7537, "step": 14509 }, { "epoch": 0.7933025798735691, "grad_norm": 3.0737016201019287, "learning_rate": 1.0799054407763559e-05, "loss": 1.1915, "step": 14510 }, { "epoch": 0.7933572526909277, "grad_norm": 2.6798808574676514, "learning_rate": 1.0793559298631773e-05, "loss": 1.085, "step": 14511 }, { "epoch": 0.7934119255082863, "grad_norm": 2.6991209983825684, "learning_rate": 1.0788065418783372e-05, "loss": 1.077, "step": 14512 }, { "epoch": 0.7934665983256449, "grad_norm": 2.7050745487213135, "learning_rate": 1.0782572768390615e-05, "loss": 1.1132, "step": 14513 }, { "epoch": 0.7935212711430036, "grad_norm": 3.1242313385009766, "learning_rate": 1.0777081347625717e-05, "loss": 1.2034, "step": 14514 }, { "epoch": 0.7935759439603622, "grad_norm": 3.475402593612671, "learning_rate": 1.0771591156660853e-05, "loss": 1.0683, "step": 14515 }, { "epoch": 0.7936306167777208, "grad_norm": 2.5573036670684814, "learning_rate": 1.0766102195668166e-05, "loss": 1.0121, "step": 14516 }, { "epoch": 0.7936852895950794, "grad_norm": 2.097095489501953, "learning_rate": 1.0760614464819757e-05, "loss": 0.93, "step": 14517 }, { "epoch": 0.793739962412438, "grad_norm": 2.8175318241119385, "learning_rate": 1.0755127964287676e-05, "loss": 0.9559, "step": 14518 }, { "epoch": 0.7937946352297967, "grad_norm": 3.168139696121216, "learning_rate": 1.0749642694243971e-05, "loss": 1.1073, "step": 14519 }, { "epoch": 0.7938493080471553, "grad_norm": 3.184088706970215, "learning_rate": 1.0744158654860619e-05, "loss": 0.9044, "step": 14520 }, { "epoch": 0.793903980864514, "grad_norm": 2.350405216217041, "learning_rate": 1.073867584630957e-05, "loss": 1.1015, "step": 14521 }, { "epoch": 0.7939586536818726, "grad_norm": 3.6433162689208984, "learning_rate": 1.0733194268762725e-05, "loss": 1.2507, "step": 14522 }, { "epoch": 0.7940133264992312, "grad_norm": 2.8114397525787354, "learning_rate": 1.0727713922391957e-05, "loss": 0.9849, "step": 14523 }, { "epoch": 0.7940679993165898, "grad_norm": 2.336899518966675, "learning_rate": 1.0722234807369103e-05, "loss": 1.1483, "step": 14524 }, { "epoch": 0.7941226721339484, "grad_norm": 2.738154888153076, "learning_rate": 1.0716756923865946e-05, "loss": 0.8378, "step": 14525 }, { "epoch": 0.794177344951307, "grad_norm": 2.462158441543579, "learning_rate": 1.0711280272054242e-05, "loss": 1.0029, "step": 14526 }, { "epoch": 0.7942320177686656, "grad_norm": 2.493476629257202, "learning_rate": 1.070580485210571e-05, "loss": 1.0378, "step": 14527 }, { "epoch": 0.7942866905860243, "grad_norm": 2.93727445602417, "learning_rate": 1.0700330664192033e-05, "loss": 0.9953, "step": 14528 }, { "epoch": 0.7943413634033829, "grad_norm": 2.8241498470306396, "learning_rate": 1.0694857708484824e-05, "loss": 0.9635, "step": 14529 }, { "epoch": 0.7943960362207415, "grad_norm": 2.117546796798706, "learning_rate": 1.0689385985155715e-05, "loss": 1.0035, "step": 14530 }, { "epoch": 0.7944507090381001, "grad_norm": 2.660234212875366, "learning_rate": 1.0683915494376257e-05, "loss": 1.0916, "step": 14531 }, { "epoch": 0.7945053818554587, "grad_norm": 2.342010974884033, "learning_rate": 1.0678446236317962e-05, "loss": 0.9657, "step": 14532 }, { "epoch": 0.7945600546728173, "grad_norm": 2.3250906467437744, "learning_rate": 1.0672978211152323e-05, "loss": 0.847, "step": 14533 }, { "epoch": 0.794614727490176, "grad_norm": 3.305694580078125, "learning_rate": 1.0667511419050785e-05, "loss": 1.1004, "step": 14534 }, { "epoch": 0.7946694003075346, "grad_norm": 3.9169633388519287, "learning_rate": 1.0662045860184755e-05, "loss": 1.1416, "step": 14535 }, { "epoch": 0.7947240731248932, "grad_norm": 2.570180892944336, "learning_rate": 1.0656581534725596e-05, "loss": 1.1097, "step": 14536 }, { "epoch": 0.7947787459422518, "grad_norm": 2.408212661743164, "learning_rate": 1.0651118442844637e-05, "loss": 0.8067, "step": 14537 }, { "epoch": 0.7948334187596104, "grad_norm": 2.6697146892547607, "learning_rate": 1.0645656584713171e-05, "loss": 1.1309, "step": 14538 }, { "epoch": 0.794888091576969, "grad_norm": 4.71291971206665, "learning_rate": 1.0640195960502436e-05, "loss": 1.0682, "step": 14539 }, { "epoch": 0.7949427643943277, "grad_norm": 2.12097430229187, "learning_rate": 1.0634736570383669e-05, "loss": 0.864, "step": 14540 }, { "epoch": 0.7949974372116864, "grad_norm": 2.681284189224243, "learning_rate": 1.0629278414528038e-05, "loss": 0.9897, "step": 14541 }, { "epoch": 0.795052110029045, "grad_norm": 2.353158712387085, "learning_rate": 1.0623821493106673e-05, "loss": 1.0039, "step": 14542 }, { "epoch": 0.7951067828464036, "grad_norm": 2.9083001613616943, "learning_rate": 1.061836580629067e-05, "loss": 0.9473, "step": 14543 }, { "epoch": 0.7951614556637622, "grad_norm": 2.422701358795166, "learning_rate": 1.0612911354251093e-05, "loss": 1.0288, "step": 14544 }, { "epoch": 0.7952161284811208, "grad_norm": 3.372826337814331, "learning_rate": 1.0607458137158954e-05, "loss": 1.0435, "step": 14545 }, { "epoch": 0.7952708012984794, "grad_norm": 2.2094602584838867, "learning_rate": 1.0602006155185241e-05, "loss": 0.8665, "step": 14546 }, { "epoch": 0.795325474115838, "grad_norm": 2.772326946258545, "learning_rate": 1.0596555408500892e-05, "loss": 0.9009, "step": 14547 }, { "epoch": 0.7953801469331967, "grad_norm": 4.434857368469238, "learning_rate": 1.059110589727681e-05, "loss": 1.0333, "step": 14548 }, { "epoch": 0.7954348197505553, "grad_norm": 3.208765745162964, "learning_rate": 1.0585657621683848e-05, "loss": 0.9771, "step": 14549 }, { "epoch": 0.7954894925679139, "grad_norm": 3.1573867797851562, "learning_rate": 1.0580210581892863e-05, "loss": 1.0277, "step": 14550 }, { "epoch": 0.7955441653852725, "grad_norm": 3.761233329772949, "learning_rate": 1.057476477807462e-05, "loss": 0.9869, "step": 14551 }, { "epoch": 0.7955988382026311, "grad_norm": 2.513490676879883, "learning_rate": 1.0569320210399869e-05, "loss": 0.8139, "step": 14552 }, { "epoch": 0.7956535110199897, "grad_norm": 2.7390294075012207, "learning_rate": 1.0563876879039325e-05, "loss": 1.191, "step": 14553 }, { "epoch": 0.7957081838373483, "grad_norm": 2.974768877029419, "learning_rate": 1.0558434784163656e-05, "loss": 0.9933, "step": 14554 }, { "epoch": 0.795762856654707, "grad_norm": 2.772599458694458, "learning_rate": 1.0552993925943493e-05, "loss": 1.083, "step": 14555 }, { "epoch": 0.7958175294720656, "grad_norm": 3.275486946105957, "learning_rate": 1.0547554304549429e-05, "loss": 1.0792, "step": 14556 }, { "epoch": 0.7958722022894242, "grad_norm": 2.728973388671875, "learning_rate": 1.0542115920152024e-05, "loss": 0.933, "step": 14557 }, { "epoch": 0.7959268751067828, "grad_norm": 2.622124195098877, "learning_rate": 1.0536678772921788e-05, "loss": 1.0345, "step": 14558 }, { "epoch": 0.7959815479241414, "grad_norm": 2.5171425342559814, "learning_rate": 1.0531242863029183e-05, "loss": 0.8878, "step": 14559 }, { "epoch": 0.7960362207415, "grad_norm": 2.93241024017334, "learning_rate": 1.0525808190644675e-05, "loss": 1.1666, "step": 14560 }, { "epoch": 0.7960908935588588, "grad_norm": 2.60620379447937, "learning_rate": 1.0520374755938656e-05, "loss": 0.9687, "step": 14561 }, { "epoch": 0.7961455663762174, "grad_norm": 2.854186534881592, "learning_rate": 1.0514942559081486e-05, "loss": 0.978, "step": 14562 }, { "epoch": 0.796200239193576, "grad_norm": 2.776306629180908, "learning_rate": 1.0509511600243478e-05, "loss": 0.8994, "step": 14563 }, { "epoch": 0.7962549120109346, "grad_norm": 2.014773368835449, "learning_rate": 1.0504081879594923e-05, "loss": 0.9747, "step": 14564 }, { "epoch": 0.7963095848282932, "grad_norm": 2.3460965156555176, "learning_rate": 1.0498653397306057e-05, "loss": 1.0278, "step": 14565 }, { "epoch": 0.7963642576456518, "grad_norm": 2.5606608390808105, "learning_rate": 1.0493226153547098e-05, "loss": 1.0052, "step": 14566 }, { "epoch": 0.7964189304630104, "grad_norm": 2.7330026626586914, "learning_rate": 1.0487800148488203e-05, "loss": 0.9015, "step": 14567 }, { "epoch": 0.7964736032803691, "grad_norm": 2.673900842666626, "learning_rate": 1.0482375382299486e-05, "loss": 0.8834, "step": 14568 }, { "epoch": 0.7965282760977277, "grad_norm": 2.5689687728881836, "learning_rate": 1.0476951855151063e-05, "loss": 1.1072, "step": 14569 }, { "epoch": 0.7965829489150863, "grad_norm": 2.314012289047241, "learning_rate": 1.0471529567212973e-05, "loss": 0.8299, "step": 14570 }, { "epoch": 0.7966376217324449, "grad_norm": 2.478888511657715, "learning_rate": 1.0466108518655233e-05, "loss": 1.1394, "step": 14571 }, { "epoch": 0.7966922945498035, "grad_norm": 2.323352813720703, "learning_rate": 1.0460688709647803e-05, "loss": 0.9321, "step": 14572 }, { "epoch": 0.7967469673671621, "grad_norm": 2.85259747505188, "learning_rate": 1.0455270140360623e-05, "loss": 1.1362, "step": 14573 }, { "epoch": 0.7968016401845207, "grad_norm": 2.689279794692993, "learning_rate": 1.0449852810963584e-05, "loss": 0.9605, "step": 14574 }, { "epoch": 0.7968563130018794, "grad_norm": 4.466980934143066, "learning_rate": 1.0444436721626544e-05, "loss": 1.1812, "step": 14575 }, { "epoch": 0.796910985819238, "grad_norm": 3.1127729415893555, "learning_rate": 1.0439021872519322e-05, "loss": 0.9271, "step": 14576 }, { "epoch": 0.7969656586365966, "grad_norm": 2.5367140769958496, "learning_rate": 1.0433608263811694e-05, "loss": 1.0183, "step": 14577 }, { "epoch": 0.7970203314539552, "grad_norm": 3.3161745071411133, "learning_rate": 1.0428195895673387e-05, "loss": 0.9917, "step": 14578 }, { "epoch": 0.7970750042713138, "grad_norm": 2.442094326019287, "learning_rate": 1.0422784768274119e-05, "loss": 1.0792, "step": 14579 }, { "epoch": 0.7971296770886724, "grad_norm": 2.940586566925049, "learning_rate": 1.0417374881783548e-05, "loss": 1.0933, "step": 14580 }, { "epoch": 0.797184349906031, "grad_norm": 2.4614994525909424, "learning_rate": 1.0411966236371295e-05, "loss": 1.0616, "step": 14581 }, { "epoch": 0.7972390227233898, "grad_norm": 2.836711883544922, "learning_rate": 1.0406558832206941e-05, "loss": 0.9906, "step": 14582 }, { "epoch": 0.7972936955407484, "grad_norm": 3.3390920162200928, "learning_rate": 1.0401152669460028e-05, "loss": 0.925, "step": 14583 }, { "epoch": 0.797348368358107, "grad_norm": 2.370717763900757, "learning_rate": 1.0395747748300066e-05, "loss": 0.7882, "step": 14584 }, { "epoch": 0.7974030411754656, "grad_norm": 2.4058918952941895, "learning_rate": 1.0390344068896518e-05, "loss": 0.9123, "step": 14585 }, { "epoch": 0.7974577139928242, "grad_norm": 2.292973756790161, "learning_rate": 1.038494163141881e-05, "loss": 0.9734, "step": 14586 }, { "epoch": 0.7975123868101828, "grad_norm": 5.389148235321045, "learning_rate": 1.037954043603634e-05, "loss": 0.9753, "step": 14587 }, { "epoch": 0.7975670596275415, "grad_norm": 2.6256566047668457, "learning_rate": 1.0374140482918432e-05, "loss": 1.0521, "step": 14588 }, { "epoch": 0.7976217324449001, "grad_norm": 2.58140230178833, "learning_rate": 1.0368741772234436e-05, "loss": 0.9193, "step": 14589 }, { "epoch": 0.7976764052622587, "grad_norm": 3.0098283290863037, "learning_rate": 1.0363344304153599e-05, "loss": 1.3131, "step": 14590 }, { "epoch": 0.7977310780796173, "grad_norm": 3.289263963699341, "learning_rate": 1.0357948078845165e-05, "loss": 0.8318, "step": 14591 }, { "epoch": 0.7977857508969759, "grad_norm": 2.389500379562378, "learning_rate": 1.0352553096478313e-05, "loss": 1.0468, "step": 14592 }, { "epoch": 0.7978404237143345, "grad_norm": 2.345841646194458, "learning_rate": 1.0347159357222213e-05, "loss": 1.0275, "step": 14593 }, { "epoch": 0.7978950965316931, "grad_norm": 2.6556472778320312, "learning_rate": 1.0341766861245972e-05, "loss": 0.9796, "step": 14594 }, { "epoch": 0.7979497693490518, "grad_norm": 2.1369853019714355, "learning_rate": 1.0336375608718674e-05, "loss": 0.9223, "step": 14595 }, { "epoch": 0.7980044421664104, "grad_norm": 2.4093263149261475, "learning_rate": 1.0330985599809345e-05, "loss": 0.9258, "step": 14596 }, { "epoch": 0.798059114983769, "grad_norm": 2.771148204803467, "learning_rate": 1.0325596834686995e-05, "loss": 0.9897, "step": 14597 }, { "epoch": 0.7981137878011276, "grad_norm": 2.3211047649383545, "learning_rate": 1.0320209313520568e-05, "loss": 1.0206, "step": 14598 }, { "epoch": 0.7981684606184862, "grad_norm": 3.1261179447174072, "learning_rate": 1.0314823036479015e-05, "loss": 1.1622, "step": 14599 }, { "epoch": 0.7982231334358448, "grad_norm": 2.3244073390960693, "learning_rate": 1.0309438003731193e-05, "loss": 1.1021, "step": 14600 }, { "epoch": 0.7982778062532034, "grad_norm": 2.5404279232025146, "learning_rate": 1.0304054215445957e-05, "loss": 1.0099, "step": 14601 }, { "epoch": 0.7983324790705622, "grad_norm": 4.015076160430908, "learning_rate": 1.0298671671792104e-05, "loss": 1.2212, "step": 14602 }, { "epoch": 0.7983871518879208, "grad_norm": 2.322139263153076, "learning_rate": 1.0293290372938403e-05, "loss": 0.8701, "step": 14603 }, { "epoch": 0.7984418247052794, "grad_norm": 2.4348952770233154, "learning_rate": 1.0287910319053578e-05, "loss": 1.1256, "step": 14604 }, { "epoch": 0.798496497522638, "grad_norm": 2.729556083679199, "learning_rate": 1.0282531510306315e-05, "loss": 1.0804, "step": 14605 }, { "epoch": 0.7985511703399966, "grad_norm": 3.279980421066284, "learning_rate": 1.0277153946865264e-05, "loss": 1.0055, "step": 14606 }, { "epoch": 0.7986058431573552, "grad_norm": 2.2510242462158203, "learning_rate": 1.0271777628899032e-05, "loss": 1.0144, "step": 14607 }, { "epoch": 0.7986605159747138, "grad_norm": 3.3628196716308594, "learning_rate": 1.0266402556576177e-05, "loss": 1.1473, "step": 14608 }, { "epoch": 0.7987151887920725, "grad_norm": 3.1327176094055176, "learning_rate": 1.0261028730065253e-05, "loss": 1.0989, "step": 14609 }, { "epoch": 0.7987698616094311, "grad_norm": 2.4353127479553223, "learning_rate": 1.0255656149534743e-05, "loss": 1.1284, "step": 14610 }, { "epoch": 0.7988245344267897, "grad_norm": 2.432316541671753, "learning_rate": 1.0250284815153094e-05, "loss": 1.0439, "step": 14611 }, { "epoch": 0.7988792072441483, "grad_norm": 2.9391396045684814, "learning_rate": 1.0244914727088722e-05, "loss": 0.9617, "step": 14612 }, { "epoch": 0.7989338800615069, "grad_norm": 2.6767728328704834, "learning_rate": 1.0239545885510004e-05, "loss": 0.9502, "step": 14613 }, { "epoch": 0.7989885528788655, "grad_norm": 4.736365795135498, "learning_rate": 1.0234178290585279e-05, "loss": 1.2411, "step": 14614 }, { "epoch": 0.7990432256962242, "grad_norm": 2.0811221599578857, "learning_rate": 1.022881194248283e-05, "loss": 1.0444, "step": 14615 }, { "epoch": 0.7990978985135828, "grad_norm": 2.49367356300354, "learning_rate": 1.022344684137092e-05, "loss": 0.9663, "step": 14616 }, { "epoch": 0.7991525713309414, "grad_norm": 2.4040579795837402, "learning_rate": 1.0218082987417771e-05, "loss": 1.0833, "step": 14617 }, { "epoch": 0.7992072441483, "grad_norm": 2.602189540863037, "learning_rate": 1.0212720380791547e-05, "loss": 1.0947, "step": 14618 }, { "epoch": 0.7992619169656586, "grad_norm": 4.919745445251465, "learning_rate": 1.0207359021660417e-05, "loss": 0.9898, "step": 14619 }, { "epoch": 0.7993165897830172, "grad_norm": 2.594987154006958, "learning_rate": 1.0201998910192462e-05, "loss": 1.1107, "step": 14620 }, { "epoch": 0.7993712626003758, "grad_norm": 3.2699620723724365, "learning_rate": 1.0196640046555744e-05, "loss": 0.8344, "step": 14621 }, { "epoch": 0.7994259354177345, "grad_norm": 2.6930532455444336, "learning_rate": 1.0191282430918292e-05, "loss": 1.0365, "step": 14622 }, { "epoch": 0.7994806082350931, "grad_norm": 2.0935566425323486, "learning_rate": 1.0185926063448082e-05, "loss": 0.8435, "step": 14623 }, { "epoch": 0.7995352810524518, "grad_norm": 2.3973796367645264, "learning_rate": 1.0180570944313062e-05, "loss": 0.8372, "step": 14624 }, { "epoch": 0.7995899538698104, "grad_norm": 2.583014488220215, "learning_rate": 1.0175217073681136e-05, "loss": 1.078, "step": 14625 }, { "epoch": 0.799644626687169, "grad_norm": 3.172420024871826, "learning_rate": 1.0169864451720174e-05, "loss": 0.9625, "step": 14626 }, { "epoch": 0.7996992995045276, "grad_norm": 3.015428304672241, "learning_rate": 1.016451307859798e-05, "loss": 1.1338, "step": 14627 }, { "epoch": 0.7997539723218862, "grad_norm": 3.0434250831604004, "learning_rate": 1.0159162954482377e-05, "loss": 1.0015, "step": 14628 }, { "epoch": 0.7998086451392449, "grad_norm": 3.5406994819641113, "learning_rate": 1.0153814079541096e-05, "loss": 1.1429, "step": 14629 }, { "epoch": 0.7998633179566035, "grad_norm": 2.801909923553467, "learning_rate": 1.0148466453941851e-05, "loss": 1.092, "step": 14630 }, { "epoch": 0.7999179907739621, "grad_norm": 2.8215315341949463, "learning_rate": 1.0143120077852308e-05, "loss": 0.9725, "step": 14631 }, { "epoch": 0.7999726635913207, "grad_norm": 2.09320330619812, "learning_rate": 1.0137774951440094e-05, "loss": 0.9469, "step": 14632 }, { "epoch": 0.8000273364086793, "grad_norm": 2.891716241836548, "learning_rate": 1.0132431074872806e-05, "loss": 1.1454, "step": 14633 }, { "epoch": 0.8000820092260379, "grad_norm": 2.71506929397583, "learning_rate": 1.0127088448318e-05, "loss": 1.0114, "step": 14634 }, { "epoch": 0.8001366820433965, "grad_norm": 2.8231654167175293, "learning_rate": 1.0121747071943182e-05, "loss": 0.8742, "step": 14635 }, { "epoch": 0.8001913548607552, "grad_norm": 2.5747575759887695, "learning_rate": 1.011640694591583e-05, "loss": 0.9064, "step": 14636 }, { "epoch": 0.8002460276781138, "grad_norm": 2.546525716781616, "learning_rate": 1.0111068070403362e-05, "loss": 1.0829, "step": 14637 }, { "epoch": 0.8003007004954724, "grad_norm": 4.16175651550293, "learning_rate": 1.0105730445573209e-05, "loss": 0.9898, "step": 14638 }, { "epoch": 0.800355373312831, "grad_norm": 2.4944186210632324, "learning_rate": 1.01003940715927e-05, "loss": 0.9415, "step": 14639 }, { "epoch": 0.8004100461301896, "grad_norm": 2.9292290210723877, "learning_rate": 1.0095058948629167e-05, "loss": 0.948, "step": 14640 }, { "epoch": 0.8004647189475482, "grad_norm": 2.1911213397979736, "learning_rate": 1.0089725076849882e-05, "loss": 0.8859, "step": 14641 }, { "epoch": 0.8005193917649069, "grad_norm": 2.319079637527466, "learning_rate": 1.0084392456422082e-05, "loss": 1.0458, "step": 14642 }, { "epoch": 0.8005740645822655, "grad_norm": 2.541999340057373, "learning_rate": 1.0079061087512964e-05, "loss": 1.0375, "step": 14643 }, { "epoch": 0.8006287373996241, "grad_norm": 2.7816731929779053, "learning_rate": 1.0073730970289697e-05, "loss": 1.0875, "step": 14644 }, { "epoch": 0.8006834102169827, "grad_norm": 2.6594526767730713, "learning_rate": 1.00684021049194e-05, "loss": 1.0528, "step": 14645 }, { "epoch": 0.8007380830343414, "grad_norm": 2.909172534942627, "learning_rate": 1.0063074491569146e-05, "loss": 1.1495, "step": 14646 }, { "epoch": 0.8007927558517, "grad_norm": 2.97365665435791, "learning_rate": 1.0057748130405975e-05, "loss": 1.0559, "step": 14647 }, { "epoch": 0.8008474286690586, "grad_norm": 2.8174047470092773, "learning_rate": 1.0052423021596913e-05, "loss": 0.984, "step": 14648 }, { "epoch": 0.8009021014864173, "grad_norm": 2.679270029067993, "learning_rate": 1.004709916530891e-05, "loss": 1.033, "step": 14649 }, { "epoch": 0.8009567743037759, "grad_norm": 2.344999313354492, "learning_rate": 1.0041776561708893e-05, "loss": 0.8522, "step": 14650 }, { "epoch": 0.8010114471211345, "grad_norm": 2.5858092308044434, "learning_rate": 1.0036455210963742e-05, "loss": 1.0126, "step": 14651 }, { "epoch": 0.8010661199384931, "grad_norm": 2.0525026321411133, "learning_rate": 1.003113511324031e-05, "loss": 1.0356, "step": 14652 }, { "epoch": 0.8011207927558517, "grad_norm": 3.3645060062408447, "learning_rate": 1.0025816268705402e-05, "loss": 0.9913, "step": 14653 }, { "epoch": 0.8011754655732103, "grad_norm": 2.5665090084075928, "learning_rate": 1.0020498677525786e-05, "loss": 1.067, "step": 14654 }, { "epoch": 0.8012301383905689, "grad_norm": 2.7771525382995605, "learning_rate": 1.0015182339868185e-05, "loss": 1.1411, "step": 14655 }, { "epoch": 0.8012848112079276, "grad_norm": 2.4194679260253906, "learning_rate": 1.0009867255899297e-05, "loss": 0.9427, "step": 14656 }, { "epoch": 0.8013394840252862, "grad_norm": 3.0024173259735107, "learning_rate": 1.0004553425785752e-05, "loss": 1.0682, "step": 14657 }, { "epoch": 0.8013941568426448, "grad_norm": 2.3877248764038086, "learning_rate": 9.999240849694186e-06, "loss": 0.9907, "step": 14658 }, { "epoch": 0.8014488296600034, "grad_norm": 2.694091320037842, "learning_rate": 9.993929527791163e-06, "loss": 1.1707, "step": 14659 }, { "epoch": 0.801503502477362, "grad_norm": 3.0008773803710938, "learning_rate": 9.988619460243209e-06, "loss": 1.1437, "step": 14660 }, { "epoch": 0.8015581752947206, "grad_norm": 2.624643325805664, "learning_rate": 9.98331064721682e-06, "loss": 1.1002, "step": 14661 }, { "epoch": 0.8016128481120792, "grad_norm": 4.128406524658203, "learning_rate": 9.978003088878445e-06, "loss": 0.9625, "step": 14662 }, { "epoch": 0.8016675209294379, "grad_norm": 2.9863271713256836, "learning_rate": 9.972696785394508e-06, "loss": 1.1491, "step": 14663 }, { "epoch": 0.8017221937467965, "grad_norm": 2.288912296295166, "learning_rate": 9.967391736931376e-06, "loss": 0.8929, "step": 14664 }, { "epoch": 0.8017768665641551, "grad_norm": 2.526435136795044, "learning_rate": 9.96208794365538e-06, "loss": 1.0276, "step": 14665 }, { "epoch": 0.8018315393815137, "grad_norm": 2.6863465309143066, "learning_rate": 9.956785405732822e-06, "loss": 1.1484, "step": 14666 }, { "epoch": 0.8018862121988724, "grad_norm": 3.1789731979370117, "learning_rate": 9.951484123329941e-06, "loss": 1.0598, "step": 14667 }, { "epoch": 0.801940885016231, "grad_norm": 2.9959142208099365, "learning_rate": 9.946184096612987e-06, "loss": 1.2204, "step": 14668 }, { "epoch": 0.8019955578335897, "grad_norm": 3.2023305892944336, "learning_rate": 9.940885325748116e-06, "loss": 1.1516, "step": 14669 }, { "epoch": 0.8020502306509483, "grad_norm": 3.4400954246520996, "learning_rate": 9.935587810901476e-06, "loss": 1.1436, "step": 14670 }, { "epoch": 0.8021049034683069, "grad_norm": 2.5628457069396973, "learning_rate": 9.930291552239157e-06, "loss": 0.9685, "step": 14671 }, { "epoch": 0.8021595762856655, "grad_norm": 2.8365302085876465, "learning_rate": 9.924996549927228e-06, "loss": 1.2209, "step": 14672 }, { "epoch": 0.8022142491030241, "grad_norm": 3.180111885070801, "learning_rate": 9.919702804131697e-06, "loss": 1.0421, "step": 14673 }, { "epoch": 0.8022689219203827, "grad_norm": 2.7863800525665283, "learning_rate": 9.914410315018551e-06, "loss": 1.044, "step": 14674 }, { "epoch": 0.8023235947377413, "grad_norm": 2.5075480937957764, "learning_rate": 9.909119082753737e-06, "loss": 1.1557, "step": 14675 }, { "epoch": 0.8023782675551, "grad_norm": 2.804678201675415, "learning_rate": 9.90382910750315e-06, "loss": 1.1348, "step": 14676 }, { "epoch": 0.8024329403724586, "grad_norm": 3.6951873302459717, "learning_rate": 9.898540389432648e-06, "loss": 1.0798, "step": 14677 }, { "epoch": 0.8024876131898172, "grad_norm": 2.7828876972198486, "learning_rate": 9.893252928708063e-06, "loss": 1.1658, "step": 14678 }, { "epoch": 0.8025422860071758, "grad_norm": 2.9681434631347656, "learning_rate": 9.887966725495162e-06, "loss": 0.9821, "step": 14679 }, { "epoch": 0.8025969588245344, "grad_norm": 2.491976261138916, "learning_rate": 9.882681779959717e-06, "loss": 0.866, "step": 14680 }, { "epoch": 0.802651631641893, "grad_norm": 2.1242432594299316, "learning_rate": 9.87739809226742e-06, "loss": 0.9524, "step": 14681 }, { "epoch": 0.8027063044592516, "grad_norm": 3.2923836708068848, "learning_rate": 9.872115662583936e-06, "loss": 0.9054, "step": 14682 }, { "epoch": 0.8027609772766103, "grad_norm": 2.3464343547821045, "learning_rate": 9.866834491074883e-06, "loss": 0.9287, "step": 14683 }, { "epoch": 0.8028156500939689, "grad_norm": 2.5898642539978027, "learning_rate": 9.861554577905863e-06, "loss": 0.9638, "step": 14684 }, { "epoch": 0.8028703229113275, "grad_norm": 2.364069938659668, "learning_rate": 9.856275923242408e-06, "loss": 0.9703, "step": 14685 }, { "epoch": 0.8029249957286861, "grad_norm": 2.7137341499328613, "learning_rate": 9.850998527250033e-06, "loss": 1.1183, "step": 14686 }, { "epoch": 0.8029796685460447, "grad_norm": 2.5525496006011963, "learning_rate": 9.845722390094208e-06, "loss": 0.9967, "step": 14687 }, { "epoch": 0.8030343413634033, "grad_norm": 2.6045773029327393, "learning_rate": 9.840447511940354e-06, "loss": 0.9618, "step": 14688 }, { "epoch": 0.803089014180762, "grad_norm": 2.432509422302246, "learning_rate": 9.83517389295387e-06, "loss": 0.9826, "step": 14689 }, { "epoch": 0.8031436869981207, "grad_norm": 3.3676507472991943, "learning_rate": 9.829901533300095e-06, "loss": 1.021, "step": 14690 }, { "epoch": 0.8031983598154793, "grad_norm": 2.9789810180664062, "learning_rate": 9.82463043314435e-06, "loss": 0.9603, "step": 14691 }, { "epoch": 0.8032530326328379, "grad_norm": 3.9644789695739746, "learning_rate": 9.819360592651889e-06, "loss": 0.8966, "step": 14692 }, { "epoch": 0.8033077054501965, "grad_norm": 2.4229907989501953, "learning_rate": 9.814092011987964e-06, "loss": 0.8723, "step": 14693 }, { "epoch": 0.8033623782675551, "grad_norm": 2.5600087642669678, "learning_rate": 9.808824691317753e-06, "loss": 1.1997, "step": 14694 }, { "epoch": 0.8034170510849137, "grad_norm": 2.2724056243896484, "learning_rate": 9.803558630806419e-06, "loss": 1.1231, "step": 14695 }, { "epoch": 0.8034717239022724, "grad_norm": 2.8431708812713623, "learning_rate": 9.798293830619065e-06, "loss": 0.9974, "step": 14696 }, { "epoch": 0.803526396719631, "grad_norm": 2.233938694000244, "learning_rate": 9.793030290920768e-06, "loss": 1.0238, "step": 14697 }, { "epoch": 0.8035810695369896, "grad_norm": 2.176939010620117, "learning_rate": 9.787768011876563e-06, "loss": 0.9223, "step": 14698 }, { "epoch": 0.8036357423543482, "grad_norm": 2.743016242980957, "learning_rate": 9.782506993651441e-06, "loss": 1.1052, "step": 14699 }, { "epoch": 0.8036904151717068, "grad_norm": 4.032900810241699, "learning_rate": 9.777247236410359e-06, "loss": 0.9954, "step": 14700 }, { "epoch": 0.8037450879890654, "grad_norm": 2.284093141555786, "learning_rate": 9.771988740318227e-06, "loss": 0.8805, "step": 14701 }, { "epoch": 0.803799760806424, "grad_norm": 2.486333131790161, "learning_rate": 9.766731505539928e-06, "loss": 0.9056, "step": 14702 }, { "epoch": 0.8038544336237827, "grad_norm": 2.4570674896240234, "learning_rate": 9.761475532240294e-06, "loss": 1.0868, "step": 14703 }, { "epoch": 0.8039091064411413, "grad_norm": 3.0228147506713867, "learning_rate": 9.756220820584116e-06, "loss": 1.1307, "step": 14704 }, { "epoch": 0.8039637792584999, "grad_norm": 2.264674663543701, "learning_rate": 9.750967370736146e-06, "loss": 1.0207, "step": 14705 }, { "epoch": 0.8040184520758585, "grad_norm": 3.0250332355499268, "learning_rate": 9.745715182861132e-06, "loss": 1.1298, "step": 14706 }, { "epoch": 0.8040731248932171, "grad_norm": 2.2537527084350586, "learning_rate": 9.740464257123727e-06, "loss": 1.0312, "step": 14707 }, { "epoch": 0.8041277977105757, "grad_norm": 3.5243265628814697, "learning_rate": 9.735214593688569e-06, "loss": 0.9835, "step": 14708 }, { "epoch": 0.8041824705279343, "grad_norm": 2.587337017059326, "learning_rate": 9.729966192720269e-06, "loss": 1.1558, "step": 14709 }, { "epoch": 0.8042371433452931, "grad_norm": 3.3366541862487793, "learning_rate": 9.724719054383375e-06, "loss": 1.157, "step": 14710 }, { "epoch": 0.8042918161626517, "grad_norm": 2.2294468879699707, "learning_rate": 9.719473178842408e-06, "loss": 0.9496, "step": 14711 }, { "epoch": 0.8043464889800103, "grad_norm": 2.8977363109588623, "learning_rate": 9.714228566261852e-06, "loss": 1.1319, "step": 14712 }, { "epoch": 0.8044011617973689, "grad_norm": 2.292567253112793, "learning_rate": 9.708985216806138e-06, "loss": 0.8934, "step": 14713 }, { "epoch": 0.8044558346147275, "grad_norm": 2.321568012237549, "learning_rate": 9.703743130639681e-06, "loss": 1.1072, "step": 14714 }, { "epoch": 0.8045105074320861, "grad_norm": 2.689218282699585, "learning_rate": 9.698502307926831e-06, "loss": 1.0171, "step": 14715 }, { "epoch": 0.8045651802494447, "grad_norm": 2.075249195098877, "learning_rate": 9.6932627488319e-06, "loss": 0.9121, "step": 14716 }, { "epoch": 0.8046198530668034, "grad_norm": 2.2575085163116455, "learning_rate": 9.688024453519196e-06, "loss": 0.7285, "step": 14717 }, { "epoch": 0.804674525884162, "grad_norm": 2.9428181648254395, "learning_rate": 9.682787422152945e-06, "loss": 1.1138, "step": 14718 }, { "epoch": 0.8047291987015206, "grad_norm": 2.9812984466552734, "learning_rate": 9.677551654897355e-06, "loss": 1.0038, "step": 14719 }, { "epoch": 0.8047838715188792, "grad_norm": 2.479020118713379, "learning_rate": 9.672317151916583e-06, "loss": 1.2855, "step": 14720 }, { "epoch": 0.8048385443362378, "grad_norm": 2.454857110977173, "learning_rate": 9.667083913374758e-06, "loss": 1.0168, "step": 14721 }, { "epoch": 0.8048932171535964, "grad_norm": 2.876361131668091, "learning_rate": 9.661851939435962e-06, "loss": 1.139, "step": 14722 }, { "epoch": 0.804947889970955, "grad_norm": 4.204779148101807, "learning_rate": 9.656621230264234e-06, "loss": 0.9688, "step": 14723 }, { "epoch": 0.8050025627883137, "grad_norm": 2.7295680046081543, "learning_rate": 9.651391786023584e-06, "loss": 0.9925, "step": 14724 }, { "epoch": 0.8050572356056723, "grad_norm": 2.8894808292388916, "learning_rate": 9.646163606877961e-06, "loss": 1.0472, "step": 14725 }, { "epoch": 0.8051119084230309, "grad_norm": 4.557424545288086, "learning_rate": 9.640936692991315e-06, "loss": 1.0694, "step": 14726 }, { "epoch": 0.8051665812403895, "grad_norm": 2.78047513961792, "learning_rate": 9.635711044527517e-06, "loss": 1.1767, "step": 14727 }, { "epoch": 0.8052212540577481, "grad_norm": 2.9306981563568115, "learning_rate": 9.630486661650422e-06, "loss": 0.9335, "step": 14728 }, { "epoch": 0.8052759268751067, "grad_norm": 2.84594464302063, "learning_rate": 9.625263544523827e-06, "loss": 1.0142, "step": 14729 }, { "epoch": 0.8053305996924655, "grad_norm": 2.524984121322632, "learning_rate": 9.620041693311499e-06, "loss": 1.1699, "step": 14730 }, { "epoch": 0.8053852725098241, "grad_norm": 2.577056884765625, "learning_rate": 9.614821108177163e-06, "loss": 0.7818, "step": 14731 }, { "epoch": 0.8054399453271827, "grad_norm": 2.8526580333709717, "learning_rate": 9.609601789284517e-06, "loss": 1.1899, "step": 14732 }, { "epoch": 0.8054946181445413, "grad_norm": 2.318129062652588, "learning_rate": 9.604383736797195e-06, "loss": 1.0045, "step": 14733 }, { "epoch": 0.8055492909618999, "grad_norm": 3.8691885471343994, "learning_rate": 9.599166950878807e-06, "loss": 1.1704, "step": 14734 }, { "epoch": 0.8056039637792585, "grad_norm": 3.0540008544921875, "learning_rate": 9.593951431692916e-06, "loss": 1.2223, "step": 14735 }, { "epoch": 0.8056586365966171, "grad_norm": 2.3237524032592773, "learning_rate": 9.588737179403067e-06, "loss": 0.9887, "step": 14736 }, { "epoch": 0.8057133094139758, "grad_norm": 3.1467361450195312, "learning_rate": 9.583524194172738e-06, "loss": 0.8805, "step": 14737 }, { "epoch": 0.8057679822313344, "grad_norm": 2.4629247188568115, "learning_rate": 9.578312476165379e-06, "loss": 1.013, "step": 14738 }, { "epoch": 0.805822655048693, "grad_norm": 2.598858594894409, "learning_rate": 9.573102025544395e-06, "loss": 0.9181, "step": 14739 }, { "epoch": 0.8058773278660516, "grad_norm": 2.4915266036987305, "learning_rate": 9.567892842473164e-06, "loss": 0.8149, "step": 14740 }, { "epoch": 0.8059320006834102, "grad_norm": 2.1501853466033936, "learning_rate": 9.562684927115002e-06, "loss": 0.9325, "step": 14741 }, { "epoch": 0.8059866735007688, "grad_norm": 2.731278657913208, "learning_rate": 9.557478279633209e-06, "loss": 0.9661, "step": 14742 }, { "epoch": 0.8060413463181274, "grad_norm": 2.4871745109558105, "learning_rate": 9.552272900191034e-06, "loss": 0.948, "step": 14743 }, { "epoch": 0.8060960191354861, "grad_norm": 2.801326274871826, "learning_rate": 9.547068788951679e-06, "loss": 1.117, "step": 14744 }, { "epoch": 0.8061506919528447, "grad_norm": 2.614379644393921, "learning_rate": 9.541865946078316e-06, "loss": 1.1663, "step": 14745 }, { "epoch": 0.8062053647702033, "grad_norm": 3.311933994293213, "learning_rate": 9.536664371734083e-06, "loss": 0.9756, "step": 14746 }, { "epoch": 0.8062600375875619, "grad_norm": 2.7637529373168945, "learning_rate": 9.531464066082075e-06, "loss": 1.0494, "step": 14747 }, { "epoch": 0.8063147104049205, "grad_norm": 2.6410322189331055, "learning_rate": 9.52626502928533e-06, "loss": 1.0277, "step": 14748 }, { "epoch": 0.8063693832222791, "grad_norm": 2.1360037326812744, "learning_rate": 9.521067261506871e-06, "loss": 0.8933, "step": 14749 }, { "epoch": 0.8064240560396377, "grad_norm": 2.35424542427063, "learning_rate": 9.515870762909656e-06, "loss": 0.7622, "step": 14750 }, { "epoch": 0.8064787288569965, "grad_norm": 3.3142175674438477, "learning_rate": 9.510675533656627e-06, "loss": 0.9969, "step": 14751 }, { "epoch": 0.806533401674355, "grad_norm": 2.3317956924438477, "learning_rate": 9.505481573910674e-06, "loss": 0.9353, "step": 14752 }, { "epoch": 0.8065880744917137, "grad_norm": 2.6059682369232178, "learning_rate": 9.500288883834647e-06, "loss": 1.2073, "step": 14753 }, { "epoch": 0.8066427473090723, "grad_norm": 3.5903544425964355, "learning_rate": 9.495097463591357e-06, "loss": 0.9946, "step": 14754 }, { "epoch": 0.8066974201264309, "grad_norm": 2.532921552658081, "learning_rate": 9.489907313343565e-06, "loss": 0.932, "step": 14755 }, { "epoch": 0.8067520929437895, "grad_norm": 2.5298027992248535, "learning_rate": 9.48471843325403e-06, "loss": 0.9232, "step": 14756 }, { "epoch": 0.8068067657611482, "grad_norm": 3.5315046310424805, "learning_rate": 9.479530823485433e-06, "loss": 1.0137, "step": 14757 }, { "epoch": 0.8068614385785068, "grad_norm": 2.75091290473938, "learning_rate": 9.474344484200427e-06, "loss": 1.128, "step": 14758 }, { "epoch": 0.8069161113958654, "grad_norm": 2.7464020252227783, "learning_rate": 9.469159415561618e-06, "loss": 0.9956, "step": 14759 }, { "epoch": 0.806970784213224, "grad_norm": 2.745811700820923, "learning_rate": 9.463975617731585e-06, "loss": 1.0271, "step": 14760 }, { "epoch": 0.8070254570305826, "grad_norm": 2.898580551147461, "learning_rate": 9.45879309087287e-06, "loss": 1.1607, "step": 14761 }, { "epoch": 0.8070801298479412, "grad_norm": 2.3606276512145996, "learning_rate": 9.453611835147946e-06, "loss": 1.2055, "step": 14762 }, { "epoch": 0.8071348026652998, "grad_norm": 2.7654380798339844, "learning_rate": 9.448431850719286e-06, "loss": 1.0509, "step": 14763 }, { "epoch": 0.8071894754826585, "grad_norm": 2.5589358806610107, "learning_rate": 9.443253137749297e-06, "loss": 0.8051, "step": 14764 }, { "epoch": 0.8072441483000171, "grad_norm": 2.6655499935150146, "learning_rate": 9.438075696400333e-06, "loss": 0.9861, "step": 14765 }, { "epoch": 0.8072988211173757, "grad_norm": 2.851647138595581, "learning_rate": 9.432899526834765e-06, "loss": 1.0327, "step": 14766 }, { "epoch": 0.8073534939347343, "grad_norm": 2.7359519004821777, "learning_rate": 9.427724629214874e-06, "loss": 0.915, "step": 14767 }, { "epoch": 0.8074081667520929, "grad_norm": 2.8152995109558105, "learning_rate": 9.4225510037029e-06, "loss": 1.1067, "step": 14768 }, { "epoch": 0.8074628395694515, "grad_norm": 2.715174913406372, "learning_rate": 9.417378650461073e-06, "loss": 1.227, "step": 14769 }, { "epoch": 0.8075175123868101, "grad_norm": 2.3724777698516846, "learning_rate": 9.412207569651565e-06, "loss": 0.8478, "step": 14770 }, { "epoch": 0.8075721852041688, "grad_norm": 3.1053640842437744, "learning_rate": 9.407037761436505e-06, "loss": 1.1356, "step": 14771 }, { "epoch": 0.8076268580215274, "grad_norm": 2.5996344089508057, "learning_rate": 9.401869225977988e-06, "loss": 1.0441, "step": 14772 }, { "epoch": 0.807681530838886, "grad_norm": 2.987522602081299, "learning_rate": 9.39670196343807e-06, "loss": 1.0456, "step": 14773 }, { "epoch": 0.8077362036562447, "grad_norm": 3.1382198333740234, "learning_rate": 9.391535973978772e-06, "loss": 0.7942, "step": 14774 }, { "epoch": 0.8077908764736033, "grad_norm": 3.2711379528045654, "learning_rate": 9.386371257762049e-06, "loss": 1.0496, "step": 14775 }, { "epoch": 0.8078455492909619, "grad_norm": 3.63252854347229, "learning_rate": 9.381207814949867e-06, "loss": 1.0066, "step": 14776 }, { "epoch": 0.8079002221083205, "grad_norm": 1.987019419670105, "learning_rate": 9.376045645704106e-06, "loss": 0.707, "step": 14777 }, { "epoch": 0.8079548949256792, "grad_norm": 2.3789479732513428, "learning_rate": 9.37088475018662e-06, "loss": 1.044, "step": 14778 }, { "epoch": 0.8080095677430378, "grad_norm": 3.422173023223877, "learning_rate": 9.365725128559221e-06, "loss": 0.8847, "step": 14779 }, { "epoch": 0.8080642405603964, "grad_norm": 2.5323052406311035, "learning_rate": 9.360566780983693e-06, "loss": 1.015, "step": 14780 }, { "epoch": 0.808118913377755, "grad_norm": 2.1655914783477783, "learning_rate": 9.355409707621765e-06, "loss": 0.869, "step": 14781 }, { "epoch": 0.8081735861951136, "grad_norm": 2.747054100036621, "learning_rate": 9.350253908635137e-06, "loss": 0.8723, "step": 14782 }, { "epoch": 0.8082282590124722, "grad_norm": 2.5712952613830566, "learning_rate": 9.345099384185463e-06, "loss": 0.907, "step": 14783 }, { "epoch": 0.8082829318298309, "grad_norm": 2.540370464324951, "learning_rate": 9.339946134434342e-06, "loss": 1.0537, "step": 14784 }, { "epoch": 0.8083376046471895, "grad_norm": 2.5847229957580566, "learning_rate": 9.334794159543381e-06, "loss": 1.0421, "step": 14785 }, { "epoch": 0.8083922774645481, "grad_norm": 2.6495635509490967, "learning_rate": 9.329643459674098e-06, "loss": 1.0504, "step": 14786 }, { "epoch": 0.8084469502819067, "grad_norm": 2.6601321697235107, "learning_rate": 9.32449403498799e-06, "loss": 1.1117, "step": 14787 }, { "epoch": 0.8085016230992653, "grad_norm": 1.9960200786590576, "learning_rate": 9.319345885646513e-06, "loss": 0.9687, "step": 14788 }, { "epoch": 0.8085562959166239, "grad_norm": 2.4324612617492676, "learning_rate": 9.314199011811082e-06, "loss": 0.9617, "step": 14789 }, { "epoch": 0.8086109687339825, "grad_norm": 3.144970178604126, "learning_rate": 9.309053413643077e-06, "loss": 1.0863, "step": 14790 }, { "epoch": 0.8086656415513412, "grad_norm": 2.792353630065918, "learning_rate": 9.30390909130383e-06, "loss": 1.1215, "step": 14791 }, { "epoch": 0.8087203143686998, "grad_norm": 5.241759300231934, "learning_rate": 9.298766044954632e-06, "loss": 1.0672, "step": 14792 }, { "epoch": 0.8087749871860584, "grad_norm": 2.49782657623291, "learning_rate": 9.293624274756752e-06, "loss": 0.7998, "step": 14793 }, { "epoch": 0.808829660003417, "grad_norm": 2.7201454639434814, "learning_rate": 9.288483780871376e-06, "loss": 1.0853, "step": 14794 }, { "epoch": 0.8088843328207757, "grad_norm": 2.259491205215454, "learning_rate": 9.283344563459723e-06, "loss": 0.9293, "step": 14795 }, { "epoch": 0.8089390056381343, "grad_norm": 2.4221224784851074, "learning_rate": 9.2782066226829e-06, "loss": 1.0417, "step": 14796 }, { "epoch": 0.8089936784554929, "grad_norm": 2.4346957206726074, "learning_rate": 9.273069958702013e-06, "loss": 1.0823, "step": 14797 }, { "epoch": 0.8090483512728516, "grad_norm": 3.0788543224334717, "learning_rate": 9.26793457167811e-06, "loss": 1.031, "step": 14798 }, { "epoch": 0.8091030240902102, "grad_norm": 2.132587194442749, "learning_rate": 9.262800461772214e-06, "loss": 0.908, "step": 14799 }, { "epoch": 0.8091576969075688, "grad_norm": 2.4172866344451904, "learning_rate": 9.257667629145295e-06, "loss": 0.9968, "step": 14800 }, { "epoch": 0.8092123697249274, "grad_norm": 3.1708171367645264, "learning_rate": 9.25253607395829e-06, "loss": 0.923, "step": 14801 }, { "epoch": 0.809267042542286, "grad_norm": 2.6633310317993164, "learning_rate": 9.247405796372094e-06, "loss": 1.0285, "step": 14802 }, { "epoch": 0.8093217153596446, "grad_norm": 3.0884368419647217, "learning_rate": 9.242276796547567e-06, "loss": 0.9828, "step": 14803 }, { "epoch": 0.8093763881770032, "grad_norm": 2.8132517337799072, "learning_rate": 9.237149074645501e-06, "loss": 1.0109, "step": 14804 }, { "epoch": 0.8094310609943619, "grad_norm": 2.0492095947265625, "learning_rate": 9.23202263082671e-06, "loss": 0.989, "step": 14805 }, { "epoch": 0.8094857338117205, "grad_norm": 2.5273830890655518, "learning_rate": 9.226897465251904e-06, "loss": 1.0188, "step": 14806 }, { "epoch": 0.8095404066290791, "grad_norm": 2.522599220275879, "learning_rate": 9.221773578081789e-06, "loss": 0.977, "step": 14807 }, { "epoch": 0.8095950794464377, "grad_norm": 2.973578691482544, "learning_rate": 9.216650969477009e-06, "loss": 1.1064, "step": 14808 }, { "epoch": 0.8096497522637963, "grad_norm": 2.891714096069336, "learning_rate": 9.211529639598188e-06, "loss": 0.9841, "step": 14809 }, { "epoch": 0.8097044250811549, "grad_norm": 2.8288516998291016, "learning_rate": 9.206409588605897e-06, "loss": 0.9298, "step": 14810 }, { "epoch": 0.8097590978985136, "grad_norm": 2.3476996421813965, "learning_rate": 9.201290816660674e-06, "loss": 1.1394, "step": 14811 }, { "epoch": 0.8098137707158722, "grad_norm": 2.549015522003174, "learning_rate": 9.196173323923007e-06, "loss": 0.94, "step": 14812 }, { "epoch": 0.8098684435332308, "grad_norm": 2.9354445934295654, "learning_rate": 9.191057110553353e-06, "loss": 1.2003, "step": 14813 }, { "epoch": 0.8099231163505894, "grad_norm": 2.2686381340026855, "learning_rate": 9.185942176712114e-06, "loss": 0.9351, "step": 14814 }, { "epoch": 0.809977789167948, "grad_norm": 2.8448407649993896, "learning_rate": 9.180828522559692e-06, "loss": 0.9923, "step": 14815 }, { "epoch": 0.8100324619853067, "grad_norm": 3.083209276199341, "learning_rate": 9.175716148256409e-06, "loss": 0.9398, "step": 14816 }, { "epoch": 0.8100871348026653, "grad_norm": 4.7546820640563965, "learning_rate": 9.170605053962555e-06, "loss": 0.9094, "step": 14817 }, { "epoch": 0.810141807620024, "grad_norm": 2.5326926708221436, "learning_rate": 9.165495239838389e-06, "loss": 1.1095, "step": 14818 }, { "epoch": 0.8101964804373826, "grad_norm": 2.9249985218048096, "learning_rate": 9.160386706044116e-06, "loss": 0.9074, "step": 14819 }, { "epoch": 0.8102511532547412, "grad_norm": 3.0866715908050537, "learning_rate": 9.155279452739918e-06, "loss": 1.1072, "step": 14820 }, { "epoch": 0.8103058260720998, "grad_norm": 2.657729148864746, "learning_rate": 9.150173480085922e-06, "loss": 0.8736, "step": 14821 }, { "epoch": 0.8103604988894584, "grad_norm": 2.3547565937042236, "learning_rate": 9.145068788242227e-06, "loss": 0.837, "step": 14822 }, { "epoch": 0.810415171706817, "grad_norm": 2.3413710594177246, "learning_rate": 9.139965377368887e-06, "loss": 1.0299, "step": 14823 }, { "epoch": 0.8104698445241756, "grad_norm": 2.605013608932495, "learning_rate": 9.134863247625896e-06, "loss": 1.2705, "step": 14824 }, { "epoch": 0.8105245173415343, "grad_norm": 2.8192036151885986, "learning_rate": 9.129762399173253e-06, "loss": 1.1005, "step": 14825 }, { "epoch": 0.8105791901588929, "grad_norm": 3.413452386856079, "learning_rate": 9.124662832170882e-06, "loss": 0.9922, "step": 14826 }, { "epoch": 0.8106338629762515, "grad_norm": 2.244424343109131, "learning_rate": 9.119564546778675e-06, "loss": 0.8189, "step": 14827 }, { "epoch": 0.8106885357936101, "grad_norm": 2.775827169418335, "learning_rate": 9.11446754315648e-06, "loss": 1.0195, "step": 14828 }, { "epoch": 0.8107432086109687, "grad_norm": 2.310844898223877, "learning_rate": 9.109371821464113e-06, "loss": 1.0067, "step": 14829 }, { "epoch": 0.8107978814283273, "grad_norm": 2.5975840091705322, "learning_rate": 9.104277381861342e-06, "loss": 1.0246, "step": 14830 }, { "epoch": 0.8108525542456859, "grad_norm": 4.128420829772949, "learning_rate": 9.099184224507906e-06, "loss": 0.8923, "step": 14831 }, { "epoch": 0.8109072270630446, "grad_norm": 2.984344720840454, "learning_rate": 9.094092349563487e-06, "loss": 0.8839, "step": 14832 }, { "epoch": 0.8109618998804032, "grad_norm": 2.4958717823028564, "learning_rate": 9.089001757187732e-06, "loss": 1.0138, "step": 14833 }, { "epoch": 0.8110165726977618, "grad_norm": 2.459665060043335, "learning_rate": 9.083912447540272e-06, "loss": 0.8618, "step": 14834 }, { "epoch": 0.8110712455151204, "grad_norm": 2.847971200942993, "learning_rate": 9.078824420780668e-06, "loss": 1.1509, "step": 14835 }, { "epoch": 0.811125918332479, "grad_norm": 2.8721249103546143, "learning_rate": 9.07373767706845e-06, "loss": 0.8974, "step": 14836 }, { "epoch": 0.8111805911498376, "grad_norm": 2.232487440109253, "learning_rate": 9.068652216563106e-06, "loss": 0.9877, "step": 14837 }, { "epoch": 0.8112352639671964, "grad_norm": 2.7784786224365234, "learning_rate": 9.063568039424086e-06, "loss": 0.9546, "step": 14838 }, { "epoch": 0.811289936784555, "grad_norm": 2.577207326889038, "learning_rate": 9.058485145810808e-06, "loss": 1.0344, "step": 14839 }, { "epoch": 0.8113446096019136, "grad_norm": 3.6037325859069824, "learning_rate": 9.053403535882631e-06, "loss": 0.8483, "step": 14840 }, { "epoch": 0.8113992824192722, "grad_norm": 2.5230979919433594, "learning_rate": 9.048323209798893e-06, "loss": 1.0622, "step": 14841 }, { "epoch": 0.8114539552366308, "grad_norm": 2.7992258071899414, "learning_rate": 9.043244167718873e-06, "loss": 1.1734, "step": 14842 }, { "epoch": 0.8115086280539894, "grad_norm": 2.9805474281311035, "learning_rate": 9.038166409801819e-06, "loss": 0.9135, "step": 14843 }, { "epoch": 0.811563300871348, "grad_norm": 2.8256845474243164, "learning_rate": 9.033089936206956e-06, "loss": 1.0293, "step": 14844 }, { "epoch": 0.8116179736887067, "grad_norm": 2.9237942695617676, "learning_rate": 9.028014747093445e-06, "loss": 1.2307, "step": 14845 }, { "epoch": 0.8116726465060653, "grad_norm": 3.4572103023529053, "learning_rate": 9.02294084262041e-06, "loss": 1.0151, "step": 14846 }, { "epoch": 0.8117273193234239, "grad_norm": 2.327709913253784, "learning_rate": 9.01786822294694e-06, "loss": 0.9131, "step": 14847 }, { "epoch": 0.8117819921407825, "grad_norm": 2.13216233253479, "learning_rate": 9.012796888232083e-06, "loss": 0.8626, "step": 14848 }, { "epoch": 0.8118366649581411, "grad_norm": 2.2564141750335693, "learning_rate": 9.00772683863485e-06, "loss": 0.8928, "step": 14849 }, { "epoch": 0.8118913377754997, "grad_norm": 2.8235247135162354, "learning_rate": 9.002658074314201e-06, "loss": 0.9548, "step": 14850 }, { "epoch": 0.8119460105928583, "grad_norm": 2.1501481533050537, "learning_rate": 8.997590595429067e-06, "loss": 0.9193, "step": 14851 }, { "epoch": 0.812000683410217, "grad_norm": 3.360351324081421, "learning_rate": 8.992524402138336e-06, "loss": 0.8069, "step": 14852 }, { "epoch": 0.8120553562275756, "grad_norm": 2.3182566165924072, "learning_rate": 8.987459494600837e-06, "loss": 0.9216, "step": 14853 }, { "epoch": 0.8121100290449342, "grad_norm": 3.0356223583221436, "learning_rate": 8.982395872975402e-06, "loss": 1.1419, "step": 14854 }, { "epoch": 0.8121647018622928, "grad_norm": 3.83667254447937, "learning_rate": 8.977333537420785e-06, "loss": 1.1266, "step": 14855 }, { "epoch": 0.8122193746796514, "grad_norm": 2.298616647720337, "learning_rate": 8.972272488095706e-06, "loss": 0.9569, "step": 14856 }, { "epoch": 0.81227404749701, "grad_norm": 3.1141443252563477, "learning_rate": 8.967212725158864e-06, "loss": 1.0132, "step": 14857 }, { "epoch": 0.8123287203143686, "grad_norm": 2.439256191253662, "learning_rate": 8.962154248768889e-06, "loss": 0.9849, "step": 14858 }, { "epoch": 0.8123833931317274, "grad_norm": 3.717951536178589, "learning_rate": 8.957097059084391e-06, "loss": 0.9176, "step": 14859 }, { "epoch": 0.812438065949086, "grad_norm": 3.433199405670166, "learning_rate": 8.95204115626393e-06, "loss": 1.1669, "step": 14860 }, { "epoch": 0.8124927387664446, "grad_norm": 2.657318353652954, "learning_rate": 8.946986540466034e-06, "loss": 1.0373, "step": 14861 }, { "epoch": 0.8125474115838032, "grad_norm": 2.8233580589294434, "learning_rate": 8.94193321184918e-06, "loss": 1.0401, "step": 14862 }, { "epoch": 0.8126020844011618, "grad_norm": 2.5727579593658447, "learning_rate": 8.936881170571821e-06, "loss": 1.0508, "step": 14863 }, { "epoch": 0.8126567572185204, "grad_norm": 2.588862180709839, "learning_rate": 8.931830416792347e-06, "loss": 1.0778, "step": 14864 }, { "epoch": 0.8127114300358791, "grad_norm": 2.681797981262207, "learning_rate": 8.926780950669128e-06, "loss": 1.067, "step": 14865 }, { "epoch": 0.8127661028532377, "grad_norm": 2.3910434246063232, "learning_rate": 8.921732772360475e-06, "loss": 1.003, "step": 14866 }, { "epoch": 0.8128207756705963, "grad_norm": 2.8946175575256348, "learning_rate": 8.916685882024684e-06, "loss": 0.8915, "step": 14867 }, { "epoch": 0.8128754484879549, "grad_norm": 2.718052625656128, "learning_rate": 8.911640279819994e-06, "loss": 0.9301, "step": 14868 }, { "epoch": 0.8129301213053135, "grad_norm": 3.1775624752044678, "learning_rate": 8.906595965904602e-06, "loss": 1.1813, "step": 14869 }, { "epoch": 0.8129847941226721, "grad_norm": 2.4800970554351807, "learning_rate": 8.901552940436665e-06, "loss": 1.1612, "step": 14870 }, { "epoch": 0.8130394669400307, "grad_norm": 3.0758605003356934, "learning_rate": 8.896511203574298e-06, "loss": 1.1341, "step": 14871 }, { "epoch": 0.8130941397573894, "grad_norm": 2.287881851196289, "learning_rate": 8.891470755475595e-06, "loss": 0.9024, "step": 14872 }, { "epoch": 0.813148812574748, "grad_norm": 2.4475815296173096, "learning_rate": 8.886431596298583e-06, "loss": 1.0454, "step": 14873 }, { "epoch": 0.8132034853921066, "grad_norm": 2.3381149768829346, "learning_rate": 8.881393726201265e-06, "loss": 1.1406, "step": 14874 }, { "epoch": 0.8132581582094652, "grad_norm": 2.4180641174316406, "learning_rate": 8.876357145341597e-06, "loss": 0.8514, "step": 14875 }, { "epoch": 0.8133128310268238, "grad_norm": 4.5077223777771, "learning_rate": 8.871321853877495e-06, "loss": 1.1969, "step": 14876 }, { "epoch": 0.8133675038441824, "grad_norm": 2.2421114444732666, "learning_rate": 8.866287851966843e-06, "loss": 1.0512, "step": 14877 }, { "epoch": 0.813422176661541, "grad_norm": 3.007251024246216, "learning_rate": 8.861255139767471e-06, "loss": 1.1925, "step": 14878 }, { "epoch": 0.8134768494788998, "grad_norm": 2.1266930103302, "learning_rate": 8.856223717437162e-06, "loss": 0.8825, "step": 14879 }, { "epoch": 0.8135315222962584, "grad_norm": 3.292868137359619, "learning_rate": 8.851193585133704e-06, "loss": 1.0294, "step": 14880 }, { "epoch": 0.813586195113617, "grad_norm": 3.585073947906494, "learning_rate": 8.846164743014796e-06, "loss": 1.0296, "step": 14881 }, { "epoch": 0.8136408679309756, "grad_norm": 2.712526321411133, "learning_rate": 8.841137191238114e-06, "loss": 1.0964, "step": 14882 }, { "epoch": 0.8136955407483342, "grad_norm": 3.510467767715454, "learning_rate": 8.836110929961289e-06, "loss": 1.11, "step": 14883 }, { "epoch": 0.8137502135656928, "grad_norm": 2.534424066543579, "learning_rate": 8.831085959341911e-06, "loss": 1.0556, "step": 14884 }, { "epoch": 0.8138048863830514, "grad_norm": 2.139643669128418, "learning_rate": 8.826062279537545e-06, "loss": 0.6761, "step": 14885 }, { "epoch": 0.8138595592004101, "grad_norm": 2.6199021339416504, "learning_rate": 8.8210398907057e-06, "loss": 1.132, "step": 14886 }, { "epoch": 0.8139142320177687, "grad_norm": 2.3406665325164795, "learning_rate": 8.816018793003844e-06, "loss": 1.0583, "step": 14887 }, { "epoch": 0.8139689048351273, "grad_norm": 2.701772689819336, "learning_rate": 8.810998986589413e-06, "loss": 1.0764, "step": 14888 }, { "epoch": 0.8140235776524859, "grad_norm": 3.127347469329834, "learning_rate": 8.805980471619802e-06, "loss": 1.1891, "step": 14889 }, { "epoch": 0.8140782504698445, "grad_norm": 2.4817750453948975, "learning_rate": 8.800963248252353e-06, "loss": 0.9853, "step": 14890 }, { "epoch": 0.8141329232872031, "grad_norm": 2.733323812484741, "learning_rate": 8.795947316644382e-06, "loss": 0.9857, "step": 14891 }, { "epoch": 0.8141875961045618, "grad_norm": 2.817293167114258, "learning_rate": 8.790932676953151e-06, "loss": 0.9883, "step": 14892 }, { "epoch": 0.8142422689219204, "grad_norm": 2.4150612354278564, "learning_rate": 8.785919329335907e-06, "loss": 1.1478, "step": 14893 }, { "epoch": 0.814296941739279, "grad_norm": 2.627983570098877, "learning_rate": 8.780907273949823e-06, "loss": 1.1565, "step": 14894 }, { "epoch": 0.8143516145566376, "grad_norm": 2.691877841949463, "learning_rate": 8.775896510952064e-06, "loss": 0.9456, "step": 14895 }, { "epoch": 0.8144062873739962, "grad_norm": 2.5580601692199707, "learning_rate": 8.77088704049972e-06, "loss": 0.8372, "step": 14896 }, { "epoch": 0.8144609601913548, "grad_norm": 2.6213059425354004, "learning_rate": 8.76587886274987e-06, "loss": 0.9825, "step": 14897 }, { "epoch": 0.8145156330087134, "grad_norm": 2.9977149963378906, "learning_rate": 8.76087197785954e-06, "loss": 1.0171, "step": 14898 }, { "epoch": 0.8145703058260721, "grad_norm": 2.6941497325897217, "learning_rate": 8.755866385985712e-06, "loss": 1.0133, "step": 14899 }, { "epoch": 0.8146249786434308, "grad_norm": 2.546186685562134, "learning_rate": 8.750862087285333e-06, "loss": 0.9523, "step": 14900 }, { "epoch": 0.8146796514607894, "grad_norm": 2.586782932281494, "learning_rate": 8.74585908191531e-06, "loss": 1.158, "step": 14901 }, { "epoch": 0.814734324278148, "grad_norm": 2.962109327316284, "learning_rate": 8.740857370032496e-06, "loss": 0.9732, "step": 14902 }, { "epoch": 0.8147889970955066, "grad_norm": 2.753166913986206, "learning_rate": 8.735856951793737e-06, "loss": 0.9901, "step": 14903 }, { "epoch": 0.8148436699128652, "grad_norm": 2.035398244857788, "learning_rate": 8.730857827355803e-06, "loss": 0.9113, "step": 14904 }, { "epoch": 0.8148983427302238, "grad_norm": 2.940370559692383, "learning_rate": 8.725859996875446e-06, "loss": 1.214, "step": 14905 }, { "epoch": 0.8149530155475825, "grad_norm": 2.923593044281006, "learning_rate": 8.72086346050936e-06, "loss": 1.077, "step": 14906 }, { "epoch": 0.8150076883649411, "grad_norm": 2.2270073890686035, "learning_rate": 8.715868218414208e-06, "loss": 0.9426, "step": 14907 }, { "epoch": 0.8150623611822997, "grad_norm": 3.0693578720092773, "learning_rate": 8.710874270746616e-06, "loss": 1.0337, "step": 14908 }, { "epoch": 0.8151170339996583, "grad_norm": 2.98303484916687, "learning_rate": 8.705881617663165e-06, "loss": 0.8202, "step": 14909 }, { "epoch": 0.8151717068170169, "grad_norm": 2.895740270614624, "learning_rate": 8.700890259320388e-06, "loss": 1.0291, "step": 14910 }, { "epoch": 0.8152263796343755, "grad_norm": 2.541645050048828, "learning_rate": 8.69590019587479e-06, "loss": 1.0839, "step": 14911 }, { "epoch": 0.8152810524517341, "grad_norm": 3.3748183250427246, "learning_rate": 8.690911427482812e-06, "loss": 1.0137, "step": 14912 }, { "epoch": 0.8153357252690928, "grad_norm": 2.374950408935547, "learning_rate": 8.685923954300905e-06, "loss": 0.8563, "step": 14913 }, { "epoch": 0.8153903980864514, "grad_norm": 2.0366272926330566, "learning_rate": 8.680937776485438e-06, "loss": 0.8956, "step": 14914 }, { "epoch": 0.81544507090381, "grad_norm": 2.5817677974700928, "learning_rate": 8.675952894192735e-06, "loss": 1.0492, "step": 14915 }, { "epoch": 0.8154997437211686, "grad_norm": 2.2204654216766357, "learning_rate": 8.670969307579097e-06, "loss": 0.9018, "step": 14916 }, { "epoch": 0.8155544165385272, "grad_norm": 2.8171162605285645, "learning_rate": 8.665987016800786e-06, "loss": 1.0793, "step": 14917 }, { "epoch": 0.8156090893558858, "grad_norm": 2.2113733291625977, "learning_rate": 8.661006022014012e-06, "loss": 0.9999, "step": 14918 }, { "epoch": 0.8156637621732445, "grad_norm": 2.02303147315979, "learning_rate": 8.656026323374949e-06, "loss": 0.9171, "step": 14919 }, { "epoch": 0.8157184349906031, "grad_norm": 2.599539041519165, "learning_rate": 8.651047921039735e-06, "loss": 1.209, "step": 14920 }, { "epoch": 0.8157731078079618, "grad_norm": 3.000861883163452, "learning_rate": 8.646070815164464e-06, "loss": 1.0182, "step": 14921 }, { "epoch": 0.8158277806253204, "grad_norm": 2.7051804065704346, "learning_rate": 8.64109500590517e-06, "loss": 0.852, "step": 14922 }, { "epoch": 0.815882453442679, "grad_norm": 2.596278667449951, "learning_rate": 8.636120493417898e-06, "loss": 0.966, "step": 14923 }, { "epoch": 0.8159371262600376, "grad_norm": 4.217535018920898, "learning_rate": 8.631147277858597e-06, "loss": 0.8706, "step": 14924 }, { "epoch": 0.8159917990773962, "grad_norm": 2.576979398727417, "learning_rate": 8.62617535938321e-06, "loss": 1.0163, "step": 14925 }, { "epoch": 0.8160464718947549, "grad_norm": 2.867074728012085, "learning_rate": 8.621204738147615e-06, "loss": 0.9062, "step": 14926 }, { "epoch": 0.8161011447121135, "grad_norm": 2.7248477935791016, "learning_rate": 8.616235414307672e-06, "loss": 1.0553, "step": 14927 }, { "epoch": 0.8161558175294721, "grad_norm": 2.763375759124756, "learning_rate": 8.61126738801918e-06, "loss": 0.9286, "step": 14928 }, { "epoch": 0.8162104903468307, "grad_norm": 3.410825490951538, "learning_rate": 8.606300659437915e-06, "loss": 0.8609, "step": 14929 }, { "epoch": 0.8162651631641893, "grad_norm": 2.4368720054626465, "learning_rate": 8.601335228719603e-06, "loss": 0.857, "step": 14930 }, { "epoch": 0.8163198359815479, "grad_norm": 2.43515682220459, "learning_rate": 8.596371096019923e-06, "loss": 0.945, "step": 14931 }, { "epoch": 0.8163745087989065, "grad_norm": 2.5332376956939697, "learning_rate": 8.591408261494521e-06, "loss": 0.8529, "step": 14932 }, { "epoch": 0.8164291816162652, "grad_norm": 2.8607757091522217, "learning_rate": 8.58644672529902e-06, "loss": 1.0933, "step": 14933 }, { "epoch": 0.8164838544336238, "grad_norm": 2.1729488372802734, "learning_rate": 8.581486487588969e-06, "loss": 0.7905, "step": 14934 }, { "epoch": 0.8165385272509824, "grad_norm": 2.674053192138672, "learning_rate": 8.576527548519902e-06, "loss": 1.057, "step": 14935 }, { "epoch": 0.816593200068341, "grad_norm": 2.4716200828552246, "learning_rate": 8.57156990824729e-06, "loss": 1.0281, "step": 14936 }, { "epoch": 0.8166478728856996, "grad_norm": 2.5933520793914795, "learning_rate": 8.566613566926584e-06, "loss": 1.1227, "step": 14937 }, { "epoch": 0.8167025457030582, "grad_norm": 2.3276898860931396, "learning_rate": 8.561658524713184e-06, "loss": 1.0407, "step": 14938 }, { "epoch": 0.8167572185204168, "grad_norm": 2.3414669036865234, "learning_rate": 8.556704781762453e-06, "loss": 1.1421, "step": 14939 }, { "epoch": 0.8168118913377755, "grad_norm": 2.629290819168091, "learning_rate": 8.551752338229702e-06, "loss": 1.0323, "step": 14940 }, { "epoch": 0.8168665641551341, "grad_norm": 2.948500394821167, "learning_rate": 8.54680119427021e-06, "loss": 0.845, "step": 14941 }, { "epoch": 0.8169212369724927, "grad_norm": 3.909796953201294, "learning_rate": 8.541851350039231e-06, "loss": 0.9289, "step": 14942 }, { "epoch": 0.8169759097898514, "grad_norm": 2.806833267211914, "learning_rate": 8.53690280569196e-06, "loss": 1.1513, "step": 14943 }, { "epoch": 0.81703058260721, "grad_norm": 2.449742078781128, "learning_rate": 8.531955561383541e-06, "loss": 1.1626, "step": 14944 }, { "epoch": 0.8170852554245686, "grad_norm": 2.218316078186035, "learning_rate": 8.527009617269105e-06, "loss": 1.1304, "step": 14945 }, { "epoch": 0.8171399282419273, "grad_norm": 2.1930785179138184, "learning_rate": 8.522064973503719e-06, "loss": 0.9692, "step": 14946 }, { "epoch": 0.8171946010592859, "grad_norm": 2.4132156372070312, "learning_rate": 8.51712163024242e-06, "loss": 1.0266, "step": 14947 }, { "epoch": 0.8172492738766445, "grad_norm": 2.469001531600952, "learning_rate": 8.5121795876402e-06, "loss": 1.0999, "step": 14948 }, { "epoch": 0.8173039466940031, "grad_norm": 2.959623336791992, "learning_rate": 8.507238845852022e-06, "loss": 0.8823, "step": 14949 }, { "epoch": 0.8173586195113617, "grad_norm": 2.7451469898223877, "learning_rate": 8.502299405032787e-06, "loss": 1.0494, "step": 14950 }, { "epoch": 0.8174132923287203, "grad_norm": 3.5141587257385254, "learning_rate": 8.497361265337356e-06, "loss": 0.8411, "step": 14951 }, { "epoch": 0.8174679651460789, "grad_norm": 2.244309186935425, "learning_rate": 8.492424426920591e-06, "loss": 0.8686, "step": 14952 }, { "epoch": 0.8175226379634376, "grad_norm": 2.638744354248047, "learning_rate": 8.487488889937262e-06, "loss": 1.1706, "step": 14953 }, { "epoch": 0.8175773107807962, "grad_norm": 3.1469202041625977, "learning_rate": 8.48255465454213e-06, "loss": 1.1486, "step": 14954 }, { "epoch": 0.8176319835981548, "grad_norm": 2.767664670944214, "learning_rate": 8.47762172088989e-06, "loss": 0.9631, "step": 14955 }, { "epoch": 0.8176866564155134, "grad_norm": 2.6125590801239014, "learning_rate": 8.472690089135215e-06, "loss": 0.9204, "step": 14956 }, { "epoch": 0.817741329232872, "grad_norm": 2.6643168926239014, "learning_rate": 8.467759759432735e-06, "loss": 1.225, "step": 14957 }, { "epoch": 0.8177960020502306, "grad_norm": 2.5930240154266357, "learning_rate": 8.462830731937038e-06, "loss": 0.9805, "step": 14958 }, { "epoch": 0.8178506748675892, "grad_norm": 2.4527411460876465, "learning_rate": 8.457903006802665e-06, "loss": 1.0021, "step": 14959 }, { "epoch": 0.8179053476849479, "grad_norm": 3.7794947624206543, "learning_rate": 8.452976584184119e-06, "loss": 1.1244, "step": 14960 }, { "epoch": 0.8179600205023065, "grad_norm": 2.33520770072937, "learning_rate": 8.448051464235852e-06, "loss": 0.914, "step": 14961 }, { "epoch": 0.8180146933196651, "grad_norm": 2.8780884742736816, "learning_rate": 8.443127647112314e-06, "loss": 1.059, "step": 14962 }, { "epoch": 0.8180693661370237, "grad_norm": 3.8800909519195557, "learning_rate": 8.438205132967874e-06, "loss": 1.1325, "step": 14963 }, { "epoch": 0.8181240389543823, "grad_norm": 2.2663280963897705, "learning_rate": 8.433283921956875e-06, "loss": 0.9401, "step": 14964 }, { "epoch": 0.818178711771741, "grad_norm": 3.0149757862091064, "learning_rate": 8.428364014233608e-06, "loss": 1.1405, "step": 14965 }, { "epoch": 0.8182333845890996, "grad_norm": 3.3609936237335205, "learning_rate": 8.423445409952347e-06, "loss": 1.1548, "step": 14966 }, { "epoch": 0.8182880574064583, "grad_norm": 2.4394497871398926, "learning_rate": 8.418528109267293e-06, "loss": 1.0852, "step": 14967 }, { "epoch": 0.8183427302238169, "grad_norm": 2.829256057739258, "learning_rate": 8.413612112332642e-06, "loss": 0.9975, "step": 14968 }, { "epoch": 0.8183974030411755, "grad_norm": 2.6549324989318848, "learning_rate": 8.408697419302518e-06, "loss": 1.1046, "step": 14969 }, { "epoch": 0.8184520758585341, "grad_norm": 3.4441587924957275, "learning_rate": 8.403784030331019e-06, "loss": 0.9796, "step": 14970 }, { "epoch": 0.8185067486758927, "grad_norm": 3.287571430206299, "learning_rate": 8.398871945572196e-06, "loss": 1.0472, "step": 14971 }, { "epoch": 0.8185614214932513, "grad_norm": 2.4266364574432373, "learning_rate": 8.393961165180076e-06, "loss": 0.9249, "step": 14972 }, { "epoch": 0.81861609431061, "grad_norm": 2.909459114074707, "learning_rate": 8.389051689308624e-06, "loss": 1.2075, "step": 14973 }, { "epoch": 0.8186707671279686, "grad_norm": 2.25978946685791, "learning_rate": 8.384143518111776e-06, "loss": 1.0064, "step": 14974 }, { "epoch": 0.8187254399453272, "grad_norm": 2.359924554824829, "learning_rate": 8.379236651743422e-06, "loss": 0.9242, "step": 14975 }, { "epoch": 0.8187801127626858, "grad_norm": 2.162139654159546, "learning_rate": 8.374331090357408e-06, "loss": 0.9118, "step": 14976 }, { "epoch": 0.8188347855800444, "grad_norm": 2.80812931060791, "learning_rate": 8.369426834107547e-06, "loss": 1.0663, "step": 14977 }, { "epoch": 0.818889458397403, "grad_norm": 2.7067415714263916, "learning_rate": 8.364523883147612e-06, "loss": 1.065, "step": 14978 }, { "epoch": 0.8189441312147616, "grad_norm": 2.1521151065826416, "learning_rate": 8.359622237631321e-06, "loss": 1.1357, "step": 14979 }, { "epoch": 0.8189988040321203, "grad_norm": 3.680999517440796, "learning_rate": 8.354721897712369e-06, "loss": 1.1139, "step": 14980 }, { "epoch": 0.8190534768494789, "grad_norm": 4.361452579498291, "learning_rate": 8.349822863544382e-06, "loss": 0.9282, "step": 14981 }, { "epoch": 0.8191081496668375, "grad_norm": 2.3452723026275635, "learning_rate": 8.344925135281001e-06, "loss": 0.8534, "step": 14982 }, { "epoch": 0.8191628224841961, "grad_norm": 3.382659673690796, "learning_rate": 8.340028713075765e-06, "loss": 1.0141, "step": 14983 }, { "epoch": 0.8192174953015547, "grad_norm": 2.4913477897644043, "learning_rate": 8.335133597082201e-06, "loss": 0.976, "step": 14984 }, { "epoch": 0.8192721681189133, "grad_norm": 2.6098294258117676, "learning_rate": 8.330239787453797e-06, "loss": 1.146, "step": 14985 }, { "epoch": 0.819326840936272, "grad_norm": 3.2364964485168457, "learning_rate": 8.325347284343987e-06, "loss": 0.8007, "step": 14986 }, { "epoch": 0.8193815137536307, "grad_norm": 4.24802303314209, "learning_rate": 8.320456087906176e-06, "loss": 0.7974, "step": 14987 }, { "epoch": 0.8194361865709893, "grad_norm": 2.2084920406341553, "learning_rate": 8.315566198293722e-06, "loss": 1.0626, "step": 14988 }, { "epoch": 0.8194908593883479, "grad_norm": 3.000014543533325, "learning_rate": 8.31067761565994e-06, "loss": 1.0937, "step": 14989 }, { "epoch": 0.8195455322057065, "grad_norm": 2.259751796722412, "learning_rate": 8.305790340158098e-06, "loss": 0.958, "step": 14990 }, { "epoch": 0.8196002050230651, "grad_norm": 2.34871506690979, "learning_rate": 8.300904371941454e-06, "loss": 1.1244, "step": 14991 }, { "epoch": 0.8196548778404237, "grad_norm": 2.937609910964966, "learning_rate": 8.296019711163194e-06, "loss": 0.8547, "step": 14992 }, { "epoch": 0.8197095506577823, "grad_norm": 1.814394474029541, "learning_rate": 8.291136357976475e-06, "loss": 1.0102, "step": 14993 }, { "epoch": 0.819764223475141, "grad_norm": 2.115248918533325, "learning_rate": 8.286254312534403e-06, "loss": 1.014, "step": 14994 }, { "epoch": 0.8198188962924996, "grad_norm": 3.880648136138916, "learning_rate": 8.281373574990054e-06, "loss": 1.0469, "step": 14995 }, { "epoch": 0.8198735691098582, "grad_norm": 1.8947463035583496, "learning_rate": 8.276494145496455e-06, "loss": 1.0314, "step": 14996 }, { "epoch": 0.8199282419272168, "grad_norm": 3.51737380027771, "learning_rate": 8.271616024206602e-06, "loss": 1.1284, "step": 14997 }, { "epoch": 0.8199829147445754, "grad_norm": 2.4409008026123047, "learning_rate": 8.266739211273444e-06, "loss": 0.9912, "step": 14998 }, { "epoch": 0.820037587561934, "grad_norm": 2.8999390602111816, "learning_rate": 8.261863706849887e-06, "loss": 1.0923, "step": 14999 }, { "epoch": 0.8200922603792927, "grad_norm": 3.393542528152466, "learning_rate": 8.256989511088781e-06, "loss": 1.0422, "step": 15000 }, { "epoch": 0.8201469331966513, "grad_norm": 2.4934628009796143, "learning_rate": 8.252116624142985e-06, "loss": 1.0103, "step": 15001 }, { "epoch": 0.8202016060140099, "grad_norm": 2.7784996032714844, "learning_rate": 8.247245046165275e-06, "loss": 0.8894, "step": 15002 }, { "epoch": 0.8202562788313685, "grad_norm": 2.3182501792907715, "learning_rate": 8.242374777308381e-06, "loss": 1.0331, "step": 15003 }, { "epoch": 0.8203109516487271, "grad_norm": 2.4899818897247314, "learning_rate": 8.237505817725017e-06, "loss": 1.0436, "step": 15004 }, { "epoch": 0.8203656244660857, "grad_norm": 2.5800957679748535, "learning_rate": 8.23263816756784e-06, "loss": 0.784, "step": 15005 }, { "epoch": 0.8204202972834443, "grad_norm": 4.090090751647949, "learning_rate": 8.227771826989473e-06, "loss": 1.1053, "step": 15006 }, { "epoch": 0.8204749701008031, "grad_norm": 3.9363791942596436, "learning_rate": 8.222906796142493e-06, "loss": 0.8914, "step": 15007 }, { "epoch": 0.8205296429181617, "grad_norm": 3.105086326599121, "learning_rate": 8.218043075179444e-06, "loss": 0.7942, "step": 15008 }, { "epoch": 0.8205843157355203, "grad_norm": 2.4211132526397705, "learning_rate": 8.213180664252824e-06, "loss": 1.069, "step": 15009 }, { "epoch": 0.8206389885528789, "grad_norm": 2.4778285026550293, "learning_rate": 8.208319563515066e-06, "loss": 0.9932, "step": 15010 }, { "epoch": 0.8206936613702375, "grad_norm": 2.6328444480895996, "learning_rate": 8.203459773118626e-06, "loss": 1.1452, "step": 15011 }, { "epoch": 0.8207483341875961, "grad_norm": 2.2543394565582275, "learning_rate": 8.198601293215851e-06, "loss": 0.9956, "step": 15012 }, { "epoch": 0.8208030070049547, "grad_norm": 3.2225654125213623, "learning_rate": 8.193744123959085e-06, "loss": 1.2809, "step": 15013 }, { "epoch": 0.8208576798223134, "grad_norm": 2.5329513549804688, "learning_rate": 8.188888265500622e-06, "loss": 0.9288, "step": 15014 }, { "epoch": 0.820912352639672, "grad_norm": 2.343330144882202, "learning_rate": 8.1840337179927e-06, "loss": 0.9023, "step": 15015 }, { "epoch": 0.8209670254570306, "grad_norm": 2.266099452972412, "learning_rate": 8.17918048158754e-06, "loss": 1.0325, "step": 15016 }, { "epoch": 0.8210216982743892, "grad_norm": 2.831751823425293, "learning_rate": 8.174328556437311e-06, "loss": 0.9855, "step": 15017 }, { "epoch": 0.8210763710917478, "grad_norm": 2.287451982498169, "learning_rate": 8.169477942694132e-06, "loss": 0.8774, "step": 15018 }, { "epoch": 0.8211310439091064, "grad_norm": 2.881389617919922, "learning_rate": 8.164628640510102e-06, "loss": 0.8589, "step": 15019 }, { "epoch": 0.821185716726465, "grad_norm": 2.3425827026367188, "learning_rate": 8.15978065003724e-06, "loss": 1.1346, "step": 15020 }, { "epoch": 0.8212403895438237, "grad_norm": 2.4601447582244873, "learning_rate": 8.154933971427592e-06, "loss": 1.0734, "step": 15021 }, { "epoch": 0.8212950623611823, "grad_norm": 2.3098273277282715, "learning_rate": 8.150088604833096e-06, "loss": 1.0441, "step": 15022 }, { "epoch": 0.8213497351785409, "grad_norm": 2.6657960414886475, "learning_rate": 8.145244550405678e-06, "loss": 0.9874, "step": 15023 }, { "epoch": 0.8214044079958995, "grad_norm": 2.0302176475524902, "learning_rate": 8.140401808297216e-06, "loss": 0.863, "step": 15024 }, { "epoch": 0.8214590808132581, "grad_norm": 2.534039258956909, "learning_rate": 8.135560378659556e-06, "loss": 0.9726, "step": 15025 }, { "epoch": 0.8215137536306167, "grad_norm": 2.5644214153289795, "learning_rate": 8.130720261644498e-06, "loss": 1.1384, "step": 15026 }, { "epoch": 0.8215684264479753, "grad_norm": 2.4654974937438965, "learning_rate": 8.12588145740379e-06, "loss": 1.0316, "step": 15027 }, { "epoch": 0.8216230992653341, "grad_norm": 3.312614679336548, "learning_rate": 8.121043966089159e-06, "loss": 1.1545, "step": 15028 }, { "epoch": 0.8216777720826927, "grad_norm": 2.3989570140838623, "learning_rate": 8.116207787852271e-06, "loss": 0.9999, "step": 15029 }, { "epoch": 0.8217324449000513, "grad_norm": 2.2664973735809326, "learning_rate": 8.11137292284475e-06, "loss": 1.0296, "step": 15030 }, { "epoch": 0.8217871177174099, "grad_norm": 2.244141101837158, "learning_rate": 8.106539371218224e-06, "loss": 1.0901, "step": 15031 }, { "epoch": 0.8218417905347685, "grad_norm": 3.0754599571228027, "learning_rate": 8.101707133124214e-06, "loss": 0.8828, "step": 15032 }, { "epoch": 0.8218964633521271, "grad_norm": 2.6358492374420166, "learning_rate": 8.096876208714249e-06, "loss": 0.9176, "step": 15033 }, { "epoch": 0.8219511361694858, "grad_norm": 2.893843173980713, "learning_rate": 8.092046598139785e-06, "loss": 1.1351, "step": 15034 }, { "epoch": 0.8220058089868444, "grad_norm": 2.3398454189300537, "learning_rate": 8.087218301552257e-06, "loss": 0.6955, "step": 15035 }, { "epoch": 0.822060481804203, "grad_norm": 3.374396562576294, "learning_rate": 8.08239131910305e-06, "loss": 0.9864, "step": 15036 }, { "epoch": 0.8221151546215616, "grad_norm": 2.6927993297576904, "learning_rate": 8.077565650943513e-06, "loss": 1.1403, "step": 15037 }, { "epoch": 0.8221698274389202, "grad_norm": 3.149071216583252, "learning_rate": 8.072741297224946e-06, "loss": 0.9197, "step": 15038 }, { "epoch": 0.8222245002562788, "grad_norm": 2.1444613933563232, "learning_rate": 8.067918258098612e-06, "loss": 0.6925, "step": 15039 }, { "epoch": 0.8222791730736374, "grad_norm": 2.4957263469696045, "learning_rate": 8.063096533715719e-06, "loss": 0.8601, "step": 15040 }, { "epoch": 0.8223338458909961, "grad_norm": 2.6690473556518555, "learning_rate": 8.058276124227481e-06, "loss": 0.934, "step": 15041 }, { "epoch": 0.8223885187083547, "grad_norm": 2.5779404640197754, "learning_rate": 8.053457029785022e-06, "loss": 1.2128, "step": 15042 }, { "epoch": 0.8224431915257133, "grad_norm": 2.2694876194000244, "learning_rate": 8.048639250539437e-06, "loss": 0.9549, "step": 15043 }, { "epoch": 0.8224978643430719, "grad_norm": 3.2141964435577393, "learning_rate": 8.043822786641786e-06, "loss": 1.0821, "step": 15044 }, { "epoch": 0.8225525371604305, "grad_norm": 2.5073578357696533, "learning_rate": 8.03900763824308e-06, "loss": 1.0762, "step": 15045 }, { "epoch": 0.8226072099777891, "grad_norm": 3.0498223304748535, "learning_rate": 8.0341938054943e-06, "loss": 0.91, "step": 15046 }, { "epoch": 0.8226618827951477, "grad_norm": 2.873944044113159, "learning_rate": 8.029381288546384e-06, "loss": 0.9229, "step": 15047 }, { "epoch": 0.8227165556125065, "grad_norm": 2.9396557807922363, "learning_rate": 8.024570087550209e-06, "loss": 0.9605, "step": 15048 }, { "epoch": 0.822771228429865, "grad_norm": 2.626636505126953, "learning_rate": 8.01976020265664e-06, "loss": 1.0392, "step": 15049 }, { "epoch": 0.8228259012472237, "grad_norm": 2.4666149616241455, "learning_rate": 8.014951634016477e-06, "loss": 0.7964, "step": 15050 }, { "epoch": 0.8228805740645823, "grad_norm": 2.3409879207611084, "learning_rate": 8.010144381780499e-06, "loss": 1.0527, "step": 15051 }, { "epoch": 0.8229352468819409, "grad_norm": 2.2671186923980713, "learning_rate": 8.005338446099419e-06, "loss": 0.9538, "step": 15052 }, { "epoch": 0.8229899196992995, "grad_norm": 2.7344465255737305, "learning_rate": 8.000533827123923e-06, "loss": 1.059, "step": 15053 }, { "epoch": 0.8230445925166581, "grad_norm": 2.524418830871582, "learning_rate": 7.99573052500468e-06, "loss": 0.9738, "step": 15054 }, { "epoch": 0.8230992653340168, "grad_norm": 2.57553768157959, "learning_rate": 7.990928539892273e-06, "loss": 1.0793, "step": 15055 }, { "epoch": 0.8231539381513754, "grad_norm": 2.739473581314087, "learning_rate": 7.986127871937266e-06, "loss": 0.9451, "step": 15056 }, { "epoch": 0.823208610968734, "grad_norm": 2.8208906650543213, "learning_rate": 7.981328521290182e-06, "loss": 0.9976, "step": 15057 }, { "epoch": 0.8232632837860926, "grad_norm": 4.329056739807129, "learning_rate": 7.976530488101502e-06, "loss": 0.7893, "step": 15058 }, { "epoch": 0.8233179566034512, "grad_norm": 2.7928221225738525, "learning_rate": 7.971733772521662e-06, "loss": 1.2419, "step": 15059 }, { "epoch": 0.8233726294208098, "grad_norm": 2.523252010345459, "learning_rate": 7.966938374701056e-06, "loss": 1.1318, "step": 15060 }, { "epoch": 0.8234273022381685, "grad_norm": 2.2208895683288574, "learning_rate": 7.962144294790042e-06, "loss": 1.0636, "step": 15061 }, { "epoch": 0.8234819750555271, "grad_norm": 3.0634474754333496, "learning_rate": 7.95735153293894e-06, "loss": 1.1916, "step": 15062 }, { "epoch": 0.8235366478728857, "grad_norm": 2.4845879077911377, "learning_rate": 7.952560089298011e-06, "loss": 0.9127, "step": 15063 }, { "epoch": 0.8235913206902443, "grad_norm": 2.7962279319763184, "learning_rate": 7.947769964017493e-06, "loss": 1.0407, "step": 15064 }, { "epoch": 0.8236459935076029, "grad_norm": 1.9626950025558472, "learning_rate": 7.94298115724758e-06, "loss": 0.8252, "step": 15065 }, { "epoch": 0.8237006663249615, "grad_norm": 2.2724881172180176, "learning_rate": 7.9381936691384e-06, "loss": 1.029, "step": 15066 }, { "epoch": 0.8237553391423201, "grad_norm": 2.4041922092437744, "learning_rate": 7.93340749984009e-06, "loss": 1.1412, "step": 15067 }, { "epoch": 0.8238100119596788, "grad_norm": 2.419895648956299, "learning_rate": 7.92862264950271e-06, "loss": 1.1474, "step": 15068 }, { "epoch": 0.8238646847770374, "grad_norm": 2.7558071613311768, "learning_rate": 7.923839118276271e-06, "loss": 0.9717, "step": 15069 }, { "epoch": 0.823919357594396, "grad_norm": 2.348205804824829, "learning_rate": 7.919056906310762e-06, "loss": 1.0396, "step": 15070 }, { "epoch": 0.8239740304117547, "grad_norm": 2.5363404750823975, "learning_rate": 7.914276013756133e-06, "loss": 1.0296, "step": 15071 }, { "epoch": 0.8240287032291133, "grad_norm": 2.8629162311553955, "learning_rate": 7.909496440762276e-06, "loss": 0.9561, "step": 15072 }, { "epoch": 0.8240833760464719, "grad_norm": 3.373079299926758, "learning_rate": 7.904718187479049e-06, "loss": 1.0835, "step": 15073 }, { "epoch": 0.8241380488638305, "grad_norm": 2.94248366355896, "learning_rate": 7.899941254056276e-06, "loss": 1.2125, "step": 15074 }, { "epoch": 0.8241927216811892, "grad_norm": 2.531755208969116, "learning_rate": 7.895165640643732e-06, "loss": 0.9761, "step": 15075 }, { "epoch": 0.8242473944985478, "grad_norm": 2.6307265758514404, "learning_rate": 7.890391347391146e-06, "loss": 0.8549, "step": 15076 }, { "epoch": 0.8243020673159064, "grad_norm": 3.940286159515381, "learning_rate": 7.885618374448223e-06, "loss": 1.2338, "step": 15077 }, { "epoch": 0.824356740133265, "grad_norm": 2.530646324157715, "learning_rate": 7.880846721964607e-06, "loss": 1.0061, "step": 15078 }, { "epoch": 0.8244114129506236, "grad_norm": 3.0332906246185303, "learning_rate": 7.876076390089899e-06, "loss": 1.1314, "step": 15079 }, { "epoch": 0.8244660857679822, "grad_norm": 3.028461217880249, "learning_rate": 7.871307378973692e-06, "loss": 1.1194, "step": 15080 }, { "epoch": 0.8245207585853408, "grad_norm": 2.5755016803741455, "learning_rate": 7.8665396887655e-06, "loss": 1.121, "step": 15081 }, { "epoch": 0.8245754314026995, "grad_norm": 2.942136526107788, "learning_rate": 7.861773319614817e-06, "loss": 1.1271, "step": 15082 }, { "epoch": 0.8246301042200581, "grad_norm": 2.30312442779541, "learning_rate": 7.857008271671084e-06, "loss": 0.9592, "step": 15083 }, { "epoch": 0.8246847770374167, "grad_norm": 2.1544392108917236, "learning_rate": 7.852244545083704e-06, "loss": 0.9465, "step": 15084 }, { "epoch": 0.8247394498547753, "grad_norm": 3.533184766769409, "learning_rate": 7.847482140002039e-06, "loss": 1.0334, "step": 15085 }, { "epoch": 0.8247941226721339, "grad_norm": 3.753192901611328, "learning_rate": 7.842721056575409e-06, "loss": 0.8422, "step": 15086 }, { "epoch": 0.8248487954894925, "grad_norm": 2.8661866188049316, "learning_rate": 7.8379612949531e-06, "loss": 0.9758, "step": 15087 }, { "epoch": 0.8249034683068512, "grad_norm": 2.319352388381958, "learning_rate": 7.833202855284344e-06, "loss": 0.8804, "step": 15088 }, { "epoch": 0.8249581411242098, "grad_norm": 2.1128246784210205, "learning_rate": 7.828445737718327e-06, "loss": 0.8896, "step": 15089 }, { "epoch": 0.8250128139415684, "grad_norm": 2.5468640327453613, "learning_rate": 7.823689942404228e-06, "loss": 1.0312, "step": 15090 }, { "epoch": 0.825067486758927, "grad_norm": 2.7114808559417725, "learning_rate": 7.818935469491152e-06, "loss": 0.8993, "step": 15091 }, { "epoch": 0.8251221595762857, "grad_norm": 3.753490686416626, "learning_rate": 7.814182319128167e-06, "loss": 1.055, "step": 15092 }, { "epoch": 0.8251768323936443, "grad_norm": 2.102383852005005, "learning_rate": 7.809430491464304e-06, "loss": 0.8909, "step": 15093 }, { "epoch": 0.8252315052110029, "grad_norm": 2.377614974975586, "learning_rate": 7.804679986648555e-06, "loss": 1.0726, "step": 15094 }, { "epoch": 0.8252861780283616, "grad_norm": 2.6352200508117676, "learning_rate": 7.79993080482987e-06, "loss": 0.8577, "step": 15095 }, { "epoch": 0.8253408508457202, "grad_norm": 2.739135503768921, "learning_rate": 7.795182946157153e-06, "loss": 1.0279, "step": 15096 }, { "epoch": 0.8253955236630788, "grad_norm": 2.5988924503326416, "learning_rate": 7.790436410779267e-06, "loss": 0.9898, "step": 15097 }, { "epoch": 0.8254501964804374, "grad_norm": 2.4778153896331787, "learning_rate": 7.785691198845024e-06, "loss": 0.9287, "step": 15098 }, { "epoch": 0.825504869297796, "grad_norm": 2.3998961448669434, "learning_rate": 7.780947310503228e-06, "loss": 1.0556, "step": 15099 }, { "epoch": 0.8255595421151546, "grad_norm": 2.9926674365997314, "learning_rate": 7.77620474590261e-06, "loss": 1.2377, "step": 15100 }, { "epoch": 0.8256142149325132, "grad_norm": 2.7759547233581543, "learning_rate": 7.771463505191873e-06, "loss": 1.0918, "step": 15101 }, { "epoch": 0.8256688877498719, "grad_norm": 2.532513380050659, "learning_rate": 7.76672358851967e-06, "loss": 1.0564, "step": 15102 }, { "epoch": 0.8257235605672305, "grad_norm": 2.507753610610962, "learning_rate": 7.761984996034615e-06, "loss": 0.9841, "step": 15103 }, { "epoch": 0.8257782333845891, "grad_norm": 2.349092721939087, "learning_rate": 7.757247727885286e-06, "loss": 1.1831, "step": 15104 }, { "epoch": 0.8258329062019477, "grad_norm": 2.1828224658966064, "learning_rate": 7.752511784220217e-06, "loss": 1.048, "step": 15105 }, { "epoch": 0.8258875790193063, "grad_norm": 2.709641695022583, "learning_rate": 7.747777165187892e-06, "loss": 1.1392, "step": 15106 }, { "epoch": 0.8259422518366649, "grad_norm": 3.1526880264282227, "learning_rate": 7.743043870936767e-06, "loss": 0.9573, "step": 15107 }, { "epoch": 0.8259969246540235, "grad_norm": 2.448333740234375, "learning_rate": 7.738311901615242e-06, "loss": 1.058, "step": 15108 }, { "epoch": 0.8260515974713822, "grad_norm": 2.6876273155212402, "learning_rate": 7.733581257371698e-06, "loss": 1.1579, "step": 15109 }, { "epoch": 0.8261062702887408, "grad_norm": 2.26843523979187, "learning_rate": 7.728851938354453e-06, "loss": 0.9077, "step": 15110 }, { "epoch": 0.8261609431060994, "grad_norm": 2.551809549331665, "learning_rate": 7.724123944711791e-06, "loss": 1.015, "step": 15111 }, { "epoch": 0.826215615923458, "grad_norm": 2.5808088779449463, "learning_rate": 7.719397276591956e-06, "loss": 0.9034, "step": 15112 }, { "epoch": 0.8262702887408166, "grad_norm": 3.079756498336792, "learning_rate": 7.714671934143142e-06, "loss": 0.9847, "step": 15113 }, { "epoch": 0.8263249615581753, "grad_norm": 2.6335220336914062, "learning_rate": 7.709947917513516e-06, "loss": 0.9727, "step": 15114 }, { "epoch": 0.826379634375534, "grad_norm": 2.597729444503784, "learning_rate": 7.705225226851192e-06, "loss": 1.0052, "step": 15115 }, { "epoch": 0.8264343071928926, "grad_norm": 3.282733917236328, "learning_rate": 7.700503862304243e-06, "loss": 1.1315, "step": 15116 }, { "epoch": 0.8264889800102512, "grad_norm": 2.8776752948760986, "learning_rate": 7.695783824020702e-06, "loss": 1.2387, "step": 15117 }, { "epoch": 0.8265436528276098, "grad_norm": 2.2246742248535156, "learning_rate": 7.69106511214856e-06, "loss": 1.0536, "step": 15118 }, { "epoch": 0.8265983256449684, "grad_norm": 4.0962090492248535, "learning_rate": 7.68634772683578e-06, "loss": 1.1152, "step": 15119 }, { "epoch": 0.826652998462327, "grad_norm": 2.669398546218872, "learning_rate": 7.681631668230266e-06, "loss": 1.1429, "step": 15120 }, { "epoch": 0.8267076712796856, "grad_norm": 3.7258646488189697, "learning_rate": 7.676916936479884e-06, "loss": 0.8772, "step": 15121 }, { "epoch": 0.8267623440970443, "grad_norm": 2.9600698947906494, "learning_rate": 7.672203531732463e-06, "loss": 0.9334, "step": 15122 }, { "epoch": 0.8268170169144029, "grad_norm": 2.6208741664886475, "learning_rate": 7.667491454135784e-06, "loss": 1.0265, "step": 15123 }, { "epoch": 0.8268716897317615, "grad_norm": 3.1278867721557617, "learning_rate": 7.662780703837592e-06, "loss": 0.9882, "step": 15124 }, { "epoch": 0.8269263625491201, "grad_norm": 2.969914197921753, "learning_rate": 7.65807128098559e-06, "loss": 1.0793, "step": 15125 }, { "epoch": 0.8269810353664787, "grad_norm": 2.938142776489258, "learning_rate": 7.65336318572743e-06, "loss": 1.005, "step": 15126 }, { "epoch": 0.8270357081838373, "grad_norm": 1.9603264331817627, "learning_rate": 7.648656418210742e-06, "loss": 0.934, "step": 15127 }, { "epoch": 0.8270903810011959, "grad_norm": 2.6710431575775146, "learning_rate": 7.643950978583081e-06, "loss": 1.0951, "step": 15128 }, { "epoch": 0.8271450538185546, "grad_norm": 3.371188163757324, "learning_rate": 7.639246866992005e-06, "loss": 1.1157, "step": 15129 }, { "epoch": 0.8271997266359132, "grad_norm": 2.7104897499084473, "learning_rate": 7.63454408358501e-06, "loss": 0.9396, "step": 15130 }, { "epoch": 0.8272543994532718, "grad_norm": 2.523386240005493, "learning_rate": 7.629842628509532e-06, "loss": 1.1298, "step": 15131 }, { "epoch": 0.8273090722706304, "grad_norm": 2.5350499153137207, "learning_rate": 7.6251425019129854e-06, "loss": 0.8932, "step": 15132 }, { "epoch": 0.827363745087989, "grad_norm": 2.7327280044555664, "learning_rate": 7.620443703942736e-06, "loss": 1.0178, "step": 15133 }, { "epoch": 0.8274184179053476, "grad_norm": 3.4935829639434814, "learning_rate": 7.615746234746119e-06, "loss": 0.8364, "step": 15134 }, { "epoch": 0.8274730907227063, "grad_norm": 2.392727851867676, "learning_rate": 7.611050094470412e-06, "loss": 1.092, "step": 15135 }, { "epoch": 0.827527763540065, "grad_norm": 2.4555323123931885, "learning_rate": 7.606355283262862e-06, "loss": 1.0914, "step": 15136 }, { "epoch": 0.8275824363574236, "grad_norm": 2.3085570335388184, "learning_rate": 7.601661801270665e-06, "loss": 1.0303, "step": 15137 }, { "epoch": 0.8276371091747822, "grad_norm": 2.754798650741577, "learning_rate": 7.596969648640978e-06, "loss": 1.0399, "step": 15138 }, { "epoch": 0.8276917819921408, "grad_norm": 2.6544294357299805, "learning_rate": 7.592278825520938e-06, "loss": 1.1188, "step": 15139 }, { "epoch": 0.8277464548094994, "grad_norm": 2.4959990978240967, "learning_rate": 7.58758933205761e-06, "loss": 0.9789, "step": 15140 }, { "epoch": 0.827801127626858, "grad_norm": 2.958494186401367, "learning_rate": 7.5829011683980266e-06, "loss": 1.2159, "step": 15141 }, { "epoch": 0.8278558004442167, "grad_norm": 2.745455503463745, "learning_rate": 7.578214334689182e-06, "loss": 0.998, "step": 15142 }, { "epoch": 0.8279104732615753, "grad_norm": 2.88992977142334, "learning_rate": 7.573528831078036e-06, "loss": 1.1038, "step": 15143 }, { "epoch": 0.8279651460789339, "grad_norm": 2.6284492015838623, "learning_rate": 7.568844657711488e-06, "loss": 1.1378, "step": 15144 }, { "epoch": 0.8280198188962925, "grad_norm": 2.1167757511138916, "learning_rate": 7.564161814736409e-06, "loss": 0.99, "step": 15145 }, { "epoch": 0.8280744917136511, "grad_norm": 2.3637118339538574, "learning_rate": 7.559480302299626e-06, "loss": 0.9393, "step": 15146 }, { "epoch": 0.8281291645310097, "grad_norm": 3.573753833770752, "learning_rate": 7.554800120547911e-06, "loss": 1.0763, "step": 15147 }, { "epoch": 0.8281838373483683, "grad_norm": 2.4683823585510254, "learning_rate": 7.550121269628036e-06, "loss": 1.0082, "step": 15148 }, { "epoch": 0.828238510165727, "grad_norm": 2.3179731369018555, "learning_rate": 7.545443749686681e-06, "loss": 1.0712, "step": 15149 }, { "epoch": 0.8282931829830856, "grad_norm": 2.2749693393707275, "learning_rate": 7.540767560870515e-06, "loss": 0.8675, "step": 15150 }, { "epoch": 0.8283478558004442, "grad_norm": 2.9946353435516357, "learning_rate": 7.5360927033261475e-06, "loss": 1.1668, "step": 15151 }, { "epoch": 0.8284025286178028, "grad_norm": 2.0358827114105225, "learning_rate": 7.531419177200161e-06, "loss": 0.9476, "step": 15152 }, { "epoch": 0.8284572014351614, "grad_norm": 3.1710028648376465, "learning_rate": 7.526746982639088e-06, "loss": 1.2595, "step": 15153 }, { "epoch": 0.82851187425252, "grad_norm": 2.351653814315796, "learning_rate": 7.522076119789418e-06, "loss": 0.8987, "step": 15154 }, { "epoch": 0.8285665470698786, "grad_norm": 2.777388095855713, "learning_rate": 7.517406588797604e-06, "loss": 0.7965, "step": 15155 }, { "epoch": 0.8286212198872374, "grad_norm": 3.002293825149536, "learning_rate": 7.512738389810059e-06, "loss": 1.0093, "step": 15156 }, { "epoch": 0.828675892704596, "grad_norm": 2.0209169387817383, "learning_rate": 7.5080715229731316e-06, "loss": 1.0012, "step": 15157 }, { "epoch": 0.8287305655219546, "grad_norm": 3.3145861625671387, "learning_rate": 7.503405988433171e-06, "loss": 1.0485, "step": 15158 }, { "epoch": 0.8287852383393132, "grad_norm": 3.693453788757324, "learning_rate": 7.498741786336455e-06, "loss": 0.8741, "step": 15159 }, { "epoch": 0.8288399111566718, "grad_norm": 2.676438808441162, "learning_rate": 7.4940789168292225e-06, "loss": 1.0098, "step": 15160 }, { "epoch": 0.8288945839740304, "grad_norm": 3.010976791381836, "learning_rate": 7.4894173800576785e-06, "loss": 1.2032, "step": 15161 }, { "epoch": 0.828949256791389, "grad_norm": 2.4984538555145264, "learning_rate": 7.484757176167967e-06, "loss": 1.1016, "step": 15162 }, { "epoch": 0.8290039296087477, "grad_norm": 2.379258871078491, "learning_rate": 7.480098305306221e-06, "loss": 1.0214, "step": 15163 }, { "epoch": 0.8290586024261063, "grad_norm": 1.9051862955093384, "learning_rate": 7.4754407676185075e-06, "loss": 0.8535, "step": 15164 }, { "epoch": 0.8291132752434649, "grad_norm": 2.8491053581237793, "learning_rate": 7.47078456325086e-06, "loss": 1.1571, "step": 15165 }, { "epoch": 0.8291679480608235, "grad_norm": 1.9551079273223877, "learning_rate": 7.4661296923492665e-06, "loss": 0.7801, "step": 15166 }, { "epoch": 0.8292226208781821, "grad_norm": 2.4301040172576904, "learning_rate": 7.461476155059671e-06, "loss": 1.1065, "step": 15167 }, { "epoch": 0.8292772936955407, "grad_norm": 3.0343663692474365, "learning_rate": 7.456823951528003e-06, "loss": 0.9778, "step": 15168 }, { "epoch": 0.8293319665128994, "grad_norm": 2.2886054515838623, "learning_rate": 7.452173081900115e-06, "loss": 0.8519, "step": 15169 }, { "epoch": 0.829386639330258, "grad_norm": 3.4120795726776123, "learning_rate": 7.4475235463218275e-06, "loss": 1.1055, "step": 15170 }, { "epoch": 0.8294413121476166, "grad_norm": 2.3952133655548096, "learning_rate": 7.4428753449389325e-06, "loss": 0.939, "step": 15171 }, { "epoch": 0.8294959849649752, "grad_norm": 2.473304510116577, "learning_rate": 7.438228477897158e-06, "loss": 0.9467, "step": 15172 }, { "epoch": 0.8295506577823338, "grad_norm": 3.0359561443328857, "learning_rate": 7.43358294534221e-06, "loss": 1.0776, "step": 15173 }, { "epoch": 0.8296053305996924, "grad_norm": 2.396207094192505, "learning_rate": 7.428938747419745e-06, "loss": 1.019, "step": 15174 }, { "epoch": 0.829660003417051, "grad_norm": 2.365675926208496, "learning_rate": 7.424295884275378e-06, "loss": 1.01, "step": 15175 }, { "epoch": 0.8297146762344098, "grad_norm": 3.0067954063415527, "learning_rate": 7.419654356054678e-06, "loss": 0.877, "step": 15176 }, { "epoch": 0.8297693490517684, "grad_norm": 3.0683367252349854, "learning_rate": 7.415014162903166e-06, "loss": 1.0448, "step": 15177 }, { "epoch": 0.829824021869127, "grad_norm": 2.571683168411255, "learning_rate": 7.410375304966355e-06, "loss": 1.0191, "step": 15178 }, { "epoch": 0.8298786946864856, "grad_norm": 2.745023250579834, "learning_rate": 7.405737782389682e-06, "loss": 1.0241, "step": 15179 }, { "epoch": 0.8299333675038442, "grad_norm": 2.668358564376831, "learning_rate": 7.401101595318549e-06, "loss": 0.9137, "step": 15180 }, { "epoch": 0.8299880403212028, "grad_norm": 2.6531052589416504, "learning_rate": 7.396466743898323e-06, "loss": 1.0852, "step": 15181 }, { "epoch": 0.8300427131385614, "grad_norm": 2.1419761180877686, "learning_rate": 7.391833228274325e-06, "loss": 0.884, "step": 15182 }, { "epoch": 0.8300973859559201, "grad_norm": 1.938461422920227, "learning_rate": 7.387201048591829e-06, "loss": 0.9652, "step": 15183 }, { "epoch": 0.8301520587732787, "grad_norm": 2.405366897583008, "learning_rate": 7.382570204996086e-06, "loss": 1.1931, "step": 15184 }, { "epoch": 0.8302067315906373, "grad_norm": 2.470022678375244, "learning_rate": 7.3779406976322794e-06, "loss": 1.174, "step": 15185 }, { "epoch": 0.8302614044079959, "grad_norm": 2.5681264400482178, "learning_rate": 7.373312526645565e-06, "loss": 1.0653, "step": 15186 }, { "epoch": 0.8303160772253545, "grad_norm": 2.8469839096069336, "learning_rate": 7.368685692181055e-06, "loss": 0.9298, "step": 15187 }, { "epoch": 0.8303707500427131, "grad_norm": 2.2548763751983643, "learning_rate": 7.364060194383826e-06, "loss": 0.9426, "step": 15188 }, { "epoch": 0.8304254228600717, "grad_norm": 2.159611940383911, "learning_rate": 7.3594360333989084e-06, "loss": 0.8875, "step": 15189 }, { "epoch": 0.8304800956774304, "grad_norm": 3.13858699798584, "learning_rate": 7.354813209371281e-06, "loss": 0.8116, "step": 15190 }, { "epoch": 0.830534768494789, "grad_norm": 2.6016998291015625, "learning_rate": 7.350191722445892e-06, "loss": 0.942, "step": 15191 }, { "epoch": 0.8305894413121476, "grad_norm": 2.8904061317443848, "learning_rate": 7.34557157276764e-06, "loss": 1.0604, "step": 15192 }, { "epoch": 0.8306441141295062, "grad_norm": 2.3689730167388916, "learning_rate": 7.34095276048139e-06, "loss": 1.1858, "step": 15193 }, { "epoch": 0.8306987869468648, "grad_norm": 2.7210872173309326, "learning_rate": 7.33633528573196e-06, "loss": 1.0477, "step": 15194 }, { "epoch": 0.8307534597642234, "grad_norm": 2.440861463546753, "learning_rate": 7.331719148664129e-06, "loss": 0.9039, "step": 15195 }, { "epoch": 0.8308081325815821, "grad_norm": 2.4356510639190674, "learning_rate": 7.3271043494226145e-06, "loss": 0.881, "step": 15196 }, { "epoch": 0.8308628053989408, "grad_norm": 2.860997200012207, "learning_rate": 7.322490888152134e-06, "loss": 0.9431, "step": 15197 }, { "epoch": 0.8309174782162994, "grad_norm": 2.701934814453125, "learning_rate": 7.3178787649973325e-06, "loss": 0.6661, "step": 15198 }, { "epoch": 0.830972151033658, "grad_norm": 4.110451698303223, "learning_rate": 7.313267980102811e-06, "loss": 0.9552, "step": 15199 }, { "epoch": 0.8310268238510166, "grad_norm": 2.003727912902832, "learning_rate": 7.3086585336131445e-06, "loss": 0.9255, "step": 15200 }, { "epoch": 0.8310814966683752, "grad_norm": 2.2338924407958984, "learning_rate": 7.304050425672848e-06, "loss": 0.9442, "step": 15201 }, { "epoch": 0.8311361694857338, "grad_norm": 3.0866174697875977, "learning_rate": 7.299443656426419e-06, "loss": 0.7326, "step": 15202 }, { "epoch": 0.8311908423030925, "grad_norm": 2.6522793769836426, "learning_rate": 7.294838226018285e-06, "loss": 1.2217, "step": 15203 }, { "epoch": 0.8312455151204511, "grad_norm": 2.1490426063537598, "learning_rate": 7.290234134592855e-06, "loss": 1.0686, "step": 15204 }, { "epoch": 0.8313001879378097, "grad_norm": 4.824155807495117, "learning_rate": 7.285631382294478e-06, "loss": 1.0532, "step": 15205 }, { "epoch": 0.8313548607551683, "grad_norm": 2.1781110763549805, "learning_rate": 7.281029969267461e-06, "loss": 1.0555, "step": 15206 }, { "epoch": 0.8314095335725269, "grad_norm": 3.0781259536743164, "learning_rate": 7.276429895656106e-06, "loss": 1.2779, "step": 15207 }, { "epoch": 0.8314642063898855, "grad_norm": 2.3438589572906494, "learning_rate": 7.271831161604625e-06, "loss": 0.9975, "step": 15208 }, { "epoch": 0.8315188792072441, "grad_norm": 2.3901662826538086, "learning_rate": 7.267233767257214e-06, "loss": 0.8818, "step": 15209 }, { "epoch": 0.8315735520246028, "grad_norm": 2.5595123767852783, "learning_rate": 7.262637712758013e-06, "loss": 1.0471, "step": 15210 }, { "epoch": 0.8316282248419614, "grad_norm": 2.377833366394043, "learning_rate": 7.25804299825113e-06, "loss": 1.0143, "step": 15211 }, { "epoch": 0.83168289765932, "grad_norm": 2.5430145263671875, "learning_rate": 7.253449623880631e-06, "loss": 0.9881, "step": 15212 }, { "epoch": 0.8317375704766786, "grad_norm": 2.5616159439086914, "learning_rate": 7.248857589790531e-06, "loss": 1.077, "step": 15213 }, { "epoch": 0.8317922432940372, "grad_norm": 2.7961621284484863, "learning_rate": 7.244266896124818e-06, "loss": 0.9272, "step": 15214 }, { "epoch": 0.8318469161113958, "grad_norm": 3.151902675628662, "learning_rate": 7.239677543027423e-06, "loss": 1.2425, "step": 15215 }, { "epoch": 0.8319015889287544, "grad_norm": 2.4349398612976074, "learning_rate": 7.235089530642231e-06, "loss": 1.041, "step": 15216 }, { "epoch": 0.8319562617461131, "grad_norm": 3.045560121536255, "learning_rate": 7.230502859113114e-06, "loss": 0.9533, "step": 15217 }, { "epoch": 0.8320109345634717, "grad_norm": 2.0199365615844727, "learning_rate": 7.225917528583881e-06, "loss": 0.8263, "step": 15218 }, { "epoch": 0.8320656073808304, "grad_norm": 3.128235101699829, "learning_rate": 7.221333539198294e-06, "loss": 0.7826, "step": 15219 }, { "epoch": 0.832120280198189, "grad_norm": 2.8043506145477295, "learning_rate": 7.216750891100077e-06, "loss": 1.1073, "step": 15220 }, { "epoch": 0.8321749530155476, "grad_norm": 3.454711437225342, "learning_rate": 7.212169584432926e-06, "loss": 0.7878, "step": 15221 }, { "epoch": 0.8322296258329062, "grad_norm": 3.1230874061584473, "learning_rate": 7.207589619340477e-06, "loss": 1.0529, "step": 15222 }, { "epoch": 0.8322842986502649, "grad_norm": 3.7636795043945312, "learning_rate": 7.203010995966325e-06, "loss": 1.0009, "step": 15223 }, { "epoch": 0.8323389714676235, "grad_norm": 2.8761672973632812, "learning_rate": 7.198433714454039e-06, "loss": 1.0669, "step": 15224 }, { "epoch": 0.8323936442849821, "grad_norm": 2.6276779174804688, "learning_rate": 7.193857774947132e-06, "loss": 1.1404, "step": 15225 }, { "epoch": 0.8324483171023407, "grad_norm": 3.141883373260498, "learning_rate": 7.189283177589079e-06, "loss": 1.1967, "step": 15226 }, { "epoch": 0.8325029899196993, "grad_norm": 2.558164596557617, "learning_rate": 7.184709922523297e-06, "loss": 0.9295, "step": 15227 }, { "epoch": 0.8325576627370579, "grad_norm": 2.330864906311035, "learning_rate": 7.180138009893201e-06, "loss": 0.9616, "step": 15228 }, { "epoch": 0.8326123355544165, "grad_norm": 2.752250909805298, "learning_rate": 7.175567439842129e-06, "loss": 1.1189, "step": 15229 }, { "epoch": 0.8326670083717752, "grad_norm": 2.4002034664154053, "learning_rate": 7.170998212513391e-06, "loss": 1.0189, "step": 15230 }, { "epoch": 0.8327216811891338, "grad_norm": 2.721996545791626, "learning_rate": 7.166430328050244e-06, "loss": 1.14, "step": 15231 }, { "epoch": 0.8327763540064924, "grad_norm": 3.1141035556793213, "learning_rate": 7.161863786595918e-06, "loss": 0.9258, "step": 15232 }, { "epoch": 0.832831026823851, "grad_norm": 4.3270392417907715, "learning_rate": 7.157298588293587e-06, "loss": 0.8011, "step": 15233 }, { "epoch": 0.8328856996412096, "grad_norm": 3.100847005844116, "learning_rate": 7.152734733286387e-06, "loss": 1.0373, "step": 15234 }, { "epoch": 0.8329403724585682, "grad_norm": 2.9855897426605225, "learning_rate": 7.148172221717414e-06, "loss": 1.2109, "step": 15235 }, { "epoch": 0.8329950452759268, "grad_norm": 2.5613811016082764, "learning_rate": 7.1436110537297314e-06, "loss": 0.9362, "step": 15236 }, { "epoch": 0.8330497180932855, "grad_norm": 3.0541155338287354, "learning_rate": 7.139051229466337e-06, "loss": 1.0384, "step": 15237 }, { "epoch": 0.8331043909106441, "grad_norm": 2.9199788570404053, "learning_rate": 7.13449274907021e-06, "loss": 1.1259, "step": 15238 }, { "epoch": 0.8331590637280027, "grad_norm": 2.8497278690338135, "learning_rate": 7.129935612684274e-06, "loss": 1.0375, "step": 15239 }, { "epoch": 0.8332137365453613, "grad_norm": 2.478254795074463, "learning_rate": 7.1253798204514e-06, "loss": 0.9843, "step": 15240 }, { "epoch": 0.83326840936272, "grad_norm": 3.474390983581543, "learning_rate": 7.120825372514461e-06, "loss": 1.2465, "step": 15241 }, { "epoch": 0.8333230821800786, "grad_norm": 1.7788829803466797, "learning_rate": 7.1162722690162385e-06, "loss": 0.828, "step": 15242 }, { "epoch": 0.8333777549974372, "grad_norm": 3.157661199569702, "learning_rate": 7.111720510099495e-06, "loss": 0.9972, "step": 15243 }, { "epoch": 0.8334324278147959, "grad_norm": 3.4556667804718018, "learning_rate": 7.107170095906945e-06, "loss": 1.0834, "step": 15244 }, { "epoch": 0.8334871006321545, "grad_norm": 2.3090310096740723, "learning_rate": 7.102621026581263e-06, "loss": 0.8375, "step": 15245 }, { "epoch": 0.8335417734495131, "grad_norm": 2.547821044921875, "learning_rate": 7.098073302265079e-06, "loss": 1.0024, "step": 15246 }, { "epoch": 0.8335964462668717, "grad_norm": 2.628173828125, "learning_rate": 7.09352692310099e-06, "loss": 0.9855, "step": 15247 }, { "epoch": 0.8336511190842303, "grad_norm": 2.3374674320220947, "learning_rate": 7.088981889231538e-06, "loss": 0.9568, "step": 15248 }, { "epoch": 0.8337057919015889, "grad_norm": 5.580234527587891, "learning_rate": 7.0844382007992315e-06, "loss": 1.1874, "step": 15249 }, { "epoch": 0.8337604647189476, "grad_norm": 3.052520275115967, "learning_rate": 7.079895857946533e-06, "loss": 0.9052, "step": 15250 }, { "epoch": 0.8338151375363062, "grad_norm": 2.926285982131958, "learning_rate": 7.075354860815858e-06, "loss": 1.0457, "step": 15251 }, { "epoch": 0.8338698103536648, "grad_norm": 2.557687997817993, "learning_rate": 7.070815209549597e-06, "loss": 1.0167, "step": 15252 }, { "epoch": 0.8339244831710234, "grad_norm": 3.2437195777893066, "learning_rate": 7.066276904290064e-06, "loss": 1.0182, "step": 15253 }, { "epoch": 0.833979155988382, "grad_norm": 4.478669166564941, "learning_rate": 7.0617399451795795e-06, "loss": 1.1131, "step": 15254 }, { "epoch": 0.8340338288057406, "grad_norm": 2.3697140216827393, "learning_rate": 7.05720433236039e-06, "loss": 1.0237, "step": 15255 }, { "epoch": 0.8340885016230992, "grad_norm": 2.544499635696411, "learning_rate": 7.052670065974698e-06, "loss": 1.1508, "step": 15256 }, { "epoch": 0.8341431744404579, "grad_norm": 2.8786306381225586, "learning_rate": 7.0481371461646795e-06, "loss": 1.1482, "step": 15257 }, { "epoch": 0.8341978472578165, "grad_norm": 2.983861207962036, "learning_rate": 7.043605573072454e-06, "loss": 1.2339, "step": 15258 }, { "epoch": 0.8342525200751751, "grad_norm": 2.6105144023895264, "learning_rate": 7.039075346840102e-06, "loss": 1.144, "step": 15259 }, { "epoch": 0.8343071928925337, "grad_norm": 2.5848610401153564, "learning_rate": 7.034546467609676e-06, "loss": 1.0232, "step": 15260 }, { "epoch": 0.8343618657098923, "grad_norm": 2.492577075958252, "learning_rate": 7.030018935523164e-06, "loss": 0.8902, "step": 15261 }, { "epoch": 0.834416538527251, "grad_norm": 4.5263848304748535, "learning_rate": 7.0254927507225285e-06, "loss": 0.9695, "step": 15262 }, { "epoch": 0.8344712113446096, "grad_norm": 4.0098466873168945, "learning_rate": 7.020967913349685e-06, "loss": 1.1088, "step": 15263 }, { "epoch": 0.8345258841619683, "grad_norm": 2.7009871006011963, "learning_rate": 7.016444423546503e-06, "loss": 1.1016, "step": 15264 }, { "epoch": 0.8345805569793269, "grad_norm": 2.7024762630462646, "learning_rate": 7.011922281454802e-06, "loss": 1.0468, "step": 15265 }, { "epoch": 0.8346352297966855, "grad_norm": 2.0812151432037354, "learning_rate": 7.0074014872163915e-06, "loss": 1.0158, "step": 15266 }, { "epoch": 0.8346899026140441, "grad_norm": 2.5388381481170654, "learning_rate": 7.0028820409730075e-06, "loss": 0.8707, "step": 15267 }, { "epoch": 0.8347445754314027, "grad_norm": 3.083176612854004, "learning_rate": 6.998363942866348e-06, "loss": 1.1087, "step": 15268 }, { "epoch": 0.8347992482487613, "grad_norm": 2.777644157409668, "learning_rate": 6.993847193038084e-06, "loss": 0.8228, "step": 15269 }, { "epoch": 0.8348539210661199, "grad_norm": 3.2089760303497314, "learning_rate": 6.9893317916298215e-06, "loss": 1.1761, "step": 15270 }, { "epoch": 0.8349085938834786, "grad_norm": 2.858815908432007, "learning_rate": 6.984817738783151e-06, "loss": 1.0061, "step": 15271 }, { "epoch": 0.8349632667008372, "grad_norm": 2.2568016052246094, "learning_rate": 6.980305034639595e-06, "loss": 0.8752, "step": 15272 }, { "epoch": 0.8350179395181958, "grad_norm": 2.6740975379943848, "learning_rate": 6.975793679340653e-06, "loss": 0.9595, "step": 15273 }, { "epoch": 0.8350726123355544, "grad_norm": 2.5817551612854004, "learning_rate": 6.9712836730277675e-06, "loss": 0.8872, "step": 15274 }, { "epoch": 0.835127285152913, "grad_norm": 2.4562060832977295, "learning_rate": 6.966775015842342e-06, "loss": 1.0186, "step": 15275 }, { "epoch": 0.8351819579702716, "grad_norm": 3.387129545211792, "learning_rate": 6.962267707925757e-06, "loss": 0.911, "step": 15276 }, { "epoch": 0.8352366307876303, "grad_norm": 2.7487916946411133, "learning_rate": 6.9577617494193285e-06, "loss": 1.0913, "step": 15277 }, { "epoch": 0.8352913036049889, "grad_norm": 2.6876883506774902, "learning_rate": 6.953257140464337e-06, "loss": 1.0188, "step": 15278 }, { "epoch": 0.8353459764223475, "grad_norm": 2.154921770095825, "learning_rate": 6.948753881202019e-06, "loss": 0.9197, "step": 15279 }, { "epoch": 0.8354006492397061, "grad_norm": 3.155907154083252, "learning_rate": 6.944251971773569e-06, "loss": 1.0214, "step": 15280 }, { "epoch": 0.8354553220570647, "grad_norm": 2.2825207710266113, "learning_rate": 6.939751412320145e-06, "loss": 1.0002, "step": 15281 }, { "epoch": 0.8355099948744233, "grad_norm": 2.292001247406006, "learning_rate": 6.93525220298285e-06, "loss": 1.2311, "step": 15282 }, { "epoch": 0.835564667691782, "grad_norm": 2.2708327770233154, "learning_rate": 6.9307543439027625e-06, "loss": 1.0326, "step": 15283 }, { "epoch": 0.8356193405091407, "grad_norm": 2.6464359760284424, "learning_rate": 6.926257835220901e-06, "loss": 0.8983, "step": 15284 }, { "epoch": 0.8356740133264993, "grad_norm": 3.2899701595306396, "learning_rate": 6.921762677078242e-06, "loss": 0.969, "step": 15285 }, { "epoch": 0.8357286861438579, "grad_norm": 4.012633323669434, "learning_rate": 6.917268869615751e-06, "loss": 1.1438, "step": 15286 }, { "epoch": 0.8357833589612165, "grad_norm": 2.3288419246673584, "learning_rate": 6.912776412974309e-06, "loss": 1.0138, "step": 15287 }, { "epoch": 0.8358380317785751, "grad_norm": 2.4707517623901367, "learning_rate": 6.908285307294782e-06, "loss": 0.9019, "step": 15288 }, { "epoch": 0.8358927045959337, "grad_norm": 2.0908570289611816, "learning_rate": 6.903795552717984e-06, "loss": 0.8651, "step": 15289 }, { "epoch": 0.8359473774132923, "grad_norm": 2.540616035461426, "learning_rate": 6.8993071493846814e-06, "loss": 1.1169, "step": 15290 }, { "epoch": 0.836002050230651, "grad_norm": 3.3845396041870117, "learning_rate": 6.894820097435606e-06, "loss": 1.1402, "step": 15291 }, { "epoch": 0.8360567230480096, "grad_norm": 2.266507148742676, "learning_rate": 6.890334397011444e-06, "loss": 0.8861, "step": 15292 }, { "epoch": 0.8361113958653682, "grad_norm": 2.7024121284484863, "learning_rate": 6.885850048252846e-06, "loss": 1.0846, "step": 15293 }, { "epoch": 0.8361660686827268, "grad_norm": 2.555889129638672, "learning_rate": 6.881367051300414e-06, "loss": 0.8905, "step": 15294 }, { "epoch": 0.8362207415000854, "grad_norm": 3.536844491958618, "learning_rate": 6.876885406294686e-06, "loss": 1.1692, "step": 15295 }, { "epoch": 0.836275414317444, "grad_norm": 3.1191203594207764, "learning_rate": 6.872405113376218e-06, "loss": 1.11, "step": 15296 }, { "epoch": 0.8363300871348026, "grad_norm": 3.1018221378326416, "learning_rate": 6.867926172685469e-06, "loss": 0.9171, "step": 15297 }, { "epoch": 0.8363847599521613, "grad_norm": 2.8539535999298096, "learning_rate": 6.863448584362869e-06, "loss": 0.8805, "step": 15298 }, { "epoch": 0.8364394327695199, "grad_norm": 2.6899254322052, "learning_rate": 6.858972348548809e-06, "loss": 1.1368, "step": 15299 }, { "epoch": 0.8364941055868785, "grad_norm": 2.3783955574035645, "learning_rate": 6.854497465383641e-06, "loss": 0.9646, "step": 15300 }, { "epoch": 0.8365487784042371, "grad_norm": 2.3336243629455566, "learning_rate": 6.850023935007671e-06, "loss": 1.0773, "step": 15301 }, { "epoch": 0.8366034512215957, "grad_norm": 2.9070885181427, "learning_rate": 6.845551757561158e-06, "loss": 0.9735, "step": 15302 }, { "epoch": 0.8366581240389543, "grad_norm": 2.664759397506714, "learning_rate": 6.841080933184329e-06, "loss": 1.1434, "step": 15303 }, { "epoch": 0.8367127968563131, "grad_norm": 3.2782130241394043, "learning_rate": 6.836611462017345e-06, "loss": 1.0908, "step": 15304 }, { "epoch": 0.8367674696736717, "grad_norm": 2.4822020530700684, "learning_rate": 6.83214334420037e-06, "loss": 0.8014, "step": 15305 }, { "epoch": 0.8368221424910303, "grad_norm": 2.4038591384887695, "learning_rate": 6.827676579873488e-06, "loss": 0.9089, "step": 15306 }, { "epoch": 0.8368768153083889, "grad_norm": 2.915289878845215, "learning_rate": 6.8232111691767405e-06, "loss": 1.1276, "step": 15307 }, { "epoch": 0.8369314881257475, "grad_norm": 2.085283041000366, "learning_rate": 6.818747112250151e-06, "loss": 0.8352, "step": 15308 }, { "epoch": 0.8369861609431061, "grad_norm": 2.128270387649536, "learning_rate": 6.814284409233673e-06, "loss": 0.9421, "step": 15309 }, { "epoch": 0.8370408337604647, "grad_norm": 2.941209316253662, "learning_rate": 6.8098230602672395e-06, "loss": 1.1447, "step": 15310 }, { "epoch": 0.8370955065778234, "grad_norm": 2.6489484310150146, "learning_rate": 6.805363065490727e-06, "loss": 0.9193, "step": 15311 }, { "epoch": 0.837150179395182, "grad_norm": 2.913534164428711, "learning_rate": 6.800904425043974e-06, "loss": 1.0246, "step": 15312 }, { "epoch": 0.8372048522125406, "grad_norm": 2.7421910762786865, "learning_rate": 6.796447139066786e-06, "loss": 1.0481, "step": 15313 }, { "epoch": 0.8372595250298992, "grad_norm": 2.4149210453033447, "learning_rate": 6.791991207698895e-06, "loss": 0.9813, "step": 15314 }, { "epoch": 0.8373141978472578, "grad_norm": 2.9108200073242188, "learning_rate": 6.787536631080044e-06, "loss": 1.132, "step": 15315 }, { "epoch": 0.8373688706646164, "grad_norm": 2.5322835445404053, "learning_rate": 6.783083409349883e-06, "loss": 1.0113, "step": 15316 }, { "epoch": 0.837423543481975, "grad_norm": 2.466325283050537, "learning_rate": 6.7786315426480455e-06, "loss": 0.9542, "step": 15317 }, { "epoch": 0.8374782162993337, "grad_norm": 2.169447660446167, "learning_rate": 6.774181031114113e-06, "loss": 1.113, "step": 15318 }, { "epoch": 0.8375328891166923, "grad_norm": 2.4503166675567627, "learning_rate": 6.76973187488763e-06, "loss": 1.0209, "step": 15319 }, { "epoch": 0.8375875619340509, "grad_norm": 2.691622734069824, "learning_rate": 6.7652840741080914e-06, "loss": 1.1095, "step": 15320 }, { "epoch": 0.8376422347514095, "grad_norm": 2.2805042266845703, "learning_rate": 6.760837628914951e-06, "loss": 0.7359, "step": 15321 }, { "epoch": 0.8376969075687681, "grad_norm": 2.294142961502075, "learning_rate": 6.756392539447637e-06, "loss": 1.0371, "step": 15322 }, { "epoch": 0.8377515803861267, "grad_norm": 2.47359299659729, "learning_rate": 6.7519488058455096e-06, "loss": 1.0687, "step": 15323 }, { "epoch": 0.8378062532034853, "grad_norm": 2.3762776851654053, "learning_rate": 6.74750642824789e-06, "loss": 1.0168, "step": 15324 }, { "epoch": 0.837860926020844, "grad_norm": 2.481361150741577, "learning_rate": 6.743065406794086e-06, "loss": 0.9838, "step": 15325 }, { "epoch": 0.8379155988382027, "grad_norm": 2.906667947769165, "learning_rate": 6.7386257416233335e-06, "loss": 1.2141, "step": 15326 }, { "epoch": 0.8379702716555613, "grad_norm": 2.4699301719665527, "learning_rate": 6.734187432874833e-06, "loss": 0.9495, "step": 15327 }, { "epoch": 0.8380249444729199, "grad_norm": 3.069723606109619, "learning_rate": 6.729750480687741e-06, "loss": 0.8794, "step": 15328 }, { "epoch": 0.8380796172902785, "grad_norm": 3.4531056880950928, "learning_rate": 6.725314885201184e-06, "loss": 1.2031, "step": 15329 }, { "epoch": 0.8381342901076371, "grad_norm": 2.015047788619995, "learning_rate": 6.720880646554223e-06, "loss": 0.9794, "step": 15330 }, { "epoch": 0.8381889629249958, "grad_norm": 2.9321882724761963, "learning_rate": 6.716447764885897e-06, "loss": 1.1774, "step": 15331 }, { "epoch": 0.8382436357423544, "grad_norm": 2.5112900733947754, "learning_rate": 6.7120162403351946e-06, "loss": 1.0376, "step": 15332 }, { "epoch": 0.838298308559713, "grad_norm": 2.5072624683380127, "learning_rate": 6.707586073041061e-06, "loss": 1.1494, "step": 15333 }, { "epoch": 0.8383529813770716, "grad_norm": 3.273151159286499, "learning_rate": 6.70315726314239e-06, "loss": 1.1691, "step": 15334 }, { "epoch": 0.8384076541944302, "grad_norm": 2.7951810359954834, "learning_rate": 6.698729810778065e-06, "loss": 0.8377, "step": 15335 }, { "epoch": 0.8384623270117888, "grad_norm": 3.3669421672821045, "learning_rate": 6.694303716086897e-06, "loss": 1.1149, "step": 15336 }, { "epoch": 0.8385169998291474, "grad_norm": 2.3152780532836914, "learning_rate": 6.689878979207653e-06, "loss": 1.1248, "step": 15337 }, { "epoch": 0.8385716726465061, "grad_norm": 2.150421380996704, "learning_rate": 6.685455600279078e-06, "loss": 0.954, "step": 15338 }, { "epoch": 0.8386263454638647, "grad_norm": 3.5165205001831055, "learning_rate": 6.681033579439855e-06, "loss": 0.9902, "step": 15339 }, { "epoch": 0.8386810182812233, "grad_norm": 4.1901774406433105, "learning_rate": 6.676612916828639e-06, "loss": 1.2021, "step": 15340 }, { "epoch": 0.8387356910985819, "grad_norm": 2.0006110668182373, "learning_rate": 6.672193612584027e-06, "loss": 0.8174, "step": 15341 }, { "epoch": 0.8387903639159405, "grad_norm": 3.1236307621002197, "learning_rate": 6.667775666844589e-06, "loss": 1.1235, "step": 15342 }, { "epoch": 0.8388450367332991, "grad_norm": 3.3920555114746094, "learning_rate": 6.663359079748849e-06, "loss": 1.0017, "step": 15343 }, { "epoch": 0.8388997095506577, "grad_norm": 2.434866189956665, "learning_rate": 6.658943851435267e-06, "loss": 1.0845, "step": 15344 }, { "epoch": 0.8389543823680164, "grad_norm": 2.201626777648926, "learning_rate": 6.654529982042301e-06, "loss": 0.9913, "step": 15345 }, { "epoch": 0.839009055185375, "grad_norm": 2.6219167709350586, "learning_rate": 6.650117471708339e-06, "loss": 0.8414, "step": 15346 }, { "epoch": 0.8390637280027337, "grad_norm": 2.325324296951294, "learning_rate": 6.645706320571726e-06, "loss": 1.0689, "step": 15347 }, { "epoch": 0.8391184008200923, "grad_norm": 2.5439517498016357, "learning_rate": 6.641296528770774e-06, "loss": 0.926, "step": 15348 }, { "epoch": 0.8391730736374509, "grad_norm": 3.2513339519500732, "learning_rate": 6.636888096443744e-06, "loss": 0.9677, "step": 15349 }, { "epoch": 0.8392277464548095, "grad_norm": 3.014003276824951, "learning_rate": 6.632481023728859e-06, "loss": 0.9411, "step": 15350 }, { "epoch": 0.8392824192721681, "grad_norm": 2.369466781616211, "learning_rate": 6.628075310764304e-06, "loss": 0.8604, "step": 15351 }, { "epoch": 0.8393370920895268, "grad_norm": 2.397023916244507, "learning_rate": 6.623670957688205e-06, "loss": 1.0029, "step": 15352 }, { "epoch": 0.8393917649068854, "grad_norm": 2.822160243988037, "learning_rate": 6.619267964638659e-06, "loss": 1.2291, "step": 15353 }, { "epoch": 0.839446437724244, "grad_norm": 2.4592578411102295, "learning_rate": 6.614866331753733e-06, "loss": 0.8522, "step": 15354 }, { "epoch": 0.8395011105416026, "grad_norm": 3.383124351501465, "learning_rate": 6.610466059171422e-06, "loss": 0.897, "step": 15355 }, { "epoch": 0.8395557833589612, "grad_norm": 3.0811619758605957, "learning_rate": 6.606067147029704e-06, "loss": 0.8638, "step": 15356 }, { "epoch": 0.8396104561763198, "grad_norm": 2.5354835987091064, "learning_rate": 6.601669595466492e-06, "loss": 0.7725, "step": 15357 }, { "epoch": 0.8396651289936784, "grad_norm": 2.7347822189331055, "learning_rate": 6.597273404619669e-06, "loss": 1.1541, "step": 15358 }, { "epoch": 0.8397198018110371, "grad_norm": 2.6344406604766846, "learning_rate": 6.592878574627082e-06, "loss": 0.7785, "step": 15359 }, { "epoch": 0.8397744746283957, "grad_norm": 2.3116044998168945, "learning_rate": 6.588485105626513e-06, "loss": 1.0263, "step": 15360 }, { "epoch": 0.8398291474457543, "grad_norm": 3.1211304664611816, "learning_rate": 6.5840929977557305e-06, "loss": 1.1467, "step": 15361 }, { "epoch": 0.8398838202631129, "grad_norm": 1.9979848861694336, "learning_rate": 6.579702251152431e-06, "loss": 1.0039, "step": 15362 }, { "epoch": 0.8399384930804715, "grad_norm": 3.0118300914764404, "learning_rate": 6.575312865954286e-06, "loss": 1.1811, "step": 15363 }, { "epoch": 0.8399931658978301, "grad_norm": 2.5272574424743652, "learning_rate": 6.570924842298931e-06, "loss": 1.0934, "step": 15364 }, { "epoch": 0.8400478387151888, "grad_norm": 3.0185904502868652, "learning_rate": 6.566538180323939e-06, "loss": 1.0873, "step": 15365 }, { "epoch": 0.8401025115325474, "grad_norm": 2.547802686691284, "learning_rate": 6.562152880166861e-06, "loss": 0.93, "step": 15366 }, { "epoch": 0.840157184349906, "grad_norm": 2.889272451400757, "learning_rate": 6.557768941965175e-06, "loss": 1.0484, "step": 15367 }, { "epoch": 0.8402118571672647, "grad_norm": 2.8869876861572266, "learning_rate": 6.5533863658563564e-06, "loss": 1.1561, "step": 15368 }, { "epoch": 0.8402665299846233, "grad_norm": 3.3272740840911865, "learning_rate": 6.549005151977805e-06, "loss": 1.121, "step": 15369 }, { "epoch": 0.8403212028019819, "grad_norm": 3.027217149734497, "learning_rate": 6.544625300466889e-06, "loss": 0.9574, "step": 15370 }, { "epoch": 0.8403758756193405, "grad_norm": 2.8413915634155273, "learning_rate": 6.540246811460937e-06, "loss": 1.1337, "step": 15371 }, { "epoch": 0.8404305484366992, "grad_norm": 3.4996888637542725, "learning_rate": 6.53586968509724e-06, "loss": 1.1608, "step": 15372 }, { "epoch": 0.8404852212540578, "grad_norm": 3.8902511596679688, "learning_rate": 6.531493921513015e-06, "loss": 1.1273, "step": 15373 }, { "epoch": 0.8405398940714164, "grad_norm": 3.2386934757232666, "learning_rate": 6.5271195208454924e-06, "loss": 1.0655, "step": 15374 }, { "epoch": 0.840594566888775, "grad_norm": 2.9403181076049805, "learning_rate": 6.522746483231806e-06, "loss": 0.9038, "step": 15375 }, { "epoch": 0.8406492397061336, "grad_norm": 2.650117874145508, "learning_rate": 6.518374808809086e-06, "loss": 1.0686, "step": 15376 }, { "epoch": 0.8407039125234922, "grad_norm": 2.693182945251465, "learning_rate": 6.514004497714382e-06, "loss": 0.9117, "step": 15377 }, { "epoch": 0.8407585853408508, "grad_norm": 2.3562798500061035, "learning_rate": 6.509635550084736e-06, "loss": 1.0859, "step": 15378 }, { "epoch": 0.8408132581582095, "grad_norm": 2.416391372680664, "learning_rate": 6.505267966057127e-06, "loss": 0.8728, "step": 15379 }, { "epoch": 0.8408679309755681, "grad_norm": 2.972278356552124, "learning_rate": 6.500901745768501e-06, "loss": 0.8842, "step": 15380 }, { "epoch": 0.8409226037929267, "grad_norm": 3.502126932144165, "learning_rate": 6.496536889355748e-06, "loss": 1.2955, "step": 15381 }, { "epoch": 0.8409772766102853, "grad_norm": 2.4871249198913574, "learning_rate": 6.492173396955731e-06, "loss": 1.1638, "step": 15382 }, { "epoch": 0.8410319494276439, "grad_norm": 2.864476442337036, "learning_rate": 6.487811268705252e-06, "loss": 1.1183, "step": 15383 }, { "epoch": 0.8410866222450025, "grad_norm": 2.7514073848724365, "learning_rate": 6.483450504741101e-06, "loss": 0.9172, "step": 15384 }, { "epoch": 0.8411412950623611, "grad_norm": 2.0671303272247314, "learning_rate": 6.479091105199997e-06, "loss": 0.692, "step": 15385 }, { "epoch": 0.8411959678797198, "grad_norm": 2.9519693851470947, "learning_rate": 6.474733070218625e-06, "loss": 0.956, "step": 15386 }, { "epoch": 0.8412506406970784, "grad_norm": 2.3938698768615723, "learning_rate": 6.470376399933631e-06, "loss": 0.9087, "step": 15387 }, { "epoch": 0.841305313514437, "grad_norm": 3.0796260833740234, "learning_rate": 6.466021094481606e-06, "loss": 1.0992, "step": 15388 }, { "epoch": 0.8413599863317957, "grad_norm": 4.422785758972168, "learning_rate": 6.461667153999113e-06, "loss": 1.2791, "step": 15389 }, { "epoch": 0.8414146591491543, "grad_norm": 2.577846050262451, "learning_rate": 6.457314578622664e-06, "loss": 1.0448, "step": 15390 }, { "epoch": 0.8414693319665129, "grad_norm": 3.3001160621643066, "learning_rate": 6.4529633684887295e-06, "loss": 0.9417, "step": 15391 }, { "epoch": 0.8415240047838716, "grad_norm": 3.0955207347869873, "learning_rate": 6.448613523733738e-06, "loss": 1.1163, "step": 15392 }, { "epoch": 0.8415786776012302, "grad_norm": 2.183732509613037, "learning_rate": 6.4442650444940685e-06, "loss": 0.9502, "step": 15393 }, { "epoch": 0.8416333504185888, "grad_norm": 2.864773988723755, "learning_rate": 6.439917930906081e-06, "loss": 0.8718, "step": 15394 }, { "epoch": 0.8416880232359474, "grad_norm": 2.5730581283569336, "learning_rate": 6.435572183106065e-06, "loss": 1.0457, "step": 15395 }, { "epoch": 0.841742696053306, "grad_norm": 1.8895210027694702, "learning_rate": 6.431227801230278e-06, "loss": 0.6536, "step": 15396 }, { "epoch": 0.8417973688706646, "grad_norm": 2.957679033279419, "learning_rate": 6.426884785414933e-06, "loss": 1.1051, "step": 15397 }, { "epoch": 0.8418520416880232, "grad_norm": 2.2820887565612793, "learning_rate": 6.422543135796205e-06, "loss": 1.0134, "step": 15398 }, { "epoch": 0.8419067145053819, "grad_norm": 2.531951904296875, "learning_rate": 6.418202852510219e-06, "loss": 0.9969, "step": 15399 }, { "epoch": 0.8419613873227405, "grad_norm": 2.502577543258667, "learning_rate": 6.413863935693065e-06, "loss": 0.9881, "step": 15400 }, { "epoch": 0.8420160601400991, "grad_norm": 2.996074676513672, "learning_rate": 6.40952638548078e-06, "loss": 1.0174, "step": 15401 }, { "epoch": 0.8420707329574577, "grad_norm": 2.500682830810547, "learning_rate": 6.40519020200937e-06, "loss": 1.0612, "step": 15402 }, { "epoch": 0.8421254057748163, "grad_norm": 2.4076151847839355, "learning_rate": 6.400855385414772e-06, "loss": 1.1527, "step": 15403 }, { "epoch": 0.8421800785921749, "grad_norm": 2.6344287395477295, "learning_rate": 6.3965219358329385e-06, "loss": 1.0575, "step": 15404 }, { "epoch": 0.8422347514095335, "grad_norm": 2.2405173778533936, "learning_rate": 6.3921898533997105e-06, "loss": 0.9186, "step": 15405 }, { "epoch": 0.8422894242268922, "grad_norm": 3.0037150382995605, "learning_rate": 6.3878591382509344e-06, "loss": 0.9693, "step": 15406 }, { "epoch": 0.8423440970442508, "grad_norm": 3.1705548763275146, "learning_rate": 6.383529790522385e-06, "loss": 1.0998, "step": 15407 }, { "epoch": 0.8423987698616094, "grad_norm": 2.6332101821899414, "learning_rate": 6.379201810349805e-06, "loss": 1.2483, "step": 15408 }, { "epoch": 0.842453442678968, "grad_norm": 2.5590097904205322, "learning_rate": 6.374875197868901e-06, "loss": 1.0169, "step": 15409 }, { "epoch": 0.8425081154963266, "grad_norm": 2.282468318939209, "learning_rate": 6.3705499532153264e-06, "loss": 0.8608, "step": 15410 }, { "epoch": 0.8425627883136853, "grad_norm": 4.229084014892578, "learning_rate": 6.366226076524695e-06, "loss": 1.0291, "step": 15411 }, { "epoch": 0.8426174611310439, "grad_norm": 2.3158915042877197, "learning_rate": 6.3619035679325815e-06, "loss": 1.0062, "step": 15412 }, { "epoch": 0.8426721339484026, "grad_norm": 2.589583396911621, "learning_rate": 6.357582427574504e-06, "loss": 1.0996, "step": 15413 }, { "epoch": 0.8427268067657612, "grad_norm": 2.244206666946411, "learning_rate": 6.353262655585951e-06, "loss": 1.0188, "step": 15414 }, { "epoch": 0.8427814795831198, "grad_norm": 2.5601518154144287, "learning_rate": 6.348944252102379e-06, "loss": 1.042, "step": 15415 }, { "epoch": 0.8428361524004784, "grad_norm": 2.542593002319336, "learning_rate": 6.34462721725918e-06, "loss": 1.0059, "step": 15416 }, { "epoch": 0.842890825217837, "grad_norm": 2.956002950668335, "learning_rate": 6.3403115511917074e-06, "loss": 0.8635, "step": 15417 }, { "epoch": 0.8429454980351956, "grad_norm": 3.6397769451141357, "learning_rate": 6.335997254035281e-06, "loss": 1.1362, "step": 15418 }, { "epoch": 0.8430001708525543, "grad_norm": 2.447816848754883, "learning_rate": 6.331684325925164e-06, "loss": 1.0503, "step": 15419 }, { "epoch": 0.8430548436699129, "grad_norm": 2.473512649536133, "learning_rate": 6.327372766996592e-06, "loss": 0.9986, "step": 15420 }, { "epoch": 0.8431095164872715, "grad_norm": 3.1375906467437744, "learning_rate": 6.323062577384742e-06, "loss": 1.1068, "step": 15421 }, { "epoch": 0.8431641893046301, "grad_norm": 1.8197532892227173, "learning_rate": 6.3187537572247604e-06, "loss": 0.9469, "step": 15422 }, { "epoch": 0.8432188621219887, "grad_norm": 1.8760102987289429, "learning_rate": 6.3144463066517505e-06, "loss": 0.8864, "step": 15423 }, { "epoch": 0.8432735349393473, "grad_norm": 4.0735039710998535, "learning_rate": 6.310140225800765e-06, "loss": 1.1153, "step": 15424 }, { "epoch": 0.8433282077567059, "grad_norm": 2.58013916015625, "learning_rate": 6.305835514806813e-06, "loss": 0.9548, "step": 15425 }, { "epoch": 0.8433828805740646, "grad_norm": 2.3675382137298584, "learning_rate": 6.301532173804875e-06, "loss": 0.9898, "step": 15426 }, { "epoch": 0.8434375533914232, "grad_norm": 3.355842113494873, "learning_rate": 6.297230202929855e-06, "loss": 1.0333, "step": 15427 }, { "epoch": 0.8434922262087818, "grad_norm": 2.386472702026367, "learning_rate": 6.292929602316672e-06, "loss": 0.9682, "step": 15428 }, { "epoch": 0.8435468990261404, "grad_norm": 3.0044643878936768, "learning_rate": 6.288630372100146e-06, "loss": 0.8163, "step": 15429 }, { "epoch": 0.843601571843499, "grad_norm": 2.1338860988616943, "learning_rate": 6.284332512415081e-06, "loss": 0.984, "step": 15430 }, { "epoch": 0.8436562446608576, "grad_norm": 3.5603489875793457, "learning_rate": 6.280036023396229e-06, "loss": 0.8535, "step": 15431 }, { "epoch": 0.8437109174782162, "grad_norm": 2.808194637298584, "learning_rate": 6.275740905178313e-06, "loss": 1.1714, "step": 15432 }, { "epoch": 0.843765590295575, "grad_norm": 2.5862135887145996, "learning_rate": 6.271447157895988e-06, "loss": 0.9107, "step": 15433 }, { "epoch": 0.8438202631129336, "grad_norm": 2.5839552879333496, "learning_rate": 6.267154781683893e-06, "loss": 1.1016, "step": 15434 }, { "epoch": 0.8438749359302922, "grad_norm": 2.182772159576416, "learning_rate": 6.262863776676603e-06, "loss": 0.9231, "step": 15435 }, { "epoch": 0.8439296087476508, "grad_norm": 2.7414610385894775, "learning_rate": 6.2585741430086605e-06, "loss": 1.134, "step": 15436 }, { "epoch": 0.8439842815650094, "grad_norm": 2.281492233276367, "learning_rate": 6.2542858808145696e-06, "loss": 0.8783, "step": 15437 }, { "epoch": 0.844038954382368, "grad_norm": 4.271790981292725, "learning_rate": 6.249998990228773e-06, "loss": 1.0594, "step": 15438 }, { "epoch": 0.8440936271997266, "grad_norm": 2.1160507202148438, "learning_rate": 6.245713471385694e-06, "loss": 0.902, "step": 15439 }, { "epoch": 0.8441483000170853, "grad_norm": 2.220055103302002, "learning_rate": 6.241429324419684e-06, "loss": 1.0875, "step": 15440 }, { "epoch": 0.8442029728344439, "grad_norm": 4.482484817504883, "learning_rate": 6.237146549465095e-06, "loss": 1.2194, "step": 15441 }, { "epoch": 0.8442576456518025, "grad_norm": 3.315056800842285, "learning_rate": 6.232865146656197e-06, "loss": 1.12, "step": 15442 }, { "epoch": 0.8443123184691611, "grad_norm": 2.925058126449585, "learning_rate": 6.228585116127228e-06, "loss": 0.9527, "step": 15443 }, { "epoch": 0.8443669912865197, "grad_norm": 2.4375181198120117, "learning_rate": 6.22430645801238e-06, "loss": 1.1191, "step": 15444 }, { "epoch": 0.8444216641038783, "grad_norm": 3.136375665664673, "learning_rate": 6.220029172445818e-06, "loss": 1.2056, "step": 15445 }, { "epoch": 0.844476336921237, "grad_norm": 2.585252285003662, "learning_rate": 6.215753259561641e-06, "loss": 1.0811, "step": 15446 }, { "epoch": 0.8445310097385956, "grad_norm": 2.5971927642822266, "learning_rate": 6.211478719493924e-06, "loss": 0.7931, "step": 15447 }, { "epoch": 0.8445856825559542, "grad_norm": 2.509272813796997, "learning_rate": 6.207205552376688e-06, "loss": 0.9687, "step": 15448 }, { "epoch": 0.8446403553733128, "grad_norm": 2.250117540359497, "learning_rate": 6.202933758343921e-06, "loss": 0.9614, "step": 15449 }, { "epoch": 0.8446950281906714, "grad_norm": 3.861556053161621, "learning_rate": 6.198663337529548e-06, "loss": 0.9455, "step": 15450 }, { "epoch": 0.84474970100803, "grad_norm": 3.0670006275177, "learning_rate": 6.194394290067479e-06, "loss": 0.9443, "step": 15451 }, { "epoch": 0.8448043738253886, "grad_norm": 2.486738443374634, "learning_rate": 6.190126616091541e-06, "loss": 0.9074, "step": 15452 }, { "epoch": 0.8448590466427474, "grad_norm": 3.290919065475464, "learning_rate": 6.185860315735581e-06, "loss": 1.1752, "step": 15453 }, { "epoch": 0.844913719460106, "grad_norm": 2.214587450027466, "learning_rate": 6.181595389133338e-06, "loss": 1.1003, "step": 15454 }, { "epoch": 0.8449683922774646, "grad_norm": 2.6954832077026367, "learning_rate": 6.177331836418549e-06, "loss": 1.1728, "step": 15455 }, { "epoch": 0.8450230650948232, "grad_norm": 2.9696438312530518, "learning_rate": 6.173069657724884e-06, "loss": 1.2075, "step": 15456 }, { "epoch": 0.8450777379121818, "grad_norm": 2.379711627960205, "learning_rate": 6.168808853185981e-06, "loss": 1.0138, "step": 15457 }, { "epoch": 0.8451324107295404, "grad_norm": 2.543234348297119, "learning_rate": 6.164549422935439e-06, "loss": 1.1061, "step": 15458 }, { "epoch": 0.845187083546899, "grad_norm": 2.171008825302124, "learning_rate": 6.160291367106807e-06, "loss": 1.0747, "step": 15459 }, { "epoch": 0.8452417563642577, "grad_norm": 2.530452013015747, "learning_rate": 6.156034685833589e-06, "loss": 1.0777, "step": 15460 }, { "epoch": 0.8452964291816163, "grad_norm": 2.457531452178955, "learning_rate": 6.151779379249245e-06, "loss": 1.0664, "step": 15461 }, { "epoch": 0.8453511019989749, "grad_norm": 2.5303308963775635, "learning_rate": 6.147525447487212e-06, "loss": 0.9976, "step": 15462 }, { "epoch": 0.8454057748163335, "grad_norm": 2.1299095153808594, "learning_rate": 6.143272890680863e-06, "loss": 0.9316, "step": 15463 }, { "epoch": 0.8454604476336921, "grad_norm": 2.9724206924438477, "learning_rate": 6.1390217089635216e-06, "loss": 0.9855, "step": 15464 }, { "epoch": 0.8455151204510507, "grad_norm": 2.7179696559906006, "learning_rate": 6.134771902468495e-06, "loss": 0.9207, "step": 15465 }, { "epoch": 0.8455697932684093, "grad_norm": 3.186617612838745, "learning_rate": 6.130523471329025e-06, "loss": 0.9945, "step": 15466 }, { "epoch": 0.845624466085768, "grad_norm": 2.797569513320923, "learning_rate": 6.126276415678311e-06, "loss": 1.0172, "step": 15467 }, { "epoch": 0.8456791389031266, "grad_norm": 2.3358452320098877, "learning_rate": 6.122030735649531e-06, "loss": 1.0954, "step": 15468 }, { "epoch": 0.8457338117204852, "grad_norm": 3.2576189041137695, "learning_rate": 6.117786431375788e-06, "loss": 1.145, "step": 15469 }, { "epoch": 0.8457884845378438, "grad_norm": 2.5947070121765137, "learning_rate": 6.113543502990171e-06, "loss": 1.0433, "step": 15470 }, { "epoch": 0.8458431573552024, "grad_norm": 2.7440221309661865, "learning_rate": 6.109301950625695e-06, "loss": 0.9464, "step": 15471 }, { "epoch": 0.845897830172561, "grad_norm": 3.1206724643707275, "learning_rate": 6.105061774415377e-06, "loss": 1.1861, "step": 15472 }, { "epoch": 0.8459525029899198, "grad_norm": 2.7732698917388916, "learning_rate": 6.100822974492149e-06, "loss": 1.0601, "step": 15473 }, { "epoch": 0.8460071758072784, "grad_norm": 2.2954952716827393, "learning_rate": 6.09658555098892e-06, "loss": 0.888, "step": 15474 }, { "epoch": 0.846061848624637, "grad_norm": 3.2552378177642822, "learning_rate": 6.092349504038542e-06, "loss": 0.7774, "step": 15475 }, { "epoch": 0.8461165214419956, "grad_norm": 3.199352979660034, "learning_rate": 6.088114833773844e-06, "loss": 0.9593, "step": 15476 }, { "epoch": 0.8461711942593542, "grad_norm": 2.433678150177002, "learning_rate": 6.083881540327591e-06, "loss": 0.9164, "step": 15477 }, { "epoch": 0.8462258670767128, "grad_norm": 2.1870429515838623, "learning_rate": 6.079649623832512e-06, "loss": 0.9586, "step": 15478 }, { "epoch": 0.8462805398940714, "grad_norm": 2.3517041206359863, "learning_rate": 6.075419084421308e-06, "loss": 0.9901, "step": 15479 }, { "epoch": 0.8463352127114301, "grad_norm": 2.502624273300171, "learning_rate": 6.071189922226611e-06, "loss": 0.9589, "step": 15480 }, { "epoch": 0.8463898855287887, "grad_norm": 2.6201882362365723, "learning_rate": 6.0669621373810215e-06, "loss": 1.1202, "step": 15481 }, { "epoch": 0.8464445583461473, "grad_norm": 2.4222540855407715, "learning_rate": 6.06273573001711e-06, "loss": 0.8902, "step": 15482 }, { "epoch": 0.8464992311635059, "grad_norm": 2.7422287464141846, "learning_rate": 6.058510700267389e-06, "loss": 1.0868, "step": 15483 }, { "epoch": 0.8465539039808645, "grad_norm": 2.436798095703125, "learning_rate": 6.054287048264324e-06, "loss": 1.0528, "step": 15484 }, { "epoch": 0.8466085767982231, "grad_norm": 2.309818983078003, "learning_rate": 6.050064774140352e-06, "loss": 0.9196, "step": 15485 }, { "epoch": 0.8466632496155817, "grad_norm": 2.874756097793579, "learning_rate": 6.045843878027851e-06, "loss": 1.0784, "step": 15486 }, { "epoch": 0.8467179224329404, "grad_norm": 2.308603525161743, "learning_rate": 6.041624360059167e-06, "loss": 0.8417, "step": 15487 }, { "epoch": 0.846772595250299, "grad_norm": 3.472904920578003, "learning_rate": 6.037406220366604e-06, "loss": 0.7563, "step": 15488 }, { "epoch": 0.8468272680676576, "grad_norm": 1.8923468589782715, "learning_rate": 6.033189459082405e-06, "loss": 0.8981, "step": 15489 }, { "epoch": 0.8468819408850162, "grad_norm": 3.4249563217163086, "learning_rate": 6.028974076338795e-06, "loss": 1.135, "step": 15490 }, { "epoch": 0.8469366137023748, "grad_norm": 2.168792486190796, "learning_rate": 6.024760072267926e-06, "loss": 0.8594, "step": 15491 }, { "epoch": 0.8469912865197334, "grad_norm": 2.531414747238159, "learning_rate": 6.020547447001951e-06, "loss": 0.8742, "step": 15492 }, { "epoch": 0.847045959337092, "grad_norm": 2.6398532390594482, "learning_rate": 6.016336200672939e-06, "loss": 0.9, "step": 15493 }, { "epoch": 0.8471006321544508, "grad_norm": 2.276684284210205, "learning_rate": 6.012126333412932e-06, "loss": 0.8727, "step": 15494 }, { "epoch": 0.8471553049718094, "grad_norm": 2.326220989227295, "learning_rate": 6.0079178453539276e-06, "loss": 0.8963, "step": 15495 }, { "epoch": 0.847209977789168, "grad_norm": 2.3700344562530518, "learning_rate": 6.003710736627871e-06, "loss": 1.0096, "step": 15496 }, { "epoch": 0.8472646506065266, "grad_norm": 3.4337034225463867, "learning_rate": 5.999505007366685e-06, "loss": 0.9661, "step": 15497 }, { "epoch": 0.8473193234238852, "grad_norm": 2.354515552520752, "learning_rate": 5.995300657702224e-06, "loss": 1.0039, "step": 15498 }, { "epoch": 0.8473739962412438, "grad_norm": 2.503526210784912, "learning_rate": 5.9910976877663224e-06, "loss": 0.8054, "step": 15499 }, { "epoch": 0.8474286690586025, "grad_norm": 3.5244126319885254, "learning_rate": 5.986896097690753e-06, "loss": 1.157, "step": 15500 }, { "epoch": 0.8474833418759611, "grad_norm": 2.0002694129943848, "learning_rate": 5.9826958876072484e-06, "loss": 0.9283, "step": 15501 }, { "epoch": 0.8475380146933197, "grad_norm": 2.7897417545318604, "learning_rate": 5.978497057647514e-06, "loss": 1.15, "step": 15502 }, { "epoch": 0.8475926875106783, "grad_norm": 3.2829530239105225, "learning_rate": 5.974299607943201e-06, "loss": 0.9169, "step": 15503 }, { "epoch": 0.8476473603280369, "grad_norm": 2.669837236404419, "learning_rate": 5.9701035386259156e-06, "loss": 1.0323, "step": 15504 }, { "epoch": 0.8477020331453955, "grad_norm": 5.099688529968262, "learning_rate": 5.965908849827212e-06, "loss": 1.2446, "step": 15505 }, { "epoch": 0.8477567059627541, "grad_norm": 2.5311129093170166, "learning_rate": 5.9617155416786195e-06, "loss": 1.113, "step": 15506 }, { "epoch": 0.8478113787801128, "grad_norm": 2.487579107284546, "learning_rate": 5.957523614311616e-06, "loss": 0.9548, "step": 15507 }, { "epoch": 0.8478660515974714, "grad_norm": 3.8337619304656982, "learning_rate": 5.95333306785763e-06, "loss": 0.7542, "step": 15508 }, { "epoch": 0.84792072441483, "grad_norm": 2.7748069763183594, "learning_rate": 5.9491439024480564e-06, "loss": 1.0688, "step": 15509 }, { "epoch": 0.8479753972321886, "grad_norm": 2.79215407371521, "learning_rate": 5.944956118214234e-06, "loss": 1.1465, "step": 15510 }, { "epoch": 0.8480300700495472, "grad_norm": 2.317427635192871, "learning_rate": 5.940769715287481e-06, "loss": 0.9751, "step": 15511 }, { "epoch": 0.8480847428669058, "grad_norm": 3.843137502670288, "learning_rate": 5.936584693799052e-06, "loss": 0.9851, "step": 15512 }, { "epoch": 0.8481394156842644, "grad_norm": 2.750718593597412, "learning_rate": 5.932401053880171e-06, "loss": 0.7962, "step": 15513 }, { "epoch": 0.8481940885016231, "grad_norm": 2.588820219039917, "learning_rate": 5.928218795661999e-06, "loss": 0.9453, "step": 15514 }, { "epoch": 0.8482487613189817, "grad_norm": 2.2907886505126953, "learning_rate": 5.9240379192756825e-06, "loss": 0.7473, "step": 15515 }, { "epoch": 0.8483034341363404, "grad_norm": 3.0248353481292725, "learning_rate": 5.919858424852293e-06, "loss": 1.1986, "step": 15516 }, { "epoch": 0.848358106953699, "grad_norm": 2.2124316692352295, "learning_rate": 5.915680312522887e-06, "loss": 0.8758, "step": 15517 }, { "epoch": 0.8484127797710576, "grad_norm": 2.8301498889923096, "learning_rate": 5.911503582418465e-06, "loss": 1.0264, "step": 15518 }, { "epoch": 0.8484674525884162, "grad_norm": 2.9654290676116943, "learning_rate": 5.907328234669973e-06, "loss": 0.9081, "step": 15519 }, { "epoch": 0.8485221254057748, "grad_norm": 3.34683895111084, "learning_rate": 5.903154269408329e-06, "loss": 0.9699, "step": 15520 }, { "epoch": 0.8485767982231335, "grad_norm": 2.611978769302368, "learning_rate": 5.8989816867644155e-06, "loss": 1.0306, "step": 15521 }, { "epoch": 0.8486314710404921, "grad_norm": 2.8111865520477295, "learning_rate": 5.894810486869057e-06, "loss": 1.0591, "step": 15522 }, { "epoch": 0.8486861438578507, "grad_norm": 2.3763484954833984, "learning_rate": 5.890640669853032e-06, "loss": 0.9397, "step": 15523 }, { "epoch": 0.8487408166752093, "grad_norm": 2.685729503631592, "learning_rate": 5.886472235847079e-06, "loss": 0.888, "step": 15524 }, { "epoch": 0.8487954894925679, "grad_norm": 2.6032297611236572, "learning_rate": 5.882305184981907e-06, "loss": 1.0826, "step": 15525 }, { "epoch": 0.8488501623099265, "grad_norm": 2.745748996734619, "learning_rate": 5.878139517388159e-06, "loss": 0.9349, "step": 15526 }, { "epoch": 0.8489048351272852, "grad_norm": 2.4078049659729004, "learning_rate": 5.873975233196449e-06, "loss": 1.0314, "step": 15527 }, { "epoch": 0.8489595079446438, "grad_norm": 2.393211603164673, "learning_rate": 5.86981233253735e-06, "loss": 1.0437, "step": 15528 }, { "epoch": 0.8490141807620024, "grad_norm": 2.9065325260162354, "learning_rate": 5.865650815541379e-06, "loss": 1.2116, "step": 15529 }, { "epoch": 0.849068853579361, "grad_norm": 3.5155794620513916, "learning_rate": 5.86149068233901e-06, "loss": 1.0067, "step": 15530 }, { "epoch": 0.8491235263967196, "grad_norm": 2.8427722454071045, "learning_rate": 5.8573319330606945e-06, "loss": 1.0547, "step": 15531 }, { "epoch": 0.8491781992140782, "grad_norm": 2.996678352355957, "learning_rate": 5.853174567836828e-06, "loss": 1.197, "step": 15532 }, { "epoch": 0.8492328720314368, "grad_norm": 2.5652055740356445, "learning_rate": 5.849018586797756e-06, "loss": 0.7788, "step": 15533 }, { "epoch": 0.8492875448487955, "grad_norm": 3.52353572845459, "learning_rate": 5.844863990073779e-06, "loss": 1.0495, "step": 15534 }, { "epoch": 0.8493422176661541, "grad_norm": 2.28031063079834, "learning_rate": 5.840710777795166e-06, "loss": 0.8805, "step": 15535 }, { "epoch": 0.8493968904835127, "grad_norm": 2.671236276626587, "learning_rate": 5.836558950092136e-06, "loss": 0.8386, "step": 15536 }, { "epoch": 0.8494515633008713, "grad_norm": 2.597992420196533, "learning_rate": 5.832408507094872e-06, "loss": 1.0208, "step": 15537 }, { "epoch": 0.84950623611823, "grad_norm": 2.5090835094451904, "learning_rate": 5.828259448933498e-06, "loss": 1.0641, "step": 15538 }, { "epoch": 0.8495609089355886, "grad_norm": 2.583035707473755, "learning_rate": 5.824111775738111e-06, "loss": 1.1452, "step": 15539 }, { "epoch": 0.8496155817529472, "grad_norm": 2.0702855587005615, "learning_rate": 5.819965487638746e-06, "loss": 0.949, "step": 15540 }, { "epoch": 0.8496702545703059, "grad_norm": 2.4774696826934814, "learning_rate": 5.815820584765419e-06, "loss": 1.0396, "step": 15541 }, { "epoch": 0.8497249273876645, "grad_norm": 2.4548614025115967, "learning_rate": 5.811677067248095e-06, "loss": 1.097, "step": 15542 }, { "epoch": 0.8497796002050231, "grad_norm": 2.6195147037506104, "learning_rate": 5.8075349352166745e-06, "loss": 0.9836, "step": 15543 }, { "epoch": 0.8498342730223817, "grad_norm": 2.5488762855529785, "learning_rate": 5.803394188801042e-06, "loss": 1.0234, "step": 15544 }, { "epoch": 0.8498889458397403, "grad_norm": 3.4830245971679688, "learning_rate": 5.799254828131023e-06, "loss": 1.2173, "step": 15545 }, { "epoch": 0.8499436186570989, "grad_norm": 2.8365345001220703, "learning_rate": 5.7951168533363964e-06, "loss": 1.1304, "step": 15546 }, { "epoch": 0.8499982914744575, "grad_norm": 3.2763397693634033, "learning_rate": 5.790980264546919e-06, "loss": 1.2052, "step": 15547 }, { "epoch": 0.8500529642918162, "grad_norm": 2.821613311767578, "learning_rate": 5.7868450618922765e-06, "loss": 1.1228, "step": 15548 }, { "epoch": 0.8501076371091748, "grad_norm": 3.5692098140716553, "learning_rate": 5.782711245502132e-06, "loss": 1.0421, "step": 15549 }, { "epoch": 0.8501623099265334, "grad_norm": 2.801626682281494, "learning_rate": 5.778578815506086e-06, "loss": 1.0032, "step": 15550 }, { "epoch": 0.850216982743892, "grad_norm": 2.52494740486145, "learning_rate": 5.774447772033726e-06, "loss": 1.0768, "step": 15551 }, { "epoch": 0.8502716555612506, "grad_norm": 2.6977436542510986, "learning_rate": 5.770318115214573e-06, "loss": 1.0685, "step": 15552 }, { "epoch": 0.8503263283786092, "grad_norm": 3.17584228515625, "learning_rate": 5.766189845178099e-06, "loss": 1.0225, "step": 15553 }, { "epoch": 0.8503810011959679, "grad_norm": 4.107143878936768, "learning_rate": 5.762062962053749e-06, "loss": 0.9917, "step": 15554 }, { "epoch": 0.8504356740133265, "grad_norm": 2.9182026386260986, "learning_rate": 5.757937465970914e-06, "loss": 1.0487, "step": 15555 }, { "epoch": 0.8504903468306851, "grad_norm": 2.1907501220703125, "learning_rate": 5.753813357058952e-06, "loss": 0.8285, "step": 15556 }, { "epoch": 0.8505450196480437, "grad_norm": 2.8079299926757812, "learning_rate": 5.749690635447158e-06, "loss": 1.0451, "step": 15557 }, { "epoch": 0.8505996924654023, "grad_norm": 2.631157875061035, "learning_rate": 5.745569301264814e-06, "loss": 1.0402, "step": 15558 }, { "epoch": 0.850654365282761, "grad_norm": 2.6767091751098633, "learning_rate": 5.741449354641127e-06, "loss": 1.0647, "step": 15559 }, { "epoch": 0.8507090381001196, "grad_norm": 2.304001569747925, "learning_rate": 5.737330795705264e-06, "loss": 1.1046, "step": 15560 }, { "epoch": 0.8507637109174783, "grad_norm": 2.1903223991394043, "learning_rate": 5.733213624586392e-06, "loss": 0.8565, "step": 15561 }, { "epoch": 0.8508183837348369, "grad_norm": 2.295322895050049, "learning_rate": 5.729097841413577e-06, "loss": 1.0115, "step": 15562 }, { "epoch": 0.8508730565521955, "grad_norm": 2.7542502880096436, "learning_rate": 5.7249834463158735e-06, "loss": 0.9307, "step": 15563 }, { "epoch": 0.8509277293695541, "grad_norm": 2.0698907375335693, "learning_rate": 5.720870439422282e-06, "loss": 0.9267, "step": 15564 }, { "epoch": 0.8509824021869127, "grad_norm": 2.9057416915893555, "learning_rate": 5.716758820861761e-06, "loss": 1.113, "step": 15565 }, { "epoch": 0.8510370750042713, "grad_norm": 2.740262985229492, "learning_rate": 5.712648590763231e-06, "loss": 1.024, "step": 15566 }, { "epoch": 0.8510917478216299, "grad_norm": 2.251584768295288, "learning_rate": 5.708539749255559e-06, "loss": 1.0358, "step": 15567 }, { "epoch": 0.8511464206389886, "grad_norm": 3.3666751384735107, "learning_rate": 5.704432296467582e-06, "loss": 1.0533, "step": 15568 }, { "epoch": 0.8512010934563472, "grad_norm": 4.292349338531494, "learning_rate": 5.700326232528064e-06, "loss": 1.2358, "step": 15569 }, { "epoch": 0.8512557662737058, "grad_norm": 2.729279041290283, "learning_rate": 5.696221557565778e-06, "loss": 0.7597, "step": 15570 }, { "epoch": 0.8513104390910644, "grad_norm": 2.5670576095581055, "learning_rate": 5.692118271709407e-06, "loss": 0.861, "step": 15571 }, { "epoch": 0.851365111908423, "grad_norm": 2.2838540077209473, "learning_rate": 5.688016375087612e-06, "loss": 1.0482, "step": 15572 }, { "epoch": 0.8514197847257816, "grad_norm": 2.3101015090942383, "learning_rate": 5.683915867828993e-06, "loss": 0.9785, "step": 15573 }, { "epoch": 0.8514744575431402, "grad_norm": 3.205927610397339, "learning_rate": 5.679816750062128e-06, "loss": 1.023, "step": 15574 }, { "epoch": 0.8515291303604989, "grad_norm": 3.077831745147705, "learning_rate": 5.675719021915538e-06, "loss": 1.1385, "step": 15575 }, { "epoch": 0.8515838031778575, "grad_norm": 2.623321056365967, "learning_rate": 5.6716226835177026e-06, "loss": 1.0071, "step": 15576 }, { "epoch": 0.8516384759952161, "grad_norm": 3.5023815631866455, "learning_rate": 5.667527734997058e-06, "loss": 0.9849, "step": 15577 }, { "epoch": 0.8516931488125747, "grad_norm": 2.6833736896514893, "learning_rate": 5.663434176481997e-06, "loss": 1.0234, "step": 15578 }, { "epoch": 0.8517478216299333, "grad_norm": 2.5134987831115723, "learning_rate": 5.659342008100866e-06, "loss": 0.9735, "step": 15579 }, { "epoch": 0.851802494447292, "grad_norm": 2.258563280105591, "learning_rate": 5.655251229981984e-06, "loss": 0.9113, "step": 15580 }, { "epoch": 0.8518571672646507, "grad_norm": 2.345168352127075, "learning_rate": 5.651161842253605e-06, "loss": 0.9743, "step": 15581 }, { "epoch": 0.8519118400820093, "grad_norm": 2.692451238632202, "learning_rate": 5.647073845043954e-06, "loss": 1.136, "step": 15582 }, { "epoch": 0.8519665128993679, "grad_norm": 2.6671624183654785, "learning_rate": 5.642987238481201e-06, "loss": 1.1377, "step": 15583 }, { "epoch": 0.8520211857167265, "grad_norm": 2.7764718532562256, "learning_rate": 5.638902022693482e-06, "loss": 1.1994, "step": 15584 }, { "epoch": 0.8520758585340851, "grad_norm": 4.396239757537842, "learning_rate": 5.634818197808878e-06, "loss": 1.1238, "step": 15585 }, { "epoch": 0.8521305313514437, "grad_norm": 2.8421289920806885, "learning_rate": 5.630735763955442e-06, "loss": 1.1766, "step": 15586 }, { "epoch": 0.8521852041688023, "grad_norm": 2.444159507751465, "learning_rate": 5.626654721261171e-06, "loss": 1.097, "step": 15587 }, { "epoch": 0.852239876986161, "grad_norm": 2.773116111755371, "learning_rate": 5.622575069854025e-06, "loss": 0.9786, "step": 15588 }, { "epoch": 0.8522945498035196, "grad_norm": 2.3908512592315674, "learning_rate": 5.6184968098619e-06, "loss": 1.1077, "step": 15589 }, { "epoch": 0.8523492226208782, "grad_norm": 1.9755696058273315, "learning_rate": 5.614419941412697e-06, "loss": 0.9633, "step": 15590 }, { "epoch": 0.8524038954382368, "grad_norm": 2.534297227859497, "learning_rate": 5.610344464634226e-06, "loss": 0.8973, "step": 15591 }, { "epoch": 0.8524585682555954, "grad_norm": 2.9983294010162354, "learning_rate": 5.606270379654271e-06, "loss": 1.0364, "step": 15592 }, { "epoch": 0.852513241072954, "grad_norm": 2.609395742416382, "learning_rate": 5.602197686600574e-06, "loss": 1.0422, "step": 15593 }, { "epoch": 0.8525679138903126, "grad_norm": 2.5223209857940674, "learning_rate": 5.598126385600827e-06, "loss": 1.2222, "step": 15594 }, { "epoch": 0.8526225867076713, "grad_norm": 3.320775032043457, "learning_rate": 5.5940564767826885e-06, "loss": 1.2097, "step": 15595 }, { "epoch": 0.8526772595250299, "grad_norm": 2.377439498901367, "learning_rate": 5.589987960273757e-06, "loss": 1.101, "step": 15596 }, { "epoch": 0.8527319323423885, "grad_norm": 2.7528343200683594, "learning_rate": 5.585920836201602e-06, "loss": 0.6326, "step": 15597 }, { "epoch": 0.8527866051597471, "grad_norm": 2.7801921367645264, "learning_rate": 5.581855104693751e-06, "loss": 0.9698, "step": 15598 }, { "epoch": 0.8528412779771057, "grad_norm": 2.7197115421295166, "learning_rate": 5.5777907658776714e-06, "loss": 1.1209, "step": 15599 }, { "epoch": 0.8528959507944643, "grad_norm": 3.142483711242676, "learning_rate": 5.573727819880803e-06, "loss": 1.096, "step": 15600 }, { "epoch": 0.852950623611823, "grad_norm": 3.0183334350585938, "learning_rate": 5.56966626683052e-06, "loss": 1.169, "step": 15601 }, { "epoch": 0.8530052964291817, "grad_norm": 3.680055618286133, "learning_rate": 5.5656061068541985e-06, "loss": 0.9119, "step": 15602 }, { "epoch": 0.8530599692465403, "grad_norm": 2.3562183380126953, "learning_rate": 5.561547340079121e-06, "loss": 0.8222, "step": 15603 }, { "epoch": 0.8531146420638989, "grad_norm": 2.515824794769287, "learning_rate": 5.557489966632551e-06, "loss": 1.085, "step": 15604 }, { "epoch": 0.8531693148812575, "grad_norm": 2.7604098320007324, "learning_rate": 5.55343398664171e-06, "loss": 1.0884, "step": 15605 }, { "epoch": 0.8532239876986161, "grad_norm": 2.9127862453460693, "learning_rate": 5.549379400233756e-06, "loss": 1.2159, "step": 15606 }, { "epoch": 0.8532786605159747, "grad_norm": 2.628647565841675, "learning_rate": 5.545326207535828e-06, "loss": 1.21, "step": 15607 }, { "epoch": 0.8533333333333334, "grad_norm": 2.4290928840637207, "learning_rate": 5.541274408675007e-06, "loss": 0.9912, "step": 15608 }, { "epoch": 0.853388006150692, "grad_norm": 2.7614338397979736, "learning_rate": 5.537224003778335e-06, "loss": 0.8785, "step": 15609 }, { "epoch": 0.8534426789680506, "grad_norm": 2.519912004470825, "learning_rate": 5.533174992972806e-06, "loss": 1.0053, "step": 15610 }, { "epoch": 0.8534973517854092, "grad_norm": 2.302727699279785, "learning_rate": 5.529127376385373e-06, "loss": 1.0581, "step": 15611 }, { "epoch": 0.8535520246027678, "grad_norm": 2.957277297973633, "learning_rate": 5.525081154142947e-06, "loss": 1.0336, "step": 15612 }, { "epoch": 0.8536066974201264, "grad_norm": 2.650301218032837, "learning_rate": 5.521036326372397e-06, "loss": 0.9169, "step": 15613 }, { "epoch": 0.853661370237485, "grad_norm": 3.2909791469573975, "learning_rate": 5.5169928932005285e-06, "loss": 1.0219, "step": 15614 }, { "epoch": 0.8537160430548437, "grad_norm": 2.5573644638061523, "learning_rate": 5.512950854754145e-06, "loss": 1.0951, "step": 15615 }, { "epoch": 0.8537707158722023, "grad_norm": 2.8724024295806885, "learning_rate": 5.508910211159968e-06, "loss": 1.1703, "step": 15616 }, { "epoch": 0.8538253886895609, "grad_norm": 2.852339744567871, "learning_rate": 5.5048709625446895e-06, "loss": 0.9643, "step": 15617 }, { "epoch": 0.8538800615069195, "grad_norm": 2.5789783000946045, "learning_rate": 5.500833109034958e-06, "loss": 1.0898, "step": 15618 }, { "epoch": 0.8539347343242781, "grad_norm": 2.925220489501953, "learning_rate": 5.4967966507573745e-06, "loss": 0.9874, "step": 15619 }, { "epoch": 0.8539894071416367, "grad_norm": 3.207397222518921, "learning_rate": 5.492761587838496e-06, "loss": 1.2083, "step": 15620 }, { "epoch": 0.8540440799589953, "grad_norm": 2.6266720294952393, "learning_rate": 5.4887279204048455e-06, "loss": 1.1486, "step": 15621 }, { "epoch": 0.854098752776354, "grad_norm": 2.5731372833251953, "learning_rate": 5.484695648582888e-06, "loss": 0.9938, "step": 15622 }, { "epoch": 0.8541534255937127, "grad_norm": 2.206786870956421, "learning_rate": 5.480664772499061e-06, "loss": 0.9213, "step": 15623 }, { "epoch": 0.8542080984110713, "grad_norm": 2.5907230377197266, "learning_rate": 5.476635292279742e-06, "loss": 1.1146, "step": 15624 }, { "epoch": 0.8542627712284299, "grad_norm": 2.8147969245910645, "learning_rate": 5.472607208051267e-06, "loss": 1.0246, "step": 15625 }, { "epoch": 0.8543174440457885, "grad_norm": 2.9286088943481445, "learning_rate": 5.468580519939942e-06, "loss": 1.0544, "step": 15626 }, { "epoch": 0.8543721168631471, "grad_norm": 2.8774969577789307, "learning_rate": 5.4645552280720105e-06, "loss": 1.1351, "step": 15627 }, { "epoch": 0.8544267896805057, "grad_norm": 2.6607370376586914, "learning_rate": 5.460531332573693e-06, "loss": 0.9914, "step": 15628 }, { "epoch": 0.8544814624978644, "grad_norm": 2.7446699142456055, "learning_rate": 5.4565088335711555e-06, "loss": 1.0378, "step": 15629 }, { "epoch": 0.854536135315223, "grad_norm": 2.6470701694488525, "learning_rate": 5.452487731190514e-06, "loss": 0.9901, "step": 15630 }, { "epoch": 0.8545908081325816, "grad_norm": 3.0296618938446045, "learning_rate": 5.448468025557852e-06, "loss": 0.9851, "step": 15631 }, { "epoch": 0.8546454809499402, "grad_norm": 2.7887871265411377, "learning_rate": 5.444449716799194e-06, "loss": 1.1596, "step": 15632 }, { "epoch": 0.8547001537672988, "grad_norm": 3.520082950592041, "learning_rate": 5.440432805040535e-06, "loss": 0.9285, "step": 15633 }, { "epoch": 0.8547548265846574, "grad_norm": 2.7257959842681885, "learning_rate": 5.43641729040783e-06, "loss": 0.9408, "step": 15634 }, { "epoch": 0.8548094994020161, "grad_norm": 2.8309152126312256, "learning_rate": 5.432403173026967e-06, "loss": 1.0972, "step": 15635 }, { "epoch": 0.8548641722193747, "grad_norm": 3.146941900253296, "learning_rate": 5.428390453023818e-06, "loss": 0.8328, "step": 15636 }, { "epoch": 0.8549188450367333, "grad_norm": 2.549778699874878, "learning_rate": 5.424379130524193e-06, "loss": 0.9194, "step": 15637 }, { "epoch": 0.8549735178540919, "grad_norm": 2.273941993713379, "learning_rate": 5.4203692056538576e-06, "loss": 1.1097, "step": 15638 }, { "epoch": 0.8550281906714505, "grad_norm": 3.1250698566436768, "learning_rate": 5.416360678538551e-06, "loss": 1.0918, "step": 15639 }, { "epoch": 0.8550828634888091, "grad_norm": 2.638054609298706, "learning_rate": 5.41235354930395e-06, "loss": 0.9428, "step": 15640 }, { "epoch": 0.8551375363061677, "grad_norm": 2.8000588417053223, "learning_rate": 5.408347818075704e-06, "loss": 1.073, "step": 15641 }, { "epoch": 0.8551922091235264, "grad_norm": 2.756467819213867, "learning_rate": 5.404343484979396e-06, "loss": 1.103, "step": 15642 }, { "epoch": 0.855246881940885, "grad_norm": 2.8741984367370605, "learning_rate": 5.400340550140581e-06, "loss": 0.9206, "step": 15643 }, { "epoch": 0.8553015547582437, "grad_norm": 2.995789051055908, "learning_rate": 5.396339013684776e-06, "loss": 1.0856, "step": 15644 }, { "epoch": 0.8553562275756023, "grad_norm": 2.46222186088562, "learning_rate": 5.39233887573744e-06, "loss": 0.9751, "step": 15645 }, { "epoch": 0.8554109003929609, "grad_norm": 2.136216878890991, "learning_rate": 5.388340136423991e-06, "loss": 1.065, "step": 15646 }, { "epoch": 0.8554655732103195, "grad_norm": 2.3220033645629883, "learning_rate": 5.384342795869807e-06, "loss": 0.9096, "step": 15647 }, { "epoch": 0.8555202460276781, "grad_norm": 2.5935158729553223, "learning_rate": 5.380346854200219e-06, "loss": 1.1631, "step": 15648 }, { "epoch": 0.8555749188450368, "grad_norm": 2.8274497985839844, "learning_rate": 5.3763523115405224e-06, "loss": 1.0142, "step": 15649 }, { "epoch": 0.8556295916623954, "grad_norm": 2.399320602416992, "learning_rate": 5.372359168015967e-06, "loss": 1.0879, "step": 15650 }, { "epoch": 0.855684264479754, "grad_norm": 2.7652220726013184, "learning_rate": 5.368367423751747e-06, "loss": 1.2892, "step": 15651 }, { "epoch": 0.8557389372971126, "grad_norm": 2.8370048999786377, "learning_rate": 5.364377078873017e-06, "loss": 0.8868, "step": 15652 }, { "epoch": 0.8557936101144712, "grad_norm": 2.596104383468628, "learning_rate": 5.360388133504896e-06, "loss": 0.9875, "step": 15653 }, { "epoch": 0.8558482829318298, "grad_norm": 2.9896955490112305, "learning_rate": 5.356400587772453e-06, "loss": 1.0326, "step": 15654 }, { "epoch": 0.8559029557491884, "grad_norm": 3.2503154277801514, "learning_rate": 5.352414441800713e-06, "loss": 1.0146, "step": 15655 }, { "epoch": 0.8559576285665471, "grad_norm": 2.6351478099823, "learning_rate": 5.348429695714657e-06, "loss": 1.0974, "step": 15656 }, { "epoch": 0.8560123013839057, "grad_norm": 2.8269577026367188, "learning_rate": 5.3444463496392205e-06, "loss": 0.8632, "step": 15657 }, { "epoch": 0.8560669742012643, "grad_norm": 2.134272813796997, "learning_rate": 5.3404644036992965e-06, "loss": 0.8922, "step": 15658 }, { "epoch": 0.8561216470186229, "grad_norm": 2.6705451011657715, "learning_rate": 5.336483858019753e-06, "loss": 1.0318, "step": 15659 }, { "epoch": 0.8561763198359815, "grad_norm": 2.8725101947784424, "learning_rate": 5.332504712725383e-06, "loss": 1.0624, "step": 15660 }, { "epoch": 0.8562309926533401, "grad_norm": 2.3699092864990234, "learning_rate": 5.32852696794095e-06, "loss": 1.0186, "step": 15661 }, { "epoch": 0.8562856654706988, "grad_norm": 2.8681325912475586, "learning_rate": 5.324550623791169e-06, "loss": 1.1785, "step": 15662 }, { "epoch": 0.8563403382880574, "grad_norm": 2.356095790863037, "learning_rate": 5.320575680400725e-06, "loss": 0.9279, "step": 15663 }, { "epoch": 0.856395011105416, "grad_norm": 2.4951279163360596, "learning_rate": 5.316602137894239e-06, "loss": 1.1109, "step": 15664 }, { "epoch": 0.8564496839227747, "grad_norm": 2.595010280609131, "learning_rate": 5.312629996396301e-06, "loss": 0.9497, "step": 15665 }, { "epoch": 0.8565043567401333, "grad_norm": 2.8826868534088135, "learning_rate": 5.3086592560314504e-06, "loss": 0.9659, "step": 15666 }, { "epoch": 0.8565590295574919, "grad_norm": 2.666680335998535, "learning_rate": 5.304689916924199e-06, "loss": 1.1713, "step": 15667 }, { "epoch": 0.8566137023748505, "grad_norm": 3.122875928878784, "learning_rate": 5.30072197919898e-06, "loss": 1.153, "step": 15668 }, { "epoch": 0.8566683751922092, "grad_norm": 2.9499354362487793, "learning_rate": 5.296755442980223e-06, "loss": 1.1257, "step": 15669 }, { "epoch": 0.8567230480095678, "grad_norm": 2.6169824600219727, "learning_rate": 5.292790308392298e-06, "loss": 1.1075, "step": 15670 }, { "epoch": 0.8567777208269264, "grad_norm": 3.3854422569274902, "learning_rate": 5.288826575559513e-06, "loss": 0.8635, "step": 15671 }, { "epoch": 0.856832393644285, "grad_norm": 2.5072622299194336, "learning_rate": 5.284864244606158e-06, "loss": 1.0628, "step": 15672 }, { "epoch": 0.8568870664616436, "grad_norm": 3.5917906761169434, "learning_rate": 5.280903315656466e-06, "loss": 1.1971, "step": 15673 }, { "epoch": 0.8569417392790022, "grad_norm": 3.020526885986328, "learning_rate": 5.276943788834626e-06, "loss": 1.0934, "step": 15674 }, { "epoch": 0.8569964120963608, "grad_norm": 2.6607282161712646, "learning_rate": 5.27298566426479e-06, "loss": 0.761, "step": 15675 }, { "epoch": 0.8570510849137195, "grad_norm": 3.1680796146392822, "learning_rate": 5.2690289420710585e-06, "loss": 0.8952, "step": 15676 }, { "epoch": 0.8571057577310781, "grad_norm": 2.9362645149230957, "learning_rate": 5.265073622377481e-06, "loss": 1.0294, "step": 15677 }, { "epoch": 0.8571604305484367, "grad_norm": 2.8805651664733887, "learning_rate": 5.261119705308087e-06, "loss": 1.0678, "step": 15678 }, { "epoch": 0.8572151033657953, "grad_norm": 2.381769895553589, "learning_rate": 5.25716719098685e-06, "loss": 1.0633, "step": 15679 }, { "epoch": 0.8572697761831539, "grad_norm": 2.632819652557373, "learning_rate": 5.253216079537693e-06, "loss": 1.1592, "step": 15680 }, { "epoch": 0.8573244490005125, "grad_norm": 2.1960182189941406, "learning_rate": 5.249266371084493e-06, "loss": 0.8806, "step": 15681 }, { "epoch": 0.8573791218178711, "grad_norm": 2.7572247982025146, "learning_rate": 5.245318065751098e-06, "loss": 1.0308, "step": 15682 }, { "epoch": 0.8574337946352298, "grad_norm": 2.2979485988616943, "learning_rate": 5.2413711636613015e-06, "loss": 0.7894, "step": 15683 }, { "epoch": 0.8574884674525884, "grad_norm": 3.0628843307495117, "learning_rate": 5.2374256649388555e-06, "loss": 1.0072, "step": 15684 }, { "epoch": 0.857543140269947, "grad_norm": 2.746194362640381, "learning_rate": 5.233481569707466e-06, "loss": 0.8219, "step": 15685 }, { "epoch": 0.8575978130873056, "grad_norm": 2.5048811435699463, "learning_rate": 5.229538878090795e-06, "loss": 0.974, "step": 15686 }, { "epoch": 0.8576524859046643, "grad_norm": 3.3983261585235596, "learning_rate": 5.225597590212456e-06, "loss": 1.0532, "step": 15687 }, { "epoch": 0.8577071587220229, "grad_norm": 2.4297008514404297, "learning_rate": 5.221657706196042e-06, "loss": 1.0371, "step": 15688 }, { "epoch": 0.8577618315393815, "grad_norm": 3.0707576274871826, "learning_rate": 5.217719226165074e-06, "loss": 1.0237, "step": 15689 }, { "epoch": 0.8578165043567402, "grad_norm": 2.288011312484741, "learning_rate": 5.213782150243041e-06, "loss": 0.8972, "step": 15690 }, { "epoch": 0.8578711771740988, "grad_norm": 2.852349042892456, "learning_rate": 5.209846478553388e-06, "loss": 1.1375, "step": 15691 }, { "epoch": 0.8579258499914574, "grad_norm": 2.78292179107666, "learning_rate": 5.205912211219516e-06, "loss": 1.156, "step": 15692 }, { "epoch": 0.857980522808816, "grad_norm": 3.592892646789551, "learning_rate": 5.201979348364772e-06, "loss": 1.0569, "step": 15693 }, { "epoch": 0.8580351956261746, "grad_norm": 2.487020254135132, "learning_rate": 5.198047890112478e-06, "loss": 1.1073, "step": 15694 }, { "epoch": 0.8580898684435332, "grad_norm": 2.436896324157715, "learning_rate": 5.194117836585893e-06, "loss": 1.1499, "step": 15695 }, { "epoch": 0.8581445412608919, "grad_norm": 3.2934985160827637, "learning_rate": 5.190189187908245e-06, "loss": 1.1313, "step": 15696 }, { "epoch": 0.8581992140782505, "grad_norm": 3.298478364944458, "learning_rate": 5.186261944202702e-06, "loss": 0.9959, "step": 15697 }, { "epoch": 0.8582538868956091, "grad_norm": 2.4270832538604736, "learning_rate": 5.182336105592417e-06, "loss": 1.0497, "step": 15698 }, { "epoch": 0.8583085597129677, "grad_norm": 2.621917486190796, "learning_rate": 5.1784116722004785e-06, "loss": 0.8822, "step": 15699 }, { "epoch": 0.8583632325303263, "grad_norm": 2.985325574874878, "learning_rate": 5.1744886441499274e-06, "loss": 1.1087, "step": 15700 }, { "epoch": 0.8584179053476849, "grad_norm": 2.406080961227417, "learning_rate": 5.1705670215637654e-06, "loss": 0.9466, "step": 15701 }, { "epoch": 0.8584725781650435, "grad_norm": 2.412278652191162, "learning_rate": 5.166646804564956e-06, "loss": 0.9703, "step": 15702 }, { "epoch": 0.8585272509824022, "grad_norm": 2.4045591354370117, "learning_rate": 5.162727993276411e-06, "loss": 0.9419, "step": 15703 }, { "epoch": 0.8585819237997608, "grad_norm": 2.5067546367645264, "learning_rate": 5.158810587821e-06, "loss": 0.9777, "step": 15704 }, { "epoch": 0.8586365966171194, "grad_norm": 3.7458956241607666, "learning_rate": 5.154894588321557e-06, "loss": 1.0803, "step": 15705 }, { "epoch": 0.858691269434478, "grad_norm": 2.345700979232788, "learning_rate": 5.150979994900862e-06, "loss": 1.1126, "step": 15706 }, { "epoch": 0.8587459422518366, "grad_norm": 2.7772631645202637, "learning_rate": 5.1470668076816385e-06, "loss": 1.1412, "step": 15707 }, { "epoch": 0.8588006150691953, "grad_norm": 3.89418888092041, "learning_rate": 5.143155026786606e-06, "loss": 1.0191, "step": 15708 }, { "epoch": 0.8588552878865539, "grad_norm": 2.3093039989471436, "learning_rate": 5.139244652338399e-06, "loss": 1.0404, "step": 15709 }, { "epoch": 0.8589099607039126, "grad_norm": 2.2664575576782227, "learning_rate": 5.13533568445963e-06, "loss": 0.931, "step": 15710 }, { "epoch": 0.8589646335212712, "grad_norm": 2.2974255084991455, "learning_rate": 5.131428123272863e-06, "loss": 1.0357, "step": 15711 }, { "epoch": 0.8590193063386298, "grad_norm": 2.4778823852539062, "learning_rate": 5.127521968900606e-06, "loss": 1.0561, "step": 15712 }, { "epoch": 0.8590739791559884, "grad_norm": 2.1412885189056396, "learning_rate": 5.123617221465343e-06, "loss": 0.9936, "step": 15713 }, { "epoch": 0.859128651973347, "grad_norm": 3.018220901489258, "learning_rate": 5.119713881089505e-06, "loss": 0.9997, "step": 15714 }, { "epoch": 0.8591833247907056, "grad_norm": 2.931852102279663, "learning_rate": 5.115811947895466e-06, "loss": 1.0993, "step": 15715 }, { "epoch": 0.8592379976080642, "grad_norm": 3.17883038520813, "learning_rate": 5.111911422005577e-06, "loss": 1.0941, "step": 15716 }, { "epoch": 0.8592926704254229, "grad_norm": 3.478806972503662, "learning_rate": 5.108012303542126e-06, "loss": 0.9315, "step": 15717 }, { "epoch": 0.8593473432427815, "grad_norm": 2.729923963546753, "learning_rate": 5.104114592627385e-06, "loss": 0.9419, "step": 15718 }, { "epoch": 0.8594020160601401, "grad_norm": 2.3722972869873047, "learning_rate": 5.100218289383546e-06, "loss": 1.0807, "step": 15719 }, { "epoch": 0.8594566888774987, "grad_norm": 2.980008602142334, "learning_rate": 5.0963233939327835e-06, "loss": 1.0034, "step": 15720 }, { "epoch": 0.8595113616948573, "grad_norm": 2.2260684967041016, "learning_rate": 5.092429906397217e-06, "loss": 1.0882, "step": 15721 }, { "epoch": 0.8595660345122159, "grad_norm": 3.069464683532715, "learning_rate": 5.08853782689892e-06, "loss": 0.9994, "step": 15722 }, { "epoch": 0.8596207073295746, "grad_norm": 4.475683689117432, "learning_rate": 5.084647155559924e-06, "loss": 1.0155, "step": 15723 }, { "epoch": 0.8596753801469332, "grad_norm": 2.495363235473633, "learning_rate": 5.080757892502225e-06, "loss": 1.027, "step": 15724 }, { "epoch": 0.8597300529642918, "grad_norm": 3.3535122871398926, "learning_rate": 5.076870037847758e-06, "loss": 1.1143, "step": 15725 }, { "epoch": 0.8597847257816504, "grad_norm": 2.4100348949432373, "learning_rate": 5.072983591718428e-06, "loss": 1.1386, "step": 15726 }, { "epoch": 0.859839398599009, "grad_norm": 2.7854349613189697, "learning_rate": 5.06909855423609e-06, "loss": 1.0088, "step": 15727 }, { "epoch": 0.8598940714163676, "grad_norm": 3.617725372314453, "learning_rate": 5.065214925522566e-06, "loss": 1.0228, "step": 15728 }, { "epoch": 0.8599487442337262, "grad_norm": 3.06002140045166, "learning_rate": 5.0613327056996065e-06, "loss": 0.9309, "step": 15729 }, { "epoch": 0.860003417051085, "grad_norm": 2.980438470840454, "learning_rate": 5.057451894888948e-06, "loss": 1.1396, "step": 15730 }, { "epoch": 0.8600580898684436, "grad_norm": 2.297435998916626, "learning_rate": 5.053572493212267e-06, "loss": 0.8581, "step": 15731 }, { "epoch": 0.8601127626858022, "grad_norm": 3.471163272857666, "learning_rate": 5.049694500791197e-06, "loss": 1.0311, "step": 15732 }, { "epoch": 0.8601674355031608, "grad_norm": 3.100498676300049, "learning_rate": 5.045817917747325e-06, "loss": 1.1671, "step": 15733 }, { "epoch": 0.8602221083205194, "grad_norm": 2.495143175125122, "learning_rate": 5.0419427442022046e-06, "loss": 0.9987, "step": 15734 }, { "epoch": 0.860276781137878, "grad_norm": 2.540756940841675, "learning_rate": 5.038068980277333e-06, "loss": 1.1252, "step": 15735 }, { "epoch": 0.8603314539552366, "grad_norm": 2.796727418899536, "learning_rate": 5.0341966260941675e-06, "loss": 1.0516, "step": 15736 }, { "epoch": 0.8603861267725953, "grad_norm": 2.443101644515991, "learning_rate": 5.030325681774134e-06, "loss": 1.1392, "step": 15737 }, { "epoch": 0.8604407995899539, "grad_norm": 2.6112565994262695, "learning_rate": 5.026456147438591e-06, "loss": 1.1571, "step": 15738 }, { "epoch": 0.8604954724073125, "grad_norm": 2.9446799755096436, "learning_rate": 5.0225880232088684e-06, "loss": 0.9209, "step": 15739 }, { "epoch": 0.8605501452246711, "grad_norm": 2.401069402694702, "learning_rate": 5.018721309206253e-06, "loss": 1.0157, "step": 15740 }, { "epoch": 0.8606048180420297, "grad_norm": 3.0081939697265625, "learning_rate": 5.014856005551976e-06, "loss": 1.0167, "step": 15741 }, { "epoch": 0.8606594908593883, "grad_norm": 3.846892833709717, "learning_rate": 5.01099211236723e-06, "loss": 1.2073, "step": 15742 }, { "epoch": 0.8607141636767469, "grad_norm": 2.8141589164733887, "learning_rate": 5.00712962977316e-06, "loss": 1.0573, "step": 15743 }, { "epoch": 0.8607688364941056, "grad_norm": 2.196842670440674, "learning_rate": 5.003268557890883e-06, "loss": 0.8534, "step": 15744 }, { "epoch": 0.8608235093114642, "grad_norm": 2.5651466846466064, "learning_rate": 4.999408896841451e-06, "loss": 0.9493, "step": 15745 }, { "epoch": 0.8608781821288228, "grad_norm": 2.4672160148620605, "learning_rate": 4.995550646745873e-06, "loss": 1.0453, "step": 15746 }, { "epoch": 0.8609328549461814, "grad_norm": 3.436460256576538, "learning_rate": 4.99169380772514e-06, "loss": 1.0389, "step": 15747 }, { "epoch": 0.86098752776354, "grad_norm": 2.2566027641296387, "learning_rate": 4.987838379900167e-06, "loss": 1.0184, "step": 15748 }, { "epoch": 0.8610422005808986, "grad_norm": 2.9004616737365723, "learning_rate": 4.983984363391842e-06, "loss": 0.8665, "step": 15749 }, { "epoch": 0.8610968733982574, "grad_norm": 2.9438421726226807, "learning_rate": 4.980131758320999e-06, "loss": 1.0499, "step": 15750 }, { "epoch": 0.861151546215616, "grad_norm": 2.763517379760742, "learning_rate": 4.976280564808444e-06, "loss": 0.9945, "step": 15751 }, { "epoch": 0.8612062190329746, "grad_norm": 3.5234463214874268, "learning_rate": 4.972430782974913e-06, "loss": 0.9021, "step": 15752 }, { "epoch": 0.8612608918503332, "grad_norm": 3.455883502960205, "learning_rate": 4.968582412941125e-06, "loss": 1.0203, "step": 15753 }, { "epoch": 0.8613155646676918, "grad_norm": 2.2807226181030273, "learning_rate": 4.964735454827734e-06, "loss": 1.1881, "step": 15754 }, { "epoch": 0.8613702374850504, "grad_norm": 4.6513752937316895, "learning_rate": 4.9608899087553616e-06, "loss": 1.0825, "step": 15755 }, { "epoch": 0.861424910302409, "grad_norm": 2.4223408699035645, "learning_rate": 4.957045774844576e-06, "loss": 0.9848, "step": 15756 }, { "epoch": 0.8614795831197677, "grad_norm": 2.304175615310669, "learning_rate": 4.953203053215916e-06, "loss": 1.2665, "step": 15757 }, { "epoch": 0.8615342559371263, "grad_norm": 3.4380409717559814, "learning_rate": 4.949361743989867e-06, "loss": 1.1632, "step": 15758 }, { "epoch": 0.8615889287544849, "grad_norm": 2.385474920272827, "learning_rate": 4.94552184728686e-06, "loss": 0.9275, "step": 15759 }, { "epoch": 0.8616436015718435, "grad_norm": 3.923597574234009, "learning_rate": 4.941683363227301e-06, "loss": 0.9553, "step": 15760 }, { "epoch": 0.8616982743892021, "grad_norm": 2.3133139610290527, "learning_rate": 4.937846291931536e-06, "loss": 0.8077, "step": 15761 }, { "epoch": 0.8617529472065607, "grad_norm": 4.294440269470215, "learning_rate": 4.934010633519875e-06, "loss": 0.9627, "step": 15762 }, { "epoch": 0.8618076200239193, "grad_norm": 2.756998062133789, "learning_rate": 4.9301763881125784e-06, "loss": 0.9595, "step": 15763 }, { "epoch": 0.861862292841278, "grad_norm": 2.518673896789551, "learning_rate": 4.926343555829877e-06, "loss": 1.0848, "step": 15764 }, { "epoch": 0.8619169656586366, "grad_norm": 2.732102632522583, "learning_rate": 4.922512136791929e-06, "loss": 1.2644, "step": 15765 }, { "epoch": 0.8619716384759952, "grad_norm": 2.631296396255493, "learning_rate": 4.918682131118873e-06, "loss": 1.0447, "step": 15766 }, { "epoch": 0.8620263112933538, "grad_norm": 2.802565336227417, "learning_rate": 4.914853538930803e-06, "loss": 1.1045, "step": 15767 }, { "epoch": 0.8620809841107124, "grad_norm": 2.357412099838257, "learning_rate": 4.911026360347754e-06, "loss": 1.0051, "step": 15768 }, { "epoch": 0.862135656928071, "grad_norm": 3.2573325634002686, "learning_rate": 4.907200595489725e-06, "loss": 1.1528, "step": 15769 }, { "epoch": 0.8621903297454296, "grad_norm": 3.5707197189331055, "learning_rate": 4.903376244476665e-06, "loss": 1.04, "step": 15770 }, { "epoch": 0.8622450025627884, "grad_norm": 3.5992064476013184, "learning_rate": 4.899553307428489e-06, "loss": 0.8247, "step": 15771 }, { "epoch": 0.862299675380147, "grad_norm": 2.7433559894561768, "learning_rate": 4.895731784465063e-06, "loss": 1.1572, "step": 15772 }, { "epoch": 0.8623543481975056, "grad_norm": 2.6585376262664795, "learning_rate": 4.891911675706201e-06, "loss": 0.9699, "step": 15773 }, { "epoch": 0.8624090210148642, "grad_norm": 2.8039000034332275, "learning_rate": 4.8880929812716855e-06, "loss": 0.9069, "step": 15774 }, { "epoch": 0.8624636938322228, "grad_norm": 2.433478832244873, "learning_rate": 4.884275701281238e-06, "loss": 1.0228, "step": 15775 }, { "epoch": 0.8625183666495814, "grad_norm": 2.625077486038208, "learning_rate": 4.8804598358545565e-06, "loss": 0.9271, "step": 15776 }, { "epoch": 0.8625730394669401, "grad_norm": 2.206740617752075, "learning_rate": 4.876645385111284e-06, "loss": 0.9102, "step": 15777 }, { "epoch": 0.8626277122842987, "grad_norm": 2.8904683589935303, "learning_rate": 4.872832349171014e-06, "loss": 0.9865, "step": 15778 }, { "epoch": 0.8626823851016573, "grad_norm": 2.836347818374634, "learning_rate": 4.869020728153306e-06, "loss": 1.2021, "step": 15779 }, { "epoch": 0.8627370579190159, "grad_norm": 2.8375582695007324, "learning_rate": 4.8652105221776654e-06, "loss": 1.1406, "step": 15780 }, { "epoch": 0.8627917307363745, "grad_norm": 2.4645273685455322, "learning_rate": 4.861401731363563e-06, "loss": 0.9739, "step": 15781 }, { "epoch": 0.8628464035537331, "grad_norm": 2.6220765113830566, "learning_rate": 4.857594355830414e-06, "loss": 1.0448, "step": 15782 }, { "epoch": 0.8629010763710917, "grad_norm": 2.8195888996124268, "learning_rate": 4.853788395697595e-06, "loss": 1.1048, "step": 15783 }, { "epoch": 0.8629557491884504, "grad_norm": 2.0632567405700684, "learning_rate": 4.849983851084444e-06, "loss": 0.8988, "step": 15784 }, { "epoch": 0.863010422005809, "grad_norm": 3.249483585357666, "learning_rate": 4.846180722110244e-06, "loss": 0.9547, "step": 15785 }, { "epoch": 0.8630650948231676, "grad_norm": 4.20560884475708, "learning_rate": 4.842379008894244e-06, "loss": 1.0128, "step": 15786 }, { "epoch": 0.8631197676405262, "grad_norm": 2.6502063274383545, "learning_rate": 4.838578711555641e-06, "loss": 1.0145, "step": 15787 }, { "epoch": 0.8631744404578848, "grad_norm": 3.9214417934417725, "learning_rate": 4.834779830213582e-06, "loss": 0.853, "step": 15788 }, { "epoch": 0.8632291132752434, "grad_norm": 2.426805257797241, "learning_rate": 4.830982364987191e-06, "loss": 1.1155, "step": 15789 }, { "epoch": 0.863283786092602, "grad_norm": 2.5795743465423584, "learning_rate": 4.827186315995524e-06, "loss": 1.1124, "step": 15790 }, { "epoch": 0.8633384589099607, "grad_norm": 2.459091901779175, "learning_rate": 4.823391683357615e-06, "loss": 1.1221, "step": 15791 }, { "epoch": 0.8633931317273194, "grad_norm": 2.1659069061279297, "learning_rate": 4.819598467192432e-06, "loss": 1.1084, "step": 15792 }, { "epoch": 0.863447804544678, "grad_norm": 2.3413333892822266, "learning_rate": 4.815806667618905e-06, "loss": 0.9845, "step": 15793 }, { "epoch": 0.8635024773620366, "grad_norm": 2.19997239112854, "learning_rate": 4.812016284755932e-06, "loss": 1.0705, "step": 15794 }, { "epoch": 0.8635571501793952, "grad_norm": 2.841496229171753, "learning_rate": 4.808227318722352e-06, "loss": 1.0499, "step": 15795 }, { "epoch": 0.8636118229967538, "grad_norm": 3.6808409690856934, "learning_rate": 4.804439769636959e-06, "loss": 0.8172, "step": 15796 }, { "epoch": 0.8636664958141124, "grad_norm": 2.3924856185913086, "learning_rate": 4.800653637618519e-06, "loss": 0.8758, "step": 15797 }, { "epoch": 0.8637211686314711, "grad_norm": 2.452234983444214, "learning_rate": 4.796868922785741e-06, "loss": 0.8981, "step": 15798 }, { "epoch": 0.8637758414488297, "grad_norm": 3.2067766189575195, "learning_rate": 4.793085625257282e-06, "loss": 0.9323, "step": 15799 }, { "epoch": 0.8638305142661883, "grad_norm": 2.592738151550293, "learning_rate": 4.789303745151774e-06, "loss": 0.9047, "step": 15800 }, { "epoch": 0.8638851870835469, "grad_norm": 1.8735300302505493, "learning_rate": 4.785523282587778e-06, "loss": 0.8856, "step": 15801 }, { "epoch": 0.8639398599009055, "grad_norm": 5.332171440124512, "learning_rate": 4.781744237683849e-06, "loss": 1.0161, "step": 15802 }, { "epoch": 0.8639945327182641, "grad_norm": 2.7994282245635986, "learning_rate": 4.7779666105584705e-06, "loss": 0.9013, "step": 15803 }, { "epoch": 0.8640492055356228, "grad_norm": 2.693268299102783, "learning_rate": 4.774190401330081e-06, "loss": 1.0831, "step": 15804 }, { "epoch": 0.8641038783529814, "grad_norm": 3.128523111343384, "learning_rate": 4.770415610117079e-06, "loss": 1.0548, "step": 15805 }, { "epoch": 0.86415855117034, "grad_norm": 2.383329153060913, "learning_rate": 4.766642237037827e-06, "loss": 1.073, "step": 15806 }, { "epoch": 0.8642132239876986, "grad_norm": 3.054969310760498, "learning_rate": 4.762870282210629e-06, "loss": 1.18, "step": 15807 }, { "epoch": 0.8642678968050572, "grad_norm": 2.6854021549224854, "learning_rate": 4.7590997457537536e-06, "loss": 1.0152, "step": 15808 }, { "epoch": 0.8643225696224158, "grad_norm": 2.662475347518921, "learning_rate": 4.755330627785426e-06, "loss": 1.0439, "step": 15809 }, { "epoch": 0.8643772424397744, "grad_norm": 2.2877655029296875, "learning_rate": 4.7515629284238135e-06, "loss": 1.1314, "step": 15810 }, { "epoch": 0.8644319152571331, "grad_norm": 2.787452459335327, "learning_rate": 4.747796647787062e-06, "loss": 0.9837, "step": 15811 }, { "epoch": 0.8644865880744917, "grad_norm": 2.0847041606903076, "learning_rate": 4.744031785993247e-06, "loss": 0.923, "step": 15812 }, { "epoch": 0.8645412608918503, "grad_norm": 2.610299587249756, "learning_rate": 4.740268343160426e-06, "loss": 1.1241, "step": 15813 }, { "epoch": 0.864595933709209, "grad_norm": 2.5311121940612793, "learning_rate": 4.736506319406581e-06, "loss": 1.0366, "step": 15814 }, { "epoch": 0.8646506065265676, "grad_norm": 2.9283928871154785, "learning_rate": 4.732745714849684e-06, "loss": 1.261, "step": 15815 }, { "epoch": 0.8647052793439262, "grad_norm": 2.8875348567962646, "learning_rate": 4.728986529607637e-06, "loss": 0.9717, "step": 15816 }, { "epoch": 0.8647599521612848, "grad_norm": 3.894658088684082, "learning_rate": 4.725228763798312e-06, "loss": 1.1389, "step": 15817 }, { "epoch": 0.8648146249786435, "grad_norm": 2.4594295024871826, "learning_rate": 4.72147241753953e-06, "loss": 1.1225, "step": 15818 }, { "epoch": 0.8648692977960021, "grad_norm": 2.7218990325927734, "learning_rate": 4.717717490949058e-06, "loss": 0.9628, "step": 15819 }, { "epoch": 0.8649239706133607, "grad_norm": 3.0428667068481445, "learning_rate": 4.713963984144637e-06, "loss": 1.0799, "step": 15820 }, { "epoch": 0.8649786434307193, "grad_norm": 2.0389297008514404, "learning_rate": 4.710211897243949e-06, "loss": 0.9125, "step": 15821 }, { "epoch": 0.8650333162480779, "grad_norm": 2.9082181453704834, "learning_rate": 4.706461230364645e-06, "loss": 1.0952, "step": 15822 }, { "epoch": 0.8650879890654365, "grad_norm": 2.4491543769836426, "learning_rate": 4.702711983624319e-06, "loss": 1.1609, "step": 15823 }, { "epoch": 0.8651426618827951, "grad_norm": 2.9944705963134766, "learning_rate": 4.698964157140523e-06, "loss": 1.1783, "step": 15824 }, { "epoch": 0.8651973347001538, "grad_norm": 2.5387985706329346, "learning_rate": 4.695217751030767e-06, "loss": 1.1202, "step": 15825 }, { "epoch": 0.8652520075175124, "grad_norm": 3.567401170730591, "learning_rate": 4.691472765412525e-06, "loss": 1.2012, "step": 15826 }, { "epoch": 0.865306680334871, "grad_norm": 2.29360294342041, "learning_rate": 4.687729200403207e-06, "loss": 0.9851, "step": 15827 }, { "epoch": 0.8653613531522296, "grad_norm": 2.8747000694274902, "learning_rate": 4.683987056120198e-06, "loss": 0.8117, "step": 15828 }, { "epoch": 0.8654160259695882, "grad_norm": 2.3631749153137207, "learning_rate": 4.680246332680827e-06, "loss": 1.1506, "step": 15829 }, { "epoch": 0.8654706987869468, "grad_norm": 2.4923393726348877, "learning_rate": 4.676507030202382e-06, "loss": 0.9233, "step": 15830 }, { "epoch": 0.8655253716043055, "grad_norm": 4.025989532470703, "learning_rate": 4.672769148802098e-06, "loss": 0.9744, "step": 15831 }, { "epoch": 0.8655800444216641, "grad_norm": 2.8319263458251953, "learning_rate": 4.66903268859718e-06, "loss": 1.2408, "step": 15832 }, { "epoch": 0.8656347172390227, "grad_norm": 3.052879571914673, "learning_rate": 4.665297649704781e-06, "loss": 0.9284, "step": 15833 }, { "epoch": 0.8656893900563813, "grad_norm": 4.472597599029541, "learning_rate": 4.661564032241999e-06, "loss": 1.1519, "step": 15834 }, { "epoch": 0.86574406287374, "grad_norm": 2.2362308502197266, "learning_rate": 4.657831836325916e-06, "loss": 0.9192, "step": 15835 }, { "epoch": 0.8657987356910986, "grad_norm": 3.1173601150512695, "learning_rate": 4.654101062073546e-06, "loss": 0.9509, "step": 15836 }, { "epoch": 0.8658534085084572, "grad_norm": 2.8164138793945312, "learning_rate": 4.6503717096018586e-06, "loss": 0.8786, "step": 15837 }, { "epoch": 0.8659080813258159, "grad_norm": 3.555424690246582, "learning_rate": 4.646643779027787e-06, "loss": 1.1405, "step": 15838 }, { "epoch": 0.8659627541431745, "grad_norm": 2.4607038497924805, "learning_rate": 4.642917270468222e-06, "loss": 1.1816, "step": 15839 }, { "epoch": 0.8660174269605331, "grad_norm": 2.656010389328003, "learning_rate": 4.639192184039998e-06, "loss": 1.047, "step": 15840 }, { "epoch": 0.8660720997778917, "grad_norm": 2.736398220062256, "learning_rate": 4.635468519859914e-06, "loss": 1.2251, "step": 15841 }, { "epoch": 0.8661267725952503, "grad_norm": 2.7391090393066406, "learning_rate": 4.631746278044719e-06, "loss": 1.0308, "step": 15842 }, { "epoch": 0.8661814454126089, "grad_norm": 2.4920248985290527, "learning_rate": 4.628025458711127e-06, "loss": 0.8691, "step": 15843 }, { "epoch": 0.8662361182299675, "grad_norm": 3.9235315322875977, "learning_rate": 4.624306061975792e-06, "loss": 1.0147, "step": 15844 }, { "epoch": 0.8662907910473262, "grad_norm": 2.613680124282837, "learning_rate": 4.620588087955346e-06, "loss": 0.9288, "step": 15845 }, { "epoch": 0.8663454638646848, "grad_norm": 2.7626571655273438, "learning_rate": 4.616871536766354e-06, "loss": 0.9553, "step": 15846 }, { "epoch": 0.8664001366820434, "grad_norm": 2.1808056831359863, "learning_rate": 4.613156408525349e-06, "loss": 0.9234, "step": 15847 }, { "epoch": 0.866454809499402, "grad_norm": 2.651062488555908, "learning_rate": 4.609442703348815e-06, "loss": 0.8985, "step": 15848 }, { "epoch": 0.8665094823167606, "grad_norm": 2.355630397796631, "learning_rate": 4.605730421353183e-06, "loss": 1.035, "step": 15849 }, { "epoch": 0.8665641551341192, "grad_norm": 2.8169074058532715, "learning_rate": 4.602019562654864e-06, "loss": 1.282, "step": 15850 }, { "epoch": 0.8666188279514778, "grad_norm": 3.3249881267547607, "learning_rate": 4.598310127370192e-06, "loss": 1.0181, "step": 15851 }, { "epoch": 0.8666735007688365, "grad_norm": 2.8967738151550293, "learning_rate": 4.594602115615487e-06, "loss": 0.9152, "step": 15852 }, { "epoch": 0.8667281735861951, "grad_norm": 2.7725374698638916, "learning_rate": 4.590895527507005e-06, "loss": 1.0505, "step": 15853 }, { "epoch": 0.8667828464035537, "grad_norm": 3.336167573928833, "learning_rate": 4.587190363160948e-06, "loss": 1.097, "step": 15854 }, { "epoch": 0.8668375192209123, "grad_norm": 2.482074022293091, "learning_rate": 4.583486622693517e-06, "loss": 0.9783, "step": 15855 }, { "epoch": 0.866892192038271, "grad_norm": 2.012049436569214, "learning_rate": 4.579784306220824e-06, "loss": 1.021, "step": 15856 }, { "epoch": 0.8669468648556296, "grad_norm": 2.1962804794311523, "learning_rate": 4.576083413858951e-06, "loss": 0.7854, "step": 15857 }, { "epoch": 0.8670015376729883, "grad_norm": 2.385942220687866, "learning_rate": 4.5723839457239406e-06, "loss": 0.9792, "step": 15858 }, { "epoch": 0.8670562104903469, "grad_norm": 2.537405014038086, "learning_rate": 4.56868590193178e-06, "loss": 1.1359, "step": 15859 }, { "epoch": 0.8671108833077055, "grad_norm": 2.353863000869751, "learning_rate": 4.564989282598426e-06, "loss": 0.8571, "step": 15860 }, { "epoch": 0.8671655561250641, "grad_norm": 2.2975308895111084, "learning_rate": 4.561294087839779e-06, "loss": 0.8051, "step": 15861 }, { "epoch": 0.8672202289424227, "grad_norm": 2.7553932666778564, "learning_rate": 4.557600317771698e-06, "loss": 0.9231, "step": 15862 }, { "epoch": 0.8672749017597813, "grad_norm": 2.354586124420166, "learning_rate": 4.553907972509996e-06, "loss": 0.8876, "step": 15863 }, { "epoch": 0.8673295745771399, "grad_norm": 2.688565254211426, "learning_rate": 4.550217052170441e-06, "loss": 0.9531, "step": 15864 }, { "epoch": 0.8673842473944986, "grad_norm": 2.2763071060180664, "learning_rate": 4.546527556868768e-06, "loss": 0.981, "step": 15865 }, { "epoch": 0.8674389202118572, "grad_norm": 4.373367786407471, "learning_rate": 4.542839486720657e-06, "loss": 1.0143, "step": 15866 }, { "epoch": 0.8674935930292158, "grad_norm": 2.661890745162964, "learning_rate": 4.539152841841737e-06, "loss": 1.0729, "step": 15867 }, { "epoch": 0.8675482658465744, "grad_norm": 2.530763864517212, "learning_rate": 4.535467622347606e-06, "loss": 1.0847, "step": 15868 }, { "epoch": 0.867602938663933, "grad_norm": 2.51619815826416, "learning_rate": 4.531783828353803e-06, "loss": 1.1276, "step": 15869 }, { "epoch": 0.8676576114812916, "grad_norm": 3.6766161918640137, "learning_rate": 4.528101459975836e-06, "loss": 1.0025, "step": 15870 }, { "epoch": 0.8677122842986502, "grad_norm": 2.310821771621704, "learning_rate": 4.524420517329165e-06, "loss": 0.784, "step": 15871 }, { "epoch": 0.8677669571160089, "grad_norm": 4.200865268707275, "learning_rate": 4.520741000529194e-06, "loss": 0.8736, "step": 15872 }, { "epoch": 0.8678216299333675, "grad_norm": 2.3839876651763916, "learning_rate": 4.5170629096912995e-06, "loss": 0.9854, "step": 15873 }, { "epoch": 0.8678763027507261, "grad_norm": 3.954021692276001, "learning_rate": 4.51338624493079e-06, "loss": 0.8081, "step": 15874 }, { "epoch": 0.8679309755680847, "grad_norm": 3.6604201793670654, "learning_rate": 4.509711006362965e-06, "loss": 1.0262, "step": 15875 }, { "epoch": 0.8679856483854433, "grad_norm": 2.422835111618042, "learning_rate": 4.506037194103046e-06, "loss": 1.0574, "step": 15876 }, { "epoch": 0.868040321202802, "grad_norm": 2.8295280933380127, "learning_rate": 4.50236480826623e-06, "loss": 0.9408, "step": 15877 }, { "epoch": 0.8680949940201605, "grad_norm": 2.456874370574951, "learning_rate": 4.49869384896765e-06, "loss": 1.1394, "step": 15878 }, { "epoch": 0.8681496668375193, "grad_norm": 5.016119003295898, "learning_rate": 4.495024316322416e-06, "loss": 1.2535, "step": 15879 }, { "epoch": 0.8682043396548779, "grad_norm": 4.2610883712768555, "learning_rate": 4.49135621044558e-06, "loss": 1.1366, "step": 15880 }, { "epoch": 0.8682590124722365, "grad_norm": 3.9936001300811768, "learning_rate": 4.487689531452149e-06, "loss": 0.8598, "step": 15881 }, { "epoch": 0.8683136852895951, "grad_norm": 3.8877220153808594, "learning_rate": 4.484024279457089e-06, "loss": 0.7086, "step": 15882 }, { "epoch": 0.8683683581069537, "grad_norm": 2.4434609413146973, "learning_rate": 4.480360454575316e-06, "loss": 1.0957, "step": 15883 }, { "epoch": 0.8684230309243123, "grad_norm": 3.059588670730591, "learning_rate": 4.476698056921719e-06, "loss": 0.9303, "step": 15884 }, { "epoch": 0.868477703741671, "grad_norm": 2.969287157058716, "learning_rate": 4.473037086611126e-06, "loss": 1.0908, "step": 15885 }, { "epoch": 0.8685323765590296, "grad_norm": 2.425234079360962, "learning_rate": 4.469377543758318e-06, "loss": 1.0468, "step": 15886 }, { "epoch": 0.8685870493763882, "grad_norm": 2.8085086345672607, "learning_rate": 4.465719428478038e-06, "loss": 1.0836, "step": 15887 }, { "epoch": 0.8686417221937468, "grad_norm": 2.5062015056610107, "learning_rate": 4.462062740884982e-06, "loss": 0.9727, "step": 15888 }, { "epoch": 0.8686963950111054, "grad_norm": 2.526580572128296, "learning_rate": 4.458407481093807e-06, "loss": 0.943, "step": 15889 }, { "epoch": 0.868751067828464, "grad_norm": 2.8005623817443848, "learning_rate": 4.454753649219118e-06, "loss": 1.0932, "step": 15890 }, { "epoch": 0.8688057406458226, "grad_norm": 2.316744565963745, "learning_rate": 4.451101245375472e-06, "loss": 0.8714, "step": 15891 }, { "epoch": 0.8688604134631813, "grad_norm": 2.4679675102233887, "learning_rate": 4.4474502696774e-06, "loss": 0.888, "step": 15892 }, { "epoch": 0.8689150862805399, "grad_norm": 2.2950592041015625, "learning_rate": 4.44380072223935e-06, "loss": 1.0339, "step": 15893 }, { "epoch": 0.8689697590978985, "grad_norm": 2.453624725341797, "learning_rate": 4.440152603175779e-06, "loss": 1.1801, "step": 15894 }, { "epoch": 0.8690244319152571, "grad_norm": 2.8865344524383545, "learning_rate": 4.436505912601063e-06, "loss": 1.1474, "step": 15895 }, { "epoch": 0.8690791047326157, "grad_norm": 3.9392917156219482, "learning_rate": 4.432860650629533e-06, "loss": 1.1652, "step": 15896 }, { "epoch": 0.8691337775499743, "grad_norm": 2.654355764389038, "learning_rate": 4.4292168173754865e-06, "loss": 1.0587, "step": 15897 }, { "epoch": 0.8691884503673329, "grad_norm": 3.122445821762085, "learning_rate": 4.425574412953176e-06, "loss": 1.1086, "step": 15898 }, { "epoch": 0.8692431231846917, "grad_norm": 2.3175435066223145, "learning_rate": 4.4219334374768e-06, "loss": 0.9489, "step": 15899 }, { "epoch": 0.8692977960020503, "grad_norm": 2.6543753147125244, "learning_rate": 4.418293891060521e-06, "loss": 1.1744, "step": 15900 }, { "epoch": 0.8693524688194089, "grad_norm": 2.266230344772339, "learning_rate": 4.414655773818455e-06, "loss": 1.0632, "step": 15901 }, { "epoch": 0.8694071416367675, "grad_norm": 2.2764604091644287, "learning_rate": 4.41101908586467e-06, "loss": 1.1578, "step": 15902 }, { "epoch": 0.8694618144541261, "grad_norm": 2.853982448577881, "learning_rate": 4.407383827313183e-06, "loss": 1.0619, "step": 15903 }, { "epoch": 0.8695164872714847, "grad_norm": 2.875716209411621, "learning_rate": 4.40374999827799e-06, "loss": 0.9291, "step": 15904 }, { "epoch": 0.8695711600888433, "grad_norm": 3.00728178024292, "learning_rate": 4.400117598873022e-06, "loss": 1.029, "step": 15905 }, { "epoch": 0.869625832906202, "grad_norm": 2.480897903442383, "learning_rate": 4.3964866292121655e-06, "loss": 0.9099, "step": 15906 }, { "epoch": 0.8696805057235606, "grad_norm": 4.146538734436035, "learning_rate": 4.392857089409269e-06, "loss": 1.3021, "step": 15907 }, { "epoch": 0.8697351785409192, "grad_norm": 2.9592549800872803, "learning_rate": 4.38922897957813e-06, "loss": 0.9702, "step": 15908 }, { "epoch": 0.8697898513582778, "grad_norm": 2.5598387718200684, "learning_rate": 4.385602299832514e-06, "loss": 1.0019, "step": 15909 }, { "epoch": 0.8698445241756364, "grad_norm": 2.551947832107544, "learning_rate": 4.381977050286118e-06, "loss": 0.976, "step": 15910 }, { "epoch": 0.869899196992995, "grad_norm": 2.2501516342163086, "learning_rate": 4.378353231052623e-06, "loss": 1.0057, "step": 15911 }, { "epoch": 0.8699538698103537, "grad_norm": 2.63911509513855, "learning_rate": 4.374730842245639e-06, "loss": 0.9335, "step": 15912 }, { "epoch": 0.8700085426277123, "grad_norm": 2.864043951034546, "learning_rate": 4.371109883978741e-06, "loss": 1.0609, "step": 15913 }, { "epoch": 0.8700632154450709, "grad_norm": 2.3929359912872314, "learning_rate": 4.367490356365478e-06, "loss": 1.0969, "step": 15914 }, { "epoch": 0.8701178882624295, "grad_norm": 2.147127866744995, "learning_rate": 4.3638722595193245e-06, "loss": 0.7959, "step": 15915 }, { "epoch": 0.8701725610797881, "grad_norm": 3.832629919052124, "learning_rate": 4.360255593553725e-06, "loss": 1.1825, "step": 15916 }, { "epoch": 0.8702272338971467, "grad_norm": 2.156874895095825, "learning_rate": 4.356640358582076e-06, "loss": 0.9544, "step": 15917 }, { "epoch": 0.8702819067145053, "grad_norm": 2.154893159866333, "learning_rate": 4.353026554717732e-06, "loss": 0.8873, "step": 15918 }, { "epoch": 0.870336579531864, "grad_norm": 3.1195409297943115, "learning_rate": 4.349414182073996e-06, "loss": 1.0741, "step": 15919 }, { "epoch": 0.8703912523492227, "grad_norm": 2.9396538734436035, "learning_rate": 4.3458032407641405e-06, "loss": 0.9827, "step": 15920 }, { "epoch": 0.8704459251665813, "grad_norm": 2.7915050983428955, "learning_rate": 4.342193730901373e-06, "loss": 0.884, "step": 15921 }, { "epoch": 0.8705005979839399, "grad_norm": 2.701883554458618, "learning_rate": 4.3385856525988695e-06, "loss": 1.0346, "step": 15922 }, { "epoch": 0.8705552708012985, "grad_norm": 2.7659928798675537, "learning_rate": 4.334979005969753e-06, "loss": 0.8547, "step": 15923 }, { "epoch": 0.8706099436186571, "grad_norm": 3.426023483276367, "learning_rate": 4.331373791127119e-06, "loss": 1.0795, "step": 15924 }, { "epoch": 0.8706646164360157, "grad_norm": 2.426711320877075, "learning_rate": 4.327770008184001e-06, "loss": 0.8464, "step": 15925 }, { "epoch": 0.8707192892533744, "grad_norm": 2.421201705932617, "learning_rate": 4.3241676572533915e-06, "loss": 1.0143, "step": 15926 }, { "epoch": 0.870773962070733, "grad_norm": 2.9680333137512207, "learning_rate": 4.32056673844824e-06, "loss": 1.2006, "step": 15927 }, { "epoch": 0.8708286348880916, "grad_norm": 2.7917003631591797, "learning_rate": 4.316967251881449e-06, "loss": 0.9181, "step": 15928 }, { "epoch": 0.8708833077054502, "grad_norm": 2.5098555088043213, "learning_rate": 4.313369197665879e-06, "loss": 1.0761, "step": 15929 }, { "epoch": 0.8709379805228088, "grad_norm": 2.40891432762146, "learning_rate": 4.309772575914339e-06, "loss": 0.9466, "step": 15930 }, { "epoch": 0.8709926533401674, "grad_norm": 2.1090126037597656, "learning_rate": 4.3061773867396015e-06, "loss": 1.0317, "step": 15931 }, { "epoch": 0.871047326157526, "grad_norm": 3.2099270820617676, "learning_rate": 4.302583630254375e-06, "loss": 1.1425, "step": 15932 }, { "epoch": 0.8711019989748847, "grad_norm": 2.610227108001709, "learning_rate": 4.298991306571371e-06, "loss": 1.0119, "step": 15933 }, { "epoch": 0.8711566717922433, "grad_norm": 7.277899742126465, "learning_rate": 4.295400415803202e-06, "loss": 0.9706, "step": 15934 }, { "epoch": 0.8712113446096019, "grad_norm": 2.515895366668701, "learning_rate": 4.291810958062459e-06, "loss": 0.8504, "step": 15935 }, { "epoch": 0.8712660174269605, "grad_norm": 2.171287775039673, "learning_rate": 4.288222933461694e-06, "loss": 0.9885, "step": 15936 }, { "epoch": 0.8713206902443191, "grad_norm": 3.4391438961029053, "learning_rate": 4.284636342113396e-06, "loss": 1.0925, "step": 15937 }, { "epoch": 0.8713753630616777, "grad_norm": 3.278697967529297, "learning_rate": 4.28105118413003e-06, "loss": 1.1006, "step": 15938 }, { "epoch": 0.8714300358790364, "grad_norm": 3.3652257919311523, "learning_rate": 4.277467459623996e-06, "loss": 1.0179, "step": 15939 }, { "epoch": 0.871484708696395, "grad_norm": 2.4932661056518555, "learning_rate": 4.273885168707659e-06, "loss": 0.9083, "step": 15940 }, { "epoch": 0.8715393815137537, "grad_norm": 2.879720687866211, "learning_rate": 4.270304311493345e-06, "loss": 1.1744, "step": 15941 }, { "epoch": 0.8715940543311123, "grad_norm": 1.9324026107788086, "learning_rate": 4.266724888093315e-06, "loss": 0.8119, "step": 15942 }, { "epoch": 0.8716487271484709, "grad_norm": 2.9009034633636475, "learning_rate": 4.263146898619824e-06, "loss": 0.9661, "step": 15943 }, { "epoch": 0.8717033999658295, "grad_norm": 2.8749499320983887, "learning_rate": 4.259570343185037e-06, "loss": 1.0193, "step": 15944 }, { "epoch": 0.8717580727831881, "grad_norm": 2.5432236194610596, "learning_rate": 4.255995221901099e-06, "loss": 0.9278, "step": 15945 }, { "epoch": 0.8718127456005468, "grad_norm": 2.5570247173309326, "learning_rate": 4.2524215348801025e-06, "loss": 1.1045, "step": 15946 }, { "epoch": 0.8718674184179054, "grad_norm": 2.9284615516662598, "learning_rate": 4.248849282234102e-06, "loss": 1.0266, "step": 15947 }, { "epoch": 0.871922091235264, "grad_norm": 3.381524085998535, "learning_rate": 4.2452784640750976e-06, "loss": 1.163, "step": 15948 }, { "epoch": 0.8719767640526226, "grad_norm": 2.7305941581726074, "learning_rate": 4.241709080515055e-06, "loss": 0.9427, "step": 15949 }, { "epoch": 0.8720314368699812, "grad_norm": 2.988290786743164, "learning_rate": 4.238141131665879e-06, "loss": 1.0263, "step": 15950 }, { "epoch": 0.8720861096873398, "grad_norm": 2.8013856410980225, "learning_rate": 4.234574617639447e-06, "loss": 0.9793, "step": 15951 }, { "epoch": 0.8721407825046984, "grad_norm": 2.8472952842712402, "learning_rate": 4.231009538547576e-06, "loss": 1.1291, "step": 15952 }, { "epoch": 0.8721954553220571, "grad_norm": 2.9834063053131104, "learning_rate": 4.227445894502064e-06, "loss": 0.8908, "step": 15953 }, { "epoch": 0.8722501281394157, "grad_norm": 2.2961971759796143, "learning_rate": 4.223883685614627e-06, "loss": 0.9374, "step": 15954 }, { "epoch": 0.8723048009567743, "grad_norm": 2.8783183097839355, "learning_rate": 4.220322911996965e-06, "loss": 1.0839, "step": 15955 }, { "epoch": 0.8723594737741329, "grad_norm": 6.239689826965332, "learning_rate": 4.216763573760724e-06, "loss": 0.7429, "step": 15956 }, { "epoch": 0.8724141465914915, "grad_norm": 2.6794934272766113, "learning_rate": 4.2132056710175e-06, "loss": 1.0758, "step": 15957 }, { "epoch": 0.8724688194088501, "grad_norm": 2.6772518157958984, "learning_rate": 4.20964920387884e-06, "loss": 0.9487, "step": 15958 }, { "epoch": 0.8725234922262087, "grad_norm": 3.5529630184173584, "learning_rate": 4.206094172456271e-06, "loss": 0.9811, "step": 15959 }, { "epoch": 0.8725781650435674, "grad_norm": 2.479189157485962, "learning_rate": 4.202540576861247e-06, "loss": 1.0163, "step": 15960 }, { "epoch": 0.872632837860926, "grad_norm": 2.8211770057678223, "learning_rate": 4.198988417205185e-06, "loss": 1.1659, "step": 15961 }, { "epoch": 0.8726875106782847, "grad_norm": 2.760570764541626, "learning_rate": 4.195437693599458e-06, "loss": 1.1202, "step": 15962 }, { "epoch": 0.8727421834956433, "grad_norm": 3.0975990295410156, "learning_rate": 4.191888406155409e-06, "loss": 0.9588, "step": 15963 }, { "epoch": 0.8727968563130019, "grad_norm": 2.6105704307556152, "learning_rate": 4.1883405549843215e-06, "loss": 1.063, "step": 15964 }, { "epoch": 0.8728515291303605, "grad_norm": 2.7362818717956543, "learning_rate": 4.1847941401974235e-06, "loss": 1.1837, "step": 15965 }, { "epoch": 0.8729062019477192, "grad_norm": 2.940706491470337, "learning_rate": 4.18124916190592e-06, "loss": 1.009, "step": 15966 }, { "epoch": 0.8729608747650778, "grad_norm": 3.53617000579834, "learning_rate": 4.1777056202209565e-06, "loss": 0.9933, "step": 15967 }, { "epoch": 0.8730155475824364, "grad_norm": 2.4154903888702393, "learning_rate": 4.174163515253638e-06, "loss": 0.9138, "step": 15968 }, { "epoch": 0.873070220399795, "grad_norm": 2.8064887523651123, "learning_rate": 4.1706228471150244e-06, "loss": 1.0058, "step": 15969 }, { "epoch": 0.8731248932171536, "grad_norm": 2.984844923019409, "learning_rate": 4.167083615916123e-06, "loss": 1.0943, "step": 15970 }, { "epoch": 0.8731795660345122, "grad_norm": 2.456717014312744, "learning_rate": 4.163545821767917e-06, "loss": 1.0466, "step": 15971 }, { "epoch": 0.8732342388518708, "grad_norm": 2.6277031898498535, "learning_rate": 4.160009464781322e-06, "loss": 1.0678, "step": 15972 }, { "epoch": 0.8732889116692295, "grad_norm": 3.150012969970703, "learning_rate": 4.156474545067218e-06, "loss": 1.1822, "step": 15973 }, { "epoch": 0.8733435844865881, "grad_norm": 2.2897238731384277, "learning_rate": 4.152941062736443e-06, "loss": 1.0546, "step": 15974 }, { "epoch": 0.8733982573039467, "grad_norm": 3.099964141845703, "learning_rate": 4.149409017899775e-06, "loss": 0.8468, "step": 15975 }, { "epoch": 0.8734529301213053, "grad_norm": 2.1938817501068115, "learning_rate": 4.145878410667975e-06, "loss": 0.9574, "step": 15976 }, { "epoch": 0.8735076029386639, "grad_norm": 2.5669476985931396, "learning_rate": 4.142349241151728e-06, "loss": 1.0726, "step": 15977 }, { "epoch": 0.8735622757560225, "grad_norm": 2.6116526126861572, "learning_rate": 4.138821509461699e-06, "loss": 0.788, "step": 15978 }, { "epoch": 0.8736169485733811, "grad_norm": 2.7133941650390625, "learning_rate": 4.135295215708496e-06, "loss": 0.9714, "step": 15979 }, { "epoch": 0.8736716213907398, "grad_norm": 2.26651668548584, "learning_rate": 4.131770360002673e-06, "loss": 0.9638, "step": 15980 }, { "epoch": 0.8737262942080984, "grad_norm": 3.2877607345581055, "learning_rate": 4.128246942454755e-06, "loss": 1.0054, "step": 15981 }, { "epoch": 0.873780967025457, "grad_norm": 2.082005500793457, "learning_rate": 4.1247249631752135e-06, "loss": 0.8829, "step": 15982 }, { "epoch": 0.8738356398428156, "grad_norm": 2.3595211505889893, "learning_rate": 4.1212044222744825e-06, "loss": 1.0021, "step": 15983 }, { "epoch": 0.8738903126601743, "grad_norm": 2.613081693649292, "learning_rate": 4.117685319862935e-06, "loss": 0.9981, "step": 15984 }, { "epoch": 0.8739449854775329, "grad_norm": 2.5291662216186523, "learning_rate": 4.114167656050921e-06, "loss": 0.8942, "step": 15985 }, { "epoch": 0.8739996582948915, "grad_norm": 2.629297971725464, "learning_rate": 4.110651430948731e-06, "loss": 1.0607, "step": 15986 }, { "epoch": 0.8740543311122502, "grad_norm": 3.6602113246917725, "learning_rate": 4.107136644666609e-06, "loss": 1.0601, "step": 15987 }, { "epoch": 0.8741090039296088, "grad_norm": 2.0838961601257324, "learning_rate": 4.103623297314746e-06, "loss": 0.952, "step": 15988 }, { "epoch": 0.8741636767469674, "grad_norm": 3.334120273590088, "learning_rate": 4.10011138900333e-06, "loss": 0.9369, "step": 15989 }, { "epoch": 0.874218349564326, "grad_norm": 2.7385730743408203, "learning_rate": 4.0966009198424525e-06, "loss": 1.0002, "step": 15990 }, { "epoch": 0.8742730223816846, "grad_norm": 2.8397345542907715, "learning_rate": 4.093091889942186e-06, "loss": 0.8173, "step": 15991 }, { "epoch": 0.8743276951990432, "grad_norm": 2.9325315952301025, "learning_rate": 4.089584299412558e-06, "loss": 1.2569, "step": 15992 }, { "epoch": 0.8743823680164018, "grad_norm": 2.280616283416748, "learning_rate": 4.086078148363537e-06, "loss": 0.9178, "step": 15993 }, { "epoch": 0.8744370408337605, "grad_norm": 2.4220986366271973, "learning_rate": 4.0825734369050575e-06, "loss": 0.8562, "step": 15994 }, { "epoch": 0.8744917136511191, "grad_norm": 2.9972448348999023, "learning_rate": 4.079070165147014e-06, "loss": 1.0751, "step": 15995 }, { "epoch": 0.8745463864684777, "grad_norm": 3.066322088241577, "learning_rate": 4.075568333199236e-06, "loss": 1.1611, "step": 15996 }, { "epoch": 0.8746010592858363, "grad_norm": 2.8284852504730225, "learning_rate": 4.072067941171531e-06, "loss": 1.1289, "step": 15997 }, { "epoch": 0.8746557321031949, "grad_norm": 2.6512906551361084, "learning_rate": 4.068568989173649e-06, "loss": 1.1638, "step": 15998 }, { "epoch": 0.8747104049205535, "grad_norm": 2.491306781768799, "learning_rate": 4.065071477315296e-06, "loss": 0.9386, "step": 15999 }, { "epoch": 0.8747650777379122, "grad_norm": 2.702439785003662, "learning_rate": 4.0615754057061305e-06, "loss": 1.2396, "step": 16000 }, { "epoch": 0.8748197505552708, "grad_norm": 2.7803585529327393, "learning_rate": 4.058080774455758e-06, "loss": 1.123, "step": 16001 }, { "epoch": 0.8748744233726294, "grad_norm": 2.1992733478546143, "learning_rate": 4.0545875836737745e-06, "loss": 0.9357, "step": 16002 }, { "epoch": 0.874929096189988, "grad_norm": 2.4725124835968018, "learning_rate": 4.051095833469692e-06, "loss": 0.7803, "step": 16003 }, { "epoch": 0.8749837690073466, "grad_norm": 3.428652286529541, "learning_rate": 4.047605523952991e-06, "loss": 1.0109, "step": 16004 }, { "epoch": 0.8750384418247052, "grad_norm": 3.0638909339904785, "learning_rate": 4.04411665523311e-06, "loss": 1.2384, "step": 16005 }, { "epoch": 0.8750931146420639, "grad_norm": 2.512739896774292, "learning_rate": 4.040629227419435e-06, "loss": 1.1201, "step": 16006 }, { "epoch": 0.8751477874594226, "grad_norm": 3.1924514770507812, "learning_rate": 4.0371432406213215e-06, "loss": 1.266, "step": 16007 }, { "epoch": 0.8752024602767812, "grad_norm": 2.396314859390259, "learning_rate": 4.033658694948056e-06, "loss": 1.0302, "step": 16008 }, { "epoch": 0.8752571330941398, "grad_norm": 2.3200466632843018, "learning_rate": 4.0301755905089e-06, "loss": 1.0112, "step": 16009 }, { "epoch": 0.8753118059114984, "grad_norm": 2.792668104171753, "learning_rate": 4.026693927413066e-06, "loss": 0.9845, "step": 16010 }, { "epoch": 0.875366478728857, "grad_norm": 3.4010417461395264, "learning_rate": 4.023213705769701e-06, "loss": 1.0725, "step": 16011 }, { "epoch": 0.8754211515462156, "grad_norm": 3.337460994720459, "learning_rate": 4.019734925687957e-06, "loss": 0.9523, "step": 16012 }, { "epoch": 0.8754758243635742, "grad_norm": 3.5630574226379395, "learning_rate": 4.016257587276884e-06, "loss": 1.0859, "step": 16013 }, { "epoch": 0.8755304971809329, "grad_norm": 2.506340503692627, "learning_rate": 4.012781690645512e-06, "loss": 1.0679, "step": 16014 }, { "epoch": 0.8755851699982915, "grad_norm": 2.58302903175354, "learning_rate": 4.009307235902837e-06, "loss": 0.9563, "step": 16015 }, { "epoch": 0.8756398428156501, "grad_norm": 3.147090196609497, "learning_rate": 4.005834223157784e-06, "loss": 1.1192, "step": 16016 }, { "epoch": 0.8756945156330087, "grad_norm": 2.5198824405670166, "learning_rate": 4.002362652519254e-06, "loss": 1.1647, "step": 16017 }, { "epoch": 0.8757491884503673, "grad_norm": 3.104597330093384, "learning_rate": 3.998892524096093e-06, "loss": 0.7682, "step": 16018 }, { "epoch": 0.8758038612677259, "grad_norm": 2.6206417083740234, "learning_rate": 3.995423837997103e-06, "loss": 1.0413, "step": 16019 }, { "epoch": 0.8758585340850845, "grad_norm": 4.746584415435791, "learning_rate": 3.9919565943310424e-06, "loss": 1.0891, "step": 16020 }, { "epoch": 0.8759132069024432, "grad_norm": 2.598952531814575, "learning_rate": 3.9884907932066176e-06, "loss": 1.037, "step": 16021 }, { "epoch": 0.8759678797198018, "grad_norm": 2.854710578918457, "learning_rate": 3.985026434732508e-06, "loss": 0.8707, "step": 16022 }, { "epoch": 0.8760225525371604, "grad_norm": 2.93808913230896, "learning_rate": 3.981563519017328e-06, "loss": 1.0421, "step": 16023 }, { "epoch": 0.876077225354519, "grad_norm": 2.622074842453003, "learning_rate": 3.978102046169657e-06, "loss": 0.9175, "step": 16024 }, { "epoch": 0.8761318981718776, "grad_norm": 2.3040945529937744, "learning_rate": 3.974642016298024e-06, "loss": 0.8981, "step": 16025 }, { "epoch": 0.8761865709892362, "grad_norm": 2.517483949661255, "learning_rate": 3.971183429510922e-06, "loss": 1.0331, "step": 16026 }, { "epoch": 0.876241243806595, "grad_norm": 3.1079347133636475, "learning_rate": 3.967726285916778e-06, "loss": 1.1015, "step": 16027 }, { "epoch": 0.8762959166239536, "grad_norm": 2.309612989425659, "learning_rate": 3.964270585623997e-06, "loss": 0.9607, "step": 16028 }, { "epoch": 0.8763505894413122, "grad_norm": 2.8899412155151367, "learning_rate": 3.960816328740935e-06, "loss": 1.1629, "step": 16029 }, { "epoch": 0.8764052622586708, "grad_norm": 3.0019452571868896, "learning_rate": 3.957363515375884e-06, "loss": 0.6235, "step": 16030 }, { "epoch": 0.8764599350760294, "grad_norm": 3.7723984718322754, "learning_rate": 3.953912145637101e-06, "loss": 0.9379, "step": 16031 }, { "epoch": 0.876514607893388, "grad_norm": 3.1744167804718018, "learning_rate": 3.9504622196328225e-06, "loss": 1.046, "step": 16032 }, { "epoch": 0.8765692807107466, "grad_norm": 3.4509918689727783, "learning_rate": 3.9470137374712e-06, "loss": 1.0446, "step": 16033 }, { "epoch": 0.8766239535281053, "grad_norm": 2.5530905723571777, "learning_rate": 3.943566699260365e-06, "loss": 1.0242, "step": 16034 }, { "epoch": 0.8766786263454639, "grad_norm": 2.4999067783355713, "learning_rate": 3.940121105108396e-06, "loss": 0.9338, "step": 16035 }, { "epoch": 0.8767332991628225, "grad_norm": 2.5916213989257812, "learning_rate": 3.936676955123325e-06, "loss": 1.0289, "step": 16036 }, { "epoch": 0.8767879719801811, "grad_norm": 2.606659173965454, "learning_rate": 3.933234249413137e-06, "loss": 1.1346, "step": 16037 }, { "epoch": 0.8768426447975397, "grad_norm": 3.0045549869537354, "learning_rate": 3.9297929880857846e-06, "loss": 0.9, "step": 16038 }, { "epoch": 0.8768973176148983, "grad_norm": 2.4664509296417236, "learning_rate": 3.926353171249153e-06, "loss": 0.9528, "step": 16039 }, { "epoch": 0.8769519904322569, "grad_norm": 2.5265231132507324, "learning_rate": 3.92291479901109e-06, "loss": 0.9732, "step": 16040 }, { "epoch": 0.8770066632496156, "grad_norm": 2.3497209548950195, "learning_rate": 3.919477871479427e-06, "loss": 0.9847, "step": 16041 }, { "epoch": 0.8770613360669742, "grad_norm": 2.9350929260253906, "learning_rate": 3.916042388761909e-06, "loss": 0.9789, "step": 16042 }, { "epoch": 0.8771160088843328, "grad_norm": 2.7421679496765137, "learning_rate": 3.912608350966263e-06, "loss": 0.8756, "step": 16043 }, { "epoch": 0.8771706817016914, "grad_norm": 3.0456318855285645, "learning_rate": 3.9091757582001456e-06, "loss": 0.9168, "step": 16044 }, { "epoch": 0.87722535451905, "grad_norm": 2.3833489418029785, "learning_rate": 3.905744610571188e-06, "loss": 0.9177, "step": 16045 }, { "epoch": 0.8772800273364086, "grad_norm": 2.5657355785369873, "learning_rate": 3.902314908186977e-06, "loss": 0.9754, "step": 16046 }, { "epoch": 0.8773347001537672, "grad_norm": 2.6285934448242188, "learning_rate": 3.8988866511550486e-06, "loss": 0.9041, "step": 16047 }, { "epoch": 0.877389372971126, "grad_norm": 3.6453065872192383, "learning_rate": 3.895459839582882e-06, "loss": 1.2634, "step": 16048 }, { "epoch": 0.8774440457884846, "grad_norm": 3.349154472351074, "learning_rate": 3.8920344735779265e-06, "loss": 1.1812, "step": 16049 }, { "epoch": 0.8774987186058432, "grad_norm": 2.455336332321167, "learning_rate": 3.888610553247579e-06, "loss": 0.9225, "step": 16050 }, { "epoch": 0.8775533914232018, "grad_norm": 2.912889242172241, "learning_rate": 3.8851880786992035e-06, "loss": 1.1842, "step": 16051 }, { "epoch": 0.8776080642405604, "grad_norm": 2.778646230697632, "learning_rate": 3.881767050040097e-06, "loss": 0.9555, "step": 16052 }, { "epoch": 0.877662737057919, "grad_norm": 2.3650214672088623, "learning_rate": 3.878347467377535e-06, "loss": 1.1223, "step": 16053 }, { "epoch": 0.8777174098752777, "grad_norm": 2.444530487060547, "learning_rate": 3.874929330818727e-06, "loss": 0.9778, "step": 16054 }, { "epoch": 0.8777720826926363, "grad_norm": 3.352367877960205, "learning_rate": 3.871512640470848e-06, "loss": 1.0894, "step": 16055 }, { "epoch": 0.8778267555099949, "grad_norm": 2.877753496170044, "learning_rate": 3.868097396441023e-06, "loss": 1.1053, "step": 16056 }, { "epoch": 0.8778814283273535, "grad_norm": 2.4743738174438477, "learning_rate": 3.864683598836339e-06, "loss": 1.0544, "step": 16057 }, { "epoch": 0.8779361011447121, "grad_norm": 2.2946858406066895, "learning_rate": 3.861271247763826e-06, "loss": 0.9919, "step": 16058 }, { "epoch": 0.8779907739620707, "grad_norm": 5.6036529541015625, "learning_rate": 3.857860343330482e-06, "loss": 1.1125, "step": 16059 }, { "epoch": 0.8780454467794293, "grad_norm": 3.0338871479034424, "learning_rate": 3.854450885643235e-06, "loss": 0.9398, "step": 16060 }, { "epoch": 0.878100119596788, "grad_norm": 3.0343799591064453, "learning_rate": 3.851042874809013e-06, "loss": 1.1871, "step": 16061 }, { "epoch": 0.8781547924141466, "grad_norm": 2.4850921630859375, "learning_rate": 3.84763631093466e-06, "loss": 1.0702, "step": 16062 }, { "epoch": 0.8782094652315052, "grad_norm": 2.909418821334839, "learning_rate": 3.844231194126979e-06, "loss": 0.8938, "step": 16063 }, { "epoch": 0.8782641380488638, "grad_norm": 2.7993767261505127, "learning_rate": 3.840827524492746e-06, "loss": 0.9898, "step": 16064 }, { "epoch": 0.8783188108662224, "grad_norm": 2.8403658866882324, "learning_rate": 3.83742530213867e-06, "loss": 1.0299, "step": 16065 }, { "epoch": 0.878373483683581, "grad_norm": 2.693500280380249, "learning_rate": 3.834024527171426e-06, "loss": 0.9971, "step": 16066 }, { "epoch": 0.8784281565009396, "grad_norm": 2.537592649459839, "learning_rate": 3.830625199697646e-06, "loss": 0.858, "step": 16067 }, { "epoch": 0.8784828293182984, "grad_norm": 3.2933387756347656, "learning_rate": 3.8272273198239116e-06, "loss": 1.375, "step": 16068 }, { "epoch": 0.878537502135657, "grad_norm": 2.8475935459136963, "learning_rate": 3.823830887656759e-06, "loss": 1.0898, "step": 16069 }, { "epoch": 0.8785921749530156, "grad_norm": 3.3343048095703125, "learning_rate": 3.820435903302671e-06, "loss": 1.308, "step": 16070 }, { "epoch": 0.8786468477703742, "grad_norm": 2.2257771492004395, "learning_rate": 3.817042366868118e-06, "loss": 0.89, "step": 16071 }, { "epoch": 0.8787015205877328, "grad_norm": 3.0089519023895264, "learning_rate": 3.813650278459485e-06, "loss": 1.0813, "step": 16072 }, { "epoch": 0.8787561934050914, "grad_norm": 2.560638666152954, "learning_rate": 3.8102596381831333e-06, "loss": 0.9821, "step": 16073 }, { "epoch": 0.87881086622245, "grad_norm": 3.049264907836914, "learning_rate": 3.806870446145372e-06, "loss": 1.1132, "step": 16074 }, { "epoch": 0.8788655390398087, "grad_norm": 2.7622647285461426, "learning_rate": 3.8034827024524653e-06, "loss": 1.0324, "step": 16075 }, { "epoch": 0.8789202118571673, "grad_norm": 2.1901094913482666, "learning_rate": 3.800096407210629e-06, "loss": 1.1283, "step": 16076 }, { "epoch": 0.8789748846745259, "grad_norm": 2.7746901512145996, "learning_rate": 3.796711560526045e-06, "loss": 1.0441, "step": 16077 }, { "epoch": 0.8790295574918845, "grad_norm": 3.4354188442230225, "learning_rate": 3.793328162504839e-06, "loss": 1.0308, "step": 16078 }, { "epoch": 0.8790842303092431, "grad_norm": 2.3610754013061523, "learning_rate": 3.7899462132530928e-06, "loss": 1.0191, "step": 16079 }, { "epoch": 0.8791389031266017, "grad_norm": 2.8307015895843506, "learning_rate": 3.786565712876833e-06, "loss": 1.0162, "step": 16080 }, { "epoch": 0.8791935759439604, "grad_norm": 2.174329996109009, "learning_rate": 3.7831866614820797e-06, "loss": 1.0658, "step": 16081 }, { "epoch": 0.879248248761319, "grad_norm": 3.4653289318084717, "learning_rate": 3.779809059174766e-06, "loss": 1.1491, "step": 16082 }, { "epoch": 0.8793029215786776, "grad_norm": 2.246940851211548, "learning_rate": 3.7764329060607895e-06, "loss": 1.0304, "step": 16083 }, { "epoch": 0.8793575943960362, "grad_norm": 3.132827043533325, "learning_rate": 3.7730582022460103e-06, "loss": 1.1003, "step": 16084 }, { "epoch": 0.8794122672133948, "grad_norm": 2.4120373725891113, "learning_rate": 3.7696849478362386e-06, "loss": 0.9676, "step": 16085 }, { "epoch": 0.8794669400307534, "grad_norm": 2.6797633171081543, "learning_rate": 3.766313142937239e-06, "loss": 1.0185, "step": 16086 }, { "epoch": 0.879521612848112, "grad_norm": 2.8445358276367188, "learning_rate": 3.7629427876547386e-06, "loss": 0.9543, "step": 16087 }, { "epoch": 0.8795762856654707, "grad_norm": 3.2458746433258057, "learning_rate": 3.759573882094397e-06, "loss": 1.2589, "step": 16088 }, { "epoch": 0.8796309584828294, "grad_norm": 2.3900091648101807, "learning_rate": 3.7562064263618524e-06, "loss": 1.0956, "step": 16089 }, { "epoch": 0.879685631300188, "grad_norm": 2.2261438369750977, "learning_rate": 3.752840420562692e-06, "loss": 1.0455, "step": 16090 }, { "epoch": 0.8797403041175466, "grad_norm": 3.7535581588745117, "learning_rate": 3.7494758648024485e-06, "loss": 1.0944, "step": 16091 }, { "epoch": 0.8797949769349052, "grad_norm": 2.7710840702056885, "learning_rate": 3.7461127591866207e-06, "loss": 1.1766, "step": 16092 }, { "epoch": 0.8798496497522638, "grad_norm": 2.2952191829681396, "learning_rate": 3.742751103820652e-06, "loss": 1.0137, "step": 16093 }, { "epoch": 0.8799043225696224, "grad_norm": 2.5972936153411865, "learning_rate": 3.7393908988099413e-06, "loss": 0.8457, "step": 16094 }, { "epoch": 0.8799589953869811, "grad_norm": 2.819857120513916, "learning_rate": 3.7360321442598435e-06, "loss": 1.0822, "step": 16095 }, { "epoch": 0.8800136682043397, "grad_norm": 2.128213882446289, "learning_rate": 3.7326748402756796e-06, "loss": 0.799, "step": 16096 }, { "epoch": 0.8800683410216983, "grad_norm": 3.117241859436035, "learning_rate": 3.7293189869627043e-06, "loss": 0.7796, "step": 16097 }, { "epoch": 0.8801230138390569, "grad_norm": 3.394308567047119, "learning_rate": 3.725964584426139e-06, "loss": 1.2918, "step": 16098 }, { "epoch": 0.8801776866564155, "grad_norm": 3.2429850101470947, "learning_rate": 3.7226116327711557e-06, "loss": 1.1019, "step": 16099 }, { "epoch": 0.8802323594737741, "grad_norm": 3.3418118953704834, "learning_rate": 3.7192601321028975e-06, "loss": 1.0382, "step": 16100 }, { "epoch": 0.8802870322911327, "grad_norm": 2.718125820159912, "learning_rate": 3.715910082526436e-06, "loss": 1.19, "step": 16101 }, { "epoch": 0.8803417051084914, "grad_norm": 2.126291036605835, "learning_rate": 3.7125614841468093e-06, "loss": 0.8904, "step": 16102 }, { "epoch": 0.88039637792585, "grad_norm": 2.6599018573760986, "learning_rate": 3.709214337069017e-06, "loss": 0.9924, "step": 16103 }, { "epoch": 0.8804510507432086, "grad_norm": 2.8537983894348145, "learning_rate": 3.705868641397997e-06, "loss": 1.1157, "step": 16104 }, { "epoch": 0.8805057235605672, "grad_norm": 2.155566453933716, "learning_rate": 3.702524397238655e-06, "loss": 0.8208, "step": 16105 }, { "epoch": 0.8805603963779258, "grad_norm": 2.3242297172546387, "learning_rate": 3.699181604695845e-06, "loss": 1.0347, "step": 16106 }, { "epoch": 0.8806150691952844, "grad_norm": 2.7531840801239014, "learning_rate": 3.6958402638743784e-06, "loss": 1.0859, "step": 16107 }, { "epoch": 0.8806697420126431, "grad_norm": 2.50091552734375, "learning_rate": 3.692500374879021e-06, "loss": 0.9348, "step": 16108 }, { "epoch": 0.8807244148300017, "grad_norm": 2.336155414581299, "learning_rate": 3.6891619378144837e-06, "loss": 1.1604, "step": 16109 }, { "epoch": 0.8807790876473603, "grad_norm": 2.796049118041992, "learning_rate": 3.6858249527854547e-06, "loss": 1.0239, "step": 16110 }, { "epoch": 0.880833760464719, "grad_norm": 2.617938280105591, "learning_rate": 3.6824894198965566e-06, "loss": 0.9522, "step": 16111 }, { "epoch": 0.8808884332820776, "grad_norm": 2.6061837673187256, "learning_rate": 3.6791553392523715e-06, "loss": 0.9697, "step": 16112 }, { "epoch": 0.8809431060994362, "grad_norm": 2.4837300777435303, "learning_rate": 3.6758227109574327e-06, "loss": 0.929, "step": 16113 }, { "epoch": 0.8809977789167948, "grad_norm": 3.018934965133667, "learning_rate": 3.6724915351162403e-06, "loss": 1.2248, "step": 16114 }, { "epoch": 0.8810524517341535, "grad_norm": 2.9271881580352783, "learning_rate": 3.669161811833227e-06, "loss": 1.0159, "step": 16115 }, { "epoch": 0.8811071245515121, "grad_norm": 2.9888198375701904, "learning_rate": 3.665833541212804e-06, "loss": 1.109, "step": 16116 }, { "epoch": 0.8811617973688707, "grad_norm": 2.1785471439361572, "learning_rate": 3.662506723359327e-06, "loss": 0.8573, "step": 16117 }, { "epoch": 0.8812164701862293, "grad_norm": 2.8345117568969727, "learning_rate": 3.6591813583771007e-06, "loss": 1.0274, "step": 16118 }, { "epoch": 0.8812711430035879, "grad_norm": 2.3023464679718018, "learning_rate": 3.655857446370381e-06, "loss": 1.0456, "step": 16119 }, { "epoch": 0.8813258158209465, "grad_norm": 1.794150710105896, "learning_rate": 3.652534987443401e-06, "loss": 0.9193, "step": 16120 }, { "epoch": 0.8813804886383051, "grad_norm": 2.518054723739624, "learning_rate": 3.6492139817003336e-06, "loss": 0.9625, "step": 16121 }, { "epoch": 0.8814351614556638, "grad_norm": 2.6762914657592773, "learning_rate": 3.6458944292452945e-06, "loss": 1.1679, "step": 16122 }, { "epoch": 0.8814898342730224, "grad_norm": 5.510868549346924, "learning_rate": 3.642576330182379e-06, "loss": 0.9294, "step": 16123 }, { "epoch": 0.881544507090381, "grad_norm": 2.3780744075775146, "learning_rate": 3.639259684615609e-06, "loss": 0.8701, "step": 16124 }, { "epoch": 0.8815991799077396, "grad_norm": 3.5149972438812256, "learning_rate": 3.635944492648985e-06, "loss": 1.1875, "step": 16125 }, { "epoch": 0.8816538527250982, "grad_norm": 2.8641278743743896, "learning_rate": 3.6326307543864458e-06, "loss": 1.1273, "step": 16126 }, { "epoch": 0.8817085255424568, "grad_norm": 2.670902967453003, "learning_rate": 3.6293184699318918e-06, "loss": 1.01, "step": 16127 }, { "epoch": 0.8817631983598154, "grad_norm": 2.792980432510376, "learning_rate": 3.6260076393891786e-06, "loss": 0.8382, "step": 16128 }, { "epoch": 0.8818178711771741, "grad_norm": 2.1797657012939453, "learning_rate": 3.622698262862112e-06, "loss": 0.8459, "step": 16129 }, { "epoch": 0.8818725439945327, "grad_norm": 4.087050437927246, "learning_rate": 3.619390340454459e-06, "loss": 1.1211, "step": 16130 }, { "epoch": 0.8819272168118913, "grad_norm": 2.61350417137146, "learning_rate": 3.616083872269932e-06, "loss": 1.0226, "step": 16131 }, { "epoch": 0.88198188962925, "grad_norm": 2.787864923477173, "learning_rate": 3.612778858412208e-06, "loss": 1.2512, "step": 16132 }, { "epoch": 0.8820365624466086, "grad_norm": 2.7455556392669678, "learning_rate": 3.6094752989849103e-06, "loss": 0.9406, "step": 16133 }, { "epoch": 0.8820912352639672, "grad_norm": 2.353980302810669, "learning_rate": 3.606173194091622e-06, "loss": 0.9095, "step": 16134 }, { "epoch": 0.8821459080813259, "grad_norm": 2.320983648300171, "learning_rate": 3.602872543835867e-06, "loss": 0.9089, "step": 16135 }, { "epoch": 0.8822005808986845, "grad_norm": 2.1344830989837646, "learning_rate": 3.5995733483211446e-06, "loss": 0.969, "step": 16136 }, { "epoch": 0.8822552537160431, "grad_norm": 3.487886905670166, "learning_rate": 3.5962756076508897e-06, "loss": 1.0659, "step": 16137 }, { "epoch": 0.8823099265334017, "grad_norm": 2.4952504634857178, "learning_rate": 3.5929793219285137e-06, "loss": 1.1289, "step": 16138 }, { "epoch": 0.8823645993507603, "grad_norm": 2.26290225982666, "learning_rate": 3.5896844912573446e-06, "loss": 0.8778, "step": 16139 }, { "epoch": 0.8824192721681189, "grad_norm": 2.6838531494140625, "learning_rate": 3.586391115740717e-06, "loss": 0.8055, "step": 16140 }, { "epoch": 0.8824739449854775, "grad_norm": 3.3174989223480225, "learning_rate": 3.583099195481876e-06, "loss": 0.8928, "step": 16141 }, { "epoch": 0.8825286178028362, "grad_norm": 2.0345005989074707, "learning_rate": 3.5798087305840387e-06, "loss": 0.788, "step": 16142 }, { "epoch": 0.8825832906201948, "grad_norm": 3.0783181190490723, "learning_rate": 3.5765197211503787e-06, "loss": 1.0705, "step": 16143 }, { "epoch": 0.8826379634375534, "grad_norm": 3.1555769443511963, "learning_rate": 3.5732321672840185e-06, "loss": 1.0795, "step": 16144 }, { "epoch": 0.882692636254912, "grad_norm": 3.026503562927246, "learning_rate": 3.5699460690880373e-06, "loss": 1.0469, "step": 16145 }, { "epoch": 0.8827473090722706, "grad_norm": 2.3988687992095947, "learning_rate": 3.5666614266654576e-06, "loss": 1.1212, "step": 16146 }, { "epoch": 0.8828019818896292, "grad_norm": 2.8529021739959717, "learning_rate": 3.5633782401192808e-06, "loss": 1.0952, "step": 16147 }, { "epoch": 0.8828566547069878, "grad_norm": 2.2073123455047607, "learning_rate": 3.5600965095524408e-06, "loss": 1.0057, "step": 16148 }, { "epoch": 0.8829113275243465, "grad_norm": 2.3796935081481934, "learning_rate": 3.556816235067828e-06, "loss": 0.9082, "step": 16149 }, { "epoch": 0.8829660003417051, "grad_norm": 2.7541592121124268, "learning_rate": 3.5535374167683043e-06, "loss": 1.0642, "step": 16150 }, { "epoch": 0.8830206731590637, "grad_norm": 2.4513869285583496, "learning_rate": 3.5502600547566713e-06, "loss": 1.0224, "step": 16151 }, { "epoch": 0.8830753459764223, "grad_norm": 2.943546772003174, "learning_rate": 3.5469841491356905e-06, "loss": 1.1694, "step": 16152 }, { "epoch": 0.883130018793781, "grad_norm": 3.403745651245117, "learning_rate": 3.5437097000080634e-06, "loss": 1.1504, "step": 16153 }, { "epoch": 0.8831846916111395, "grad_norm": 2.3741567134857178, "learning_rate": 3.540436707476463e-06, "loss": 1.046, "step": 16154 }, { "epoch": 0.8832393644284982, "grad_norm": 2.3662357330322266, "learning_rate": 3.5371651716435195e-06, "loss": 1.1323, "step": 16155 }, { "epoch": 0.8832940372458569, "grad_norm": 1.9706270694732666, "learning_rate": 3.5338950926117943e-06, "loss": 0.9045, "step": 16156 }, { "epoch": 0.8833487100632155, "grad_norm": 2.7143585681915283, "learning_rate": 3.530626470483833e-06, "loss": 1.0441, "step": 16157 }, { "epoch": 0.8834033828805741, "grad_norm": 2.0611414909362793, "learning_rate": 3.5273593053621044e-06, "loss": 0.8206, "step": 16158 }, { "epoch": 0.8834580556979327, "grad_norm": 2.7903242111206055, "learning_rate": 3.524093597349065e-06, "loss": 0.9998, "step": 16159 }, { "epoch": 0.8835127285152913, "grad_norm": 2.7053945064544678, "learning_rate": 3.520829346547094e-06, "loss": 0.9379, "step": 16160 }, { "epoch": 0.8835674013326499, "grad_norm": 3.1525509357452393, "learning_rate": 3.5175665530585432e-06, "loss": 0.866, "step": 16161 }, { "epoch": 0.8836220741500086, "grad_norm": 2.8174386024475098, "learning_rate": 3.514305216985708e-06, "loss": 1.0715, "step": 16162 }, { "epoch": 0.8836767469673672, "grad_norm": 2.4242420196533203, "learning_rate": 3.5110453384308626e-06, "loss": 1.0363, "step": 16163 }, { "epoch": 0.8837314197847258, "grad_norm": 2.991359233856201, "learning_rate": 3.507786917496203e-06, "loss": 1.1344, "step": 16164 }, { "epoch": 0.8837860926020844, "grad_norm": 4.3193745613098145, "learning_rate": 3.5045299542839027e-06, "loss": 1.1593, "step": 16165 }, { "epoch": 0.883840765419443, "grad_norm": 2.2591378688812256, "learning_rate": 3.5012744488960803e-06, "loss": 1.1701, "step": 16166 }, { "epoch": 0.8838954382368016, "grad_norm": 2.468541383743286, "learning_rate": 3.4980204014347985e-06, "loss": 0.9659, "step": 16167 }, { "epoch": 0.8839501110541602, "grad_norm": 2.6758973598480225, "learning_rate": 3.4947678120020978e-06, "loss": 1.2122, "step": 16168 }, { "epoch": 0.8840047838715189, "grad_norm": 2.3506102561950684, "learning_rate": 3.4915166806999523e-06, "loss": 1.0898, "step": 16169 }, { "epoch": 0.8840594566888775, "grad_norm": 2.8996634483337402, "learning_rate": 3.488267007630297e-06, "loss": 1.2164, "step": 16170 }, { "epoch": 0.8841141295062361, "grad_norm": 2.7973084449768066, "learning_rate": 3.485018792895034e-06, "loss": 1.1081, "step": 16171 }, { "epoch": 0.8841688023235947, "grad_norm": 2.216047525405884, "learning_rate": 3.4817720365959928e-06, "loss": 1.053, "step": 16172 }, { "epoch": 0.8842234751409533, "grad_norm": 2.785046100616455, "learning_rate": 3.478526738834986e-06, "loss": 1.1111, "step": 16173 }, { "epoch": 0.8842781479583119, "grad_norm": 2.2747910022735596, "learning_rate": 3.475282899713761e-06, "loss": 0.8579, "step": 16174 }, { "epoch": 0.8843328207756705, "grad_norm": 2.6854615211486816, "learning_rate": 3.472040519334013e-06, "loss": 0.9819, "step": 16175 }, { "epoch": 0.8843874935930293, "grad_norm": 2.405033588409424, "learning_rate": 3.4687995977974284e-06, "loss": 1.075, "step": 16176 }, { "epoch": 0.8844421664103879, "grad_norm": 2.807321548461914, "learning_rate": 3.4655601352056145e-06, "loss": 0.9103, "step": 16177 }, { "epoch": 0.8844968392277465, "grad_norm": 2.6552934646606445, "learning_rate": 3.462322131660134e-06, "loss": 1.1747, "step": 16178 }, { "epoch": 0.8845515120451051, "grad_norm": 2.923560380935669, "learning_rate": 3.4590855872625226e-06, "loss": 1.1204, "step": 16179 }, { "epoch": 0.8846061848624637, "grad_norm": 3.091911554336548, "learning_rate": 3.4558505021142495e-06, "loss": 1.2105, "step": 16180 }, { "epoch": 0.8846608576798223, "grad_norm": 3.7085981369018555, "learning_rate": 3.4526168763167556e-06, "loss": 0.9838, "step": 16181 }, { "epoch": 0.8847155304971809, "grad_norm": 2.729447841644287, "learning_rate": 3.4493847099714204e-06, "loss": 0.9811, "step": 16182 }, { "epoch": 0.8847702033145396, "grad_norm": 2.3864634037017822, "learning_rate": 3.4461540031795916e-06, "loss": 1.0147, "step": 16183 }, { "epoch": 0.8848248761318982, "grad_norm": 3.1318695545196533, "learning_rate": 3.442924756042565e-06, "loss": 0.8904, "step": 16184 }, { "epoch": 0.8848795489492568, "grad_norm": 2.6832709312438965, "learning_rate": 3.4396969686615877e-06, "loss": 1.1349, "step": 16185 }, { "epoch": 0.8849342217666154, "grad_norm": 2.6218466758728027, "learning_rate": 3.436470641137868e-06, "loss": 1.0526, "step": 16186 }, { "epoch": 0.884988894583974, "grad_norm": 2.621715784072876, "learning_rate": 3.4332457735725633e-06, "loss": 1.1087, "step": 16187 }, { "epoch": 0.8850435674013326, "grad_norm": 2.822575807571411, "learning_rate": 3.4300223660667765e-06, "loss": 0.885, "step": 16188 }, { "epoch": 0.8850982402186913, "grad_norm": 2.542202949523926, "learning_rate": 3.4268004187215874e-06, "loss": 0.9849, "step": 16189 }, { "epoch": 0.8851529130360499, "grad_norm": 2.2736732959747314, "learning_rate": 3.4235799316380156e-06, "loss": 0.8294, "step": 16190 }, { "epoch": 0.8852075858534085, "grad_norm": 2.128038167953491, "learning_rate": 3.420360904917036e-06, "loss": 0.962, "step": 16191 }, { "epoch": 0.8852622586707671, "grad_norm": 2.231527328491211, "learning_rate": 3.4171433386595788e-06, "loss": 0.893, "step": 16192 }, { "epoch": 0.8853169314881257, "grad_norm": 3.4789516925811768, "learning_rate": 3.413927232966524e-06, "loss": 1.0997, "step": 16193 }, { "epoch": 0.8853716043054843, "grad_norm": 3.0919477939605713, "learning_rate": 3.4107125879387135e-06, "loss": 1.1359, "step": 16194 }, { "epoch": 0.8854262771228429, "grad_norm": 3.0614123344421387, "learning_rate": 3.407499403676939e-06, "loss": 0.9797, "step": 16195 }, { "epoch": 0.8854809499402017, "grad_norm": 2.569272041320801, "learning_rate": 3.4042876802819425e-06, "loss": 0.9354, "step": 16196 }, { "epoch": 0.8855356227575603, "grad_norm": 2.847085952758789, "learning_rate": 3.401077417854426e-06, "loss": 1.0506, "step": 16197 }, { "epoch": 0.8855902955749189, "grad_norm": 3.0486433506011963, "learning_rate": 3.3978686164950478e-06, "loss": 1.1141, "step": 16198 }, { "epoch": 0.8856449683922775, "grad_norm": 2.624267101287842, "learning_rate": 3.394661276304423e-06, "loss": 1.0719, "step": 16199 }, { "epoch": 0.8856996412096361, "grad_norm": 2.4545371532440186, "learning_rate": 3.391455397383103e-06, "loss": 1.0229, "step": 16200 }, { "epoch": 0.8857543140269947, "grad_norm": 3.069058418273926, "learning_rate": 3.3882509798316144e-06, "loss": 1.1466, "step": 16201 }, { "epoch": 0.8858089868443533, "grad_norm": 2.331435441970825, "learning_rate": 3.38504802375042e-06, "loss": 1.0269, "step": 16202 }, { "epoch": 0.885863659661712, "grad_norm": 2.424710750579834, "learning_rate": 3.3818465292399514e-06, "loss": 1.0933, "step": 16203 }, { "epoch": 0.8859183324790706, "grad_norm": 2.919308662414551, "learning_rate": 3.3786464964005892e-06, "loss": 1.0983, "step": 16204 }, { "epoch": 0.8859730052964292, "grad_norm": 2.796186923980713, "learning_rate": 3.3754479253326697e-06, "loss": 0.9212, "step": 16205 }, { "epoch": 0.8860276781137878, "grad_norm": 2.337244987487793, "learning_rate": 3.372250816136474e-06, "loss": 0.8905, "step": 16206 }, { "epoch": 0.8860823509311464, "grad_norm": 2.232783555984497, "learning_rate": 3.3690551689122385e-06, "loss": 0.962, "step": 16207 }, { "epoch": 0.886137023748505, "grad_norm": 2.4596245288848877, "learning_rate": 3.3658609837601827e-06, "loss": 1.1155, "step": 16208 }, { "epoch": 0.8861916965658636, "grad_norm": 2.697265625, "learning_rate": 3.362668260780444e-06, "loss": 1.1351, "step": 16209 }, { "epoch": 0.8862463693832223, "grad_norm": 2.6236259937286377, "learning_rate": 3.3594770000731245e-06, "loss": 0.8999, "step": 16210 }, { "epoch": 0.8863010422005809, "grad_norm": 2.4244134426116943, "learning_rate": 3.3562872017382896e-06, "loss": 0.8663, "step": 16211 }, { "epoch": 0.8863557150179395, "grad_norm": 2.0452187061309814, "learning_rate": 3.353098865875948e-06, "loss": 0.8929, "step": 16212 }, { "epoch": 0.8864103878352981, "grad_norm": 2.555765390396118, "learning_rate": 3.349911992586069e-06, "loss": 1.107, "step": 16213 }, { "epoch": 0.8864650606526567, "grad_norm": 2.5004944801330566, "learning_rate": 3.3467265819685735e-06, "loss": 0.9474, "step": 16214 }, { "epoch": 0.8865197334700153, "grad_norm": 2.1204304695129395, "learning_rate": 3.343542634123342e-06, "loss": 1.0479, "step": 16215 }, { "epoch": 0.886574406287374, "grad_norm": 2.5122432708740234, "learning_rate": 3.340360149150196e-06, "loss": 0.9737, "step": 16216 }, { "epoch": 0.8866290791047327, "grad_norm": 2.80975341796875, "learning_rate": 3.3371791271489204e-06, "loss": 1.1904, "step": 16217 }, { "epoch": 0.8866837519220913, "grad_norm": 2.0757405757904053, "learning_rate": 3.3339995682192594e-06, "loss": 0.88, "step": 16218 }, { "epoch": 0.8867384247394499, "grad_norm": 2.8503808975219727, "learning_rate": 3.3308214724609044e-06, "loss": 1.0466, "step": 16219 }, { "epoch": 0.8867930975568085, "grad_norm": 2.2636473178863525, "learning_rate": 3.3276448399735037e-06, "loss": 0.9207, "step": 16220 }, { "epoch": 0.8868477703741671, "grad_norm": 2.701188325881958, "learning_rate": 3.32446967085665e-06, "loss": 0.9366, "step": 16221 }, { "epoch": 0.8869024431915257, "grad_norm": 2.919442653656006, "learning_rate": 3.3212959652099028e-06, "loss": 1.0256, "step": 16222 }, { "epoch": 0.8869571160088844, "grad_norm": 2.4394493103027344, "learning_rate": 3.318123723132771e-06, "loss": 0.9916, "step": 16223 }, { "epoch": 0.887011788826243, "grad_norm": 2.482816457748413, "learning_rate": 3.3149529447247197e-06, "loss": 0.9767, "step": 16224 }, { "epoch": 0.8870664616436016, "grad_norm": 2.684560537338257, "learning_rate": 3.311783630085158e-06, "loss": 1.0884, "step": 16225 }, { "epoch": 0.8871211344609602, "grad_norm": 2.8354268074035645, "learning_rate": 3.308615779313462e-06, "loss": 1.1918, "step": 16226 }, { "epoch": 0.8871758072783188, "grad_norm": 3.296729564666748, "learning_rate": 3.3054493925089526e-06, "loss": 1.0478, "step": 16227 }, { "epoch": 0.8872304800956774, "grad_norm": 2.439347505569458, "learning_rate": 3.3022844697709165e-06, "loss": 1.0784, "step": 16228 }, { "epoch": 0.887285152913036, "grad_norm": 2.681626319885254, "learning_rate": 3.299121011198586e-06, "loss": 1.0696, "step": 16229 }, { "epoch": 0.8873398257303947, "grad_norm": 2.6711087226867676, "learning_rate": 3.2959590168911425e-06, "loss": 1.0939, "step": 16230 }, { "epoch": 0.8873944985477533, "grad_norm": 2.772930145263672, "learning_rate": 3.2927984869477344e-06, "loss": 0.8714, "step": 16231 }, { "epoch": 0.8874491713651119, "grad_norm": 2.3943796157836914, "learning_rate": 3.2896394214674554e-06, "loss": 0.8937, "step": 16232 }, { "epoch": 0.8875038441824705, "grad_norm": 2.8954615592956543, "learning_rate": 3.286481820549353e-06, "loss": 1.0985, "step": 16233 }, { "epoch": 0.8875585169998291, "grad_norm": 2.31675124168396, "learning_rate": 3.283325684292432e-06, "loss": 1.0515, "step": 16234 }, { "epoch": 0.8876131898171877, "grad_norm": 2.844618797302246, "learning_rate": 3.2801710127956463e-06, "loss": 0.9574, "step": 16235 }, { "epoch": 0.8876678626345463, "grad_norm": 3.010605573654175, "learning_rate": 3.277017806157917e-06, "loss": 0.9227, "step": 16236 }, { "epoch": 0.887722535451905, "grad_norm": 2.5026071071624756, "learning_rate": 3.2738660644780928e-06, "loss": 0.8202, "step": 16237 }, { "epoch": 0.8877772082692637, "grad_norm": 2.7078285217285156, "learning_rate": 3.2707157878550167e-06, "loss": 0.9408, "step": 16238 }, { "epoch": 0.8878318810866223, "grad_norm": 2.635838031768799, "learning_rate": 3.267566976387454e-06, "loss": 1.2281, "step": 16239 }, { "epoch": 0.8878865539039809, "grad_norm": 2.886363983154297, "learning_rate": 3.2644196301741257e-06, "loss": 1.2181, "step": 16240 }, { "epoch": 0.8879412267213395, "grad_norm": 2.629833221435547, "learning_rate": 3.2612737493137202e-06, "loss": 1.1431, "step": 16241 }, { "epoch": 0.8879958995386981, "grad_norm": 2.619680643081665, "learning_rate": 3.2581293339048745e-06, "loss": 1.0826, "step": 16242 }, { "epoch": 0.8880505723560568, "grad_norm": 2.5766613483428955, "learning_rate": 3.2549863840461768e-06, "loss": 0.8715, "step": 16243 }, { "epoch": 0.8881052451734154, "grad_norm": 3.0102033615112305, "learning_rate": 3.251844899836176e-06, "loss": 0.8065, "step": 16244 }, { "epoch": 0.888159917990774, "grad_norm": 3.621873617172241, "learning_rate": 3.24870488137336e-06, "loss": 1.0873, "step": 16245 }, { "epoch": 0.8882145908081326, "grad_norm": 2.43277645111084, "learning_rate": 3.2455663287561833e-06, "loss": 0.9967, "step": 16246 }, { "epoch": 0.8882692636254912, "grad_norm": 2.3661160469055176, "learning_rate": 3.242429242083067e-06, "loss": 1.0187, "step": 16247 }, { "epoch": 0.8883239364428498, "grad_norm": 2.20908522605896, "learning_rate": 3.2392936214523606e-06, "loss": 0.9906, "step": 16248 }, { "epoch": 0.8883786092602084, "grad_norm": 3.287924289703369, "learning_rate": 3.2361594669623795e-06, "loss": 1.0297, "step": 16249 }, { "epoch": 0.8884332820775671, "grad_norm": 2.514591932296753, "learning_rate": 3.23302677871139e-06, "loss": 0.9993, "step": 16250 }, { "epoch": 0.8884879548949257, "grad_norm": 3.224719285964966, "learning_rate": 3.229895556797624e-06, "loss": 1.2543, "step": 16251 }, { "epoch": 0.8885426277122843, "grad_norm": 2.324812412261963, "learning_rate": 3.2267658013192426e-06, "loss": 1.0334, "step": 16252 }, { "epoch": 0.8885973005296429, "grad_norm": 2.5381762981414795, "learning_rate": 3.2236375123743946e-06, "loss": 1.0142, "step": 16253 }, { "epoch": 0.8886519733470015, "grad_norm": 3.9349770545959473, "learning_rate": 3.2205106900611515e-06, "loss": 1.0674, "step": 16254 }, { "epoch": 0.8887066461643601, "grad_norm": 2.513453483581543, "learning_rate": 3.2173853344775574e-06, "loss": 1.1135, "step": 16255 }, { "epoch": 0.8887613189817187, "grad_norm": 2.71101713180542, "learning_rate": 3.2142614457215947e-06, "loss": 1.0465, "step": 16256 }, { "epoch": 0.8888159917990774, "grad_norm": 2.678297996520996, "learning_rate": 3.2111390238912297e-06, "loss": 1.1358, "step": 16257 }, { "epoch": 0.888870664616436, "grad_norm": 2.7085094451904297, "learning_rate": 3.2080180690843508e-06, "loss": 0.8606, "step": 16258 }, { "epoch": 0.8889253374337946, "grad_norm": 2.3752477169036865, "learning_rate": 3.204898581398813e-06, "loss": 0.9807, "step": 16259 }, { "epoch": 0.8889800102511533, "grad_norm": 2.8448891639709473, "learning_rate": 3.2017805609324327e-06, "loss": 0.9214, "step": 16260 }, { "epoch": 0.8890346830685119, "grad_norm": 2.5243308544158936, "learning_rate": 3.198664007782964e-06, "loss": 0.9616, "step": 16261 }, { "epoch": 0.8890893558858705, "grad_norm": 3.7481555938720703, "learning_rate": 3.195548922048125e-06, "loss": 1.1855, "step": 16262 }, { "epoch": 0.8891440287032291, "grad_norm": 3.267442464828491, "learning_rate": 3.1924353038255916e-06, "loss": 0.942, "step": 16263 }, { "epoch": 0.8891987015205878, "grad_norm": 3.7353315353393555, "learning_rate": 3.1893231532129866e-06, "loss": 1.286, "step": 16264 }, { "epoch": 0.8892533743379464, "grad_norm": 2.745544910430908, "learning_rate": 3.186212470307881e-06, "loss": 1.061, "step": 16265 }, { "epoch": 0.889308047155305, "grad_norm": 2.2286148071289062, "learning_rate": 3.1831032552078086e-06, "loss": 0.8951, "step": 16266 }, { "epoch": 0.8893627199726636, "grad_norm": 3.189195394515991, "learning_rate": 3.179995508010275e-06, "loss": 1.1085, "step": 16267 }, { "epoch": 0.8894173927900222, "grad_norm": 2.7502059936523438, "learning_rate": 3.1768892288127018e-06, "loss": 0.9699, "step": 16268 }, { "epoch": 0.8894720656073808, "grad_norm": 2.395946741104126, "learning_rate": 3.1737844177124887e-06, "loss": 0.8953, "step": 16269 }, { "epoch": 0.8895267384247395, "grad_norm": 2.4346747398376465, "learning_rate": 3.170681074806986e-06, "loss": 1.2016, "step": 16270 }, { "epoch": 0.8895814112420981, "grad_norm": 2.648038387298584, "learning_rate": 3.1675792001934936e-06, "loss": 1.2012, "step": 16271 }, { "epoch": 0.8896360840594567, "grad_norm": 2.819842576980591, "learning_rate": 3.164478793969272e-06, "loss": 1.1667, "step": 16272 }, { "epoch": 0.8896907568768153, "grad_norm": 2.5950238704681396, "learning_rate": 3.1613798562315277e-06, "loss": 1.1216, "step": 16273 }, { "epoch": 0.8897454296941739, "grad_norm": 2.493309259414673, "learning_rate": 3.1582823870774214e-06, "loss": 0.917, "step": 16274 }, { "epoch": 0.8898001025115325, "grad_norm": 2.488970994949341, "learning_rate": 3.155186386604081e-06, "loss": 0.9915, "step": 16275 }, { "epoch": 0.8898547753288911, "grad_norm": 3.3631319999694824, "learning_rate": 3.1520918549085675e-06, "loss": 1.1213, "step": 16276 }, { "epoch": 0.8899094481462498, "grad_norm": 2.095705270767212, "learning_rate": 3.148998792087926e-06, "loss": 0.9939, "step": 16277 }, { "epoch": 0.8899641209636084, "grad_norm": 2.313365936279297, "learning_rate": 3.1459071982391177e-06, "loss": 1.0901, "step": 16278 }, { "epoch": 0.890018793780967, "grad_norm": 2.680612325668335, "learning_rate": 3.1428170734590866e-06, "loss": 1.0485, "step": 16279 }, { "epoch": 0.8900734665983256, "grad_norm": 3.044780731201172, "learning_rate": 3.139728417844723e-06, "loss": 1.0919, "step": 16280 }, { "epoch": 0.8901281394156842, "grad_norm": 3.9959006309509277, "learning_rate": 3.1366412314928596e-06, "loss": 1.1011, "step": 16281 }, { "epoch": 0.8901828122330429, "grad_norm": 2.2116239070892334, "learning_rate": 3.133555514500297e-06, "loss": 1.1418, "step": 16282 }, { "epoch": 0.8902374850504015, "grad_norm": 2.9693171977996826, "learning_rate": 3.130471266963786e-06, "loss": 1.0194, "step": 16283 }, { "epoch": 0.8902921578677602, "grad_norm": 2.0566515922546387, "learning_rate": 3.1273884889800265e-06, "loss": 0.9401, "step": 16284 }, { "epoch": 0.8903468306851188, "grad_norm": 3.1267306804656982, "learning_rate": 3.1243071806456857e-06, "loss": 1.2068, "step": 16285 }, { "epoch": 0.8904015035024774, "grad_norm": 2.9834611415863037, "learning_rate": 3.121227342057359e-06, "loss": 0.9229, "step": 16286 }, { "epoch": 0.890456176319836, "grad_norm": 3.565890073776245, "learning_rate": 3.1181489733116297e-06, "loss": 1.1174, "step": 16287 }, { "epoch": 0.8905108491371946, "grad_norm": 2.6302013397216797, "learning_rate": 3.115072074505004e-06, "loss": 1.0418, "step": 16288 }, { "epoch": 0.8905655219545532, "grad_norm": 2.191030263900757, "learning_rate": 3.1119966457339668e-06, "loss": 0.8988, "step": 16289 }, { "epoch": 0.8906201947719118, "grad_norm": 2.528151512145996, "learning_rate": 3.1089226870949395e-06, "loss": 1.0519, "step": 16290 }, { "epoch": 0.8906748675892705, "grad_norm": 3.1782753467559814, "learning_rate": 3.105850198684307e-06, "loss": 1.12, "step": 16291 }, { "epoch": 0.8907295404066291, "grad_norm": 2.5784265995025635, "learning_rate": 3.1027791805983975e-06, "loss": 0.8652, "step": 16292 }, { "epoch": 0.8907842132239877, "grad_norm": 3.2492988109588623, "learning_rate": 3.0997096329335006e-06, "loss": 1.0467, "step": 16293 }, { "epoch": 0.8908388860413463, "grad_norm": 2.6111555099487305, "learning_rate": 3.0966415557858676e-06, "loss": 1.0988, "step": 16294 }, { "epoch": 0.8908935588587049, "grad_norm": 2.6359262466430664, "learning_rate": 3.0935749492516874e-06, "loss": 1.049, "step": 16295 }, { "epoch": 0.8909482316760635, "grad_norm": 2.66693115234375, "learning_rate": 3.090509813427106e-06, "loss": 1.173, "step": 16296 }, { "epoch": 0.8910029044934222, "grad_norm": 2.6299662590026855, "learning_rate": 3.087446148408246e-06, "loss": 0.9406, "step": 16297 }, { "epoch": 0.8910575773107808, "grad_norm": 3.494825601577759, "learning_rate": 3.0843839542911533e-06, "loss": 0.9214, "step": 16298 }, { "epoch": 0.8911122501281394, "grad_norm": 2.0608346462249756, "learning_rate": 3.08132323117184e-06, "loss": 0.9851, "step": 16299 }, { "epoch": 0.891166922945498, "grad_norm": 2.695394515991211, "learning_rate": 3.0782639791462785e-06, "loss": 0.9619, "step": 16300 }, { "epoch": 0.8912215957628566, "grad_norm": 2.532839059829712, "learning_rate": 3.0752061983103817e-06, "loss": 1.0313, "step": 16301 }, { "epoch": 0.8912762685802152, "grad_norm": 2.831317663192749, "learning_rate": 3.0721498887600286e-06, "loss": 1.0477, "step": 16302 }, { "epoch": 0.8913309413975739, "grad_norm": 3.891430139541626, "learning_rate": 3.0690950505910477e-06, "loss": 1.1402, "step": 16303 }, { "epoch": 0.8913856142149326, "grad_norm": 2.6668901443481445, "learning_rate": 3.0660416838992124e-06, "loss": 1.0023, "step": 16304 }, { "epoch": 0.8914402870322912, "grad_norm": 2.028740167617798, "learning_rate": 3.0629897887802626e-06, "loss": 0.8138, "step": 16305 }, { "epoch": 0.8914949598496498, "grad_norm": 2.055208206176758, "learning_rate": 3.0599393653299004e-06, "loss": 0.8948, "step": 16306 }, { "epoch": 0.8915496326670084, "grad_norm": 2.4620795249938965, "learning_rate": 3.0568904136437537e-06, "loss": 1.0573, "step": 16307 }, { "epoch": 0.891604305484367, "grad_norm": 2.3513565063476562, "learning_rate": 3.0538429338174246e-06, "loss": 0.7476, "step": 16308 }, { "epoch": 0.8916589783017256, "grad_norm": 2.696180582046509, "learning_rate": 3.0507969259464643e-06, "loss": 1.0912, "step": 16309 }, { "epoch": 0.8917136511190842, "grad_norm": 2.7907345294952393, "learning_rate": 3.0477523901263737e-06, "loss": 0.9868, "step": 16310 }, { "epoch": 0.8917683239364429, "grad_norm": 2.247088670730591, "learning_rate": 3.044709326452622e-06, "loss": 0.8436, "step": 16311 }, { "epoch": 0.8918229967538015, "grad_norm": 2.2697532176971436, "learning_rate": 3.0416677350206147e-06, "loss": 0.8979, "step": 16312 }, { "epoch": 0.8918776695711601, "grad_norm": 3.8980088233947754, "learning_rate": 3.0386276159257154e-06, "loss": 1.0053, "step": 16313 }, { "epoch": 0.8919323423885187, "grad_norm": 4.838906288146973, "learning_rate": 3.0355889692632476e-06, "loss": 0.8341, "step": 16314 }, { "epoch": 0.8919870152058773, "grad_norm": 2.9924392700195312, "learning_rate": 3.03255179512848e-06, "loss": 1.1754, "step": 16315 }, { "epoch": 0.8920416880232359, "grad_norm": 2.8249950408935547, "learning_rate": 3.0295160936166466e-06, "loss": 0.8647, "step": 16316 }, { "epoch": 0.8920963608405945, "grad_norm": 2.1171205043792725, "learning_rate": 3.0264818648229387e-06, "loss": 1.0352, "step": 16317 }, { "epoch": 0.8921510336579532, "grad_norm": 2.9287142753601074, "learning_rate": 3.023449108842474e-06, "loss": 1.0944, "step": 16318 }, { "epoch": 0.8922057064753118, "grad_norm": 2.7982378005981445, "learning_rate": 3.02041782577035e-06, "loss": 1.0868, "step": 16319 }, { "epoch": 0.8922603792926704, "grad_norm": 2.3481369018554688, "learning_rate": 3.017388015701611e-06, "loss": 1.0425, "step": 16320 }, { "epoch": 0.892315052110029, "grad_norm": 3.885185956954956, "learning_rate": 3.0143596787312545e-06, "loss": 0.9852, "step": 16321 }, { "epoch": 0.8923697249273876, "grad_norm": 2.4429070949554443, "learning_rate": 3.0113328149542263e-06, "loss": 1.0119, "step": 16322 }, { "epoch": 0.8924243977447462, "grad_norm": 2.662750244140625, "learning_rate": 3.0083074244654343e-06, "loss": 1.0922, "step": 16323 }, { "epoch": 0.8924790705621048, "grad_norm": 2.9216198921203613, "learning_rate": 3.0052835073597407e-06, "loss": 0.9374, "step": 16324 }, { "epoch": 0.8925337433794636, "grad_norm": 2.5660643577575684, "learning_rate": 3.0022610637319427e-06, "loss": 1.0484, "step": 16325 }, { "epoch": 0.8925884161968222, "grad_norm": 2.498345136642456, "learning_rate": 2.999240093676825e-06, "loss": 1.0627, "step": 16326 }, { "epoch": 0.8926430890141808, "grad_norm": 2.96065092086792, "learning_rate": 2.9962205972890956e-06, "loss": 1.102, "step": 16327 }, { "epoch": 0.8926977618315394, "grad_norm": 2.50795841217041, "learning_rate": 2.9932025746634396e-06, "loss": 1.0475, "step": 16328 }, { "epoch": 0.892752434648898, "grad_norm": 2.8771679401397705, "learning_rate": 2.990186025894476e-06, "loss": 1.0697, "step": 16329 }, { "epoch": 0.8928071074662566, "grad_norm": 2.9352850914001465, "learning_rate": 2.987170951076784e-06, "loss": 1.1098, "step": 16330 }, { "epoch": 0.8928617802836153, "grad_norm": 2.935854196548462, "learning_rate": 2.9841573503049003e-06, "loss": 0.9007, "step": 16331 }, { "epoch": 0.8929164531009739, "grad_norm": 3.6763930320739746, "learning_rate": 2.9811452236733204e-06, "loss": 0.9906, "step": 16332 }, { "epoch": 0.8929711259183325, "grad_norm": 2.285712718963623, "learning_rate": 2.978134571276475e-06, "loss": 1.1592, "step": 16333 }, { "epoch": 0.8930257987356911, "grad_norm": 2.3156421184539795, "learning_rate": 2.975125393208772e-06, "loss": 1.1606, "step": 16334 }, { "epoch": 0.8930804715530497, "grad_norm": 1.981939435005188, "learning_rate": 2.9721176895645576e-06, "loss": 0.975, "step": 16335 }, { "epoch": 0.8931351443704083, "grad_norm": 2.824859142303467, "learning_rate": 2.9691114604381233e-06, "loss": 1.1958, "step": 16336 }, { "epoch": 0.8931898171877669, "grad_norm": 2.275756597518921, "learning_rate": 2.966106705923749e-06, "loss": 1.1357, "step": 16337 }, { "epoch": 0.8932444900051256, "grad_norm": 2.566330671310425, "learning_rate": 2.9631034261156323e-06, "loss": 0.8994, "step": 16338 }, { "epoch": 0.8932991628224842, "grad_norm": 2.6931958198547363, "learning_rate": 2.960101621107947e-06, "loss": 1.085, "step": 16339 }, { "epoch": 0.8933538356398428, "grad_norm": 2.4471704959869385, "learning_rate": 2.9571012909948015e-06, "loss": 1.1875, "step": 16340 }, { "epoch": 0.8934085084572014, "grad_norm": 2.6182823181152344, "learning_rate": 2.9541024358702762e-06, "loss": 0.9099, "step": 16341 }, { "epoch": 0.89346318127456, "grad_norm": 2.272543430328369, "learning_rate": 2.9511050558283904e-06, "loss": 0.9803, "step": 16342 }, { "epoch": 0.8935178540919186, "grad_norm": 3.0427746772766113, "learning_rate": 2.9481091509631355e-06, "loss": 0.8618, "step": 16343 }, { "epoch": 0.8935725269092772, "grad_norm": 2.9793002605438232, "learning_rate": 2.9451147213684304e-06, "loss": 1.0938, "step": 16344 }, { "epoch": 0.893627199726636, "grad_norm": 2.2986931800842285, "learning_rate": 2.9421217671381786e-06, "loss": 1.0574, "step": 16345 }, { "epoch": 0.8936818725439946, "grad_norm": 2.930558204650879, "learning_rate": 2.9391302883662097e-06, "loss": 1.0772, "step": 16346 }, { "epoch": 0.8937365453613532, "grad_norm": 2.9844470024108887, "learning_rate": 2.936140285146327e-06, "loss": 1.1719, "step": 16347 }, { "epoch": 0.8937912181787118, "grad_norm": 2.447150945663452, "learning_rate": 2.9331517575722723e-06, "loss": 0.941, "step": 16348 }, { "epoch": 0.8938458909960704, "grad_norm": 2.2714669704437256, "learning_rate": 2.9301647057377425e-06, "loss": 0.9578, "step": 16349 }, { "epoch": 0.893900563813429, "grad_norm": 2.3573861122131348, "learning_rate": 2.9271791297364127e-06, "loss": 0.992, "step": 16350 }, { "epoch": 0.8939552366307876, "grad_norm": 2.7214410305023193, "learning_rate": 2.924195029661886e-06, "loss": 0.9929, "step": 16351 }, { "epoch": 0.8940099094481463, "grad_norm": 2.627084970474243, "learning_rate": 2.9212124056077204e-06, "loss": 1.074, "step": 16352 }, { "epoch": 0.8940645822655049, "grad_norm": 2.6036665439605713, "learning_rate": 2.9182312576674366e-06, "loss": 0.8468, "step": 16353 }, { "epoch": 0.8941192550828635, "grad_norm": 2.9809072017669678, "learning_rate": 2.9152515859345085e-06, "loss": 1.1508, "step": 16354 }, { "epoch": 0.8941739279002221, "grad_norm": 2.6502528190612793, "learning_rate": 2.912273390502357e-06, "loss": 0.8998, "step": 16355 }, { "epoch": 0.8942286007175807, "grad_norm": 2.4497902393341064, "learning_rate": 2.9092966714643622e-06, "loss": 1.0157, "step": 16356 }, { "epoch": 0.8942832735349393, "grad_norm": 2.2864675521850586, "learning_rate": 2.906321428913855e-06, "loss": 1.0679, "step": 16357 }, { "epoch": 0.894337946352298, "grad_norm": 2.772181510925293, "learning_rate": 2.9033476629441225e-06, "loss": 0.9489, "step": 16358 }, { "epoch": 0.8943926191696566, "grad_norm": 2.3917860984802246, "learning_rate": 2.900375373648412e-06, "loss": 0.7797, "step": 16359 }, { "epoch": 0.8944472919870152, "grad_norm": 2.6171083450317383, "learning_rate": 2.897404561119904e-06, "loss": 1.1553, "step": 16360 }, { "epoch": 0.8945019648043738, "grad_norm": 2.498631238937378, "learning_rate": 2.8944352254517527e-06, "loss": 0.9829, "step": 16361 }, { "epoch": 0.8945566376217324, "grad_norm": 2.614741086959839, "learning_rate": 2.8914673667370497e-06, "loss": 0.9421, "step": 16362 }, { "epoch": 0.894611310439091, "grad_norm": 2.578864336013794, "learning_rate": 2.888500985068865e-06, "loss": 0.9593, "step": 16363 }, { "epoch": 0.8946659832564496, "grad_norm": 2.4709396362304688, "learning_rate": 2.885536080540202e-06, "loss": 0.9186, "step": 16364 }, { "epoch": 0.8947206560738084, "grad_norm": 3.1405441761016846, "learning_rate": 2.88257265324402e-06, "loss": 0.8688, "step": 16365 }, { "epoch": 0.894775328891167, "grad_norm": 3.119100570678711, "learning_rate": 2.8796107032732387e-06, "loss": 0.7917, "step": 16366 }, { "epoch": 0.8948300017085256, "grad_norm": 2.1893134117126465, "learning_rate": 2.876650230720718e-06, "loss": 0.8852, "step": 16367 }, { "epoch": 0.8948846745258842, "grad_norm": 3.3177616596221924, "learning_rate": 2.8736912356792935e-06, "loss": 0.9435, "step": 16368 }, { "epoch": 0.8949393473432428, "grad_norm": 2.3434362411499023, "learning_rate": 2.8707337182417305e-06, "loss": 0.9677, "step": 16369 }, { "epoch": 0.8949940201606014, "grad_norm": 2.560657262802124, "learning_rate": 2.8677776785007604e-06, "loss": 1.0872, "step": 16370 }, { "epoch": 0.89504869297796, "grad_norm": 2.4299068450927734, "learning_rate": 2.8648231165490756e-06, "loss": 0.9629, "step": 16371 }, { "epoch": 0.8951033657953187, "grad_norm": 2.7132041454315186, "learning_rate": 2.8618700324793137e-06, "loss": 1.2131, "step": 16372 }, { "epoch": 0.8951580386126773, "grad_norm": 2.735940456390381, "learning_rate": 2.8589184263840553e-06, "loss": 0.954, "step": 16373 }, { "epoch": 0.8952127114300359, "grad_norm": 2.76167368888855, "learning_rate": 2.8559682983558435e-06, "loss": 1.1496, "step": 16374 }, { "epoch": 0.8952673842473945, "grad_norm": 2.5059738159179688, "learning_rate": 2.8530196484871928e-06, "loss": 1.0028, "step": 16375 }, { "epoch": 0.8953220570647531, "grad_norm": 3.674509048461914, "learning_rate": 2.8500724768705522e-06, "loss": 1.0187, "step": 16376 }, { "epoch": 0.8953767298821117, "grad_norm": 2.2149202823638916, "learning_rate": 2.8471267835983196e-06, "loss": 1.0079, "step": 16377 }, { "epoch": 0.8954314026994703, "grad_norm": 3.1460161209106445, "learning_rate": 2.84418256876286e-06, "loss": 0.9558, "step": 16378 }, { "epoch": 0.895486075516829, "grad_norm": 5.7661848068237305, "learning_rate": 2.8412398324564826e-06, "loss": 1.2725, "step": 16379 }, { "epoch": 0.8955407483341876, "grad_norm": 2.512254476547241, "learning_rate": 2.8382985747714587e-06, "loss": 0.9396, "step": 16380 }, { "epoch": 0.8955954211515462, "grad_norm": 2.7777562141418457, "learning_rate": 2.835358795800003e-06, "loss": 1.1367, "step": 16381 }, { "epoch": 0.8956500939689048, "grad_norm": 2.500777244567871, "learning_rate": 2.832420495634297e-06, "loss": 0.9923, "step": 16382 }, { "epoch": 0.8957047667862634, "grad_norm": 2.7872514724731445, "learning_rate": 2.829483674366462e-06, "loss": 1.0424, "step": 16383 }, { "epoch": 0.895759439603622, "grad_norm": 4.421524524688721, "learning_rate": 2.82654833208858e-06, "loss": 0.9772, "step": 16384 }, { "epoch": 0.8958141124209807, "grad_norm": 2.287306785583496, "learning_rate": 2.8236144688926934e-06, "loss": 1.1623, "step": 16385 }, { "epoch": 0.8958687852383393, "grad_norm": 2.543776512145996, "learning_rate": 2.8206820848707848e-06, "loss": 1.0183, "step": 16386 }, { "epoch": 0.895923458055698, "grad_norm": 2.7022974491119385, "learning_rate": 2.817751180114797e-06, "loss": 0.9778, "step": 16387 }, { "epoch": 0.8959781308730566, "grad_norm": 3.2466416358947754, "learning_rate": 2.814821754716629e-06, "loss": 0.9582, "step": 16388 }, { "epoch": 0.8960328036904152, "grad_norm": 2.4929518699645996, "learning_rate": 2.8118938087681235e-06, "loss": 0.8823, "step": 16389 }, { "epoch": 0.8960874765077738, "grad_norm": 2.6333529949188232, "learning_rate": 2.8089673423610906e-06, "loss": 1.1297, "step": 16390 }, { "epoch": 0.8961421493251324, "grad_norm": 2.9362058639526367, "learning_rate": 2.806042355587285e-06, "loss": 1.0867, "step": 16391 }, { "epoch": 0.8961968221424911, "grad_norm": 2.914792060852051, "learning_rate": 2.803118848538416e-06, "loss": 1.1846, "step": 16392 }, { "epoch": 0.8962514949598497, "grad_norm": 2.9742772579193115, "learning_rate": 2.8001968213061504e-06, "loss": 1.2125, "step": 16393 }, { "epoch": 0.8963061677772083, "grad_norm": 3.1250686645507812, "learning_rate": 2.7972762739820967e-06, "loss": 1.0582, "step": 16394 }, { "epoch": 0.8963608405945669, "grad_norm": 3.120394706726074, "learning_rate": 2.7943572066578383e-06, "loss": 1.0717, "step": 16395 }, { "epoch": 0.8964155134119255, "grad_norm": 2.790189266204834, "learning_rate": 2.7914396194248958e-06, "loss": 1.0799, "step": 16396 }, { "epoch": 0.8964701862292841, "grad_norm": 3.124391794204712, "learning_rate": 2.788523512374741e-06, "loss": 0.9986, "step": 16397 }, { "epoch": 0.8965248590466427, "grad_norm": 3.229172468185425, "learning_rate": 2.785608885598817e-06, "loss": 0.8384, "step": 16398 }, { "epoch": 0.8965795318640014, "grad_norm": 2.0804052352905273, "learning_rate": 2.782695739188501e-06, "loss": 0.9222, "step": 16399 }, { "epoch": 0.89663420468136, "grad_norm": 3.153020143508911, "learning_rate": 2.7797840732351365e-06, "loss": 1.256, "step": 16400 }, { "epoch": 0.8966888774987186, "grad_norm": 2.863119602203369, "learning_rate": 2.776873887830017e-06, "loss": 1.088, "step": 16401 }, { "epoch": 0.8967435503160772, "grad_norm": 2.115330219268799, "learning_rate": 2.773965183064381e-06, "loss": 0.8266, "step": 16402 }, { "epoch": 0.8967982231334358, "grad_norm": 3.052652597427368, "learning_rate": 2.7710579590294273e-06, "loss": 1.0197, "step": 16403 }, { "epoch": 0.8968528959507944, "grad_norm": 2.6883604526519775, "learning_rate": 2.7681522158163276e-06, "loss": 0.6805, "step": 16404 }, { "epoch": 0.896907568768153, "grad_norm": 1.9680185317993164, "learning_rate": 2.7652479535161755e-06, "loss": 0.8163, "step": 16405 }, { "epoch": 0.8969622415855117, "grad_norm": 2.9185478687286377, "learning_rate": 2.7623451722200322e-06, "loss": 1.0703, "step": 16406 }, { "epoch": 0.8970169144028703, "grad_norm": 2.229262590408325, "learning_rate": 2.7594438720189076e-06, "loss": 1.1204, "step": 16407 }, { "epoch": 0.897071587220229, "grad_norm": 2.15844988822937, "learning_rate": 2.756544053003779e-06, "loss": 0.9984, "step": 16408 }, { "epoch": 0.8971262600375876, "grad_norm": 2.4852089881896973, "learning_rate": 2.7536457152655682e-06, "loss": 0.8589, "step": 16409 }, { "epoch": 0.8971809328549462, "grad_norm": 2.354736328125, "learning_rate": 2.7507488588951357e-06, "loss": 0.8164, "step": 16410 }, { "epoch": 0.8972356056723048, "grad_norm": 2.388273000717163, "learning_rate": 2.747853483983326e-06, "loss": 1.0999, "step": 16411 }, { "epoch": 0.8972902784896635, "grad_norm": 3.991044044494629, "learning_rate": 2.7449595906209104e-06, "loss": 1.0162, "step": 16412 }, { "epoch": 0.8973449513070221, "grad_norm": 1.8013014793395996, "learning_rate": 2.7420671788986275e-06, "loss": 0.7953, "step": 16413 }, { "epoch": 0.8973996241243807, "grad_norm": 2.453477144241333, "learning_rate": 2.739176248907166e-06, "loss": 1.0794, "step": 16414 }, { "epoch": 0.8974542969417393, "grad_norm": 2.5290675163269043, "learning_rate": 2.7362868007371757e-06, "loss": 0.9282, "step": 16415 }, { "epoch": 0.8975089697590979, "grad_norm": 2.5401453971862793, "learning_rate": 2.733398834479245e-06, "loss": 0.9107, "step": 16416 }, { "epoch": 0.8975636425764565, "grad_norm": 2.5293831825256348, "learning_rate": 2.730512350223924e-06, "loss": 0.9478, "step": 16417 }, { "epoch": 0.8976183153938151, "grad_norm": 2.2120654582977295, "learning_rate": 2.7276273480617174e-06, "loss": 1.1597, "step": 16418 }, { "epoch": 0.8976729882111738, "grad_norm": 2.763566732406616, "learning_rate": 2.7247438280830818e-06, "loss": 0.9312, "step": 16419 }, { "epoch": 0.8977276610285324, "grad_norm": 3.35054874420166, "learning_rate": 2.7218617903784215e-06, "loss": 0.8874, "step": 16420 }, { "epoch": 0.897782333845891, "grad_norm": 2.895479440689087, "learning_rate": 2.718981235038115e-06, "loss": 1.1453, "step": 16421 }, { "epoch": 0.8978370066632496, "grad_norm": 2.4474782943725586, "learning_rate": 2.7161021621524673e-06, "loss": 0.853, "step": 16422 }, { "epoch": 0.8978916794806082, "grad_norm": 2.803866147994995, "learning_rate": 2.71322457181174e-06, "loss": 0.8952, "step": 16423 }, { "epoch": 0.8979463522979668, "grad_norm": 2.40022873878479, "learning_rate": 2.7103484641061825e-06, "loss": 0.9421, "step": 16424 }, { "epoch": 0.8980010251153254, "grad_norm": 3.135713577270508, "learning_rate": 2.7074738391259568e-06, "loss": 1.2011, "step": 16425 }, { "epoch": 0.8980556979326841, "grad_norm": 2.8765084743499756, "learning_rate": 2.7046006969612014e-06, "loss": 0.9296, "step": 16426 }, { "epoch": 0.8981103707500427, "grad_norm": 3.1331655979156494, "learning_rate": 2.7017290377019943e-06, "loss": 1.2319, "step": 16427 }, { "epoch": 0.8981650435674013, "grad_norm": 2.887173652648926, "learning_rate": 2.6988588614383746e-06, "loss": 1.1612, "step": 16428 }, { "epoch": 0.89821971638476, "grad_norm": 2.690619468688965, "learning_rate": 2.6959901682603373e-06, "loss": 1.1461, "step": 16429 }, { "epoch": 0.8982743892021186, "grad_norm": 2.5880839824676514, "learning_rate": 2.693122958257832e-06, "loss": 1.0706, "step": 16430 }, { "epoch": 0.8983290620194772, "grad_norm": 2.949803113937378, "learning_rate": 2.690257231520743e-06, "loss": 1.1352, "step": 16431 }, { "epoch": 0.8983837348368358, "grad_norm": 2.3080859184265137, "learning_rate": 2.687392988138937e-06, "loss": 0.9167, "step": 16432 }, { "epoch": 0.8984384076541945, "grad_norm": 2.605527877807617, "learning_rate": 2.684530228202209e-06, "loss": 1.0647, "step": 16433 }, { "epoch": 0.8984930804715531, "grad_norm": 5.374227046966553, "learning_rate": 2.6816689518003257e-06, "loss": 1.0328, "step": 16434 }, { "epoch": 0.8985477532889117, "grad_norm": 2.94561505317688, "learning_rate": 2.6788091590230045e-06, "loss": 1.0258, "step": 16435 }, { "epoch": 0.8986024261062703, "grad_norm": 2.2933928966522217, "learning_rate": 2.6759508499599016e-06, "loss": 1.0844, "step": 16436 }, { "epoch": 0.8986570989236289, "grad_norm": 2.2267112731933594, "learning_rate": 2.6730940247006396e-06, "loss": 0.7224, "step": 16437 }, { "epoch": 0.8987117717409875, "grad_norm": 2.485058307647705, "learning_rate": 2.6702386833347916e-06, "loss": 0.9136, "step": 16438 }, { "epoch": 0.8987664445583462, "grad_norm": 2.9370005130767822, "learning_rate": 2.667384825951885e-06, "loss": 0.9708, "step": 16439 }, { "epoch": 0.8988211173757048, "grad_norm": 3.032942295074463, "learning_rate": 2.664532452641405e-06, "loss": 1.074, "step": 16440 }, { "epoch": 0.8988757901930634, "grad_norm": 2.3634016513824463, "learning_rate": 2.6616815634927796e-06, "loss": 0.9263, "step": 16441 }, { "epoch": 0.898930463010422, "grad_norm": 3.0723397731781006, "learning_rate": 2.6588321585953924e-06, "loss": 1.0551, "step": 16442 }, { "epoch": 0.8989851358277806, "grad_norm": 2.9328527450561523, "learning_rate": 2.6559842380385835e-06, "loss": 1.1956, "step": 16443 }, { "epoch": 0.8990398086451392, "grad_norm": 2.7693963050842285, "learning_rate": 2.6531378019116593e-06, "loss": 1.2888, "step": 16444 }, { "epoch": 0.8990944814624978, "grad_norm": 2.3960421085357666, "learning_rate": 2.6502928503038595e-06, "loss": 0.7309, "step": 16445 }, { "epoch": 0.8991491542798565, "grad_norm": 3.43939208984375, "learning_rate": 2.6474493833043846e-06, "loss": 0.8799, "step": 16446 }, { "epoch": 0.8992038270972151, "grad_norm": 2.64137864112854, "learning_rate": 2.6446074010023913e-06, "loss": 1.0163, "step": 16447 }, { "epoch": 0.8992584999145737, "grad_norm": 2.4365499019622803, "learning_rate": 2.641766903486986e-06, "loss": 1.0723, "step": 16448 }, { "epoch": 0.8993131727319323, "grad_norm": 2.3890295028686523, "learning_rate": 2.6389278908472316e-06, "loss": 0.9556, "step": 16449 }, { "epoch": 0.899367845549291, "grad_norm": 2.699204206466675, "learning_rate": 2.636090363172139e-06, "loss": 1.1336, "step": 16450 }, { "epoch": 0.8994225183666495, "grad_norm": 2.4914469718933105, "learning_rate": 2.6332543205506766e-06, "loss": 0.9509, "step": 16451 }, { "epoch": 0.8994771911840082, "grad_norm": 3.580425977706909, "learning_rate": 2.630419763071773e-06, "loss": 0.8598, "step": 16452 }, { "epoch": 0.8995318640013669, "grad_norm": 3.171133518218994, "learning_rate": 2.6275866908242853e-06, "loss": 0.8773, "step": 16453 }, { "epoch": 0.8995865368187255, "grad_norm": 3.1375207901000977, "learning_rate": 2.624755103897064e-06, "loss": 1.0235, "step": 16454 }, { "epoch": 0.8996412096360841, "grad_norm": 2.456458568572998, "learning_rate": 2.6219250023788835e-06, "loss": 1.0649, "step": 16455 }, { "epoch": 0.8996958824534427, "grad_norm": 2.0835928916931152, "learning_rate": 2.6190963863584773e-06, "loss": 0.9168, "step": 16456 }, { "epoch": 0.8997505552708013, "grad_norm": 3.3511290550231934, "learning_rate": 2.6162692559245303e-06, "loss": 1.0738, "step": 16457 }, { "epoch": 0.8998052280881599, "grad_norm": 2.8610925674438477, "learning_rate": 2.6134436111656946e-06, "loss": 1.003, "step": 16458 }, { "epoch": 0.8998599009055185, "grad_norm": 2.269867181777954, "learning_rate": 2.610619452170554e-06, "loss": 0.9434, "step": 16459 }, { "epoch": 0.8999145737228772, "grad_norm": 2.9031875133514404, "learning_rate": 2.6077967790276714e-06, "loss": 1.0332, "step": 16460 }, { "epoch": 0.8999692465402358, "grad_norm": 2.8884146213531494, "learning_rate": 2.604975591825537e-06, "loss": 1.2575, "step": 16461 }, { "epoch": 0.9000239193575944, "grad_norm": 2.7949042320251465, "learning_rate": 2.602155890652602e-06, "loss": 0.9594, "step": 16462 }, { "epoch": 0.900078592174953, "grad_norm": 2.3736019134521484, "learning_rate": 2.599337675597291e-06, "loss": 0.9102, "step": 16463 }, { "epoch": 0.9001332649923116, "grad_norm": 3.1222033500671387, "learning_rate": 2.5965209467479657e-06, "loss": 1.0572, "step": 16464 }, { "epoch": 0.9001879378096702, "grad_norm": 2.8405332565307617, "learning_rate": 2.5937057041929335e-06, "loss": 0.9829, "step": 16465 }, { "epoch": 0.9002426106270289, "grad_norm": 3.190782070159912, "learning_rate": 2.590891948020463e-06, "loss": 1.046, "step": 16466 }, { "epoch": 0.9002972834443875, "grad_norm": 2.222499370574951, "learning_rate": 2.588079678318789e-06, "loss": 0.8936, "step": 16467 }, { "epoch": 0.9003519562617461, "grad_norm": 2.9703288078308105, "learning_rate": 2.585268895176074e-06, "loss": 1.1777, "step": 16468 }, { "epoch": 0.9004066290791047, "grad_norm": 2.4547858238220215, "learning_rate": 2.5824595986804534e-06, "loss": 1.0287, "step": 16469 }, { "epoch": 0.9004613018964633, "grad_norm": 3.742692708969116, "learning_rate": 2.5796517889200176e-06, "loss": 1.0825, "step": 16470 }, { "epoch": 0.9005159747138219, "grad_norm": 2.395490884780884, "learning_rate": 2.5768454659827858e-06, "loss": 1.0582, "step": 16471 }, { "epoch": 0.9005706475311805, "grad_norm": 2.943840503692627, "learning_rate": 2.5740406299567586e-06, "loss": 0.9705, "step": 16472 }, { "epoch": 0.9006253203485393, "grad_norm": 2.6625263690948486, "learning_rate": 2.571237280929878e-06, "loss": 1.1438, "step": 16473 }, { "epoch": 0.9006799931658979, "grad_norm": 3.2651207447052, "learning_rate": 2.568435418990045e-06, "loss": 0.9635, "step": 16474 }, { "epoch": 0.9007346659832565, "grad_norm": 2.6892900466918945, "learning_rate": 2.5656350442251063e-06, "loss": 0.9907, "step": 16475 }, { "epoch": 0.9007893388006151, "grad_norm": 2.822747230529785, "learning_rate": 2.5628361567228644e-06, "loss": 1.1532, "step": 16476 }, { "epoch": 0.9008440116179737, "grad_norm": 2.2910845279693604, "learning_rate": 2.5600387565710705e-06, "loss": 0.7564, "step": 16477 }, { "epoch": 0.9008986844353323, "grad_norm": 2.271298885345459, "learning_rate": 2.5572428438574438e-06, "loss": 0.9336, "step": 16478 }, { "epoch": 0.9009533572526909, "grad_norm": 2.292145013809204, "learning_rate": 2.554448418669647e-06, "loss": 0.9074, "step": 16479 }, { "epoch": 0.9010080300700496, "grad_norm": 2.0211374759674072, "learning_rate": 2.5516554810952885e-06, "loss": 0.8205, "step": 16480 }, { "epoch": 0.9010627028874082, "grad_norm": 2.8745462894439697, "learning_rate": 2.5488640312219425e-06, "loss": 1.0785, "step": 16481 }, { "epoch": 0.9011173757047668, "grad_norm": 2.470506429672241, "learning_rate": 2.5460740691371278e-06, "loss": 0.9993, "step": 16482 }, { "epoch": 0.9011720485221254, "grad_norm": 2.6640560626983643, "learning_rate": 2.5432855949283353e-06, "loss": 0.9681, "step": 16483 }, { "epoch": 0.901226721339484, "grad_norm": 2.7092249393463135, "learning_rate": 2.540498608682984e-06, "loss": 1.0085, "step": 16484 }, { "epoch": 0.9012813941568426, "grad_norm": 2.9276702404022217, "learning_rate": 2.5377131104884655e-06, "loss": 1.1692, "step": 16485 }, { "epoch": 0.9013360669742012, "grad_norm": 2.4857428073883057, "learning_rate": 2.534929100432104e-06, "loss": 0.9433, "step": 16486 }, { "epoch": 0.9013907397915599, "grad_norm": 2.135934829711914, "learning_rate": 2.532146578601202e-06, "loss": 0.8818, "step": 16487 }, { "epoch": 0.9014454126089185, "grad_norm": 3.93432879447937, "learning_rate": 2.529365545082996e-06, "loss": 1.0764, "step": 16488 }, { "epoch": 0.9015000854262771, "grad_norm": 2.9621598720550537, "learning_rate": 2.526585999964687e-06, "loss": 1.0883, "step": 16489 }, { "epoch": 0.9015547582436357, "grad_norm": 3.2880849838256836, "learning_rate": 2.523807943333417e-06, "loss": 1.1503, "step": 16490 }, { "epoch": 0.9016094310609943, "grad_norm": 2.8747611045837402, "learning_rate": 2.5210313752763005e-06, "loss": 1.034, "step": 16491 }, { "epoch": 0.9016641038783529, "grad_norm": 2.9592227935791016, "learning_rate": 2.5182562958803837e-06, "loss": 1.0288, "step": 16492 }, { "epoch": 0.9017187766957117, "grad_norm": 2.201650857925415, "learning_rate": 2.5154827052326856e-06, "loss": 1.0213, "step": 16493 }, { "epoch": 0.9017734495130703, "grad_norm": 2.9121713638305664, "learning_rate": 2.5127106034201653e-06, "loss": 1.1812, "step": 16494 }, { "epoch": 0.9018281223304289, "grad_norm": 2.480828046798706, "learning_rate": 2.5099399905297415e-06, "loss": 0.9581, "step": 16495 }, { "epoch": 0.9018827951477875, "grad_norm": 2.5866503715515137, "learning_rate": 2.507170866648284e-06, "loss": 0.8031, "step": 16496 }, { "epoch": 0.9019374679651461, "grad_norm": 2.895216226577759, "learning_rate": 2.5044032318626176e-06, "loss": 1.0576, "step": 16497 }, { "epoch": 0.9019921407825047, "grad_norm": 5.838606357574463, "learning_rate": 2.5016370862595173e-06, "loss": 0.8372, "step": 16498 }, { "epoch": 0.9020468135998633, "grad_norm": 2.9603123664855957, "learning_rate": 2.498872429925714e-06, "loss": 1.1853, "step": 16499 }, { "epoch": 0.902101486417222, "grad_norm": 2.3459391593933105, "learning_rate": 2.4961092629478875e-06, "loss": 0.9048, "step": 16500 }, { "epoch": 0.9021561592345806, "grad_norm": 2.443742275238037, "learning_rate": 2.4933475854126753e-06, "loss": 0.9168, "step": 16501 }, { "epoch": 0.9022108320519392, "grad_norm": 2.613291025161743, "learning_rate": 2.490587397406663e-06, "loss": 1.0067, "step": 16502 }, { "epoch": 0.9022655048692978, "grad_norm": 2.551654100418091, "learning_rate": 2.487828699016409e-06, "loss": 0.9957, "step": 16503 }, { "epoch": 0.9023201776866564, "grad_norm": 3.1795148849487305, "learning_rate": 2.4850714903284055e-06, "loss": 0.8995, "step": 16504 }, { "epoch": 0.902374850504015, "grad_norm": 2.9214975833892822, "learning_rate": 2.482315771429089e-06, "loss": 1.1788, "step": 16505 }, { "epoch": 0.9024295233213736, "grad_norm": 3.1279611587524414, "learning_rate": 2.479561542404879e-06, "loss": 0.9973, "step": 16506 }, { "epoch": 0.9024841961387323, "grad_norm": 2.114626407623291, "learning_rate": 2.476808803342118e-06, "loss": 0.983, "step": 16507 }, { "epoch": 0.9025388689560909, "grad_norm": 2.1201446056365967, "learning_rate": 2.474057554327125e-06, "loss": 0.9931, "step": 16508 }, { "epoch": 0.9025935417734495, "grad_norm": 2.3333308696746826, "learning_rate": 2.4713077954461593e-06, "loss": 0.8815, "step": 16509 }, { "epoch": 0.9026482145908081, "grad_norm": 2.187152862548828, "learning_rate": 2.4685595267854358e-06, "loss": 1.0023, "step": 16510 }, { "epoch": 0.9027028874081667, "grad_norm": 2.708402633666992, "learning_rate": 2.4658127484311235e-06, "loss": 0.837, "step": 16511 }, { "epoch": 0.9027575602255253, "grad_norm": 2.38791561126709, "learning_rate": 2.463067460469354e-06, "loss": 0.9445, "step": 16512 }, { "epoch": 0.9028122330428839, "grad_norm": 2.8569087982177734, "learning_rate": 2.460323662986197e-06, "loss": 1.1177, "step": 16513 }, { "epoch": 0.9028669058602427, "grad_norm": 2.238252878189087, "learning_rate": 2.4575813560676785e-06, "loss": 0.9845, "step": 16514 }, { "epoch": 0.9029215786776013, "grad_norm": 2.781508684158325, "learning_rate": 2.4548405397997854e-06, "loss": 0.9673, "step": 16515 }, { "epoch": 0.9029762514949599, "grad_norm": 3.07600474357605, "learning_rate": 2.452101214268454e-06, "loss": 1.1619, "step": 16516 }, { "epoch": 0.9030309243123185, "grad_norm": 2.1878533363342285, "learning_rate": 2.449363379559577e-06, "loss": 0.9898, "step": 16517 }, { "epoch": 0.9030855971296771, "grad_norm": 2.4067602157592773, "learning_rate": 2.446627035758986e-06, "loss": 1.0558, "step": 16518 }, { "epoch": 0.9031402699470357, "grad_norm": 2.500624656677246, "learning_rate": 2.443892182952484e-06, "loss": 0.9753, "step": 16519 }, { "epoch": 0.9031949427643944, "grad_norm": 2.2742722034454346, "learning_rate": 2.4411588212258194e-06, "loss": 0.8721, "step": 16520 }, { "epoch": 0.903249615581753, "grad_norm": 2.9705588817596436, "learning_rate": 2.4384269506646964e-06, "loss": 0.8936, "step": 16521 }, { "epoch": 0.9033042883991116, "grad_norm": 2.170257091522217, "learning_rate": 2.4356965713547617e-06, "loss": 0.7817, "step": 16522 }, { "epoch": 0.9033589612164702, "grad_norm": 2.670060396194458, "learning_rate": 2.432967683381626e-06, "loss": 0.9993, "step": 16523 }, { "epoch": 0.9034136340338288, "grad_norm": 2.604792356491089, "learning_rate": 2.430240286830865e-06, "loss": 0.9622, "step": 16524 }, { "epoch": 0.9034683068511874, "grad_norm": 2.649474620819092, "learning_rate": 2.4275143817879766e-06, "loss": 1.0044, "step": 16525 }, { "epoch": 0.903522979668546, "grad_norm": 2.4020957946777344, "learning_rate": 2.4247899683384423e-06, "loss": 1.1086, "step": 16526 }, { "epoch": 0.9035776524859047, "grad_norm": 2.7700836658477783, "learning_rate": 2.4220670465676774e-06, "loss": 0.8843, "step": 16527 }, { "epoch": 0.9036323253032633, "grad_norm": 2.4894940853118896, "learning_rate": 2.4193456165610528e-06, "loss": 0.9989, "step": 16528 }, { "epoch": 0.9036869981206219, "grad_norm": 2.292031764984131, "learning_rate": 2.4166256784039056e-06, "loss": 1.0899, "step": 16529 }, { "epoch": 0.9037416709379805, "grad_norm": 2.356226682662964, "learning_rate": 2.413907232181506e-06, "loss": 0.9934, "step": 16530 }, { "epoch": 0.9037963437553391, "grad_norm": 3.038904905319214, "learning_rate": 2.411190277979103e-06, "loss": 1.1619, "step": 16531 }, { "epoch": 0.9038510165726977, "grad_norm": 3.3922276496887207, "learning_rate": 2.408474815881873e-06, "loss": 1.326, "step": 16532 }, { "epoch": 0.9039056893900563, "grad_norm": 3.0474274158477783, "learning_rate": 2.4057608459749583e-06, "loss": 0.9896, "step": 16533 }, { "epoch": 0.903960362207415, "grad_norm": 2.45937442779541, "learning_rate": 2.403048368343452e-06, "loss": 1.0746, "step": 16534 }, { "epoch": 0.9040150350247736, "grad_norm": 2.8677303791046143, "learning_rate": 2.4003373830724098e-06, "loss": 1.1033, "step": 16535 }, { "epoch": 0.9040697078421323, "grad_norm": 2.283252716064453, "learning_rate": 2.3976278902468177e-06, "loss": 0.914, "step": 16536 }, { "epoch": 0.9041243806594909, "grad_norm": 3.4152278900146484, "learning_rate": 2.3949198899516413e-06, "loss": 0.9106, "step": 16537 }, { "epoch": 0.9041790534768495, "grad_norm": 2.87410831451416, "learning_rate": 2.3922133822717906e-06, "loss": 0.8989, "step": 16538 }, { "epoch": 0.9042337262942081, "grad_norm": 2.6674489974975586, "learning_rate": 2.3895083672921147e-06, "loss": 1.1064, "step": 16539 }, { "epoch": 0.9042883991115667, "grad_norm": 2.396664619445801, "learning_rate": 2.3868048450974345e-06, "loss": 1.1568, "step": 16540 }, { "epoch": 0.9043430719289254, "grad_norm": 3.7060751914978027, "learning_rate": 2.3841028157725156e-06, "loss": 1.0705, "step": 16541 }, { "epoch": 0.904397744746284, "grad_norm": 2.2016396522521973, "learning_rate": 2.381402279402073e-06, "loss": 0.9256, "step": 16542 }, { "epoch": 0.9044524175636426, "grad_norm": 2.1021816730499268, "learning_rate": 2.378703236070784e-06, "loss": 0.8911, "step": 16543 }, { "epoch": 0.9045070903810012, "grad_norm": 2.874176502227783, "learning_rate": 2.376005685863275e-06, "loss": 1.123, "step": 16544 }, { "epoch": 0.9045617631983598, "grad_norm": 2.817718267440796, "learning_rate": 2.373309628864123e-06, "loss": 1.0455, "step": 16545 }, { "epoch": 0.9046164360157184, "grad_norm": 2.4911205768585205, "learning_rate": 2.370615065157861e-06, "loss": 0.8855, "step": 16546 }, { "epoch": 0.9046711088330771, "grad_norm": 2.6656479835510254, "learning_rate": 2.3679219948289757e-06, "loss": 0.9575, "step": 16547 }, { "epoch": 0.9047257816504357, "grad_norm": 4.4126129150390625, "learning_rate": 2.365230417961906e-06, "loss": 1.1042, "step": 16548 }, { "epoch": 0.9047804544677943, "grad_norm": 1.9494974613189697, "learning_rate": 2.3625403346410335e-06, "loss": 0.8965, "step": 16549 }, { "epoch": 0.9048351272851529, "grad_norm": 2.9915287494659424, "learning_rate": 2.359851744950725e-06, "loss": 0.9571, "step": 16550 }, { "epoch": 0.9048898001025115, "grad_norm": 2.8306241035461426, "learning_rate": 2.357164648975263e-06, "loss": 1.0624, "step": 16551 }, { "epoch": 0.9049444729198701, "grad_norm": 2.9238481521606445, "learning_rate": 2.354479046798902e-06, "loss": 0.8213, "step": 16552 }, { "epoch": 0.9049991457372287, "grad_norm": 2.729624032974243, "learning_rate": 2.3517949385058525e-06, "loss": 1.0116, "step": 16553 }, { "epoch": 0.9050538185545874, "grad_norm": 2.7947566509246826, "learning_rate": 2.3491123241802638e-06, "loss": 0.9422, "step": 16554 }, { "epoch": 0.905108491371946, "grad_norm": 2.367110252380371, "learning_rate": 2.346431203906252e-06, "loss": 1.1027, "step": 16555 }, { "epoch": 0.9051631641893046, "grad_norm": 3.0535595417022705, "learning_rate": 2.3437515777678776e-06, "loss": 1.014, "step": 16556 }, { "epoch": 0.9052178370066633, "grad_norm": 3.051539897918701, "learning_rate": 2.3410734458491624e-06, "loss": 0.9304, "step": 16557 }, { "epoch": 0.9052725098240219, "grad_norm": 2.8351261615753174, "learning_rate": 2.3383968082340723e-06, "loss": 1.0252, "step": 16558 }, { "epoch": 0.9053271826413805, "grad_norm": 2.033519983291626, "learning_rate": 2.335721665006535e-06, "loss": 0.9688, "step": 16559 }, { "epoch": 0.9053818554587391, "grad_norm": 2.8721983432769775, "learning_rate": 2.333048016250422e-06, "loss": 1.0666, "step": 16560 }, { "epoch": 0.9054365282760978, "grad_norm": 2.802647590637207, "learning_rate": 2.330375862049572e-06, "loss": 1.0953, "step": 16561 }, { "epoch": 0.9054912010934564, "grad_norm": 3.5912275314331055, "learning_rate": 2.3277052024877565e-06, "loss": 1.0636, "step": 16562 }, { "epoch": 0.905545873910815, "grad_norm": 2.1338038444519043, "learning_rate": 2.3250360376487255e-06, "loss": 0.8165, "step": 16563 }, { "epoch": 0.9056005467281736, "grad_norm": 2.8661725521087646, "learning_rate": 2.322368367616157e-06, "loss": 1.1822, "step": 16564 }, { "epoch": 0.9056552195455322, "grad_norm": 2.5425307750701904, "learning_rate": 2.3197021924736993e-06, "loss": 1.1351, "step": 16565 }, { "epoch": 0.9057098923628908, "grad_norm": 3.4871413707733154, "learning_rate": 2.3170375123049426e-06, "loss": 1.0424, "step": 16566 }, { "epoch": 0.9057645651802494, "grad_norm": 3.473172664642334, "learning_rate": 2.3143743271934415e-06, "loss": 1.1947, "step": 16567 }, { "epoch": 0.9058192379976081, "grad_norm": 2.3619112968444824, "learning_rate": 2.3117126372226962e-06, "loss": 1.0642, "step": 16568 }, { "epoch": 0.9058739108149667, "grad_norm": 2.2311389446258545, "learning_rate": 2.309052442476162e-06, "loss": 0.9181, "step": 16569 }, { "epoch": 0.9059285836323253, "grad_norm": 3.4653871059417725, "learning_rate": 2.306393743037233e-06, "loss": 0.662, "step": 16570 }, { "epoch": 0.9059832564496839, "grad_norm": 2.9544715881347656, "learning_rate": 2.303736538989293e-06, "loss": 1.0422, "step": 16571 }, { "epoch": 0.9060379292670425, "grad_norm": 2.4465856552124023, "learning_rate": 2.301080830415647e-06, "loss": 0.8059, "step": 16572 }, { "epoch": 0.9060926020844011, "grad_norm": 2.5603675842285156, "learning_rate": 2.2984266173995626e-06, "loss": 0.898, "step": 16573 }, { "epoch": 0.9061472749017598, "grad_norm": 2.7092854976654053, "learning_rate": 2.2957739000242564e-06, "loss": 1.2019, "step": 16574 }, { "epoch": 0.9062019477191184, "grad_norm": 2.442268133163452, "learning_rate": 2.2931226783729054e-06, "loss": 1.0276, "step": 16575 }, { "epoch": 0.906256620536477, "grad_norm": 2.033053159713745, "learning_rate": 2.2904729525286384e-06, "loss": 0.8843, "step": 16576 }, { "epoch": 0.9063112933538356, "grad_norm": 2.232311725616455, "learning_rate": 2.287824722574533e-06, "loss": 0.9744, "step": 16577 }, { "epoch": 0.9063659661711942, "grad_norm": 2.9024689197540283, "learning_rate": 2.2851779885936176e-06, "loss": 1.0984, "step": 16578 }, { "epoch": 0.9064206389885529, "grad_norm": 2.259882926940918, "learning_rate": 2.2825327506688864e-06, "loss": 0.8797, "step": 16579 }, { "epoch": 0.9064753118059115, "grad_norm": 2.6174588203430176, "learning_rate": 2.279889008883268e-06, "loss": 1.0958, "step": 16580 }, { "epoch": 0.9065299846232702, "grad_norm": 2.337458610534668, "learning_rate": 2.2772467633196625e-06, "loss": 1.01, "step": 16581 }, { "epoch": 0.9065846574406288, "grad_norm": 2.712226629257202, "learning_rate": 2.2746060140609205e-06, "loss": 1.2276, "step": 16582 }, { "epoch": 0.9066393302579874, "grad_norm": 2.511343479156494, "learning_rate": 2.271966761189831e-06, "loss": 0.9587, "step": 16583 }, { "epoch": 0.906694003075346, "grad_norm": 4.7198896408081055, "learning_rate": 2.2693290047891503e-06, "loss": 1.0585, "step": 16584 }, { "epoch": 0.9067486758927046, "grad_norm": 2.666637420654297, "learning_rate": 2.2666927449415785e-06, "loss": 0.9635, "step": 16585 }, { "epoch": 0.9068033487100632, "grad_norm": 2.647169589996338, "learning_rate": 2.2640579817297727e-06, "loss": 1.0003, "step": 16586 }, { "epoch": 0.9068580215274218, "grad_norm": 2.994218349456787, "learning_rate": 2.261424715236349e-06, "loss": 1.0151, "step": 16587 }, { "epoch": 0.9069126943447805, "grad_norm": 3.0411994457244873, "learning_rate": 2.2587929455438693e-06, "loss": 1.1478, "step": 16588 }, { "epoch": 0.9069673671621391, "grad_norm": 3.2181761264801025, "learning_rate": 2.2561626727348517e-06, "loss": 1.0917, "step": 16589 }, { "epoch": 0.9070220399794977, "grad_norm": 2.5063676834106445, "learning_rate": 2.253533896891752e-06, "loss": 1.0676, "step": 16590 }, { "epoch": 0.9070767127968563, "grad_norm": 2.710850954055786, "learning_rate": 2.250906618097015e-06, "loss": 0.9935, "step": 16591 }, { "epoch": 0.9071313856142149, "grad_norm": 2.659121036529541, "learning_rate": 2.248280836433009e-06, "loss": 1.1078, "step": 16592 }, { "epoch": 0.9071860584315735, "grad_norm": 2.2908132076263428, "learning_rate": 2.245656551982056e-06, "loss": 0.9425, "step": 16593 }, { "epoch": 0.9072407312489321, "grad_norm": 2.0862178802490234, "learning_rate": 2.2430337648264467e-06, "loss": 1.0616, "step": 16594 }, { "epoch": 0.9072954040662908, "grad_norm": 3.1764278411865234, "learning_rate": 2.240412475048409e-06, "loss": 0.843, "step": 16595 }, { "epoch": 0.9073500768836494, "grad_norm": 2.3572704792022705, "learning_rate": 2.237792682730139e-06, "loss": 0.9517, "step": 16596 }, { "epoch": 0.907404749701008, "grad_norm": 2.8169453144073486, "learning_rate": 2.2351743879537703e-06, "loss": 1.0931, "step": 16597 }, { "epoch": 0.9074594225183666, "grad_norm": 2.1795666217803955, "learning_rate": 2.232557590801404e-06, "loss": 0.9582, "step": 16598 }, { "epoch": 0.9075140953357252, "grad_norm": 3.340848445892334, "learning_rate": 2.229942291355086e-06, "loss": 1.038, "step": 16599 }, { "epoch": 0.9075687681530838, "grad_norm": 3.8304691314697266, "learning_rate": 2.2273284896968004e-06, "loss": 0.8688, "step": 16600 }, { "epoch": 0.9076234409704426, "grad_norm": 3.4392104148864746, "learning_rate": 2.2247161859085265e-06, "loss": 1.0722, "step": 16601 }, { "epoch": 0.9076781137878012, "grad_norm": 2.400087356567383, "learning_rate": 2.222105380072159e-06, "loss": 1.0796, "step": 16602 }, { "epoch": 0.9077327866051598, "grad_norm": 4.3013386726379395, "learning_rate": 2.2194960722695613e-06, "loss": 1.125, "step": 16603 }, { "epoch": 0.9077874594225184, "grad_norm": 2.792294979095459, "learning_rate": 2.216888262582539e-06, "loss": 1.0431, "step": 16604 }, { "epoch": 0.907842132239877, "grad_norm": 3.1275436878204346, "learning_rate": 2.2142819510928615e-06, "loss": 0.8546, "step": 16605 }, { "epoch": 0.9078968050572356, "grad_norm": 2.9170379638671875, "learning_rate": 2.2116771378822453e-06, "loss": 1.1552, "step": 16606 }, { "epoch": 0.9079514778745942, "grad_norm": 2.581714153289795, "learning_rate": 2.209073823032365e-06, "loss": 1.1168, "step": 16607 }, { "epoch": 0.9080061506919529, "grad_norm": 2.6290578842163086, "learning_rate": 2.2064720066248433e-06, "loss": 1.1335, "step": 16608 }, { "epoch": 0.9080608235093115, "grad_norm": 2.9361677169799805, "learning_rate": 2.20387168874126e-06, "loss": 1.2076, "step": 16609 }, { "epoch": 0.9081154963266701, "grad_norm": 2.449737071990967, "learning_rate": 2.201272869463139e-06, "loss": 1.0896, "step": 16610 }, { "epoch": 0.9081701691440287, "grad_norm": 2.42216157913208, "learning_rate": 2.19867554887197e-06, "loss": 0.9801, "step": 16611 }, { "epoch": 0.9082248419613873, "grad_norm": 2.4295737743377686, "learning_rate": 2.196079727049194e-06, "loss": 0.94, "step": 16612 }, { "epoch": 0.9082795147787459, "grad_norm": 2.2026703357696533, "learning_rate": 2.1934854040761955e-06, "loss": 1.0119, "step": 16613 }, { "epoch": 0.9083341875961045, "grad_norm": 3.359074115753174, "learning_rate": 2.1908925800343203e-06, "loss": 1.1228, "step": 16614 }, { "epoch": 0.9083888604134632, "grad_norm": 2.1807897090911865, "learning_rate": 2.1883012550048542e-06, "loss": 1.0304, "step": 16615 }, { "epoch": 0.9084435332308218, "grad_norm": 3.248948097229004, "learning_rate": 2.1857114290690594e-06, "loss": 1.0881, "step": 16616 }, { "epoch": 0.9084982060481804, "grad_norm": 2.766406774520874, "learning_rate": 2.1831231023081265e-06, "loss": 0.9709, "step": 16617 }, { "epoch": 0.908552878865539, "grad_norm": 2.9108777046203613, "learning_rate": 2.1805362748032187e-06, "loss": 1.166, "step": 16618 }, { "epoch": 0.9086075516828976, "grad_norm": 3.72047758102417, "learning_rate": 2.1779509466354266e-06, "loss": 0.9679, "step": 16619 }, { "epoch": 0.9086622245002562, "grad_norm": 3.9671316146850586, "learning_rate": 2.17536711788584e-06, "loss": 1.02, "step": 16620 }, { "epoch": 0.9087168973176148, "grad_norm": 3.5513699054718018, "learning_rate": 2.1727847886354514e-06, "loss": 1.0497, "step": 16621 }, { "epoch": 0.9087715701349736, "grad_norm": 2.7605412006378174, "learning_rate": 2.1702039589652336e-06, "loss": 1.1911, "step": 16622 }, { "epoch": 0.9088262429523322, "grad_norm": 2.334529399871826, "learning_rate": 2.167624628956105e-06, "loss": 0.8934, "step": 16623 }, { "epoch": 0.9088809157696908, "grad_norm": 2.8546547889709473, "learning_rate": 2.1650467986889357e-06, "loss": 1.2008, "step": 16624 }, { "epoch": 0.9089355885870494, "grad_norm": 2.1893434524536133, "learning_rate": 2.1624704682445597e-06, "loss": 0.8786, "step": 16625 }, { "epoch": 0.908990261404408, "grad_norm": 2.650339126586914, "learning_rate": 2.159895637703746e-06, "loss": 0.8804, "step": 16626 }, { "epoch": 0.9090449342217666, "grad_norm": 2.8342294692993164, "learning_rate": 2.157322307147236e-06, "loss": 1.1923, "step": 16627 }, { "epoch": 0.9090996070391253, "grad_norm": 3.2765049934387207, "learning_rate": 2.1547504766557035e-06, "loss": 1.2085, "step": 16628 }, { "epoch": 0.9091542798564839, "grad_norm": 3.374626874923706, "learning_rate": 2.1521801463097846e-06, "loss": 1.0327, "step": 16629 }, { "epoch": 0.9092089526738425, "grad_norm": 2.8690433502197266, "learning_rate": 2.149611316190081e-06, "loss": 1.1985, "step": 16630 }, { "epoch": 0.9092636254912011, "grad_norm": 2.341163396835327, "learning_rate": 2.1470439863771343e-06, "loss": 0.9838, "step": 16631 }, { "epoch": 0.9093182983085597, "grad_norm": 2.6769497394561768, "learning_rate": 2.1444781569514407e-06, "loss": 0.8757, "step": 16632 }, { "epoch": 0.9093729711259183, "grad_norm": 2.7439236640930176, "learning_rate": 2.1419138279934414e-06, "loss": 1.0034, "step": 16633 }, { "epoch": 0.9094276439432769, "grad_norm": 2.210969924926758, "learning_rate": 2.1393509995835447e-06, "loss": 0.9256, "step": 16634 }, { "epoch": 0.9094823167606356, "grad_norm": 3.008422613143921, "learning_rate": 2.136789671802103e-06, "loss": 0.9313, "step": 16635 }, { "epoch": 0.9095369895779942, "grad_norm": 2.6598923206329346, "learning_rate": 2.1342298447294297e-06, "loss": 1.052, "step": 16636 }, { "epoch": 0.9095916623953528, "grad_norm": 2.585949659347534, "learning_rate": 2.1316715184457825e-06, "loss": 0.9923, "step": 16637 }, { "epoch": 0.9096463352127114, "grad_norm": 2.4771199226379395, "learning_rate": 2.1291146930313753e-06, "loss": 1.1211, "step": 16638 }, { "epoch": 0.90970100803007, "grad_norm": 2.850550413131714, "learning_rate": 2.1265593685663666e-06, "loss": 1.0638, "step": 16639 }, { "epoch": 0.9097556808474286, "grad_norm": 2.381523370742798, "learning_rate": 2.124005545130897e-06, "loss": 1.0189, "step": 16640 }, { "epoch": 0.9098103536647872, "grad_norm": 2.155970335006714, "learning_rate": 2.1214532228050255e-06, "loss": 0.9105, "step": 16641 }, { "epoch": 0.909865026482146, "grad_norm": 2.2748191356658936, "learning_rate": 2.1189024016687764e-06, "loss": 0.9234, "step": 16642 }, { "epoch": 0.9099196992995046, "grad_norm": 2.3652055263519287, "learning_rate": 2.116353081802136e-06, "loss": 0.9151, "step": 16643 }, { "epoch": 0.9099743721168632, "grad_norm": 2.1441593170166016, "learning_rate": 2.1138052632850293e-06, "loss": 0.9442, "step": 16644 }, { "epoch": 0.9100290449342218, "grad_norm": 2.931434392929077, "learning_rate": 2.1112589461973476e-06, "loss": 0.9609, "step": 16645 }, { "epoch": 0.9100837177515804, "grad_norm": 3.1156086921691895, "learning_rate": 2.108714130618916e-06, "loss": 1.0086, "step": 16646 }, { "epoch": 0.910138390568939, "grad_norm": 2.9878737926483154, "learning_rate": 2.1061708166295435e-06, "loss": 1.0743, "step": 16647 }, { "epoch": 0.9101930633862976, "grad_norm": 2.9165024757385254, "learning_rate": 2.1036290043089547e-06, "loss": 1.0121, "step": 16648 }, { "epoch": 0.9102477362036563, "grad_norm": 2.202331066131592, "learning_rate": 2.1010886937368522e-06, "loss": 0.9106, "step": 16649 }, { "epoch": 0.9103024090210149, "grad_norm": 2.5893678665161133, "learning_rate": 2.0985498849928954e-06, "loss": 1.0169, "step": 16650 }, { "epoch": 0.9103570818383735, "grad_norm": 2.3629775047302246, "learning_rate": 2.0960125781566753e-06, "loss": 0.994, "step": 16651 }, { "epoch": 0.9104117546557321, "grad_norm": 2.381737470626831, "learning_rate": 2.0934767733077566e-06, "loss": 1.0045, "step": 16652 }, { "epoch": 0.9104664274730907, "grad_norm": 2.0148990154266357, "learning_rate": 2.0909424705256363e-06, "loss": 0.8115, "step": 16653 }, { "epoch": 0.9105211002904493, "grad_norm": 2.2408363819122314, "learning_rate": 2.0884096698897793e-06, "loss": 0.905, "step": 16654 }, { "epoch": 0.9105757731078079, "grad_norm": 2.3002614974975586, "learning_rate": 2.085878371479599e-06, "loss": 1.1311, "step": 16655 }, { "epoch": 0.9106304459251666, "grad_norm": 2.408531904220581, "learning_rate": 2.0833485753744607e-06, "loss": 1.0435, "step": 16656 }, { "epoch": 0.9106851187425252, "grad_norm": 3.7874293327331543, "learning_rate": 2.0808202816536895e-06, "loss": 1.1028, "step": 16657 }, { "epoch": 0.9107397915598838, "grad_norm": 2.70143723487854, "learning_rate": 2.0782934903965545e-06, "loss": 1.078, "step": 16658 }, { "epoch": 0.9107944643772424, "grad_norm": 2.737203359603882, "learning_rate": 2.0757682016822764e-06, "loss": 0.9929, "step": 16659 }, { "epoch": 0.910849137194601, "grad_norm": 2.490816593170166, "learning_rate": 2.073244415590042e-06, "loss": 1.0609, "step": 16660 }, { "epoch": 0.9109038100119596, "grad_norm": 2.826030969619751, "learning_rate": 2.0707221321989767e-06, "loss": 0.9556, "step": 16661 }, { "epoch": 0.9109584828293184, "grad_norm": 2.5852408409118652, "learning_rate": 2.0682013515881673e-06, "loss": 1.0616, "step": 16662 }, { "epoch": 0.911013155646677, "grad_norm": 2.839735507965088, "learning_rate": 2.06568207383665e-06, "loss": 0.8774, "step": 16663 }, { "epoch": 0.9110678284640356, "grad_norm": 2.552722454071045, "learning_rate": 2.063164299023412e-06, "loss": 1.0668, "step": 16664 }, { "epoch": 0.9111225012813942, "grad_norm": 2.5884346961975098, "learning_rate": 2.0606480272273966e-06, "loss": 1.0732, "step": 16665 }, { "epoch": 0.9111771740987528, "grad_norm": 2.998614549636841, "learning_rate": 2.058133258527506e-06, "loss": 1.0378, "step": 16666 }, { "epoch": 0.9112318469161114, "grad_norm": 1.9915889501571655, "learning_rate": 2.055619993002578e-06, "loss": 0.7832, "step": 16667 }, { "epoch": 0.91128651973347, "grad_norm": 2.8839876651763916, "learning_rate": 2.0531082307314154e-06, "loss": 1.0219, "step": 16668 }, { "epoch": 0.9113411925508287, "grad_norm": 2.5296099185943604, "learning_rate": 2.0505979717927782e-06, "loss": 1.1179, "step": 16669 }, { "epoch": 0.9113958653681873, "grad_norm": 2.5823686122894287, "learning_rate": 2.048089216265375e-06, "loss": 0.8316, "step": 16670 }, { "epoch": 0.9114505381855459, "grad_norm": 2.724155902862549, "learning_rate": 2.0455819642278605e-06, "loss": 1.1398, "step": 16671 }, { "epoch": 0.9115052110029045, "grad_norm": 3.322201728820801, "learning_rate": 2.043076215758849e-06, "loss": 1.1706, "step": 16672 }, { "epoch": 0.9115598838202631, "grad_norm": 2.5181326866149902, "learning_rate": 2.0405719709369054e-06, "loss": 0.8888, "step": 16673 }, { "epoch": 0.9116145566376217, "grad_norm": 3.404221773147583, "learning_rate": 2.0380692298405448e-06, "loss": 1.2147, "step": 16674 }, { "epoch": 0.9116692294549803, "grad_norm": 2.6092724800109863, "learning_rate": 2.035567992548243e-06, "loss": 1.0106, "step": 16675 }, { "epoch": 0.911723902272339, "grad_norm": 2.8942577838897705, "learning_rate": 2.0330682591384266e-06, "loss": 1.1513, "step": 16676 }, { "epoch": 0.9117785750896976, "grad_norm": 2.382296085357666, "learning_rate": 2.030570029689466e-06, "loss": 0.9608, "step": 16677 }, { "epoch": 0.9118332479070562, "grad_norm": 3.2130942344665527, "learning_rate": 2.028073304279687e-06, "loss": 0.9801, "step": 16678 }, { "epoch": 0.9118879207244148, "grad_norm": 2.3939127922058105, "learning_rate": 2.0255780829873893e-06, "loss": 1.0036, "step": 16679 }, { "epoch": 0.9119425935417734, "grad_norm": 2.430140495300293, "learning_rate": 2.023084365890793e-06, "loss": 1.0289, "step": 16680 }, { "epoch": 0.911997266359132, "grad_norm": 4.1274895668029785, "learning_rate": 2.0205921530680904e-06, "loss": 1.1623, "step": 16681 }, { "epoch": 0.9120519391764906, "grad_norm": 2.834782838821411, "learning_rate": 2.018101444597431e-06, "loss": 0.9672, "step": 16682 }, { "epoch": 0.9121066119938493, "grad_norm": 2.4263970851898193, "learning_rate": 2.015612240556897e-06, "loss": 1.0465, "step": 16683 }, { "epoch": 0.912161284811208, "grad_norm": 2.563267707824707, "learning_rate": 2.013124541024536e-06, "loss": 0.9506, "step": 16684 }, { "epoch": 0.9122159576285666, "grad_norm": 2.5247139930725098, "learning_rate": 2.0106383460783584e-06, "loss": 1.1005, "step": 16685 }, { "epoch": 0.9122706304459252, "grad_norm": 2.4744536876678467, "learning_rate": 2.0081536557963023e-06, "loss": 0.8802, "step": 16686 }, { "epoch": 0.9123253032632838, "grad_norm": 2.4674429893493652, "learning_rate": 2.005670470256288e-06, "loss": 1.0337, "step": 16687 }, { "epoch": 0.9123799760806424, "grad_norm": 2.3184549808502197, "learning_rate": 2.0031887895361533e-06, "loss": 0.8926, "step": 16688 }, { "epoch": 0.9124346488980011, "grad_norm": 2.488689661026001, "learning_rate": 2.000708613713731e-06, "loss": 1.1057, "step": 16689 }, { "epoch": 0.9124893217153597, "grad_norm": 2.908812999725342, "learning_rate": 1.998229942866775e-06, "loss": 1.087, "step": 16690 }, { "epoch": 0.9125439945327183, "grad_norm": 2.8803822994232178, "learning_rate": 1.9957527770730012e-06, "loss": 1.1877, "step": 16691 }, { "epoch": 0.9125986673500769, "grad_norm": 2.7352941036224365, "learning_rate": 1.9932771164100805e-06, "loss": 1.1989, "step": 16692 }, { "epoch": 0.9126533401674355, "grad_norm": 3.0134427547454834, "learning_rate": 1.9908029609556346e-06, "loss": 1.2537, "step": 16693 }, { "epoch": 0.9127080129847941, "grad_norm": 2.605121374130249, "learning_rate": 1.9883303107872398e-06, "loss": 1.0747, "step": 16694 }, { "epoch": 0.9127626858021527, "grad_norm": 2.5369536876678467, "learning_rate": 1.9858591659824175e-06, "loss": 1.0377, "step": 16695 }, { "epoch": 0.9128173586195114, "grad_norm": 2.8146326541900635, "learning_rate": 1.983389526618662e-06, "loss": 0.832, "step": 16696 }, { "epoch": 0.91287203143687, "grad_norm": 2.6993305683135986, "learning_rate": 1.980921392773388e-06, "loss": 0.9921, "step": 16697 }, { "epoch": 0.9129267042542286, "grad_norm": 1.946448802947998, "learning_rate": 1.9784547645239958e-06, "loss": 0.8582, "step": 16698 }, { "epoch": 0.9129813770715872, "grad_norm": 2.4021761417388916, "learning_rate": 1.9759896419478174e-06, "loss": 0.9913, "step": 16699 }, { "epoch": 0.9130360498889458, "grad_norm": 2.5998518466949463, "learning_rate": 1.973526025122152e-06, "loss": 0.9179, "step": 16700 }, { "epoch": 0.9130907227063044, "grad_norm": 3.124152183532715, "learning_rate": 1.9710639141242384e-06, "loss": 1.0474, "step": 16701 }, { "epoch": 0.913145395523663, "grad_norm": 5.454051971435547, "learning_rate": 1.968603309031275e-06, "loss": 1.0018, "step": 16702 }, { "epoch": 0.9132000683410217, "grad_norm": 2.625622510910034, "learning_rate": 1.966144209920412e-06, "loss": 0.9365, "step": 16703 }, { "epoch": 0.9132547411583803, "grad_norm": 2.721863269805908, "learning_rate": 1.963686616868754e-06, "loss": 1.0084, "step": 16704 }, { "epoch": 0.913309413975739, "grad_norm": 2.66146183013916, "learning_rate": 1.9612305299533505e-06, "loss": 1.0623, "step": 16705 }, { "epoch": 0.9133640867930976, "grad_norm": 2.828486204147339, "learning_rate": 1.958775949251218e-06, "loss": 1.0508, "step": 16706 }, { "epoch": 0.9134187596104562, "grad_norm": 2.132155418395996, "learning_rate": 1.9563228748393114e-06, "loss": 0.6672, "step": 16707 }, { "epoch": 0.9134734324278148, "grad_norm": 2.6548337936401367, "learning_rate": 1.953871306794547e-06, "loss": 0.7635, "step": 16708 }, { "epoch": 0.9135281052451734, "grad_norm": 2.557779312133789, "learning_rate": 1.9514212451937964e-06, "loss": 1.1042, "step": 16709 }, { "epoch": 0.9135827780625321, "grad_norm": 2.4992520809173584, "learning_rate": 1.948972690113865e-06, "loss": 1.0142, "step": 16710 }, { "epoch": 0.9136374508798907, "grad_norm": 3.00065541267395, "learning_rate": 1.9465256416315415e-06, "loss": 1.0362, "step": 16711 }, { "epoch": 0.9136921236972493, "grad_norm": 2.2351267337799072, "learning_rate": 1.944080099823542e-06, "loss": 0.9831, "step": 16712 }, { "epoch": 0.9137467965146079, "grad_norm": 3.6075782775878906, "learning_rate": 1.9416360647665497e-06, "loss": 1.1228, "step": 16713 }, { "epoch": 0.9138014693319665, "grad_norm": 2.903218984603882, "learning_rate": 1.9391935365371873e-06, "loss": 0.9122, "step": 16714 }, { "epoch": 0.9138561421493251, "grad_norm": 2.9949183464050293, "learning_rate": 1.936752515212048e-06, "loss": 0.9637, "step": 16715 }, { "epoch": 0.9139108149666838, "grad_norm": 2.9267258644104004, "learning_rate": 1.9343130008676603e-06, "loss": 1.0535, "step": 16716 }, { "epoch": 0.9139654877840424, "grad_norm": 3.167529582977295, "learning_rate": 1.9318749935805127e-06, "loss": 0.9967, "step": 16717 }, { "epoch": 0.914020160601401, "grad_norm": 2.4041554927825928, "learning_rate": 1.929438493427055e-06, "loss": 0.8883, "step": 16718 }, { "epoch": 0.9140748334187596, "grad_norm": 4.999693393707275, "learning_rate": 1.9270035004836706e-06, "loss": 1.2024, "step": 16719 }, { "epoch": 0.9141295062361182, "grad_norm": 1.999392032623291, "learning_rate": 1.924570014826715e-06, "loss": 0.9166, "step": 16720 }, { "epoch": 0.9141841790534768, "grad_norm": 3.0468428134918213, "learning_rate": 1.9221380365324836e-06, "loss": 0.9166, "step": 16721 }, { "epoch": 0.9142388518708354, "grad_norm": 2.5325801372528076, "learning_rate": 1.9197075656772255e-06, "loss": 0.9382, "step": 16722 }, { "epoch": 0.9142935246881941, "grad_norm": 3.11169171333313, "learning_rate": 1.9172786023371525e-06, "loss": 0.9452, "step": 16723 }, { "epoch": 0.9143481975055527, "grad_norm": 2.1921608448028564, "learning_rate": 1.91485114658842e-06, "loss": 0.95, "step": 16724 }, { "epoch": 0.9144028703229113, "grad_norm": 3.0533297061920166, "learning_rate": 1.912425198507145e-06, "loss": 1.1026, "step": 16725 }, { "epoch": 0.91445754314027, "grad_norm": 2.3868587017059326, "learning_rate": 1.9100007581693836e-06, "loss": 0.927, "step": 16726 }, { "epoch": 0.9145122159576285, "grad_norm": 2.151886224746704, "learning_rate": 1.9075778256511524e-06, "loss": 0.8227, "step": 16727 }, { "epoch": 0.9145668887749872, "grad_norm": 2.477663278579712, "learning_rate": 1.905156401028424e-06, "loss": 1.1606, "step": 16728 }, { "epoch": 0.9146215615923458, "grad_norm": 2.1172115802764893, "learning_rate": 1.9027364843771156e-06, "loss": 0.8663, "step": 16729 }, { "epoch": 0.9146762344097045, "grad_norm": 2.773411512374878, "learning_rate": 1.9003180757731055e-06, "loss": 1.0024, "step": 16730 }, { "epoch": 0.9147309072270631, "grad_norm": 2.7547144889831543, "learning_rate": 1.897901175292216e-06, "loss": 1.0895, "step": 16731 }, { "epoch": 0.9147855800444217, "grad_norm": 2.1652612686157227, "learning_rate": 1.8954857830102312e-06, "loss": 0.9811, "step": 16732 }, { "epoch": 0.9148402528617803, "grad_norm": 3.3589141368865967, "learning_rate": 1.8930718990028852e-06, "loss": 0.7079, "step": 16733 }, { "epoch": 0.9148949256791389, "grad_norm": 2.215379238128662, "learning_rate": 1.8906595233458558e-06, "loss": 0.7784, "step": 16734 }, { "epoch": 0.9149495984964975, "grad_norm": 2.2278852462768555, "learning_rate": 1.8882486561147883e-06, "loss": 0.8976, "step": 16735 }, { "epoch": 0.9150042713138561, "grad_norm": 2.3133394718170166, "learning_rate": 1.8858392973852612e-06, "loss": 1.027, "step": 16736 }, { "epoch": 0.9150589441312148, "grad_norm": 3.7211947441101074, "learning_rate": 1.8834314472328363e-06, "loss": 0.8846, "step": 16737 }, { "epoch": 0.9151136169485734, "grad_norm": 3.339132070541382, "learning_rate": 1.8810251057329975e-06, "loss": 1.046, "step": 16738 }, { "epoch": 0.915168289765932, "grad_norm": 2.3297650814056396, "learning_rate": 1.8786202729612013e-06, "loss": 0.9252, "step": 16739 }, { "epoch": 0.9152229625832906, "grad_norm": 2.371283769607544, "learning_rate": 1.8762169489928427e-06, "loss": 1.0486, "step": 16740 }, { "epoch": 0.9152776354006492, "grad_norm": 2.0346429347991943, "learning_rate": 1.8738151339032729e-06, "loss": 0.9868, "step": 16741 }, { "epoch": 0.9153323082180078, "grad_norm": 2.890510082244873, "learning_rate": 1.8714148277678035e-06, "loss": 1.1857, "step": 16742 }, { "epoch": 0.9153869810353665, "grad_norm": 2.3987183570861816, "learning_rate": 1.8690160306616966e-06, "loss": 0.994, "step": 16743 }, { "epoch": 0.9154416538527251, "grad_norm": 2.5261456966400146, "learning_rate": 1.8666187426601644e-06, "loss": 0.9872, "step": 16744 }, { "epoch": 0.9154963266700837, "grad_norm": 2.5524816513061523, "learning_rate": 1.8642229638383634e-06, "loss": 1.0432, "step": 16745 }, { "epoch": 0.9155509994874423, "grad_norm": 2.681601047515869, "learning_rate": 1.861828694271417e-06, "loss": 1.014, "step": 16746 }, { "epoch": 0.9156056723048009, "grad_norm": 2.5951433181762695, "learning_rate": 1.859435934034387e-06, "loss": 0.9673, "step": 16747 }, { "epoch": 0.9156603451221595, "grad_norm": 2.420497179031372, "learning_rate": 1.8570446832023136e-06, "loss": 0.9863, "step": 16748 }, { "epoch": 0.9157150179395181, "grad_norm": 2.6282949447631836, "learning_rate": 1.854654941850159e-06, "loss": 1.1351, "step": 16749 }, { "epoch": 0.9157696907568769, "grad_norm": 2.1242711544036865, "learning_rate": 1.8522667100528635e-06, "loss": 0.9523, "step": 16750 }, { "epoch": 0.9158243635742355, "grad_norm": 2.1903696060180664, "learning_rate": 1.849879987885289e-06, "loss": 1.0238, "step": 16751 }, { "epoch": 0.9158790363915941, "grad_norm": 2.95660400390625, "learning_rate": 1.847494775422287e-06, "loss": 1.1579, "step": 16752 }, { "epoch": 0.9159337092089527, "grad_norm": 2.9141845703125, "learning_rate": 1.8451110727386367e-06, "loss": 1.0041, "step": 16753 }, { "epoch": 0.9159883820263113, "grad_norm": 3.8282155990600586, "learning_rate": 1.8427288799090726e-06, "loss": 0.9618, "step": 16754 }, { "epoch": 0.9160430548436699, "grad_norm": 3.116485834121704, "learning_rate": 1.8403481970082959e-06, "loss": 0.9702, "step": 16755 }, { "epoch": 0.9160977276610285, "grad_norm": 2.12052583694458, "learning_rate": 1.8379690241109415e-06, "loss": 0.9078, "step": 16756 }, { "epoch": 0.9161524004783872, "grad_norm": 2.6875951290130615, "learning_rate": 1.8355913612916054e-06, "loss": 0.969, "step": 16757 }, { "epoch": 0.9162070732957458, "grad_norm": 3.216047525405884, "learning_rate": 1.8332152086248443e-06, "loss": 1.0437, "step": 16758 }, { "epoch": 0.9162617461131044, "grad_norm": 2.445582389831543, "learning_rate": 1.8308405661851602e-06, "loss": 0.9063, "step": 16759 }, { "epoch": 0.916316418930463, "grad_norm": 3.648965358734131, "learning_rate": 1.8284674340470099e-06, "loss": 1.0748, "step": 16760 }, { "epoch": 0.9163710917478216, "grad_norm": 2.6254305839538574, "learning_rate": 1.826095812284795e-06, "loss": 0.9612, "step": 16761 }, { "epoch": 0.9164257645651802, "grad_norm": 2.571743965148926, "learning_rate": 1.8237257009728725e-06, "loss": 0.8289, "step": 16762 }, { "epoch": 0.9164804373825388, "grad_norm": 4.076217174530029, "learning_rate": 1.821357100185561e-06, "loss": 0.8976, "step": 16763 }, { "epoch": 0.9165351101998975, "grad_norm": 2.1974687576293945, "learning_rate": 1.818990009997129e-06, "loss": 1.0774, "step": 16764 }, { "epoch": 0.9165897830172561, "grad_norm": 3.062225103378296, "learning_rate": 1.8166244304817892e-06, "loss": 1.1139, "step": 16765 }, { "epoch": 0.9166444558346147, "grad_norm": 2.6201391220092773, "learning_rate": 1.8142603617137155e-06, "loss": 0.987, "step": 16766 }, { "epoch": 0.9166991286519733, "grad_norm": 2.6775503158569336, "learning_rate": 1.8118978037670154e-06, "loss": 0.8191, "step": 16767 }, { "epoch": 0.9167538014693319, "grad_norm": 2.401940107345581, "learning_rate": 1.8095367567157906e-06, "loss": 0.8007, "step": 16768 }, { "epoch": 0.9168084742866905, "grad_norm": 2.486644744873047, "learning_rate": 1.8071772206340598e-06, "loss": 0.9943, "step": 16769 }, { "epoch": 0.9168631471040493, "grad_norm": 2.5025222301483154, "learning_rate": 1.8048191955957972e-06, "loss": 0.9361, "step": 16770 }, { "epoch": 0.9169178199214079, "grad_norm": 2.808487892150879, "learning_rate": 1.8024626816749435e-06, "loss": 1.0603, "step": 16771 }, { "epoch": 0.9169724927387665, "grad_norm": 2.4554860591888428, "learning_rate": 1.8001076789453786e-06, "loss": 1.3122, "step": 16772 }, { "epoch": 0.9170271655561251, "grad_norm": 2.914619207382202, "learning_rate": 1.7977541874809545e-06, "loss": 0.9825, "step": 16773 }, { "epoch": 0.9170818383734837, "grad_norm": 2.588094711303711, "learning_rate": 1.7954022073554456e-06, "loss": 1.0627, "step": 16774 }, { "epoch": 0.9171365111908423, "grad_norm": 3.3075480461120605, "learning_rate": 1.7930517386426093e-06, "loss": 1.0215, "step": 16775 }, { "epoch": 0.9171911840082009, "grad_norm": 2.032345771789551, "learning_rate": 1.7907027814161315e-06, "loss": 0.9956, "step": 16776 }, { "epoch": 0.9172458568255596, "grad_norm": 2.7259397506713867, "learning_rate": 1.7883553357496752e-06, "loss": 1.1551, "step": 16777 }, { "epoch": 0.9173005296429182, "grad_norm": 2.4234542846679688, "learning_rate": 1.7860094017168315e-06, "loss": 1.0399, "step": 16778 }, { "epoch": 0.9173552024602768, "grad_norm": 3.4243650436401367, "learning_rate": 1.7836649793911641e-06, "loss": 1.0993, "step": 16779 }, { "epoch": 0.9174098752776354, "grad_norm": 3.1887824535369873, "learning_rate": 1.7813220688461696e-06, "loss": 1.0182, "step": 16780 }, { "epoch": 0.917464548094994, "grad_norm": 2.737532377243042, "learning_rate": 1.7789806701553168e-06, "loss": 1.0589, "step": 16781 }, { "epoch": 0.9175192209123526, "grad_norm": 2.8281564712524414, "learning_rate": 1.7766407833920196e-06, "loss": 1.0954, "step": 16782 }, { "epoch": 0.9175738937297112, "grad_norm": 2.0942485332489014, "learning_rate": 1.77430240862963e-06, "loss": 0.9265, "step": 16783 }, { "epoch": 0.9176285665470699, "grad_norm": 2.3274805545806885, "learning_rate": 1.7719655459414786e-06, "loss": 0.8901, "step": 16784 }, { "epoch": 0.9176832393644285, "grad_norm": 3.8536338806152344, "learning_rate": 1.7696301954008343e-06, "loss": 1.1184, "step": 16785 }, { "epoch": 0.9177379121817871, "grad_norm": 2.9184231758117676, "learning_rate": 1.7672963570809054e-06, "loss": 1.1563, "step": 16786 }, { "epoch": 0.9177925849991457, "grad_norm": 3.2758285999298096, "learning_rate": 1.7649640310548887e-06, "loss": 1.0626, "step": 16787 }, { "epoch": 0.9178472578165043, "grad_norm": 3.5600264072418213, "learning_rate": 1.762633217395898e-06, "loss": 0.9483, "step": 16788 }, { "epoch": 0.9179019306338629, "grad_norm": 4.672057151794434, "learning_rate": 1.7603039161770196e-06, "loss": 1.3114, "step": 16789 }, { "epoch": 0.9179566034512215, "grad_norm": 3.262105941772461, "learning_rate": 1.7579761274712837e-06, "loss": 1.1424, "step": 16790 }, { "epoch": 0.9180112762685803, "grad_norm": 2.6132149696350098, "learning_rate": 1.7556498513516818e-06, "loss": 1.0159, "step": 16791 }, { "epoch": 0.9180659490859389, "grad_norm": 2.7761125564575195, "learning_rate": 1.7533250878911444e-06, "loss": 1.0115, "step": 16792 }, { "epoch": 0.9181206219032975, "grad_norm": 2.6476573944091797, "learning_rate": 1.7510018371625692e-06, "loss": 0.7618, "step": 16793 }, { "epoch": 0.9181752947206561, "grad_norm": 2.722985029220581, "learning_rate": 1.7486800992387974e-06, "loss": 0.9619, "step": 16794 }, { "epoch": 0.9182299675380147, "grad_norm": 2.479212999343872, "learning_rate": 1.7463598741926213e-06, "loss": 1.0817, "step": 16795 }, { "epoch": 0.9182846403553733, "grad_norm": 2.1669962406158447, "learning_rate": 1.7440411620967879e-06, "loss": 0.9095, "step": 16796 }, { "epoch": 0.918339313172732, "grad_norm": 2.703583002090454, "learning_rate": 1.7417239630240057e-06, "loss": 0.9608, "step": 16797 }, { "epoch": 0.9183939859900906, "grad_norm": 2.8211565017700195, "learning_rate": 1.7394082770469333e-06, "loss": 1.0554, "step": 16798 }, { "epoch": 0.9184486588074492, "grad_norm": 3.203737497329712, "learning_rate": 1.7370941042381629e-06, "loss": 0.8394, "step": 16799 }, { "epoch": 0.9185033316248078, "grad_norm": 4.365339279174805, "learning_rate": 1.7347814446702581e-06, "loss": 1.1619, "step": 16800 }, { "epoch": 0.9185580044421664, "grad_norm": 2.701162576675415, "learning_rate": 1.7324702984157392e-06, "loss": 1.1366, "step": 16801 }, { "epoch": 0.918612677259525, "grad_norm": 2.421649217605591, "learning_rate": 1.7301606655470593e-06, "loss": 1.1389, "step": 16802 }, { "epoch": 0.9186673500768836, "grad_norm": 2.5163214206695557, "learning_rate": 1.7278525461366379e-06, "loss": 1.0741, "step": 16803 }, { "epoch": 0.9187220228942423, "grad_norm": 2.86824369430542, "learning_rate": 1.7255459402568452e-06, "loss": 0.897, "step": 16804 }, { "epoch": 0.9187766957116009, "grad_norm": 2.0049352645874023, "learning_rate": 1.7232408479800012e-06, "loss": 0.8946, "step": 16805 }, { "epoch": 0.9188313685289595, "grad_norm": 2.2603180408477783, "learning_rate": 1.7209372693783754e-06, "loss": 0.9357, "step": 16806 }, { "epoch": 0.9188860413463181, "grad_norm": 2.325805902481079, "learning_rate": 1.718635204524205e-06, "loss": 0.8995, "step": 16807 }, { "epoch": 0.9189407141636767, "grad_norm": 2.5699987411499023, "learning_rate": 1.716334653489665e-06, "loss": 1.1358, "step": 16808 }, { "epoch": 0.9189953869810353, "grad_norm": 3.1059188842773438, "learning_rate": 1.7140356163468929e-06, "loss": 0.9804, "step": 16809 }, { "epoch": 0.9190500597983939, "grad_norm": 2.5889687538146973, "learning_rate": 1.7117380931679582e-06, "loss": 1.1305, "step": 16810 }, { "epoch": 0.9191047326157527, "grad_norm": 2.574828863143921, "learning_rate": 1.7094420840249092e-06, "loss": 0.9469, "step": 16811 }, { "epoch": 0.9191594054331113, "grad_norm": 3.41473388671875, "learning_rate": 1.7071475889897326e-06, "loss": 0.9587, "step": 16812 }, { "epoch": 0.9192140782504699, "grad_norm": 2.3593385219573975, "learning_rate": 1.7048546081343708e-06, "loss": 0.9086, "step": 16813 }, { "epoch": 0.9192687510678285, "grad_norm": 2.774308443069458, "learning_rate": 1.7025631415307164e-06, "loss": 1.1154, "step": 16814 }, { "epoch": 0.9193234238851871, "grad_norm": 2.4186511039733887, "learning_rate": 1.7002731892506175e-06, "loss": 1.0236, "step": 16815 }, { "epoch": 0.9193780967025457, "grad_norm": 3.145481824874878, "learning_rate": 1.6979847513658665e-06, "loss": 1.0457, "step": 16816 }, { "epoch": 0.9194327695199043, "grad_norm": 2.381655693054199, "learning_rate": 1.6956978279482284e-06, "loss": 0.8261, "step": 16817 }, { "epoch": 0.919487442337263, "grad_norm": 2.843719959259033, "learning_rate": 1.6934124190694012e-06, "loss": 0.8568, "step": 16818 }, { "epoch": 0.9195421151546216, "grad_norm": 2.3585686683654785, "learning_rate": 1.6911285248010445e-06, "loss": 1.0231, "step": 16819 }, { "epoch": 0.9195967879719802, "grad_norm": 3.082458734512329, "learning_rate": 1.6888461452147618e-06, "loss": 1.2266, "step": 16820 }, { "epoch": 0.9196514607893388, "grad_norm": 2.9452383518218994, "learning_rate": 1.6865652803821185e-06, "loss": 1.0108, "step": 16821 }, { "epoch": 0.9197061336066974, "grad_norm": 2.6501948833465576, "learning_rate": 1.6842859303746294e-06, "loss": 0.8568, "step": 16822 }, { "epoch": 0.919760806424056, "grad_norm": 2.3525230884552, "learning_rate": 1.6820080952637652e-06, "loss": 0.926, "step": 16823 }, { "epoch": 0.9198154792414147, "grad_norm": 2.1576709747314453, "learning_rate": 1.6797317751209408e-06, "loss": 0.9635, "step": 16824 }, { "epoch": 0.9198701520587733, "grad_norm": 2.5095348358154297, "learning_rate": 1.6774569700175213e-06, "loss": 1.1497, "step": 16825 }, { "epoch": 0.9199248248761319, "grad_norm": 2.4950969219207764, "learning_rate": 1.6751836800248445e-06, "loss": 0.9236, "step": 16826 }, { "epoch": 0.9199794976934905, "grad_norm": 2.5228519439697266, "learning_rate": 1.6729119052141805e-06, "loss": 1.0855, "step": 16827 }, { "epoch": 0.9200341705108491, "grad_norm": 2.666839599609375, "learning_rate": 1.670641645656762e-06, "loss": 1.0569, "step": 16828 }, { "epoch": 0.9200888433282077, "grad_norm": 4.898153781890869, "learning_rate": 1.6683729014237647e-06, "loss": 1.0963, "step": 16829 }, { "epoch": 0.9201435161455663, "grad_norm": 2.5004193782806396, "learning_rate": 1.6661056725863321e-06, "loss": 0.9544, "step": 16830 }, { "epoch": 0.920198188962925, "grad_norm": 2.9629318714141846, "learning_rate": 1.6638399592155462e-06, "loss": 0.8689, "step": 16831 }, { "epoch": 0.9202528617802836, "grad_norm": 2.5158159732818604, "learning_rate": 1.6615757613824444e-06, "loss": 1.1197, "step": 16832 }, { "epoch": 0.9203075345976423, "grad_norm": 2.732330083847046, "learning_rate": 1.659313079158026e-06, "loss": 0.9508, "step": 16833 }, { "epoch": 0.9203622074150009, "grad_norm": 3.4469947814941406, "learning_rate": 1.6570519126132277e-06, "loss": 1.1871, "step": 16834 }, { "epoch": 0.9204168802323595, "grad_norm": 2.3310327529907227, "learning_rate": 1.6547922618189381e-06, "loss": 1.0153, "step": 16835 }, { "epoch": 0.9204715530497181, "grad_norm": 3.2155725955963135, "learning_rate": 1.6525341268460281e-06, "loss": 1.095, "step": 16836 }, { "epoch": 0.9205262258670767, "grad_norm": 2.8005220890045166, "learning_rate": 1.650277507765291e-06, "loss": 0.9486, "step": 16837 }, { "epoch": 0.9205808986844354, "grad_norm": 2.259032964706421, "learning_rate": 1.6480224046474757e-06, "loss": 0.9842, "step": 16838 }, { "epoch": 0.920635571501794, "grad_norm": 2.690160036087036, "learning_rate": 1.6457688175632924e-06, "loss": 1.2608, "step": 16839 }, { "epoch": 0.9206902443191526, "grad_norm": 2.186683177947998, "learning_rate": 1.6435167465834011e-06, "loss": 1.1314, "step": 16840 }, { "epoch": 0.9207449171365112, "grad_norm": 2.2141737937927246, "learning_rate": 1.6412661917784122e-06, "loss": 1.0441, "step": 16841 }, { "epoch": 0.9207995899538698, "grad_norm": 2.6529181003570557, "learning_rate": 1.6390171532188913e-06, "loss": 1.22, "step": 16842 }, { "epoch": 0.9208542627712284, "grad_norm": 2.554278612136841, "learning_rate": 1.6367696309753543e-06, "loss": 0.9922, "step": 16843 }, { "epoch": 0.920908935588587, "grad_norm": 2.0424132347106934, "learning_rate": 1.6345236251182727e-06, "loss": 0.8077, "step": 16844 }, { "epoch": 0.9209636084059457, "grad_norm": 2.813244581222534, "learning_rate": 1.6322791357180568e-06, "loss": 1.0332, "step": 16845 }, { "epoch": 0.9210182812233043, "grad_norm": 2.239320755004883, "learning_rate": 1.630036162845089e-06, "loss": 0.9117, "step": 16846 }, { "epoch": 0.9210729540406629, "grad_norm": 2.6472649574279785, "learning_rate": 1.6277947065697018e-06, "loss": 0.9899, "step": 16847 }, { "epoch": 0.9211276268580215, "grad_norm": 2.6931519508361816, "learning_rate": 1.6255547669621674e-06, "loss": 1.1539, "step": 16848 }, { "epoch": 0.9211822996753801, "grad_norm": 2.2280020713806152, "learning_rate": 1.623316344092718e-06, "loss": 1.0974, "step": 16849 }, { "epoch": 0.9212369724927387, "grad_norm": 2.228660821914673, "learning_rate": 1.6210794380315363e-06, "loss": 0.8686, "step": 16850 }, { "epoch": 0.9212916453100974, "grad_norm": 5.4321675300598145, "learning_rate": 1.618844048848761e-06, "loss": 0.8279, "step": 16851 }, { "epoch": 0.921346318127456, "grad_norm": 4.302646160125732, "learning_rate": 1.6166101766144802e-06, "loss": 1.0482, "step": 16852 }, { "epoch": 0.9214009909448146, "grad_norm": 2.8195273876190186, "learning_rate": 1.6143778213987326e-06, "loss": 1.027, "step": 16853 }, { "epoch": 0.9214556637621732, "grad_norm": 3.111489772796631, "learning_rate": 1.612146983271512e-06, "loss": 0.8453, "step": 16854 }, { "epoch": 0.9215103365795319, "grad_norm": 2.4650940895080566, "learning_rate": 1.6099176623027623e-06, "loss": 0.8523, "step": 16855 }, { "epoch": 0.9215650093968905, "grad_norm": 2.5155131816864014, "learning_rate": 1.607689858562389e-06, "loss": 0.9259, "step": 16856 }, { "epoch": 0.9216196822142491, "grad_norm": 3.3495113849639893, "learning_rate": 1.6054635721202415e-06, "loss": 0.9458, "step": 16857 }, { "epoch": 0.9216743550316078, "grad_norm": 2.420656442642212, "learning_rate": 1.6032388030461144e-06, "loss": 1.1298, "step": 16858 }, { "epoch": 0.9217290278489664, "grad_norm": 3.049285650253296, "learning_rate": 1.6010155514097736e-06, "loss": 0.9713, "step": 16859 }, { "epoch": 0.921783700666325, "grad_norm": 3.0565903186798096, "learning_rate": 1.5987938172809248e-06, "loss": 1.1677, "step": 16860 }, { "epoch": 0.9218383734836836, "grad_norm": 2.146353006362915, "learning_rate": 1.5965736007292232e-06, "loss": 1.0325, "step": 16861 }, { "epoch": 0.9218930463010422, "grad_norm": 2.7949883937835693, "learning_rate": 1.5943549018242909e-06, "loss": 1.0454, "step": 16862 }, { "epoch": 0.9219477191184008, "grad_norm": 2.379478931427002, "learning_rate": 1.5921377206356836e-06, "loss": 1.0345, "step": 16863 }, { "epoch": 0.9220023919357594, "grad_norm": 2.5470807552337646, "learning_rate": 1.5899220572329231e-06, "loss": 1.1659, "step": 16864 }, { "epoch": 0.9220570647531181, "grad_norm": 3.0180044174194336, "learning_rate": 1.5877079116854765e-06, "loss": 1.2171, "step": 16865 }, { "epoch": 0.9221117375704767, "grad_norm": 2.213791608810425, "learning_rate": 1.5854952840627712e-06, "loss": 0.9426, "step": 16866 }, { "epoch": 0.9221664103878353, "grad_norm": 2.736341714859009, "learning_rate": 1.5832841744341854e-06, "loss": 0.9207, "step": 16867 }, { "epoch": 0.9222210832051939, "grad_norm": 3.412487745285034, "learning_rate": 1.5810745828690409e-06, "loss": 1.1977, "step": 16868 }, { "epoch": 0.9222757560225525, "grad_norm": 3.488818645477295, "learning_rate": 1.5788665094366163e-06, "loss": 0.9383, "step": 16869 }, { "epoch": 0.9223304288399111, "grad_norm": 2.5814478397369385, "learning_rate": 1.5766599542061444e-06, "loss": 0.9093, "step": 16870 }, { "epoch": 0.9223851016572697, "grad_norm": 2.648097515106201, "learning_rate": 1.5744549172468093e-06, "loss": 0.8869, "step": 16871 }, { "epoch": 0.9224397744746284, "grad_norm": 2.119018077850342, "learning_rate": 1.5722513986277554e-06, "loss": 1.0731, "step": 16872 }, { "epoch": 0.922494447291987, "grad_norm": 3.2304913997650146, "learning_rate": 1.5700493984180665e-06, "loss": 1.0471, "step": 16873 }, { "epoch": 0.9225491201093456, "grad_norm": 2.917602300643921, "learning_rate": 1.5678489166867816e-06, "loss": 1.1147, "step": 16874 }, { "epoch": 0.9226037929267042, "grad_norm": 2.1043877601623535, "learning_rate": 1.5656499535028902e-06, "loss": 0.8523, "step": 16875 }, { "epoch": 0.9226584657440629, "grad_norm": 2.286072015762329, "learning_rate": 1.5634525089353535e-06, "loss": 0.9837, "step": 16876 }, { "epoch": 0.9227131385614215, "grad_norm": 4.356941223144531, "learning_rate": 1.5612565830530668e-06, "loss": 1.0102, "step": 16877 }, { "epoch": 0.9227678113787802, "grad_norm": 1.8930394649505615, "learning_rate": 1.5590621759248748e-06, "loss": 0.9449, "step": 16878 }, { "epoch": 0.9228224841961388, "grad_norm": 3.002119541168213, "learning_rate": 1.5568692876195834e-06, "loss": 1.1795, "step": 16879 }, { "epoch": 0.9228771570134974, "grad_norm": 2.4273786544799805, "learning_rate": 1.5546779182059546e-06, "loss": 0.9828, "step": 16880 }, { "epoch": 0.922931829830856, "grad_norm": 2.770021915435791, "learning_rate": 1.5524880677526832e-06, "loss": 0.9181, "step": 16881 }, { "epoch": 0.9229865026482146, "grad_norm": 2.2760579586029053, "learning_rate": 1.5502997363284477e-06, "loss": 1.155, "step": 16882 }, { "epoch": 0.9230411754655732, "grad_norm": 3.3869454860687256, "learning_rate": 1.5481129240018433e-06, "loss": 1.0814, "step": 16883 }, { "epoch": 0.9230958482829318, "grad_norm": 3.262737512588501, "learning_rate": 1.5459276308414484e-06, "loss": 0.9526, "step": 16884 }, { "epoch": 0.9231505211002905, "grad_norm": 2.752866744995117, "learning_rate": 1.5437438569157747e-06, "loss": 1.0873, "step": 16885 }, { "epoch": 0.9232051939176491, "grad_norm": 3.406587600708008, "learning_rate": 1.541561602293301e-06, "loss": 0.8726, "step": 16886 }, { "epoch": 0.9232598667350077, "grad_norm": 2.162376880645752, "learning_rate": 1.5393808670424393e-06, "loss": 0.8399, "step": 16887 }, { "epoch": 0.9233145395523663, "grad_norm": 2.706976890563965, "learning_rate": 1.5372016512315678e-06, "loss": 1.0472, "step": 16888 }, { "epoch": 0.9233692123697249, "grad_norm": 3.269510507583618, "learning_rate": 1.5350239549290213e-06, "loss": 1.0564, "step": 16889 }, { "epoch": 0.9234238851870835, "grad_norm": 2.7285211086273193, "learning_rate": 1.532847778203067e-06, "loss": 1.1538, "step": 16890 }, { "epoch": 0.9234785580044421, "grad_norm": 3.653616428375244, "learning_rate": 1.5306731211219505e-06, "loss": 1.1264, "step": 16891 }, { "epoch": 0.9235332308218008, "grad_norm": 3.4097578525543213, "learning_rate": 1.528499983753845e-06, "loss": 0.9616, "step": 16892 }, { "epoch": 0.9235879036391594, "grad_norm": 2.810075521469116, "learning_rate": 1.5263283661668904e-06, "loss": 1.0973, "step": 16893 }, { "epoch": 0.923642576456518, "grad_norm": 2.86784291267395, "learning_rate": 1.5241582684291765e-06, "loss": 0.9229, "step": 16894 }, { "epoch": 0.9236972492738766, "grad_norm": 2.0718653202056885, "learning_rate": 1.5219896906087493e-06, "loss": 0.9132, "step": 16895 }, { "epoch": 0.9237519220912352, "grad_norm": 2.6596627235412598, "learning_rate": 1.5198226327735988e-06, "loss": 1.0231, "step": 16896 }, { "epoch": 0.9238065949085938, "grad_norm": 2.20304274559021, "learning_rate": 1.5176570949916646e-06, "loss": 0.8241, "step": 16897 }, { "epoch": 0.9238612677259525, "grad_norm": 2.655043125152588, "learning_rate": 1.515493077330854e-06, "loss": 1.0495, "step": 16898 }, { "epoch": 0.9239159405433112, "grad_norm": 2.42085337638855, "learning_rate": 1.513330579859018e-06, "loss": 1.0401, "step": 16899 }, { "epoch": 0.9239706133606698, "grad_norm": 2.1143839359283447, "learning_rate": 1.5111696026439582e-06, "loss": 1.0194, "step": 16900 }, { "epoch": 0.9240252861780284, "grad_norm": 2.93992280960083, "learning_rate": 1.5090101457534256e-06, "loss": 0.9502, "step": 16901 }, { "epoch": 0.924079958995387, "grad_norm": 2.6835196018218994, "learning_rate": 1.506852209255133e-06, "loss": 1.0169, "step": 16902 }, { "epoch": 0.9241346318127456, "grad_norm": 3.1684017181396484, "learning_rate": 1.5046957932167427e-06, "loss": 0.9245, "step": 16903 }, { "epoch": 0.9241893046301042, "grad_norm": 2.4150185585021973, "learning_rate": 1.502540897705862e-06, "loss": 1.0607, "step": 16904 }, { "epoch": 0.9242439774474629, "grad_norm": 2.692521810531616, "learning_rate": 1.5003875227900589e-06, "loss": 1.1837, "step": 16905 }, { "epoch": 0.9242986502648215, "grad_norm": 2.509957790374756, "learning_rate": 1.498235668536846e-06, "loss": 1.1146, "step": 16906 }, { "epoch": 0.9243533230821801, "grad_norm": 3.0648467540740967, "learning_rate": 1.4960853350136972e-06, "loss": 1.0721, "step": 16907 }, { "epoch": 0.9244079958995387, "grad_norm": 2.3568105697631836, "learning_rate": 1.4939365222880364e-06, "loss": 0.9688, "step": 16908 }, { "epoch": 0.9244626687168973, "grad_norm": 2.871403217315674, "learning_rate": 1.491789230427232e-06, "loss": 1.226, "step": 16909 }, { "epoch": 0.9245173415342559, "grad_norm": 2.9489402770996094, "learning_rate": 1.4896434594986075e-06, "loss": 1.1977, "step": 16910 }, { "epoch": 0.9245720143516145, "grad_norm": 3.055945634841919, "learning_rate": 1.4874992095694485e-06, "loss": 0.8164, "step": 16911 }, { "epoch": 0.9246266871689732, "grad_norm": 4.45676326751709, "learning_rate": 1.4853564807069897e-06, "loss": 1.1589, "step": 16912 }, { "epoch": 0.9246813599863318, "grad_norm": 2.944713830947876, "learning_rate": 1.4832152729784111e-06, "loss": 1.1036, "step": 16913 }, { "epoch": 0.9247360328036904, "grad_norm": 3.064006805419922, "learning_rate": 1.4810755864508418e-06, "loss": 1.1951, "step": 16914 }, { "epoch": 0.924790705621049, "grad_norm": 3.0109004974365234, "learning_rate": 1.4789374211913787e-06, "loss": 1.0417, "step": 16915 }, { "epoch": 0.9248453784384076, "grad_norm": 2.5614230632781982, "learning_rate": 1.4768007772670567e-06, "loss": 1.0444, "step": 16916 }, { "epoch": 0.9249000512557662, "grad_norm": 2.1957645416259766, "learning_rate": 1.4746656547448668e-06, "loss": 0.8343, "step": 16917 }, { "epoch": 0.9249547240731248, "grad_norm": 2.0938007831573486, "learning_rate": 1.4725320536917608e-06, "loss": 0.8727, "step": 16918 }, { "epoch": 0.9250093968904836, "grad_norm": 2.5221428871154785, "learning_rate": 1.4703999741746299e-06, "loss": 0.951, "step": 16919 }, { "epoch": 0.9250640697078422, "grad_norm": 2.455165147781372, "learning_rate": 1.468269416260326e-06, "loss": 0.9732, "step": 16920 }, { "epoch": 0.9251187425252008, "grad_norm": 2.347118377685547, "learning_rate": 1.4661403800156514e-06, "loss": 1.004, "step": 16921 }, { "epoch": 0.9251734153425594, "grad_norm": 2.641339063644409, "learning_rate": 1.4640128655073582e-06, "loss": 1.0076, "step": 16922 }, { "epoch": 0.925228088159918, "grad_norm": 2.6021335124969482, "learning_rate": 1.4618868728021484e-06, "loss": 0.945, "step": 16923 }, { "epoch": 0.9252827609772766, "grad_norm": 2.455920696258545, "learning_rate": 1.459762401966691e-06, "loss": 0.9568, "step": 16924 }, { "epoch": 0.9253374337946352, "grad_norm": 2.775843858718872, "learning_rate": 1.4576394530675942e-06, "loss": 1.186, "step": 16925 }, { "epoch": 0.9253921066119939, "grad_norm": 4.130113124847412, "learning_rate": 1.4555180261714207e-06, "loss": 1.1473, "step": 16926 }, { "epoch": 0.9254467794293525, "grad_norm": 3.231795072555542, "learning_rate": 1.453398121344679e-06, "loss": 0.9967, "step": 16927 }, { "epoch": 0.9255014522467111, "grad_norm": 2.342599391937256, "learning_rate": 1.4512797386538435e-06, "loss": 1.0765, "step": 16928 }, { "epoch": 0.9255561250640697, "grad_norm": 3.351029396057129, "learning_rate": 1.4491628781653333e-06, "loss": 0.9455, "step": 16929 }, { "epoch": 0.9256107978814283, "grad_norm": 2.8596198558807373, "learning_rate": 1.447047539945523e-06, "loss": 1.0571, "step": 16930 }, { "epoch": 0.9256654706987869, "grad_norm": 2.0455312728881836, "learning_rate": 1.444933724060732e-06, "loss": 0.7637, "step": 16931 }, { "epoch": 0.9257201435161456, "grad_norm": 3.0159237384796143, "learning_rate": 1.4428214305772402e-06, "loss": 1.1424, "step": 16932 }, { "epoch": 0.9257748163335042, "grad_norm": 3.5081756114959717, "learning_rate": 1.4407106595612674e-06, "loss": 1.0856, "step": 16933 }, { "epoch": 0.9258294891508628, "grad_norm": 2.642185926437378, "learning_rate": 1.4386014110790102e-06, "loss": 1.1243, "step": 16934 }, { "epoch": 0.9258841619682214, "grad_norm": 2.7826685905456543, "learning_rate": 1.4364936851965993e-06, "loss": 1.147, "step": 16935 }, { "epoch": 0.92593883478558, "grad_norm": 2.6407089233398438, "learning_rate": 1.4343874819801094e-06, "loss": 1.0499, "step": 16936 }, { "epoch": 0.9259935076029386, "grad_norm": 3.3380286693573, "learning_rate": 1.4322828014955935e-06, "loss": 0.8529, "step": 16937 }, { "epoch": 0.9260481804202972, "grad_norm": 2.6040306091308594, "learning_rate": 1.4301796438090321e-06, "loss": 1.1058, "step": 16938 }, { "epoch": 0.926102853237656, "grad_norm": 3.3008229732513428, "learning_rate": 1.4280780089863665e-06, "loss": 1.0866, "step": 16939 }, { "epoch": 0.9261575260550146, "grad_norm": 2.9168360233306885, "learning_rate": 1.4259778970935001e-06, "loss": 0.936, "step": 16940 }, { "epoch": 0.9262121988723732, "grad_norm": 2.7920501232147217, "learning_rate": 1.4238793081962742e-06, "loss": 0.919, "step": 16941 }, { "epoch": 0.9262668716897318, "grad_norm": 2.750368118286133, "learning_rate": 1.421782242360492e-06, "loss": 1.0866, "step": 16942 }, { "epoch": 0.9263215445070904, "grad_norm": 2.8591630458831787, "learning_rate": 1.4196866996518955e-06, "loss": 0.9365, "step": 16943 }, { "epoch": 0.926376217324449, "grad_norm": 2.588794469833374, "learning_rate": 1.4175926801361984e-06, "loss": 0.9269, "step": 16944 }, { "epoch": 0.9264308901418076, "grad_norm": 2.2746872901916504, "learning_rate": 1.4155001838790537e-06, "loss": 0.8988, "step": 16945 }, { "epoch": 0.9264855629591663, "grad_norm": 3.0474183559417725, "learning_rate": 1.4134092109460706e-06, "loss": 1.1679, "step": 16946 }, { "epoch": 0.9265402357765249, "grad_norm": 3.218024969100952, "learning_rate": 1.4113197614028128e-06, "loss": 1.0383, "step": 16947 }, { "epoch": 0.9265949085938835, "grad_norm": 2.0354268550872803, "learning_rate": 1.4092318353147894e-06, "loss": 0.9089, "step": 16948 }, { "epoch": 0.9266495814112421, "grad_norm": 2.2866804599761963, "learning_rate": 1.4071454327474643e-06, "loss": 0.9248, "step": 16949 }, { "epoch": 0.9267042542286007, "grad_norm": 3.1205809116363525, "learning_rate": 1.4050605537662521e-06, "loss": 1.0333, "step": 16950 }, { "epoch": 0.9267589270459593, "grad_norm": 2.2433366775512695, "learning_rate": 1.4029771984365337e-06, "loss": 0.9319, "step": 16951 }, { "epoch": 0.9268135998633179, "grad_norm": 3.238668441772461, "learning_rate": 1.400895366823618e-06, "loss": 1.0421, "step": 16952 }, { "epoch": 0.9268682726806766, "grad_norm": 3.5608980655670166, "learning_rate": 1.3988150589927807e-06, "loss": 1.1729, "step": 16953 }, { "epoch": 0.9269229454980352, "grad_norm": 2.6531925201416016, "learning_rate": 1.3967362750092584e-06, "loss": 0.9712, "step": 16954 }, { "epoch": 0.9269776183153938, "grad_norm": 2.746852159500122, "learning_rate": 1.3946590149382266e-06, "loss": 0.9091, "step": 16955 }, { "epoch": 0.9270322911327524, "grad_norm": 2.7394728660583496, "learning_rate": 1.3925832788448056e-06, "loss": 0.9497, "step": 16956 }, { "epoch": 0.927086963950111, "grad_norm": 2.63212251663208, "learning_rate": 1.3905090667940878e-06, "loss": 0.8593, "step": 16957 }, { "epoch": 0.9271416367674696, "grad_norm": 3.300147771835327, "learning_rate": 1.3884363788511046e-06, "loss": 1.0774, "step": 16958 }, { "epoch": 0.9271963095848282, "grad_norm": 2.871159791946411, "learning_rate": 1.3863652150808481e-06, "loss": 0.8917, "step": 16959 }, { "epoch": 0.927250982402187, "grad_norm": 2.3679580688476562, "learning_rate": 1.38429557554825e-06, "loss": 0.852, "step": 16960 }, { "epoch": 0.9273056552195456, "grad_norm": 2.398543357849121, "learning_rate": 1.3822274603182084e-06, "loss": 1.0754, "step": 16961 }, { "epoch": 0.9273603280369042, "grad_norm": 2.555055856704712, "learning_rate": 1.3801608694555656e-06, "loss": 1.0348, "step": 16962 }, { "epoch": 0.9274150008542628, "grad_norm": 2.936053991317749, "learning_rate": 1.378095803025109e-06, "loss": 1.173, "step": 16963 }, { "epoch": 0.9274696736716214, "grad_norm": 2.660602331161499, "learning_rate": 1.3760322610916033e-06, "loss": 1.049, "step": 16964 }, { "epoch": 0.92752434648898, "grad_norm": 2.5779078006744385, "learning_rate": 1.3739702437197354e-06, "loss": 0.912, "step": 16965 }, { "epoch": 0.9275790193063387, "grad_norm": 3.172940254211426, "learning_rate": 1.3719097509741706e-06, "loss": 0.9278, "step": 16966 }, { "epoch": 0.9276336921236973, "grad_norm": 3.4430959224700928, "learning_rate": 1.3698507829195017e-06, "loss": 1.247, "step": 16967 }, { "epoch": 0.9276883649410559, "grad_norm": 2.1667838096618652, "learning_rate": 1.3677933396202936e-06, "loss": 1.2177, "step": 16968 }, { "epoch": 0.9277430377584145, "grad_norm": 3.106557607650757, "learning_rate": 1.36573742114105e-06, "loss": 1.0768, "step": 16969 }, { "epoch": 0.9277977105757731, "grad_norm": 3.0681872367858887, "learning_rate": 1.3636830275462364e-06, "loss": 0.956, "step": 16970 }, { "epoch": 0.9278523833931317, "grad_norm": 2.7486743927001953, "learning_rate": 1.3616301589002623e-06, "loss": 1.0284, "step": 16971 }, { "epoch": 0.9279070562104903, "grad_norm": 2.5325050354003906, "learning_rate": 1.3595788152674983e-06, "loss": 1.0869, "step": 16972 }, { "epoch": 0.927961729027849, "grad_norm": 2.2887444496154785, "learning_rate": 1.3575289967122595e-06, "loss": 0.8918, "step": 16973 }, { "epoch": 0.9280164018452076, "grad_norm": 2.9319028854370117, "learning_rate": 1.355480703298817e-06, "loss": 1.0542, "step": 16974 }, { "epoch": 0.9280710746625662, "grad_norm": 3.082676887512207, "learning_rate": 1.3534339350913972e-06, "loss": 1.2368, "step": 16975 }, { "epoch": 0.9281257474799248, "grad_norm": 2.478214740753174, "learning_rate": 1.3513886921541652e-06, "loss": 0.9948, "step": 16976 }, { "epoch": 0.9281804202972834, "grad_norm": 2.5707366466522217, "learning_rate": 1.3493449745512588e-06, "loss": 0.9198, "step": 16977 }, { "epoch": 0.928235093114642, "grad_norm": 2.569633722305298, "learning_rate": 1.3473027823467543e-06, "loss": 1.0793, "step": 16978 }, { "epoch": 0.9282897659320006, "grad_norm": 2.788315534591675, "learning_rate": 1.345262115604673e-06, "loss": 0.9532, "step": 16979 }, { "epoch": 0.9283444387493593, "grad_norm": 3.076545476913452, "learning_rate": 1.3432229743890135e-06, "loss": 1.0141, "step": 16980 }, { "epoch": 0.928399111566718, "grad_norm": 2.206141471862793, "learning_rate": 1.341185358763697e-06, "loss": 1.0962, "step": 16981 }, { "epoch": 0.9284537843840766, "grad_norm": 3.042720317840576, "learning_rate": 1.3391492687926166e-06, "loss": 1.009, "step": 16982 }, { "epoch": 0.9285084572014352, "grad_norm": 2.151797294616699, "learning_rate": 1.337114704539616e-06, "loss": 0.9941, "step": 16983 }, { "epoch": 0.9285631300187938, "grad_norm": 2.8576388359069824, "learning_rate": 1.3350816660684827e-06, "loss": 1.0332, "step": 16984 }, { "epoch": 0.9286178028361524, "grad_norm": 2.295288324356079, "learning_rate": 1.3330501534429662e-06, "loss": 0.9606, "step": 16985 }, { "epoch": 0.928672475653511, "grad_norm": 2.2896902561187744, "learning_rate": 1.3310201667267542e-06, "loss": 0.8021, "step": 16986 }, { "epoch": 0.9287271484708697, "grad_norm": 2.922259569168091, "learning_rate": 1.3289917059835067e-06, "loss": 0.9255, "step": 16987 }, { "epoch": 0.9287818212882283, "grad_norm": 2.0603702068328857, "learning_rate": 1.3269647712768118e-06, "loss": 0.9089, "step": 16988 }, { "epoch": 0.9288364941055869, "grad_norm": 2.8776209354400635, "learning_rate": 1.32493936267023e-06, "loss": 0.8958, "step": 16989 }, { "epoch": 0.9288911669229455, "grad_norm": 2.9455740451812744, "learning_rate": 1.3229154802272603e-06, "loss": 0.8622, "step": 16990 }, { "epoch": 0.9289458397403041, "grad_norm": 2.9431827068328857, "learning_rate": 1.3208931240113686e-06, "loss": 0.9112, "step": 16991 }, { "epoch": 0.9290005125576627, "grad_norm": 2.2545533180236816, "learning_rate": 1.3188722940859544e-06, "loss": 0.889, "step": 16992 }, { "epoch": 0.9290551853750214, "grad_norm": 2.2886157035827637, "learning_rate": 1.3168529905143834e-06, "loss": 0.8027, "step": 16993 }, { "epoch": 0.92910985819238, "grad_norm": 2.760611057281494, "learning_rate": 1.3148352133599717e-06, "loss": 0.8749, "step": 16994 }, { "epoch": 0.9291645310097386, "grad_norm": 2.951977491378784, "learning_rate": 1.3128189626859854e-06, "loss": 0.9114, "step": 16995 }, { "epoch": 0.9292192038270972, "grad_norm": 2.159980535507202, "learning_rate": 1.3108042385556351e-06, "loss": 0.9619, "step": 16996 }, { "epoch": 0.9292738766444558, "grad_norm": 4.93351411819458, "learning_rate": 1.308791041032098e-06, "loss": 1.1922, "step": 16997 }, { "epoch": 0.9293285494618144, "grad_norm": 2.9717421531677246, "learning_rate": 1.3067793701784902e-06, "loss": 1.0025, "step": 16998 }, { "epoch": 0.929383222279173, "grad_norm": 3.081777334213257, "learning_rate": 1.3047692260578947e-06, "loss": 1.0165, "step": 16999 }, { "epoch": 0.9294378950965317, "grad_norm": 2.623462200164795, "learning_rate": 1.3027606087333278e-06, "loss": 1.1323, "step": 17000 }, { "epoch": 0.9294925679138903, "grad_norm": 2.9342844486236572, "learning_rate": 1.3007535182677722e-06, "loss": 0.9062, "step": 17001 }, { "epoch": 0.929547240731249, "grad_norm": 2.9563777446746826, "learning_rate": 1.29874795472415e-06, "loss": 1.0623, "step": 17002 }, { "epoch": 0.9296019135486076, "grad_norm": 2.6463825702667236, "learning_rate": 1.2967439181653606e-06, "loss": 0.9292, "step": 17003 }, { "epoch": 0.9296565863659662, "grad_norm": 2.5345394611358643, "learning_rate": 1.294741408654232e-06, "loss": 1.0882, "step": 17004 }, { "epoch": 0.9297112591833248, "grad_norm": 3.9029343128204346, "learning_rate": 1.292740426253547e-06, "loss": 0.9825, "step": 17005 }, { "epoch": 0.9297659320006834, "grad_norm": 2.0868420600891113, "learning_rate": 1.29074097102605e-06, "loss": 0.8264, "step": 17006 }, { "epoch": 0.9298206048180421, "grad_norm": 2.1655046939849854, "learning_rate": 1.2887430430344294e-06, "loss": 1.0054, "step": 17007 }, { "epoch": 0.9298752776354007, "grad_norm": 3.4034571647644043, "learning_rate": 1.2867466423413243e-06, "loss": 1.2109, "step": 17008 }, { "epoch": 0.9299299504527593, "grad_norm": 2.838719606399536, "learning_rate": 1.2847517690093348e-06, "loss": 0.9741, "step": 17009 }, { "epoch": 0.9299846232701179, "grad_norm": 4.067981719970703, "learning_rate": 1.2827584231010105e-06, "loss": 1.2893, "step": 17010 }, { "epoch": 0.9300392960874765, "grad_norm": 2.42010498046875, "learning_rate": 1.2807666046788457e-06, "loss": 0.8282, "step": 17011 }, { "epoch": 0.9300939689048351, "grad_norm": 3.66857647895813, "learning_rate": 1.278776313805291e-06, "loss": 1.0652, "step": 17012 }, { "epoch": 0.9301486417221937, "grad_norm": 2.175119161605835, "learning_rate": 1.2767875505427573e-06, "loss": 0.9513, "step": 17013 }, { "epoch": 0.9302033145395524, "grad_norm": 3.468296766281128, "learning_rate": 1.2748003149536002e-06, "loss": 1.053, "step": 17014 }, { "epoch": 0.930257987356911, "grad_norm": 2.865206003189087, "learning_rate": 1.2728146071001202e-06, "loss": 1.2927, "step": 17015 }, { "epoch": 0.9303126601742696, "grad_norm": 2.5719189643859863, "learning_rate": 1.2708304270445892e-06, "loss": 0.8748, "step": 17016 }, { "epoch": 0.9303673329916282, "grad_norm": 2.7963035106658936, "learning_rate": 1.2688477748492078e-06, "loss": 1.1112, "step": 17017 }, { "epoch": 0.9304220058089868, "grad_norm": 2.954721689224243, "learning_rate": 1.2668666505761427e-06, "loss": 1.015, "step": 17018 }, { "epoch": 0.9304766786263454, "grad_norm": 1.8108799457550049, "learning_rate": 1.2648870542875114e-06, "loss": 0.765, "step": 17019 }, { "epoch": 0.9305313514437041, "grad_norm": 2.5371484756469727, "learning_rate": 1.2629089860453857e-06, "loss": 1.0168, "step": 17020 }, { "epoch": 0.9305860242610627, "grad_norm": 2.935671091079712, "learning_rate": 1.2609324459117832e-06, "loss": 0.9421, "step": 17021 }, { "epoch": 0.9306406970784213, "grad_norm": 2.6784369945526123, "learning_rate": 1.258957433948671e-06, "loss": 1.0698, "step": 17022 }, { "epoch": 0.93069536989578, "grad_norm": 3.1842033863067627, "learning_rate": 1.2569839502179882e-06, "loss": 1.133, "step": 17023 }, { "epoch": 0.9307500427131385, "grad_norm": 3.0111851692199707, "learning_rate": 1.255011994781602e-06, "loss": 1.1009, "step": 17024 }, { "epoch": 0.9308047155304972, "grad_norm": 2.4024369716644287, "learning_rate": 1.2530415677013408e-06, "loss": 1.0301, "step": 17025 }, { "epoch": 0.9308593883478558, "grad_norm": 2.9518980979919434, "learning_rate": 1.2510726690389885e-06, "loss": 1.0162, "step": 17026 }, { "epoch": 0.9309140611652145, "grad_norm": 3.1904022693634033, "learning_rate": 1.249105298856279e-06, "loss": 0.8309, "step": 17027 }, { "epoch": 0.9309687339825731, "grad_norm": 2.6731984615325928, "learning_rate": 1.247139457214891e-06, "loss": 0.9719, "step": 17028 }, { "epoch": 0.9310234067999317, "grad_norm": 2.2154042720794678, "learning_rate": 1.2451751441764691e-06, "loss": 1.1574, "step": 17029 }, { "epoch": 0.9310780796172903, "grad_norm": 2.315249443054199, "learning_rate": 1.243212359802598e-06, "loss": 1.1043, "step": 17030 }, { "epoch": 0.9311327524346489, "grad_norm": 5.550619125366211, "learning_rate": 1.241251104154828e-06, "loss": 1.1365, "step": 17031 }, { "epoch": 0.9311874252520075, "grad_norm": 2.5280375480651855, "learning_rate": 1.2392913772946325e-06, "loss": 0.9648, "step": 17032 }, { "epoch": 0.9312420980693661, "grad_norm": 2.6227102279663086, "learning_rate": 1.2373331792834786e-06, "loss": 0.988, "step": 17033 }, { "epoch": 0.9312967708867248, "grad_norm": 2.6237173080444336, "learning_rate": 1.2353765101827507e-06, "loss": 1.111, "step": 17034 }, { "epoch": 0.9313514437040834, "grad_norm": 2.8055760860443115, "learning_rate": 1.233421370053811e-06, "loss": 0.7767, "step": 17035 }, { "epoch": 0.931406116521442, "grad_norm": 2.615506649017334, "learning_rate": 1.2314677589579438e-06, "loss": 0.9726, "step": 17036 }, { "epoch": 0.9314607893388006, "grad_norm": 2.8708231449127197, "learning_rate": 1.229515676956422e-06, "loss": 0.9431, "step": 17037 }, { "epoch": 0.9315154621561592, "grad_norm": 2.557614803314209, "learning_rate": 1.2275651241104358e-06, "loss": 0.9301, "step": 17038 }, { "epoch": 0.9315701349735178, "grad_norm": 2.4377009868621826, "learning_rate": 1.2256161004811472e-06, "loss": 0.9684, "step": 17039 }, { "epoch": 0.9316248077908764, "grad_norm": 2.354294538497925, "learning_rate": 1.2236686061296688e-06, "loss": 1.1207, "step": 17040 }, { "epoch": 0.9316794806082351, "grad_norm": 4.115566253662109, "learning_rate": 1.2217226411170625e-06, "loss": 0.9387, "step": 17041 }, { "epoch": 0.9317341534255937, "grad_norm": 1.8153955936431885, "learning_rate": 1.2197782055043406e-06, "loss": 0.9025, "step": 17042 }, { "epoch": 0.9317888262429523, "grad_norm": 2.146712064743042, "learning_rate": 1.217835299352471e-06, "loss": 0.8463, "step": 17043 }, { "epoch": 0.9318434990603109, "grad_norm": 2.273409605026245, "learning_rate": 1.215893922722372e-06, "loss": 0.9652, "step": 17044 }, { "epoch": 0.9318981718776695, "grad_norm": 2.6521198749542236, "learning_rate": 1.2139540756749113e-06, "loss": 1.0321, "step": 17045 }, { "epoch": 0.9319528446950281, "grad_norm": 2.502992630004883, "learning_rate": 1.2120157582709125e-06, "loss": 0.9836, "step": 17046 }, { "epoch": 0.9320075175123869, "grad_norm": 2.096201181411743, "learning_rate": 1.210078970571149e-06, "loss": 1.0761, "step": 17047 }, { "epoch": 0.9320621903297455, "grad_norm": 2.3660058975219727, "learning_rate": 1.2081437126363503e-06, "loss": 1.0481, "step": 17048 }, { "epoch": 0.9321168631471041, "grad_norm": 3.2640581130981445, "learning_rate": 1.2062099845271901e-06, "loss": 1.0512, "step": 17049 }, { "epoch": 0.9321715359644627, "grad_norm": 3.251929998397827, "learning_rate": 1.2042777863042976e-06, "loss": 0.9364, "step": 17050 }, { "epoch": 0.9322262087818213, "grad_norm": 2.5368473529815674, "learning_rate": 1.2023471180282576e-06, "loss": 1.0913, "step": 17051 }, { "epoch": 0.9322808815991799, "grad_norm": 3.201202154159546, "learning_rate": 1.2004179797596105e-06, "loss": 1.0077, "step": 17052 }, { "epoch": 0.9323355544165385, "grad_norm": 3.6085479259490967, "learning_rate": 1.1984903715588359e-06, "loss": 1.056, "step": 17053 }, { "epoch": 0.9323902272338972, "grad_norm": 2.5856783390045166, "learning_rate": 1.196564293486374e-06, "loss": 1.0698, "step": 17054 }, { "epoch": 0.9324449000512558, "grad_norm": 2.618952989578247, "learning_rate": 1.194639745602616e-06, "loss": 0.96, "step": 17055 }, { "epoch": 0.9324995728686144, "grad_norm": 3.0133800506591797, "learning_rate": 1.1927167279679018e-06, "loss": 1.1782, "step": 17056 }, { "epoch": 0.932554245685973, "grad_norm": 2.821667194366455, "learning_rate": 1.1907952406425283e-06, "loss": 0.9354, "step": 17057 }, { "epoch": 0.9326089185033316, "grad_norm": 2.832468271255493, "learning_rate": 1.1888752836867413e-06, "loss": 0.9481, "step": 17058 }, { "epoch": 0.9326635913206902, "grad_norm": 1.8618170022964478, "learning_rate": 1.1869568571607426e-06, "loss": 0.9466, "step": 17059 }, { "epoch": 0.9327182641380488, "grad_norm": 3.022345542907715, "learning_rate": 1.1850399611246732e-06, "loss": 1.0161, "step": 17060 }, { "epoch": 0.9327729369554075, "grad_norm": 3.446500062942505, "learning_rate": 1.1831245956386405e-06, "loss": 1.1559, "step": 17061 }, { "epoch": 0.9328276097727661, "grad_norm": 3.0980050563812256, "learning_rate": 1.1812107607627077e-06, "loss": 1.0397, "step": 17062 }, { "epoch": 0.9328822825901247, "grad_norm": 2.8013710975646973, "learning_rate": 1.179298456556871e-06, "loss": 0.9974, "step": 17063 }, { "epoch": 0.9329369554074833, "grad_norm": 2.8655261993408203, "learning_rate": 1.1773876830810937e-06, "loss": 0.8173, "step": 17064 }, { "epoch": 0.9329916282248419, "grad_norm": 2.960139036178589, "learning_rate": 1.175478440395289e-06, "loss": 1.0736, "step": 17065 }, { "epoch": 0.9330463010422005, "grad_norm": 2.3940882682800293, "learning_rate": 1.173570728559309e-06, "loss": 0.8859, "step": 17066 }, { "epoch": 0.9331009738595591, "grad_norm": 2.229306221008301, "learning_rate": 1.171664547632978e-06, "loss": 0.9046, "step": 17067 }, { "epoch": 0.9331556466769179, "grad_norm": 3.0810937881469727, "learning_rate": 1.1697598976760593e-06, "loss": 1.1338, "step": 17068 }, { "epoch": 0.9332103194942765, "grad_norm": 2.2396512031555176, "learning_rate": 1.1678567787482719e-06, "loss": 0.8426, "step": 17069 }, { "epoch": 0.9332649923116351, "grad_norm": 2.1790404319763184, "learning_rate": 1.1659551909092848e-06, "loss": 0.8579, "step": 17070 }, { "epoch": 0.9333196651289937, "grad_norm": 2.5801401138305664, "learning_rate": 1.1640551342187222e-06, "loss": 1.0922, "step": 17071 }, { "epoch": 0.9333743379463523, "grad_norm": 2.70607590675354, "learning_rate": 1.162156608736159e-06, "loss": 1.0112, "step": 17072 }, { "epoch": 0.9334290107637109, "grad_norm": 2.9234838485717773, "learning_rate": 1.1602596145211253e-06, "loss": 0.9393, "step": 17073 }, { "epoch": 0.9334836835810696, "grad_norm": 2.1460180282592773, "learning_rate": 1.15836415163309e-06, "loss": 0.8107, "step": 17074 }, { "epoch": 0.9335383563984282, "grad_norm": 3.251610040664673, "learning_rate": 1.1564702201314947e-06, "loss": 1.1929, "step": 17075 }, { "epoch": 0.9335930292157868, "grad_norm": 1.997401475906372, "learning_rate": 1.154577820075714e-06, "loss": 0.925, "step": 17076 }, { "epoch": 0.9336477020331454, "grad_norm": 4.552245616912842, "learning_rate": 1.1526869515250838e-06, "loss": 1.2488, "step": 17077 }, { "epoch": 0.933702374850504, "grad_norm": 2.3469479084014893, "learning_rate": 1.1507976145388954e-06, "loss": 1.207, "step": 17078 }, { "epoch": 0.9337570476678626, "grad_norm": 2.7700672149658203, "learning_rate": 1.1489098091763794e-06, "loss": 0.9743, "step": 17079 }, { "epoch": 0.9338117204852212, "grad_norm": 2.4361395835876465, "learning_rate": 1.1470235354967329e-06, "loss": 0.9322, "step": 17080 }, { "epoch": 0.9338663933025799, "grad_norm": 2.6644835472106934, "learning_rate": 1.1451387935590973e-06, "loss": 1.1277, "step": 17081 }, { "epoch": 0.9339210661199385, "grad_norm": 2.2231013774871826, "learning_rate": 1.14325558342257e-06, "loss": 0.8406, "step": 17082 }, { "epoch": 0.9339757389372971, "grad_norm": 2.645310640335083, "learning_rate": 1.141373905146187e-06, "loss": 0.8819, "step": 17083 }, { "epoch": 0.9340304117546557, "grad_norm": 3.1072399616241455, "learning_rate": 1.139493758788951e-06, "loss": 1.3073, "step": 17084 }, { "epoch": 0.9340850845720143, "grad_norm": 2.239560842514038, "learning_rate": 1.1376151444098149e-06, "loss": 1.0433, "step": 17085 }, { "epoch": 0.9341397573893729, "grad_norm": 3.5123047828674316, "learning_rate": 1.1357380620676872e-06, "loss": 0.9392, "step": 17086 }, { "epoch": 0.9341944302067315, "grad_norm": 2.388672113418579, "learning_rate": 1.1338625118214097e-06, "loss": 1.0342, "step": 17087 }, { "epoch": 0.9342491030240903, "grad_norm": 2.664491653442383, "learning_rate": 1.1319884937297964e-06, "loss": 1.0757, "step": 17088 }, { "epoch": 0.9343037758414489, "grad_norm": 2.827143430709839, "learning_rate": 1.130116007851606e-06, "loss": 1.108, "step": 17089 }, { "epoch": 0.9343584486588075, "grad_norm": 2.47800874710083, "learning_rate": 1.1282450542455413e-06, "loss": 0.9167, "step": 17090 }, { "epoch": 0.9344131214761661, "grad_norm": 3.3549797534942627, "learning_rate": 1.1263756329702725e-06, "loss": 1.1583, "step": 17091 }, { "epoch": 0.9344677942935247, "grad_norm": 3.388370990753174, "learning_rate": 1.1245077440844076e-06, "loss": 1.1782, "step": 17092 }, { "epoch": 0.9345224671108833, "grad_norm": 3.193467378616333, "learning_rate": 1.122641387646517e-06, "loss": 1.0042, "step": 17093 }, { "epoch": 0.9345771399282419, "grad_norm": 2.5726897716522217, "learning_rate": 1.1207765637151147e-06, "loss": 0.9684, "step": 17094 }, { "epoch": 0.9346318127456006, "grad_norm": 3.2195816040039062, "learning_rate": 1.118913272348676e-06, "loss": 1.0454, "step": 17095 }, { "epoch": 0.9346864855629592, "grad_norm": 2.2655112743377686, "learning_rate": 1.1170515136056214e-06, "loss": 0.7719, "step": 17096 }, { "epoch": 0.9347411583803178, "grad_norm": 3.100217580795288, "learning_rate": 1.115191287544315e-06, "loss": 1.0421, "step": 17097 }, { "epoch": 0.9347958311976764, "grad_norm": 2.4758851528167725, "learning_rate": 1.1133325942230933e-06, "loss": 0.9692, "step": 17098 }, { "epoch": 0.934850504015035, "grad_norm": 2.4130523204803467, "learning_rate": 1.111475433700232e-06, "loss": 1.1091, "step": 17099 }, { "epoch": 0.9349051768323936, "grad_norm": 3.2595882415771484, "learning_rate": 1.1096198060339624e-06, "loss": 0.8955, "step": 17100 }, { "epoch": 0.9349598496497523, "grad_norm": 2.211786985397339, "learning_rate": 1.1077657112824601e-06, "loss": 0.9563, "step": 17101 }, { "epoch": 0.9350145224671109, "grad_norm": 2.228639602661133, "learning_rate": 1.1059131495038677e-06, "loss": 0.8927, "step": 17102 }, { "epoch": 0.9350691952844695, "grad_norm": 2.559530735015869, "learning_rate": 1.1040621207562606e-06, "loss": 1.0806, "step": 17103 }, { "epoch": 0.9351238681018281, "grad_norm": 2.256749391555786, "learning_rate": 1.1022126250976817e-06, "loss": 1.0162, "step": 17104 }, { "epoch": 0.9351785409191867, "grad_norm": 2.1890552043914795, "learning_rate": 1.1003646625861174e-06, "loss": 0.7973, "step": 17105 }, { "epoch": 0.9352332137365453, "grad_norm": 2.6161110401153564, "learning_rate": 1.0985182332795108e-06, "loss": 0.9918, "step": 17106 }, { "epoch": 0.9352878865539039, "grad_norm": 2.9981565475463867, "learning_rate": 1.0966733372357595e-06, "loss": 0.946, "step": 17107 }, { "epoch": 0.9353425593712626, "grad_norm": 2.3597488403320312, "learning_rate": 1.0948299745127012e-06, "loss": 1.1053, "step": 17108 }, { "epoch": 0.9353972321886213, "grad_norm": 2.1575465202331543, "learning_rate": 1.0929881451681333e-06, "loss": 0.9627, "step": 17109 }, { "epoch": 0.9354519050059799, "grad_norm": 2.867266893386841, "learning_rate": 1.0911478492598048e-06, "loss": 1.1071, "step": 17110 }, { "epoch": 0.9355065778233385, "grad_norm": 3.855447769165039, "learning_rate": 1.0893090868454247e-06, "loss": 0.9291, "step": 17111 }, { "epoch": 0.9355612506406971, "grad_norm": 2.7618508338928223, "learning_rate": 1.0874718579826415e-06, "loss": 0.8237, "step": 17112 }, { "epoch": 0.9356159234580557, "grad_norm": 2.8455235958099365, "learning_rate": 1.0856361627290535e-06, "loss": 1.0181, "step": 17113 }, { "epoch": 0.9356705962754143, "grad_norm": 2.747190237045288, "learning_rate": 1.0838020011422256e-06, "loss": 1.0643, "step": 17114 }, { "epoch": 0.935725269092773, "grad_norm": 2.505713939666748, "learning_rate": 1.081969373279662e-06, "loss": 0.907, "step": 17115 }, { "epoch": 0.9357799419101316, "grad_norm": 2.882560968399048, "learning_rate": 1.0801382791988224e-06, "loss": 1.0875, "step": 17116 }, { "epoch": 0.9358346147274902, "grad_norm": 2.626035690307617, "learning_rate": 1.0783087189571218e-06, "loss": 1.0449, "step": 17117 }, { "epoch": 0.9358892875448488, "grad_norm": 2.309999942779541, "learning_rate": 1.0764806926119252e-06, "loss": 0.9649, "step": 17118 }, { "epoch": 0.9359439603622074, "grad_norm": 2.652817487716675, "learning_rate": 1.0746542002205485e-06, "loss": 0.9287, "step": 17119 }, { "epoch": 0.935998633179566, "grad_norm": 2.181875467300415, "learning_rate": 1.0728292418402508e-06, "loss": 0.923, "step": 17120 }, { "epoch": 0.9360533059969246, "grad_norm": 2.3985612392425537, "learning_rate": 1.0710058175282644e-06, "loss": 1.0733, "step": 17121 }, { "epoch": 0.9361079788142833, "grad_norm": 2.7621757984161377, "learning_rate": 1.0691839273417548e-06, "loss": 1.1064, "step": 17122 }, { "epoch": 0.9361626516316419, "grad_norm": 2.2271838188171387, "learning_rate": 1.0673635713378482e-06, "loss": 1.1372, "step": 17123 }, { "epoch": 0.9362173244490005, "grad_norm": 2.5307090282440186, "learning_rate": 1.0655447495736215e-06, "loss": 0.9387, "step": 17124 }, { "epoch": 0.9362719972663591, "grad_norm": 2.199802875518799, "learning_rate": 1.063727462106101e-06, "loss": 1.0171, "step": 17125 }, { "epoch": 0.9363266700837177, "grad_norm": 2.796318769454956, "learning_rate": 1.0619117089922636e-06, "loss": 0.761, "step": 17126 }, { "epoch": 0.9363813429010763, "grad_norm": 2.1998987197875977, "learning_rate": 1.0600974902890415e-06, "loss": 1.0199, "step": 17127 }, { "epoch": 0.936436015718435, "grad_norm": 2.322161912918091, "learning_rate": 1.0582848060533167e-06, "loss": 0.8449, "step": 17128 }, { "epoch": 0.9364906885357936, "grad_norm": 2.8210384845733643, "learning_rate": 1.0564736563419276e-06, "loss": 1.1429, "step": 17129 }, { "epoch": 0.9365453613531523, "grad_norm": 2.6776320934295654, "learning_rate": 1.0546640412116616e-06, "loss": 0.991, "step": 17130 }, { "epoch": 0.9366000341705109, "grad_norm": 2.960996627807617, "learning_rate": 1.0528559607192513e-06, "loss": 1.1179, "step": 17131 }, { "epoch": 0.9366547069878695, "grad_norm": 2.852897882461548, "learning_rate": 1.0510494149213957e-06, "loss": 1.0573, "step": 17132 }, { "epoch": 0.9367093798052281, "grad_norm": 3.0524094104766846, "learning_rate": 1.0492444038747384e-06, "loss": 0.9326, "step": 17133 }, { "epoch": 0.9367640526225867, "grad_norm": 3.5107457637786865, "learning_rate": 1.0474409276358622e-06, "loss": 0.9086, "step": 17134 }, { "epoch": 0.9368187254399454, "grad_norm": 2.459975242614746, "learning_rate": 1.0456389862613215e-06, "loss": 0.8644, "step": 17135 }, { "epoch": 0.936873398257304, "grad_norm": 3.009660243988037, "learning_rate": 1.043838579807621e-06, "loss": 1.1443, "step": 17136 }, { "epoch": 0.9369280710746626, "grad_norm": 2.7765707969665527, "learning_rate": 1.0420397083311939e-06, "loss": 1.1544, "step": 17137 }, { "epoch": 0.9369827438920212, "grad_norm": 2.826073408126831, "learning_rate": 1.0402423718884612e-06, "loss": 0.8587, "step": 17138 }, { "epoch": 0.9370374167093798, "grad_norm": 2.399034261703491, "learning_rate": 1.038446570535756e-06, "loss": 1.0768, "step": 17139 }, { "epoch": 0.9370920895267384, "grad_norm": 2.3620426654815674, "learning_rate": 1.0366523043293996e-06, "loss": 1.046, "step": 17140 }, { "epoch": 0.937146762344097, "grad_norm": 2.504471778869629, "learning_rate": 1.0348595733256529e-06, "loss": 1.0362, "step": 17141 }, { "epoch": 0.9372014351614557, "grad_norm": 3.1213622093200684, "learning_rate": 1.0330683775807093e-06, "loss": 1.0799, "step": 17142 }, { "epoch": 0.9372561079788143, "grad_norm": 2.719956636428833, "learning_rate": 1.0312787171507466e-06, "loss": 0.9429, "step": 17143 }, { "epoch": 0.9373107807961729, "grad_norm": 2.406034469604492, "learning_rate": 1.0294905920918641e-06, "loss": 1.0362, "step": 17144 }, { "epoch": 0.9373654536135315, "grad_norm": 2.402512788772583, "learning_rate": 1.0277040024601392e-06, "loss": 1.0391, "step": 17145 }, { "epoch": 0.9374201264308901, "grad_norm": 3.633610963821411, "learning_rate": 1.0259189483115827e-06, "loss": 1.0671, "step": 17146 }, { "epoch": 0.9374747992482487, "grad_norm": 1.9117072820663452, "learning_rate": 1.0241354297021555e-06, "loss": 0.9102, "step": 17147 }, { "epoch": 0.9375294720656073, "grad_norm": 3.0801501274108887, "learning_rate": 1.0223534466877959e-06, "loss": 1.0696, "step": 17148 }, { "epoch": 0.937584144882966, "grad_norm": 2.736643075942993, "learning_rate": 1.0205729993243596e-06, "loss": 1.109, "step": 17149 }, { "epoch": 0.9376388177003246, "grad_norm": 3.221400022506714, "learning_rate": 1.0187940876676794e-06, "loss": 0.8976, "step": 17150 }, { "epoch": 0.9376934905176832, "grad_norm": 2.668684244155884, "learning_rate": 1.017016711773533e-06, "loss": 0.8, "step": 17151 }, { "epoch": 0.9377481633350419, "grad_norm": 3.196535110473633, "learning_rate": 1.0152408716976426e-06, "loss": 1.0258, "step": 17152 }, { "epoch": 0.9378028361524005, "grad_norm": 3.0399081707000732, "learning_rate": 1.0134665674956967e-06, "loss": 1.2211, "step": 17153 }, { "epoch": 0.9378575089697591, "grad_norm": 2.495138168334961, "learning_rate": 1.0116937992233177e-06, "loss": 1.1697, "step": 17154 }, { "epoch": 0.9379121817871178, "grad_norm": 2.2433574199676514, "learning_rate": 1.009922566936089e-06, "loss": 1.0028, "step": 17155 }, { "epoch": 0.9379668546044764, "grad_norm": 2.731045722961426, "learning_rate": 1.008152870689555e-06, "loss": 0.9832, "step": 17156 }, { "epoch": 0.938021527421835, "grad_norm": 3.90063214302063, "learning_rate": 1.0063847105391988e-06, "loss": 1.0563, "step": 17157 }, { "epoch": 0.9380762002391936, "grad_norm": 2.255825996398926, "learning_rate": 1.0046180865404598e-06, "loss": 0.9933, "step": 17158 }, { "epoch": 0.9381308730565522, "grad_norm": 2.5467329025268555, "learning_rate": 1.0028529987487211e-06, "loss": 0.9859, "step": 17159 }, { "epoch": 0.9381855458739108, "grad_norm": 3.656968116760254, "learning_rate": 1.0010894472193387e-06, "loss": 1.0046, "step": 17160 }, { "epoch": 0.9382402186912694, "grad_norm": 3.6078269481658936, "learning_rate": 9.993274320075963e-07, "loss": 0.955, "step": 17161 }, { "epoch": 0.9382948915086281, "grad_norm": 2.8688299655914307, "learning_rate": 9.975669531687494e-07, "loss": 1.1383, "step": 17162 }, { "epoch": 0.9383495643259867, "grad_norm": 2.34240984916687, "learning_rate": 9.958080107579925e-07, "loss": 1.0928, "step": 17163 }, { "epoch": 0.9384042371433453, "grad_norm": 2.491356611251831, "learning_rate": 9.94050604830471e-07, "loss": 1.0659, "step": 17164 }, { "epoch": 0.9384589099607039, "grad_norm": 2.650467872619629, "learning_rate": 9.922947354412903e-07, "loss": 1.0109, "step": 17165 }, { "epoch": 0.9385135827780625, "grad_norm": 2.670994520187378, "learning_rate": 9.905404026455068e-07, "loss": 0.8524, "step": 17166 }, { "epoch": 0.9385682555954211, "grad_norm": 2.8711724281311035, "learning_rate": 9.88787606498126e-07, "loss": 0.8639, "step": 17167 }, { "epoch": 0.9386229284127797, "grad_norm": 2.8063697814941406, "learning_rate": 9.870363470540988e-07, "loss": 0.9164, "step": 17168 }, { "epoch": 0.9386776012301384, "grad_norm": 2.8283498287200928, "learning_rate": 9.852866243683368e-07, "loss": 1.0798, "step": 17169 }, { "epoch": 0.938732274047497, "grad_norm": 2.3464465141296387, "learning_rate": 9.835384384957068e-07, "loss": 0.9541, "step": 17170 }, { "epoch": 0.9387869468648556, "grad_norm": 2.646348476409912, "learning_rate": 9.817917894910155e-07, "loss": 1.0098, "step": 17171 }, { "epoch": 0.9388416196822142, "grad_norm": 2.61974835395813, "learning_rate": 9.8004667740903e-07, "loss": 0.9898, "step": 17172 }, { "epoch": 0.9388962924995728, "grad_norm": 3.4992165565490723, "learning_rate": 9.783031023044675e-07, "loss": 1.0872, "step": 17173 }, { "epoch": 0.9389509653169315, "grad_norm": 2.487297296524048, "learning_rate": 9.765610642319957e-07, "loss": 1.0189, "step": 17174 }, { "epoch": 0.93900563813429, "grad_norm": 2.6629252433776855, "learning_rate": 9.74820563246237e-07, "loss": 1.0028, "step": 17175 }, { "epoch": 0.9390603109516488, "grad_norm": 4.034539222717285, "learning_rate": 9.73081599401754e-07, "loss": 1.0372, "step": 17176 }, { "epoch": 0.9391149837690074, "grad_norm": 2.7306835651397705, "learning_rate": 9.713441727530803e-07, "loss": 0.7963, "step": 17177 }, { "epoch": 0.939169656586366, "grad_norm": 2.9450488090515137, "learning_rate": 9.696082833546894e-07, "loss": 0.8203, "step": 17178 }, { "epoch": 0.9392243294037246, "grad_norm": 2.7229816913604736, "learning_rate": 9.678739312609987e-07, "loss": 0.9473, "step": 17179 }, { "epoch": 0.9392790022210832, "grad_norm": 2.226834535598755, "learning_rate": 9.661411165264035e-07, "loss": 1.1004, "step": 17180 }, { "epoch": 0.9393336750384418, "grad_norm": 2.9011802673339844, "learning_rate": 9.64409839205227e-07, "loss": 0.8275, "step": 17181 }, { "epoch": 0.9393883478558005, "grad_norm": 2.651531219482422, "learning_rate": 9.626800993517538e-07, "loss": 0.9449, "step": 17182 }, { "epoch": 0.9394430206731591, "grad_norm": 2.577436923980713, "learning_rate": 9.609518970202124e-07, "loss": 1.024, "step": 17183 }, { "epoch": 0.9394976934905177, "grad_norm": 2.2338919639587402, "learning_rate": 9.592252322647932e-07, "loss": 0.9767, "step": 17184 }, { "epoch": 0.9395523663078763, "grad_norm": 2.6095666885375977, "learning_rate": 9.57500105139636e-07, "loss": 0.9789, "step": 17185 }, { "epoch": 0.9396070391252349, "grad_norm": 2.7365431785583496, "learning_rate": 9.557765156988251e-07, "loss": 1.1365, "step": 17186 }, { "epoch": 0.9396617119425935, "grad_norm": 2.5285041332244873, "learning_rate": 9.540544639964066e-07, "loss": 1.0325, "step": 17187 }, { "epoch": 0.9397163847599521, "grad_norm": 2.434957265853882, "learning_rate": 9.52333950086376e-07, "loss": 0.9799, "step": 17188 }, { "epoch": 0.9397710575773108, "grad_norm": 3.0524768829345703, "learning_rate": 9.506149740226677e-07, "loss": 0.8624, "step": 17189 }, { "epoch": 0.9398257303946694, "grad_norm": 3.000824213027954, "learning_rate": 9.488975358591945e-07, "loss": 0.8211, "step": 17190 }, { "epoch": 0.939880403212028, "grad_norm": 2.9648375511169434, "learning_rate": 9.471816356497964e-07, "loss": 1.1048, "step": 17191 }, { "epoch": 0.9399350760293866, "grad_norm": 3.5703377723693848, "learning_rate": 9.45467273448275e-07, "loss": 1.156, "step": 17192 }, { "epoch": 0.9399897488467452, "grad_norm": 2.629584550857544, "learning_rate": 9.437544493083816e-07, "loss": 1.069, "step": 17193 }, { "epoch": 0.9400444216641038, "grad_norm": 3.6812713146209717, "learning_rate": 9.420431632838178e-07, "loss": 1.1203, "step": 17194 }, { "epoch": 0.9400990944814624, "grad_norm": 2.637068748474121, "learning_rate": 9.403334154282462e-07, "loss": 0.9223, "step": 17195 }, { "epoch": 0.9401537672988212, "grad_norm": 2.5904979705810547, "learning_rate": 9.386252057952683e-07, "loss": 1.131, "step": 17196 }, { "epoch": 0.9402084401161798, "grad_norm": 2.2035226821899414, "learning_rate": 9.369185344384468e-07, "loss": 1.0259, "step": 17197 }, { "epoch": 0.9402631129335384, "grad_norm": 2.237464427947998, "learning_rate": 9.35213401411289e-07, "loss": 1.0421, "step": 17198 }, { "epoch": 0.940317785750897, "grad_norm": 2.507032632827759, "learning_rate": 9.335098067672687e-07, "loss": 1.1908, "step": 17199 }, { "epoch": 0.9403724585682556, "grad_norm": 2.738008737564087, "learning_rate": 9.318077505597877e-07, "loss": 1.1099, "step": 17200 }, { "epoch": 0.9404271313856142, "grad_norm": 2.3303322792053223, "learning_rate": 9.3010723284222e-07, "loss": 1.0085, "step": 17201 }, { "epoch": 0.9404818042029728, "grad_norm": 2.8656015396118164, "learning_rate": 9.284082536678784e-07, "loss": 0.8038, "step": 17202 }, { "epoch": 0.9405364770203315, "grad_norm": 3.6811721324920654, "learning_rate": 9.267108130900426e-07, "loss": 0.9145, "step": 17203 }, { "epoch": 0.9405911498376901, "grad_norm": 2.441645383834839, "learning_rate": 9.2501491116192e-07, "loss": 0.9778, "step": 17204 }, { "epoch": 0.9406458226550487, "grad_norm": 2.850980758666992, "learning_rate": 9.233205479366957e-07, "loss": 1.1564, "step": 17205 }, { "epoch": 0.9407004954724073, "grad_norm": 2.042994976043701, "learning_rate": 9.216277234674942e-07, "loss": 0.8548, "step": 17206 }, { "epoch": 0.9407551682897659, "grad_norm": 2.704693555831909, "learning_rate": 9.199364378073838e-07, "loss": 1.0762, "step": 17207 }, { "epoch": 0.9408098411071245, "grad_norm": 2.9372451305389404, "learning_rate": 9.182466910094001e-07, "loss": 1.2058, "step": 17208 }, { "epoch": 0.9408645139244832, "grad_norm": 3.5681865215301514, "learning_rate": 9.165584831265228e-07, "loss": 1.0677, "step": 17209 }, { "epoch": 0.9409191867418418, "grad_norm": 2.5092499256134033, "learning_rate": 9.148718142116818e-07, "loss": 1.0763, "step": 17210 }, { "epoch": 0.9409738595592004, "grad_norm": 2.6186678409576416, "learning_rate": 9.131866843177683e-07, "loss": 0.9978, "step": 17211 }, { "epoch": 0.941028532376559, "grad_norm": 2.1637449264526367, "learning_rate": 9.115030934976121e-07, "loss": 1.0134, "step": 17212 }, { "epoch": 0.9410832051939176, "grad_norm": 2.4219777584075928, "learning_rate": 9.098210418039987e-07, "loss": 1.0276, "step": 17213 }, { "epoch": 0.9411378780112762, "grad_norm": 2.3845481872558594, "learning_rate": 9.081405292896694e-07, "loss": 1.1754, "step": 17214 }, { "epoch": 0.9411925508286348, "grad_norm": 2.299520969390869, "learning_rate": 9.064615560073208e-07, "loss": 1.1304, "step": 17215 }, { "epoch": 0.9412472236459936, "grad_norm": 2.7437117099761963, "learning_rate": 9.047841220095887e-07, "loss": 1.1116, "step": 17216 }, { "epoch": 0.9413018964633522, "grad_norm": 2.8381083011627197, "learning_rate": 9.031082273490699e-07, "loss": 0.9592, "step": 17217 }, { "epoch": 0.9413565692807108, "grad_norm": 2.8772950172424316, "learning_rate": 9.014338720783056e-07, "loss": 1.2843, "step": 17218 }, { "epoch": 0.9414112420980694, "grad_norm": 3.063218832015991, "learning_rate": 8.997610562498038e-07, "loss": 1.1289, "step": 17219 }, { "epoch": 0.941465914915428, "grad_norm": 3.056022882461548, "learning_rate": 8.98089779916006e-07, "loss": 0.9004, "step": 17220 }, { "epoch": 0.9415205877327866, "grad_norm": 3.063000202178955, "learning_rate": 8.964200431293146e-07, "loss": 0.9639, "step": 17221 }, { "epoch": 0.9415752605501452, "grad_norm": 2.7087159156799316, "learning_rate": 8.947518459420878e-07, "loss": 0.8712, "step": 17222 }, { "epoch": 0.9416299333675039, "grad_norm": 2.3356828689575195, "learning_rate": 8.930851884066283e-07, "loss": 1.0134, "step": 17223 }, { "epoch": 0.9416846061848625, "grad_norm": 2.6122658252716064, "learning_rate": 8.91420070575194e-07, "loss": 0.9978, "step": 17224 }, { "epoch": 0.9417392790022211, "grad_norm": 3.101548671722412, "learning_rate": 8.89756492499988e-07, "loss": 1.0049, "step": 17225 }, { "epoch": 0.9417939518195797, "grad_norm": 3.317718744277954, "learning_rate": 8.880944542331682e-07, "loss": 0.9943, "step": 17226 }, { "epoch": 0.9418486246369383, "grad_norm": 3.037893772125244, "learning_rate": 8.864339558268597e-07, "loss": 1.0935, "step": 17227 }, { "epoch": 0.9419032974542969, "grad_norm": 2.9039595127105713, "learning_rate": 8.847749973331099e-07, "loss": 1.055, "step": 17228 }, { "epoch": 0.9419579702716555, "grad_norm": 2.326819896697998, "learning_rate": 8.831175788039436e-07, "loss": 0.9008, "step": 17229 }, { "epoch": 0.9420126430890142, "grad_norm": 2.5879623889923096, "learning_rate": 8.81461700291325e-07, "loss": 0.9805, "step": 17230 }, { "epoch": 0.9420673159063728, "grad_norm": 2.286813974380493, "learning_rate": 8.798073618471791e-07, "loss": 0.9914, "step": 17231 }, { "epoch": 0.9421219887237314, "grad_norm": 2.0892462730407715, "learning_rate": 8.781545635233646e-07, "loss": 0.938, "step": 17232 }, { "epoch": 0.94217666154109, "grad_norm": 2.2772090435028076, "learning_rate": 8.76503305371712e-07, "loss": 0.9715, "step": 17233 }, { "epoch": 0.9422313343584486, "grad_norm": 3.0483264923095703, "learning_rate": 8.748535874439967e-07, "loss": 1.1267, "step": 17234 }, { "epoch": 0.9422860071758072, "grad_norm": 2.5271317958831787, "learning_rate": 8.732054097919329e-07, "loss": 1.0173, "step": 17235 }, { "epoch": 0.942340679993166, "grad_norm": 2.3012969493865967, "learning_rate": 8.71558772467207e-07, "loss": 0.9151, "step": 17236 }, { "epoch": 0.9423953528105246, "grad_norm": 2.1548964977264404, "learning_rate": 8.699136755214499e-07, "loss": 1.0555, "step": 17237 }, { "epoch": 0.9424500256278832, "grad_norm": 3.0211896896362305, "learning_rate": 8.682701190062314e-07, "loss": 1.1843, "step": 17238 }, { "epoch": 0.9425046984452418, "grad_norm": 2.3055779933929443, "learning_rate": 8.666281029730939e-07, "loss": 0.8961, "step": 17239 }, { "epoch": 0.9425593712626004, "grad_norm": 2.6066648960113525, "learning_rate": 8.649876274735125e-07, "loss": 0.882, "step": 17240 }, { "epoch": 0.942614044079959, "grad_norm": 2.429216146469116, "learning_rate": 8.633486925589351e-07, "loss": 1.0468, "step": 17241 }, { "epoch": 0.9426687168973176, "grad_norm": 2.9075815677642822, "learning_rate": 8.617112982807429e-07, "loss": 0.9104, "step": 17242 }, { "epoch": 0.9427233897146763, "grad_norm": 2.248307704925537, "learning_rate": 8.600754446902671e-07, "loss": 1.0951, "step": 17243 }, { "epoch": 0.9427780625320349, "grad_norm": 2.4550578594207764, "learning_rate": 8.584411318388108e-07, "loss": 0.9358, "step": 17244 }, { "epoch": 0.9428327353493935, "grad_norm": 4.252204418182373, "learning_rate": 8.568083597776111e-07, "loss": 0.9601, "step": 17245 }, { "epoch": 0.9428874081667521, "grad_norm": 2.9430978298187256, "learning_rate": 8.551771285578603e-07, "loss": 1.0333, "step": 17246 }, { "epoch": 0.9429420809841107, "grad_norm": 2.5506608486175537, "learning_rate": 8.535474382307062e-07, "loss": 0.9598, "step": 17247 }, { "epoch": 0.9429967538014693, "grad_norm": 2.4378576278686523, "learning_rate": 8.519192888472472e-07, "loss": 0.8967, "step": 17248 }, { "epoch": 0.9430514266188279, "grad_norm": 2.7012932300567627, "learning_rate": 8.50292680458531e-07, "loss": 0.9668, "step": 17249 }, { "epoch": 0.9431060994361866, "grad_norm": 2.510960102081299, "learning_rate": 8.486676131155558e-07, "loss": 0.9511, "step": 17250 }, { "epoch": 0.9431607722535452, "grad_norm": 2.6082112789154053, "learning_rate": 8.470440868692808e-07, "loss": 0.898, "step": 17251 }, { "epoch": 0.9432154450709038, "grad_norm": 2.7656314373016357, "learning_rate": 8.454221017706098e-07, "loss": 1.0244, "step": 17252 }, { "epoch": 0.9432701178882624, "grad_norm": 2.273463249206543, "learning_rate": 8.438016578703911e-07, "loss": 0.9408, "step": 17253 }, { "epoch": 0.943324790705621, "grad_norm": 2.9764199256896973, "learning_rate": 8.421827552194394e-07, "loss": 0.9125, "step": 17254 }, { "epoch": 0.9433794635229796, "grad_norm": 2.4243266582489014, "learning_rate": 8.405653938685087e-07, "loss": 1.0103, "step": 17255 }, { "epoch": 0.9434341363403382, "grad_norm": 2.450603485107422, "learning_rate": 8.38949573868314e-07, "loss": 0.9135, "step": 17256 }, { "epoch": 0.943488809157697, "grad_norm": 2.5149521827697754, "learning_rate": 8.373352952695201e-07, "loss": 1.0078, "step": 17257 }, { "epoch": 0.9435434819750556, "grad_norm": 3.364093780517578, "learning_rate": 8.357225581227257e-07, "loss": 0.9495, "step": 17258 }, { "epoch": 0.9435981547924142, "grad_norm": 2.7071518898010254, "learning_rate": 8.341113624785179e-07, "loss": 0.8909, "step": 17259 }, { "epoch": 0.9436528276097728, "grad_norm": 2.942221164703369, "learning_rate": 8.325017083874065e-07, "loss": 1.146, "step": 17260 }, { "epoch": 0.9437075004271314, "grad_norm": 2.5329151153564453, "learning_rate": 8.308935958998565e-07, "loss": 0.9603, "step": 17261 }, { "epoch": 0.94376217324449, "grad_norm": 2.681532382965088, "learning_rate": 8.292870250662943e-07, "loss": 1.0977, "step": 17262 }, { "epoch": 0.9438168460618487, "grad_norm": 2.358194589614868, "learning_rate": 8.276819959370907e-07, "loss": 0.9675, "step": 17263 }, { "epoch": 0.9438715188792073, "grad_norm": 2.4869801998138428, "learning_rate": 8.260785085625667e-07, "loss": 1.0933, "step": 17264 }, { "epoch": 0.9439261916965659, "grad_norm": 2.6052846908569336, "learning_rate": 8.24476562993004e-07, "loss": 1.0905, "step": 17265 }, { "epoch": 0.9439808645139245, "grad_norm": 3.055422306060791, "learning_rate": 8.228761592786239e-07, "loss": 1.0092, "step": 17266 }, { "epoch": 0.9440355373312831, "grad_norm": 2.7644519805908203, "learning_rate": 8.212772974696081e-07, "loss": 1.0253, "step": 17267 }, { "epoch": 0.9440902101486417, "grad_norm": 2.889248847961426, "learning_rate": 8.196799776160891e-07, "loss": 1.0531, "step": 17268 }, { "epoch": 0.9441448829660003, "grad_norm": 3.2843477725982666, "learning_rate": 8.180841997681543e-07, "loss": 1.1761, "step": 17269 }, { "epoch": 0.944199555783359, "grad_norm": 2.3975048065185547, "learning_rate": 8.16489963975825e-07, "loss": 0.8837, "step": 17270 }, { "epoch": 0.9442542286007176, "grad_norm": 3.098856210708618, "learning_rate": 8.148972702890944e-07, "loss": 0.9359, "step": 17271 }, { "epoch": 0.9443089014180762, "grad_norm": 2.5085031986236572, "learning_rate": 8.133061187579005e-07, "loss": 1.0824, "step": 17272 }, { "epoch": 0.9443635742354348, "grad_norm": 2.219144582748413, "learning_rate": 8.117165094321311e-07, "loss": 0.7915, "step": 17273 }, { "epoch": 0.9444182470527934, "grad_norm": 4.262820243835449, "learning_rate": 8.101284423616295e-07, "loss": 0.9712, "step": 17274 }, { "epoch": 0.944472919870152, "grad_norm": 2.54068660736084, "learning_rate": 8.085419175961895e-07, "loss": 1.0364, "step": 17275 }, { "epoch": 0.9445275926875106, "grad_norm": 3.9693586826324463, "learning_rate": 8.069569351855488e-07, "loss": 1.0785, "step": 17276 }, { "epoch": 0.9445822655048693, "grad_norm": 1.9992681741714478, "learning_rate": 8.053734951794067e-07, "loss": 0.928, "step": 17277 }, { "epoch": 0.944636938322228, "grad_norm": 2.280041217803955, "learning_rate": 8.037915976274124e-07, "loss": 0.9507, "step": 17278 }, { "epoch": 0.9446916111395866, "grad_norm": 2.2219581604003906, "learning_rate": 8.022112425791595e-07, "loss": 0.9658, "step": 17279 }, { "epoch": 0.9447462839569452, "grad_norm": 2.3241536617279053, "learning_rate": 8.006324300842027e-07, "loss": 0.9409, "step": 17280 }, { "epoch": 0.9448009567743038, "grad_norm": 4.177645683288574, "learning_rate": 7.990551601920415e-07, "loss": 0.8919, "step": 17281 }, { "epoch": 0.9448556295916624, "grad_norm": 2.5001070499420166, "learning_rate": 7.974794329521362e-07, "loss": 0.9261, "step": 17282 }, { "epoch": 0.944910302409021, "grad_norm": 2.401951789855957, "learning_rate": 7.959052484138863e-07, "loss": 0.9134, "step": 17283 }, { "epoch": 0.9449649752263797, "grad_norm": 3.0182931423187256, "learning_rate": 7.943326066266466e-07, "loss": 1.0957, "step": 17284 }, { "epoch": 0.9450196480437383, "grad_norm": 3.5664141178131104, "learning_rate": 7.927615076397333e-07, "loss": 0.8031, "step": 17285 }, { "epoch": 0.9450743208610969, "grad_norm": 2.006742238998413, "learning_rate": 7.911919515024014e-07, "loss": 0.8453, "step": 17286 }, { "epoch": 0.9451289936784555, "grad_norm": 2.8552815914154053, "learning_rate": 7.89623938263867e-07, "loss": 1.298, "step": 17287 }, { "epoch": 0.9451836664958141, "grad_norm": 2.4865806102752686, "learning_rate": 7.88057467973291e-07, "loss": 0.9592, "step": 17288 }, { "epoch": 0.9452383393131727, "grad_norm": 2.643486261367798, "learning_rate": 7.864925406797896e-07, "loss": 1.0442, "step": 17289 }, { "epoch": 0.9452930121305313, "grad_norm": 3.037160634994507, "learning_rate": 7.84929156432429e-07, "loss": 1.0746, "step": 17290 }, { "epoch": 0.94534768494789, "grad_norm": 2.532252073287964, "learning_rate": 7.833673152802312e-07, "loss": 1.0423, "step": 17291 }, { "epoch": 0.9454023577652486, "grad_norm": 2.043002128601074, "learning_rate": 7.818070172721625e-07, "loss": 0.95, "step": 17292 }, { "epoch": 0.9454570305826072, "grad_norm": 2.157989740371704, "learning_rate": 7.80248262457145e-07, "loss": 0.8022, "step": 17293 }, { "epoch": 0.9455117033999658, "grad_norm": 2.615255117416382, "learning_rate": 7.786910508840506e-07, "loss": 0.9545, "step": 17294 }, { "epoch": 0.9455663762173244, "grad_norm": 3.16802716255188, "learning_rate": 7.77135382601707e-07, "loss": 1.0724, "step": 17295 }, { "epoch": 0.945621049034683, "grad_norm": 3.22232723236084, "learning_rate": 7.755812576588861e-07, "loss": 1.336, "step": 17296 }, { "epoch": 0.9456757218520417, "grad_norm": 2.968107223510742, "learning_rate": 7.740286761043269e-07, "loss": 1.105, "step": 17297 }, { "epoch": 0.9457303946694003, "grad_norm": 2.9847934246063232, "learning_rate": 7.724776379867016e-07, "loss": 0.8181, "step": 17298 }, { "epoch": 0.945785067486759, "grad_norm": 2.2337419986724854, "learning_rate": 7.709281433546378e-07, "loss": 0.6734, "step": 17299 }, { "epoch": 0.9458397403041175, "grad_norm": 2.608649730682373, "learning_rate": 7.693801922567301e-07, "loss": 1.0582, "step": 17300 }, { "epoch": 0.9458944131214762, "grad_norm": 2.304318428039551, "learning_rate": 7.678337847415007e-07, "loss": 0.9753, "step": 17301 }, { "epoch": 0.9459490859388348, "grad_norm": 2.721412420272827, "learning_rate": 7.662889208574442e-07, "loss": 0.9629, "step": 17302 }, { "epoch": 0.9460037587561934, "grad_norm": 2.9489707946777344, "learning_rate": 7.647456006529941e-07, "loss": 1.0635, "step": 17303 }, { "epoch": 0.9460584315735521, "grad_norm": 2.362644672393799, "learning_rate": 7.632038241765449e-07, "loss": 0.9549, "step": 17304 }, { "epoch": 0.9461131043909107, "grad_norm": 2.220790147781372, "learning_rate": 7.616635914764303e-07, "loss": 0.8782, "step": 17305 }, { "epoch": 0.9461677772082693, "grad_norm": 2.4223484992980957, "learning_rate": 7.601249026009449e-07, "loss": 0.8423, "step": 17306 }, { "epoch": 0.9462224500256279, "grad_norm": 2.2646803855895996, "learning_rate": 7.585877575983391e-07, "loss": 1.0375, "step": 17307 }, { "epoch": 0.9462771228429865, "grad_norm": 3.2127254009246826, "learning_rate": 7.57052156516802e-07, "loss": 1.3627, "step": 17308 }, { "epoch": 0.9463317956603451, "grad_norm": 2.4918320178985596, "learning_rate": 7.555180994044842e-07, "loss": 0.9324, "step": 17309 }, { "epoch": 0.9463864684777037, "grad_norm": 2.837432622909546, "learning_rate": 7.539855863094857e-07, "loss": 0.931, "step": 17310 }, { "epoch": 0.9464411412950624, "grad_norm": 2.600151777267456, "learning_rate": 7.524546172798575e-07, "loss": 0.8821, "step": 17311 }, { "epoch": 0.946495814112421, "grad_norm": 2.771711826324463, "learning_rate": 7.509251923635941e-07, "loss": 0.9266, "step": 17312 }, { "epoch": 0.9465504869297796, "grad_norm": 2.234992027282715, "learning_rate": 7.493973116086572e-07, "loss": 1.0781, "step": 17313 }, { "epoch": 0.9466051597471382, "grad_norm": 2.9153435230255127, "learning_rate": 7.478709750629531e-07, "loss": 1.0281, "step": 17314 }, { "epoch": 0.9466598325644968, "grad_norm": 6.301955699920654, "learning_rate": 7.463461827743323e-07, "loss": 1.192, "step": 17315 }, { "epoch": 0.9467145053818554, "grad_norm": 2.6405560970306396, "learning_rate": 7.448229347906011e-07, "loss": 0.9743, "step": 17316 }, { "epoch": 0.946769178199214, "grad_norm": 3.1695189476013184, "learning_rate": 7.433012311595322e-07, "loss": 0.8997, "step": 17317 }, { "epoch": 0.9468238510165727, "grad_norm": 3.0882866382598877, "learning_rate": 7.417810719288266e-07, "loss": 1.0182, "step": 17318 }, { "epoch": 0.9468785238339313, "grad_norm": 2.313098430633545, "learning_rate": 7.402624571461514e-07, "loss": 0.8649, "step": 17319 }, { "epoch": 0.9469331966512899, "grad_norm": 3.362673282623291, "learning_rate": 7.387453868591244e-07, "loss": 1.0793, "step": 17320 }, { "epoch": 0.9469878694686485, "grad_norm": 2.673231601715088, "learning_rate": 7.372298611153072e-07, "loss": 0.8092, "step": 17321 }, { "epoch": 0.9470425422860071, "grad_norm": 2.7233564853668213, "learning_rate": 7.357158799622177e-07, "loss": 0.9152, "step": 17322 }, { "epoch": 0.9470972151033658, "grad_norm": 2.4220614433288574, "learning_rate": 7.342034434473288e-07, "loss": 0.8306, "step": 17323 }, { "epoch": 0.9471518879207245, "grad_norm": 3.1047043800354004, "learning_rate": 7.326925516180583e-07, "loss": 1.1545, "step": 17324 }, { "epoch": 0.9472065607380831, "grad_norm": 2.663252830505371, "learning_rate": 7.311832045217792e-07, "loss": 0.8901, "step": 17325 }, { "epoch": 0.9472612335554417, "grad_norm": 2.359976291656494, "learning_rate": 7.29675402205815e-07, "loss": 0.9379, "step": 17326 }, { "epoch": 0.9473159063728003, "grad_norm": 3.4816246032714844, "learning_rate": 7.281691447174499e-07, "loss": 1.1591, "step": 17327 }, { "epoch": 0.9473705791901589, "grad_norm": 2.048840045928955, "learning_rate": 7.266644321039018e-07, "loss": 0.9996, "step": 17328 }, { "epoch": 0.9474252520075175, "grad_norm": 2.2991273403167725, "learning_rate": 7.251612644123496e-07, "loss": 0.9125, "step": 17329 }, { "epoch": 0.9474799248248761, "grad_norm": 2.6369788646698, "learning_rate": 7.236596416899333e-07, "loss": 1.1148, "step": 17330 }, { "epoch": 0.9475345976422348, "grad_norm": 2.914966344833374, "learning_rate": 7.221595639837209e-07, "loss": 1.1563, "step": 17331 }, { "epoch": 0.9475892704595934, "grad_norm": 2.882908344268799, "learning_rate": 7.20661031340758e-07, "loss": 0.9596, "step": 17332 }, { "epoch": 0.947643943276952, "grad_norm": 2.1963748931884766, "learning_rate": 7.191640438080238e-07, "loss": 1.023, "step": 17333 }, { "epoch": 0.9476986160943106, "grad_norm": 2.543889284133911, "learning_rate": 7.176686014324585e-07, "loss": 1.0265, "step": 17334 }, { "epoch": 0.9477532889116692, "grad_norm": 2.647130012512207, "learning_rate": 7.161747042609468e-07, "loss": 1.1157, "step": 17335 }, { "epoch": 0.9478079617290278, "grad_norm": 2.870054006576538, "learning_rate": 7.14682352340329e-07, "loss": 1.2525, "step": 17336 }, { "epoch": 0.9478626345463864, "grad_norm": 2.6851611137390137, "learning_rate": 7.13191545717401e-07, "loss": 1.1082, "step": 17337 }, { "epoch": 0.9479173073637451, "grad_norm": 3.2456483840942383, "learning_rate": 7.117022844389032e-07, "loss": 1.091, "step": 17338 }, { "epoch": 0.9479719801811037, "grad_norm": 2.5520551204681396, "learning_rate": 7.10214568551526e-07, "loss": 1.1773, "step": 17339 }, { "epoch": 0.9480266529984623, "grad_norm": 3.4778058528900146, "learning_rate": 7.08728398101921e-07, "loss": 0.8756, "step": 17340 }, { "epoch": 0.9480813258158209, "grad_norm": 2.985661506652832, "learning_rate": 7.072437731366788e-07, "loss": 1.0494, "step": 17341 }, { "epoch": 0.9481359986331795, "grad_norm": 2.5641908645629883, "learning_rate": 7.057606937023565e-07, "loss": 0.8942, "step": 17342 }, { "epoch": 0.9481906714505381, "grad_norm": 2.088078498840332, "learning_rate": 7.042791598454501e-07, "loss": 0.9865, "step": 17343 }, { "epoch": 0.9482453442678968, "grad_norm": 2.5130035877227783, "learning_rate": 7.027991716124171e-07, "loss": 1.0721, "step": 17344 }, { "epoch": 0.9483000170852555, "grad_norm": 2.56851863861084, "learning_rate": 7.013207290496537e-07, "loss": 1.3196, "step": 17345 }, { "epoch": 0.9483546899026141, "grad_norm": 2.717081308364868, "learning_rate": 6.998438322035173e-07, "loss": 1.15, "step": 17346 }, { "epoch": 0.9484093627199727, "grad_norm": 4.854321002960205, "learning_rate": 6.983684811203151e-07, "loss": 0.8827, "step": 17347 }, { "epoch": 0.9484640355373313, "grad_norm": 3.0244147777557373, "learning_rate": 6.968946758463102e-07, "loss": 1.1369, "step": 17348 }, { "epoch": 0.9485187083546899, "grad_norm": 3.2369771003723145, "learning_rate": 6.954224164277101e-07, "loss": 1.1581, "step": 17349 }, { "epoch": 0.9485733811720485, "grad_norm": 2.3064610958099365, "learning_rate": 6.939517029106723e-07, "loss": 1.0119, "step": 17350 }, { "epoch": 0.9486280539894072, "grad_norm": 2.635810613632202, "learning_rate": 6.9248253534131e-07, "loss": 0.9785, "step": 17351 }, { "epoch": 0.9486827268067658, "grad_norm": 2.460029125213623, "learning_rate": 6.910149137656974e-07, "loss": 1.1521, "step": 17352 }, { "epoch": 0.9487373996241244, "grad_norm": 2.827263832092285, "learning_rate": 6.895488382298365e-07, "loss": 1.0349, "step": 17353 }, { "epoch": 0.948792072441483, "grad_norm": 3.0419816970825195, "learning_rate": 6.880843087797017e-07, "loss": 1.1061, "step": 17354 }, { "epoch": 0.9488467452588416, "grad_norm": 2.3237953186035156, "learning_rate": 6.866213254612063e-07, "loss": 1.0092, "step": 17355 }, { "epoch": 0.9489014180762002, "grad_norm": 2.9404900074005127, "learning_rate": 6.851598883202359e-07, "loss": 1.0592, "step": 17356 }, { "epoch": 0.9489560908935588, "grad_norm": 3.1243410110473633, "learning_rate": 6.836999974025982e-07, "loss": 0.906, "step": 17357 }, { "epoch": 0.9490107637109175, "grad_norm": 4.170051574707031, "learning_rate": 6.822416527540731e-07, "loss": 1.2854, "step": 17358 }, { "epoch": 0.9490654365282761, "grad_norm": 2.688415765762329, "learning_rate": 6.807848544203798e-07, "loss": 1.1007, "step": 17359 }, { "epoch": 0.9491201093456347, "grad_norm": 3.2093687057495117, "learning_rate": 6.79329602447204e-07, "loss": 0.8343, "step": 17360 }, { "epoch": 0.9491747821629933, "grad_norm": 3.2210638523101807, "learning_rate": 6.778758968801702e-07, "loss": 0.7151, "step": 17361 }, { "epoch": 0.9492294549803519, "grad_norm": 2.5235533714294434, "learning_rate": 6.76423737764853e-07, "loss": 1.0945, "step": 17362 }, { "epoch": 0.9492841277977105, "grad_norm": 2.883991003036499, "learning_rate": 6.749731251467883e-07, "loss": 1.1848, "step": 17363 }, { "epoch": 0.9493388006150691, "grad_norm": 2.3669207096099854, "learning_rate": 6.735240590714565e-07, "loss": 1.0173, "step": 17364 }, { "epoch": 0.9493934734324279, "grad_norm": 4.159989356994629, "learning_rate": 6.720765395842932e-07, "loss": 0.8755, "step": 17365 }, { "epoch": 0.9494481462497865, "grad_norm": 2.6788878440856934, "learning_rate": 6.706305667306845e-07, "loss": 0.9485, "step": 17366 }, { "epoch": 0.9495028190671451, "grad_norm": 2.554856300354004, "learning_rate": 6.691861405559663e-07, "loss": 0.9098, "step": 17367 }, { "epoch": 0.9495574918845037, "grad_norm": 2.8225409984588623, "learning_rate": 6.677432611054302e-07, "loss": 1.0656, "step": 17368 }, { "epoch": 0.9496121647018623, "grad_norm": 2.381321668624878, "learning_rate": 6.663019284243178e-07, "loss": 0.9453, "step": 17369 }, { "epoch": 0.9496668375192209, "grad_norm": 2.9093711376190186, "learning_rate": 6.64862142557815e-07, "loss": 1.0588, "step": 17370 }, { "epoch": 0.9497215103365795, "grad_norm": 3.369414806365967, "learning_rate": 6.634239035510636e-07, "loss": 0.8349, "step": 17371 }, { "epoch": 0.9497761831539382, "grad_norm": 3.0287413597106934, "learning_rate": 6.619872114491665e-07, "loss": 1.0793, "step": 17372 }, { "epoch": 0.9498308559712968, "grad_norm": 2.140399217605591, "learning_rate": 6.605520662971654e-07, "loss": 1.0608, "step": 17373 }, { "epoch": 0.9498855287886554, "grad_norm": 2.6754510402679443, "learning_rate": 6.59118468140052e-07, "loss": 1.0804, "step": 17374 }, { "epoch": 0.949940201606014, "grad_norm": 2.9705088138580322, "learning_rate": 6.576864170227848e-07, "loss": 0.938, "step": 17375 }, { "epoch": 0.9499948744233726, "grad_norm": 2.971824884414673, "learning_rate": 6.562559129902613e-07, "loss": 1.0474, "step": 17376 }, { "epoch": 0.9500495472407312, "grad_norm": 2.549171209335327, "learning_rate": 6.548269560873343e-07, "loss": 1.1711, "step": 17377 }, { "epoch": 0.9501042200580899, "grad_norm": 3.3891286849975586, "learning_rate": 6.533995463588127e-07, "loss": 0.8263, "step": 17378 }, { "epoch": 0.9501588928754485, "grad_norm": 2.9155263900756836, "learning_rate": 6.519736838494383e-07, "loss": 1.0841, "step": 17379 }, { "epoch": 0.9502135656928071, "grad_norm": 2.1125030517578125, "learning_rate": 6.50549368603931e-07, "loss": 0.8382, "step": 17380 }, { "epoch": 0.9502682385101657, "grad_norm": 3.4561169147491455, "learning_rate": 6.491266006669383e-07, "loss": 1.0361, "step": 17381 }, { "epoch": 0.9503229113275243, "grad_norm": 2.6529481410980225, "learning_rate": 6.477053800830745e-07, "loss": 0.993, "step": 17382 }, { "epoch": 0.9503775841448829, "grad_norm": 3.2128241062164307, "learning_rate": 6.462857068969041e-07, "loss": 1.2312, "step": 17383 }, { "epoch": 0.9504322569622415, "grad_norm": 2.751833915710449, "learning_rate": 6.448675811529359e-07, "loss": 1.0623, "step": 17384 }, { "epoch": 0.9504869297796003, "grad_norm": 2.4085147380828857, "learning_rate": 6.434510028956342e-07, "loss": 1.0021, "step": 17385 }, { "epoch": 0.9505416025969589, "grad_norm": 2.910158634185791, "learning_rate": 6.420359721694136e-07, "loss": 0.8418, "step": 17386 }, { "epoch": 0.9505962754143175, "grad_norm": 2.449901580810547, "learning_rate": 6.406224890186497e-07, "loss": 1.1582, "step": 17387 }, { "epoch": 0.9506509482316761, "grad_norm": 2.0847692489624023, "learning_rate": 6.392105534876458e-07, "loss": 0.7809, "step": 17388 }, { "epoch": 0.9507056210490347, "grad_norm": 2.4422669410705566, "learning_rate": 6.378001656206833e-07, "loss": 1.1369, "step": 17389 }, { "epoch": 0.9507602938663933, "grad_norm": 3.4631588459014893, "learning_rate": 6.363913254619824e-07, "loss": 1.0181, "step": 17390 }, { "epoch": 0.9508149666837519, "grad_norm": 3.1259050369262695, "learning_rate": 6.349840330557133e-07, "loss": 0.9509, "step": 17391 }, { "epoch": 0.9508696395011106, "grad_norm": 3.035825490951538, "learning_rate": 6.335782884460018e-07, "loss": 0.9577, "step": 17392 }, { "epoch": 0.9509243123184692, "grad_norm": 3.7299327850341797, "learning_rate": 6.321740916769181e-07, "loss": 0.9609, "step": 17393 }, { "epoch": 0.9509789851358278, "grad_norm": 2.8271052837371826, "learning_rate": 6.307714427924993e-07, "loss": 0.9217, "step": 17394 }, { "epoch": 0.9510336579531864, "grad_norm": 2.641451597213745, "learning_rate": 6.293703418367158e-07, "loss": 1.0488, "step": 17395 }, { "epoch": 0.951088330770545, "grad_norm": 2.920769453048706, "learning_rate": 6.279707888535047e-07, "loss": 1.1266, "step": 17396 }, { "epoch": 0.9511430035879036, "grad_norm": 2.783092737197876, "learning_rate": 6.265727838867419e-07, "loss": 1.1113, "step": 17397 }, { "epoch": 0.9511976764052622, "grad_norm": 2.720755100250244, "learning_rate": 6.251763269802646e-07, "loss": 1.1034, "step": 17398 }, { "epoch": 0.9512523492226209, "grad_norm": 2.362133264541626, "learning_rate": 6.237814181778601e-07, "loss": 1.0289, "step": 17399 }, { "epoch": 0.9513070220399795, "grad_norm": 1.9994606971740723, "learning_rate": 6.223880575232599e-07, "loss": 0.8053, "step": 17400 }, { "epoch": 0.9513616948573381, "grad_norm": 3.127119302749634, "learning_rate": 6.209962450601459e-07, "loss": 0.9976, "step": 17401 }, { "epoch": 0.9514163676746967, "grad_norm": 2.409264087677002, "learning_rate": 6.196059808321719e-07, "loss": 1.1115, "step": 17402 }, { "epoch": 0.9514710404920553, "grad_norm": 2.3274929523468018, "learning_rate": 6.182172648829143e-07, "loss": 0.9036, "step": 17403 }, { "epoch": 0.9515257133094139, "grad_norm": 2.667407512664795, "learning_rate": 6.168300972559216e-07, "loss": 1.0089, "step": 17404 }, { "epoch": 0.9515803861267726, "grad_norm": 2.7880589962005615, "learning_rate": 6.154444779946866e-07, "loss": 0.9671, "step": 17405 }, { "epoch": 0.9516350589441313, "grad_norm": 3.0144124031066895, "learning_rate": 6.140604071426582e-07, "loss": 1.2064, "step": 17406 }, { "epoch": 0.9516897317614899, "grad_norm": 2.1900081634521484, "learning_rate": 6.126778847432236e-07, "loss": 0.978, "step": 17407 }, { "epoch": 0.9517444045788485, "grad_norm": 3.567385196685791, "learning_rate": 6.11296910839737e-07, "loss": 1.0215, "step": 17408 }, { "epoch": 0.9517990773962071, "grad_norm": 2.948760509490967, "learning_rate": 6.099174854754974e-07, "loss": 1.0376, "step": 17409 }, { "epoch": 0.9518537502135657, "grad_norm": 3.1649701595306396, "learning_rate": 6.085396086937534e-07, "loss": 0.9757, "step": 17410 }, { "epoch": 0.9519084230309243, "grad_norm": 2.45173978805542, "learning_rate": 6.071632805377092e-07, "loss": 0.9687, "step": 17411 }, { "epoch": 0.951963095848283, "grad_norm": 2.8579981327056885, "learning_rate": 6.057885010505194e-07, "loss": 1.0599, "step": 17412 }, { "epoch": 0.9520177686656416, "grad_norm": 2.297956705093384, "learning_rate": 6.044152702752825e-07, "loss": 1.003, "step": 17413 }, { "epoch": 0.9520724414830002, "grad_norm": 2.474226474761963, "learning_rate": 6.030435882550589e-07, "loss": 0.9997, "step": 17414 }, { "epoch": 0.9521271143003588, "grad_norm": 2.3370249271392822, "learning_rate": 6.016734550328585e-07, "loss": 1.0042, "step": 17415 }, { "epoch": 0.9521817871177174, "grad_norm": 2.4054839611053467, "learning_rate": 6.003048706516357e-07, "loss": 1.0075, "step": 17416 }, { "epoch": 0.952236459935076, "grad_norm": 2.8951945304870605, "learning_rate": 5.989378351543117e-07, "loss": 1.1873, "step": 17417 }, { "epoch": 0.9522911327524346, "grad_norm": 2.2512547969818115, "learning_rate": 5.975723485837359e-07, "loss": 0.955, "step": 17418 }, { "epoch": 0.9523458055697933, "grad_norm": 2.14374041557312, "learning_rate": 5.962084109827292e-07, "loss": 1.0715, "step": 17419 }, { "epoch": 0.9524004783871519, "grad_norm": 2.9222922325134277, "learning_rate": 5.948460223940577e-07, "loss": 1.046, "step": 17420 }, { "epoch": 0.9524551512045105, "grad_norm": 2.089449882507324, "learning_rate": 5.934851828604316e-07, "loss": 0.8667, "step": 17421 }, { "epoch": 0.9525098240218691, "grad_norm": 2.9096341133117676, "learning_rate": 5.921258924245221e-07, "loss": 1.1724, "step": 17422 }, { "epoch": 0.9525644968392277, "grad_norm": 2.4553041458129883, "learning_rate": 5.907681511289509e-07, "loss": 0.9933, "step": 17423 }, { "epoch": 0.9526191696565863, "grad_norm": 2.7185709476470947, "learning_rate": 5.894119590162783e-07, "loss": 1.0108, "step": 17424 }, { "epoch": 0.9526738424739449, "grad_norm": 2.5560736656188965, "learning_rate": 5.880573161290426e-07, "loss": 1.0857, "step": 17425 }, { "epoch": 0.9527285152913036, "grad_norm": 3.0511302947998047, "learning_rate": 5.867042225097097e-07, "loss": 1.1656, "step": 17426 }, { "epoch": 0.9527831881086622, "grad_norm": 2.1194980144500732, "learning_rate": 5.853526782007068e-07, "loss": 0.9331, "step": 17427 }, { "epoch": 0.9528378609260209, "grad_norm": 2.267085552215576, "learning_rate": 5.840026832444057e-07, "loss": 1.093, "step": 17428 }, { "epoch": 0.9528925337433795, "grad_norm": 2.645339012145996, "learning_rate": 5.826542376831334e-07, "loss": 0.9325, "step": 17429 }, { "epoch": 0.9529472065607381, "grad_norm": 2.8380446434020996, "learning_rate": 5.813073415591785e-07, "loss": 1.2156, "step": 17430 }, { "epoch": 0.9530018793780967, "grad_norm": 2.32420015335083, "learning_rate": 5.799619949147628e-07, "loss": 0.9819, "step": 17431 }, { "epoch": 0.9530565521954554, "grad_norm": 2.682656764984131, "learning_rate": 5.786181977920746e-07, "loss": 0.9189, "step": 17432 }, { "epoch": 0.953111225012814, "grad_norm": 2.560391426086426, "learning_rate": 5.772759502332414e-07, "loss": 0.9852, "step": 17433 }, { "epoch": 0.9531658978301726, "grad_norm": 2.8535778522491455, "learning_rate": 5.759352522803519e-07, "loss": 0.9843, "step": 17434 }, { "epoch": 0.9532205706475312, "grad_norm": 2.5222907066345215, "learning_rate": 5.745961039754388e-07, "loss": 1.0515, "step": 17435 }, { "epoch": 0.9532752434648898, "grad_norm": 2.649176597595215, "learning_rate": 5.732585053604966e-07, "loss": 0.9924, "step": 17436 }, { "epoch": 0.9533299162822484, "grad_norm": 2.606102705001831, "learning_rate": 5.719224564774583e-07, "loss": 1.2269, "step": 17437 }, { "epoch": 0.953384589099607, "grad_norm": 2.504573345184326, "learning_rate": 5.705879573682238e-07, "loss": 1.1812, "step": 17438 }, { "epoch": 0.9534392619169657, "grad_norm": 2.5353662967681885, "learning_rate": 5.692550080746206e-07, "loss": 0.8676, "step": 17439 }, { "epoch": 0.9534939347343243, "grad_norm": 2.052440881729126, "learning_rate": 5.679236086384542e-07, "loss": 0.9013, "step": 17440 }, { "epoch": 0.9535486075516829, "grad_norm": 3.2825186252593994, "learning_rate": 5.665937591014637e-07, "loss": 0.9836, "step": 17441 }, { "epoch": 0.9536032803690415, "grad_norm": 3.1301815509796143, "learning_rate": 5.652654595053486e-07, "loss": 1.013, "step": 17442 }, { "epoch": 0.9536579531864001, "grad_norm": 2.1844558715820312, "learning_rate": 5.639387098917537e-07, "loss": 0.8711, "step": 17443 }, { "epoch": 0.9537126260037587, "grad_norm": 2.1448261737823486, "learning_rate": 5.626135103022845e-07, "loss": 1.0107, "step": 17444 }, { "epoch": 0.9537672988211173, "grad_norm": 4.557733058929443, "learning_rate": 5.612898607784744e-07, "loss": 0.9051, "step": 17445 }, { "epoch": 0.953821971638476, "grad_norm": 3.0602943897247314, "learning_rate": 5.599677613618459e-07, "loss": 0.914, "step": 17446 }, { "epoch": 0.9538766444558346, "grad_norm": 3.8541102409362793, "learning_rate": 5.586472120938435e-07, "loss": 1.0744, "step": 17447 }, { "epoch": 0.9539313172731932, "grad_norm": 3.274722099304199, "learning_rate": 5.573282130158675e-07, "loss": 1.0087, "step": 17448 }, { "epoch": 0.9539859900905518, "grad_norm": 2.5584542751312256, "learning_rate": 5.560107641692791e-07, "loss": 0.9934, "step": 17449 }, { "epoch": 0.9540406629079105, "grad_norm": 2.5295023918151855, "learning_rate": 5.546948655953899e-07, "loss": 0.9731, "step": 17450 }, { "epoch": 0.9540953357252691, "grad_norm": 2.1891250610351562, "learning_rate": 5.533805173354501e-07, "loss": 0.9011, "step": 17451 }, { "epoch": 0.9541500085426277, "grad_norm": 2.7718710899353027, "learning_rate": 5.520677194306711e-07, "loss": 1.1076, "step": 17452 }, { "epoch": 0.9542046813599864, "grad_norm": 2.564728260040283, "learning_rate": 5.507564719222202e-07, "loss": 1.0135, "step": 17453 }, { "epoch": 0.954259354177345, "grad_norm": 2.398324489593506, "learning_rate": 5.494467748512089e-07, "loss": 1.0753, "step": 17454 }, { "epoch": 0.9543140269947036, "grad_norm": 2.7774994373321533, "learning_rate": 5.481386282586986e-07, "loss": 1.1029, "step": 17455 }, { "epoch": 0.9543686998120622, "grad_norm": 3.229844570159912, "learning_rate": 5.468320321857067e-07, "loss": 0.9806, "step": 17456 }, { "epoch": 0.9544233726294208, "grad_norm": 2.684152603149414, "learning_rate": 5.455269866731949e-07, "loss": 0.8372, "step": 17457 }, { "epoch": 0.9544780454467794, "grad_norm": 2.6855857372283936, "learning_rate": 5.442234917620914e-07, "loss": 1.0517, "step": 17458 }, { "epoch": 0.9545327182641381, "grad_norm": 2.316377878189087, "learning_rate": 5.42921547493258e-07, "loss": 0.9455, "step": 17459 }, { "epoch": 0.9545873910814967, "grad_norm": 3.3700711727142334, "learning_rate": 5.416211539075233e-07, "loss": 1.042, "step": 17460 }, { "epoch": 0.9546420638988553, "grad_norm": 2.196859836578369, "learning_rate": 5.403223110456601e-07, "loss": 1.1097, "step": 17461 }, { "epoch": 0.9546967367162139, "grad_norm": 2.687530517578125, "learning_rate": 5.390250189483803e-07, "loss": 0.81, "step": 17462 }, { "epoch": 0.9547514095335725, "grad_norm": 3.1842918395996094, "learning_rate": 5.377292776563736e-07, "loss": 0.85, "step": 17463 }, { "epoch": 0.9548060823509311, "grad_norm": 2.7838337421417236, "learning_rate": 5.36435087210263e-07, "loss": 1.0936, "step": 17464 }, { "epoch": 0.9548607551682897, "grad_norm": 3.016453981399536, "learning_rate": 5.351424476506217e-07, "loss": 1.0128, "step": 17465 }, { "epoch": 0.9549154279856484, "grad_norm": 3.1330642700195312, "learning_rate": 5.338513590179783e-07, "loss": 1.2429, "step": 17466 }, { "epoch": 0.954970100803007, "grad_norm": 2.399493455886841, "learning_rate": 5.325618213528228e-07, "loss": 0.9251, "step": 17467 }, { "epoch": 0.9550247736203656, "grad_norm": 1.9413560628890991, "learning_rate": 5.312738346955781e-07, "loss": 0.7547, "step": 17468 }, { "epoch": 0.9550794464377242, "grad_norm": 2.7799267768859863, "learning_rate": 5.2998739908664e-07, "loss": 1.1404, "step": 17469 }, { "epoch": 0.9551341192550828, "grad_norm": 3.251594305038452, "learning_rate": 5.287025145663316e-07, "loss": 1.0506, "step": 17470 }, { "epoch": 0.9551887920724415, "grad_norm": 3.270045042037964, "learning_rate": 5.274191811749373e-07, "loss": 1.0038, "step": 17471 }, { "epoch": 0.9552434648898, "grad_norm": 2.621490001678467, "learning_rate": 5.261373989527085e-07, "loss": 1.0652, "step": 17472 }, { "epoch": 0.9552981377071588, "grad_norm": 3.3737220764160156, "learning_rate": 5.24857167939824e-07, "loss": 1.1873, "step": 17473 }, { "epoch": 0.9553528105245174, "grad_norm": 2.528900384902954, "learning_rate": 5.235784881764294e-07, "loss": 1.0499, "step": 17474 }, { "epoch": 0.955407483341876, "grad_norm": 2.3665010929107666, "learning_rate": 5.223013597026094e-07, "loss": 0.988, "step": 17475 }, { "epoch": 0.9554621561592346, "grad_norm": 2.187459707260132, "learning_rate": 5.210257825584209e-07, "loss": 0.8891, "step": 17476 }, { "epoch": 0.9555168289765932, "grad_norm": 2.9954378604888916, "learning_rate": 5.197517567838428e-07, "loss": 1.1156, "step": 17477 }, { "epoch": 0.9555715017939518, "grad_norm": 2.369832754135132, "learning_rate": 5.184792824188323e-07, "loss": 0.8954, "step": 17478 }, { "epoch": 0.9556261746113104, "grad_norm": 2.7271640300750732, "learning_rate": 5.172083595032795e-07, "loss": 0.8708, "step": 17479 }, { "epoch": 0.9556808474286691, "grad_norm": 2.497788906097412, "learning_rate": 5.15938988077036e-07, "loss": 1.1127, "step": 17480 }, { "epoch": 0.9557355202460277, "grad_norm": 2.412296772003174, "learning_rate": 5.146711681799033e-07, "loss": 1.0907, "step": 17481 }, { "epoch": 0.9557901930633863, "grad_norm": 2.886820077896118, "learning_rate": 5.134048998516328e-07, "loss": 0.9396, "step": 17482 }, { "epoch": 0.9558448658807449, "grad_norm": 3.613264799118042, "learning_rate": 5.121401831319206e-07, "loss": 0.8214, "step": 17483 }, { "epoch": 0.9558995386981035, "grad_norm": 2.5694422721862793, "learning_rate": 5.108770180604295e-07, "loss": 1.1523, "step": 17484 }, { "epoch": 0.9559542115154621, "grad_norm": 2.7817442417144775, "learning_rate": 5.096154046767609e-07, "loss": 1.0641, "step": 17485 }, { "epoch": 0.9560088843328208, "grad_norm": 3.141854763031006, "learning_rate": 5.083553430204723e-07, "loss": 1.1507, "step": 17486 }, { "epoch": 0.9560635571501794, "grad_norm": 2.9156014919281006, "learning_rate": 5.070968331310766e-07, "loss": 0.9904, "step": 17487 }, { "epoch": 0.956118229967538, "grad_norm": 1.8583340644836426, "learning_rate": 5.058398750480198e-07, "loss": 0.9467, "step": 17488 }, { "epoch": 0.9561729027848966, "grad_norm": 3.4056012630462646, "learning_rate": 5.045844688107259e-07, "loss": 1.1296, "step": 17489 }, { "epoch": 0.9562275756022552, "grad_norm": 2.716237783432007, "learning_rate": 5.033306144585526e-07, "loss": 1.2923, "step": 17490 }, { "epoch": 0.9562822484196138, "grad_norm": 3.777815818786621, "learning_rate": 5.020783120308125e-07, "loss": 1.4188, "step": 17491 }, { "epoch": 0.9563369212369724, "grad_norm": 4.639859199523926, "learning_rate": 5.008275615667746e-07, "loss": 1.0455, "step": 17492 }, { "epoch": 0.9563915940543312, "grad_norm": 2.067769765853882, "learning_rate": 4.995783631056406e-07, "loss": 0.8665, "step": 17493 }, { "epoch": 0.9564462668716898, "grad_norm": 2.7590954303741455, "learning_rate": 4.983307166866014e-07, "loss": 0.8946, "step": 17494 }, { "epoch": 0.9565009396890484, "grad_norm": 2.3714449405670166, "learning_rate": 4.97084622348759e-07, "loss": 0.8048, "step": 17495 }, { "epoch": 0.956555612506407, "grad_norm": 4.133817672729492, "learning_rate": 4.958400801311824e-07, "loss": 1.0759, "step": 17496 }, { "epoch": 0.9566102853237656, "grad_norm": 2.5750784873962402, "learning_rate": 4.945970900729069e-07, "loss": 0.9064, "step": 17497 }, { "epoch": 0.9566649581411242, "grad_norm": 3.997417688369751, "learning_rate": 4.933556522128957e-07, "loss": 1.1292, "step": 17498 }, { "epoch": 0.9567196309584828, "grad_norm": 2.415170669555664, "learning_rate": 4.921157665900733e-07, "loss": 0.7366, "step": 17499 }, { "epoch": 0.9567743037758415, "grad_norm": 2.6759276390075684, "learning_rate": 4.908774332433141e-07, "loss": 0.9077, "step": 17500 }, { "epoch": 0.9568289765932001, "grad_norm": 2.663994312286377, "learning_rate": 4.896406522114482e-07, "loss": 1.1324, "step": 17501 }, { "epoch": 0.9568836494105587, "grad_norm": 2.47579288482666, "learning_rate": 4.884054235332558e-07, "loss": 0.9262, "step": 17502 }, { "epoch": 0.9569383222279173, "grad_norm": 2.429328203201294, "learning_rate": 4.871717472474613e-07, "loss": 1.0219, "step": 17503 }, { "epoch": 0.9569929950452759, "grad_norm": 4.5865159034729, "learning_rate": 4.859396233927449e-07, "loss": 1.1247, "step": 17504 }, { "epoch": 0.9570476678626345, "grad_norm": 2.8553647994995117, "learning_rate": 4.847090520077479e-07, "loss": 1.0302, "step": 17505 }, { "epoch": 0.9571023406799931, "grad_norm": 2.6881284713745117, "learning_rate": 4.834800331310452e-07, "loss": 1.0878, "step": 17506 }, { "epoch": 0.9571570134973518, "grad_norm": 2.2225587368011475, "learning_rate": 4.822525668011724e-07, "loss": 0.8606, "step": 17507 }, { "epoch": 0.9572116863147104, "grad_norm": 2.417675733566284, "learning_rate": 4.810266530566154e-07, "loss": 0.9809, "step": 17508 }, { "epoch": 0.957266359132069, "grad_norm": 2.345674514770508, "learning_rate": 4.798022919358159e-07, "loss": 1.0584, "step": 17509 }, { "epoch": 0.9573210319494276, "grad_norm": 2.367136001586914, "learning_rate": 4.785794834771596e-07, "loss": 0.9501, "step": 17510 }, { "epoch": 0.9573757047667862, "grad_norm": 2.776840925216675, "learning_rate": 4.773582277189881e-07, "loss": 0.9202, "step": 17511 }, { "epoch": 0.9574303775841448, "grad_norm": 2.591130256652832, "learning_rate": 4.761385246995875e-07, "loss": 1.0263, "step": 17512 }, { "epoch": 0.9574850504015036, "grad_norm": 2.405137300491333, "learning_rate": 4.749203744572106e-07, "loss": 0.9275, "step": 17513 }, { "epoch": 0.9575397232188622, "grad_norm": 2.375462532043457, "learning_rate": 4.737037770300434e-07, "loss": 1.1076, "step": 17514 }, { "epoch": 0.9575943960362208, "grad_norm": 2.2454535961151123, "learning_rate": 4.7248873245623325e-07, "loss": 1.0731, "step": 17515 }, { "epoch": 0.9576490688535794, "grad_norm": 2.145598888397217, "learning_rate": 4.712752407738774e-07, "loss": 1.0411, "step": 17516 }, { "epoch": 0.957703741670938, "grad_norm": 3.388408899307251, "learning_rate": 4.7006330202102323e-07, "loss": 0.8435, "step": 17517 }, { "epoch": 0.9577584144882966, "grad_norm": 2.667274236679077, "learning_rate": 4.688529162356681e-07, "loss": 1.0292, "step": 17518 }, { "epoch": 0.9578130873056552, "grad_norm": 2.333019971847534, "learning_rate": 4.6764408345576494e-07, "loss": 0.9824, "step": 17519 }, { "epoch": 0.9578677601230139, "grad_norm": 2.7561559677124023, "learning_rate": 4.664368037192168e-07, "loss": 0.9893, "step": 17520 }, { "epoch": 0.9579224329403725, "grad_norm": 2.6074132919311523, "learning_rate": 4.652310770638768e-07, "loss": 1.0935, "step": 17521 }, { "epoch": 0.9579771057577311, "grad_norm": 2.670668363571167, "learning_rate": 4.640269035275424e-07, "loss": 1.1228, "step": 17522 }, { "epoch": 0.9580317785750897, "grad_norm": 2.6048009395599365, "learning_rate": 4.628242831479834e-07, "loss": 1.0819, "step": 17523 }, { "epoch": 0.9580864513924483, "grad_norm": 2.695547342300415, "learning_rate": 4.6162321596289196e-07, "loss": 1.0968, "step": 17524 }, { "epoch": 0.9581411242098069, "grad_norm": 2.3911373615264893, "learning_rate": 4.604237020099378e-07, "loss": 0.8119, "step": 17525 }, { "epoch": 0.9581957970271655, "grad_norm": 2.8583426475524902, "learning_rate": 4.5922574132672424e-07, "loss": 1.0984, "step": 17526 }, { "epoch": 0.9582504698445242, "grad_norm": 2.221538543701172, "learning_rate": 4.5802933395081015e-07, "loss": 0.87, "step": 17527 }, { "epoch": 0.9583051426618828, "grad_norm": 2.915008068084717, "learning_rate": 4.568344799197155e-07, "loss": 1.0759, "step": 17528 }, { "epoch": 0.9583598154792414, "grad_norm": 2.6691651344299316, "learning_rate": 4.5564117927090476e-07, "loss": 1.0093, "step": 17529 }, { "epoch": 0.9584144882966, "grad_norm": 2.2289912700653076, "learning_rate": 4.544494320417814e-07, "loss": 1.0989, "step": 17530 }, { "epoch": 0.9584691611139586, "grad_norm": 2.238738536834717, "learning_rate": 4.532592382697209e-07, "loss": 0.9871, "step": 17531 }, { "epoch": 0.9585238339313172, "grad_norm": 2.4396135807037354, "learning_rate": 4.5207059799203254e-07, "loss": 1.1247, "step": 17532 }, { "epoch": 0.9585785067486758, "grad_norm": 2.490346670150757, "learning_rate": 4.508835112459975e-07, "loss": 1.0915, "step": 17533 }, { "epoch": 0.9586331795660346, "grad_norm": 2.839630126953125, "learning_rate": 4.4969797806882485e-07, "loss": 1.1963, "step": 17534 }, { "epoch": 0.9586878523833932, "grad_norm": 2.5647964477539062, "learning_rate": 4.485139984976905e-07, "loss": 1.0906, "step": 17535 }, { "epoch": 0.9587425252007518, "grad_norm": 2.82757568359375, "learning_rate": 4.4733157256972024e-07, "loss": 1.0199, "step": 17536 }, { "epoch": 0.9587971980181104, "grad_norm": 2.9612793922424316, "learning_rate": 4.461507003219845e-07, "loss": 1.2677, "step": 17537 }, { "epoch": 0.958851870835469, "grad_norm": 2.5747852325439453, "learning_rate": 4.4497138179150356e-07, "loss": 0.9225, "step": 17538 }, { "epoch": 0.9589065436528276, "grad_norm": 2.6363136768341064, "learning_rate": 4.4379361701526456e-07, "loss": 1.106, "step": 17539 }, { "epoch": 0.9589612164701863, "grad_norm": 3.063441514968872, "learning_rate": 4.426174060301824e-07, "loss": 1.0392, "step": 17540 }, { "epoch": 0.9590158892875449, "grad_norm": 2.763732433319092, "learning_rate": 4.4144274887314986e-07, "loss": 0.988, "step": 17541 }, { "epoch": 0.9590705621049035, "grad_norm": 2.564911127090454, "learning_rate": 4.4026964558098736e-07, "loss": 0.9777, "step": 17542 }, { "epoch": 0.9591252349222621, "grad_norm": 2.270610809326172, "learning_rate": 4.3909809619047673e-07, "loss": 0.9695, "step": 17543 }, { "epoch": 0.9591799077396207, "grad_norm": 2.9685518741607666, "learning_rate": 4.379281007383607e-07, "loss": 1.0031, "step": 17544 }, { "epoch": 0.9592345805569793, "grad_norm": 2.832719326019287, "learning_rate": 4.3675965926131547e-07, "loss": 0.8605, "step": 17545 }, { "epoch": 0.9592892533743379, "grad_norm": 3.0950169563293457, "learning_rate": 4.355927717959729e-07, "loss": 1.1223, "step": 17546 }, { "epoch": 0.9593439261916966, "grad_norm": 2.2132039070129395, "learning_rate": 4.344274383789315e-07, "loss": 0.908, "step": 17547 }, { "epoch": 0.9593985990090552, "grad_norm": 3.4570086002349854, "learning_rate": 4.332636590467176e-07, "loss": 0.8309, "step": 17548 }, { "epoch": 0.9594532718264138, "grad_norm": 2.4936912059783936, "learning_rate": 4.3210143383582423e-07, "loss": 0.858, "step": 17549 }, { "epoch": 0.9595079446437724, "grad_norm": 3.9471054077148438, "learning_rate": 4.3094076278269447e-07, "loss": 1.0083, "step": 17550 }, { "epoch": 0.959562617461131, "grad_norm": 3.172452688217163, "learning_rate": 4.2978164592372136e-07, "loss": 1.0896, "step": 17551 }, { "epoch": 0.9596172902784896, "grad_norm": 2.451496124267578, "learning_rate": 4.2862408329523706e-07, "loss": 1.0912, "step": 17552 }, { "epoch": 0.9596719630958482, "grad_norm": 2.7913436889648438, "learning_rate": 4.2746807493355133e-07, "loss": 1.1701, "step": 17553 }, { "epoch": 0.959726635913207, "grad_norm": 2.096423864364624, "learning_rate": 4.263136208749019e-07, "loss": 0.8142, "step": 17554 }, { "epoch": 0.9597813087305656, "grad_norm": 3.034086227416992, "learning_rate": 4.2516072115548756e-07, "loss": 1.1313, "step": 17555 }, { "epoch": 0.9598359815479242, "grad_norm": 2.1621644496917725, "learning_rate": 4.2400937581145164e-07, "loss": 0.8575, "step": 17556 }, { "epoch": 0.9598906543652828, "grad_norm": 2.635409355163574, "learning_rate": 4.2285958487889853e-07, "loss": 0.9745, "step": 17557 }, { "epoch": 0.9599453271826414, "grad_norm": 2.5041849613189697, "learning_rate": 4.2171134839387726e-07, "loss": 0.9857, "step": 17558 }, { "epoch": 0.96, "grad_norm": 2.5871260166168213, "learning_rate": 4.2056466639239234e-07, "loss": 1.1193, "step": 17559 }, { "epoch": 0.9600546728173586, "grad_norm": 2.504932403564453, "learning_rate": 4.194195389103872e-07, "loss": 0.8928, "step": 17560 }, { "epoch": 0.9601093456347173, "grad_norm": 3.2863926887512207, "learning_rate": 4.182759659837776e-07, "loss": 1.0446, "step": 17561 }, { "epoch": 0.9601640184520759, "grad_norm": 3.342402935028076, "learning_rate": 4.171339476484182e-07, "loss": 1.2945, "step": 17562 }, { "epoch": 0.9602186912694345, "grad_norm": 2.5390491485595703, "learning_rate": 4.159934839401136e-07, "loss": 0.9302, "step": 17563 }, { "epoch": 0.9602733640867931, "grad_norm": 2.574120283126831, "learning_rate": 4.1485457489461863e-07, "loss": 1.1896, "step": 17564 }, { "epoch": 0.9603280369041517, "grad_norm": 3.2910048961639404, "learning_rate": 4.137172205476436e-07, "loss": 1.1726, "step": 17565 }, { "epoch": 0.9603827097215103, "grad_norm": 2.848109245300293, "learning_rate": 4.1258142093485996e-07, "loss": 1.06, "step": 17566 }, { "epoch": 0.960437382538869, "grad_norm": 2.4726974964141846, "learning_rate": 4.1144717609186143e-07, "loss": 1.1219, "step": 17567 }, { "epoch": 0.9604920553562276, "grad_norm": 2.706986665725708, "learning_rate": 4.103144860542252e-07, "loss": 1.1854, "step": 17568 }, { "epoch": 0.9605467281735862, "grad_norm": 4.103484153747559, "learning_rate": 4.091833508574616e-07, "loss": 1.1356, "step": 17569 }, { "epoch": 0.9606014009909448, "grad_norm": 2.697551727294922, "learning_rate": 4.0805377053703686e-07, "loss": 1.0242, "step": 17570 }, { "epoch": 0.9606560738083034, "grad_norm": 2.4983456134796143, "learning_rate": 4.06925745128367e-07, "loss": 1.1166, "step": 17571 }, { "epoch": 0.960710746625662, "grad_norm": 2.931918144226074, "learning_rate": 4.057992746668182e-07, "loss": 1.118, "step": 17572 }, { "epoch": 0.9607654194430206, "grad_norm": 2.6080799102783203, "learning_rate": 4.0467435918771777e-07, "loss": 0.9643, "step": 17573 }, { "epoch": 0.9608200922603793, "grad_norm": 2.9730279445648193, "learning_rate": 4.035509987263264e-07, "loss": 1.0469, "step": 17574 }, { "epoch": 0.960874765077738, "grad_norm": 4.114807605743408, "learning_rate": 4.02429193317877e-07, "loss": 1.2034, "step": 17575 }, { "epoch": 0.9609294378950965, "grad_norm": 2.709913969039917, "learning_rate": 4.013089429975303e-07, "loss": 1.0128, "step": 17576 }, { "epoch": 0.9609841107124552, "grad_norm": 2.4312024116516113, "learning_rate": 4.001902478004194e-07, "loss": 1.1065, "step": 17577 }, { "epoch": 0.9610387835298138, "grad_norm": 3.119935989379883, "learning_rate": 3.990731077616161e-07, "loss": 1.0657, "step": 17578 }, { "epoch": 0.9610934563471724, "grad_norm": 2.6710572242736816, "learning_rate": 3.979575229161481e-07, "loss": 0.9771, "step": 17579 }, { "epoch": 0.961148129164531, "grad_norm": 2.390918493270874, "learning_rate": 3.968434932989984e-07, "loss": 0.8215, "step": 17580 }, { "epoch": 0.9612028019818897, "grad_norm": 2.8532192707061768, "learning_rate": 3.9573101894508913e-07, "loss": 1.0075, "step": 17581 }, { "epoch": 0.9612574747992483, "grad_norm": 2.238831043243408, "learning_rate": 3.946200998893035e-07, "loss": 0.8578, "step": 17582 }, { "epoch": 0.9613121476166069, "grad_norm": 2.4984171390533447, "learning_rate": 3.935107361664747e-07, "loss": 1.0851, "step": 17583 }, { "epoch": 0.9613668204339655, "grad_norm": 2.8352103233337402, "learning_rate": 3.924029278113861e-07, "loss": 1.1551, "step": 17584 }, { "epoch": 0.9614214932513241, "grad_norm": 2.725318431854248, "learning_rate": 3.912966748587765e-07, "loss": 1.1379, "step": 17585 }, { "epoch": 0.9614761660686827, "grad_norm": 2.618055820465088, "learning_rate": 3.9019197734331823e-07, "loss": 0.9797, "step": 17586 }, { "epoch": 0.9615308388860413, "grad_norm": 2.483088493347168, "learning_rate": 3.890888352996613e-07, "loss": 0.8774, "step": 17587 }, { "epoch": 0.9615855117034, "grad_norm": 2.7084853649139404, "learning_rate": 3.879872487623837e-07, "loss": 1.1655, "step": 17588 }, { "epoch": 0.9616401845207586, "grad_norm": 5.121312141418457, "learning_rate": 3.8688721776603543e-07, "loss": 1.4203, "step": 17589 }, { "epoch": 0.9616948573381172, "grad_norm": 3.281898260116577, "learning_rate": 3.8578874234509457e-07, "loss": 1.0515, "step": 17590 }, { "epoch": 0.9617495301554758, "grad_norm": 3.1820881366729736, "learning_rate": 3.8469182253401126e-07, "loss": 0.9095, "step": 17591 }, { "epoch": 0.9618042029728344, "grad_norm": 2.4696133136749268, "learning_rate": 3.835964583671803e-07, "loss": 1.0114, "step": 17592 }, { "epoch": 0.961858875790193, "grad_norm": 3.1015665531158447, "learning_rate": 3.8250264987893524e-07, "loss": 1.1302, "step": 17593 }, { "epoch": 0.9619135486075517, "grad_norm": 2.993757963180542, "learning_rate": 3.814103971035876e-07, "loss": 1.0204, "step": 17594 }, { "epoch": 0.9619682214249103, "grad_norm": 2.82755184173584, "learning_rate": 3.8031970007536553e-07, "loss": 1.0325, "step": 17595 }, { "epoch": 0.9620228942422689, "grad_norm": 2.340731382369995, "learning_rate": 3.792305588284806e-07, "loss": 0.8412, "step": 17596 }, { "epoch": 0.9620775670596275, "grad_norm": 2.6089987754821777, "learning_rate": 3.781429733970776e-07, "loss": 1.0564, "step": 17597 }, { "epoch": 0.9621322398769862, "grad_norm": 2.234192371368408, "learning_rate": 3.7705694381525713e-07, "loss": 1.004, "step": 17598 }, { "epoch": 0.9621869126943448, "grad_norm": 2.959531307220459, "learning_rate": 3.759724701170697e-07, "loss": 1.0683, "step": 17599 }, { "epoch": 0.9622415855117034, "grad_norm": 2.5313847064971924, "learning_rate": 3.7488955233652143e-07, "loss": 0.9917, "step": 17600 }, { "epoch": 0.9622962583290621, "grad_norm": 2.5969130992889404, "learning_rate": 3.738081905075574e-07, "loss": 0.9687, "step": 17601 }, { "epoch": 0.9623509311464207, "grad_norm": 2.8154256343841553, "learning_rate": 3.7272838466408944e-07, "loss": 0.9139, "step": 17602 }, { "epoch": 0.9624056039637793, "grad_norm": 2.6476027965545654, "learning_rate": 3.716501348399737e-07, "loss": 1.0591, "step": 17603 }, { "epoch": 0.9624602767811379, "grad_norm": 2.7765843868255615, "learning_rate": 3.70573441069022e-07, "loss": 0.9362, "step": 17604 }, { "epoch": 0.9625149495984965, "grad_norm": 2.838279962539673, "learning_rate": 3.6949830338498527e-07, "loss": 1.1146, "step": 17605 }, { "epoch": 0.9625696224158551, "grad_norm": 2.37862229347229, "learning_rate": 3.684247218215753e-07, "loss": 0.9257, "step": 17606 }, { "epoch": 0.9626242952332137, "grad_norm": 2.949885845184326, "learning_rate": 3.6735269641245407e-07, "loss": 1.0767, "step": 17607 }, { "epoch": 0.9626789680505724, "grad_norm": 4.250142574310303, "learning_rate": 3.662822271912336e-07, "loss": 1.0741, "step": 17608 }, { "epoch": 0.962733640867931, "grad_norm": 3.3536930084228516, "learning_rate": 3.652133141914815e-07, "loss": 1.099, "step": 17609 }, { "epoch": 0.9627883136852896, "grad_norm": 2.8789074420928955, "learning_rate": 3.641459574467043e-07, "loss": 1.0399, "step": 17610 }, { "epoch": 0.9628429865026482, "grad_norm": 2.9089863300323486, "learning_rate": 3.6308015699038076e-07, "loss": 0.9436, "step": 17611 }, { "epoch": 0.9628976593200068, "grad_norm": 2.794689893722534, "learning_rate": 3.6201591285591753e-07, "loss": 0.9837, "step": 17612 }, { "epoch": 0.9629523321373654, "grad_norm": 2.5938785076141357, "learning_rate": 3.609532250766823e-07, "loss": 0.9537, "step": 17613 }, { "epoch": 0.963007004954724, "grad_norm": 2.170825958251953, "learning_rate": 3.59892093686004e-07, "loss": 1.1078, "step": 17614 }, { "epoch": 0.9630616777720827, "grad_norm": 2.7635018825531006, "learning_rate": 3.5883251871714486e-07, "loss": 1.1005, "step": 17615 }, { "epoch": 0.9631163505894413, "grad_norm": 2.648714542388916, "learning_rate": 3.5777450020333394e-07, "loss": 0.9367, "step": 17616 }, { "epoch": 0.9631710234067999, "grad_norm": 2.553187847137451, "learning_rate": 3.567180381777335e-07, "loss": 1.0937, "step": 17617 }, { "epoch": 0.9632256962241585, "grad_norm": 2.918668746948242, "learning_rate": 3.556631326734783e-07, "loss": 0.9877, "step": 17618 }, { "epoch": 0.9632803690415171, "grad_norm": 2.8754799365997314, "learning_rate": 3.546097837236417e-07, "loss": 0.8852, "step": 17619 }, { "epoch": 0.9633350418588758, "grad_norm": 2.4803478717803955, "learning_rate": 3.5355799136124744e-07, "loss": 0.9737, "step": 17620 }, { "epoch": 0.9633897146762344, "grad_norm": 2.4478087425231934, "learning_rate": 3.5250775561928017e-07, "loss": 1.0209, "step": 17621 }, { "epoch": 0.9634443874935931, "grad_norm": 2.948063850402832, "learning_rate": 3.51459076530658e-07, "loss": 1.1154, "step": 17622 }, { "epoch": 0.9634990603109517, "grad_norm": 2.374523162841797, "learning_rate": 3.504119541282713e-07, "loss": 1.0537, "step": 17623 }, { "epoch": 0.9635537331283103, "grad_norm": 3.0547916889190674, "learning_rate": 3.493663884449494e-07, "loss": 1.1524, "step": 17624 }, { "epoch": 0.9636084059456689, "grad_norm": 3.1969754695892334, "learning_rate": 3.4832237951347713e-07, "loss": 1.0776, "step": 17625 }, { "epoch": 0.9636630787630275, "grad_norm": 2.374473810195923, "learning_rate": 3.472799273665783e-07, "loss": 0.9725, "step": 17626 }, { "epoch": 0.9637177515803861, "grad_norm": 2.892564535140991, "learning_rate": 3.4623903203694905e-07, "loss": 1.1301, "step": 17627 }, { "epoch": 0.9637724243977448, "grad_norm": 2.994781970977783, "learning_rate": 3.451996935572188e-07, "loss": 0.9519, "step": 17628 }, { "epoch": 0.9638270972151034, "grad_norm": 2.241323709487915, "learning_rate": 3.441619119599837e-07, "loss": 0.9102, "step": 17629 }, { "epoch": 0.963881770032462, "grad_norm": 3.128284215927124, "learning_rate": 3.431256872777733e-07, "loss": 1.0776, "step": 17630 }, { "epoch": 0.9639364428498206, "grad_norm": 2.2632226943969727, "learning_rate": 3.420910195430782e-07, "loss": 0.9665, "step": 17631 }, { "epoch": 0.9639911156671792, "grad_norm": 2.421814441680908, "learning_rate": 3.410579087883448e-07, "loss": 0.9764, "step": 17632 }, { "epoch": 0.9640457884845378, "grad_norm": 3.1706624031066895, "learning_rate": 3.400263550459637e-07, "loss": 0.949, "step": 17633 }, { "epoch": 0.9641004613018964, "grad_norm": 2.3364107608795166, "learning_rate": 3.3899635834827584e-07, "loss": 0.9698, "step": 17634 }, { "epoch": 0.9641551341192551, "grad_norm": 2.7240874767303467, "learning_rate": 3.379679187275775e-07, "loss": 0.9163, "step": 17635 }, { "epoch": 0.9642098069366137, "grad_norm": 2.192636728286743, "learning_rate": 3.3694103621611516e-07, "loss": 0.9624, "step": 17636 }, { "epoch": 0.9642644797539723, "grad_norm": 2.6693155765533447, "learning_rate": 3.359157108460853e-07, "loss": 0.9572, "step": 17637 }, { "epoch": 0.9643191525713309, "grad_norm": 1.9498419761657715, "learning_rate": 3.3489194264963997e-07, "loss": 0.9991, "step": 17638 }, { "epoch": 0.9643738253886895, "grad_norm": 2.350353240966797, "learning_rate": 3.338697316588701e-07, "loss": 1.0127, "step": 17639 }, { "epoch": 0.9644284982060481, "grad_norm": 2.295076847076416, "learning_rate": 3.328490779058335e-07, "loss": 0.983, "step": 17640 }, { "epoch": 0.9644831710234067, "grad_norm": 2.6715831756591797, "learning_rate": 3.3182998142252673e-07, "loss": 1.0363, "step": 17641 }, { "epoch": 0.9645378438407655, "grad_norm": 3.429778814315796, "learning_rate": 3.3081244224090205e-07, "loss": 0.9044, "step": 17642 }, { "epoch": 0.9645925166581241, "grad_norm": 2.428694725036621, "learning_rate": 3.297964603928727e-07, "loss": 1.0911, "step": 17643 }, { "epoch": 0.9646471894754827, "grad_norm": 2.7725765705108643, "learning_rate": 3.2878203591028554e-07, "loss": 1.2682, "step": 17644 }, { "epoch": 0.9647018622928413, "grad_norm": 2.331397294998169, "learning_rate": 3.277691688249429e-07, "loss": 1.1776, "step": 17645 }, { "epoch": 0.9647565351101999, "grad_norm": 2.612741708755493, "learning_rate": 3.267578591686138e-07, "loss": 1.0401, "step": 17646 }, { "epoch": 0.9648112079275585, "grad_norm": 2.404170513153076, "learning_rate": 3.2574810697300064e-07, "loss": 0.9897, "step": 17647 }, { "epoch": 0.9648658807449171, "grad_norm": 2.35617995262146, "learning_rate": 3.2473991226976695e-07, "loss": 0.9299, "step": 17648 }, { "epoch": 0.9649205535622758, "grad_norm": 2.5741372108459473, "learning_rate": 3.2373327509052085e-07, "loss": 1.0, "step": 17649 }, { "epoch": 0.9649752263796344, "grad_norm": 3.4156925678253174, "learning_rate": 3.2272819546682595e-07, "loss": 1.1395, "step": 17650 }, { "epoch": 0.965029899196993, "grad_norm": 2.92866849899292, "learning_rate": 3.217246734301904e-07, "loss": 1.1334, "step": 17651 }, { "epoch": 0.9650845720143516, "grad_norm": 3.0075132846832275, "learning_rate": 3.2072270901208346e-07, "loss": 1.0729, "step": 17652 }, { "epoch": 0.9651392448317102, "grad_norm": 2.6281654834747314, "learning_rate": 3.197223022439244e-07, "loss": 0.9081, "step": 17653 }, { "epoch": 0.9651939176490688, "grad_norm": 3.226005792617798, "learning_rate": 3.1872345315707153e-07, "loss": 1.193, "step": 17654 }, { "epoch": 0.9652485904664275, "grad_norm": 2.984799861907959, "learning_rate": 3.1772616178284974e-07, "loss": 1.2128, "step": 17655 }, { "epoch": 0.9653032632837861, "grad_norm": 1.9989420175552368, "learning_rate": 3.1673042815252297e-07, "loss": 0.8759, "step": 17656 }, { "epoch": 0.9653579361011447, "grad_norm": 3.1655991077423096, "learning_rate": 3.157362522973162e-07, "loss": 1.2183, "step": 17657 }, { "epoch": 0.9654126089185033, "grad_norm": 2.3648340702056885, "learning_rate": 3.1474363424839895e-07, "loss": 0.9, "step": 17658 }, { "epoch": 0.9654672817358619, "grad_norm": 3.5879764556884766, "learning_rate": 3.1375257403689626e-07, "loss": 0.9865, "step": 17659 }, { "epoch": 0.9655219545532205, "grad_norm": 3.419804573059082, "learning_rate": 3.127630716938779e-07, "loss": 1.0532, "step": 17660 }, { "epoch": 0.9655766273705791, "grad_norm": 3.171067714691162, "learning_rate": 3.117751272503688e-07, "loss": 1.1922, "step": 17661 }, { "epoch": 0.9656313001879379, "grad_norm": 2.6996703147888184, "learning_rate": 3.1078874073735e-07, "loss": 1.0593, "step": 17662 }, { "epoch": 0.9656859730052965, "grad_norm": 2.4442026615142822, "learning_rate": 3.098039121857466e-07, "loss": 1.0029, "step": 17663 }, { "epoch": 0.9657406458226551, "grad_norm": 2.5263447761535645, "learning_rate": 3.088206416264339e-07, "loss": 1.1924, "step": 17664 }, { "epoch": 0.9657953186400137, "grad_norm": 3.1482579708099365, "learning_rate": 3.078389290902428e-07, "loss": 0.9768, "step": 17665 }, { "epoch": 0.9658499914573723, "grad_norm": 2.2784011363983154, "learning_rate": 3.0685877460795984e-07, "loss": 0.9508, "step": 17666 }, { "epoch": 0.9659046642747309, "grad_norm": 3.649070978164673, "learning_rate": 3.058801782103049e-07, "loss": 1.2133, "step": 17667 }, { "epoch": 0.9659593370920895, "grad_norm": 2.6298763751983643, "learning_rate": 3.0490313992797556e-07, "loss": 1.039, "step": 17668 }, { "epoch": 0.9660140099094482, "grad_norm": 2.273359537124634, "learning_rate": 3.0392765979159186e-07, "loss": 0.8678, "step": 17669 }, { "epoch": 0.9660686827268068, "grad_norm": 2.4790778160095215, "learning_rate": 3.029537378317515e-07, "loss": 0.9481, "step": 17670 }, { "epoch": 0.9661233555441654, "grad_norm": 2.9076459407806396, "learning_rate": 3.0198137407898007e-07, "loss": 0.798, "step": 17671 }, { "epoch": 0.966178028361524, "grad_norm": 2.2147350311279297, "learning_rate": 3.010105685637754e-07, "loss": 0.8736, "step": 17672 }, { "epoch": 0.9662327011788826, "grad_norm": 2.9002773761749268, "learning_rate": 3.000413213165687e-07, "loss": 0.9098, "step": 17673 }, { "epoch": 0.9662873739962412, "grad_norm": 2.4679691791534424, "learning_rate": 2.990736323677523e-07, "loss": 0.9781, "step": 17674 }, { "epoch": 0.9663420468135998, "grad_norm": 3.384751796722412, "learning_rate": 2.981075017476687e-07, "loss": 1.2768, "step": 17675 }, { "epoch": 0.9663967196309585, "grad_norm": 2.45996356010437, "learning_rate": 2.9714292948661017e-07, "loss": 1.1231, "step": 17676 }, { "epoch": 0.9664513924483171, "grad_norm": 2.4780728816986084, "learning_rate": 2.9617991561481373e-07, "loss": 1.1065, "step": 17677 }, { "epoch": 0.9665060652656757, "grad_norm": 2.326622247695923, "learning_rate": 2.95218460162483e-07, "loss": 0.9364, "step": 17678 }, { "epoch": 0.9665607380830343, "grad_norm": 2.118558406829834, "learning_rate": 2.94258563159755e-07, "loss": 0.9951, "step": 17679 }, { "epoch": 0.9666154109003929, "grad_norm": 3.063094139099121, "learning_rate": 2.9330022463673333e-07, "loss": 0.9479, "step": 17680 }, { "epoch": 0.9666700837177515, "grad_norm": 2.65754771232605, "learning_rate": 2.923434446234663e-07, "loss": 1.0149, "step": 17681 }, { "epoch": 0.9667247565351103, "grad_norm": 2.266000986099243, "learning_rate": 2.913882231499465e-07, "loss": 0.9759, "step": 17682 }, { "epoch": 0.9667794293524689, "grad_norm": 2.3907816410064697, "learning_rate": 2.9043456024612783e-07, "loss": 0.9676, "step": 17683 }, { "epoch": 0.9668341021698275, "grad_norm": 2.447134494781494, "learning_rate": 2.89482455941914e-07, "loss": 1.1881, "step": 17684 }, { "epoch": 0.9668887749871861, "grad_norm": 2.5168118476867676, "learning_rate": 2.88531910267148e-07, "loss": 1.0409, "step": 17685 }, { "epoch": 0.9669434478045447, "grad_norm": 2.469202756881714, "learning_rate": 2.875829232516447e-07, "loss": 1.0063, "step": 17686 }, { "epoch": 0.9669981206219033, "grad_norm": 2.2628366947174072, "learning_rate": 2.866354949251526e-07, "loss": 1.1505, "step": 17687 }, { "epoch": 0.9670527934392619, "grad_norm": 3.1783902645111084, "learning_rate": 2.856896253173813e-07, "loss": 1.2561, "step": 17688 }, { "epoch": 0.9671074662566206, "grad_norm": 2.150614023208618, "learning_rate": 2.8474531445797923e-07, "loss": 0.9682, "step": 17689 }, { "epoch": 0.9671621390739792, "grad_norm": 2.5271596908569336, "learning_rate": 2.838025623765672e-07, "loss": 0.9774, "step": 17690 }, { "epoch": 0.9672168118913378, "grad_norm": 2.481116771697998, "learning_rate": 2.8286136910269377e-07, "loss": 0.8387, "step": 17691 }, { "epoch": 0.9672714847086964, "grad_norm": 2.593010187149048, "learning_rate": 2.819217346658742e-07, "loss": 1.123, "step": 17692 }, { "epoch": 0.967326157526055, "grad_norm": 3.243732213973999, "learning_rate": 2.8098365909556835e-07, "loss": 1.1295, "step": 17693 }, { "epoch": 0.9673808303434136, "grad_norm": 3.790478229522705, "learning_rate": 2.800471424211859e-07, "loss": 1.1754, "step": 17694 }, { "epoch": 0.9674355031607722, "grad_norm": 2.6255314350128174, "learning_rate": 2.791121846720979e-07, "loss": 0.88, "step": 17695 }, { "epoch": 0.9674901759781309, "grad_norm": 2.363290309906006, "learning_rate": 2.781787858776141e-07, "loss": 0.8626, "step": 17696 }, { "epoch": 0.9675448487954895, "grad_norm": 2.944823741912842, "learning_rate": 2.772469460670002e-07, "loss": 1.1294, "step": 17697 }, { "epoch": 0.9675995216128481, "grad_norm": 2.9544155597686768, "learning_rate": 2.763166652694771e-07, "loss": 0.9175, "step": 17698 }, { "epoch": 0.9676541944302067, "grad_norm": 3.463062286376953, "learning_rate": 2.7538794351420483e-07, "loss": 1.008, "step": 17699 }, { "epoch": 0.9677088672475653, "grad_norm": 3.139698028564453, "learning_rate": 2.744607808303157e-07, "loss": 0.965, "step": 17700 }, { "epoch": 0.9677635400649239, "grad_norm": 2.305140972137451, "learning_rate": 2.735351772468642e-07, "loss": 0.767, "step": 17701 }, { "epoch": 0.9678182128822825, "grad_norm": 3.4021008014678955, "learning_rate": 2.726111327928882e-07, "loss": 1.0505, "step": 17702 }, { "epoch": 0.9678728856996412, "grad_norm": 2.8562049865722656, "learning_rate": 2.716886474973479e-07, "loss": 1.1768, "step": 17703 }, { "epoch": 0.9679275585169999, "grad_norm": 3.3161122798919678, "learning_rate": 2.7076772138917016e-07, "loss": 1.0285, "step": 17704 }, { "epoch": 0.9679822313343585, "grad_norm": 3.795358419418335, "learning_rate": 2.698483544972319e-07, "loss": 1.0447, "step": 17705 }, { "epoch": 0.9680369041517171, "grad_norm": 2.488750457763672, "learning_rate": 2.6893054685035446e-07, "loss": 1.0025, "step": 17706 }, { "epoch": 0.9680915769690757, "grad_norm": 2.307281970977783, "learning_rate": 2.6801429847732594e-07, "loss": 1.0478, "step": 17707 }, { "epoch": 0.9681462497864343, "grad_norm": 2.534203290939331, "learning_rate": 2.670996094068623e-07, "loss": 0.964, "step": 17708 }, { "epoch": 0.968200922603793, "grad_norm": 2.582275152206421, "learning_rate": 2.661864796676461e-07, "loss": 1.0143, "step": 17709 }, { "epoch": 0.9682555954211516, "grad_norm": 2.5976102352142334, "learning_rate": 2.6527490928831e-07, "loss": 1.2225, "step": 17710 }, { "epoch": 0.9683102682385102, "grad_norm": 2.8124301433563232, "learning_rate": 2.6436489829743117e-07, "loss": 1.1959, "step": 17711 }, { "epoch": 0.9683649410558688, "grad_norm": 3.4898149967193604, "learning_rate": 2.634564467235534e-07, "loss": 1.1218, "step": 17712 }, { "epoch": 0.9684196138732274, "grad_norm": 2.6891815662384033, "learning_rate": 2.6254955459514843e-07, "loss": 0.9365, "step": 17713 }, { "epoch": 0.968474286690586, "grad_norm": 3.0912394523620605, "learning_rate": 2.616442219406545e-07, "loss": 1.3908, "step": 17714 }, { "epoch": 0.9685289595079446, "grad_norm": 2.890068531036377, "learning_rate": 2.6074044878846017e-07, "loss": 1.1881, "step": 17715 }, { "epoch": 0.9685836323253033, "grad_norm": 2.09466552734375, "learning_rate": 2.598382351668982e-07, "loss": 0.9408, "step": 17716 }, { "epoch": 0.9686383051426619, "grad_norm": 2.1675970554351807, "learning_rate": 2.589375811042627e-07, "loss": 0.939, "step": 17717 }, { "epoch": 0.9686929779600205, "grad_norm": 3.90210223197937, "learning_rate": 2.5803848662878105e-07, "loss": 0.9647, "step": 17718 }, { "epoch": 0.9687476507773791, "grad_norm": 2.98565411567688, "learning_rate": 2.5714095176865846e-07, "loss": 1.0243, "step": 17719 }, { "epoch": 0.9688023235947377, "grad_norm": 2.4097166061401367, "learning_rate": 2.5624497655202807e-07, "loss": 0.9926, "step": 17720 }, { "epoch": 0.9688569964120963, "grad_norm": 3.04620099067688, "learning_rate": 2.5535056100698394e-07, "loss": 1.2194, "step": 17721 }, { "epoch": 0.9689116692294549, "grad_norm": 2.1580734252929688, "learning_rate": 2.544577051615704e-07, "loss": 0.8974, "step": 17722 }, { "epoch": 0.9689663420468136, "grad_norm": 1.9810595512390137, "learning_rate": 2.535664090437817e-07, "loss": 0.8513, "step": 17723 }, { "epoch": 0.9690210148641722, "grad_norm": 2.8147730827331543, "learning_rate": 2.5267667268156216e-07, "loss": 1.0368, "step": 17724 }, { "epoch": 0.9690756876815309, "grad_norm": 2.4666454792022705, "learning_rate": 2.5178849610281165e-07, "loss": 0.9183, "step": 17725 }, { "epoch": 0.9691303604988895, "grad_norm": 2.3588509559631348, "learning_rate": 2.509018793353746e-07, "loss": 1.035, "step": 17726 }, { "epoch": 0.9691850333162481, "grad_norm": 2.7518396377563477, "learning_rate": 2.500168224070565e-07, "loss": 1.1046, "step": 17727 }, { "epoch": 0.9692397061336067, "grad_norm": 2.438378095626831, "learning_rate": 2.491333253455963e-07, "loss": 1.0708, "step": 17728 }, { "epoch": 0.9692943789509653, "grad_norm": 2.7020373344421387, "learning_rate": 2.482513881787052e-07, "loss": 0.8487, "step": 17729 }, { "epoch": 0.969349051768324, "grad_norm": 4.331859588623047, "learning_rate": 2.473710109340277e-07, "loss": 0.8682, "step": 17730 }, { "epoch": 0.9694037245856826, "grad_norm": 2.3115074634552, "learning_rate": 2.464921936391751e-07, "loss": 0.9403, "step": 17731 }, { "epoch": 0.9694583974030412, "grad_norm": 2.4244089126586914, "learning_rate": 2.4561493632170306e-07, "loss": 1.0263, "step": 17732 }, { "epoch": 0.9695130702203998, "grad_norm": 3.6407594680786133, "learning_rate": 2.4473923900910634e-07, "loss": 1.1546, "step": 17733 }, { "epoch": 0.9695677430377584, "grad_norm": 2.5715761184692383, "learning_rate": 2.438651017288518e-07, "loss": 1.1538, "step": 17734 }, { "epoch": 0.969622415855117, "grad_norm": 2.6357028484344482, "learning_rate": 2.4299252450833976e-07, "loss": 0.8896, "step": 17735 }, { "epoch": 0.9696770886724757, "grad_norm": 3.8869802951812744, "learning_rate": 2.4212150737493724e-07, "loss": 1.1038, "step": 17736 }, { "epoch": 0.9697317614898343, "grad_norm": 2.3456544876098633, "learning_rate": 2.4125205035595013e-07, "loss": 0.9609, "step": 17737 }, { "epoch": 0.9697864343071929, "grad_norm": 2.7234790325164795, "learning_rate": 2.403841534786344e-07, "loss": 0.9102, "step": 17738 }, { "epoch": 0.9698411071245515, "grad_norm": 2.2043192386627197, "learning_rate": 2.3951781677020725e-07, "loss": 0.8339, "step": 17739 }, { "epoch": 0.9698957799419101, "grad_norm": 2.653569459915161, "learning_rate": 2.3865304025783577e-07, "loss": 0.8445, "step": 17740 }, { "epoch": 0.9699504527592687, "grad_norm": 2.6652584075927734, "learning_rate": 2.3778982396863157e-07, "loss": 1.0625, "step": 17741 }, { "epoch": 0.9700051255766273, "grad_norm": 3.5125744342803955, "learning_rate": 2.3692816792965089e-07, "loss": 0.8581, "step": 17742 }, { "epoch": 0.970059798393986, "grad_norm": 2.528223991394043, "learning_rate": 2.3606807216792758e-07, "loss": 0.8193, "step": 17743 }, { "epoch": 0.9701144712113446, "grad_norm": 2.7845354080200195, "learning_rate": 2.3520953671041234e-07, "loss": 0.9673, "step": 17744 }, { "epoch": 0.9701691440287032, "grad_norm": 2.5107421875, "learning_rate": 2.3435256158403361e-07, "loss": 0.7654, "step": 17745 }, { "epoch": 0.9702238168460618, "grad_norm": 2.9403445720672607, "learning_rate": 2.334971468156588e-07, "loss": 1.0745, "step": 17746 }, { "epoch": 0.9702784896634205, "grad_norm": 3.4817144870758057, "learning_rate": 2.3264329243210536e-07, "loss": 1.1253, "step": 17747 }, { "epoch": 0.970333162480779, "grad_norm": 2.111846685409546, "learning_rate": 2.3179099846015185e-07, "loss": 0.7936, "step": 17748 }, { "epoch": 0.9703878352981377, "grad_norm": 3.498692035675049, "learning_rate": 2.3094026492651577e-07, "loss": 1.1084, "step": 17749 }, { "epoch": 0.9704425081154964, "grad_norm": 2.6581122875213623, "learning_rate": 2.300910918578758e-07, "loss": 0.9582, "step": 17750 }, { "epoch": 0.970497180932855, "grad_norm": 2.4357049465179443, "learning_rate": 2.2924347928084955e-07, "loss": 0.8681, "step": 17751 }, { "epoch": 0.9705518537502136, "grad_norm": 2.062567710876465, "learning_rate": 2.2839742722202128e-07, "loss": 0.935, "step": 17752 }, { "epoch": 0.9706065265675722, "grad_norm": 2.759120225906372, "learning_rate": 2.275529357079087e-07, "loss": 1.0545, "step": 17753 }, { "epoch": 0.9706611993849308, "grad_norm": 2.3727309703826904, "learning_rate": 2.267100047650017e-07, "loss": 0.9015, "step": 17754 }, { "epoch": 0.9707158722022894, "grad_norm": 2.779047727584839, "learning_rate": 2.258686344197236e-07, "loss": 0.9533, "step": 17755 }, { "epoch": 0.970770545019648, "grad_norm": 2.8637800216674805, "learning_rate": 2.2502882469845333e-07, "loss": 0.8976, "step": 17756 }, { "epoch": 0.9708252178370067, "grad_norm": 2.4282662868499756, "learning_rate": 2.2419057562752533e-07, "loss": 0.8609, "step": 17757 }, { "epoch": 0.9708798906543653, "grad_norm": 2.379340171813965, "learning_rate": 2.233538872332186e-07, "loss": 0.891, "step": 17758 }, { "epoch": 0.9709345634717239, "grad_norm": 2.453411817550659, "learning_rate": 2.2251875954177327e-07, "loss": 0.9983, "step": 17759 }, { "epoch": 0.9709892362890825, "grad_norm": 2.268254041671753, "learning_rate": 2.2168519257936836e-07, "loss": 0.8593, "step": 17760 }, { "epoch": 0.9710439091064411, "grad_norm": 2.785264015197754, "learning_rate": 2.208531863721386e-07, "loss": 1.1024, "step": 17761 }, { "epoch": 0.9710985819237997, "grad_norm": 2.4963645935058594, "learning_rate": 2.2002274094617415e-07, "loss": 0.7429, "step": 17762 }, { "epoch": 0.9711532547411584, "grad_norm": 2.329261064529419, "learning_rate": 2.1919385632751533e-07, "loss": 0.9583, "step": 17763 }, { "epoch": 0.971207927558517, "grad_norm": 2.8389947414398193, "learning_rate": 2.183665325421469e-07, "loss": 1.0734, "step": 17764 }, { "epoch": 0.9712626003758756, "grad_norm": 2.5336132049560547, "learning_rate": 2.1754076961600922e-07, "loss": 0.978, "step": 17765 }, { "epoch": 0.9713172731932342, "grad_norm": 2.79172420501709, "learning_rate": 2.167165675749927e-07, "loss": 0.8618, "step": 17766 }, { "epoch": 0.9713719460105928, "grad_norm": 2.992020845413208, "learning_rate": 2.1589392644494332e-07, "loss": 1.0074, "step": 17767 }, { "epoch": 0.9714266188279514, "grad_norm": 2.5470266342163086, "learning_rate": 2.150728462516516e-07, "loss": 0.7516, "step": 17768 }, { "epoch": 0.97148129164531, "grad_norm": 2.4746646881103516, "learning_rate": 2.1425332702085798e-07, "loss": 1.0747, "step": 17769 }, { "epoch": 0.9715359644626688, "grad_norm": 2.391200542449951, "learning_rate": 2.134353687782642e-07, "loss": 0.9186, "step": 17770 }, { "epoch": 0.9715906372800274, "grad_norm": 2.1800990104675293, "learning_rate": 2.126189715495164e-07, "loss": 0.9414, "step": 17771 }, { "epoch": 0.971645310097386, "grad_norm": 2.238415241241455, "learning_rate": 2.118041353602107e-07, "loss": 0.8761, "step": 17772 }, { "epoch": 0.9716999829147446, "grad_norm": 2.799203395843506, "learning_rate": 2.1099086023588788e-07, "loss": 1.2411, "step": 17773 }, { "epoch": 0.9717546557321032, "grad_norm": 3.0403671264648438, "learning_rate": 2.1017914620206081e-07, "loss": 0.8204, "step": 17774 }, { "epoch": 0.9718093285494618, "grad_norm": 2.748405933380127, "learning_rate": 2.0936899328417026e-07, "loss": 1.1207, "step": 17775 }, { "epoch": 0.9718640013668204, "grad_norm": 2.6278085708618164, "learning_rate": 2.0856040150762368e-07, "loss": 1.084, "step": 17776 }, { "epoch": 0.9719186741841791, "grad_norm": 2.522063970565796, "learning_rate": 2.0775337089776748e-07, "loss": 0.9786, "step": 17777 }, { "epoch": 0.9719733470015377, "grad_norm": 2.8817453384399414, "learning_rate": 2.0694790147990917e-07, "loss": 1.2076, "step": 17778 }, { "epoch": 0.9720280198188963, "grad_norm": 2.944899320602417, "learning_rate": 2.0614399327930633e-07, "loss": 0.8539, "step": 17779 }, { "epoch": 0.9720826926362549, "grad_norm": 2.9519741535186768, "learning_rate": 2.0534164632116104e-07, "loss": 0.9831, "step": 17780 }, { "epoch": 0.9721373654536135, "grad_norm": 2.5254478454589844, "learning_rate": 2.0454086063063093e-07, "loss": 1.3247, "step": 17781 }, { "epoch": 0.9721920382709721, "grad_norm": 2.328672409057617, "learning_rate": 2.037416362328237e-07, "loss": 0.9919, "step": 17782 }, { "epoch": 0.9722467110883307, "grad_norm": 2.846871852874756, "learning_rate": 2.0294397315279712e-07, "loss": 0.9926, "step": 17783 }, { "epoch": 0.9723013839056894, "grad_norm": 2.0893497467041016, "learning_rate": 2.0214787141556445e-07, "loss": 0.7855, "step": 17784 }, { "epoch": 0.972356056723048, "grad_norm": 2.1721105575561523, "learning_rate": 2.013533310460891e-07, "loss": 0.8343, "step": 17785 }, { "epoch": 0.9724107295404066, "grad_norm": 3.401355028152466, "learning_rate": 2.0056035206927337e-07, "loss": 1.0622, "step": 17786 }, { "epoch": 0.9724654023577652, "grad_norm": 2.500753402709961, "learning_rate": 1.9976893450998625e-07, "loss": 0.9399, "step": 17787 }, { "epoch": 0.9725200751751238, "grad_norm": 2.4237518310546875, "learning_rate": 1.989790783930412e-07, "loss": 0.8554, "step": 17788 }, { "epoch": 0.9725747479924824, "grad_norm": 2.329007387161255, "learning_rate": 1.981907837432073e-07, "loss": 0.9323, "step": 17789 }, { "epoch": 0.9726294208098412, "grad_norm": 2.614370584487915, "learning_rate": 1.9740405058519818e-07, "loss": 1.0838, "step": 17790 }, { "epoch": 0.9726840936271998, "grad_norm": 2.0969932079315186, "learning_rate": 1.9661887894367737e-07, "loss": 0.8886, "step": 17791 }, { "epoch": 0.9727387664445584, "grad_norm": 2.1754961013793945, "learning_rate": 1.9583526884326963e-07, "loss": 0.9528, "step": 17792 }, { "epoch": 0.972793439261917, "grad_norm": 2.459334373474121, "learning_rate": 1.9505322030853868e-07, "loss": 0.9735, "step": 17793 }, { "epoch": 0.9728481120792756, "grad_norm": 1.9113091230392456, "learning_rate": 1.942727333640093e-07, "loss": 0.978, "step": 17794 }, { "epoch": 0.9729027848966342, "grad_norm": 2.476713180541992, "learning_rate": 1.9349380803415085e-07, "loss": 1.0701, "step": 17795 }, { "epoch": 0.9729574577139928, "grad_norm": 2.901113748550415, "learning_rate": 1.927164443433882e-07, "loss": 0.8893, "step": 17796 }, { "epoch": 0.9730121305313515, "grad_norm": 3.0151784420013428, "learning_rate": 1.9194064231608523e-07, "loss": 1.0394, "step": 17797 }, { "epoch": 0.9730668033487101, "grad_norm": 2.719217300415039, "learning_rate": 1.9116640197658354e-07, "loss": 1.0241, "step": 17798 }, { "epoch": 0.9731214761660687, "grad_norm": 2.6679396629333496, "learning_rate": 1.903937233491415e-07, "loss": 0.9874, "step": 17799 }, { "epoch": 0.9731761489834273, "grad_norm": 2.4986143112182617, "learning_rate": 1.8962260645800088e-07, "loss": 0.9318, "step": 17800 }, { "epoch": 0.9732308218007859, "grad_norm": 2.9033608436584473, "learning_rate": 1.8885305132732567e-07, "loss": 0.9034, "step": 17801 }, { "epoch": 0.9732854946181445, "grad_norm": 2.7431626319885254, "learning_rate": 1.8808505798125763e-07, "loss": 1.1142, "step": 17802 }, { "epoch": 0.9733401674355031, "grad_norm": 2.4718236923217773, "learning_rate": 1.8731862644386644e-07, "loss": 1.1213, "step": 17803 }, { "epoch": 0.9733948402528618, "grad_norm": 2.60575008392334, "learning_rate": 1.865537567391884e-07, "loss": 1.0223, "step": 17804 }, { "epoch": 0.9734495130702204, "grad_norm": 2.464792251586914, "learning_rate": 1.857904488911988e-07, "loss": 1.0042, "step": 17805 }, { "epoch": 0.973504185887579, "grad_norm": 2.9389655590057373, "learning_rate": 1.8502870292383955e-07, "loss": 0.8622, "step": 17806 }, { "epoch": 0.9735588587049376, "grad_norm": 2.437377691268921, "learning_rate": 1.8426851886098606e-07, "loss": 1.0966, "step": 17807 }, { "epoch": 0.9736135315222962, "grad_norm": 2.5999324321746826, "learning_rate": 1.8350989672648033e-07, "loss": 0.831, "step": 17808 }, { "epoch": 0.9736682043396548, "grad_norm": 2.569406032562256, "learning_rate": 1.8275283654410335e-07, "loss": 0.9294, "step": 17809 }, { "epoch": 0.9737228771570134, "grad_norm": 2.911024808883667, "learning_rate": 1.819973383375917e-07, "loss": 0.9893, "step": 17810 }, { "epoch": 0.9737775499743722, "grad_norm": 2.4479870796203613, "learning_rate": 1.8124340213064306e-07, "loss": 0.8385, "step": 17811 }, { "epoch": 0.9738322227917308, "grad_norm": 2.6282620429992676, "learning_rate": 1.80491027946883e-07, "loss": 0.9143, "step": 17812 }, { "epoch": 0.9738868956090894, "grad_norm": 2.9049034118652344, "learning_rate": 1.797402158099093e-07, "loss": 1.0511, "step": 17813 }, { "epoch": 0.973941568426448, "grad_norm": 3.509385824203491, "learning_rate": 1.7899096574325868e-07, "loss": 1.222, "step": 17814 }, { "epoch": 0.9739962412438066, "grad_norm": 2.6503536701202393, "learning_rate": 1.7824327777042905e-07, "loss": 0.9504, "step": 17815 }, { "epoch": 0.9740509140611652, "grad_norm": 2.3342714309692383, "learning_rate": 1.7749715191485716e-07, "loss": 0.9784, "step": 17816 }, { "epoch": 0.9741055868785239, "grad_norm": 2.379159688949585, "learning_rate": 1.76752588199941e-07, "loss": 0.9606, "step": 17817 }, { "epoch": 0.9741602596958825, "grad_norm": 2.8997793197631836, "learning_rate": 1.7600958664902855e-07, "loss": 0.9449, "step": 17818 }, { "epoch": 0.9742149325132411, "grad_norm": 3.090841770172119, "learning_rate": 1.7526814728540675e-07, "loss": 0.8786, "step": 17819 }, { "epoch": 0.9742696053305997, "grad_norm": 2.3386144638061523, "learning_rate": 1.745282701323292e-07, "loss": 0.8586, "step": 17820 }, { "epoch": 0.9743242781479583, "grad_norm": 2.1552836894989014, "learning_rate": 1.7378995521299402e-07, "loss": 0.9396, "step": 17821 }, { "epoch": 0.9743789509653169, "grad_norm": 3.133930206298828, "learning_rate": 1.730532025505549e-07, "loss": 1.0752, "step": 17822 }, { "epoch": 0.9744336237826755, "grad_norm": 3.0096304416656494, "learning_rate": 1.7231801216809894e-07, "loss": 0.8589, "step": 17823 }, { "epoch": 0.9744882966000342, "grad_norm": 2.2666163444519043, "learning_rate": 1.7158438408869105e-07, "loss": 0.9129, "step": 17824 }, { "epoch": 0.9745429694173928, "grad_norm": 2.5538759231567383, "learning_rate": 1.708523183353239e-07, "loss": 1.1281, "step": 17825 }, { "epoch": 0.9745976422347514, "grad_norm": 2.234844923019409, "learning_rate": 1.7012181493095693e-07, "loss": 0.7821, "step": 17826 }, { "epoch": 0.97465231505211, "grad_norm": 3.0662522315979004, "learning_rate": 1.6939287389848845e-07, "loss": 1.0823, "step": 17827 }, { "epoch": 0.9747069878694686, "grad_norm": 2.8568618297576904, "learning_rate": 1.6866549526077802e-07, "loss": 1.1796, "step": 17828 }, { "epoch": 0.9747616606868272, "grad_norm": 2.236290454864502, "learning_rate": 1.6793967904063512e-07, "loss": 1.0421, "step": 17829 }, { "epoch": 0.9748163335041858, "grad_norm": 2.8727235794067383, "learning_rate": 1.6721542526080823e-07, "loss": 1.0932, "step": 17830 }, { "epoch": 0.9748710063215446, "grad_norm": 3.1412575244903564, "learning_rate": 1.664927339440181e-07, "loss": 1.0704, "step": 17831 }, { "epoch": 0.9749256791389032, "grad_norm": 2.6633570194244385, "learning_rate": 1.6577160511290767e-07, "loss": 1.2508, "step": 17832 }, { "epoch": 0.9749803519562618, "grad_norm": 3.028390407562256, "learning_rate": 1.6505203879010333e-07, "loss": 1.008, "step": 17833 }, { "epoch": 0.9750350247736204, "grad_norm": 2.5238583087921143, "learning_rate": 1.643340349981537e-07, "loss": 1.1475, "step": 17834 }, { "epoch": 0.975089697590979, "grad_norm": 2.5438637733459473, "learning_rate": 1.6361759375957964e-07, "loss": 0.9819, "step": 17835 }, { "epoch": 0.9751443704083376, "grad_norm": 2.8057048320770264, "learning_rate": 1.6290271509684097e-07, "loss": 1.1124, "step": 17836 }, { "epoch": 0.9751990432256962, "grad_norm": 2.6202101707458496, "learning_rate": 1.6218939903235307e-07, "loss": 0.9641, "step": 17837 }, { "epoch": 0.9752537160430549, "grad_norm": 3.0552451610565186, "learning_rate": 1.6147764558848143e-07, "loss": 1.0478, "step": 17838 }, { "epoch": 0.9753083888604135, "grad_norm": 5.186117172241211, "learning_rate": 1.6076745478754151e-07, "loss": 0.9094, "step": 17839 }, { "epoch": 0.9753630616777721, "grad_norm": 2.4457008838653564, "learning_rate": 1.600588266518044e-07, "loss": 0.8964, "step": 17840 }, { "epoch": 0.9754177344951307, "grad_norm": 2.7763993740081787, "learning_rate": 1.593517612034856e-07, "loss": 1.0165, "step": 17841 }, { "epoch": 0.9754724073124893, "grad_norm": 2.588036298751831, "learning_rate": 1.586462584647508e-07, "loss": 1.0073, "step": 17842 }, { "epoch": 0.9755270801298479, "grad_norm": 3.595661163330078, "learning_rate": 1.5794231845772667e-07, "loss": 1.0682, "step": 17843 }, { "epoch": 0.9755817529472066, "grad_norm": 3.0444934368133545, "learning_rate": 1.5723994120447894e-07, "loss": 1.0608, "step": 17844 }, { "epoch": 0.9756364257645652, "grad_norm": 2.5695717334747314, "learning_rate": 1.5653912672702887e-07, "loss": 0.9589, "step": 17845 }, { "epoch": 0.9756910985819238, "grad_norm": 3.0210483074188232, "learning_rate": 1.558398750473644e-07, "loss": 0.8991, "step": 17846 }, { "epoch": 0.9757457713992824, "grad_norm": 2.6364619731903076, "learning_rate": 1.551421861873903e-07, "loss": 1.1457, "step": 17847 }, { "epoch": 0.975800444216641, "grad_norm": 2.3841609954833984, "learning_rate": 1.544460601690001e-07, "loss": 0.9017, "step": 17848 }, { "epoch": 0.9758551170339996, "grad_norm": 2.6216113567352295, "learning_rate": 1.5375149701400414e-07, "loss": 0.938, "step": 17849 }, { "epoch": 0.9759097898513582, "grad_norm": 2.99023175239563, "learning_rate": 1.530584967441906e-07, "loss": 1.0022, "step": 17850 }, { "epoch": 0.975964462668717, "grad_norm": 3.276000738143921, "learning_rate": 1.523670593812865e-07, "loss": 1.0059, "step": 17851 }, { "epoch": 0.9760191354860756, "grad_norm": 2.6793317794799805, "learning_rate": 1.5167718494696337e-07, "loss": 0.8698, "step": 17852 }, { "epoch": 0.9760738083034342, "grad_norm": 2.7886457443237305, "learning_rate": 1.509888734628595e-07, "loss": 1.1559, "step": 17853 }, { "epoch": 0.9761284811207928, "grad_norm": 2.313429355621338, "learning_rate": 1.5030212495055762e-07, "loss": 0.9186, "step": 17854 }, { "epoch": 0.9761831539381514, "grad_norm": 2.489318609237671, "learning_rate": 1.4961693943158494e-07, "loss": 1.1092, "step": 17855 }, { "epoch": 0.97623782675551, "grad_norm": 2.7221386432647705, "learning_rate": 1.489333169274243e-07, "loss": 1.1488, "step": 17856 }, { "epoch": 0.9762924995728686, "grad_norm": 2.5486834049224854, "learning_rate": 1.4825125745951408e-07, "loss": 1.2136, "step": 17857 }, { "epoch": 0.9763471723902273, "grad_norm": 2.611506223678589, "learning_rate": 1.4757076104923718e-07, "loss": 0.9442, "step": 17858 }, { "epoch": 0.9764018452075859, "grad_norm": 3.051938772201538, "learning_rate": 1.4689182771793207e-07, "loss": 0.85, "step": 17859 }, { "epoch": 0.9764565180249445, "grad_norm": 4.347580909729004, "learning_rate": 1.462144574868818e-07, "loss": 1.2314, "step": 17860 }, { "epoch": 0.9765111908423031, "grad_norm": 2.534777879714966, "learning_rate": 1.4553865037733038e-07, "loss": 0.9513, "step": 17861 }, { "epoch": 0.9765658636596617, "grad_norm": 2.644294500350952, "learning_rate": 1.448644064104665e-07, "loss": 0.9406, "step": 17862 }, { "epoch": 0.9766205364770203, "grad_norm": 2.4809446334838867, "learning_rate": 1.4419172560742322e-07, "loss": 1.0859, "step": 17863 }, { "epoch": 0.9766752092943789, "grad_norm": 2.078713893890381, "learning_rate": 1.4352060798930035e-07, "loss": 0.9645, "step": 17864 }, { "epoch": 0.9767298821117376, "grad_norm": 2.171952247619629, "learning_rate": 1.4285105357713659e-07, "loss": 1.0043, "step": 17865 }, { "epoch": 0.9767845549290962, "grad_norm": 5.0688982009887695, "learning_rate": 1.4218306239192626e-07, "loss": 1.0958, "step": 17866 }, { "epoch": 0.9768392277464548, "grad_norm": 2.641775369644165, "learning_rate": 1.415166344546137e-07, "loss": 0.9462, "step": 17867 }, { "epoch": 0.9768939005638134, "grad_norm": 2.5573179721832275, "learning_rate": 1.4085176978608782e-07, "loss": 1.0927, "step": 17868 }, { "epoch": 0.976948573381172, "grad_norm": 2.175973892211914, "learning_rate": 1.4018846840720412e-07, "loss": 0.7182, "step": 17869 }, { "epoch": 0.9770032461985306, "grad_norm": 3.442826271057129, "learning_rate": 1.3952673033875707e-07, "loss": 1.1449, "step": 17870 }, { "epoch": 0.9770579190158893, "grad_norm": 2.675142765045166, "learning_rate": 1.3886655560149675e-07, "loss": 1.0502, "step": 17871 }, { "epoch": 0.977112591833248, "grad_norm": 3.586751699447632, "learning_rate": 1.3820794421611217e-07, "loss": 1.0424, "step": 17872 }, { "epoch": 0.9771672646506065, "grad_norm": 2.2071657180786133, "learning_rate": 1.3755089620326457e-07, "loss": 1.0367, "step": 17873 }, { "epoch": 0.9772219374679652, "grad_norm": 2.631246566772461, "learning_rate": 1.3689541158355413e-07, "loss": 1.0038, "step": 17874 }, { "epoch": 0.9772766102853238, "grad_norm": 2.6620895862579346, "learning_rate": 1.3624149037752554e-07, "loss": 1.1617, "step": 17875 }, { "epoch": 0.9773312831026824, "grad_norm": 2.390712022781372, "learning_rate": 1.3558913260569017e-07, "loss": 1.073, "step": 17876 }, { "epoch": 0.977385955920041, "grad_norm": 3.398800849914551, "learning_rate": 1.3493833828849833e-07, "loss": 0.9578, "step": 17877 }, { "epoch": 0.9774406287373997, "grad_norm": 2.2756495475769043, "learning_rate": 1.3428910744635037e-07, "loss": 0.9899, "step": 17878 }, { "epoch": 0.9774953015547583, "grad_norm": 2.545191764831543, "learning_rate": 1.3364144009961333e-07, "loss": 0.9008, "step": 17879 }, { "epoch": 0.9775499743721169, "grad_norm": 2.5550999641418457, "learning_rate": 1.3299533626858762e-07, "loss": 0.9392, "step": 17880 }, { "epoch": 0.9776046471894755, "grad_norm": 2.868288993835449, "learning_rate": 1.323507959735293e-07, "loss": 1.1079, "step": 17881 }, { "epoch": 0.9776593200068341, "grad_norm": 2.313687324523926, "learning_rate": 1.3170781923465548e-07, "loss": 1.0283, "step": 17882 }, { "epoch": 0.9777139928241927, "grad_norm": 2.887150526046753, "learning_rate": 1.3106640607211674e-07, "loss": 0.9704, "step": 17883 }, { "epoch": 0.9777686656415513, "grad_norm": 3.5737905502319336, "learning_rate": 1.3042655650602475e-07, "loss": 1.3102, "step": 17884 }, { "epoch": 0.97782333845891, "grad_norm": 3.828321933746338, "learning_rate": 1.2978827055644683e-07, "loss": 1.0589, "step": 17885 }, { "epoch": 0.9778780112762686, "grad_norm": 2.2130587100982666, "learning_rate": 1.291515482433947e-07, "loss": 1.0463, "step": 17886 }, { "epoch": 0.9779326840936272, "grad_norm": 2.4911606311798096, "learning_rate": 1.2851638958683022e-07, "loss": 0.9653, "step": 17887 }, { "epoch": 0.9779873569109858, "grad_norm": 3.1077725887298584, "learning_rate": 1.2788279460667075e-07, "loss": 1.1107, "step": 17888 }, { "epoch": 0.9780420297283444, "grad_norm": 2.962170362472534, "learning_rate": 1.2725076332278374e-07, "loss": 0.9785, "step": 17889 }, { "epoch": 0.978096702545703, "grad_norm": 2.611116647720337, "learning_rate": 1.2662029575497557e-07, "loss": 0.8872, "step": 17890 }, { "epoch": 0.9781513753630616, "grad_norm": 2.805640697479248, "learning_rate": 1.259913919230249e-07, "loss": 1.053, "step": 17891 }, { "epoch": 0.9782060481804203, "grad_norm": 2.700659990310669, "learning_rate": 1.2536405184664922e-07, "loss": 1.189, "step": 17892 }, { "epoch": 0.9782607209977789, "grad_norm": 2.6590616703033447, "learning_rate": 1.2473827554551067e-07, "loss": 0.9774, "step": 17893 }, { "epoch": 0.9783153938151375, "grad_norm": 2.1538946628570557, "learning_rate": 1.241140630392379e-07, "loss": 0.9649, "step": 17894 }, { "epoch": 0.9783700666324961, "grad_norm": 3.570298194885254, "learning_rate": 1.2349141434739865e-07, "loss": 0.8791, "step": 17895 }, { "epoch": 0.9784247394498548, "grad_norm": 3.579996109008789, "learning_rate": 1.2287032948951616e-07, "loss": 1.1065, "step": 17896 }, { "epoch": 0.9784794122672134, "grad_norm": 2.123563051223755, "learning_rate": 1.2225080848506376e-07, "loss": 1.0587, "step": 17897 }, { "epoch": 0.9785340850845721, "grad_norm": 2.2666590213775635, "learning_rate": 1.2163285135347035e-07, "loss": 1.1685, "step": 17898 }, { "epoch": 0.9785887579019307, "grad_norm": 2.4122776985168457, "learning_rate": 1.2101645811410378e-07, "loss": 1.1033, "step": 17899 }, { "epoch": 0.9786434307192893, "grad_norm": 2.8882927894592285, "learning_rate": 1.2040162878629856e-07, "loss": 1.0305, "step": 17900 }, { "epoch": 0.9786981035366479, "grad_norm": 2.3957905769348145, "learning_rate": 1.1978836338932263e-07, "loss": 1.0984, "step": 17901 }, { "epoch": 0.9787527763540065, "grad_norm": 3.4319865703582764, "learning_rate": 1.1917666194241617e-07, "loss": 1.1147, "step": 17902 }, { "epoch": 0.9788074491713651, "grad_norm": 2.8365252017974854, "learning_rate": 1.1856652446474714e-07, "loss": 1.0884, "step": 17903 }, { "epoch": 0.9788621219887237, "grad_norm": 2.4023656845092773, "learning_rate": 1.1795795097545581e-07, "loss": 0.9815, "step": 17904 }, { "epoch": 0.9789167948060824, "grad_norm": 2.5214943885803223, "learning_rate": 1.1735094149361025e-07, "loss": 1.014, "step": 17905 }, { "epoch": 0.978971467623441, "grad_norm": 2.6827232837677, "learning_rate": 1.1674549603825635e-07, "loss": 1.1371, "step": 17906 }, { "epoch": 0.9790261404407996, "grad_norm": 3.2134218215942383, "learning_rate": 1.1614161462837336e-07, "loss": 0.9978, "step": 17907 }, { "epoch": 0.9790808132581582, "grad_norm": 2.208219051361084, "learning_rate": 1.1553929728289059e-07, "loss": 1.0142, "step": 17908 }, { "epoch": 0.9791354860755168, "grad_norm": 2.8618907928466797, "learning_rate": 1.1493854402069848e-07, "loss": 1.0458, "step": 17909 }, { "epoch": 0.9791901588928754, "grad_norm": 3.3868091106414795, "learning_rate": 1.1433935486062641e-07, "loss": 0.9252, "step": 17910 }, { "epoch": 0.979244831710234, "grad_norm": 2.4640719890594482, "learning_rate": 1.1374172982147047e-07, "loss": 1.0846, "step": 17911 }, { "epoch": 0.9792995045275927, "grad_norm": 2.751145362854004, "learning_rate": 1.1314566892196565e-07, "loss": 1.0025, "step": 17912 }, { "epoch": 0.9793541773449513, "grad_norm": 3.808602809906006, "learning_rate": 1.1255117218080257e-07, "loss": 0.9359, "step": 17913 }, { "epoch": 0.9794088501623099, "grad_norm": 2.3842008113861084, "learning_rate": 1.1195823961661079e-07, "loss": 0.9841, "step": 17914 }, { "epoch": 0.9794635229796685, "grad_norm": 2.9517338275909424, "learning_rate": 1.1136687124799206e-07, "loss": 1.1546, "step": 17915 }, { "epoch": 0.9795181957970271, "grad_norm": 2.8201587200164795, "learning_rate": 1.1077706709348157e-07, "loss": 1.0849, "step": 17916 }, { "epoch": 0.9795728686143857, "grad_norm": 2.90958309173584, "learning_rate": 1.1018882717158119e-07, "loss": 1.0264, "step": 17917 }, { "epoch": 0.9796275414317444, "grad_norm": 2.1534423828125, "learning_rate": 1.0960215150072617e-07, "loss": 0.836, "step": 17918 }, { "epoch": 0.9796822142491031, "grad_norm": 2.4051148891448975, "learning_rate": 1.0901704009931291e-07, "loss": 0.9886, "step": 17919 }, { "epoch": 0.9797368870664617, "grad_norm": 2.709341526031494, "learning_rate": 1.0843349298568783e-07, "loss": 0.9399, "step": 17920 }, { "epoch": 0.9797915598838203, "grad_norm": 2.1475117206573486, "learning_rate": 1.0785151017815299e-07, "loss": 1.0165, "step": 17921 }, { "epoch": 0.9798462327011789, "grad_norm": 2.8431918621063232, "learning_rate": 1.0727109169494376e-07, "loss": 1.0423, "step": 17922 }, { "epoch": 0.9799009055185375, "grad_norm": 2.2276151180267334, "learning_rate": 1.0669223755426783e-07, "loss": 1.1273, "step": 17923 }, { "epoch": 0.9799555783358961, "grad_norm": 2.881287097930908, "learning_rate": 1.0611494777427733e-07, "loss": 1.0898, "step": 17924 }, { "epoch": 0.9800102511532548, "grad_norm": 3.3240485191345215, "learning_rate": 1.055392223730578e-07, "loss": 1.0747, "step": 17925 }, { "epoch": 0.9800649239706134, "grad_norm": 2.8496007919311523, "learning_rate": 1.0496506136867811e-07, "loss": 1.0017, "step": 17926 }, { "epoch": 0.980119596787972, "grad_norm": 3.4398980140686035, "learning_rate": 1.0439246477912945e-07, "loss": 1.0042, "step": 17927 }, { "epoch": 0.9801742696053306, "grad_norm": 2.641017436981201, "learning_rate": 1.0382143262236965e-07, "loss": 1.0725, "step": 17928 }, { "epoch": 0.9802289424226892, "grad_norm": 3.060746192932129, "learning_rate": 1.0325196491630662e-07, "loss": 1.1573, "step": 17929 }, { "epoch": 0.9802836152400478, "grad_norm": 3.0259084701538086, "learning_rate": 1.026840616787872e-07, "loss": 1.1577, "step": 17930 }, { "epoch": 0.9803382880574064, "grad_norm": 2.0752880573272705, "learning_rate": 1.0211772292761934e-07, "loss": 0.945, "step": 17931 }, { "epoch": 0.9803929608747651, "grad_norm": 3.1263890266418457, "learning_rate": 1.015529486805611e-07, "loss": 0.9851, "step": 17932 }, { "epoch": 0.9804476336921237, "grad_norm": 3.0890018939971924, "learning_rate": 1.0098973895532604e-07, "loss": 1.0991, "step": 17933 }, { "epoch": 0.9805023065094823, "grad_norm": 2.5559935569763184, "learning_rate": 1.004280937695612e-07, "loss": 1.0622, "step": 17934 }, { "epoch": 0.9805569793268409, "grad_norm": 2.568586587905884, "learning_rate": 9.986801314089134e-08, "loss": 0.924, "step": 17935 }, { "epoch": 0.9806116521441995, "grad_norm": 2.7067947387695312, "learning_rate": 9.930949708686354e-08, "loss": 1.0499, "step": 17936 }, { "epoch": 0.9806663249615581, "grad_norm": 3.1098546981811523, "learning_rate": 9.875254562500269e-08, "loss": 1.0861, "step": 17937 }, { "epoch": 0.9807209977789167, "grad_norm": 2.2997233867645264, "learning_rate": 9.819715877275592e-08, "loss": 1.0557, "step": 17938 }, { "epoch": 0.9807756705962755, "grad_norm": 2.9309234619140625, "learning_rate": 9.764333654755375e-08, "loss": 0.9579, "step": 17939 }, { "epoch": 0.9808303434136341, "grad_norm": 3.0851852893829346, "learning_rate": 9.709107896674341e-08, "loss": 0.8857, "step": 17940 }, { "epoch": 0.9808850162309927, "grad_norm": 2.512493848800659, "learning_rate": 9.654038604765548e-08, "loss": 0.9078, "step": 17941 }, { "epoch": 0.9809396890483513, "grad_norm": 3.1552629470825195, "learning_rate": 9.599125780754837e-08, "loss": 1.0903, "step": 17942 }, { "epoch": 0.9809943618657099, "grad_norm": 2.6541152000427246, "learning_rate": 9.544369426364163e-08, "loss": 1.0158, "step": 17943 }, { "epoch": 0.9810490346830685, "grad_norm": 2.51336669921875, "learning_rate": 9.48976954331049e-08, "loss": 0.9255, "step": 17944 }, { "epoch": 0.9811037075004271, "grad_norm": 2.4351913928985596, "learning_rate": 9.435326133305778e-08, "loss": 1.0021, "step": 17945 }, { "epoch": 0.9811583803177858, "grad_norm": 2.72780179977417, "learning_rate": 9.38103919805644e-08, "loss": 0.9839, "step": 17946 }, { "epoch": 0.9812130531351444, "grad_norm": 2.4410531520843506, "learning_rate": 9.32690873926556e-08, "loss": 1.0413, "step": 17947 }, { "epoch": 0.981267725952503, "grad_norm": 2.4802932739257812, "learning_rate": 9.272934758629558e-08, "loss": 0.9658, "step": 17948 }, { "epoch": 0.9813223987698616, "grad_norm": 2.2905359268188477, "learning_rate": 9.21911725784097e-08, "loss": 0.9121, "step": 17949 }, { "epoch": 0.9813770715872202, "grad_norm": 2.401369333267212, "learning_rate": 9.165456238586779e-08, "loss": 0.9721, "step": 17950 }, { "epoch": 0.9814317444045788, "grad_norm": 2.9450135231018066, "learning_rate": 9.111951702550637e-08, "loss": 1.1086, "step": 17951 }, { "epoch": 0.9814864172219374, "grad_norm": 3.2178828716278076, "learning_rate": 9.058603651409536e-08, "loss": 1.34, "step": 17952 }, { "epoch": 0.9815410900392961, "grad_norm": 2.725965738296509, "learning_rate": 9.005412086835474e-08, "loss": 1.0369, "step": 17953 }, { "epoch": 0.9815957628566547, "grad_norm": 2.787092924118042, "learning_rate": 8.952377010497115e-08, "loss": 1.1945, "step": 17954 }, { "epoch": 0.9816504356740133, "grad_norm": 2.840700626373291, "learning_rate": 8.899498424057017e-08, "loss": 1.1511, "step": 17955 }, { "epoch": 0.9817051084913719, "grad_norm": 2.7547953128814697, "learning_rate": 8.8467763291733e-08, "loss": 1.0243, "step": 17956 }, { "epoch": 0.9817597813087305, "grad_norm": 2.7419822216033936, "learning_rate": 8.794210727498531e-08, "loss": 1.1397, "step": 17957 }, { "epoch": 0.9818144541260891, "grad_norm": 2.354370355606079, "learning_rate": 8.74180162068139e-08, "loss": 0.9619, "step": 17958 }, { "epoch": 0.9818691269434479, "grad_norm": 2.7415146827697754, "learning_rate": 8.689549010365006e-08, "loss": 0.8636, "step": 17959 }, { "epoch": 0.9819237997608065, "grad_norm": 2.4011762142181396, "learning_rate": 8.637452898187515e-08, "loss": 0.8202, "step": 17960 }, { "epoch": 0.9819784725781651, "grad_norm": 2.6861929893493652, "learning_rate": 8.585513285782609e-08, "loss": 1.0865, "step": 17961 }, { "epoch": 0.9820331453955237, "grad_norm": 2.449840545654297, "learning_rate": 8.533730174778431e-08, "loss": 1.0388, "step": 17962 }, { "epoch": 0.9820878182128823, "grad_norm": 2.509120225906372, "learning_rate": 8.482103566798683e-08, "loss": 1.1175, "step": 17963 }, { "epoch": 0.9821424910302409, "grad_norm": 2.7211804389953613, "learning_rate": 8.430633463462622e-08, "loss": 0.7735, "step": 17964 }, { "epoch": 0.9821971638475995, "grad_norm": 2.1537888050079346, "learning_rate": 8.379319866383406e-08, "loss": 1.1899, "step": 17965 }, { "epoch": 0.9822518366649582, "grad_norm": 2.307302236557007, "learning_rate": 8.328162777170301e-08, "loss": 1.0355, "step": 17966 }, { "epoch": 0.9823065094823168, "grad_norm": 2.8883392810821533, "learning_rate": 8.277162197427024e-08, "loss": 1.0948, "step": 17967 }, { "epoch": 0.9823611822996754, "grad_norm": 2.455138921737671, "learning_rate": 8.226318128752852e-08, "loss": 1.1279, "step": 17968 }, { "epoch": 0.982415855117034, "grad_norm": 2.6005334854125977, "learning_rate": 8.17563057274151e-08, "loss": 1.0916, "step": 17969 }, { "epoch": 0.9824705279343926, "grad_norm": 2.4126927852630615, "learning_rate": 8.125099530982839e-08, "loss": 1.0775, "step": 17970 }, { "epoch": 0.9825252007517512, "grad_norm": 2.6752429008483887, "learning_rate": 8.074725005061123e-08, "loss": 0.8257, "step": 17971 }, { "epoch": 0.9825798735691098, "grad_norm": 2.3644673824310303, "learning_rate": 8.024506996555659e-08, "loss": 0.8167, "step": 17972 }, { "epoch": 0.9826345463864685, "grad_norm": 2.5314695835113525, "learning_rate": 7.974445507041295e-08, "loss": 0.7904, "step": 17973 }, { "epoch": 0.9826892192038271, "grad_norm": 2.5922439098358154, "learning_rate": 7.924540538086778e-08, "loss": 0.869, "step": 17974 }, { "epoch": 0.9827438920211857, "grad_norm": 2.667431592941284, "learning_rate": 7.874792091258076e-08, "loss": 1.0456, "step": 17975 }, { "epoch": 0.9827985648385443, "grad_norm": 1.96286940574646, "learning_rate": 7.825200168113944e-08, "loss": 0.9487, "step": 17976 }, { "epoch": 0.9828532376559029, "grad_norm": 3.7793080806732178, "learning_rate": 7.775764770209803e-08, "loss": 0.9043, "step": 17977 }, { "epoch": 0.9829079104732615, "grad_norm": 2.82275652885437, "learning_rate": 7.726485899095525e-08, "loss": 1.0215, "step": 17978 }, { "epoch": 0.9829625832906201, "grad_norm": 2.3546528816223145, "learning_rate": 7.677363556316542e-08, "loss": 0.8257, "step": 17979 }, { "epoch": 0.9830172561079789, "grad_norm": 3.017778158187866, "learning_rate": 7.62839774341273e-08, "loss": 1.0163, "step": 17980 }, { "epoch": 0.9830719289253375, "grad_norm": 2.85117769241333, "learning_rate": 7.579588461918974e-08, "loss": 0.995, "step": 17981 }, { "epoch": 0.9831266017426961, "grad_norm": 2.9529190063476562, "learning_rate": 7.530935713366271e-08, "loss": 1.1217, "step": 17982 }, { "epoch": 0.9831812745600547, "grad_norm": 2.9125406742095947, "learning_rate": 7.482439499279515e-08, "loss": 1.0189, "step": 17983 }, { "epoch": 0.9832359473774133, "grad_norm": 2.5828700065612793, "learning_rate": 7.434099821180262e-08, "loss": 0.8028, "step": 17984 }, { "epoch": 0.9832906201947719, "grad_norm": 2.696683168411255, "learning_rate": 7.385916680583416e-08, "loss": 1.0803, "step": 17985 }, { "epoch": 0.9833452930121306, "grad_norm": 2.539116621017456, "learning_rate": 7.337890078999432e-08, "loss": 1.0523, "step": 17986 }, { "epoch": 0.9833999658294892, "grad_norm": 2.843891143798828, "learning_rate": 7.290020017934885e-08, "loss": 0.7294, "step": 17987 }, { "epoch": 0.9834546386468478, "grad_norm": 2.689089775085449, "learning_rate": 7.242306498890238e-08, "loss": 0.8842, "step": 17988 }, { "epoch": 0.9835093114642064, "grad_norm": 2.986257791519165, "learning_rate": 7.194749523361522e-08, "loss": 1.1607, "step": 17989 }, { "epoch": 0.983563984281565, "grad_norm": 2.1745541095733643, "learning_rate": 7.147349092839761e-08, "loss": 1.0156, "step": 17990 }, { "epoch": 0.9836186570989236, "grad_norm": 2.8062143325805664, "learning_rate": 7.100105208811547e-08, "loss": 0.7751, "step": 17991 }, { "epoch": 0.9836733299162822, "grad_norm": 2.680757522583008, "learning_rate": 7.053017872757917e-08, "loss": 1.0176, "step": 17992 }, { "epoch": 0.9837280027336409, "grad_norm": 2.68914532661438, "learning_rate": 7.006087086155466e-08, "loss": 1.0576, "step": 17993 }, { "epoch": 0.9837826755509995, "grad_norm": 2.385962724685669, "learning_rate": 6.959312850475242e-08, "loss": 1.1269, "step": 17994 }, { "epoch": 0.9838373483683581, "grad_norm": 2.046365976333618, "learning_rate": 6.912695167184402e-08, "loss": 0.9538, "step": 17995 }, { "epoch": 0.9838920211857167, "grad_norm": 2.585392713546753, "learning_rate": 6.866234037744001e-08, "loss": 1.0782, "step": 17996 }, { "epoch": 0.9839466940030753, "grad_norm": 2.6445538997650146, "learning_rate": 6.819929463611208e-08, "loss": 1.1304, "step": 17997 }, { "epoch": 0.9840013668204339, "grad_norm": 3.4128761291503906, "learning_rate": 6.773781446237082e-08, "loss": 1.0134, "step": 17998 }, { "epoch": 0.9840560396377925, "grad_norm": 2.4213223457336426, "learning_rate": 6.727789987069911e-08, "loss": 0.9087, "step": 17999 }, { "epoch": 0.9841107124551512, "grad_norm": 2.827585220336914, "learning_rate": 6.681955087550762e-08, "loss": 0.9688, "step": 18000 }, { "epoch": 0.9841653852725099, "grad_norm": 2.9810047149658203, "learning_rate": 6.636276749116821e-08, "loss": 1.1889, "step": 18001 }, { "epoch": 0.9842200580898685, "grad_norm": 2.797804594039917, "learning_rate": 6.590754973200275e-08, "loss": 1.0741, "step": 18002 }, { "epoch": 0.9842747309072271, "grad_norm": 2.39697003364563, "learning_rate": 6.54538976122887e-08, "loss": 1.0294, "step": 18003 }, { "epoch": 0.9843294037245857, "grad_norm": 2.0281031131744385, "learning_rate": 6.500181114624804e-08, "loss": 1.023, "step": 18004 }, { "epoch": 0.9843840765419443, "grad_norm": 2.4867594242095947, "learning_rate": 6.455129034805273e-08, "loss": 1.0706, "step": 18005 }, { "epoch": 0.9844387493593029, "grad_norm": 2.540287494659424, "learning_rate": 6.41023352318304e-08, "loss": 1.0622, "step": 18006 }, { "epoch": 0.9844934221766616, "grad_norm": 2.565502166748047, "learning_rate": 6.36549458116531e-08, "loss": 1.1602, "step": 18007 }, { "epoch": 0.9845480949940202, "grad_norm": 2.416578531265259, "learning_rate": 6.320912210155961e-08, "loss": 0.9186, "step": 18008 }, { "epoch": 0.9846027678113788, "grad_norm": 2.284925937652588, "learning_rate": 6.276486411551652e-08, "loss": 1.0679, "step": 18009 }, { "epoch": 0.9846574406287374, "grad_norm": 2.452549695968628, "learning_rate": 6.23221718674627e-08, "loss": 1.1562, "step": 18010 }, { "epoch": 0.984712113446096, "grad_norm": 2.450289487838745, "learning_rate": 6.188104537127037e-08, "loss": 1.1402, "step": 18011 }, { "epoch": 0.9847667862634546, "grad_norm": 2.1172478199005127, "learning_rate": 6.144148464077293e-08, "loss": 0.8745, "step": 18012 }, { "epoch": 0.9848214590808133, "grad_norm": 2.656924247741699, "learning_rate": 6.100348968975377e-08, "loss": 1.0563, "step": 18013 }, { "epoch": 0.9848761318981719, "grad_norm": 2.3769471645355225, "learning_rate": 6.056706053195193e-08, "loss": 0.8693, "step": 18014 }, { "epoch": 0.9849308047155305, "grad_norm": 2.8516037464141846, "learning_rate": 6.013219718103979e-08, "loss": 0.9861, "step": 18015 }, { "epoch": 0.9849854775328891, "grad_norm": 2.726290702819824, "learning_rate": 5.969889965065645e-08, "loss": 1.0839, "step": 18016 }, { "epoch": 0.9850401503502477, "grad_norm": 3.025690793991089, "learning_rate": 5.9267167954385474e-08, "loss": 1.2288, "step": 18017 }, { "epoch": 0.9850948231676063, "grad_norm": 2.6565022468566895, "learning_rate": 5.8837002105771585e-08, "loss": 0.9612, "step": 18018 }, { "epoch": 0.9851494959849649, "grad_norm": 2.0612542629241943, "learning_rate": 5.840840211829291e-08, "loss": 0.8168, "step": 18019 }, { "epoch": 0.9852041688023236, "grad_norm": 2.2564947605133057, "learning_rate": 5.798136800539422e-08, "loss": 0.9434, "step": 18020 }, { "epoch": 0.9852588416196822, "grad_norm": 2.1755614280700684, "learning_rate": 5.755589978046483e-08, "loss": 0.9228, "step": 18021 }, { "epoch": 0.9853135144370408, "grad_norm": 2.510582685470581, "learning_rate": 5.7131997456838506e-08, "loss": 0.9117, "step": 18022 }, { "epoch": 0.9853681872543995, "grad_norm": 2.4745402336120605, "learning_rate": 5.670966104781017e-08, "loss": 1.0647, "step": 18023 }, { "epoch": 0.9854228600717581, "grad_norm": 2.80307674407959, "learning_rate": 5.628889056662479e-08, "loss": 0.7562, "step": 18024 }, { "epoch": 0.9854775328891167, "grad_norm": 3.1604485511779785, "learning_rate": 5.58696860264718e-08, "loss": 0.9472, "step": 18025 }, { "epoch": 0.9855322057064753, "grad_norm": 2.7287206649780273, "learning_rate": 5.545204744049626e-08, "loss": 1.1153, "step": 18026 }, { "epoch": 0.985586878523834, "grad_norm": 2.842607021331787, "learning_rate": 5.5035974821793234e-08, "loss": 1.1234, "step": 18027 }, { "epoch": 0.9856415513411926, "grad_norm": 2.4229273796081543, "learning_rate": 5.46214681834023e-08, "loss": 0.9615, "step": 18028 }, { "epoch": 0.9856962241585512, "grad_norm": 2.6950840950012207, "learning_rate": 5.420852753832972e-08, "loss": 1.136, "step": 18029 }, { "epoch": 0.9857508969759098, "grad_norm": 2.226299524307251, "learning_rate": 5.3797152899515146e-08, "loss": 1.0049, "step": 18030 }, { "epoch": 0.9858055697932684, "grad_norm": 1.9439022541046143, "learning_rate": 5.3387344279859366e-08, "loss": 0.8509, "step": 18031 }, { "epoch": 0.985860242610627, "grad_norm": 2.1486213207244873, "learning_rate": 5.297910169221321e-08, "loss": 0.9085, "step": 18032 }, { "epoch": 0.9859149154279856, "grad_norm": 1.9974803924560547, "learning_rate": 5.2572425149377545e-08, "loss": 0.8101, "step": 18033 }, { "epoch": 0.9859695882453443, "grad_norm": 3.347407817840576, "learning_rate": 5.216731466409775e-08, "loss": 1.1759, "step": 18034 }, { "epoch": 0.9860242610627029, "grad_norm": 2.7155416011810303, "learning_rate": 5.17637702490803e-08, "loss": 1.0878, "step": 18035 }, { "epoch": 0.9860789338800615, "grad_norm": 3.1356537342071533, "learning_rate": 5.136179191698176e-08, "loss": 0.8912, "step": 18036 }, { "epoch": 0.9861336066974201, "grad_norm": 2.880099296569824, "learning_rate": 5.0961379680397605e-08, "loss": 0.992, "step": 18037 }, { "epoch": 0.9861882795147787, "grad_norm": 2.6223371028900146, "learning_rate": 5.056253355188445e-08, "loss": 1.2176, "step": 18038 }, { "epoch": 0.9862429523321373, "grad_norm": 4.043069362640381, "learning_rate": 5.0165253543948966e-08, "loss": 1.232, "step": 18039 }, { "epoch": 0.986297625149496, "grad_norm": 2.9197216033935547, "learning_rate": 4.976953966904785e-08, "loss": 0.9194, "step": 18040 }, { "epoch": 0.9863522979668546, "grad_norm": 3.9407176971435547, "learning_rate": 4.93753919395934e-08, "loss": 1.0835, "step": 18041 }, { "epoch": 0.9864069707842132, "grad_norm": 2.453735113143921, "learning_rate": 4.898281036793129e-08, "loss": 1.0699, "step": 18042 }, { "epoch": 0.9864616436015718, "grad_norm": 2.2634682655334473, "learning_rate": 4.8591794966384995e-08, "loss": 1.0892, "step": 18043 }, { "epoch": 0.9865163164189305, "grad_norm": 2.1466801166534424, "learning_rate": 4.8202345747200285e-08, "loss": 0.8824, "step": 18044 }, { "epoch": 0.986570989236289, "grad_norm": 2.1241040229797363, "learning_rate": 4.7814462722600706e-08, "loss": 0.727, "step": 18045 }, { "epoch": 0.9866256620536477, "grad_norm": 3.2077572345733643, "learning_rate": 4.742814590473765e-08, "loss": 1.1816, "step": 18046 }, { "epoch": 0.9866803348710064, "grad_norm": 2.6750197410583496, "learning_rate": 4.704339530573476e-08, "loss": 1.0599, "step": 18047 }, { "epoch": 0.986735007688365, "grad_norm": 2.6718809604644775, "learning_rate": 4.66602109376435e-08, "loss": 1.0674, "step": 18048 }, { "epoch": 0.9867896805057236, "grad_norm": 2.5920181274414062, "learning_rate": 4.6278592812487585e-08, "loss": 1.0599, "step": 18049 }, { "epoch": 0.9868443533230822, "grad_norm": 2.7895021438598633, "learning_rate": 4.5898540942229675e-08, "loss": 1.1308, "step": 18050 }, { "epoch": 0.9868990261404408, "grad_norm": 2.931549310684204, "learning_rate": 4.5520055338782455e-08, "loss": 1.1234, "step": 18051 }, { "epoch": 0.9869536989577994, "grad_norm": 2.10040283203125, "learning_rate": 4.5143136014014206e-08, "loss": 0.8096, "step": 18052 }, { "epoch": 0.987008371775158, "grad_norm": 2.6285784244537354, "learning_rate": 4.476778297974327e-08, "loss": 0.8398, "step": 18053 }, { "epoch": 0.9870630445925167, "grad_norm": 2.7001163959503174, "learning_rate": 4.4393996247743544e-08, "loss": 0.9246, "step": 18054 }, { "epoch": 0.9871177174098753, "grad_norm": 2.579359531402588, "learning_rate": 4.4021775829727885e-08, "loss": 0.9237, "step": 18055 }, { "epoch": 0.9871723902272339, "grad_norm": 2.173552989959717, "learning_rate": 4.365112173737029e-08, "loss": 1.0024, "step": 18056 }, { "epoch": 0.9872270630445925, "grad_norm": 2.465536117553711, "learning_rate": 4.32820339822948e-08, "loss": 0.9892, "step": 18057 }, { "epoch": 0.9872817358619511, "grad_norm": 2.3422040939331055, "learning_rate": 4.2914512576069934e-08, "loss": 0.9884, "step": 18058 }, { "epoch": 0.9873364086793097, "grad_norm": 2.8228659629821777, "learning_rate": 4.25485575302198e-08, "loss": 0.9022, "step": 18059 }, { "epoch": 0.9873910814966683, "grad_norm": 2.8531973361968994, "learning_rate": 4.2184168856218566e-08, "loss": 1.041, "step": 18060 }, { "epoch": 0.987445754314027, "grad_norm": 4.005501747131348, "learning_rate": 4.182134656549042e-08, "loss": 0.8498, "step": 18061 }, { "epoch": 0.9875004271313856, "grad_norm": 2.5626776218414307, "learning_rate": 4.146009066940959e-08, "loss": 1.2133, "step": 18062 }, { "epoch": 0.9875550999487442, "grad_norm": 2.508302927017212, "learning_rate": 4.1100401179311465e-08, "loss": 1.057, "step": 18063 }, { "epoch": 0.9876097727661028, "grad_norm": 2.1179678440093994, "learning_rate": 4.0742278106464806e-08, "loss": 1.0473, "step": 18064 }, { "epoch": 0.9876644455834614, "grad_norm": 2.5925323963165283, "learning_rate": 4.0385721462099515e-08, "loss": 0.9545, "step": 18065 }, { "epoch": 0.98771911840082, "grad_norm": 2.4543821811676025, "learning_rate": 4.003073125740109e-08, "loss": 0.9514, "step": 18066 }, { "epoch": 0.9877737912181788, "grad_norm": 2.315263032913208, "learning_rate": 3.967730750349397e-08, "loss": 0.9939, "step": 18067 }, { "epoch": 0.9878284640355374, "grad_norm": 2.870882749557495, "learning_rate": 3.932545021146372e-08, "loss": 0.9072, "step": 18068 }, { "epoch": 0.987883136852896, "grad_norm": 2.4370813369750977, "learning_rate": 3.8975159392340424e-08, "loss": 0.8288, "step": 18069 }, { "epoch": 0.9879378096702546, "grad_norm": 2.4653286933898926, "learning_rate": 3.862643505710417e-08, "loss": 1.0143, "step": 18070 }, { "epoch": 0.9879924824876132, "grad_norm": 2.2391209602355957, "learning_rate": 3.827927721669067e-08, "loss": 1.0638, "step": 18071 }, { "epoch": 0.9880471553049718, "grad_norm": 3.8379690647125244, "learning_rate": 3.7933685881985646e-08, "loss": 0.9114, "step": 18072 }, { "epoch": 0.9881018281223304, "grad_norm": 2.5613925457000732, "learning_rate": 3.758966106383044e-08, "loss": 1.0929, "step": 18073 }, { "epoch": 0.9881565009396891, "grad_norm": 2.6416125297546387, "learning_rate": 3.7247202772999754e-08, "loss": 0.9513, "step": 18074 }, { "epoch": 0.9882111737570477, "grad_norm": 2.739490032196045, "learning_rate": 3.6906311020240557e-08, "loss": 0.9393, "step": 18075 }, { "epoch": 0.9882658465744063, "grad_norm": 2.25826358795166, "learning_rate": 3.6566985816238744e-08, "loss": 1.0633, "step": 18076 }, { "epoch": 0.9883205193917649, "grad_norm": 2.347105026245117, "learning_rate": 3.6229227171630245e-08, "loss": 0.9879, "step": 18077 }, { "epoch": 0.9883751922091235, "grad_norm": 2.8538124561309814, "learning_rate": 3.589303509701214e-08, "loss": 0.9389, "step": 18078 }, { "epoch": 0.9884298650264821, "grad_norm": 3.8400723934173584, "learning_rate": 3.5558409602914897e-08, "loss": 1.0585, "step": 18079 }, { "epoch": 0.9884845378438407, "grad_norm": 2.3462517261505127, "learning_rate": 3.522535069984123e-08, "loss": 1.0138, "step": 18080 }, { "epoch": 0.9885392106611994, "grad_norm": 2.6204750537872314, "learning_rate": 3.489385839822723e-08, "loss": 0.988, "step": 18081 }, { "epoch": 0.988593883478558, "grad_norm": 2.523414373397827, "learning_rate": 3.456393270847014e-08, "loss": 1.0076, "step": 18082 }, { "epoch": 0.9886485562959166, "grad_norm": 2.297412395477295, "learning_rate": 3.423557364091168e-08, "loss": 0.9653, "step": 18083 }, { "epoch": 0.9887032291132752, "grad_norm": 3.0291600227355957, "learning_rate": 3.390878120584917e-08, "loss": 1.1478, "step": 18084 }, { "epoch": 0.9887579019306338, "grad_norm": 3.959975004196167, "learning_rate": 3.3583555413529974e-08, "loss": 1.0498, "step": 18085 }, { "epoch": 0.9888125747479924, "grad_norm": 2.6869454383850098, "learning_rate": 3.325989627414594e-08, "loss": 1.0388, "step": 18086 }, { "epoch": 0.988867247565351, "grad_norm": 2.3682162761688232, "learning_rate": 3.2937803797855604e-08, "loss": 1.1164, "step": 18087 }, { "epoch": 0.9889219203827098, "grad_norm": 2.3683888912200928, "learning_rate": 3.261727799474534e-08, "loss": 0.8837, "step": 18088 }, { "epoch": 0.9889765932000684, "grad_norm": 2.574374198913574, "learning_rate": 3.229831887486823e-08, "loss": 0.9509, "step": 18089 }, { "epoch": 0.989031266017427, "grad_norm": 3.089484691619873, "learning_rate": 3.198092644823292e-08, "loss": 0.9767, "step": 18090 }, { "epoch": 0.9890859388347856, "grad_norm": 2.6297149658203125, "learning_rate": 3.166510072478146e-08, "loss": 0.9221, "step": 18091 }, { "epoch": 0.9891406116521442, "grad_norm": 3.264108180999756, "learning_rate": 3.1350841714422594e-08, "loss": 0.8799, "step": 18092 }, { "epoch": 0.9891952844695028, "grad_norm": 2.6970908641815186, "learning_rate": 3.103814942700955e-08, "loss": 1.0471, "step": 18093 }, { "epoch": 0.9892499572868615, "grad_norm": 2.4380903244018555, "learning_rate": 3.0727023872340054e-08, "loss": 0.9504, "step": 18094 }, { "epoch": 0.9893046301042201, "grad_norm": 2.1971170902252197, "learning_rate": 3.0417465060172956e-08, "loss": 0.9284, "step": 18095 }, { "epoch": 0.9893593029215787, "grad_norm": 2.709603786468506, "learning_rate": 3.010947300021716e-08, "loss": 0.89, "step": 18096 }, { "epoch": 0.9894139757389373, "grad_norm": 2.7071094512939453, "learning_rate": 2.9803047702126055e-08, "loss": 0.9935, "step": 18097 }, { "epoch": 0.9894686485562959, "grad_norm": 2.061063528060913, "learning_rate": 2.9498189175508616e-08, "loss": 1.0835, "step": 18098 }, { "epoch": 0.9895233213736545, "grad_norm": 2.7189431190490723, "learning_rate": 2.9194897429923872e-08, "loss": 1.0744, "step": 18099 }, { "epoch": 0.9895779941910131, "grad_norm": 2.521688461303711, "learning_rate": 2.889317247488088e-08, "loss": 1.1594, "step": 18100 }, { "epoch": 0.9896326670083718, "grad_norm": 2.55778169631958, "learning_rate": 2.859301431983319e-08, "loss": 0.931, "step": 18101 }, { "epoch": 0.9896873398257304, "grad_norm": 2.886828660964966, "learning_rate": 2.829442297420659e-08, "loss": 1.11, "step": 18102 }, { "epoch": 0.989742012643089, "grad_norm": 2.612969160079956, "learning_rate": 2.7997398447349165e-08, "loss": 1.2438, "step": 18103 }, { "epoch": 0.9897966854604476, "grad_norm": 2.5654032230377197, "learning_rate": 2.7701940748581235e-08, "loss": 1.0842, "step": 18104 }, { "epoch": 0.9898513582778062, "grad_norm": 1.8944040536880493, "learning_rate": 2.7408049887167607e-08, "loss": 0.6982, "step": 18105 }, { "epoch": 0.9899060310951648, "grad_norm": 2.8292324542999268, "learning_rate": 2.7115725872317587e-08, "loss": 1.1197, "step": 18106 }, { "epoch": 0.9899607039125234, "grad_norm": 2.747795581817627, "learning_rate": 2.6824968713201616e-08, "loss": 0.9877, "step": 18107 }, { "epoch": 0.9900153767298822, "grad_norm": 2.7684528827667236, "learning_rate": 2.653577841893462e-08, "loss": 0.9279, "step": 18108 }, { "epoch": 0.9900700495472408, "grad_norm": 2.5544450283050537, "learning_rate": 2.6248154998576026e-08, "loss": 0.912, "step": 18109 }, { "epoch": 0.9901247223645994, "grad_norm": 2.9499425888061523, "learning_rate": 2.5962098461157492e-08, "loss": 1.1284, "step": 18110 }, { "epoch": 0.990179395181958, "grad_norm": 3.1617271900177, "learning_rate": 2.5677608815638522e-08, "loss": 1.3159, "step": 18111 }, { "epoch": 0.9902340679993166, "grad_norm": 2.433103561401367, "learning_rate": 2.5394686070945305e-08, "loss": 0.8862, "step": 18112 }, { "epoch": 0.9902887408166752, "grad_norm": 2.843590259552002, "learning_rate": 2.511333023594853e-08, "loss": 1.2897, "step": 18113 }, { "epoch": 0.9903434136340338, "grad_norm": 2.458763599395752, "learning_rate": 2.483354131946336e-08, "loss": 0.8516, "step": 18114 }, { "epoch": 0.9903980864513925, "grad_norm": 3.0867502689361572, "learning_rate": 2.4555319330266113e-08, "loss": 1.0602, "step": 18115 }, { "epoch": 0.9904527592687511, "grad_norm": 3.206805467605591, "learning_rate": 2.427866427707759e-08, "loss": 1.031, "step": 18116 }, { "epoch": 0.9905074320861097, "grad_norm": 2.483067274093628, "learning_rate": 2.4003576168574183e-08, "loss": 0.9357, "step": 18117 }, { "epoch": 0.9905621049034683, "grad_norm": 2.629775285720825, "learning_rate": 2.3730055013387874e-08, "loss": 1.1117, "step": 18118 }, { "epoch": 0.9906167777208269, "grad_norm": 3.5164802074432373, "learning_rate": 2.3458100820084038e-08, "loss": 0.9653, "step": 18119 }, { "epoch": 0.9906714505381855, "grad_norm": 3.221430540084839, "learning_rate": 2.3187713597194736e-08, "loss": 1.0021, "step": 18120 }, { "epoch": 0.9907261233555442, "grad_norm": 2.569648504257202, "learning_rate": 2.2918893353190975e-08, "loss": 0.9152, "step": 18121 }, { "epoch": 0.9907807961729028, "grad_norm": 2.279045343399048, "learning_rate": 2.265164009651599e-08, "loss": 0.9348, "step": 18122 }, { "epoch": 0.9908354689902614, "grad_norm": 2.81876277923584, "learning_rate": 2.2385953835535323e-08, "loss": 0.9518, "step": 18123 }, { "epoch": 0.99089014180762, "grad_norm": 2.445016384124756, "learning_rate": 2.212183457858674e-08, "loss": 1.0501, "step": 18124 }, { "epoch": 0.9909448146249786, "grad_norm": 2.352539300918579, "learning_rate": 2.1859282333946963e-08, "loss": 1.0319, "step": 18125 }, { "epoch": 0.9909994874423372, "grad_norm": 2.157334804534912, "learning_rate": 2.1598297109848286e-08, "loss": 0.9311, "step": 18126 }, { "epoch": 0.9910541602596958, "grad_norm": 3.4168038368225098, "learning_rate": 2.133887891447861e-08, "loss": 0.7419, "step": 18127 }, { "epoch": 0.9911088330770546, "grad_norm": 2.0931663513183594, "learning_rate": 2.108102775597032e-08, "loss": 0.8835, "step": 18128 }, { "epoch": 0.9911635058944132, "grad_norm": 2.4824485778808594, "learning_rate": 2.082474364240583e-08, "loss": 0.9285, "step": 18129 }, { "epoch": 0.9912181787117718, "grad_norm": 2.9512619972229004, "learning_rate": 2.0570026581817614e-08, "loss": 0.9058, "step": 18130 }, { "epoch": 0.9912728515291304, "grad_norm": 2.6936097145080566, "learning_rate": 2.0316876582199275e-08, "loss": 1.0139, "step": 18131 }, { "epoch": 0.991327524346489, "grad_norm": 2.969271659851074, "learning_rate": 2.0065293651483353e-08, "loss": 0.9213, "step": 18132 }, { "epoch": 0.9913821971638476, "grad_norm": 3.3925795555114746, "learning_rate": 1.9815277797557986e-08, "loss": 1.0903, "step": 18133 }, { "epoch": 0.9914368699812062, "grad_norm": 3.4382591247558594, "learning_rate": 1.9566829028266897e-08, "loss": 1.0582, "step": 18134 }, { "epoch": 0.9914915427985649, "grad_norm": 2.8103432655334473, "learning_rate": 1.9319947351398305e-08, "loss": 1.0374, "step": 18135 }, { "epoch": 0.9915462156159235, "grad_norm": 2.7462944984436035, "learning_rate": 1.9074632774684907e-08, "loss": 0.6513, "step": 18136 }, { "epoch": 0.9916008884332821, "grad_norm": 2.5552446842193604, "learning_rate": 1.883088530583166e-08, "loss": 1.0621, "step": 18137 }, { "epoch": 0.9916555612506407, "grad_norm": 2.681513547897339, "learning_rate": 1.8588704952471337e-08, "loss": 1.0754, "step": 18138 }, { "epoch": 0.9917102340679993, "grad_norm": 2.7389795780181885, "learning_rate": 1.834809172219787e-08, "loss": 0.8709, "step": 18139 }, { "epoch": 0.9917649068853579, "grad_norm": 3.111572265625, "learning_rate": 1.810904562256077e-08, "loss": 1.1226, "step": 18140 }, { "epoch": 0.9918195797027165, "grad_norm": 2.4597129821777344, "learning_rate": 1.78715666610485e-08, "loss": 0.8781, "step": 18141 }, { "epoch": 0.9918742525200752, "grad_norm": 2.6837124824523926, "learning_rate": 1.763565484511065e-08, "loss": 0.829, "step": 18142 }, { "epoch": 0.9919289253374338, "grad_norm": 2.5302584171295166, "learning_rate": 1.7401310182146856e-08, "loss": 0.9548, "step": 18143 }, { "epoch": 0.9919835981547924, "grad_norm": 2.739842176437378, "learning_rate": 1.7168532679501248e-08, "loss": 1.1697, "step": 18144 }, { "epoch": 0.992038270972151, "grad_norm": 3.529381036758423, "learning_rate": 1.6937322344473538e-08, "loss": 0.9925, "step": 18145 }, { "epoch": 0.9920929437895096, "grad_norm": 2.7393317222595215, "learning_rate": 1.6707679184313486e-08, "loss": 1.1614, "step": 18146 }, { "epoch": 0.9921476166068682, "grad_norm": 2.915496826171875, "learning_rate": 1.6479603206220883e-08, "loss": 1.1091, "step": 18147 }, { "epoch": 0.992202289424227, "grad_norm": 2.4017422199249268, "learning_rate": 1.625309441734557e-08, "loss": 1.055, "step": 18148 }, { "epoch": 0.9922569622415855, "grad_norm": 2.459529161453247, "learning_rate": 1.6028152824787422e-08, "loss": 0.9979, "step": 18149 }, { "epoch": 0.9923116350589442, "grad_norm": 2.7723593711853027, "learning_rate": 1.5804778435601907e-08, "loss": 0.7799, "step": 18150 }, { "epoch": 0.9923663078763028, "grad_norm": 2.7924790382385254, "learning_rate": 1.558297125679453e-08, "loss": 1.1158, "step": 18151 }, { "epoch": 0.9924209806936614, "grad_norm": 2.3829469680786133, "learning_rate": 1.5362731295320843e-08, "loss": 1.0516, "step": 18152 }, { "epoch": 0.99247565351102, "grad_norm": 3.7764978408813477, "learning_rate": 1.5144058558080877e-08, "loss": 0.9977, "step": 18153 }, { "epoch": 0.9925303263283786, "grad_norm": 3.1370224952697754, "learning_rate": 1.492695305193581e-08, "loss": 1.1026, "step": 18154 }, { "epoch": 0.9925849991457373, "grad_norm": 2.5394833087921143, "learning_rate": 1.4711414783691314e-08, "loss": 0.8697, "step": 18155 }, { "epoch": 0.9926396719630959, "grad_norm": 2.3120079040527344, "learning_rate": 1.449744376010309e-08, "loss": 0.9619, "step": 18156 }, { "epoch": 0.9926943447804545, "grad_norm": 2.882692813873291, "learning_rate": 1.4285039987882442e-08, "loss": 0.9345, "step": 18157 }, { "epoch": 0.9927490175978131, "grad_norm": 3.183807849884033, "learning_rate": 1.4074203473690706e-08, "loss": 1.1078, "step": 18158 }, { "epoch": 0.9928036904151717, "grad_norm": 2.6858901977539062, "learning_rate": 1.3864934224133708e-08, "loss": 0.9816, "step": 18159 }, { "epoch": 0.9928583632325303, "grad_norm": 2.355072259902954, "learning_rate": 1.3657232245778417e-08, "loss": 0.767, "step": 18160 }, { "epoch": 0.9929130360498889, "grad_norm": 2.3659420013427734, "learning_rate": 1.3451097545130741e-08, "loss": 1.1534, "step": 18161 }, { "epoch": 0.9929677088672476, "grad_norm": 2.3671517372131348, "learning_rate": 1.324653012865773e-08, "loss": 0.871, "step": 18162 }, { "epoch": 0.9930223816846062, "grad_norm": 2.913210153579712, "learning_rate": 1.3043530002776471e-08, "loss": 1.0362, "step": 18163 }, { "epoch": 0.9930770545019648, "grad_norm": 2.4128100872039795, "learning_rate": 1.2842097173842994e-08, "loss": 1.086, "step": 18164 }, { "epoch": 0.9931317273193234, "grad_norm": 2.2188587188720703, "learning_rate": 1.2642231648180014e-08, "loss": 0.959, "step": 18165 }, { "epoch": 0.993186400136682, "grad_norm": 2.6331634521484375, "learning_rate": 1.2443933432054743e-08, "loss": 1.1222, "step": 18166 }, { "epoch": 0.9932410729540406, "grad_norm": 3.3772189617156982, "learning_rate": 1.2247202531684433e-08, "loss": 1.0377, "step": 18167 }, { "epoch": 0.9932957457713992, "grad_norm": 2.6886773109436035, "learning_rate": 1.2052038953230815e-08, "loss": 0.917, "step": 18168 }, { "epoch": 0.9933504185887579, "grad_norm": 3.787132740020752, "learning_rate": 1.1858442702816775e-08, "loss": 0.9694, "step": 18169 }, { "epoch": 0.9934050914061165, "grad_norm": 2.3199710845947266, "learning_rate": 1.1666413786515228e-08, "loss": 1.0046, "step": 18170 }, { "epoch": 0.9934597642234752, "grad_norm": 2.7423033714294434, "learning_rate": 1.1475952210349139e-08, "loss": 1.1183, "step": 18171 }, { "epoch": 0.9935144370408338, "grad_norm": 2.479527473449707, "learning_rate": 1.1287057980280402e-08, "loss": 0.9578, "step": 18172 }, { "epoch": 0.9935691098581924, "grad_norm": 2.9826767444610596, "learning_rate": 1.109973110224316e-08, "loss": 0.945, "step": 18173 }, { "epoch": 0.993623782675551, "grad_norm": 3.874553680419922, "learning_rate": 1.0913971582099392e-08, "loss": 0.9674, "step": 18174 }, { "epoch": 0.9936784554929097, "grad_norm": 2.560807466506958, "learning_rate": 1.0729779425683318e-08, "loss": 0.9897, "step": 18175 }, { "epoch": 0.9937331283102683, "grad_norm": 2.776315689086914, "learning_rate": 1.0547154638762547e-08, "loss": 0.7852, "step": 18176 }, { "epoch": 0.9937878011276269, "grad_norm": 3.565333604812622, "learning_rate": 1.0366097227071381e-08, "loss": 1.0608, "step": 18177 }, { "epoch": 0.9938424739449855, "grad_norm": 3.068613290786743, "learning_rate": 1.018660719627751e-08, "loss": 0.9141, "step": 18178 }, { "epoch": 0.9938971467623441, "grad_norm": 2.4557034969329834, "learning_rate": 1.0008684552015313e-08, "loss": 1.0662, "step": 18179 }, { "epoch": 0.9939518195797027, "grad_norm": 2.4119930267333984, "learning_rate": 9.832329299858111e-09, "loss": 1.0291, "step": 18180 }, { "epoch": 0.9940064923970613, "grad_norm": 2.6298611164093018, "learning_rate": 9.657541445340367e-09, "loss": 0.9131, "step": 18181 }, { "epoch": 0.99406116521442, "grad_norm": 2.7494282722473145, "learning_rate": 9.484320993941032e-09, "loss": 0.9454, "step": 18182 }, { "epoch": 0.9941158380317786, "grad_norm": 2.222320079803467, "learning_rate": 9.312667951094644e-09, "loss": 0.8739, "step": 18183 }, { "epoch": 0.9941705108491372, "grad_norm": 2.292915105819702, "learning_rate": 9.142582322174686e-09, "loss": 0.9237, "step": 18184 }, { "epoch": 0.9942251836664958, "grad_norm": 2.4018054008483887, "learning_rate": 8.97406411252133e-09, "loss": 0.9455, "step": 18185 }, { "epoch": 0.9942798564838544, "grad_norm": 2.8775265216827393, "learning_rate": 8.807113327413686e-09, "loss": 1.1491, "step": 18186 }, { "epoch": 0.994334529301213, "grad_norm": 3.354627847671509, "learning_rate": 8.641729972086455e-09, "loss": 1.3274, "step": 18187 }, { "epoch": 0.9943892021185716, "grad_norm": 2.598877429962158, "learning_rate": 8.477914051729929e-09, "loss": 0.8679, "step": 18188 }, { "epoch": 0.9944438749359303, "grad_norm": 2.8934006690979004, "learning_rate": 8.315665571478893e-09, "loss": 0.9459, "step": 18189 }, { "epoch": 0.9944985477532889, "grad_norm": 2.432101011276245, "learning_rate": 8.154984536412614e-09, "loss": 1.0158, "step": 18190 }, { "epoch": 0.9945532205706475, "grad_norm": 2.5771467685699463, "learning_rate": 7.995870951582607e-09, "loss": 0.8998, "step": 18191 }, { "epoch": 0.9946078933880061, "grad_norm": 2.6506288051605225, "learning_rate": 7.838324821968224e-09, "loss": 0.9714, "step": 18192 }, { "epoch": 0.9946625662053648, "grad_norm": 2.378934621810913, "learning_rate": 7.682346152509956e-09, "loss": 0.806, "step": 18193 }, { "epoch": 0.9947172390227234, "grad_norm": 2.4392387866973877, "learning_rate": 7.527934948098336e-09, "loss": 1.0382, "step": 18194 }, { "epoch": 0.994771911840082, "grad_norm": 3.3173606395721436, "learning_rate": 7.375091213579488e-09, "loss": 1.0598, "step": 18195 }, { "epoch": 0.9948265846574407, "grad_norm": 3.9827935695648193, "learning_rate": 7.223814953744023e-09, "loss": 0.9157, "step": 18196 }, { "epoch": 0.9948812574747993, "grad_norm": 3.0791831016540527, "learning_rate": 7.0741061733325955e-09, "loss": 0.9478, "step": 18197 }, { "epoch": 0.9949359302921579, "grad_norm": 2.7495102882385254, "learning_rate": 6.9259648770414464e-09, "loss": 1.0705, "step": 18198 }, { "epoch": 0.9949906031095165, "grad_norm": 2.755213499069214, "learning_rate": 6.779391069511309e-09, "loss": 1.1368, "step": 18199 }, { "epoch": 0.9950452759268751, "grad_norm": 2.245496988296509, "learning_rate": 6.6343847553440585e-09, "loss": 0.9431, "step": 18200 }, { "epoch": 0.9950999487442337, "grad_norm": 2.5020675659179688, "learning_rate": 6.490945939080506e-09, "loss": 1.0127, "step": 18201 }, { "epoch": 0.9951546215615924, "grad_norm": 2.6039628982543945, "learning_rate": 6.349074625222606e-09, "loss": 1.1159, "step": 18202 }, { "epoch": 0.995209294378951, "grad_norm": 2.2803735733032227, "learning_rate": 6.208770818216803e-09, "loss": 1.027, "step": 18203 }, { "epoch": 0.9952639671963096, "grad_norm": 2.688920259475708, "learning_rate": 6.0700345224595776e-09, "loss": 0.8253, "step": 18204 }, { "epoch": 0.9953186400136682, "grad_norm": 2.334468364715576, "learning_rate": 5.932865742308557e-09, "loss": 1.1566, "step": 18205 }, { "epoch": 0.9953733128310268, "grad_norm": 2.763972043991089, "learning_rate": 5.797264482054754e-09, "loss": 1.1008, "step": 18206 }, { "epoch": 0.9954279856483854, "grad_norm": 2.546722412109375, "learning_rate": 5.663230745955872e-09, "loss": 1.1431, "step": 18207 }, { "epoch": 0.995482658465744, "grad_norm": 2.6998307704925537, "learning_rate": 5.530764538208555e-09, "loss": 1.0299, "step": 18208 }, { "epoch": 0.9955373312831027, "grad_norm": 2.136823892593384, "learning_rate": 5.399865862976139e-09, "loss": 0.9652, "step": 18209 }, { "epoch": 0.9955920041004613, "grad_norm": 2.9537765979766846, "learning_rate": 5.270534724355347e-09, "loss": 0.7698, "step": 18210 }, { "epoch": 0.9956466769178199, "grad_norm": 2.485213279724121, "learning_rate": 5.142771126404044e-09, "loss": 1.17, "step": 18211 }, { "epoch": 0.9957013497351785, "grad_norm": 2.822504758834839, "learning_rate": 5.016575073124586e-09, "loss": 1.054, "step": 18212 }, { "epoch": 0.9957560225525371, "grad_norm": 2.798894166946411, "learning_rate": 4.891946568480465e-09, "loss": 1.0776, "step": 18213 }, { "epoch": 0.9958106953698957, "grad_norm": 2.6317312717437744, "learning_rate": 4.768885616374119e-09, "loss": 0.7231, "step": 18214 }, { "epoch": 0.9958653681872544, "grad_norm": 6.427474498748779, "learning_rate": 4.647392220663571e-09, "loss": 1.1001, "step": 18215 }, { "epoch": 0.9959200410046131, "grad_norm": 2.4785189628601074, "learning_rate": 4.527466385156886e-09, "loss": 1.0154, "step": 18216 }, { "epoch": 0.9959747138219717, "grad_norm": 2.3232076168060303, "learning_rate": 4.409108113623272e-09, "loss": 1.021, "step": 18217 }, { "epoch": 0.9960293866393303, "grad_norm": 2.407447576522827, "learning_rate": 4.292317409765323e-09, "loss": 1.0913, "step": 18218 }, { "epoch": 0.9960840594566889, "grad_norm": 3.3906049728393555, "learning_rate": 4.177094277246774e-09, "loss": 0.9242, "step": 18219 }, { "epoch": 0.9961387322740475, "grad_norm": 3.1066102981567383, "learning_rate": 4.06343871967585e-09, "loss": 1.2145, "step": 18220 }, { "epoch": 0.9961934050914061, "grad_norm": 2.0842409133911133, "learning_rate": 3.951350740627468e-09, "loss": 0.9646, "step": 18221 }, { "epoch": 0.9962480779087647, "grad_norm": 2.4083147048950195, "learning_rate": 3.8408303436099354e-09, "loss": 0.9095, "step": 18222 }, { "epoch": 0.9963027507261234, "grad_norm": 2.7142882347106934, "learning_rate": 3.731877532081596e-09, "loss": 1.016, "step": 18223 }, { "epoch": 0.996357423543482, "grad_norm": 2.925635814666748, "learning_rate": 3.6244923094730375e-09, "loss": 1.0059, "step": 18224 }, { "epoch": 0.9964120963608406, "grad_norm": 3.494220733642578, "learning_rate": 3.518674679137135e-09, "loss": 0.9429, "step": 18225 }, { "epoch": 0.9964667691781992, "grad_norm": 2.6528000831604004, "learning_rate": 3.414424644399006e-09, "loss": 1.1451, "step": 18226 }, { "epoch": 0.9965214419955578, "grad_norm": 2.223998546600342, "learning_rate": 3.3117422085282568e-09, "loss": 1.0838, "step": 18227 }, { "epoch": 0.9965761148129164, "grad_norm": 2.218229293823242, "learning_rate": 3.210627374744535e-09, "loss": 0.9852, "step": 18228 }, { "epoch": 0.9966307876302751, "grad_norm": 2.8149478435516357, "learning_rate": 3.1110801462119752e-09, "loss": 0.8696, "step": 18229 }, { "epoch": 0.9966854604476337, "grad_norm": 2.8865103721618652, "learning_rate": 3.0131005260558564e-09, "loss": 1.0193, "step": 18230 }, { "epoch": 0.9967401332649923, "grad_norm": 2.725992202758789, "learning_rate": 2.9166885173459445e-09, "loss": 1.0027, "step": 18231 }, { "epoch": 0.9967948060823509, "grad_norm": 2.040931463241577, "learning_rate": 2.821844123113149e-09, "loss": 0.8091, "step": 18232 }, { "epoch": 0.9968494788997095, "grad_norm": 3.096287250518799, "learning_rate": 2.728567346321764e-09, "loss": 0.8058, "step": 18233 }, { "epoch": 0.9969041517170681, "grad_norm": 2.9377715587615967, "learning_rate": 2.63685818990278e-09, "loss": 1.0594, "step": 18234 }, { "epoch": 0.9969588245344267, "grad_norm": 2.5403153896331787, "learning_rate": 2.5467166567261226e-09, "loss": 0.9335, "step": 18235 }, { "epoch": 0.9970134973517855, "grad_norm": 2.6466078758239746, "learning_rate": 2.4581427496228602e-09, "loss": 1.2031, "step": 18236 }, { "epoch": 0.9970681701691441, "grad_norm": 2.8200528621673584, "learning_rate": 2.3711364713685512e-09, "loss": 0.8746, "step": 18237 }, { "epoch": 0.9971228429865027, "grad_norm": 3.4276793003082275, "learning_rate": 2.285697824688793e-09, "loss": 1.0082, "step": 18238 }, { "epoch": 0.9971775158038613, "grad_norm": 5.429924964904785, "learning_rate": 2.2018268122647735e-09, "loss": 1.0672, "step": 18239 }, { "epoch": 0.9972321886212199, "grad_norm": 3.1501381397247314, "learning_rate": 2.1195234367277216e-09, "loss": 1.1169, "step": 18240 }, { "epoch": 0.9972868614385785, "grad_norm": 2.846791982650757, "learning_rate": 2.0387877006589063e-09, "loss": 1.1345, "step": 18241 }, { "epoch": 0.9973415342559371, "grad_norm": 3.076993703842163, "learning_rate": 1.9596196065840845e-09, "loss": 0.9508, "step": 18242 }, { "epoch": 0.9973962070732958, "grad_norm": 3.30422306060791, "learning_rate": 1.8820191569846045e-09, "loss": 1.2876, "step": 18243 }, { "epoch": 0.9974508798906544, "grad_norm": 2.333313465118408, "learning_rate": 1.8059863543029575e-09, "loss": 0.9375, "step": 18244 }, { "epoch": 0.997505552708013, "grad_norm": 2.3672173023223877, "learning_rate": 1.7315212009150206e-09, "loss": 1.084, "step": 18245 }, { "epoch": 0.9975602255253716, "grad_norm": 2.8023922443389893, "learning_rate": 1.658623699163364e-09, "loss": 0.983, "step": 18246 }, { "epoch": 0.9976148983427302, "grad_norm": 2.7670063972473145, "learning_rate": 1.5872938513239456e-09, "loss": 1.1325, "step": 18247 }, { "epoch": 0.9976695711600888, "grad_norm": 2.668914556503296, "learning_rate": 1.5175316596394152e-09, "loss": 1.156, "step": 18248 }, { "epoch": 0.9977242439774474, "grad_norm": 3.612527847290039, "learning_rate": 1.4493371262969125e-09, "loss": 1.1449, "step": 18249 }, { "epoch": 0.9977789167948061, "grad_norm": 2.9200050830841064, "learning_rate": 1.3827102534280655e-09, "loss": 0.9926, "step": 18250 }, { "epoch": 0.9978335896121647, "grad_norm": 2.705785036087036, "learning_rate": 1.3176510431311962e-09, "loss": 1.0391, "step": 18251 }, { "epoch": 0.9978882624295233, "grad_norm": 2.4576005935668945, "learning_rate": 1.2541594974435634e-09, "loss": 0.773, "step": 18252 }, { "epoch": 0.9979429352468819, "grad_norm": 2.587250232696533, "learning_rate": 1.1922356183524663e-09, "loss": 1.2361, "step": 18253 }, { "epoch": 0.9979976080642405, "grad_norm": 2.925442695617676, "learning_rate": 1.1318794078007955e-09, "loss": 0.9504, "step": 18254 }, { "epoch": 0.9980522808815991, "grad_norm": 2.912444591522217, "learning_rate": 1.073090867681481e-09, "loss": 1.1593, "step": 18255 }, { "epoch": 0.9981069536989577, "grad_norm": 2.1877894401550293, "learning_rate": 1.0158699998374933e-09, "loss": 0.8335, "step": 18256 }, { "epoch": 0.9981616265163165, "grad_norm": 3.7495343685150146, "learning_rate": 9.602168060673932e-10, "loss": 1.0623, "step": 18257 }, { "epoch": 0.9982162993336751, "grad_norm": 2.000237464904785, "learning_rate": 9.061312881086803e-10, "loss": 0.9368, "step": 18258 }, { "epoch": 0.9982709721510337, "grad_norm": 3.3577191829681396, "learning_rate": 8.536134476599956e-10, "loss": 1.0193, "step": 18259 }, { "epoch": 0.9983256449683923, "grad_norm": 3.5034072399139404, "learning_rate": 8.026632863700201e-10, "loss": 1.0016, "step": 18260 }, { "epoch": 0.9983803177857509, "grad_norm": 3.5828936100006104, "learning_rate": 7.532808058319241e-10, "loss": 1.0632, "step": 18261 }, { "epoch": 0.9984349906031095, "grad_norm": 2.804192066192627, "learning_rate": 7.054660076000197e-10, "loss": 0.9445, "step": 18262 }, { "epoch": 0.9984896634204682, "grad_norm": 2.342967987060547, "learning_rate": 6.59218893173108e-10, "loss": 1.0864, "step": 18263 }, { "epoch": 0.9985443362378268, "grad_norm": 2.7749671936035156, "learning_rate": 6.145394639944791e-10, "loss": 1.0607, "step": 18264 }, { "epoch": 0.9985990090551854, "grad_norm": 2.686915159225464, "learning_rate": 5.714277214685648e-10, "loss": 1.0083, "step": 18265 }, { "epoch": 0.998653681872544, "grad_norm": 2.5508620738983154, "learning_rate": 5.298836669498375e-10, "loss": 0.9735, "step": 18266 }, { "epoch": 0.9987083546899026, "grad_norm": 2.504246234893799, "learning_rate": 4.899073017372579e-10, "loss": 1.0823, "step": 18267 }, { "epoch": 0.9987630275072612, "grad_norm": 2.564606189727783, "learning_rate": 4.514986270853783e-10, "loss": 1.0215, "step": 18268 }, { "epoch": 0.9988177003246198, "grad_norm": 2.7371509075164795, "learning_rate": 4.1465764419879037e-10, "loss": 1.0808, "step": 18269 }, { "epoch": 0.9988723731419785, "grad_norm": 3.9664299488067627, "learning_rate": 3.7938435423212627e-10, "loss": 1.0426, "step": 18270 }, { "epoch": 0.9989270459593371, "grad_norm": 2.090718984603882, "learning_rate": 3.456787582956089e-10, "loss": 1.0019, "step": 18271 }, { "epoch": 0.9989817187766957, "grad_norm": 2.446965456008911, "learning_rate": 3.135408574383991e-10, "loss": 0.9861, "step": 18272 }, { "epoch": 0.9990363915940543, "grad_norm": 2.2903943061828613, "learning_rate": 2.8297065267635094e-10, "loss": 1.0303, "step": 18273 }, { "epoch": 0.9990910644114129, "grad_norm": 3.048846960067749, "learning_rate": 2.5396814495870504e-10, "loss": 1.1642, "step": 18274 }, { "epoch": 0.9991457372287715, "grad_norm": 2.5878310203552246, "learning_rate": 2.265333352013954e-10, "loss": 0.934, "step": 18275 }, { "epoch": 0.9992004100461301, "grad_norm": 2.205627679824829, "learning_rate": 2.0066622425929383e-10, "loss": 1.0577, "step": 18276 }, { "epoch": 0.9992550828634889, "grad_norm": 2.9297595024108887, "learning_rate": 1.7636681295396528e-10, "loss": 0.9704, "step": 18277 }, { "epoch": 0.9993097556808475, "grad_norm": 3.1834769248962402, "learning_rate": 1.5363510203481035e-10, "loss": 0.841, "step": 18278 }, { "epoch": 0.9993644284982061, "grad_norm": 2.595243215560913, "learning_rate": 1.3247109222347398e-10, "loss": 0.894, "step": 18279 }, { "epoch": 0.9994191013155647, "grad_norm": 3.6711556911468506, "learning_rate": 1.1287478418053888e-10, "loss": 0.9822, "step": 18280 }, { "epoch": 0.9994737741329233, "grad_norm": 2.904005289077759, "learning_rate": 9.484617851662769e-11, "loss": 0.9974, "step": 18281 }, { "epoch": 0.9995284469502819, "grad_norm": 2.680284023284912, "learning_rate": 7.83852758035053e-11, "loss": 1.003, "step": 18282 }, { "epoch": 0.9995831197676405, "grad_norm": 2.7326130867004395, "learning_rate": 6.349207655187428e-11, "loss": 1.079, "step": 18283 }, { "epoch": 0.9996377925849992, "grad_norm": 3.526822090148926, "learning_rate": 5.0166581233579426e-11, "loss": 0.923, "step": 18284 }, { "epoch": 0.9996924654023578, "grad_norm": 3.211313486099243, "learning_rate": 3.840879025940325e-11, "loss": 1.1488, "step": 18285 }, { "epoch": 0.9997471382197164, "grad_norm": 2.7119498252868652, "learning_rate": 2.8218704006821583e-11, "loss": 0.8596, "step": 18286 }, { "epoch": 0.999801811037075, "grad_norm": 3.5004024505615234, "learning_rate": 1.959632279224799e-11, "loss": 0.8517, "step": 18287 }, { "epoch": 0.9998564838544336, "grad_norm": 2.669280529022217, "learning_rate": 1.2541646882135993e-11, "loss": 1.0809, "step": 18288 }, { "epoch": 0.9999111566717922, "grad_norm": 2.6650495529174805, "learning_rate": 7.054676498530199e-12, "loss": 1.2453, "step": 18289 }, { "epoch": 0.9999658294891509, "grad_norm": 2.9307446479797363, "learning_rate": 3.135411819066292e-12, "loss": 0.9442, "step": 18290 }, { "epoch": 1.0, "grad_norm": 3.796144485473633, "learning_rate": 7.838529603176881e-13, "loss": 1.1644, "step": 18291 }, { "epoch": 1.0, "step": 18291, "total_flos": 1.5010357981644058e+18, "train_loss": 1.0857669527257854, "train_runtime": 53386.6601, "train_samples_per_second": 10.963, "train_steps_per_second": 0.343 } ], "logging_steps": 1.0, "max_steps": 18291, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 2000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.5010357981644058e+18, "train_batch_size": 4, "trial_name": null, "trial_params": null }