| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9984496124031006, | |
| "eval_steps": 500, | |
| "global_step": 1449, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.020671834625323, | |
| "grad_norm": 19.961172103881836, | |
| "learning_rate": 6.896551724137932e-06, | |
| "loss": 1.4671, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.041343669250646, | |
| "grad_norm": 10.104804039001465, | |
| "learning_rate": 1.3793103448275863e-05, | |
| "loss": 1.2814, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06201550387596899, | |
| "grad_norm": 10.660629272460938, | |
| "learning_rate": 2.0689655172413793e-05, | |
| "loss": 1.0494, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.082687338501292, | |
| "grad_norm": 4.328464031219482, | |
| "learning_rate": 2.7586206896551727e-05, | |
| "loss": 0.8603, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10335917312661498, | |
| "grad_norm": 2.360297918319702, | |
| "learning_rate": 3.4482758620689657e-05, | |
| "loss": 0.7456, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12403100775193798, | |
| "grad_norm": 2.756227731704712, | |
| "learning_rate": 4.1379310344827587e-05, | |
| "loss": 0.6606, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.14470284237726097, | |
| "grad_norm": 2.7377092838287354, | |
| "learning_rate": 4.827586206896552e-05, | |
| "loss": 0.6343, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.165374677002584, | |
| "grad_norm": 2.682518243789673, | |
| "learning_rate": 5.517241379310345e-05, | |
| "loss": 0.5962, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.18604651162790697, | |
| "grad_norm": 2.2480661869049072, | |
| "learning_rate": 6.206896551724138e-05, | |
| "loss": 0.5689, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.20671834625322996, | |
| "grad_norm": 2.5809719562530518, | |
| "learning_rate": 6.896551724137931e-05, | |
| "loss": 0.5812, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.22739018087855298, | |
| "grad_norm": 1.933281660079956, | |
| "learning_rate": 7.586206896551724e-05, | |
| "loss": 0.5438, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.24806201550387597, | |
| "grad_norm": 2.1786251068115234, | |
| "learning_rate": 8.275862068965517e-05, | |
| "loss": 0.5379, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.268733850129199, | |
| "grad_norm": 1.6331806182861328, | |
| "learning_rate": 8.96551724137931e-05, | |
| "loss": 0.5383, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.28940568475452194, | |
| "grad_norm": 1.713693380355835, | |
| "learning_rate": 9.655172413793105e-05, | |
| "loss": 0.5359, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.31007751937984496, | |
| "grad_norm": 1.6057534217834473, | |
| "learning_rate": 9.999637240054163e-05, | |
| "loss": 0.5957, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.330749354005168, | |
| "grad_norm": 1.2600524425506592, | |
| "learning_rate": 9.996735476307291e-05, | |
| "loss": 0.5528, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.35142118863049093, | |
| "grad_norm": 1.258549451828003, | |
| "learning_rate": 9.990933632982306e-05, | |
| "loss": 0.5274, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.37209302325581395, | |
| "grad_norm": 1.1361678838729858, | |
| "learning_rate": 9.982235077439241e-05, | |
| "loss": 0.5363, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.39276485788113696, | |
| "grad_norm": 1.1429818868637085, | |
| "learning_rate": 9.970644858275008e-05, | |
| "loss": 0.5626, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4134366925064599, | |
| "grad_norm": 1.168615460395813, | |
| "learning_rate": 9.956169702393215e-05, | |
| "loss": 0.5331, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.43410852713178294, | |
| "grad_norm": 1.353784441947937, | |
| "learning_rate": 9.938818011099905e-05, | |
| "loss": 0.5232, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.45478036175710596, | |
| "grad_norm": 1.1773430109024048, | |
| "learning_rate": 9.918599855227486e-05, | |
| "loss": 0.536, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.4754521963824289, | |
| "grad_norm": 1.1550217866897583, | |
| "learning_rate": 9.895526969289671e-05, | |
| "loss": 0.5162, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.49612403100775193, | |
| "grad_norm": 1.0943946838378906, | |
| "learning_rate": 9.869612744670818e-05, | |
| "loss": 0.4939, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5167958656330749, | |
| "grad_norm": 1.0564571619033813, | |
| "learning_rate": 9.84087222185365e-05, | |
| "loss": 0.5053, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.537467700258398, | |
| "grad_norm": 0.9963967800140381, | |
| "learning_rate": 9.809322081689833e-05, | |
| "loss": 0.5277, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.5581395348837209, | |
| "grad_norm": 1.1690253019332886, | |
| "learning_rate": 9.774980635718494e-05, | |
| "loss": 0.5568, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.5788113695090439, | |
| "grad_norm": 1.0432251691818237, | |
| "learning_rate": 9.737867815538293e-05, | |
| "loss": 0.5567, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.599483204134367, | |
| "grad_norm": 1.033795714378357, | |
| "learning_rate": 9.698005161239236e-05, | |
| "loss": 0.5373, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6201550387596899, | |
| "grad_norm": 1.0568259954452515, | |
| "learning_rate": 9.655415808900914e-05, | |
| "loss": 0.528, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6408268733850129, | |
| "grad_norm": 1.0200306177139282, | |
| "learning_rate": 9.610124477164435e-05, | |
| "loss": 0.5364, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.661498708010336, | |
| "grad_norm": 1.0433367490768433, | |
| "learning_rate": 9.56215745288586e-05, | |
| "loss": 0.546, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.6821705426356589, | |
| "grad_norm": 0.936161458492279, | |
| "learning_rate": 9.51154257587944e-05, | |
| "loss": 0.5283, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.7028423772609819, | |
| "grad_norm": 0.8251316547393799, | |
| "learning_rate": 9.45830922275954e-05, | |
| "loss": 0.5165, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7235142118863049, | |
| "grad_norm": 0.9545398354530334, | |
| "learning_rate": 9.402488289890591e-05, | |
| "loss": 0.5344, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.7441860465116279, | |
| "grad_norm": 1.0172969102859497, | |
| "learning_rate": 9.344112175455013e-05, | |
| "loss": 0.5108, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.7648578811369509, | |
| "grad_norm": 0.9597331881523132, | |
| "learning_rate": 9.283214760649461e-05, | |
| "loss": 0.5082, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.7855297157622739, | |
| "grad_norm": 0.9407294988632202, | |
| "learning_rate": 9.219831390020366e-05, | |
| "loss": 0.5438, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.8062015503875969, | |
| "grad_norm": 0.8958045840263367, | |
| "learning_rate": 9.153998850950132e-05, | |
| "loss": 0.5383, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.8268733850129198, | |
| "grad_norm": 1.0094271898269653, | |
| "learning_rate": 9.08575535230594e-05, | |
| "loss": 0.4745, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.8475452196382429, | |
| "grad_norm": 0.9919396638870239, | |
| "learning_rate": 9.015140502263506e-05, | |
| "loss": 0.4849, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.8682170542635659, | |
| "grad_norm": 1.1863609552383423, | |
| "learning_rate": 8.942195285318704e-05, | |
| "loss": 0.5239, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.9280211925506592, | |
| "learning_rate": 8.866962038500379e-05, | |
| "loss": 0.4919, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.9095607235142119, | |
| "grad_norm": 1.0376496315002441, | |
| "learning_rate": 8.789484426798146e-05, | |
| "loss": 0.5155, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.9302325581395349, | |
| "grad_norm": 0.9633381962776184, | |
| "learning_rate": 8.709807417819465e-05, | |
| "loss": 0.5188, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.9509043927648578, | |
| "grad_norm": 1.0249930620193481, | |
| "learning_rate": 8.627977255690657e-05, | |
| "loss": 0.5031, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.9715762273901809, | |
| "grad_norm": 1.0092591047286987, | |
| "learning_rate": 8.544041434217068e-05, | |
| "loss": 0.513, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.9922480620155039, | |
| "grad_norm": 0.8698219060897827, | |
| "learning_rate": 8.458048669317896e-05, | |
| "loss": 0.5067, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.014470284237726, | |
| "grad_norm": 0.8564507365226746, | |
| "learning_rate": 8.370048870751733e-05, | |
| "loss": 0.4898, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.0351421188630492, | |
| "grad_norm": 1.9524496793746948, | |
| "learning_rate": 8.280093113149182e-05, | |
| "loss": 0.4215, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0558139534883721, | |
| "grad_norm": 1.0247145891189575, | |
| "learning_rate": 8.188233606369422e-05, | |
| "loss": 0.428, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.076485788113695, | |
| "grad_norm": 1.123751163482666, | |
| "learning_rate": 8.094523665197862e-05, | |
| "loss": 0.4318, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.097157622739018, | |
| "grad_norm": 1.0905773639678955, | |
| "learning_rate": 7.999017678402519e-05, | |
| "loss": 0.4303, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.117829457364341, | |
| "grad_norm": 0.9824921488761902, | |
| "learning_rate": 7.901771077167052e-05, | |
| "loss": 0.4068, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.138501291989664, | |
| "grad_norm": 0.9725044965744019, | |
| "learning_rate": 7.802840302918795e-05, | |
| "loss": 0.3728, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.1591731266149872, | |
| "grad_norm": 0.9440091848373413, | |
| "learning_rate": 7.702282774570435e-05, | |
| "loss": 0.4264, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.1798449612403101, | |
| "grad_norm": 1.0231075286865234, | |
| "learning_rate": 7.600156855194376e-05, | |
| "loss": 0.3708, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.200516795865633, | |
| "grad_norm": 0.9228759407997131, | |
| "learning_rate": 7.496521818149114e-05, | |
| "loss": 0.3771, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.221188630490956, | |
| "grad_norm": 0.9908185601234436, | |
| "learning_rate": 7.391437812677273e-05, | |
| "loss": 0.424, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.241860465116279, | |
| "grad_norm": 0.8130841255187988, | |
| "learning_rate": 7.284965828995309e-05, | |
| "loss": 0.4202, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.262532299741602, | |
| "grad_norm": 1.2041234970092773, | |
| "learning_rate": 7.177167662895087e-05, | |
| "loss": 0.3821, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.2832041343669252, | |
| "grad_norm": 0.9226158261299133, | |
| "learning_rate": 7.068105879877933e-05, | |
| "loss": 0.4288, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.3038759689922481, | |
| "grad_norm": 0.9127386808395386, | |
| "learning_rate": 6.957843778841937e-05, | |
| "loss": 0.4177, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.324547803617571, | |
| "grad_norm": 0.9465218186378479, | |
| "learning_rate": 6.84644535534359e-05, | |
| "loss": 0.4326, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.345219638242894, | |
| "grad_norm": 0.9808584451675415, | |
| "learning_rate": 6.733975264455097e-05, | |
| "loss": 0.391, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.365891472868217, | |
| "grad_norm": 0.8926200866699219, | |
| "learning_rate": 6.620498783238911e-05, | |
| "loss": 0.4072, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.3865633074935402, | |
| "grad_norm": 1.060142993927002, | |
| "learning_rate": 6.506081772861254e-05, | |
| "loss": 0.4062, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.407235142118863, | |
| "grad_norm": 0.931640625, | |
| "learning_rate": 6.390790640366635e-05, | |
| "loss": 0.4287, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.427906976744186, | |
| "grad_norm": 0.8396949172019958, | |
| "learning_rate": 6.27469230013555e-05, | |
| "loss": 0.3781, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.448578811369509, | |
| "grad_norm": 0.8786910176277161, | |
| "learning_rate": 6.157854135047707e-05, | |
| "loss": 0.4089, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.469250645994832, | |
| "grad_norm": 0.877200722694397, | |
| "learning_rate": 6.0403439573733666e-05, | |
| "loss": 0.4034, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.489922480620155, | |
| "grad_norm": 0.8826427459716797, | |
| "learning_rate": 5.9222299694154316e-05, | |
| "loss": 0.4237, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.510594315245478, | |
| "grad_norm": 1.0366460084915161, | |
| "learning_rate": 5.803580723925193e-05, | |
| "loss": 0.4131, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.5312661498708011, | |
| "grad_norm": 0.8167237639427185, | |
| "learning_rate": 5.6844650843146595e-05, | |
| "loss": 0.3821, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.551937984496124, | |
| "grad_norm": 0.8496309518814087, | |
| "learning_rate": 5.5649521846885876e-05, | |
| "loss": 0.3998, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.572609819121447, | |
| "grad_norm": 1.0631760358810425, | |
| "learning_rate": 5.445111389719408e-05, | |
| "loss": 0.4448, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.59328165374677, | |
| "grad_norm": 0.9399399757385254, | |
| "learning_rate": 5.3250122543883197e-05, | |
| "loss": 0.4061, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.613953488372093, | |
| "grad_norm": 0.9156986474990845, | |
| "learning_rate": 5.20472448361594e-05, | |
| "loss": 0.4181, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.6346253229974161, | |
| "grad_norm": 0.9186833500862122, | |
| "learning_rate": 5.084317891805928e-05, | |
| "loss": 0.3888, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.6552971576227389, | |
| "grad_norm": 1.0180436372756958, | |
| "learning_rate": 4.963862362325058e-05, | |
| "loss": 0.4265, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.675968992248062, | |
| "grad_norm": 0.9096766710281372, | |
| "learning_rate": 4.8434278069432834e-05, | |
| "loss": 0.3958, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.696640826873385, | |
| "grad_norm": 0.88401198387146, | |
| "learning_rate": 4.7230841252572906e-05, | |
| "loss": 0.3952, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.717312661498708, | |
| "grad_norm": 0.834771454334259, | |
| "learning_rate": 4.602901164121145e-05, | |
| "loss": 0.3905, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.7379844961240312, | |
| "grad_norm": 1.0104914903640747, | |
| "learning_rate": 4.482948677107533e-05, | |
| "loss": 0.3677, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.758656330749354, | |
| "grad_norm": 0.9692713618278503, | |
| "learning_rate": 4.363296284023139e-05, | |
| "loss": 0.4024, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.779328165374677, | |
| "grad_norm": 0.9530401229858398, | |
| "learning_rate": 4.24401343050168e-05, | |
| "loss": 0.3809, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 1.4324836730957031, | |
| "learning_rate": 4.125169347698009e-05, | |
| "loss": 0.4011, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.820671834625323, | |
| "grad_norm": 0.9663997888565063, | |
| "learning_rate": 4.006833012106707e-05, | |
| "loss": 0.3726, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.841343669250646, | |
| "grad_norm": 0.8397408127784729, | |
| "learning_rate": 3.8890731055284893e-05, | |
| "loss": 0.3845, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.862015503875969, | |
| "grad_norm": 0.9423091411590576, | |
| "learning_rate": 3.77195797520763e-05, | |
| "loss": 0.4097, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.882687338501292, | |
| "grad_norm": 0.9247391223907471, | |
| "learning_rate": 3.6555555941635865e-05, | |
| "loss": 0.3979, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.9033591731266148, | |
| "grad_norm": 0.9327929019927979, | |
| "learning_rate": 3.539933521739793e-05, | |
| "loss": 0.4075, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.924031007751938, | |
| "grad_norm": 0.93698650598526, | |
| "learning_rate": 3.425158864392576e-05, | |
| "loss": 0.3885, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.944702842377261, | |
| "grad_norm": 0.8598852753639221, | |
| "learning_rate": 3.31129823674291e-05, | |
| "loss": 0.402, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.965374677002584, | |
| "grad_norm": 0.8426728844642639, | |
| "learning_rate": 3.1984177229136285e-05, | |
| "loss": 0.3899, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.9860465116279071, | |
| "grad_norm": 0.8942709565162659, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.3789, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.0082687338501293, | |
| "grad_norm": 0.7830824255943298, | |
| "learning_rate": 2.9758584909177433e-05, | |
| "loss": 0.4181, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.028940568475452, | |
| "grad_norm": 0.9163928627967834, | |
| "learning_rate": 2.8663089449850243e-05, | |
| "loss": 0.3397, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.049612403100775, | |
| "grad_norm": 0.9074885845184326, | |
| "learning_rate": 2.7579977823695723e-05, | |
| "loss": 0.298, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.0702842377260984, | |
| "grad_norm": 0.9496545791625977, | |
| "learning_rate": 2.6509878663132514e-05, | |
| "loss": 0.3163, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.090956072351421, | |
| "grad_norm": 0.9921571016311646, | |
| "learning_rate": 2.5453413048211172e-05, | |
| "loss": 0.3213, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.1116279069767443, | |
| "grad_norm": 1.1148159503936768, | |
| "learning_rate": 2.4411194146142407e-05, | |
| "loss": 0.2921, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.132299741602067, | |
| "grad_norm": 1.0226593017578125, | |
| "learning_rate": 2.338382685541806e-05, | |
| "loss": 0.2943, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.15297157622739, | |
| "grad_norm": 0.955251932144165, | |
| "learning_rate": 2.2371907454731167e-05, | |
| "loss": 0.3286, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.173643410852713, | |
| "grad_norm": 1.0427072048187256, | |
| "learning_rate": 2.137602325689873e-05, | |
| "loss": 0.3214, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.194315245478036, | |
| "grad_norm": 1.0497926473617554, | |
| "learning_rate": 2.039675226798854e-05, | |
| "loss": 0.3143, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.2149870801033593, | |
| "grad_norm": 1.0081120729446411, | |
| "learning_rate": 1.9434662851847325e-05, | |
| "loss": 0.3213, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.235658914728682, | |
| "grad_norm": 0.9074374437332153, | |
| "learning_rate": 1.8490313400225294e-05, | |
| "loss": 0.3204, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.2563307493540052, | |
| "grad_norm": 0.9639903903007507, | |
| "learning_rate": 1.7564252008688514e-05, | |
| "loss": 0.3066, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.277002583979328, | |
| "grad_norm": 0.9500643610954285, | |
| "learning_rate": 1.6657016158506966e-05, | |
| "loss": 0.3079, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.297674418604651, | |
| "grad_norm": 0.9133275151252747, | |
| "learning_rate": 1.5769132404703274e-05, | |
| "loss": 0.3127, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.3183462532299743, | |
| "grad_norm": 0.9715905785560608, | |
| "learning_rate": 1.4901116070442772e-05, | |
| "loss": 0.3221, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.339018087855297, | |
| "grad_norm": 1.0215041637420654, | |
| "learning_rate": 1.4053470947942693e-05, | |
| "loss": 0.3112, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.3596899224806203, | |
| "grad_norm": 0.9813144207000732, | |
| "learning_rate": 1.3226689006073712e-05, | |
| "loss": 0.3053, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.380361757105943, | |
| "grad_norm": 0.9730923175811768, | |
| "learning_rate": 1.2421250104823684e-05, | |
| "loss": 0.3172, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.401033591731266, | |
| "grad_norm": 1.038800597190857, | |
| "learning_rate": 1.163762171678951e-05, | |
| "loss": 0.3085, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.4217054263565894, | |
| "grad_norm": 0.9317840933799744, | |
| "learning_rate": 1.0876258655858307e-05, | |
| "loss": 0.3281, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.442377260981912, | |
| "grad_norm": 1.0310304164886475, | |
| "learning_rate": 1.0137602813235824e-05, | |
| "loss": 0.3118, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.4630490956072353, | |
| "grad_norm": 0.9994140267372131, | |
| "learning_rate": 9.422082900975104e-06, | |
| "loss": 0.309, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.483720930232558, | |
| "grad_norm": 1.1645585298538208, | |
| "learning_rate": 8.730114203154144e-06, | |
| "loss": 0.3219, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.504392764857881, | |
| "grad_norm": 1.0404480695724487, | |
| "learning_rate": 8.062098334847184e-06, | |
| "loss": 0.3165, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.525064599483204, | |
| "grad_norm": 1.055424451828003, | |
| "learning_rate": 7.418423009029362e-06, | |
| "loss": 0.2978, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.545736434108527, | |
| "grad_norm": 0.9607129693031311, | |
| "learning_rate": 6.799461811550101e-06, | |
| "loss": 0.3369, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.5664082687338503, | |
| "grad_norm": 1.0298357009887695, | |
| "learning_rate": 6.205573984305857e-06, | |
| "loss": 0.3295, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.587080103359173, | |
| "grad_norm": 0.9973547458648682, | |
| "learning_rate": 5.6371042167378706e-06, | |
| "loss": 0.3166, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.6077519379844962, | |
| "grad_norm": 1.4321331977844238, | |
| "learning_rate": 5.09438244577628e-06, | |
| "loss": 0.339, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.628423772609819, | |
| "grad_norm": 0.9741699695587158, | |
| "learning_rate": 4.5777236643463786e-06, | |
| "loss": 0.3011, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.649095607235142, | |
| "grad_norm": 0.980993390083313, | |
| "learning_rate": 4.087427738548321e-06, | |
| "loss": 0.3072, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.669767441860465, | |
| "grad_norm": 1.0376126766204834, | |
| "learning_rate": 3.623779233616442e-06, | |
| "loss": 0.3159, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.690439276485788, | |
| "grad_norm": 1.0413364171981812, | |
| "learning_rate": 3.1870472487589843e-06, | |
| "loss": 0.2953, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.7111111111111112, | |
| "grad_norm": 0.9663779139518738, | |
| "learning_rate": 2.7774852609743886e-06, | |
| "loss": 0.3072, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.731782945736434, | |
| "grad_norm": 0.9956408739089966, | |
| "learning_rate": 2.39533097793444e-06, | |
| "loss": 0.2828, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 2.752454780361757, | |
| "grad_norm": 0.9878751039505005, | |
| "learning_rate": 2.0408062000200625e-06, | |
| "loss": 0.3278, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 2.7731266149870804, | |
| "grad_norm": 1.0932310819625854, | |
| "learning_rate": 1.714116691589457e-06, | |
| "loss": 0.3071, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 2.793798449612403, | |
| "grad_norm": 1.0455061197280884, | |
| "learning_rate": 1.4154520615535183e-06, | |
| "loss": 0.3256, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.814470284237726, | |
| "grad_norm": 1.0817687511444092, | |
| "learning_rate": 1.1449856533278625e-06, | |
| "loss": 0.3147, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 2.835142118863049, | |
| "grad_norm": 1.0755105018615723, | |
| "learning_rate": 9.028744442251102e-07, | |
| "loss": 0.3353, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 2.855813953488372, | |
| "grad_norm": 1.0853437185287476, | |
| "learning_rate": 6.892589543461392e-07, | |
| "loss": 0.3174, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 2.876485788113695, | |
| "grad_norm": 0.9791375398635864, | |
| "learning_rate": 5.042631650229058e-07, | |
| "loss": 0.3113, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 2.897157622739018, | |
| "grad_norm": 0.9765632748603821, | |
| "learning_rate": 3.4799444686031693e-07, | |
| "loss": 0.2972, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.9178294573643413, | |
| "grad_norm": 1.0426656007766724, | |
| "learning_rate": 2.2054349741888468e-07, | |
| "loss": 0.296, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 2.938501291989664, | |
| "grad_norm": 0.9949988722801208, | |
| "learning_rate": 1.219842885743394e-07, | |
| "loss": 0.2913, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 2.959173126614987, | |
| "grad_norm": 0.9954948425292969, | |
| "learning_rate": 5.237402358471144e-08, | |
| "loss": 0.3192, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 2.97984496124031, | |
| "grad_norm": 1.0401126146316528, | |
| "learning_rate": 1.1753103889883266e-08, | |
| "loss": 0.288, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 2.9984496124031006, | |
| "step": 1449, | |
| "total_flos": 2.170312406348071e+18, | |
| "train_loss": 0.43735031344464437, | |
| "train_runtime": 9561.9202, | |
| "train_samples_per_second": 2.428, | |
| "train_steps_per_second": 0.152 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1449, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.170312406348071e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |