{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.754084625052367, "eval_steps": 500, "global_step": 1800, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00041893590280687055, "grad_norm": 8.333969116210938, "learning_rate": 2e-05, "loss": 3.3261, "step": 1 }, { "epoch": 0.0008378718056137411, "grad_norm": 7.348582744598389, "learning_rate": 1.9998324256388776e-05, "loss": 3.2312, "step": 2 }, { "epoch": 0.0012568077084206116, "grad_norm": 3.1899449825286865, "learning_rate": 1.9996648512777547e-05, "loss": 2.9318, "step": 3 }, { "epoch": 0.0016757436112274822, "grad_norm": 2.177359104156494, "learning_rate": 1.9994972769166317e-05, "loss": 2.8876, "step": 4 }, { "epoch": 0.0020946795140343527, "grad_norm": 2.1708009243011475, "learning_rate": 1.999329702555509e-05, "loss": 3.068, "step": 5 }, { "epoch": 0.0025136154168412233, "grad_norm": 1.77362060546875, "learning_rate": 1.9991621281943865e-05, "loss": 2.6598, "step": 6 }, { "epoch": 0.002932551319648094, "grad_norm": 1.709831714630127, "learning_rate": 1.9989945538332636e-05, "loss": 2.767, "step": 7 }, { "epoch": 0.0033514872224549644, "grad_norm": 1.5493128299713135, "learning_rate": 1.998826979472141e-05, "loss": 2.7182, "step": 8 }, { "epoch": 0.003770423125261835, "grad_norm": 1.39557945728302, "learning_rate": 1.998659405111018e-05, "loss": 2.8695, "step": 9 }, { "epoch": 0.0041893590280687055, "grad_norm": 1.1357755661010742, "learning_rate": 1.9984918307498955e-05, "loss": 2.5497, "step": 10 }, { "epoch": 0.004608294930875576, "grad_norm": 1.0683544874191284, "learning_rate": 1.9983242563887726e-05, "loss": 2.7363, "step": 11 }, { "epoch": 0.005027230833682447, "grad_norm": 0.9199109673500061, "learning_rate": 1.99815668202765e-05, "loss": 2.4438, "step": 12 }, { "epoch": 0.005446166736489317, "grad_norm": 0.9708887338638306, "learning_rate": 1.997989107666527e-05, "loss": 2.6098, "step": 13 }, { "epoch": 0.005865102639296188, "grad_norm": 0.9026995301246643, "learning_rate": 1.9978215333054045e-05, "loss": 2.4444, "step": 14 }, { "epoch": 0.006284038542103058, "grad_norm": 1.2418183088302612, "learning_rate": 1.9976539589442816e-05, "loss": 2.5436, "step": 15 }, { "epoch": 0.006702974444909929, "grad_norm": 0.8761052489280701, "learning_rate": 1.997486384583159e-05, "loss": 2.3926, "step": 16 }, { "epoch": 0.007121910347716799, "grad_norm": 0.8849633932113647, "learning_rate": 1.997318810222036e-05, "loss": 2.5935, "step": 17 }, { "epoch": 0.00754084625052367, "grad_norm": 0.8368175029754639, "learning_rate": 1.9971512358609135e-05, "loss": 2.4684, "step": 18 }, { "epoch": 0.007959782153330541, "grad_norm": 0.697807788848877, "learning_rate": 1.9969836614997905e-05, "loss": 2.3537, "step": 19 }, { "epoch": 0.008378718056137411, "grad_norm": 0.7476556301116943, "learning_rate": 1.996816087138668e-05, "loss": 2.4659, "step": 20 }, { "epoch": 0.008797653958944282, "grad_norm": 0.7885666489601135, "learning_rate": 1.9966485127775454e-05, "loss": 2.4466, "step": 21 }, { "epoch": 0.009216589861751152, "grad_norm": 0.7271686792373657, "learning_rate": 1.9964809384164224e-05, "loss": 2.3659, "step": 22 }, { "epoch": 0.009635525764558023, "grad_norm": 0.7286465764045715, "learning_rate": 1.9963133640552995e-05, "loss": 2.4473, "step": 23 }, { "epoch": 0.010054461667364893, "grad_norm": 0.8572853207588196, "learning_rate": 1.996145789694177e-05, "loss": 2.3595, "step": 24 }, { "epoch": 0.010473397570171765, "grad_norm": 0.8283334374427795, "learning_rate": 1.9959782153330543e-05, "loss": 2.5291, "step": 25 }, { "epoch": 0.010892333472978634, "grad_norm": 0.6586313843727112, "learning_rate": 1.9958106409719314e-05, "loss": 2.3985, "step": 26 }, { "epoch": 0.011311269375785506, "grad_norm": 0.6430657505989075, "learning_rate": 1.9956430666108085e-05, "loss": 2.3578, "step": 27 }, { "epoch": 0.011730205278592375, "grad_norm": 0.6550448536872864, "learning_rate": 1.995475492249686e-05, "loss": 2.4077, "step": 28 }, { "epoch": 0.012149141181399247, "grad_norm": 0.7592840194702148, "learning_rate": 1.9953079178885633e-05, "loss": 2.5008, "step": 29 }, { "epoch": 0.012568077084206116, "grad_norm": 0.7858672738075256, "learning_rate": 1.9951403435274407e-05, "loss": 2.4674, "step": 30 }, { "epoch": 0.012987012987012988, "grad_norm": 0.6130352020263672, "learning_rate": 1.9949727691663178e-05, "loss": 2.3526, "step": 31 }, { "epoch": 0.013405948889819858, "grad_norm": 0.6684207320213318, "learning_rate": 1.994805194805195e-05, "loss": 2.3732, "step": 32 }, { "epoch": 0.013824884792626729, "grad_norm": 0.8275600671768188, "learning_rate": 1.9946376204440723e-05, "loss": 2.135, "step": 33 }, { "epoch": 0.014243820695433599, "grad_norm": 0.5858725309371948, "learning_rate": 1.9944700460829494e-05, "loss": 2.1368, "step": 34 }, { "epoch": 0.01466275659824047, "grad_norm": 0.7133444547653198, "learning_rate": 1.9943024717218268e-05, "loss": 2.304, "step": 35 }, { "epoch": 0.01508169250104734, "grad_norm": 0.5466803312301636, "learning_rate": 1.994134897360704e-05, "loss": 2.1682, "step": 36 }, { "epoch": 0.015500628403854211, "grad_norm": 0.5196086168289185, "learning_rate": 1.9939673229995813e-05, "loss": 2.1546, "step": 37 }, { "epoch": 0.015919564306661083, "grad_norm": 0.5088497400283813, "learning_rate": 1.9937997486384583e-05, "loss": 2.1018, "step": 38 }, { "epoch": 0.016338500209467952, "grad_norm": 0.6117899417877197, "learning_rate": 1.9936321742773358e-05, "loss": 2.2346, "step": 39 }, { "epoch": 0.016757436112274822, "grad_norm": 0.5710458159446716, "learning_rate": 1.993464599916213e-05, "loss": 2.2147, "step": 40 }, { "epoch": 0.01717637201508169, "grad_norm": 0.5152861475944519, "learning_rate": 1.9932970255550902e-05, "loss": 2.2716, "step": 41 }, { "epoch": 0.017595307917888565, "grad_norm": 0.6851192712783813, "learning_rate": 1.9931294511939673e-05, "loss": 2.3158, "step": 42 }, { "epoch": 0.018014243820695434, "grad_norm": 0.5485531687736511, "learning_rate": 1.9929618768328447e-05, "loss": 2.2679, "step": 43 }, { "epoch": 0.018433179723502304, "grad_norm": 0.48592010140419006, "learning_rate": 1.992794302471722e-05, "loss": 2.1303, "step": 44 }, { "epoch": 0.018852115626309174, "grad_norm": 0.5533665418624878, "learning_rate": 1.9926267281105992e-05, "loss": 2.1981, "step": 45 }, { "epoch": 0.019271051529116047, "grad_norm": 0.5932656526565552, "learning_rate": 1.9924591537494763e-05, "loss": 2.3737, "step": 46 }, { "epoch": 0.019689987431922917, "grad_norm": 0.5236673951148987, "learning_rate": 1.9922915793883537e-05, "loss": 2.2694, "step": 47 }, { "epoch": 0.020108923334729786, "grad_norm": 0.5357316732406616, "learning_rate": 1.992124005027231e-05, "loss": 2.2368, "step": 48 }, { "epoch": 0.020527859237536656, "grad_norm": 0.5500349998474121, "learning_rate": 1.9919564306661082e-05, "loss": 2.213, "step": 49 }, { "epoch": 0.02094679514034353, "grad_norm": 0.48040810227394104, "learning_rate": 1.9917888563049853e-05, "loss": 2.1892, "step": 50 }, { "epoch": 0.0213657310431504, "grad_norm": 0.5716186165809631, "learning_rate": 1.9916212819438627e-05, "loss": 2.2039, "step": 51 }, { "epoch": 0.02178466694595727, "grad_norm": 0.5564374923706055, "learning_rate": 1.99145370758274e-05, "loss": 2.1411, "step": 52 }, { "epoch": 0.022203602848764138, "grad_norm": 0.4996980130672455, "learning_rate": 1.9912861332216175e-05, "loss": 2.1521, "step": 53 }, { "epoch": 0.02262253875157101, "grad_norm": 0.5239240527153015, "learning_rate": 1.9911185588604946e-05, "loss": 2.0742, "step": 54 }, { "epoch": 0.02304147465437788, "grad_norm": 0.4403076767921448, "learning_rate": 1.9909509844993716e-05, "loss": 1.9841, "step": 55 }, { "epoch": 0.02346041055718475, "grad_norm": 0.5169032216072083, "learning_rate": 1.990783410138249e-05, "loss": 2.0327, "step": 56 }, { "epoch": 0.02387934645999162, "grad_norm": 0.4901898503303528, "learning_rate": 1.9906158357771265e-05, "loss": 2.0063, "step": 57 }, { "epoch": 0.024298282362798494, "grad_norm": 0.6581910252571106, "learning_rate": 1.9904482614160035e-05, "loss": 2.1385, "step": 58 }, { "epoch": 0.024717218265605363, "grad_norm": 0.4522070586681366, "learning_rate": 1.9902806870548806e-05, "loss": 1.9944, "step": 59 }, { "epoch": 0.025136154168412233, "grad_norm": 0.5315820574760437, "learning_rate": 1.990113112693758e-05, "loss": 2.1579, "step": 60 }, { "epoch": 0.025555090071219103, "grad_norm": 0.4661259353160858, "learning_rate": 1.9899455383326354e-05, "loss": 2.1193, "step": 61 }, { "epoch": 0.025974025974025976, "grad_norm": 0.4940222203731537, "learning_rate": 1.9897779639715125e-05, "loss": 2.0844, "step": 62 }, { "epoch": 0.026392961876832845, "grad_norm": 0.46520665287971497, "learning_rate": 1.98961038961039e-05, "loss": 1.9306, "step": 63 }, { "epoch": 0.026811897779639715, "grad_norm": 0.5645989179611206, "learning_rate": 1.989442815249267e-05, "loss": 2.1236, "step": 64 }, { "epoch": 0.027230833682446585, "grad_norm": 0.47880157828330994, "learning_rate": 1.989275240888144e-05, "loss": 2.0206, "step": 65 }, { "epoch": 0.027649769585253458, "grad_norm": 0.6371349692344666, "learning_rate": 1.9891076665270215e-05, "loss": 2.019, "step": 66 }, { "epoch": 0.028068705488060328, "grad_norm": 0.5742272734642029, "learning_rate": 1.988940092165899e-05, "loss": 2.0899, "step": 67 }, { "epoch": 0.028487641390867197, "grad_norm": 0.5579768419265747, "learning_rate": 1.988772517804776e-05, "loss": 2.081, "step": 68 }, { "epoch": 0.028906577293674067, "grad_norm": 0.5897182822227478, "learning_rate": 1.988604943443653e-05, "loss": 1.9601, "step": 69 }, { "epoch": 0.02932551319648094, "grad_norm": 0.46881428360939026, "learning_rate": 1.9884373690825305e-05, "loss": 1.9085, "step": 70 }, { "epoch": 0.02974444909928781, "grad_norm": 0.6095844507217407, "learning_rate": 1.988269794721408e-05, "loss": 1.9762, "step": 71 }, { "epoch": 0.03016338500209468, "grad_norm": 0.599513053894043, "learning_rate": 1.988102220360285e-05, "loss": 1.8723, "step": 72 }, { "epoch": 0.03058232090490155, "grad_norm": 0.585457980632782, "learning_rate": 1.987934645999162e-05, "loss": 1.9209, "step": 73 }, { "epoch": 0.031001256807708422, "grad_norm": 0.42224225401878357, "learning_rate": 1.9877670716380394e-05, "loss": 1.9186, "step": 74 }, { "epoch": 0.03142019271051529, "grad_norm": 0.4566991329193115, "learning_rate": 1.987599497276917e-05, "loss": 2.018, "step": 75 }, { "epoch": 0.031839128613322165, "grad_norm": 0.47718995809555054, "learning_rate": 1.9874319229157943e-05, "loss": 2.0119, "step": 76 }, { "epoch": 0.03225806451612903, "grad_norm": 0.4412285089492798, "learning_rate": 1.9872643485546713e-05, "loss": 1.9211, "step": 77 }, { "epoch": 0.032677000418935905, "grad_norm": 0.4711454212665558, "learning_rate": 1.9870967741935484e-05, "loss": 1.9051, "step": 78 }, { "epoch": 0.03309593632174277, "grad_norm": 0.4665948450565338, "learning_rate": 1.9869291998324258e-05, "loss": 1.9571, "step": 79 }, { "epoch": 0.033514872224549644, "grad_norm": 0.46011775732040405, "learning_rate": 1.9867616254713032e-05, "loss": 1.9599, "step": 80 }, { "epoch": 0.03393380812735652, "grad_norm": 0.46272069215774536, "learning_rate": 1.9865940511101803e-05, "loss": 1.9161, "step": 81 }, { "epoch": 0.03435274403016338, "grad_norm": 0.5554195046424866, "learning_rate": 1.9864264767490574e-05, "loss": 2.0202, "step": 82 }, { "epoch": 0.034771679932970256, "grad_norm": 0.5324104428291321, "learning_rate": 1.9862589023879348e-05, "loss": 1.9356, "step": 83 }, { "epoch": 0.03519061583577713, "grad_norm": 0.5279750823974609, "learning_rate": 1.9860913280268122e-05, "loss": 1.9511, "step": 84 }, { "epoch": 0.035609551738583996, "grad_norm": 0.5002080202102661, "learning_rate": 1.9859237536656893e-05, "loss": 1.9248, "step": 85 }, { "epoch": 0.03602848764139087, "grad_norm": 0.5625497102737427, "learning_rate": 1.9857561793045667e-05, "loss": 2.0023, "step": 86 }, { "epoch": 0.036447423544197735, "grad_norm": 0.6030247807502747, "learning_rate": 1.9855886049434438e-05, "loss": 1.893, "step": 87 }, { "epoch": 0.03686635944700461, "grad_norm": 0.4760509729385376, "learning_rate": 1.9854210305823212e-05, "loss": 1.8902, "step": 88 }, { "epoch": 0.03728529534981148, "grad_norm": 0.6618624925613403, "learning_rate": 1.9852534562211983e-05, "loss": 1.9173, "step": 89 }, { "epoch": 0.03770423125261835, "grad_norm": 0.47204822301864624, "learning_rate": 1.9850858818600757e-05, "loss": 1.9266, "step": 90 }, { "epoch": 0.03812316715542522, "grad_norm": 0.5421533584594727, "learning_rate": 1.9849183074989527e-05, "loss": 1.9796, "step": 91 }, { "epoch": 0.038542103058232094, "grad_norm": 0.48972201347351074, "learning_rate": 1.98475073313783e-05, "loss": 1.91, "step": 92 }, { "epoch": 0.03896103896103896, "grad_norm": 0.5566658973693848, "learning_rate": 1.9845831587767072e-05, "loss": 1.8992, "step": 93 }, { "epoch": 0.03937997486384583, "grad_norm": 0.4685937464237213, "learning_rate": 1.9844155844155846e-05, "loss": 1.9231, "step": 94 }, { "epoch": 0.0397989107666527, "grad_norm": 0.6744531393051147, "learning_rate": 1.9842480100544617e-05, "loss": 1.9109, "step": 95 }, { "epoch": 0.04021784666945957, "grad_norm": 0.6984325051307678, "learning_rate": 1.984080435693339e-05, "loss": 1.9566, "step": 96 }, { "epoch": 0.040636782572266446, "grad_norm": 0.6627328991889954, "learning_rate": 1.9839128613322162e-05, "loss": 1.9933, "step": 97 }, { "epoch": 0.04105571847507331, "grad_norm": 0.4586343765258789, "learning_rate": 1.9837452869710936e-05, "loss": 1.7939, "step": 98 }, { "epoch": 0.041474654377880185, "grad_norm": 0.6211162805557251, "learning_rate": 1.983577712609971e-05, "loss": 1.9164, "step": 99 }, { "epoch": 0.04189359028068706, "grad_norm": 0.9397639632225037, "learning_rate": 1.983410138248848e-05, "loss": 2.0262, "step": 100 }, { "epoch": 0.042312526183493925, "grad_norm": 0.7698065638542175, "learning_rate": 1.9832425638877252e-05, "loss": 1.8979, "step": 101 }, { "epoch": 0.0427314620863008, "grad_norm": 0.5800043940544128, "learning_rate": 1.9830749895266026e-05, "loss": 1.9483, "step": 102 }, { "epoch": 0.043150397989107664, "grad_norm": 0.7634892463684082, "learning_rate": 1.98290741516548e-05, "loss": 1.7777, "step": 103 }, { "epoch": 0.04356933389191454, "grad_norm": 0.5963580012321472, "learning_rate": 1.982739840804357e-05, "loss": 1.9406, "step": 104 }, { "epoch": 0.04398826979472141, "grad_norm": 0.6970496773719788, "learning_rate": 1.982572266443234e-05, "loss": 1.967, "step": 105 }, { "epoch": 0.044407205697528276, "grad_norm": 0.5826534032821655, "learning_rate": 1.9824046920821116e-05, "loss": 1.8577, "step": 106 }, { "epoch": 0.04482614160033515, "grad_norm": 0.60413658618927, "learning_rate": 1.982237117720989e-05, "loss": 1.9528, "step": 107 }, { "epoch": 0.04524507750314202, "grad_norm": 0.7267922759056091, "learning_rate": 1.982069543359866e-05, "loss": 1.7067, "step": 108 }, { "epoch": 0.04566401340594889, "grad_norm": 0.6376165747642517, "learning_rate": 1.9819019689987435e-05, "loss": 1.9888, "step": 109 }, { "epoch": 0.04608294930875576, "grad_norm": 0.5887031555175781, "learning_rate": 1.9817343946376205e-05, "loss": 1.7777, "step": 110 }, { "epoch": 0.04650188521156263, "grad_norm": 0.6548938155174255, "learning_rate": 1.981566820276498e-05, "loss": 1.9222, "step": 111 }, { "epoch": 0.0469208211143695, "grad_norm": 0.5757064819335938, "learning_rate": 1.981399245915375e-05, "loss": 1.844, "step": 112 }, { "epoch": 0.047339757017176375, "grad_norm": 0.7597166895866394, "learning_rate": 1.9812316715542524e-05, "loss": 1.8678, "step": 113 }, { "epoch": 0.04775869291998324, "grad_norm": 0.5536984801292419, "learning_rate": 1.9810640971931295e-05, "loss": 1.8502, "step": 114 }, { "epoch": 0.048177628822790114, "grad_norm": 0.5753149390220642, "learning_rate": 1.980896522832007e-05, "loss": 1.8613, "step": 115 }, { "epoch": 0.04859656472559699, "grad_norm": 0.6214611530303955, "learning_rate": 1.980728948470884e-05, "loss": 1.8803, "step": 116 }, { "epoch": 0.04901550062840385, "grad_norm": 0.5892764329910278, "learning_rate": 1.9805613741097614e-05, "loss": 1.8241, "step": 117 }, { "epoch": 0.049434436531210726, "grad_norm": 0.5623623132705688, "learning_rate": 1.9803937997486388e-05, "loss": 1.8584, "step": 118 }, { "epoch": 0.04985337243401759, "grad_norm": 0.5206480622291565, "learning_rate": 1.980226225387516e-05, "loss": 1.8058, "step": 119 }, { "epoch": 0.050272308336824466, "grad_norm": 0.7416813373565674, "learning_rate": 1.980058651026393e-05, "loss": 1.7422, "step": 120 }, { "epoch": 0.05069124423963134, "grad_norm": 0.6095878481864929, "learning_rate": 1.9798910766652704e-05, "loss": 1.7567, "step": 121 }, { "epoch": 0.051110180142438205, "grad_norm": 0.5830249786376953, "learning_rate": 1.9797235023041478e-05, "loss": 1.8099, "step": 122 }, { "epoch": 0.05152911604524508, "grad_norm": 0.7603867053985596, "learning_rate": 1.979555927943025e-05, "loss": 1.8074, "step": 123 }, { "epoch": 0.05194805194805195, "grad_norm": 0.607905387878418, "learning_rate": 1.979388353581902e-05, "loss": 1.8359, "step": 124 }, { "epoch": 0.05236698785085882, "grad_norm": 0.5446661710739136, "learning_rate": 1.9792207792207794e-05, "loss": 1.7291, "step": 125 }, { "epoch": 0.05278592375366569, "grad_norm": 0.5527285933494568, "learning_rate": 1.9790532048596568e-05, "loss": 1.7841, "step": 126 }, { "epoch": 0.05320485965647256, "grad_norm": 0.6565405130386353, "learning_rate": 1.978885630498534e-05, "loss": 1.9168, "step": 127 }, { "epoch": 0.05362379555927943, "grad_norm": 0.5959405899047852, "learning_rate": 1.978718056137411e-05, "loss": 1.8735, "step": 128 }, { "epoch": 0.0540427314620863, "grad_norm": 0.7685437202453613, "learning_rate": 1.9785504817762883e-05, "loss": 1.782, "step": 129 }, { "epoch": 0.05446166736489317, "grad_norm": 0.5747430324554443, "learning_rate": 1.9783829074151657e-05, "loss": 1.7831, "step": 130 }, { "epoch": 0.05488060326770004, "grad_norm": 0.7328975200653076, "learning_rate": 1.9782153330540428e-05, "loss": 1.7451, "step": 131 }, { "epoch": 0.055299539170506916, "grad_norm": 0.5662095546722412, "learning_rate": 1.9780477586929202e-05, "loss": 1.6731, "step": 132 }, { "epoch": 0.05571847507331378, "grad_norm": 0.6165090799331665, "learning_rate": 1.9778801843317973e-05, "loss": 1.7787, "step": 133 }, { "epoch": 0.056137410976120655, "grad_norm": 0.6399924755096436, "learning_rate": 1.9777126099706747e-05, "loss": 1.8697, "step": 134 }, { "epoch": 0.05655634687892752, "grad_norm": 0.6513495445251465, "learning_rate": 1.9775450356095518e-05, "loss": 1.7885, "step": 135 }, { "epoch": 0.056975282781734395, "grad_norm": 0.652104914188385, "learning_rate": 1.9773774612484292e-05, "loss": 1.8462, "step": 136 }, { "epoch": 0.05739421868454127, "grad_norm": 0.8418712615966797, "learning_rate": 1.9772098868873063e-05, "loss": 1.8771, "step": 137 }, { "epoch": 0.057813154587348134, "grad_norm": 0.6133163571357727, "learning_rate": 1.9770423125261837e-05, "loss": 1.7998, "step": 138 }, { "epoch": 0.05823209049015501, "grad_norm": 0.6718358993530273, "learning_rate": 1.9768747381650608e-05, "loss": 1.7633, "step": 139 }, { "epoch": 0.05865102639296188, "grad_norm": 0.6728368997573853, "learning_rate": 1.9767071638039382e-05, "loss": 1.8313, "step": 140 }, { "epoch": 0.059069962295768746, "grad_norm": 0.588307797908783, "learning_rate": 1.9765395894428156e-05, "loss": 1.7395, "step": 141 }, { "epoch": 0.05948889819857562, "grad_norm": 0.889776885509491, "learning_rate": 1.9763720150816927e-05, "loss": 1.7591, "step": 142 }, { "epoch": 0.059907834101382486, "grad_norm": 0.5996978878974915, "learning_rate": 1.9762044407205697e-05, "loss": 1.6881, "step": 143 }, { "epoch": 0.06032677000418936, "grad_norm": 0.6324535012245178, "learning_rate": 1.976036866359447e-05, "loss": 1.7142, "step": 144 }, { "epoch": 0.06074570590699623, "grad_norm": 0.6198902130126953, "learning_rate": 1.9758692919983246e-05, "loss": 1.6867, "step": 145 }, { "epoch": 0.0611646418098031, "grad_norm": 0.6651074886322021, "learning_rate": 1.9757017176372016e-05, "loss": 1.7773, "step": 146 }, { "epoch": 0.06158357771260997, "grad_norm": 0.6877864599227905, "learning_rate": 1.9755341432760787e-05, "loss": 1.792, "step": 147 }, { "epoch": 0.062002513615416845, "grad_norm": 0.5880079865455627, "learning_rate": 1.975366568914956e-05, "loss": 1.7761, "step": 148 }, { "epoch": 0.06242144951822371, "grad_norm": 0.6574519872665405, "learning_rate": 1.9751989945538335e-05, "loss": 1.7769, "step": 149 }, { "epoch": 0.06284038542103058, "grad_norm": 0.5385615825653076, "learning_rate": 1.9750314201927106e-05, "loss": 1.7226, "step": 150 }, { "epoch": 0.06325932132383745, "grad_norm": 0.6323086023330688, "learning_rate": 1.9748638458315877e-05, "loss": 1.7043, "step": 151 }, { "epoch": 0.06367825722664433, "grad_norm": 0.5224570035934448, "learning_rate": 1.974696271470465e-05, "loss": 1.7103, "step": 152 }, { "epoch": 0.0640971931294512, "grad_norm": 0.5448949933052063, "learning_rate": 1.9745286971093425e-05, "loss": 1.7691, "step": 153 }, { "epoch": 0.06451612903225806, "grad_norm": 0.47703322768211365, "learning_rate": 1.97436112274822e-05, "loss": 1.7107, "step": 154 }, { "epoch": 0.06493506493506493, "grad_norm": 0.555005669593811, "learning_rate": 1.974193548387097e-05, "loss": 1.7493, "step": 155 }, { "epoch": 0.06535400083787181, "grad_norm": 0.5083591938018799, "learning_rate": 1.974025974025974e-05, "loss": 1.621, "step": 156 }, { "epoch": 0.06577293674067868, "grad_norm": 0.5037218928337097, "learning_rate": 1.9738583996648515e-05, "loss": 1.6905, "step": 157 }, { "epoch": 0.06619187264348554, "grad_norm": 0.48570749163627625, "learning_rate": 1.973690825303729e-05, "loss": 1.73, "step": 158 }, { "epoch": 0.06661080854629242, "grad_norm": 0.5082443952560425, "learning_rate": 1.973523250942606e-05, "loss": 1.7107, "step": 159 }, { "epoch": 0.06702974444909929, "grad_norm": 0.5330659747123718, "learning_rate": 1.973355676581483e-05, "loss": 1.7756, "step": 160 }, { "epoch": 0.06744868035190615, "grad_norm": 0.6401243209838867, "learning_rate": 1.9731881022203605e-05, "loss": 1.7171, "step": 161 }, { "epoch": 0.06786761625471303, "grad_norm": 0.5555040836334229, "learning_rate": 1.9730205278592375e-05, "loss": 1.7117, "step": 162 }, { "epoch": 0.0682865521575199, "grad_norm": 0.5580366253852844, "learning_rate": 1.972852953498115e-05, "loss": 1.7173, "step": 163 }, { "epoch": 0.06870548806032677, "grad_norm": 0.6296005249023438, "learning_rate": 1.9726853791369924e-05, "loss": 1.7316, "step": 164 }, { "epoch": 0.06912442396313365, "grad_norm": 0.681302547454834, "learning_rate": 1.9725178047758694e-05, "loss": 1.7849, "step": 165 }, { "epoch": 0.06954335986594051, "grad_norm": 0.6220213770866394, "learning_rate": 1.9723502304147465e-05, "loss": 1.656, "step": 166 }, { "epoch": 0.06996229576874738, "grad_norm": 0.6640814542770386, "learning_rate": 1.972182656053624e-05, "loss": 1.8749, "step": 167 }, { "epoch": 0.07038123167155426, "grad_norm": 0.5521919131278992, "learning_rate": 1.9720150816925013e-05, "loss": 1.763, "step": 168 }, { "epoch": 0.07080016757436113, "grad_norm": 0.6188511848449707, "learning_rate": 1.9718475073313784e-05, "loss": 1.6431, "step": 169 }, { "epoch": 0.07121910347716799, "grad_norm": 0.5388275980949402, "learning_rate": 1.9716799329702555e-05, "loss": 1.7444, "step": 170 }, { "epoch": 0.07163803937997486, "grad_norm": 1.0150574445724487, "learning_rate": 1.971512358609133e-05, "loss": 1.6986, "step": 171 }, { "epoch": 0.07205697528278174, "grad_norm": 0.6714919805526733, "learning_rate": 1.9713447842480103e-05, "loss": 1.7461, "step": 172 }, { "epoch": 0.0724759111855886, "grad_norm": 0.6587640047073364, "learning_rate": 1.9711772098868874e-05, "loss": 1.6743, "step": 173 }, { "epoch": 0.07289484708839547, "grad_norm": 0.6181256175041199, "learning_rate": 1.9710096355257648e-05, "loss": 1.8552, "step": 174 }, { "epoch": 0.07331378299120235, "grad_norm": 0.5564039945602417, "learning_rate": 1.970842061164642e-05, "loss": 1.741, "step": 175 }, { "epoch": 0.07373271889400922, "grad_norm": 0.5421382188796997, "learning_rate": 1.9706744868035193e-05, "loss": 1.6919, "step": 176 }, { "epoch": 0.07415165479681608, "grad_norm": 0.6172086000442505, "learning_rate": 1.9705069124423967e-05, "loss": 1.6686, "step": 177 }, { "epoch": 0.07457059069962296, "grad_norm": 0.5004185438156128, "learning_rate": 1.9703393380812738e-05, "loss": 1.6309, "step": 178 }, { "epoch": 0.07498952660242983, "grad_norm": 0.5099078416824341, "learning_rate": 1.970171763720151e-05, "loss": 1.674, "step": 179 }, { "epoch": 0.0754084625052367, "grad_norm": 0.5554249882698059, "learning_rate": 1.9700041893590283e-05, "loss": 1.6227, "step": 180 }, { "epoch": 0.07582739840804358, "grad_norm": 0.6313985586166382, "learning_rate": 1.9698366149979057e-05, "loss": 1.7098, "step": 181 }, { "epoch": 0.07624633431085044, "grad_norm": 0.8186052441596985, "learning_rate": 1.9696690406367827e-05, "loss": 1.7933, "step": 182 }, { "epoch": 0.07666527021365731, "grad_norm": 0.5017969608306885, "learning_rate": 1.9695014662756598e-05, "loss": 1.6853, "step": 183 }, { "epoch": 0.07708420611646419, "grad_norm": 0.6917697787284851, "learning_rate": 1.9693338919145372e-05, "loss": 1.7031, "step": 184 }, { "epoch": 0.07750314201927105, "grad_norm": 0.5040557980537415, "learning_rate": 1.9691663175534146e-05, "loss": 1.6353, "step": 185 }, { "epoch": 0.07792207792207792, "grad_norm": 0.5733162760734558, "learning_rate": 1.9689987431922917e-05, "loss": 1.7278, "step": 186 }, { "epoch": 0.07834101382488479, "grad_norm": 0.7823026776313782, "learning_rate": 1.968831168831169e-05, "loss": 1.6954, "step": 187 }, { "epoch": 0.07875994972769167, "grad_norm": 0.5559296607971191, "learning_rate": 1.9686635944700462e-05, "loss": 1.7417, "step": 188 }, { "epoch": 0.07917888563049853, "grad_norm": 0.6399711966514587, "learning_rate": 1.9684960201089236e-05, "loss": 1.6529, "step": 189 }, { "epoch": 0.0795978215333054, "grad_norm": 0.6075267195701599, "learning_rate": 1.9683284457478007e-05, "loss": 1.687, "step": 190 }, { "epoch": 0.08001675743611228, "grad_norm": 0.5875303149223328, "learning_rate": 1.968160871386678e-05, "loss": 1.6569, "step": 191 }, { "epoch": 0.08043569333891915, "grad_norm": 0.6546170711517334, "learning_rate": 1.9679932970255552e-05, "loss": 1.6844, "step": 192 }, { "epoch": 0.08085462924172601, "grad_norm": 0.5778879523277283, "learning_rate": 1.9678257226644322e-05, "loss": 1.6705, "step": 193 }, { "epoch": 0.08127356514453289, "grad_norm": 0.5718396306037903, "learning_rate": 1.9676581483033097e-05, "loss": 1.6519, "step": 194 }, { "epoch": 0.08169250104733976, "grad_norm": 0.6596693992614746, "learning_rate": 1.967490573942187e-05, "loss": 1.6547, "step": 195 }, { "epoch": 0.08211143695014662, "grad_norm": 0.5057825446128845, "learning_rate": 1.9673229995810645e-05, "loss": 1.6214, "step": 196 }, { "epoch": 0.0825303728529535, "grad_norm": 0.6651629209518433, "learning_rate": 1.9671554252199416e-05, "loss": 1.6835, "step": 197 }, { "epoch": 0.08294930875576037, "grad_norm": 0.5056618452072144, "learning_rate": 1.9669878508588186e-05, "loss": 1.6368, "step": 198 }, { "epoch": 0.08336824465856724, "grad_norm": 0.4693203568458557, "learning_rate": 1.966820276497696e-05, "loss": 1.6322, "step": 199 }, { "epoch": 0.08378718056137412, "grad_norm": 0.5992833375930786, "learning_rate": 1.9666527021365735e-05, "loss": 1.7568, "step": 200 }, { "epoch": 0.08420611646418098, "grad_norm": 0.62791508436203, "learning_rate": 1.9664851277754505e-05, "loss": 1.6937, "step": 201 }, { "epoch": 0.08462505236698785, "grad_norm": 0.5130066275596619, "learning_rate": 1.9663175534143276e-05, "loss": 1.6236, "step": 202 }, { "epoch": 0.08504398826979472, "grad_norm": 0.5045161247253418, "learning_rate": 1.966149979053205e-05, "loss": 1.7386, "step": 203 }, { "epoch": 0.0854629241726016, "grad_norm": 0.6568188667297363, "learning_rate": 1.9659824046920824e-05, "loss": 1.6639, "step": 204 }, { "epoch": 0.08588186007540846, "grad_norm": 0.6545958518981934, "learning_rate": 1.9658148303309595e-05, "loss": 1.6593, "step": 205 }, { "epoch": 0.08630079597821533, "grad_norm": 0.5190823078155518, "learning_rate": 1.9656472559698366e-05, "loss": 1.6398, "step": 206 }, { "epoch": 0.08671973188102221, "grad_norm": 0.5478256344795227, "learning_rate": 1.965479681608714e-05, "loss": 1.5848, "step": 207 }, { "epoch": 0.08713866778382907, "grad_norm": 0.5818894505500793, "learning_rate": 1.9653121072475914e-05, "loss": 1.6046, "step": 208 }, { "epoch": 0.08755760368663594, "grad_norm": 0.6687189936637878, "learning_rate": 1.9651445328864685e-05, "loss": 1.6177, "step": 209 }, { "epoch": 0.08797653958944282, "grad_norm": 0.5873174071311951, "learning_rate": 1.964976958525346e-05, "loss": 1.659, "step": 210 }, { "epoch": 0.08839547549224969, "grad_norm": 0.5621105432510376, "learning_rate": 1.964809384164223e-05, "loss": 1.6739, "step": 211 }, { "epoch": 0.08881441139505655, "grad_norm": 0.7059792876243591, "learning_rate": 1.9646418098031004e-05, "loss": 1.6738, "step": 212 }, { "epoch": 0.08923334729786343, "grad_norm": 0.5294623970985413, "learning_rate": 1.9644742354419775e-05, "loss": 1.6419, "step": 213 }, { "epoch": 0.0896522832006703, "grad_norm": 0.7764983773231506, "learning_rate": 1.964306661080855e-05, "loss": 1.6793, "step": 214 }, { "epoch": 0.09007121910347717, "grad_norm": 0.628094494342804, "learning_rate": 1.964139086719732e-05, "loss": 1.676, "step": 215 }, { "epoch": 0.09049015500628405, "grad_norm": 0.5593112111091614, "learning_rate": 1.9639715123586094e-05, "loss": 1.7119, "step": 216 }, { "epoch": 0.09090909090909091, "grad_norm": 0.7385965585708618, "learning_rate": 1.9638039379974864e-05, "loss": 1.6039, "step": 217 }, { "epoch": 0.09132802681189778, "grad_norm": 0.5662972927093506, "learning_rate": 1.963636363636364e-05, "loss": 1.6255, "step": 218 }, { "epoch": 0.09174696271470464, "grad_norm": 0.7071956992149353, "learning_rate": 1.9634687892752413e-05, "loss": 1.6587, "step": 219 }, { "epoch": 0.09216589861751152, "grad_norm": 0.6986474990844727, "learning_rate": 1.9633012149141183e-05, "loss": 1.6266, "step": 220 }, { "epoch": 0.09258483452031839, "grad_norm": 0.6965208053588867, "learning_rate": 1.9631336405529954e-05, "loss": 1.6619, "step": 221 }, { "epoch": 0.09300377042312526, "grad_norm": 0.7024741768836975, "learning_rate": 1.9629660661918728e-05, "loss": 1.7327, "step": 222 }, { "epoch": 0.09342270632593214, "grad_norm": 0.5887707471847534, "learning_rate": 1.9627984918307502e-05, "loss": 1.6706, "step": 223 }, { "epoch": 0.093841642228739, "grad_norm": 0.8550237417221069, "learning_rate": 1.9626309174696273e-05, "loss": 1.5773, "step": 224 }, { "epoch": 0.09426057813154587, "grad_norm": 0.6820223331451416, "learning_rate": 1.9624633431085044e-05, "loss": 1.7496, "step": 225 }, { "epoch": 0.09467951403435275, "grad_norm": 0.7763844728469849, "learning_rate": 1.9622957687473818e-05, "loss": 1.6204, "step": 226 }, { "epoch": 0.09509844993715962, "grad_norm": 0.779120147228241, "learning_rate": 1.9621281943862592e-05, "loss": 1.617, "step": 227 }, { "epoch": 0.09551738583996648, "grad_norm": 0.7589849233627319, "learning_rate": 1.9619606200251363e-05, "loss": 1.5478, "step": 228 }, { "epoch": 0.09593632174277336, "grad_norm": 0.5152125954627991, "learning_rate": 1.9617930456640137e-05, "loss": 1.6749, "step": 229 }, { "epoch": 0.09635525764558023, "grad_norm": 0.7013604640960693, "learning_rate": 1.9616254713028908e-05, "loss": 1.5864, "step": 230 }, { "epoch": 0.0967741935483871, "grad_norm": 0.7294275760650635, "learning_rate": 1.9614578969417682e-05, "loss": 1.5845, "step": 231 }, { "epoch": 0.09719312945119397, "grad_norm": 0.5346665382385254, "learning_rate": 1.9612903225806452e-05, "loss": 1.643, "step": 232 }, { "epoch": 0.09761206535400084, "grad_norm": 0.953779935836792, "learning_rate": 1.9611227482195227e-05, "loss": 1.6152, "step": 233 }, { "epoch": 0.0980310012568077, "grad_norm": 0.6668707132339478, "learning_rate": 1.9609551738583997e-05, "loss": 1.6066, "step": 234 }, { "epoch": 0.09844993715961457, "grad_norm": 0.6693033576011658, "learning_rate": 1.960787599497277e-05, "loss": 1.6124, "step": 235 }, { "epoch": 0.09886887306242145, "grad_norm": 0.8081066608428955, "learning_rate": 1.9606200251361542e-05, "loss": 1.6351, "step": 236 }, { "epoch": 0.09928780896522832, "grad_norm": 0.7561270594596863, "learning_rate": 1.9604524507750316e-05, "loss": 1.6476, "step": 237 }, { "epoch": 0.09970674486803519, "grad_norm": 0.8342212438583374, "learning_rate": 1.9602848764139087e-05, "loss": 1.5573, "step": 238 }, { "epoch": 0.10012568077084207, "grad_norm": 0.8095865845680237, "learning_rate": 1.960117302052786e-05, "loss": 1.5594, "step": 239 }, { "epoch": 0.10054461667364893, "grad_norm": 0.8448402881622314, "learning_rate": 1.9599497276916632e-05, "loss": 1.6646, "step": 240 }, { "epoch": 0.1009635525764558, "grad_norm": 0.936273455619812, "learning_rate": 1.9597821533305406e-05, "loss": 1.5822, "step": 241 }, { "epoch": 0.10138248847926268, "grad_norm": 0.5605466365814209, "learning_rate": 1.959614578969418e-05, "loss": 1.616, "step": 242 }, { "epoch": 0.10180142438206954, "grad_norm": 1.0700498819351196, "learning_rate": 1.959447004608295e-05, "loss": 1.618, "step": 243 }, { "epoch": 0.10222036028487641, "grad_norm": 0.6166669726371765, "learning_rate": 1.959279430247172e-05, "loss": 1.5989, "step": 244 }, { "epoch": 0.10263929618768329, "grad_norm": 0.7001603841781616, "learning_rate": 1.9591118558860496e-05, "loss": 1.464, "step": 245 }, { "epoch": 0.10305823209049016, "grad_norm": 0.5694488883018494, "learning_rate": 1.958944281524927e-05, "loss": 1.5641, "step": 246 }, { "epoch": 0.10347716799329702, "grad_norm": 0.5658904314041138, "learning_rate": 1.958776707163804e-05, "loss": 1.5911, "step": 247 }, { "epoch": 0.1038961038961039, "grad_norm": 0.6600093245506287, "learning_rate": 1.958609132802681e-05, "loss": 1.6812, "step": 248 }, { "epoch": 0.10431503979891077, "grad_norm": 0.7548564672470093, "learning_rate": 1.9584415584415586e-05, "loss": 1.5563, "step": 249 }, { "epoch": 0.10473397570171764, "grad_norm": 0.6965343952178955, "learning_rate": 1.958273984080436e-05, "loss": 1.6126, "step": 250 }, { "epoch": 0.1051529116045245, "grad_norm": 0.57705157995224, "learning_rate": 1.958106409719313e-05, "loss": 1.6778, "step": 251 }, { "epoch": 0.10557184750733138, "grad_norm": 1.2478373050689697, "learning_rate": 1.9579388353581905e-05, "loss": 1.6654, "step": 252 }, { "epoch": 0.10599078341013825, "grad_norm": 0.586651623249054, "learning_rate": 1.9577712609970675e-05, "loss": 1.5895, "step": 253 }, { "epoch": 0.10640971931294511, "grad_norm": 0.6501399874687195, "learning_rate": 1.957603686635945e-05, "loss": 1.5991, "step": 254 }, { "epoch": 0.106828655215752, "grad_norm": 0.7814245223999023, "learning_rate": 1.9574361122748224e-05, "loss": 1.5765, "step": 255 }, { "epoch": 0.10724759111855886, "grad_norm": 0.691818356513977, "learning_rate": 1.9572685379136994e-05, "loss": 1.6663, "step": 256 }, { "epoch": 0.10766652702136573, "grad_norm": 0.9530359506607056, "learning_rate": 1.9571009635525765e-05, "loss": 1.6614, "step": 257 }, { "epoch": 0.1080854629241726, "grad_norm": 1.280455231666565, "learning_rate": 1.956933389191454e-05, "loss": 1.5998, "step": 258 }, { "epoch": 0.10850439882697947, "grad_norm": 0.6066200137138367, "learning_rate": 1.956765814830331e-05, "loss": 1.6352, "step": 259 }, { "epoch": 0.10892333472978634, "grad_norm": 0.6973633766174316, "learning_rate": 1.9565982404692084e-05, "loss": 1.619, "step": 260 }, { "epoch": 0.10934227063259322, "grad_norm": 0.857652485370636, "learning_rate": 1.9564306661080855e-05, "loss": 1.6507, "step": 261 }, { "epoch": 0.10976120653540009, "grad_norm": 0.5751752853393555, "learning_rate": 1.956263091746963e-05, "loss": 1.6866, "step": 262 }, { "epoch": 0.11018014243820695, "grad_norm": 0.899047315120697, "learning_rate": 1.95609551738584e-05, "loss": 1.6211, "step": 263 }, { "epoch": 0.11059907834101383, "grad_norm": 0.6887657046318054, "learning_rate": 1.9559279430247174e-05, "loss": 1.5289, "step": 264 }, { "epoch": 0.1110180142438207, "grad_norm": 0.6921897530555725, "learning_rate": 1.9557603686635948e-05, "loss": 1.6667, "step": 265 }, { "epoch": 0.11143695014662756, "grad_norm": 0.5706766843795776, "learning_rate": 1.955592794302472e-05, "loss": 1.6057, "step": 266 }, { "epoch": 0.11185588604943443, "grad_norm": 0.7291983962059021, "learning_rate": 1.955425219941349e-05, "loss": 1.5033, "step": 267 }, { "epoch": 0.11227482195224131, "grad_norm": 0.5996133089065552, "learning_rate": 1.9552576455802263e-05, "loss": 1.5232, "step": 268 }, { "epoch": 0.11269375785504818, "grad_norm": 0.6987999677658081, "learning_rate": 1.9550900712191038e-05, "loss": 1.5832, "step": 269 }, { "epoch": 0.11311269375785504, "grad_norm": 0.7466180920600891, "learning_rate": 1.954922496857981e-05, "loss": 1.6155, "step": 270 }, { "epoch": 0.11353162966066192, "grad_norm": 0.5365012884140015, "learning_rate": 1.954754922496858e-05, "loss": 1.4844, "step": 271 }, { "epoch": 0.11395056556346879, "grad_norm": 0.6302610635757446, "learning_rate": 1.9545873481357353e-05, "loss": 1.6401, "step": 272 }, { "epoch": 0.11436950146627566, "grad_norm": 0.7011299729347229, "learning_rate": 1.9544197737746127e-05, "loss": 1.5856, "step": 273 }, { "epoch": 0.11478843736908254, "grad_norm": 0.5213186740875244, "learning_rate": 1.95425219941349e-05, "loss": 1.6877, "step": 274 }, { "epoch": 0.1152073732718894, "grad_norm": 0.5973451137542725, "learning_rate": 1.9540846250523672e-05, "loss": 1.6255, "step": 275 }, { "epoch": 0.11562630917469627, "grad_norm": 0.8726099729537964, "learning_rate": 1.9539170506912443e-05, "loss": 1.6345, "step": 276 }, { "epoch": 0.11604524507750315, "grad_norm": 0.6559906005859375, "learning_rate": 1.9537494763301217e-05, "loss": 1.4426, "step": 277 }, { "epoch": 0.11646418098031001, "grad_norm": 1.2165895700454712, "learning_rate": 1.953581901968999e-05, "loss": 1.597, "step": 278 }, { "epoch": 0.11688311688311688, "grad_norm": 0.5331985354423523, "learning_rate": 1.9534143276078762e-05, "loss": 1.5959, "step": 279 }, { "epoch": 0.11730205278592376, "grad_norm": 0.7331112027168274, "learning_rate": 1.9532467532467533e-05, "loss": 1.6, "step": 280 }, { "epoch": 0.11772098868873063, "grad_norm": 0.6983991265296936, "learning_rate": 1.9530791788856307e-05, "loss": 1.6188, "step": 281 }, { "epoch": 0.11813992459153749, "grad_norm": 0.6612614393234253, "learning_rate": 1.952911604524508e-05, "loss": 1.579, "step": 282 }, { "epoch": 0.11855886049434436, "grad_norm": 0.6999834179878235, "learning_rate": 1.952744030163385e-05, "loss": 1.715, "step": 283 }, { "epoch": 0.11897779639715124, "grad_norm": 0.6970024108886719, "learning_rate": 1.9525764558022622e-05, "loss": 1.6406, "step": 284 }, { "epoch": 0.1193967322999581, "grad_norm": 0.5302523374557495, "learning_rate": 1.9524088814411397e-05, "loss": 1.6388, "step": 285 }, { "epoch": 0.11981566820276497, "grad_norm": 0.7106460332870483, "learning_rate": 1.952241307080017e-05, "loss": 1.5679, "step": 286 }, { "epoch": 0.12023460410557185, "grad_norm": 0.6428540945053101, "learning_rate": 1.952073732718894e-05, "loss": 1.5151, "step": 287 }, { "epoch": 0.12065354000837872, "grad_norm": 0.6660862565040588, "learning_rate": 1.9519061583577716e-05, "loss": 1.6999, "step": 288 }, { "epoch": 0.12107247591118558, "grad_norm": 0.6251623034477234, "learning_rate": 1.9517385839966486e-05, "loss": 1.5289, "step": 289 }, { "epoch": 0.12149141181399246, "grad_norm": 0.5240997672080994, "learning_rate": 1.9515710096355257e-05, "loss": 1.5991, "step": 290 }, { "epoch": 0.12191034771679933, "grad_norm": 0.47173094749450684, "learning_rate": 1.951403435274403e-05, "loss": 1.5734, "step": 291 }, { "epoch": 0.1223292836196062, "grad_norm": 0.775086522102356, "learning_rate": 1.9512358609132805e-05, "loss": 1.4597, "step": 292 }, { "epoch": 0.12274821952241308, "grad_norm": 0.622778594493866, "learning_rate": 1.9510682865521576e-05, "loss": 1.5872, "step": 293 }, { "epoch": 0.12316715542521994, "grad_norm": 0.5721079111099243, "learning_rate": 1.9509007121910347e-05, "loss": 1.5226, "step": 294 }, { "epoch": 0.12358609132802681, "grad_norm": 0.8591808676719666, "learning_rate": 1.950733137829912e-05, "loss": 1.6192, "step": 295 }, { "epoch": 0.12400502723083369, "grad_norm": 0.5390528440475464, "learning_rate": 1.9505655634687895e-05, "loss": 1.5228, "step": 296 }, { "epoch": 0.12442396313364056, "grad_norm": 0.6414217948913574, "learning_rate": 1.950397989107667e-05, "loss": 1.6464, "step": 297 }, { "epoch": 0.12484289903644742, "grad_norm": 0.9504109621047974, "learning_rate": 1.950230414746544e-05, "loss": 1.4574, "step": 298 }, { "epoch": 0.1252618349392543, "grad_norm": 0.7934843301773071, "learning_rate": 1.950062840385421e-05, "loss": 1.5825, "step": 299 }, { "epoch": 0.12568077084206117, "grad_norm": 1.2911075353622437, "learning_rate": 1.9498952660242985e-05, "loss": 1.5519, "step": 300 }, { "epoch": 0.12609970674486803, "grad_norm": 0.7778868079185486, "learning_rate": 1.949727691663176e-05, "loss": 1.569, "step": 301 }, { "epoch": 0.1265186426476749, "grad_norm": 0.669278621673584, "learning_rate": 1.949560117302053e-05, "loss": 1.6144, "step": 302 }, { "epoch": 0.12693757855048177, "grad_norm": 1.0039944648742676, "learning_rate": 1.94939254294093e-05, "loss": 1.5249, "step": 303 }, { "epoch": 0.12735651445328866, "grad_norm": 0.7724584937095642, "learning_rate": 1.9492249685798074e-05, "loss": 1.6277, "step": 304 }, { "epoch": 0.12777545035609553, "grad_norm": 0.759467601776123, "learning_rate": 1.949057394218685e-05, "loss": 1.5756, "step": 305 }, { "epoch": 0.1281943862589024, "grad_norm": 1.3089075088500977, "learning_rate": 1.948889819857562e-05, "loss": 1.5371, "step": 306 }, { "epoch": 0.12861332216170926, "grad_norm": 0.5424050688743591, "learning_rate": 1.9487222454964393e-05, "loss": 1.5824, "step": 307 }, { "epoch": 0.12903225806451613, "grad_norm": 0.7417402267456055, "learning_rate": 1.9485546711353164e-05, "loss": 1.5458, "step": 308 }, { "epoch": 0.129451193967323, "grad_norm": 0.6556446552276611, "learning_rate": 1.948387096774194e-05, "loss": 1.6494, "step": 309 }, { "epoch": 0.12987012987012986, "grad_norm": 0.9575488567352295, "learning_rate": 1.948219522413071e-05, "loss": 1.5509, "step": 310 }, { "epoch": 0.13028906577293675, "grad_norm": 0.8725043535232544, "learning_rate": 1.9480519480519483e-05, "loss": 1.5099, "step": 311 }, { "epoch": 0.13070800167574362, "grad_norm": 1.1596598625183105, "learning_rate": 1.9478843736908254e-05, "loss": 1.6001, "step": 312 }, { "epoch": 0.13112693757855048, "grad_norm": 0.986149251461029, "learning_rate": 1.9477167993297028e-05, "loss": 1.4582, "step": 313 }, { "epoch": 0.13154587348135735, "grad_norm": 0.6939131021499634, "learning_rate": 1.94754922496858e-05, "loss": 1.6263, "step": 314 }, { "epoch": 0.13196480938416422, "grad_norm": 0.664408802986145, "learning_rate": 1.9473816506074573e-05, "loss": 1.538, "step": 315 }, { "epoch": 0.13238374528697108, "grad_norm": 0.6826114058494568, "learning_rate": 1.9472140762463344e-05, "loss": 1.5806, "step": 316 }, { "epoch": 0.13280268118977798, "grad_norm": 0.6879693269729614, "learning_rate": 1.9470465018852118e-05, "loss": 1.5156, "step": 317 }, { "epoch": 0.13322161709258484, "grad_norm": 1.2276116609573364, "learning_rate": 1.946878927524089e-05, "loss": 1.4466, "step": 318 }, { "epoch": 0.1336405529953917, "grad_norm": 0.7346695065498352, "learning_rate": 1.9467113531629663e-05, "loss": 1.5769, "step": 319 }, { "epoch": 0.13405948889819858, "grad_norm": 0.795690655708313, "learning_rate": 1.9465437788018437e-05, "loss": 1.5348, "step": 320 }, { "epoch": 0.13447842480100544, "grad_norm": 0.8207523822784424, "learning_rate": 1.9463762044407208e-05, "loss": 1.5196, "step": 321 }, { "epoch": 0.1348973607038123, "grad_norm": 0.6205607056617737, "learning_rate": 1.9462086300795978e-05, "loss": 1.5508, "step": 322 }, { "epoch": 0.13531629660661917, "grad_norm": 0.7060804963111877, "learning_rate": 1.9460410557184752e-05, "loss": 1.547, "step": 323 }, { "epoch": 0.13573523250942607, "grad_norm": 0.6053579449653625, "learning_rate": 1.9458734813573527e-05, "loss": 1.5521, "step": 324 }, { "epoch": 0.13615416841223293, "grad_norm": 0.6387944221496582, "learning_rate": 1.9457059069962297e-05, "loss": 1.5785, "step": 325 }, { "epoch": 0.1365731043150398, "grad_norm": 0.7160474061965942, "learning_rate": 1.9455383326351068e-05, "loss": 1.5527, "step": 326 }, { "epoch": 0.13699204021784667, "grad_norm": 0.5747194290161133, "learning_rate": 1.9453707582739842e-05, "loss": 1.4228, "step": 327 }, { "epoch": 0.13741097612065353, "grad_norm": 0.7289405465126038, "learning_rate": 1.9452031839128616e-05, "loss": 1.5758, "step": 328 }, { "epoch": 0.1378299120234604, "grad_norm": 0.5292596817016602, "learning_rate": 1.9450356095517387e-05, "loss": 1.5287, "step": 329 }, { "epoch": 0.1382488479262673, "grad_norm": 0.7831090092658997, "learning_rate": 1.944868035190616e-05, "loss": 1.5584, "step": 330 }, { "epoch": 0.13866778382907416, "grad_norm": 0.6046620011329651, "learning_rate": 1.9447004608294932e-05, "loss": 1.5534, "step": 331 }, { "epoch": 0.13908671973188103, "grad_norm": 0.7165292501449585, "learning_rate": 1.9445328864683706e-05, "loss": 1.621, "step": 332 }, { "epoch": 0.1395056556346879, "grad_norm": 0.7406589388847351, "learning_rate": 1.9443653121072477e-05, "loss": 1.5954, "step": 333 }, { "epoch": 0.13992459153749476, "grad_norm": 0.5955418348312378, "learning_rate": 1.944197737746125e-05, "loss": 1.5457, "step": 334 }, { "epoch": 0.14034352744030162, "grad_norm": 0.5523016452789307, "learning_rate": 1.944030163385002e-05, "loss": 1.5131, "step": 335 }, { "epoch": 0.14076246334310852, "grad_norm": 0.7677832841873169, "learning_rate": 1.9438625890238796e-05, "loss": 1.5521, "step": 336 }, { "epoch": 0.14118139924591538, "grad_norm": 0.6301062107086182, "learning_rate": 1.9436950146627566e-05, "loss": 1.5836, "step": 337 }, { "epoch": 0.14160033514872225, "grad_norm": 0.6077446341514587, "learning_rate": 1.943527440301634e-05, "loss": 1.5108, "step": 338 }, { "epoch": 0.14201927105152912, "grad_norm": 0.6678585410118103, "learning_rate": 1.943359865940511e-05, "loss": 1.5488, "step": 339 }, { "epoch": 0.14243820695433598, "grad_norm": 0.7583240270614624, "learning_rate": 1.9431922915793885e-05, "loss": 1.551, "step": 340 }, { "epoch": 0.14285714285714285, "grad_norm": 0.5899871587753296, "learning_rate": 1.9430247172182656e-05, "loss": 1.5522, "step": 341 }, { "epoch": 0.14327607875994972, "grad_norm": 0.6008652448654175, "learning_rate": 1.942857142857143e-05, "loss": 1.5742, "step": 342 }, { "epoch": 0.1436950146627566, "grad_norm": 0.5442250967025757, "learning_rate": 1.9426895684960204e-05, "loss": 1.5352, "step": 343 }, { "epoch": 0.14411395056556348, "grad_norm": 0.5791664123535156, "learning_rate": 1.9425219941348975e-05, "loss": 1.5924, "step": 344 }, { "epoch": 0.14453288646837034, "grad_norm": 0.5690919160842896, "learning_rate": 1.9423544197737746e-05, "loss": 1.5219, "step": 345 }, { "epoch": 0.1449518223711772, "grad_norm": 0.6443383693695068, "learning_rate": 1.942186845412652e-05, "loss": 1.5994, "step": 346 }, { "epoch": 0.14537075827398407, "grad_norm": 0.5575938820838928, "learning_rate": 1.9420192710515294e-05, "loss": 1.5579, "step": 347 }, { "epoch": 0.14578969417679094, "grad_norm": 0.612278401851654, "learning_rate": 1.9418516966904065e-05, "loss": 1.6067, "step": 348 }, { "epoch": 0.14620863007959783, "grad_norm": 0.6119928956031799, "learning_rate": 1.9416841223292836e-05, "loss": 1.4636, "step": 349 }, { "epoch": 0.1466275659824047, "grad_norm": 0.568268895149231, "learning_rate": 1.941516547968161e-05, "loss": 1.4923, "step": 350 }, { "epoch": 0.14704650188521157, "grad_norm": 0.6106241345405579, "learning_rate": 1.9413489736070384e-05, "loss": 1.5735, "step": 351 }, { "epoch": 0.14746543778801843, "grad_norm": 0.5713450312614441, "learning_rate": 1.9411813992459158e-05, "loss": 1.4594, "step": 352 }, { "epoch": 0.1478843736908253, "grad_norm": 0.5222604274749756, "learning_rate": 1.941013824884793e-05, "loss": 1.4957, "step": 353 }, { "epoch": 0.14830330959363217, "grad_norm": 0.6617407202720642, "learning_rate": 1.94084625052367e-05, "loss": 1.3623, "step": 354 }, { "epoch": 0.14872224549643903, "grad_norm": 0.6270737648010254, "learning_rate": 1.9406786761625474e-05, "loss": 1.494, "step": 355 }, { "epoch": 0.14914118139924593, "grad_norm": 0.6663143634796143, "learning_rate": 1.9405111018014244e-05, "loss": 1.5093, "step": 356 }, { "epoch": 0.1495601173020528, "grad_norm": 0.5815137624740601, "learning_rate": 1.940343527440302e-05, "loss": 1.5392, "step": 357 }, { "epoch": 0.14997905320485966, "grad_norm": 0.5811892747879028, "learning_rate": 1.940175953079179e-05, "loss": 1.5553, "step": 358 }, { "epoch": 0.15039798910766652, "grad_norm": 0.5487301349639893, "learning_rate": 1.9400083787180563e-05, "loss": 1.6208, "step": 359 }, { "epoch": 0.1508169250104734, "grad_norm": 0.5299431681632996, "learning_rate": 1.9398408043569334e-05, "loss": 1.6097, "step": 360 }, { "epoch": 0.15123586091328026, "grad_norm": 0.6918801665306091, "learning_rate": 1.9396732299958108e-05, "loss": 1.5027, "step": 361 }, { "epoch": 0.15165479681608715, "grad_norm": 0.5945777893066406, "learning_rate": 1.939505655634688e-05, "loss": 1.6155, "step": 362 }, { "epoch": 0.15207373271889402, "grad_norm": 0.700545072555542, "learning_rate": 1.9393380812735653e-05, "loss": 1.6345, "step": 363 }, { "epoch": 0.15249266862170088, "grad_norm": 0.5498125553131104, "learning_rate": 1.9391705069124424e-05, "loss": 1.5087, "step": 364 }, { "epoch": 0.15291160452450775, "grad_norm": 0.5619140267372131, "learning_rate": 1.9390029325513198e-05, "loss": 1.4977, "step": 365 }, { "epoch": 0.15333054042731462, "grad_norm": 0.5968044400215149, "learning_rate": 1.9388353581901972e-05, "loss": 1.5017, "step": 366 }, { "epoch": 0.15374947633012148, "grad_norm": 0.6269423365592957, "learning_rate": 1.9386677838290743e-05, "loss": 1.5811, "step": 367 }, { "epoch": 0.15416841223292838, "grad_norm": 0.5672966241836548, "learning_rate": 1.9385002094679514e-05, "loss": 1.4781, "step": 368 }, { "epoch": 0.15458734813573524, "grad_norm": 0.8752624988555908, "learning_rate": 1.9383326351068288e-05, "loss": 1.4952, "step": 369 }, { "epoch": 0.1550062840385421, "grad_norm": 0.5117892622947693, "learning_rate": 1.9381650607457062e-05, "loss": 1.5436, "step": 370 }, { "epoch": 0.15542521994134897, "grad_norm": 0.7978183031082153, "learning_rate": 1.9379974863845833e-05, "loss": 1.4284, "step": 371 }, { "epoch": 0.15584415584415584, "grad_norm": 0.5909569263458252, "learning_rate": 1.9378299120234603e-05, "loss": 1.5057, "step": 372 }, { "epoch": 0.1562630917469627, "grad_norm": 0.6655667424201965, "learning_rate": 1.9376623376623377e-05, "loss": 1.4267, "step": 373 }, { "epoch": 0.15668202764976957, "grad_norm": 0.6063106656074524, "learning_rate": 1.937494763301215e-05, "loss": 1.5867, "step": 374 }, { "epoch": 0.15710096355257647, "grad_norm": 0.9726372361183167, "learning_rate": 1.9373271889400926e-05, "loss": 1.4887, "step": 375 }, { "epoch": 0.15751989945538333, "grad_norm": 0.711313784122467, "learning_rate": 1.9371596145789696e-05, "loss": 1.5464, "step": 376 }, { "epoch": 0.1579388353581902, "grad_norm": 0.6071950197219849, "learning_rate": 1.9369920402178467e-05, "loss": 1.4917, "step": 377 }, { "epoch": 0.15835777126099707, "grad_norm": 0.7539801597595215, "learning_rate": 1.936824465856724e-05, "loss": 1.4267, "step": 378 }, { "epoch": 0.15877670716380393, "grad_norm": 0.5340871810913086, "learning_rate": 1.9366568914956015e-05, "loss": 1.4227, "step": 379 }, { "epoch": 0.1591956430666108, "grad_norm": 0.7538002133369446, "learning_rate": 1.9364893171344786e-05, "loss": 1.5565, "step": 380 }, { "epoch": 0.1596145789694177, "grad_norm": 0.6404510736465454, "learning_rate": 1.9363217427733557e-05, "loss": 1.5314, "step": 381 }, { "epoch": 0.16003351487222456, "grad_norm": 0.6506287455558777, "learning_rate": 1.936154168412233e-05, "loss": 1.5931, "step": 382 }, { "epoch": 0.16045245077503142, "grad_norm": 0.6741127967834473, "learning_rate": 1.9359865940511105e-05, "loss": 1.5172, "step": 383 }, { "epoch": 0.1608713866778383, "grad_norm": 0.6476618647575378, "learning_rate": 1.9358190196899876e-05, "loss": 1.5038, "step": 384 }, { "epoch": 0.16129032258064516, "grad_norm": 0.7657164931297302, "learning_rate": 1.935651445328865e-05, "loss": 1.461, "step": 385 }, { "epoch": 0.16170925848345202, "grad_norm": 0.49177902936935425, "learning_rate": 1.935483870967742e-05, "loss": 1.4751, "step": 386 }, { "epoch": 0.1621281943862589, "grad_norm": 1.3233708143234253, "learning_rate": 1.935316296606619e-05, "loss": 1.4353, "step": 387 }, { "epoch": 0.16254713028906578, "grad_norm": 0.9667218923568726, "learning_rate": 1.9351487222454966e-05, "loss": 1.4472, "step": 388 }, { "epoch": 0.16296606619187265, "grad_norm": 0.6916482448577881, "learning_rate": 1.934981147884374e-05, "loss": 1.5265, "step": 389 }, { "epoch": 0.16338500209467952, "grad_norm": 0.870297372341156, "learning_rate": 1.934813573523251e-05, "loss": 1.5272, "step": 390 }, { "epoch": 0.16380393799748638, "grad_norm": 0.48826926946640015, "learning_rate": 1.934645999162128e-05, "loss": 1.4762, "step": 391 }, { "epoch": 0.16422287390029325, "grad_norm": 0.8552863597869873, "learning_rate": 1.9344784248010055e-05, "loss": 1.4508, "step": 392 }, { "epoch": 0.16464180980310011, "grad_norm": 0.626533567905426, "learning_rate": 1.934310850439883e-05, "loss": 1.4639, "step": 393 }, { "epoch": 0.165060745705907, "grad_norm": 0.6926416158676147, "learning_rate": 1.93414327607876e-05, "loss": 1.5507, "step": 394 }, { "epoch": 0.16547968160871387, "grad_norm": 0.613665759563446, "learning_rate": 1.933975701717637e-05, "loss": 1.5496, "step": 395 }, { "epoch": 0.16589861751152074, "grad_norm": 0.7060792446136475, "learning_rate": 1.9338081273565145e-05, "loss": 1.4823, "step": 396 }, { "epoch": 0.1663175534143276, "grad_norm": 0.6209156513214111, "learning_rate": 1.933640552995392e-05, "loss": 1.5661, "step": 397 }, { "epoch": 0.16673648931713447, "grad_norm": 0.7241356372833252, "learning_rate": 1.9334729786342693e-05, "loss": 1.5442, "step": 398 }, { "epoch": 0.16715542521994134, "grad_norm": 0.5998069643974304, "learning_rate": 1.9333054042731464e-05, "loss": 1.5247, "step": 399 }, { "epoch": 0.16757436112274823, "grad_norm": 0.5730302929878235, "learning_rate": 1.9331378299120235e-05, "loss": 1.5973, "step": 400 }, { "epoch": 0.1679932970255551, "grad_norm": 0.649454653263092, "learning_rate": 1.932970255550901e-05, "loss": 1.5839, "step": 401 }, { "epoch": 0.16841223292836197, "grad_norm": 0.5908178687095642, "learning_rate": 1.9328026811897783e-05, "loss": 1.4055, "step": 402 }, { "epoch": 0.16883116883116883, "grad_norm": 0.4675125181674957, "learning_rate": 1.9326351068286554e-05, "loss": 1.5132, "step": 403 }, { "epoch": 0.1692501047339757, "grad_norm": 0.738477885723114, "learning_rate": 1.9324675324675325e-05, "loss": 1.3856, "step": 404 }, { "epoch": 0.16966904063678256, "grad_norm": 0.5623185634613037, "learning_rate": 1.93229995810641e-05, "loss": 1.5222, "step": 405 }, { "epoch": 0.17008797653958943, "grad_norm": 0.6933448314666748, "learning_rate": 1.9321323837452873e-05, "loss": 1.6141, "step": 406 }, { "epoch": 0.17050691244239632, "grad_norm": 0.6374297142028809, "learning_rate": 1.9319648093841644e-05, "loss": 1.5482, "step": 407 }, { "epoch": 0.1709258483452032, "grad_norm": 0.692150354385376, "learning_rate": 1.9317972350230418e-05, "loss": 1.4039, "step": 408 }, { "epoch": 0.17134478424801006, "grad_norm": 0.5226042866706848, "learning_rate": 1.931629660661919e-05, "loss": 1.4807, "step": 409 }, { "epoch": 0.17176372015081692, "grad_norm": 0.602898895740509, "learning_rate": 1.9314620863007963e-05, "loss": 1.4713, "step": 410 }, { "epoch": 0.1721826560536238, "grad_norm": 0.6459433436393738, "learning_rate": 1.9312945119396733e-05, "loss": 1.4061, "step": 411 }, { "epoch": 0.17260159195643066, "grad_norm": 0.6216537356376648, "learning_rate": 1.9311269375785507e-05, "loss": 1.4756, "step": 412 }, { "epoch": 0.17302052785923755, "grad_norm": 0.5865094065666199, "learning_rate": 1.9309593632174278e-05, "loss": 1.5048, "step": 413 }, { "epoch": 0.17343946376204442, "grad_norm": 0.689116895198822, "learning_rate": 1.9307917888563052e-05, "loss": 1.5203, "step": 414 }, { "epoch": 0.17385839966485128, "grad_norm": 0.5802826285362244, "learning_rate": 1.9306242144951823e-05, "loss": 1.4162, "step": 415 }, { "epoch": 0.17427733556765815, "grad_norm": 0.6490867733955383, "learning_rate": 1.9304566401340597e-05, "loss": 1.4837, "step": 416 }, { "epoch": 0.17469627147046501, "grad_norm": 0.538263738155365, "learning_rate": 1.9302890657729368e-05, "loss": 1.4829, "step": 417 }, { "epoch": 0.17511520737327188, "grad_norm": 0.5698223114013672, "learning_rate": 1.9301214914118142e-05, "loss": 1.5414, "step": 418 }, { "epoch": 0.17553414327607875, "grad_norm": 0.5576086640357971, "learning_rate": 1.9299539170506913e-05, "loss": 1.5554, "step": 419 }, { "epoch": 0.17595307917888564, "grad_norm": 0.5333095192909241, "learning_rate": 1.9297863426895687e-05, "loss": 1.5389, "step": 420 }, { "epoch": 0.1763720150816925, "grad_norm": 0.6559884548187256, "learning_rate": 1.929618768328446e-05, "loss": 1.4234, "step": 421 }, { "epoch": 0.17679095098449937, "grad_norm": 0.5460498332977295, "learning_rate": 1.9294511939673232e-05, "loss": 1.39, "step": 422 }, { "epoch": 0.17720988688730624, "grad_norm": 0.636465311050415, "learning_rate": 1.9292836196062003e-05, "loss": 1.5061, "step": 423 }, { "epoch": 0.1776288227901131, "grad_norm": 1.0990898609161377, "learning_rate": 1.9291160452450777e-05, "loss": 1.5252, "step": 424 }, { "epoch": 0.17804775869291997, "grad_norm": 0.7239777445793152, "learning_rate": 1.928948470883955e-05, "loss": 1.6089, "step": 425 }, { "epoch": 0.17846669459572687, "grad_norm": 0.5494760870933533, "learning_rate": 1.928780896522832e-05, "loss": 1.5254, "step": 426 }, { "epoch": 0.17888563049853373, "grad_norm": 0.8444346189498901, "learning_rate": 1.9286133221617092e-05, "loss": 1.5971, "step": 427 }, { "epoch": 0.1793045664013406, "grad_norm": 0.6326781511306763, "learning_rate": 1.9284457478005866e-05, "loss": 1.6235, "step": 428 }, { "epoch": 0.17972350230414746, "grad_norm": 1.274570107460022, "learning_rate": 1.928278173439464e-05, "loss": 1.3773, "step": 429 }, { "epoch": 0.18014243820695433, "grad_norm": 0.8181143999099731, "learning_rate": 1.928110599078341e-05, "loss": 1.5252, "step": 430 }, { "epoch": 0.1805613741097612, "grad_norm": 1.0652360916137695, "learning_rate": 1.9279430247172185e-05, "loss": 1.4825, "step": 431 }, { "epoch": 0.1809803100125681, "grad_norm": 0.8766518831253052, "learning_rate": 1.9277754503560956e-05, "loss": 1.5517, "step": 432 }, { "epoch": 0.18139924591537496, "grad_norm": 0.730766236782074, "learning_rate": 1.927607875994973e-05, "loss": 1.4122, "step": 433 }, { "epoch": 0.18181818181818182, "grad_norm": 0.8081750869750977, "learning_rate": 1.92744030163385e-05, "loss": 1.4633, "step": 434 }, { "epoch": 0.1822371177209887, "grad_norm": 0.5756118297576904, "learning_rate": 1.9272727272727275e-05, "loss": 1.5168, "step": 435 }, { "epoch": 0.18265605362379556, "grad_norm": 0.7646397948265076, "learning_rate": 1.9271051529116046e-05, "loss": 1.3793, "step": 436 }, { "epoch": 0.18307498952660242, "grad_norm": 0.5722802877426147, "learning_rate": 1.926937578550482e-05, "loss": 1.536, "step": 437 }, { "epoch": 0.1834939254294093, "grad_norm": 0.6689785718917847, "learning_rate": 1.926770004189359e-05, "loss": 1.5591, "step": 438 }, { "epoch": 0.18391286133221618, "grad_norm": 0.6856290102005005, "learning_rate": 1.9266024298282365e-05, "loss": 1.4544, "step": 439 }, { "epoch": 0.18433179723502305, "grad_norm": 0.6789899468421936, "learning_rate": 1.9264348554671136e-05, "loss": 1.4653, "step": 440 }, { "epoch": 0.18475073313782991, "grad_norm": 0.7284293174743652, "learning_rate": 1.926267281105991e-05, "loss": 1.5527, "step": 441 }, { "epoch": 0.18516966904063678, "grad_norm": 0.7645947337150574, "learning_rate": 1.926099706744868e-05, "loss": 1.5051, "step": 442 }, { "epoch": 0.18558860494344365, "grad_norm": 0.719478964805603, "learning_rate": 1.9259321323837455e-05, "loss": 1.5189, "step": 443 }, { "epoch": 0.1860075408462505, "grad_norm": 0.695095419883728, "learning_rate": 1.925764558022623e-05, "loss": 1.5547, "step": 444 }, { "epoch": 0.1864264767490574, "grad_norm": 0.8511472344398499, "learning_rate": 1.9255969836615e-05, "loss": 1.5407, "step": 445 }, { "epoch": 0.18684541265186427, "grad_norm": 0.8481591939926147, "learning_rate": 1.925429409300377e-05, "loss": 1.4753, "step": 446 }, { "epoch": 0.18726434855467114, "grad_norm": 0.5671373009681702, "learning_rate": 1.9252618349392544e-05, "loss": 1.6334, "step": 447 }, { "epoch": 0.187683284457478, "grad_norm": 0.9575358629226685, "learning_rate": 1.925094260578132e-05, "loss": 1.4334, "step": 448 }, { "epoch": 0.18810222036028487, "grad_norm": 0.7267637252807617, "learning_rate": 1.924926686217009e-05, "loss": 1.369, "step": 449 }, { "epoch": 0.18852115626309174, "grad_norm": 0.9400660991668701, "learning_rate": 1.924759111855886e-05, "loss": 1.4424, "step": 450 }, { "epoch": 0.1889400921658986, "grad_norm": 0.6154212951660156, "learning_rate": 1.9245915374947634e-05, "loss": 1.5379, "step": 451 }, { "epoch": 0.1893590280687055, "grad_norm": 0.992761492729187, "learning_rate": 1.9244239631336408e-05, "loss": 1.4291, "step": 452 }, { "epoch": 0.18977796397151236, "grad_norm": 0.8219314217567444, "learning_rate": 1.924256388772518e-05, "loss": 1.4851, "step": 453 }, { "epoch": 0.19019689987431923, "grad_norm": 0.6872371435165405, "learning_rate": 1.9240888144113953e-05, "loss": 1.4687, "step": 454 }, { "epoch": 0.1906158357771261, "grad_norm": 0.7827102541923523, "learning_rate": 1.9239212400502724e-05, "loss": 1.4223, "step": 455 }, { "epoch": 0.19103477167993296, "grad_norm": 0.6476536989212036, "learning_rate": 1.9237536656891498e-05, "loss": 1.4416, "step": 456 }, { "epoch": 0.19145370758273983, "grad_norm": 0.8523492813110352, "learning_rate": 1.923586091328027e-05, "loss": 1.4081, "step": 457 }, { "epoch": 0.19187264348554672, "grad_norm": 0.7393168807029724, "learning_rate": 1.9234185169669043e-05, "loss": 1.4165, "step": 458 }, { "epoch": 0.1922915793883536, "grad_norm": 0.5783189535140991, "learning_rate": 1.9232509426057814e-05, "loss": 1.5124, "step": 459 }, { "epoch": 0.19271051529116046, "grad_norm": 0.5648137927055359, "learning_rate": 1.9230833682446588e-05, "loss": 1.4118, "step": 460 }, { "epoch": 0.19312945119396732, "grad_norm": 0.6089081168174744, "learning_rate": 1.922915793883536e-05, "loss": 1.5284, "step": 461 }, { "epoch": 0.1935483870967742, "grad_norm": 0.4999605417251587, "learning_rate": 1.9227482195224133e-05, "loss": 1.5311, "step": 462 }, { "epoch": 0.19396732299958105, "grad_norm": 0.5938348174095154, "learning_rate": 1.9225806451612907e-05, "loss": 1.4788, "step": 463 }, { "epoch": 0.19438625890238795, "grad_norm": 0.547335684299469, "learning_rate": 1.9224130708001677e-05, "loss": 1.4408, "step": 464 }, { "epoch": 0.19480519480519481, "grad_norm": 0.6379075050354004, "learning_rate": 1.9222454964390448e-05, "loss": 1.5705, "step": 465 }, { "epoch": 0.19522413070800168, "grad_norm": 0.5942078828811646, "learning_rate": 1.9220779220779222e-05, "loss": 1.4643, "step": 466 }, { "epoch": 0.19564306661080855, "grad_norm": 0.5671261548995972, "learning_rate": 1.9219103477167996e-05, "loss": 1.5048, "step": 467 }, { "epoch": 0.1960620025136154, "grad_norm": 0.5360516905784607, "learning_rate": 1.9217427733556767e-05, "loss": 1.4651, "step": 468 }, { "epoch": 0.19648093841642228, "grad_norm": 0.6140695810317993, "learning_rate": 1.9215751989945538e-05, "loss": 1.4735, "step": 469 }, { "epoch": 0.19689987431922915, "grad_norm": 0.573509931564331, "learning_rate": 1.9214076246334312e-05, "loss": 1.459, "step": 470 }, { "epoch": 0.19731881022203604, "grad_norm": 0.6246591210365295, "learning_rate": 1.9212400502723086e-05, "loss": 1.4701, "step": 471 }, { "epoch": 0.1977377461248429, "grad_norm": 0.5583751797676086, "learning_rate": 1.9210724759111857e-05, "loss": 1.6073, "step": 472 }, { "epoch": 0.19815668202764977, "grad_norm": 0.7271811962127686, "learning_rate": 1.9209049015500628e-05, "loss": 1.4531, "step": 473 }, { "epoch": 0.19857561793045664, "grad_norm": 0.7514092922210693, "learning_rate": 1.9207373271889402e-05, "loss": 1.4609, "step": 474 }, { "epoch": 0.1989945538332635, "grad_norm": 0.6135318875312805, "learning_rate": 1.9205697528278176e-05, "loss": 1.46, "step": 475 }, { "epoch": 0.19941348973607037, "grad_norm": 0.8104654550552368, "learning_rate": 1.920402178466695e-05, "loss": 1.3627, "step": 476 }, { "epoch": 0.19983242563887726, "grad_norm": 0.6633170247077942, "learning_rate": 1.920234604105572e-05, "loss": 1.52, "step": 477 }, { "epoch": 0.20025136154168413, "grad_norm": 0.7291746735572815, "learning_rate": 1.920067029744449e-05, "loss": 1.547, "step": 478 }, { "epoch": 0.200670297444491, "grad_norm": 0.6674147248268127, "learning_rate": 1.9198994553833266e-05, "loss": 1.4795, "step": 479 }, { "epoch": 0.20108923334729786, "grad_norm": 0.9536328911781311, "learning_rate": 1.919731881022204e-05, "loss": 1.4581, "step": 480 }, { "epoch": 0.20150816925010473, "grad_norm": 0.8882992267608643, "learning_rate": 1.919564306661081e-05, "loss": 1.4351, "step": 481 }, { "epoch": 0.2019271051529116, "grad_norm": 0.5723230838775635, "learning_rate": 1.919396732299958e-05, "loss": 1.5095, "step": 482 }, { "epoch": 0.20234604105571846, "grad_norm": 1.1361421346664429, "learning_rate": 1.9192291579388355e-05, "loss": 1.4452, "step": 483 }, { "epoch": 0.20276497695852536, "grad_norm": 0.5762605667114258, "learning_rate": 1.9190615835777126e-05, "loss": 1.5695, "step": 484 }, { "epoch": 0.20318391286133222, "grad_norm": 0.9020100831985474, "learning_rate": 1.91889400921659e-05, "loss": 1.5157, "step": 485 }, { "epoch": 0.2036028487641391, "grad_norm": 0.6302100419998169, "learning_rate": 1.9187264348554674e-05, "loss": 1.5346, "step": 486 }, { "epoch": 0.20402178466694595, "grad_norm": 1.1093989610671997, "learning_rate": 1.9185588604943445e-05, "loss": 1.5348, "step": 487 }, { "epoch": 0.20444072056975282, "grad_norm": 0.637134850025177, "learning_rate": 1.9183912861332216e-05, "loss": 1.4478, "step": 488 }, { "epoch": 0.2048596564725597, "grad_norm": 0.9395270943641663, "learning_rate": 1.918223711772099e-05, "loss": 1.4659, "step": 489 }, { "epoch": 0.20527859237536658, "grad_norm": 0.7030125260353088, "learning_rate": 1.9180561374109764e-05, "loss": 1.3621, "step": 490 }, { "epoch": 0.20569752827817345, "grad_norm": 0.5922579169273376, "learning_rate": 1.9178885630498535e-05, "loss": 1.644, "step": 491 }, { "epoch": 0.2061164641809803, "grad_norm": 1.0161982774734497, "learning_rate": 1.9177209886887306e-05, "loss": 1.3895, "step": 492 }, { "epoch": 0.20653540008378718, "grad_norm": 1.179316759109497, "learning_rate": 1.917553414327608e-05, "loss": 1.4576, "step": 493 }, { "epoch": 0.20695433598659405, "grad_norm": 0.8130103945732117, "learning_rate": 1.9173858399664854e-05, "loss": 1.4637, "step": 494 }, { "epoch": 0.2073732718894009, "grad_norm": 0.7000212669372559, "learning_rate": 1.9172182656053625e-05, "loss": 1.5152, "step": 495 }, { "epoch": 0.2077922077922078, "grad_norm": 0.8932341933250427, "learning_rate": 1.91705069124424e-05, "loss": 1.4741, "step": 496 }, { "epoch": 0.20821114369501467, "grad_norm": 1.3901516199111938, "learning_rate": 1.916883116883117e-05, "loss": 1.4953, "step": 497 }, { "epoch": 0.20863007959782154, "grad_norm": 1.0053791999816895, "learning_rate": 1.9167155425219944e-05, "loss": 1.488, "step": 498 }, { "epoch": 0.2090490155006284, "grad_norm": 0.5231297612190247, "learning_rate": 1.9165479681608718e-05, "loss": 1.4963, "step": 499 }, { "epoch": 0.20946795140343527, "grad_norm": 0.8381982445716858, "learning_rate": 1.916380393799749e-05, "loss": 1.5261, "step": 500 }, { "epoch": 0.20988688730624214, "grad_norm": 0.9278205633163452, "learning_rate": 1.916212819438626e-05, "loss": 1.3259, "step": 501 }, { "epoch": 0.210305823209049, "grad_norm": 0.9388899803161621, "learning_rate": 1.9160452450775033e-05, "loss": 1.4091, "step": 502 }, { "epoch": 0.2107247591118559, "grad_norm": 1.0538358688354492, "learning_rate": 1.9158776707163807e-05, "loss": 1.4633, "step": 503 }, { "epoch": 0.21114369501466276, "grad_norm": 0.6670867800712585, "learning_rate": 1.9157100963552578e-05, "loss": 1.5639, "step": 504 }, { "epoch": 0.21156263091746963, "grad_norm": 1.7608953714370728, "learning_rate": 1.915542521994135e-05, "loss": 1.4433, "step": 505 }, { "epoch": 0.2119815668202765, "grad_norm": 1.1406441926956177, "learning_rate": 1.9153749476330123e-05, "loss": 1.3938, "step": 506 }, { "epoch": 0.21240050272308336, "grad_norm": 1.0751662254333496, "learning_rate": 1.9152073732718897e-05, "loss": 1.5059, "step": 507 }, { "epoch": 0.21281943862589023, "grad_norm": 1.7127149105072021, "learning_rate": 1.9150397989107668e-05, "loss": 1.4072, "step": 508 }, { "epoch": 0.21323837452869712, "grad_norm": 0.7607043385505676, "learning_rate": 1.9148722245496442e-05, "loss": 1.43, "step": 509 }, { "epoch": 0.213657310431504, "grad_norm": 1.0876507759094238, "learning_rate": 1.9147046501885213e-05, "loss": 1.4219, "step": 510 }, { "epoch": 0.21407624633431085, "grad_norm": 1.704974889755249, "learning_rate": 1.9145370758273987e-05, "loss": 1.5058, "step": 511 }, { "epoch": 0.21449518223711772, "grad_norm": 1.3107315301895142, "learning_rate": 1.9143695014662758e-05, "loss": 1.3701, "step": 512 }, { "epoch": 0.2149141181399246, "grad_norm": 0.72137850522995, "learning_rate": 1.9142019271051532e-05, "loss": 1.4608, "step": 513 }, { "epoch": 0.21533305404273145, "grad_norm": 0.9491326808929443, "learning_rate": 1.9140343527440303e-05, "loss": 1.3998, "step": 514 }, { "epoch": 0.21575198994553832, "grad_norm": 0.9301955103874207, "learning_rate": 1.9138667783829073e-05, "loss": 1.5215, "step": 515 }, { "epoch": 0.2161709258483452, "grad_norm": 0.8181395530700684, "learning_rate": 1.9136992040217847e-05, "loss": 1.4322, "step": 516 }, { "epoch": 0.21658986175115208, "grad_norm": 0.7477272748947144, "learning_rate": 1.913531629660662e-05, "loss": 1.4069, "step": 517 }, { "epoch": 0.21700879765395895, "grad_norm": 0.8078567385673523, "learning_rate": 1.9133640552995392e-05, "loss": 1.4061, "step": 518 }, { "epoch": 0.2174277335567658, "grad_norm": 0.6401208639144897, "learning_rate": 1.9131964809384166e-05, "loss": 1.4146, "step": 519 }, { "epoch": 0.21784666945957268, "grad_norm": 1.1645647287368774, "learning_rate": 1.9130289065772937e-05, "loss": 1.4205, "step": 520 }, { "epoch": 0.21826560536237954, "grad_norm": 0.5319536328315735, "learning_rate": 1.912861332216171e-05, "loss": 1.4255, "step": 521 }, { "epoch": 0.21868454126518644, "grad_norm": 0.7974638938903809, "learning_rate": 1.9126937578550485e-05, "loss": 1.4991, "step": 522 }, { "epoch": 0.2191034771679933, "grad_norm": 0.7385554313659668, "learning_rate": 1.9125261834939256e-05, "loss": 1.4917, "step": 523 }, { "epoch": 0.21952241307080017, "grad_norm": 0.6328215003013611, "learning_rate": 1.9123586091328027e-05, "loss": 1.4466, "step": 524 }, { "epoch": 0.21994134897360704, "grad_norm": 0.9712186455726624, "learning_rate": 1.91219103477168e-05, "loss": 1.3888, "step": 525 }, { "epoch": 0.2203602848764139, "grad_norm": 0.8162040710449219, "learning_rate": 1.9120234604105575e-05, "loss": 1.4592, "step": 526 }, { "epoch": 0.22077922077922077, "grad_norm": 0.6039196252822876, "learning_rate": 1.9118558860494346e-05, "loss": 1.4641, "step": 527 }, { "epoch": 0.22119815668202766, "grad_norm": 0.677533745765686, "learning_rate": 1.9116883116883117e-05, "loss": 1.4318, "step": 528 }, { "epoch": 0.22161709258483453, "grad_norm": 0.5307941436767578, "learning_rate": 1.911520737327189e-05, "loss": 1.4567, "step": 529 }, { "epoch": 0.2220360284876414, "grad_norm": 0.6290689706802368, "learning_rate": 1.9113531629660665e-05, "loss": 1.5327, "step": 530 }, { "epoch": 0.22245496439044826, "grad_norm": 0.668403685092926, "learning_rate": 1.9111855886049436e-05, "loss": 1.5186, "step": 531 }, { "epoch": 0.22287390029325513, "grad_norm": 0.8590381145477295, "learning_rate": 1.911018014243821e-05, "loss": 1.4103, "step": 532 }, { "epoch": 0.223292836196062, "grad_norm": 0.8472411036491394, "learning_rate": 1.910850439882698e-05, "loss": 1.4171, "step": 533 }, { "epoch": 0.22371177209886886, "grad_norm": 0.8556522130966187, "learning_rate": 1.9106828655215755e-05, "loss": 1.4334, "step": 534 }, { "epoch": 0.22413070800167575, "grad_norm": 0.6294506192207336, "learning_rate": 1.9105152911604525e-05, "loss": 1.4425, "step": 535 }, { "epoch": 0.22454964390448262, "grad_norm": 0.8159162402153015, "learning_rate": 1.91034771679933e-05, "loss": 1.5275, "step": 536 }, { "epoch": 0.2249685798072895, "grad_norm": 0.7663982510566711, "learning_rate": 1.910180142438207e-05, "loss": 1.4252, "step": 537 }, { "epoch": 0.22538751571009635, "grad_norm": 0.6042879223823547, "learning_rate": 1.9100125680770844e-05, "loss": 1.4374, "step": 538 }, { "epoch": 0.22580645161290322, "grad_norm": 0.5414412617683411, "learning_rate": 1.9098449937159615e-05, "loss": 1.4921, "step": 539 }, { "epoch": 0.22622538751571009, "grad_norm": 0.7135291695594788, "learning_rate": 1.909677419354839e-05, "loss": 1.5495, "step": 540 }, { "epoch": 0.22664432341851698, "grad_norm": 0.5732749104499817, "learning_rate": 1.9095098449937163e-05, "loss": 1.3577, "step": 541 }, { "epoch": 0.22706325932132385, "grad_norm": 0.6375070810317993, "learning_rate": 1.9093422706325934e-05, "loss": 1.4254, "step": 542 }, { "epoch": 0.2274821952241307, "grad_norm": 0.6467480063438416, "learning_rate": 1.9091746962714705e-05, "loss": 1.4277, "step": 543 }, { "epoch": 0.22790113112693758, "grad_norm": 0.6565422415733337, "learning_rate": 1.909007121910348e-05, "loss": 1.55, "step": 544 }, { "epoch": 0.22832006702974444, "grad_norm": 0.6464892625808716, "learning_rate": 1.9088395475492253e-05, "loss": 1.4626, "step": 545 }, { "epoch": 0.2287390029325513, "grad_norm": 0.6357992887496948, "learning_rate": 1.9086719731881024e-05, "loss": 1.4343, "step": 546 }, { "epoch": 0.22915793883535818, "grad_norm": 0.6153067946434021, "learning_rate": 1.9085043988269795e-05, "loss": 1.4146, "step": 547 }, { "epoch": 0.22957687473816507, "grad_norm": 0.7078065276145935, "learning_rate": 1.908336824465857e-05, "loss": 1.4147, "step": 548 }, { "epoch": 0.22999581064097194, "grad_norm": 0.6610170602798462, "learning_rate": 1.9081692501047343e-05, "loss": 1.5137, "step": 549 }, { "epoch": 0.2304147465437788, "grad_norm": 0.6916443705558777, "learning_rate": 1.9080016757436114e-05, "loss": 1.4726, "step": 550 }, { "epoch": 0.23083368244658567, "grad_norm": 0.668258547782898, "learning_rate": 1.9078341013824884e-05, "loss": 1.4796, "step": 551 }, { "epoch": 0.23125261834939254, "grad_norm": 0.6234722137451172, "learning_rate": 1.907666527021366e-05, "loss": 1.4962, "step": 552 }, { "epoch": 0.2316715542521994, "grad_norm": 0.7003756761550903, "learning_rate": 1.9074989526602433e-05, "loss": 1.4681, "step": 553 }, { "epoch": 0.2320904901550063, "grad_norm": 0.6396431922912598, "learning_rate": 1.9073313782991203e-05, "loss": 1.3989, "step": 554 }, { "epoch": 0.23250942605781316, "grad_norm": 0.6359259486198425, "learning_rate": 1.9071638039379977e-05, "loss": 1.4533, "step": 555 }, { "epoch": 0.23292836196062003, "grad_norm": 0.6927059292793274, "learning_rate": 1.9069962295768748e-05, "loss": 1.4107, "step": 556 }, { "epoch": 0.2333472978634269, "grad_norm": 0.633521318435669, "learning_rate": 1.9068286552157522e-05, "loss": 1.4099, "step": 557 }, { "epoch": 0.23376623376623376, "grad_norm": 0.6133984923362732, "learning_rate": 1.9066610808546293e-05, "loss": 1.425, "step": 558 }, { "epoch": 0.23418516966904063, "grad_norm": 0.661888062953949, "learning_rate": 1.9064935064935067e-05, "loss": 1.5631, "step": 559 }, { "epoch": 0.23460410557184752, "grad_norm": 0.645517110824585, "learning_rate": 1.9063259321323838e-05, "loss": 1.4026, "step": 560 }, { "epoch": 0.2350230414746544, "grad_norm": 0.5653700828552246, "learning_rate": 1.9061583577712612e-05, "loss": 1.413, "step": 561 }, { "epoch": 0.23544197737746125, "grad_norm": 0.7444579601287842, "learning_rate": 1.9059907834101383e-05, "loss": 1.4424, "step": 562 }, { "epoch": 0.23586091328026812, "grad_norm": 0.618651270866394, "learning_rate": 1.9058232090490157e-05, "loss": 1.6035, "step": 563 }, { "epoch": 0.23627984918307499, "grad_norm": 0.6566857695579529, "learning_rate": 1.905655634687893e-05, "loss": 1.3807, "step": 564 }, { "epoch": 0.23669878508588185, "grad_norm": 0.5518476963043213, "learning_rate": 1.9054880603267702e-05, "loss": 1.5754, "step": 565 }, { "epoch": 0.23711772098868872, "grad_norm": 0.5864123106002808, "learning_rate": 1.9053204859656472e-05, "loss": 1.4076, "step": 566 }, { "epoch": 0.2375366568914956, "grad_norm": 0.7522138953208923, "learning_rate": 1.9051529116045247e-05, "loss": 1.439, "step": 567 }, { "epoch": 0.23795559279430248, "grad_norm": 0.616507351398468, "learning_rate": 1.904985337243402e-05, "loss": 1.463, "step": 568 }, { "epoch": 0.23837452869710934, "grad_norm": 0.5815699100494385, "learning_rate": 1.904817762882279e-05, "loss": 1.4541, "step": 569 }, { "epoch": 0.2387934645999162, "grad_norm": 0.6003520488739014, "learning_rate": 1.9046501885211562e-05, "loss": 1.4897, "step": 570 }, { "epoch": 0.23921240050272308, "grad_norm": 0.6311242580413818, "learning_rate": 1.9044826141600336e-05, "loss": 1.4004, "step": 571 }, { "epoch": 0.23963133640552994, "grad_norm": 0.607297956943512, "learning_rate": 1.904315039798911e-05, "loss": 1.5698, "step": 572 }, { "epoch": 0.24005027230833684, "grad_norm": 0.7055544257164001, "learning_rate": 1.904147465437788e-05, "loss": 1.4389, "step": 573 }, { "epoch": 0.2404692082111437, "grad_norm": 0.7283361554145813, "learning_rate": 1.9039798910766655e-05, "loss": 1.4967, "step": 574 }, { "epoch": 0.24088814411395057, "grad_norm": 0.688834547996521, "learning_rate": 1.9038123167155426e-05, "loss": 1.4883, "step": 575 }, { "epoch": 0.24130708001675744, "grad_norm": 0.47785529494285583, "learning_rate": 1.90364474235442e-05, "loss": 1.5188, "step": 576 }, { "epoch": 0.2417260159195643, "grad_norm": 0.9133197069168091, "learning_rate": 1.903477167993297e-05, "loss": 1.3748, "step": 577 }, { "epoch": 0.24214495182237117, "grad_norm": 0.6180113554000854, "learning_rate": 1.9033095936321745e-05, "loss": 1.4213, "step": 578 }, { "epoch": 0.24256388772517803, "grad_norm": 0.6890195608139038, "learning_rate": 1.9031420192710516e-05, "loss": 1.3621, "step": 579 }, { "epoch": 0.24298282362798493, "grad_norm": 0.6566532850265503, "learning_rate": 1.902974444909929e-05, "loss": 1.3666, "step": 580 }, { "epoch": 0.2434017595307918, "grad_norm": 0.572672963142395, "learning_rate": 1.902806870548806e-05, "loss": 1.3654, "step": 581 }, { "epoch": 0.24382069543359866, "grad_norm": 0.698391318321228, "learning_rate": 1.9026392961876835e-05, "loss": 1.4244, "step": 582 }, { "epoch": 0.24423963133640553, "grad_norm": 0.5516411066055298, "learning_rate": 1.9024717218265606e-05, "loss": 1.5141, "step": 583 }, { "epoch": 0.2446585672392124, "grad_norm": 0.6122570037841797, "learning_rate": 1.902304147465438e-05, "loss": 1.4333, "step": 584 }, { "epoch": 0.24507750314201926, "grad_norm": 0.7202199697494507, "learning_rate": 1.902136573104315e-05, "loss": 1.4562, "step": 585 }, { "epoch": 0.24549643904482615, "grad_norm": 0.938453733921051, "learning_rate": 1.9019689987431925e-05, "loss": 1.4605, "step": 586 }, { "epoch": 0.24591537494763302, "grad_norm": 0.5673055648803711, "learning_rate": 1.90180142438207e-05, "loss": 1.4827, "step": 587 }, { "epoch": 0.24633431085043989, "grad_norm": 0.677293062210083, "learning_rate": 1.901633850020947e-05, "loss": 1.375, "step": 588 }, { "epoch": 0.24675324675324675, "grad_norm": 0.7138928771018982, "learning_rate": 1.901466275659824e-05, "loss": 1.541, "step": 589 }, { "epoch": 0.24717218265605362, "grad_norm": 0.7003957033157349, "learning_rate": 1.9012987012987014e-05, "loss": 1.4234, "step": 590 }, { "epoch": 0.24759111855886048, "grad_norm": 0.8985845446586609, "learning_rate": 1.901131126937579e-05, "loss": 1.2981, "step": 591 }, { "epoch": 0.24801005446166738, "grad_norm": 0.6559215784072876, "learning_rate": 1.900963552576456e-05, "loss": 1.4871, "step": 592 }, { "epoch": 0.24842899036447424, "grad_norm": 1.0038827657699585, "learning_rate": 1.900795978215333e-05, "loss": 1.3604, "step": 593 }, { "epoch": 0.2488479262672811, "grad_norm": 0.670703649520874, "learning_rate": 1.9006284038542104e-05, "loss": 1.4142, "step": 594 }, { "epoch": 0.24926686217008798, "grad_norm": 0.6743998527526855, "learning_rate": 1.9004608294930878e-05, "loss": 1.421, "step": 595 }, { "epoch": 0.24968579807289484, "grad_norm": 0.90179044008255, "learning_rate": 1.900293255131965e-05, "loss": 1.3545, "step": 596 }, { "epoch": 0.2501047339757017, "grad_norm": 0.7004808187484741, "learning_rate": 1.9001256807708423e-05, "loss": 1.4334, "step": 597 }, { "epoch": 0.2505236698785086, "grad_norm": 0.811750590801239, "learning_rate": 1.8999581064097194e-05, "loss": 1.5068, "step": 598 }, { "epoch": 0.25094260578131544, "grad_norm": 0.5660247206687927, "learning_rate": 1.8997905320485968e-05, "loss": 1.4119, "step": 599 }, { "epoch": 0.25136154168412234, "grad_norm": 0.7421470880508423, "learning_rate": 1.8996229576874742e-05, "loss": 1.4193, "step": 600 }, { "epoch": 0.2517804775869292, "grad_norm": 0.7964827418327332, "learning_rate": 1.8994553833263513e-05, "loss": 1.3664, "step": 601 }, { "epoch": 0.25219941348973607, "grad_norm": 0.587858259677887, "learning_rate": 1.8992878089652283e-05, "loss": 1.4094, "step": 602 }, { "epoch": 0.25261834939254296, "grad_norm": 0.8728364109992981, "learning_rate": 1.8991202346041058e-05, "loss": 1.2841, "step": 603 }, { "epoch": 0.2530372852953498, "grad_norm": 0.7561309933662415, "learning_rate": 1.8989526602429832e-05, "loss": 1.351, "step": 604 }, { "epoch": 0.2534562211981567, "grad_norm": 0.6205732822418213, "learning_rate": 1.8987850858818602e-05, "loss": 1.4043, "step": 605 }, { "epoch": 0.25387515710096353, "grad_norm": 0.7390834093093872, "learning_rate": 1.8986175115207373e-05, "loss": 1.4274, "step": 606 }, { "epoch": 0.2542940930037704, "grad_norm": 0.7050930261611938, "learning_rate": 1.8984499371596147e-05, "loss": 1.4875, "step": 607 }, { "epoch": 0.2547130289065773, "grad_norm": 0.5341117978096008, "learning_rate": 1.898282362798492e-05, "loss": 1.4482, "step": 608 }, { "epoch": 0.25513196480938416, "grad_norm": 0.8297886848449707, "learning_rate": 1.8981147884373692e-05, "loss": 1.3514, "step": 609 }, { "epoch": 0.25555090071219105, "grad_norm": 0.6667957901954651, "learning_rate": 1.8979472140762466e-05, "loss": 1.3185, "step": 610 }, { "epoch": 0.2559698366149979, "grad_norm": 0.6411688923835754, "learning_rate": 1.8977796397151237e-05, "loss": 1.4442, "step": 611 }, { "epoch": 0.2563887725178048, "grad_norm": 0.6379684805870056, "learning_rate": 1.8976120653540008e-05, "loss": 1.4377, "step": 612 }, { "epoch": 0.2568077084206116, "grad_norm": 0.6216014623641968, "learning_rate": 1.8974444909928782e-05, "loss": 1.4474, "step": 613 }, { "epoch": 0.2572266443234185, "grad_norm": 0.5671195983886719, "learning_rate": 1.8972769166317556e-05, "loss": 1.4434, "step": 614 }, { "epoch": 0.2576455802262254, "grad_norm": 0.8159009218215942, "learning_rate": 1.8971093422706327e-05, "loss": 1.3781, "step": 615 }, { "epoch": 0.25806451612903225, "grad_norm": 0.6750363111495972, "learning_rate": 1.8969417679095098e-05, "loss": 1.5244, "step": 616 }, { "epoch": 0.25848345203183914, "grad_norm": 0.5345395803451538, "learning_rate": 1.896774193548387e-05, "loss": 1.4944, "step": 617 }, { "epoch": 0.258902387934646, "grad_norm": 1.0422483682632446, "learning_rate": 1.8966066191872646e-05, "loss": 1.4257, "step": 618 }, { "epoch": 0.2593213238374529, "grad_norm": 0.6644807457923889, "learning_rate": 1.896439044826142e-05, "loss": 1.4396, "step": 619 }, { "epoch": 0.2597402597402597, "grad_norm": 0.6991039514541626, "learning_rate": 1.896271470465019e-05, "loss": 1.4456, "step": 620 }, { "epoch": 0.2601591956430666, "grad_norm": 0.6287118792533875, "learning_rate": 1.896103896103896e-05, "loss": 1.3556, "step": 621 }, { "epoch": 0.2605781315458735, "grad_norm": 0.7149505615234375, "learning_rate": 1.8959363217427736e-05, "loss": 1.3708, "step": 622 }, { "epoch": 0.26099706744868034, "grad_norm": 0.6485461592674255, "learning_rate": 1.895768747381651e-05, "loss": 1.3813, "step": 623 }, { "epoch": 0.26141600335148724, "grad_norm": 0.796234130859375, "learning_rate": 1.895601173020528e-05, "loss": 1.4557, "step": 624 }, { "epoch": 0.2618349392542941, "grad_norm": 0.6059120297431946, "learning_rate": 1.895433598659405e-05, "loss": 1.4393, "step": 625 }, { "epoch": 0.26225387515710097, "grad_norm": 0.7328737378120422, "learning_rate": 1.8952660242982825e-05, "loss": 1.4259, "step": 626 }, { "epoch": 0.2626728110599078, "grad_norm": 0.5874695181846619, "learning_rate": 1.89509844993716e-05, "loss": 1.51, "step": 627 }, { "epoch": 0.2630917469627147, "grad_norm": 0.7244255542755127, "learning_rate": 1.894930875576037e-05, "loss": 1.4277, "step": 628 }, { "epoch": 0.2635106828655216, "grad_norm": 0.5406452417373657, "learning_rate": 1.894763301214914e-05, "loss": 1.4015, "step": 629 }, { "epoch": 0.26392961876832843, "grad_norm": 0.7187069058418274, "learning_rate": 1.8945957268537915e-05, "loss": 1.417, "step": 630 }, { "epoch": 0.2643485546711353, "grad_norm": 0.6457657217979431, "learning_rate": 1.894428152492669e-05, "loss": 1.4711, "step": 631 }, { "epoch": 0.26476749057394217, "grad_norm": 0.5307900309562683, "learning_rate": 1.894260578131546e-05, "loss": 1.4237, "step": 632 }, { "epoch": 0.26518642647674906, "grad_norm": 0.9521127343177795, "learning_rate": 1.8940930037704234e-05, "loss": 1.3934, "step": 633 }, { "epoch": 0.26560536237955595, "grad_norm": 0.596931517124176, "learning_rate": 1.8939254294093005e-05, "loss": 1.4957, "step": 634 }, { "epoch": 0.2660242982823628, "grad_norm": 0.8038269281387329, "learning_rate": 1.893757855048178e-05, "loss": 1.4551, "step": 635 }, { "epoch": 0.2664432341851697, "grad_norm": 0.7987629771232605, "learning_rate": 1.893590280687055e-05, "loss": 1.4973, "step": 636 }, { "epoch": 0.2668621700879765, "grad_norm": 0.7971741557121277, "learning_rate": 1.8934227063259324e-05, "loss": 1.331, "step": 637 }, { "epoch": 0.2672811059907834, "grad_norm": 0.6776058077812195, "learning_rate": 1.8932551319648094e-05, "loss": 1.3397, "step": 638 }, { "epoch": 0.26770004189359026, "grad_norm": 0.7527434825897217, "learning_rate": 1.893087557603687e-05, "loss": 1.3912, "step": 639 }, { "epoch": 0.26811897779639715, "grad_norm": 0.6726639866828918, "learning_rate": 1.892919983242564e-05, "loss": 1.3428, "step": 640 }, { "epoch": 0.26853791369920404, "grad_norm": 0.7143589854240417, "learning_rate": 1.8927524088814413e-05, "loss": 1.4311, "step": 641 }, { "epoch": 0.2689568496020109, "grad_norm": 0.6544737815856934, "learning_rate": 1.8925848345203188e-05, "loss": 1.4774, "step": 642 }, { "epoch": 0.2693757855048178, "grad_norm": 0.707067608833313, "learning_rate": 1.892417260159196e-05, "loss": 1.3982, "step": 643 }, { "epoch": 0.2697947214076246, "grad_norm": 0.7015464901924133, "learning_rate": 1.892249685798073e-05, "loss": 1.3921, "step": 644 }, { "epoch": 0.2702136573104315, "grad_norm": 0.7379519939422607, "learning_rate": 1.8920821114369503e-05, "loss": 1.4429, "step": 645 }, { "epoch": 0.27063259321323835, "grad_norm": 0.6990654468536377, "learning_rate": 1.8919145370758277e-05, "loss": 1.3888, "step": 646 }, { "epoch": 0.27105152911604524, "grad_norm": 0.8418135643005371, "learning_rate": 1.8917469627147048e-05, "loss": 1.3989, "step": 647 }, { "epoch": 0.27147046501885214, "grad_norm": 0.7323577404022217, "learning_rate": 1.891579388353582e-05, "loss": 1.4053, "step": 648 }, { "epoch": 0.271889400921659, "grad_norm": 0.5955424904823303, "learning_rate": 1.8914118139924593e-05, "loss": 1.4684, "step": 649 }, { "epoch": 0.27230833682446587, "grad_norm": 0.7422502040863037, "learning_rate": 1.8912442396313367e-05, "loss": 1.394, "step": 650 }, { "epoch": 0.2727272727272727, "grad_norm": 0.6807714700698853, "learning_rate": 1.8910766652702138e-05, "loss": 1.315, "step": 651 }, { "epoch": 0.2731462086300796, "grad_norm": 0.6865885257720947, "learning_rate": 1.8909090909090912e-05, "loss": 1.3815, "step": 652 }, { "epoch": 0.2735651445328865, "grad_norm": 0.7024874091148376, "learning_rate": 1.8907415165479683e-05, "loss": 1.4215, "step": 653 }, { "epoch": 0.27398408043569333, "grad_norm": 0.7904298305511475, "learning_rate": 1.8905739421868457e-05, "loss": 1.3908, "step": 654 }, { "epoch": 0.2744030163385002, "grad_norm": 0.6477106213569641, "learning_rate": 1.8904063678257228e-05, "loss": 1.4599, "step": 655 }, { "epoch": 0.27482195224130707, "grad_norm": 0.8508483171463013, "learning_rate": 1.8902387934646e-05, "loss": 1.4838, "step": 656 }, { "epoch": 0.27524088814411396, "grad_norm": 0.5711894631385803, "learning_rate": 1.8900712191034772e-05, "loss": 1.4615, "step": 657 }, { "epoch": 0.2756598240469208, "grad_norm": 0.6993704438209534, "learning_rate": 1.8899036447423547e-05, "loss": 1.4493, "step": 658 }, { "epoch": 0.2760787599497277, "grad_norm": 1.0374524593353271, "learning_rate": 1.8897360703812317e-05, "loss": 1.482, "step": 659 }, { "epoch": 0.2764976958525346, "grad_norm": 0.9369934797286987, "learning_rate": 1.889568496020109e-05, "loss": 1.3472, "step": 660 }, { "epoch": 0.2769166317553414, "grad_norm": 0.8173794746398926, "learning_rate": 1.8894009216589862e-05, "loss": 1.4428, "step": 661 }, { "epoch": 0.2773355676581483, "grad_norm": 1.059898018836975, "learning_rate": 1.8892333472978636e-05, "loss": 1.395, "step": 662 }, { "epoch": 0.27775450356095516, "grad_norm": 0.5998404026031494, "learning_rate": 1.8890657729367407e-05, "loss": 1.3945, "step": 663 }, { "epoch": 0.27817343946376205, "grad_norm": 0.6833025217056274, "learning_rate": 1.888898198575618e-05, "loss": 1.4655, "step": 664 }, { "epoch": 0.2785923753665689, "grad_norm": 0.7907499670982361, "learning_rate": 1.8887306242144955e-05, "loss": 1.3141, "step": 665 }, { "epoch": 0.2790113112693758, "grad_norm": 0.6411296129226685, "learning_rate": 1.8885630498533726e-05, "loss": 1.507, "step": 666 }, { "epoch": 0.2794302471721827, "grad_norm": 0.8076937794685364, "learning_rate": 1.8883954754922497e-05, "loss": 1.3578, "step": 667 }, { "epoch": 0.2798491830749895, "grad_norm": 0.6930973529815674, "learning_rate": 1.888227901131127e-05, "loss": 1.3186, "step": 668 }, { "epoch": 0.2802681189777964, "grad_norm": 0.7560698390007019, "learning_rate": 1.8880603267700045e-05, "loss": 1.3772, "step": 669 }, { "epoch": 0.28068705488060325, "grad_norm": 0.5842419266700745, "learning_rate": 1.8878927524088816e-05, "loss": 1.4772, "step": 670 }, { "epoch": 0.28110599078341014, "grad_norm": 0.9055956602096558, "learning_rate": 1.8877251780477586e-05, "loss": 1.4802, "step": 671 }, { "epoch": 0.28152492668621704, "grad_norm": 0.5749624371528625, "learning_rate": 1.887557603686636e-05, "loss": 1.345, "step": 672 }, { "epoch": 0.2819438625890239, "grad_norm": 0.6721547245979309, "learning_rate": 1.8873900293255135e-05, "loss": 1.3641, "step": 673 }, { "epoch": 0.28236279849183077, "grad_norm": 0.580252468585968, "learning_rate": 1.8872224549643905e-05, "loss": 1.4225, "step": 674 }, { "epoch": 0.2827817343946376, "grad_norm": 0.8793032765388489, "learning_rate": 1.887054880603268e-05, "loss": 1.3721, "step": 675 }, { "epoch": 0.2832006702974445, "grad_norm": 0.5774890184402466, "learning_rate": 1.886887306242145e-05, "loss": 1.4358, "step": 676 }, { "epoch": 0.28361960620025134, "grad_norm": 0.6694848537445068, "learning_rate": 1.8867197318810224e-05, "loss": 1.3601, "step": 677 }, { "epoch": 0.28403854210305823, "grad_norm": 0.5719591975212097, "learning_rate": 1.8865521575198995e-05, "loss": 1.526, "step": 678 }, { "epoch": 0.2844574780058651, "grad_norm": 0.6238727569580078, "learning_rate": 1.886384583158777e-05, "loss": 1.3982, "step": 679 }, { "epoch": 0.28487641390867197, "grad_norm": 0.6695346236228943, "learning_rate": 1.886217008797654e-05, "loss": 1.384, "step": 680 }, { "epoch": 0.28529534981147886, "grad_norm": 0.7487378120422363, "learning_rate": 1.8860494344365314e-05, "loss": 1.364, "step": 681 }, { "epoch": 0.2857142857142857, "grad_norm": 0.6982246041297913, "learning_rate": 1.8858818600754085e-05, "loss": 1.4175, "step": 682 }, { "epoch": 0.2861332216170926, "grad_norm": 0.6678481698036194, "learning_rate": 1.885714285714286e-05, "loss": 1.3014, "step": 683 }, { "epoch": 0.28655215751989943, "grad_norm": 0.5933229923248291, "learning_rate": 1.885546711353163e-05, "loss": 1.4171, "step": 684 }, { "epoch": 0.2869710934227063, "grad_norm": 0.6992403864860535, "learning_rate": 1.8853791369920404e-05, "loss": 1.3231, "step": 685 }, { "epoch": 0.2873900293255132, "grad_norm": 0.4942586421966553, "learning_rate": 1.8852115626309175e-05, "loss": 1.4685, "step": 686 }, { "epoch": 0.28780896522832006, "grad_norm": 0.6683540940284729, "learning_rate": 1.885043988269795e-05, "loss": 1.3826, "step": 687 }, { "epoch": 0.28822790113112695, "grad_norm": 0.4600916802883148, "learning_rate": 1.8848764139086723e-05, "loss": 1.4668, "step": 688 }, { "epoch": 0.2886468370339338, "grad_norm": 0.6156571507453918, "learning_rate": 1.8847088395475494e-05, "loss": 1.4465, "step": 689 }, { "epoch": 0.2890657729367407, "grad_norm": 0.5449684262275696, "learning_rate": 1.8845412651864264e-05, "loss": 1.2964, "step": 690 }, { "epoch": 0.2894847088395475, "grad_norm": 0.5813759565353394, "learning_rate": 1.884373690825304e-05, "loss": 1.4211, "step": 691 }, { "epoch": 0.2899036447423544, "grad_norm": 0.618743360042572, "learning_rate": 1.8842061164641813e-05, "loss": 1.3976, "step": 692 }, { "epoch": 0.2903225806451613, "grad_norm": 0.5242084264755249, "learning_rate": 1.8840385421030583e-05, "loss": 1.4076, "step": 693 }, { "epoch": 0.29074151654796815, "grad_norm": 0.676110029220581, "learning_rate": 1.8838709677419354e-05, "loss": 1.3143, "step": 694 }, { "epoch": 0.29116045245077504, "grad_norm": 0.5773074626922607, "learning_rate": 1.8837033933808128e-05, "loss": 1.4443, "step": 695 }, { "epoch": 0.2915793883535819, "grad_norm": 0.8076342940330505, "learning_rate": 1.8835358190196902e-05, "loss": 1.469, "step": 696 }, { "epoch": 0.2919983242563888, "grad_norm": 0.6035589575767517, "learning_rate": 1.8833682446585677e-05, "loss": 1.349, "step": 697 }, { "epoch": 0.29241726015919567, "grad_norm": 1.1530474424362183, "learning_rate": 1.8832006702974447e-05, "loss": 1.4056, "step": 698 }, { "epoch": 0.2928361960620025, "grad_norm": 0.6804980635643005, "learning_rate": 1.8830330959363218e-05, "loss": 1.45, "step": 699 }, { "epoch": 0.2932551319648094, "grad_norm": 0.8612604141235352, "learning_rate": 1.8828655215751992e-05, "loss": 1.4082, "step": 700 }, { "epoch": 0.29367406786761624, "grad_norm": 0.7837015390396118, "learning_rate": 1.8826979472140766e-05, "loss": 1.3432, "step": 701 }, { "epoch": 0.29409300377042313, "grad_norm": 1.0070463418960571, "learning_rate": 1.8825303728529537e-05, "loss": 1.3149, "step": 702 }, { "epoch": 0.29451193967322997, "grad_norm": 0.8743970990180969, "learning_rate": 1.8823627984918308e-05, "loss": 1.2927, "step": 703 }, { "epoch": 0.29493087557603687, "grad_norm": 0.7475900053977966, "learning_rate": 1.8821952241307082e-05, "loss": 1.4228, "step": 704 }, { "epoch": 0.29534981147884376, "grad_norm": 0.5288072824478149, "learning_rate": 1.8820276497695853e-05, "loss": 1.3062, "step": 705 }, { "epoch": 0.2957687473816506, "grad_norm": 0.718515932559967, "learning_rate": 1.8818600754084627e-05, "loss": 1.4571, "step": 706 }, { "epoch": 0.2961876832844575, "grad_norm": 0.6150030493736267, "learning_rate": 1.8816925010473397e-05, "loss": 1.4581, "step": 707 }, { "epoch": 0.29660661918726433, "grad_norm": 0.6937044858932495, "learning_rate": 1.881524926686217e-05, "loss": 1.3419, "step": 708 }, { "epoch": 0.2970255550900712, "grad_norm": 0.8995934128761292, "learning_rate": 1.8813573523250942e-05, "loss": 1.5374, "step": 709 }, { "epoch": 0.29744449099287806, "grad_norm": 0.5294831991195679, "learning_rate": 1.8811897779639716e-05, "loss": 1.4163, "step": 710 }, { "epoch": 0.29786342689568496, "grad_norm": 1.1763445138931274, "learning_rate": 1.881022203602849e-05, "loss": 1.3632, "step": 711 }, { "epoch": 0.29828236279849185, "grad_norm": 0.6113332509994507, "learning_rate": 1.880854629241726e-05, "loss": 1.417, "step": 712 }, { "epoch": 0.2987012987012987, "grad_norm": 0.7323436737060547, "learning_rate": 1.8806870548806032e-05, "loss": 1.4475, "step": 713 }, { "epoch": 0.2991202346041056, "grad_norm": 0.6122335195541382, "learning_rate": 1.8805194805194806e-05, "loss": 1.4296, "step": 714 }, { "epoch": 0.2995391705069124, "grad_norm": 0.8511880040168762, "learning_rate": 1.880351906158358e-05, "loss": 1.2773, "step": 715 }, { "epoch": 0.2999581064097193, "grad_norm": 0.540932297706604, "learning_rate": 1.880184331797235e-05, "loss": 1.4429, "step": 716 }, { "epoch": 0.3003770423125262, "grad_norm": 0.7005630731582642, "learning_rate": 1.8800167574361122e-05, "loss": 1.3484, "step": 717 }, { "epoch": 0.30079597821533305, "grad_norm": 0.4778623878955841, "learning_rate": 1.8798491830749896e-05, "loss": 1.4279, "step": 718 }, { "epoch": 0.30121491411813994, "grad_norm": 0.6638504266738892, "learning_rate": 1.879681608713867e-05, "loss": 1.3713, "step": 719 }, { "epoch": 0.3016338500209468, "grad_norm": 0.6170998811721802, "learning_rate": 1.8795140343527444e-05, "loss": 1.4593, "step": 720 }, { "epoch": 0.3020527859237537, "grad_norm": 0.8390569686889648, "learning_rate": 1.8793464599916215e-05, "loss": 1.3165, "step": 721 }, { "epoch": 0.3024717218265605, "grad_norm": 0.5174708962440491, "learning_rate": 1.8791788856304986e-05, "loss": 1.3133, "step": 722 }, { "epoch": 0.3028906577293674, "grad_norm": 0.6793212294578552, "learning_rate": 1.879011311269376e-05, "loss": 1.4321, "step": 723 }, { "epoch": 0.3033095936321743, "grad_norm": 0.6248990893363953, "learning_rate": 1.8788437369082534e-05, "loss": 1.3265, "step": 724 }, { "epoch": 0.30372852953498114, "grad_norm": 0.6905636191368103, "learning_rate": 1.8786761625471305e-05, "loss": 1.4365, "step": 725 }, { "epoch": 0.30414746543778803, "grad_norm": 0.5848572850227356, "learning_rate": 1.8785085881860075e-05, "loss": 1.3977, "step": 726 }, { "epoch": 0.30456640134059487, "grad_norm": 0.715691089630127, "learning_rate": 1.878341013824885e-05, "loss": 1.43, "step": 727 }, { "epoch": 0.30498533724340177, "grad_norm": 0.5724084377288818, "learning_rate": 1.8781734394637624e-05, "loss": 1.4189, "step": 728 }, { "epoch": 0.3054042731462086, "grad_norm": 0.6158417463302612, "learning_rate": 1.8780058651026394e-05, "loss": 1.4262, "step": 729 }, { "epoch": 0.3058232090490155, "grad_norm": 0.5914372801780701, "learning_rate": 1.877838290741517e-05, "loss": 1.3335, "step": 730 }, { "epoch": 0.3062421449518224, "grad_norm": 0.6226646900177002, "learning_rate": 1.877670716380394e-05, "loss": 1.366, "step": 731 }, { "epoch": 0.30666108085462923, "grad_norm": 0.5656031370162964, "learning_rate": 1.8775031420192713e-05, "loss": 1.2984, "step": 732 }, { "epoch": 0.3070800167574361, "grad_norm": 0.7473766207695007, "learning_rate": 1.8773355676581484e-05, "loss": 1.3788, "step": 733 }, { "epoch": 0.30749895266024296, "grad_norm": 0.686081051826477, "learning_rate": 1.8771679932970258e-05, "loss": 1.2504, "step": 734 }, { "epoch": 0.30791788856304986, "grad_norm": 0.6029173135757446, "learning_rate": 1.877000418935903e-05, "loss": 1.3931, "step": 735 }, { "epoch": 0.30833682446585675, "grad_norm": 0.761979341506958, "learning_rate": 1.8768328445747803e-05, "loss": 1.3497, "step": 736 }, { "epoch": 0.3087557603686636, "grad_norm": 0.6504870057106018, "learning_rate": 1.8766652702136574e-05, "loss": 1.4025, "step": 737 }, { "epoch": 0.3091746962714705, "grad_norm": 0.7684826254844666, "learning_rate": 1.8764976958525348e-05, "loss": 1.506, "step": 738 }, { "epoch": 0.3095936321742773, "grad_norm": 0.8104509115219116, "learning_rate": 1.876330121491412e-05, "loss": 1.4321, "step": 739 }, { "epoch": 0.3100125680770842, "grad_norm": 0.5708764791488647, "learning_rate": 1.876162547130289e-05, "loss": 1.3636, "step": 740 }, { "epoch": 0.31043150397989105, "grad_norm": 0.5689902901649475, "learning_rate": 1.8759949727691664e-05, "loss": 1.3956, "step": 741 }, { "epoch": 0.31085043988269795, "grad_norm": 0.6868107914924622, "learning_rate": 1.8758273984080438e-05, "loss": 1.3395, "step": 742 }, { "epoch": 0.31126937578550484, "grad_norm": 0.6060523390769958, "learning_rate": 1.8756598240469212e-05, "loss": 1.369, "step": 743 }, { "epoch": 0.3116883116883117, "grad_norm": 0.8488364219665527, "learning_rate": 1.8754922496857983e-05, "loss": 1.3584, "step": 744 }, { "epoch": 0.3121072475911186, "grad_norm": 0.5008958578109741, "learning_rate": 1.8753246753246753e-05, "loss": 1.4263, "step": 745 }, { "epoch": 0.3125261834939254, "grad_norm": 0.5795634388923645, "learning_rate": 1.8751571009635527e-05, "loss": 1.4323, "step": 746 }, { "epoch": 0.3129451193967323, "grad_norm": 0.5958297848701477, "learning_rate": 1.87498952660243e-05, "loss": 1.435, "step": 747 }, { "epoch": 0.31336405529953915, "grad_norm": 0.610854983329773, "learning_rate": 1.8748219522413072e-05, "loss": 1.3164, "step": 748 }, { "epoch": 0.31378299120234604, "grad_norm": 0.6233651638031006, "learning_rate": 1.8746543778801843e-05, "loss": 1.3757, "step": 749 }, { "epoch": 0.31420192710515293, "grad_norm": 0.6277685165405273, "learning_rate": 1.8744868035190617e-05, "loss": 1.3958, "step": 750 }, { "epoch": 0.3146208630079598, "grad_norm": 0.6157351732254028, "learning_rate": 1.874319229157939e-05, "loss": 1.3395, "step": 751 }, { "epoch": 0.31503979891076667, "grad_norm": 0.5872085690498352, "learning_rate": 1.8741516547968162e-05, "loss": 1.4568, "step": 752 }, { "epoch": 0.3154587348135735, "grad_norm": 0.6481055021286011, "learning_rate": 1.8739840804356936e-05, "loss": 1.466, "step": 753 }, { "epoch": 0.3158776707163804, "grad_norm": 0.5024817585945129, "learning_rate": 1.8738165060745707e-05, "loss": 1.4321, "step": 754 }, { "epoch": 0.31629660661918724, "grad_norm": 0.817737340927124, "learning_rate": 1.873648931713448e-05, "loss": 1.3119, "step": 755 }, { "epoch": 0.31671554252199413, "grad_norm": 0.5730132460594177, "learning_rate": 1.8734813573523252e-05, "loss": 1.4508, "step": 756 }, { "epoch": 0.317134478424801, "grad_norm": 0.7577594518661499, "learning_rate": 1.8733137829912026e-05, "loss": 1.3521, "step": 757 }, { "epoch": 0.31755341432760786, "grad_norm": 0.6062861680984497, "learning_rate": 1.8731462086300797e-05, "loss": 1.384, "step": 758 }, { "epoch": 0.31797235023041476, "grad_norm": 0.7353479266166687, "learning_rate": 1.872978634268957e-05, "loss": 1.2669, "step": 759 }, { "epoch": 0.3183912861332216, "grad_norm": 0.7415457963943481, "learning_rate": 1.872811059907834e-05, "loss": 1.3057, "step": 760 }, { "epoch": 0.3188102220360285, "grad_norm": 0.7072665691375732, "learning_rate": 1.8726434855467116e-05, "loss": 1.3939, "step": 761 }, { "epoch": 0.3192291579388354, "grad_norm": 0.6156973838806152, "learning_rate": 1.8724759111855886e-05, "loss": 1.444, "step": 762 }, { "epoch": 0.3196480938416422, "grad_norm": 0.8771636486053467, "learning_rate": 1.872308336824466e-05, "loss": 1.3528, "step": 763 }, { "epoch": 0.3200670297444491, "grad_norm": 0.7313105463981628, "learning_rate": 1.872140762463343e-05, "loss": 1.403, "step": 764 }, { "epoch": 0.32048596564725595, "grad_norm": 0.8612370491027832, "learning_rate": 1.8719731881022205e-05, "loss": 1.2753, "step": 765 }, { "epoch": 0.32090490155006285, "grad_norm": 0.7663282155990601, "learning_rate": 1.871805613741098e-05, "loss": 1.2537, "step": 766 }, { "epoch": 0.3213238374528697, "grad_norm": 0.6050071716308594, "learning_rate": 1.871638039379975e-05, "loss": 1.2666, "step": 767 }, { "epoch": 0.3217427733556766, "grad_norm": 0.878713846206665, "learning_rate": 1.871470465018852e-05, "loss": 1.2472, "step": 768 }, { "epoch": 0.3221617092584835, "grad_norm": 0.5855206251144409, "learning_rate": 1.8713028906577295e-05, "loss": 1.3284, "step": 769 }, { "epoch": 0.3225806451612903, "grad_norm": 0.6722334623336792, "learning_rate": 1.871135316296607e-05, "loss": 1.3594, "step": 770 }, { "epoch": 0.3229995810640972, "grad_norm": 0.5793231725692749, "learning_rate": 1.870967741935484e-05, "loss": 1.3275, "step": 771 }, { "epoch": 0.32341851696690405, "grad_norm": 0.604360818862915, "learning_rate": 1.870800167574361e-05, "loss": 1.385, "step": 772 }, { "epoch": 0.32383745286971094, "grad_norm": 0.6285070776939392, "learning_rate": 1.8706325932132385e-05, "loss": 1.3477, "step": 773 }, { "epoch": 0.3242563887725178, "grad_norm": 0.637465238571167, "learning_rate": 1.870465018852116e-05, "loss": 1.3904, "step": 774 }, { "epoch": 0.3246753246753247, "grad_norm": 0.6604148149490356, "learning_rate": 1.870297444490993e-05, "loss": 1.4409, "step": 775 }, { "epoch": 0.32509426057813157, "grad_norm": 0.5733173489570618, "learning_rate": 1.8701298701298704e-05, "loss": 1.4067, "step": 776 }, { "epoch": 0.3255131964809384, "grad_norm": 0.6333217620849609, "learning_rate": 1.8699622957687475e-05, "loss": 1.3755, "step": 777 }, { "epoch": 0.3259321323837453, "grad_norm": 0.5488452315330505, "learning_rate": 1.869794721407625e-05, "loss": 1.3702, "step": 778 }, { "epoch": 0.32635106828655214, "grad_norm": 0.501512885093689, "learning_rate": 1.869627147046502e-05, "loss": 1.354, "step": 779 }, { "epoch": 0.32677000418935903, "grad_norm": 0.6487094163894653, "learning_rate": 1.8694595726853794e-05, "loss": 1.436, "step": 780 }, { "epoch": 0.3271889400921659, "grad_norm": 0.6414726972579956, "learning_rate": 1.8692919983242564e-05, "loss": 1.3531, "step": 781 }, { "epoch": 0.32760787599497276, "grad_norm": 0.6292533278465271, "learning_rate": 1.869124423963134e-05, "loss": 1.3462, "step": 782 }, { "epoch": 0.32802681189777966, "grad_norm": 0.593009889125824, "learning_rate": 1.868956849602011e-05, "loss": 1.3921, "step": 783 }, { "epoch": 0.3284457478005865, "grad_norm": 0.8031853437423706, "learning_rate": 1.8687892752408883e-05, "loss": 1.3397, "step": 784 }, { "epoch": 0.3288646837033934, "grad_norm": 0.6368310451507568, "learning_rate": 1.8686217008797654e-05, "loss": 1.3801, "step": 785 }, { "epoch": 0.32928361960620023, "grad_norm": 0.540608286857605, "learning_rate": 1.8684541265186428e-05, "loss": 1.4328, "step": 786 }, { "epoch": 0.3297025555090071, "grad_norm": 0.6946301460266113, "learning_rate": 1.86828655215752e-05, "loss": 1.3398, "step": 787 }, { "epoch": 0.330121491411814, "grad_norm": 0.57708340883255, "learning_rate": 1.8681189777963973e-05, "loss": 1.3537, "step": 788 }, { "epoch": 0.33054042731462085, "grad_norm": 0.647994875907898, "learning_rate": 1.8679514034352747e-05, "loss": 1.4367, "step": 789 }, { "epoch": 0.33095936321742775, "grad_norm": 0.7245671153068542, "learning_rate": 1.8677838290741518e-05, "loss": 1.4373, "step": 790 }, { "epoch": 0.3313782991202346, "grad_norm": 0.5863420963287354, "learning_rate": 1.867616254713029e-05, "loss": 1.3749, "step": 791 }, { "epoch": 0.3317972350230415, "grad_norm": 0.5827834010124207, "learning_rate": 1.8674486803519063e-05, "loss": 1.4547, "step": 792 }, { "epoch": 0.3322161709258483, "grad_norm": 0.61444091796875, "learning_rate": 1.8672811059907837e-05, "loss": 1.4826, "step": 793 }, { "epoch": 0.3326351068286552, "grad_norm": 0.7494825124740601, "learning_rate": 1.8671135316296608e-05, "loss": 1.3186, "step": 794 }, { "epoch": 0.3330540427314621, "grad_norm": 0.708984375, "learning_rate": 1.866945957268538e-05, "loss": 1.3216, "step": 795 }, { "epoch": 0.33347297863426895, "grad_norm": 0.7570633888244629, "learning_rate": 1.8667783829074153e-05, "loss": 1.2755, "step": 796 }, { "epoch": 0.33389191453707584, "grad_norm": 0.6864930987358093, "learning_rate": 1.8666108085462927e-05, "loss": 1.5026, "step": 797 }, { "epoch": 0.3343108504398827, "grad_norm": 0.7167800068855286, "learning_rate": 1.86644323418517e-05, "loss": 1.417, "step": 798 }, { "epoch": 0.3347297863426896, "grad_norm": 0.6132422089576721, "learning_rate": 1.866275659824047e-05, "loss": 1.3885, "step": 799 }, { "epoch": 0.33514872224549647, "grad_norm": 0.496698796749115, "learning_rate": 1.8661080854629242e-05, "loss": 1.3729, "step": 800 }, { "epoch": 0.3355676581483033, "grad_norm": 0.718532383441925, "learning_rate": 1.8659405111018016e-05, "loss": 1.391, "step": 801 }, { "epoch": 0.3359865940511102, "grad_norm": 0.7083394527435303, "learning_rate": 1.8657729367406787e-05, "loss": 1.3375, "step": 802 }, { "epoch": 0.33640552995391704, "grad_norm": 0.6132792830467224, "learning_rate": 1.865605362379556e-05, "loss": 1.4201, "step": 803 }, { "epoch": 0.33682446585672393, "grad_norm": 0.7242376804351807, "learning_rate": 1.8654377880184332e-05, "loss": 1.4025, "step": 804 }, { "epoch": 0.33724340175953077, "grad_norm": 0.6561216711997986, "learning_rate": 1.8652702136573106e-05, "loss": 1.2498, "step": 805 }, { "epoch": 0.33766233766233766, "grad_norm": 0.6856805086135864, "learning_rate": 1.8651026392961877e-05, "loss": 1.3054, "step": 806 }, { "epoch": 0.33808127356514456, "grad_norm": 0.7083545923233032, "learning_rate": 1.864935064935065e-05, "loss": 1.4073, "step": 807 }, { "epoch": 0.3385002094679514, "grad_norm": 0.6021366119384766, "learning_rate": 1.8647674905739425e-05, "loss": 1.4361, "step": 808 }, { "epoch": 0.3389191453707583, "grad_norm": 0.5841922760009766, "learning_rate": 1.8645999162128196e-05, "loss": 1.4091, "step": 809 }, { "epoch": 0.33933808127356513, "grad_norm": 0.7605058550834656, "learning_rate": 1.8644323418516967e-05, "loss": 1.4554, "step": 810 }, { "epoch": 0.339757017176372, "grad_norm": 0.6625474095344543, "learning_rate": 1.864264767490574e-05, "loss": 1.3343, "step": 811 }, { "epoch": 0.34017595307917886, "grad_norm": 0.5613833665847778, "learning_rate": 1.8640971931294515e-05, "loss": 1.3195, "step": 812 }, { "epoch": 0.34059488898198576, "grad_norm": 0.7579832673072815, "learning_rate": 1.8639296187683286e-05, "loss": 1.2687, "step": 813 }, { "epoch": 0.34101382488479265, "grad_norm": 0.6240825653076172, "learning_rate": 1.8637620444072056e-05, "loss": 1.3975, "step": 814 }, { "epoch": 0.3414327607875995, "grad_norm": 0.669330894947052, "learning_rate": 1.863594470046083e-05, "loss": 1.3588, "step": 815 }, { "epoch": 0.3418516966904064, "grad_norm": 1.4403901100158691, "learning_rate": 1.8634268956849605e-05, "loss": 1.3911, "step": 816 }, { "epoch": 0.3422706325932132, "grad_norm": 0.5918375253677368, "learning_rate": 1.8632593213238375e-05, "loss": 1.4409, "step": 817 }, { "epoch": 0.3426895684960201, "grad_norm": 0.8068619966506958, "learning_rate": 1.8630917469627146e-05, "loss": 1.373, "step": 818 }, { "epoch": 0.34310850439882695, "grad_norm": 0.6585489511489868, "learning_rate": 1.862924172601592e-05, "loss": 1.3883, "step": 819 }, { "epoch": 0.34352744030163385, "grad_norm": 0.7592496275901794, "learning_rate": 1.8627565982404694e-05, "loss": 1.274, "step": 820 }, { "epoch": 0.34394637620444074, "grad_norm": 0.7368906736373901, "learning_rate": 1.862589023879347e-05, "loss": 1.3069, "step": 821 }, { "epoch": 0.3443653121072476, "grad_norm": 1.1015337705612183, "learning_rate": 1.862421449518224e-05, "loss": 1.359, "step": 822 }, { "epoch": 0.3447842480100545, "grad_norm": 1.0174856185913086, "learning_rate": 1.862253875157101e-05, "loss": 1.3323, "step": 823 }, { "epoch": 0.3452031839128613, "grad_norm": 0.5378293991088867, "learning_rate": 1.8620863007959784e-05, "loss": 1.363, "step": 824 }, { "epoch": 0.3456221198156682, "grad_norm": 0.5914802551269531, "learning_rate": 1.8619187264348558e-05, "loss": 1.4108, "step": 825 }, { "epoch": 0.3460410557184751, "grad_norm": 0.7762312889099121, "learning_rate": 1.861751152073733e-05, "loss": 1.5178, "step": 826 }, { "epoch": 0.34645999162128194, "grad_norm": 0.5453881025314331, "learning_rate": 1.86158357771261e-05, "loss": 1.2591, "step": 827 }, { "epoch": 0.34687892752408883, "grad_norm": 0.8273909091949463, "learning_rate": 1.8614160033514874e-05, "loss": 1.4152, "step": 828 }, { "epoch": 0.34729786342689567, "grad_norm": 0.619732677936554, "learning_rate": 1.8612484289903648e-05, "loss": 1.3843, "step": 829 }, { "epoch": 0.34771679932970256, "grad_norm": 0.8301693797111511, "learning_rate": 1.861080854629242e-05, "loss": 1.3134, "step": 830 }, { "epoch": 0.3481357352325094, "grad_norm": 0.5382381081581116, "learning_rate": 1.8609132802681193e-05, "loss": 1.3369, "step": 831 }, { "epoch": 0.3485546711353163, "grad_norm": 0.6819462776184082, "learning_rate": 1.8607457059069964e-05, "loss": 1.3153, "step": 832 }, { "epoch": 0.3489736070381232, "grad_norm": 0.5813642144203186, "learning_rate": 1.8605781315458734e-05, "loss": 1.3567, "step": 833 }, { "epoch": 0.34939254294093003, "grad_norm": 0.5303306579589844, "learning_rate": 1.860410557184751e-05, "loss": 1.3297, "step": 834 }, { "epoch": 0.3498114788437369, "grad_norm": 0.7988172769546509, "learning_rate": 1.8602429828236283e-05, "loss": 1.3171, "step": 835 }, { "epoch": 0.35023041474654376, "grad_norm": 0.6038556694984436, "learning_rate": 1.8600754084625053e-05, "loss": 1.4674, "step": 836 }, { "epoch": 0.35064935064935066, "grad_norm": 0.7679703235626221, "learning_rate": 1.8599078341013824e-05, "loss": 1.3359, "step": 837 }, { "epoch": 0.3510682865521575, "grad_norm": 0.5809141993522644, "learning_rate": 1.8597402597402598e-05, "loss": 1.3567, "step": 838 }, { "epoch": 0.3514872224549644, "grad_norm": 0.7988621592521667, "learning_rate": 1.8595726853791372e-05, "loss": 1.3453, "step": 839 }, { "epoch": 0.3519061583577713, "grad_norm": 0.5147368907928467, "learning_rate": 1.8594051110180143e-05, "loss": 1.4187, "step": 840 }, { "epoch": 0.3523250942605781, "grad_norm": 0.8276616334915161, "learning_rate": 1.8592375366568917e-05, "loss": 1.3438, "step": 841 }, { "epoch": 0.352744030163385, "grad_norm": 0.630969762802124, "learning_rate": 1.8590699622957688e-05, "loss": 1.3271, "step": 842 }, { "epoch": 0.35316296606619185, "grad_norm": 0.823090136051178, "learning_rate": 1.8589023879346462e-05, "loss": 1.3266, "step": 843 }, { "epoch": 0.35358190196899875, "grad_norm": 0.6593233346939087, "learning_rate": 1.8587348135735236e-05, "loss": 1.2582, "step": 844 }, { "epoch": 0.35400083787180564, "grad_norm": 0.5821310877799988, "learning_rate": 1.8585672392124007e-05, "loss": 1.3739, "step": 845 }, { "epoch": 0.3544197737746125, "grad_norm": 0.6901243329048157, "learning_rate": 1.8583996648512778e-05, "loss": 1.4388, "step": 846 }, { "epoch": 0.3548387096774194, "grad_norm": 0.521477460861206, "learning_rate": 1.8582320904901552e-05, "loss": 1.4263, "step": 847 }, { "epoch": 0.3552576455802262, "grad_norm": 0.6898438930511475, "learning_rate": 1.8580645161290326e-05, "loss": 1.3508, "step": 848 }, { "epoch": 0.3556765814830331, "grad_norm": 0.7993562817573547, "learning_rate": 1.8578969417679097e-05, "loss": 1.2651, "step": 849 }, { "epoch": 0.35609551738583994, "grad_norm": 0.5602364540100098, "learning_rate": 1.8577293674067867e-05, "loss": 1.3954, "step": 850 }, { "epoch": 0.35651445328864684, "grad_norm": 1.204590082168579, "learning_rate": 1.857561793045664e-05, "loss": 1.2695, "step": 851 }, { "epoch": 0.35693338919145373, "grad_norm": 0.7635987997055054, "learning_rate": 1.8573942186845416e-05, "loss": 1.5585, "step": 852 }, { "epoch": 0.35735232509426057, "grad_norm": 0.9088107943534851, "learning_rate": 1.8572266443234186e-05, "loss": 1.4667, "step": 853 }, { "epoch": 0.35777126099706746, "grad_norm": 0.9393168687820435, "learning_rate": 1.857059069962296e-05, "loss": 1.4196, "step": 854 }, { "epoch": 0.3581901968998743, "grad_norm": 0.7522462606430054, "learning_rate": 1.856891495601173e-05, "loss": 1.3734, "step": 855 }, { "epoch": 0.3586091328026812, "grad_norm": 0.868783712387085, "learning_rate": 1.8567239212400505e-05, "loss": 1.3904, "step": 856 }, { "epoch": 0.35902806870548803, "grad_norm": 0.721829354763031, "learning_rate": 1.8565563468789276e-05, "loss": 1.3377, "step": 857 }, { "epoch": 0.35944700460829493, "grad_norm": 0.6955874562263489, "learning_rate": 1.856388772517805e-05, "loss": 1.3995, "step": 858 }, { "epoch": 0.3598659405111018, "grad_norm": 0.7859539985656738, "learning_rate": 1.856221198156682e-05, "loss": 1.4676, "step": 859 }, { "epoch": 0.36028487641390866, "grad_norm": 0.8676955699920654, "learning_rate": 1.8560536237955595e-05, "loss": 1.3937, "step": 860 }, { "epoch": 0.36070381231671556, "grad_norm": 0.8304063081741333, "learning_rate": 1.8558860494344366e-05, "loss": 1.3601, "step": 861 }, { "epoch": 0.3611227482195224, "grad_norm": 0.6992982029914856, "learning_rate": 1.855718475073314e-05, "loss": 1.3896, "step": 862 }, { "epoch": 0.3615416841223293, "grad_norm": 0.7726747989654541, "learning_rate": 1.855550900712191e-05, "loss": 1.3639, "step": 863 }, { "epoch": 0.3619606200251362, "grad_norm": 0.6171780228614807, "learning_rate": 1.8553833263510685e-05, "loss": 1.447, "step": 864 }, { "epoch": 0.362379555927943, "grad_norm": 0.6462947130203247, "learning_rate": 1.8552157519899456e-05, "loss": 1.4144, "step": 865 }, { "epoch": 0.3627984918307499, "grad_norm": 0.6577037572860718, "learning_rate": 1.855048177628823e-05, "loss": 1.3563, "step": 866 }, { "epoch": 0.36321742773355675, "grad_norm": 0.633479118347168, "learning_rate": 1.8548806032677004e-05, "loss": 1.4013, "step": 867 }, { "epoch": 0.36363636363636365, "grad_norm": 0.5869176387786865, "learning_rate": 1.8547130289065775e-05, "loss": 1.2304, "step": 868 }, { "epoch": 0.3640552995391705, "grad_norm": 0.9644981026649475, "learning_rate": 1.8545454545454545e-05, "loss": 1.4055, "step": 869 }, { "epoch": 0.3644742354419774, "grad_norm": 0.4988062381744385, "learning_rate": 1.854377880184332e-05, "loss": 1.3402, "step": 870 }, { "epoch": 0.3648931713447843, "grad_norm": 0.6213245391845703, "learning_rate": 1.8542103058232094e-05, "loss": 1.3781, "step": 871 }, { "epoch": 0.3653121072475911, "grad_norm": 1.2338489294052124, "learning_rate": 1.8540427314620864e-05, "loss": 1.3705, "step": 872 }, { "epoch": 0.365731043150398, "grad_norm": 0.642489492893219, "learning_rate": 1.8538751571009635e-05, "loss": 1.302, "step": 873 }, { "epoch": 0.36614997905320484, "grad_norm": 0.5393372178077698, "learning_rate": 1.853707582739841e-05, "loss": 1.3932, "step": 874 }, { "epoch": 0.36656891495601174, "grad_norm": 0.702558696269989, "learning_rate": 1.8535400083787183e-05, "loss": 1.3118, "step": 875 }, { "epoch": 0.3669878508588186, "grad_norm": 0.5150250792503357, "learning_rate": 1.8533724340175954e-05, "loss": 1.3945, "step": 876 }, { "epoch": 0.36740678676162547, "grad_norm": 0.5648869872093201, "learning_rate": 1.8532048596564728e-05, "loss": 1.2966, "step": 877 }, { "epoch": 0.36782572266443236, "grad_norm": 0.507340133190155, "learning_rate": 1.85303728529535e-05, "loss": 1.3102, "step": 878 }, { "epoch": 0.3682446585672392, "grad_norm": 0.4831449091434479, "learning_rate": 1.8528697109342273e-05, "loss": 1.4016, "step": 879 }, { "epoch": 0.3686635944700461, "grad_norm": 0.5660369396209717, "learning_rate": 1.8527021365731044e-05, "loss": 1.3923, "step": 880 }, { "epoch": 0.36908253037285293, "grad_norm": 0.5805203318595886, "learning_rate": 1.8525345622119818e-05, "loss": 1.3403, "step": 881 }, { "epoch": 0.36950146627565983, "grad_norm": 0.5939772129058838, "learning_rate": 1.852366987850859e-05, "loss": 1.433, "step": 882 }, { "epoch": 0.36992040217846667, "grad_norm": 0.5323980450630188, "learning_rate": 1.8521994134897363e-05, "loss": 1.3378, "step": 883 }, { "epoch": 0.37033933808127356, "grad_norm": 0.6497474312782288, "learning_rate": 1.8520318391286134e-05, "loss": 1.3351, "step": 884 }, { "epoch": 0.37075827398408046, "grad_norm": 0.564187228679657, "learning_rate": 1.8518642647674908e-05, "loss": 1.3354, "step": 885 }, { "epoch": 0.3711772098868873, "grad_norm": 0.5568170547485352, "learning_rate": 1.8516966904063682e-05, "loss": 1.3902, "step": 886 }, { "epoch": 0.3715961457896942, "grad_norm": 0.635718584060669, "learning_rate": 1.8515291160452453e-05, "loss": 1.2659, "step": 887 }, { "epoch": 0.372015081692501, "grad_norm": 0.5702401399612427, "learning_rate": 1.8513615416841223e-05, "loss": 1.3953, "step": 888 }, { "epoch": 0.3724340175953079, "grad_norm": 0.9754594564437866, "learning_rate": 1.8511939673229997e-05, "loss": 1.523, "step": 889 }, { "epoch": 0.3728529534981148, "grad_norm": 0.6205545663833618, "learning_rate": 1.851026392961877e-05, "loss": 1.4438, "step": 890 }, { "epoch": 0.37327188940092165, "grad_norm": 0.6615620255470276, "learning_rate": 1.8508588186007542e-05, "loss": 1.3249, "step": 891 }, { "epoch": 0.37369082530372855, "grad_norm": 1.1198056936264038, "learning_rate": 1.8506912442396313e-05, "loss": 1.3237, "step": 892 }, { "epoch": 0.3741097612065354, "grad_norm": 0.4639185070991516, "learning_rate": 1.8505236698785087e-05, "loss": 1.3922, "step": 893 }, { "epoch": 0.3745286971093423, "grad_norm": 0.9922068119049072, "learning_rate": 1.850356095517386e-05, "loss": 1.4176, "step": 894 }, { "epoch": 0.3749476330121491, "grad_norm": 0.6543740034103394, "learning_rate": 1.8501885211562632e-05, "loss": 1.3416, "step": 895 }, { "epoch": 0.375366568914956, "grad_norm": 0.6506433486938477, "learning_rate": 1.8500209467951403e-05, "loss": 1.3429, "step": 896 }, { "epoch": 0.3757855048177629, "grad_norm": 0.6528995633125305, "learning_rate": 1.8498533724340177e-05, "loss": 1.3, "step": 897 }, { "epoch": 0.37620444072056974, "grad_norm": 0.5251516103744507, "learning_rate": 1.849685798072895e-05, "loss": 1.3076, "step": 898 }, { "epoch": 0.37662337662337664, "grad_norm": 0.6646214723587036, "learning_rate": 1.8495182237117722e-05, "loss": 1.3381, "step": 899 }, { "epoch": 0.3770423125261835, "grad_norm": 0.7112960815429688, "learning_rate": 1.8493506493506496e-05, "loss": 1.342, "step": 900 }, { "epoch": 0.37746124842899037, "grad_norm": 0.6115846037864685, "learning_rate": 1.8491830749895267e-05, "loss": 1.3231, "step": 901 }, { "epoch": 0.3778801843317972, "grad_norm": 0.5398994088172913, "learning_rate": 1.849015500628404e-05, "loss": 1.3294, "step": 902 }, { "epoch": 0.3782991202346041, "grad_norm": 0.6577754616737366, "learning_rate": 1.848847926267281e-05, "loss": 1.4425, "step": 903 }, { "epoch": 0.378718056137411, "grad_norm": 0.6344985365867615, "learning_rate": 1.8486803519061586e-05, "loss": 1.4265, "step": 904 }, { "epoch": 0.37913699204021784, "grad_norm": 0.6111234426498413, "learning_rate": 1.8485127775450356e-05, "loss": 1.358, "step": 905 }, { "epoch": 0.37955592794302473, "grad_norm": 0.7081183195114136, "learning_rate": 1.848345203183913e-05, "loss": 1.3682, "step": 906 }, { "epoch": 0.37997486384583157, "grad_norm": 0.5750409364700317, "learning_rate": 1.84817762882279e-05, "loss": 1.2761, "step": 907 }, { "epoch": 0.38039379974863846, "grad_norm": 0.5604552030563354, "learning_rate": 1.8480100544616675e-05, "loss": 1.3865, "step": 908 }, { "epoch": 0.38081273565144536, "grad_norm": 0.5597730875015259, "learning_rate": 1.847842480100545e-05, "loss": 1.4277, "step": 909 }, { "epoch": 0.3812316715542522, "grad_norm": 0.5526629686355591, "learning_rate": 1.847674905739422e-05, "loss": 1.2744, "step": 910 }, { "epoch": 0.3816506074570591, "grad_norm": 0.5272534489631653, "learning_rate": 1.847507331378299e-05, "loss": 1.3739, "step": 911 }, { "epoch": 0.3820695433598659, "grad_norm": 0.7306801676750183, "learning_rate": 1.8473397570171765e-05, "loss": 1.2646, "step": 912 }, { "epoch": 0.3824884792626728, "grad_norm": 0.8041632771492004, "learning_rate": 1.847172182656054e-05, "loss": 1.3597, "step": 913 }, { "epoch": 0.38290741516547966, "grad_norm": 0.6282241344451904, "learning_rate": 1.847004608294931e-05, "loss": 1.2337, "step": 914 }, { "epoch": 0.38332635106828655, "grad_norm": 0.6238358020782471, "learning_rate": 1.846837033933808e-05, "loss": 1.4054, "step": 915 }, { "epoch": 0.38374528697109345, "grad_norm": 0.701452910900116, "learning_rate": 1.8466694595726855e-05, "loss": 1.2824, "step": 916 }, { "epoch": 0.3841642228739003, "grad_norm": 0.7733535170555115, "learning_rate": 1.846501885211563e-05, "loss": 1.251, "step": 917 }, { "epoch": 0.3845831587767072, "grad_norm": 0.5265078544616699, "learning_rate": 1.84633431085044e-05, "loss": 1.4453, "step": 918 }, { "epoch": 0.385002094679514, "grad_norm": 0.452823668718338, "learning_rate": 1.8461667364893174e-05, "loss": 1.3404, "step": 919 }, { "epoch": 0.3854210305823209, "grad_norm": 0.8962199091911316, "learning_rate": 1.8459991621281945e-05, "loss": 1.323, "step": 920 }, { "epoch": 0.38583996648512775, "grad_norm": 0.6026387810707092, "learning_rate": 1.845831587767072e-05, "loss": 1.3102, "step": 921 }, { "epoch": 0.38625890238793464, "grad_norm": 0.8394970297813416, "learning_rate": 1.8456640134059493e-05, "loss": 1.3595, "step": 922 }, { "epoch": 0.38667783829074154, "grad_norm": 0.5857053399085999, "learning_rate": 1.8454964390448264e-05, "loss": 1.4405, "step": 923 }, { "epoch": 0.3870967741935484, "grad_norm": 0.987432599067688, "learning_rate": 1.8453288646837034e-05, "loss": 1.4044, "step": 924 }, { "epoch": 0.38751571009635527, "grad_norm": 0.5757207870483398, "learning_rate": 1.845161290322581e-05, "loss": 1.5337, "step": 925 }, { "epoch": 0.3879346459991621, "grad_norm": 1.0578022003173828, "learning_rate": 1.8449937159614583e-05, "loss": 1.3209, "step": 926 }, { "epoch": 0.388353581901969, "grad_norm": 0.5220828652381897, "learning_rate": 1.8448261416003353e-05, "loss": 1.3895, "step": 927 }, { "epoch": 0.3887725178047759, "grad_norm": 1.179112434387207, "learning_rate": 1.8446585672392124e-05, "loss": 1.3342, "step": 928 }, { "epoch": 0.38919145370758274, "grad_norm": 0.646702229976654, "learning_rate": 1.8444909928780898e-05, "loss": 1.3178, "step": 929 }, { "epoch": 0.38961038961038963, "grad_norm": 0.8807336091995239, "learning_rate": 1.844323418516967e-05, "loss": 1.2941, "step": 930 }, { "epoch": 0.39002932551319647, "grad_norm": 0.5306640267372131, "learning_rate": 1.8441558441558443e-05, "loss": 1.3575, "step": 931 }, { "epoch": 0.39044826141600336, "grad_norm": 0.99175626039505, "learning_rate": 1.8439882697947217e-05, "loss": 1.3536, "step": 932 }, { "epoch": 0.3908671973188102, "grad_norm": 0.5181053280830383, "learning_rate": 1.8438206954335988e-05, "loss": 1.3834, "step": 933 }, { "epoch": 0.3912861332216171, "grad_norm": 0.5490570664405823, "learning_rate": 1.843653121072476e-05, "loss": 1.3659, "step": 934 }, { "epoch": 0.391705069124424, "grad_norm": 0.9038254022598267, "learning_rate": 1.8434855467113533e-05, "loss": 1.4163, "step": 935 }, { "epoch": 0.3921240050272308, "grad_norm": 0.8316247463226318, "learning_rate": 1.8433179723502307e-05, "loss": 1.2176, "step": 936 }, { "epoch": 0.3925429409300377, "grad_norm": 0.9821082353591919, "learning_rate": 1.8431503979891078e-05, "loss": 1.2935, "step": 937 }, { "epoch": 0.39296187683284456, "grad_norm": 0.8063921332359314, "learning_rate": 1.842982823627985e-05, "loss": 1.4265, "step": 938 }, { "epoch": 0.39338081273565145, "grad_norm": 0.9902571439743042, "learning_rate": 1.8428152492668622e-05, "loss": 1.3794, "step": 939 }, { "epoch": 0.3937997486384583, "grad_norm": 0.5868860483169556, "learning_rate": 1.8426476749057397e-05, "loss": 1.3488, "step": 940 }, { "epoch": 0.3942186845412652, "grad_norm": 1.5364601612091064, "learning_rate": 1.8424801005446167e-05, "loss": 1.2805, "step": 941 }, { "epoch": 0.3946376204440721, "grad_norm": 0.5772972106933594, "learning_rate": 1.842312526183494e-05, "loss": 1.3529, "step": 942 }, { "epoch": 0.3950565563468789, "grad_norm": 0.7915850877761841, "learning_rate": 1.8421449518223712e-05, "loss": 1.4225, "step": 943 }, { "epoch": 0.3954754922496858, "grad_norm": 0.5602070689201355, "learning_rate": 1.8419773774612486e-05, "loss": 1.3962, "step": 944 }, { "epoch": 0.39589442815249265, "grad_norm": 0.6039633750915527, "learning_rate": 1.841809803100126e-05, "loss": 1.4176, "step": 945 }, { "epoch": 0.39631336405529954, "grad_norm": 0.7987331748008728, "learning_rate": 1.841642228739003e-05, "loss": 1.3436, "step": 946 }, { "epoch": 0.3967322999581064, "grad_norm": 0.572047233581543, "learning_rate": 1.8414746543778802e-05, "loss": 1.31, "step": 947 }, { "epoch": 0.3971512358609133, "grad_norm": 0.5866878032684326, "learning_rate": 1.8413070800167576e-05, "loss": 1.3156, "step": 948 }, { "epoch": 0.39757017176372017, "grad_norm": 0.6000043749809265, "learning_rate": 1.841139505655635e-05, "loss": 1.3694, "step": 949 }, { "epoch": 0.397989107666527, "grad_norm": 0.5844922661781311, "learning_rate": 1.840971931294512e-05, "loss": 1.3165, "step": 950 }, { "epoch": 0.3984080435693339, "grad_norm": 0.5939188599586487, "learning_rate": 1.840804356933389e-05, "loss": 1.4149, "step": 951 }, { "epoch": 0.39882697947214074, "grad_norm": 0.7252548933029175, "learning_rate": 1.8406367825722666e-05, "loss": 1.3719, "step": 952 }, { "epoch": 0.39924591537494764, "grad_norm": 0.5265613794326782, "learning_rate": 1.840469208211144e-05, "loss": 1.4457, "step": 953 }, { "epoch": 0.39966485127775453, "grad_norm": 0.8471786379814148, "learning_rate": 1.840301633850021e-05, "loss": 1.3068, "step": 954 }, { "epoch": 0.40008378718056137, "grad_norm": 0.5706002116203308, "learning_rate": 1.8401340594888985e-05, "loss": 1.3501, "step": 955 }, { "epoch": 0.40050272308336826, "grad_norm": 0.9383030533790588, "learning_rate": 1.8399664851277756e-05, "loss": 1.2473, "step": 956 }, { "epoch": 0.4009216589861751, "grad_norm": 0.5859097838401794, "learning_rate": 1.839798910766653e-05, "loss": 1.3109, "step": 957 }, { "epoch": 0.401340594888982, "grad_norm": 0.8028270602226257, "learning_rate": 1.83963133640553e-05, "loss": 1.4197, "step": 958 }, { "epoch": 0.40175953079178883, "grad_norm": 0.5209934115409851, "learning_rate": 1.8394637620444075e-05, "loss": 1.3811, "step": 959 }, { "epoch": 0.4021784666945957, "grad_norm": 0.6815239191055298, "learning_rate": 1.8392961876832845e-05, "loss": 1.3674, "step": 960 }, { "epoch": 0.4025974025974026, "grad_norm": 0.5413818359375, "learning_rate": 1.8391286133221616e-05, "loss": 1.3582, "step": 961 }, { "epoch": 0.40301633850020946, "grad_norm": 0.6124288439750671, "learning_rate": 1.838961038961039e-05, "loss": 1.2951, "step": 962 }, { "epoch": 0.40343527440301635, "grad_norm": 0.6622788906097412, "learning_rate": 1.8387934645999164e-05, "loss": 1.2459, "step": 963 }, { "epoch": 0.4038542103058232, "grad_norm": 0.6401671767234802, "learning_rate": 1.838625890238794e-05, "loss": 1.3094, "step": 964 }, { "epoch": 0.4042731462086301, "grad_norm": 0.5091043710708618, "learning_rate": 1.838458315877671e-05, "loss": 1.3991, "step": 965 }, { "epoch": 0.4046920821114369, "grad_norm": 0.6116538643836975, "learning_rate": 1.838290741516548e-05, "loss": 1.3644, "step": 966 }, { "epoch": 0.4051110180142438, "grad_norm": 0.5258737206459045, "learning_rate": 1.8381231671554254e-05, "loss": 1.3097, "step": 967 }, { "epoch": 0.4055299539170507, "grad_norm": 0.5490679740905762, "learning_rate": 1.8379555927943028e-05, "loss": 1.2985, "step": 968 }, { "epoch": 0.40594888981985755, "grad_norm": 0.5685926079750061, "learning_rate": 1.83778801843318e-05, "loss": 1.3255, "step": 969 }, { "epoch": 0.40636782572266444, "grad_norm": 0.5925977230072021, "learning_rate": 1.837620444072057e-05, "loss": 1.3693, "step": 970 }, { "epoch": 0.4067867616254713, "grad_norm": 0.5333212614059448, "learning_rate": 1.8374528697109344e-05, "loss": 1.3521, "step": 971 }, { "epoch": 0.4072056975282782, "grad_norm": 0.5770822763442993, "learning_rate": 1.8372852953498118e-05, "loss": 1.263, "step": 972 }, { "epoch": 0.40762463343108507, "grad_norm": 0.6561490893363953, "learning_rate": 1.837117720988689e-05, "loss": 1.3494, "step": 973 }, { "epoch": 0.4080435693338919, "grad_norm": 0.5791774392127991, "learning_rate": 1.836950146627566e-05, "loss": 1.422, "step": 974 }, { "epoch": 0.4084625052366988, "grad_norm": 0.6861572861671448, "learning_rate": 1.8367825722664433e-05, "loss": 1.2504, "step": 975 }, { "epoch": 0.40888144113950564, "grad_norm": 0.5480408072471619, "learning_rate": 1.8366149979053208e-05, "loss": 1.3194, "step": 976 }, { "epoch": 0.40930037704231254, "grad_norm": 0.6359973549842834, "learning_rate": 1.836447423544198e-05, "loss": 1.2548, "step": 977 }, { "epoch": 0.4097193129451194, "grad_norm": 0.5910494327545166, "learning_rate": 1.8362798491830752e-05, "loss": 1.2948, "step": 978 }, { "epoch": 0.41013824884792627, "grad_norm": 0.5293029546737671, "learning_rate": 1.8361122748219523e-05, "loss": 1.3814, "step": 979 }, { "epoch": 0.41055718475073316, "grad_norm": 0.5520710349082947, "learning_rate": 1.8359447004608297e-05, "loss": 1.4673, "step": 980 }, { "epoch": 0.41097612065354, "grad_norm": 0.7098038196563721, "learning_rate": 1.8357771260997068e-05, "loss": 1.3521, "step": 981 }, { "epoch": 0.4113950565563469, "grad_norm": 0.6136484146118164, "learning_rate": 1.8356095517385842e-05, "loss": 1.3526, "step": 982 }, { "epoch": 0.41181399245915373, "grad_norm": 0.6027216911315918, "learning_rate": 1.8354419773774613e-05, "loss": 1.2975, "step": 983 }, { "epoch": 0.4122329283619606, "grad_norm": 0.5980489253997803, "learning_rate": 1.8352744030163387e-05, "loss": 1.3214, "step": 984 }, { "epoch": 0.41265186426476747, "grad_norm": 0.6312512755393982, "learning_rate": 1.8351068286552158e-05, "loss": 1.3157, "step": 985 }, { "epoch": 0.41307080016757436, "grad_norm": 0.9795253872871399, "learning_rate": 1.8349392542940932e-05, "loss": 1.3644, "step": 986 }, { "epoch": 0.41348973607038125, "grad_norm": 0.5261685252189636, "learning_rate": 1.8347716799329706e-05, "loss": 1.3392, "step": 987 }, { "epoch": 0.4139086719731881, "grad_norm": 0.6193227767944336, "learning_rate": 1.8346041055718477e-05, "loss": 1.3444, "step": 988 }, { "epoch": 0.414327607875995, "grad_norm": 0.4504217505455017, "learning_rate": 1.8344365312107248e-05, "loss": 1.2957, "step": 989 }, { "epoch": 0.4147465437788018, "grad_norm": 0.6061900854110718, "learning_rate": 1.834268956849602e-05, "loss": 1.3048, "step": 990 }, { "epoch": 0.4151654796816087, "grad_norm": 0.5700473189353943, "learning_rate": 1.8341013824884796e-05, "loss": 1.2925, "step": 991 }, { "epoch": 0.4155844155844156, "grad_norm": 0.5876666307449341, "learning_rate": 1.8339338081273567e-05, "loss": 1.3248, "step": 992 }, { "epoch": 0.41600335148722245, "grad_norm": 0.5364834666252136, "learning_rate": 1.8337662337662337e-05, "loss": 1.302, "step": 993 }, { "epoch": 0.41642228739002934, "grad_norm": 0.7233411073684692, "learning_rate": 1.833598659405111e-05, "loss": 1.2268, "step": 994 }, { "epoch": 0.4168412232928362, "grad_norm": 0.5373887419700623, "learning_rate": 1.8334310850439886e-05, "loss": 1.2544, "step": 995 }, { "epoch": 0.4172601591956431, "grad_norm": 0.6809514164924622, "learning_rate": 1.8332635106828656e-05, "loss": 1.3745, "step": 996 }, { "epoch": 0.4176790950984499, "grad_norm": 0.4963758587837219, "learning_rate": 1.833095936321743e-05, "loss": 1.3757, "step": 997 }, { "epoch": 0.4180980310012568, "grad_norm": 0.6156362295150757, "learning_rate": 1.83292836196062e-05, "loss": 1.3654, "step": 998 }, { "epoch": 0.4185169669040637, "grad_norm": 0.6025580167770386, "learning_rate": 1.8327607875994975e-05, "loss": 1.4092, "step": 999 }, { "epoch": 0.41893590280687054, "grad_norm": 0.4706215262413025, "learning_rate": 1.8325932132383746e-05, "loss": 1.2553, "step": 1000 }, { "epoch": 0.41935483870967744, "grad_norm": 0.6168606281280518, "learning_rate": 1.832425638877252e-05, "loss": 1.263, "step": 1001 }, { "epoch": 0.4197737746124843, "grad_norm": 0.5337375402450562, "learning_rate": 1.832258064516129e-05, "loss": 1.2473, "step": 1002 }, { "epoch": 0.42019271051529117, "grad_norm": 0.5635408759117126, "learning_rate": 1.8320904901550065e-05, "loss": 1.1962, "step": 1003 }, { "epoch": 0.420611646418098, "grad_norm": 0.5376746654510498, "learning_rate": 1.8319229157938836e-05, "loss": 1.3885, "step": 1004 }, { "epoch": 0.4210305823209049, "grad_norm": 0.5582394599914551, "learning_rate": 1.831755341432761e-05, "loss": 1.4008, "step": 1005 }, { "epoch": 0.4214495182237118, "grad_norm": 0.5136025547981262, "learning_rate": 1.831587767071638e-05, "loss": 1.4049, "step": 1006 }, { "epoch": 0.42186845412651863, "grad_norm": 0.6063160300254822, "learning_rate": 1.8314201927105155e-05, "loss": 1.3763, "step": 1007 }, { "epoch": 0.4222873900293255, "grad_norm": 0.5643933415412903, "learning_rate": 1.8312526183493925e-05, "loss": 1.2941, "step": 1008 }, { "epoch": 0.42270632593213237, "grad_norm": 0.5687242150306702, "learning_rate": 1.83108504398827e-05, "loss": 1.274, "step": 1009 }, { "epoch": 0.42312526183493926, "grad_norm": 0.5480166077613831, "learning_rate": 1.8309174696271474e-05, "loss": 1.4593, "step": 1010 }, { "epoch": 0.4235441977377461, "grad_norm": 0.5176064968109131, "learning_rate": 1.8307498952660244e-05, "loss": 1.3344, "step": 1011 }, { "epoch": 0.423963133640553, "grad_norm": 0.7011755108833313, "learning_rate": 1.8305823209049015e-05, "loss": 1.3585, "step": 1012 }, { "epoch": 0.4243820695433599, "grad_norm": 0.5866506695747375, "learning_rate": 1.830414746543779e-05, "loss": 1.4471, "step": 1013 }, { "epoch": 0.4248010054461667, "grad_norm": 0.7366320490837097, "learning_rate": 1.8302471721826563e-05, "loss": 1.2817, "step": 1014 }, { "epoch": 0.4252199413489736, "grad_norm": 0.47257664799690247, "learning_rate": 1.8300795978215334e-05, "loss": 1.4617, "step": 1015 }, { "epoch": 0.42563887725178046, "grad_norm": 0.8454380035400391, "learning_rate": 1.8299120234604105e-05, "loss": 1.2917, "step": 1016 }, { "epoch": 0.42605781315458735, "grad_norm": 0.7998992800712585, "learning_rate": 1.829744449099288e-05, "loss": 1.2522, "step": 1017 }, { "epoch": 0.42647674905739424, "grad_norm": 0.6851061582565308, "learning_rate": 1.8295768747381653e-05, "loss": 1.2284, "step": 1018 }, { "epoch": 0.4268956849602011, "grad_norm": 0.9322745203971863, "learning_rate": 1.8294093003770427e-05, "loss": 1.2665, "step": 1019 }, { "epoch": 0.427314620863008, "grad_norm": 0.5133146047592163, "learning_rate": 1.8292417260159198e-05, "loss": 1.3387, "step": 1020 }, { "epoch": 0.4277335567658148, "grad_norm": 0.6651824712753296, "learning_rate": 1.829074151654797e-05, "loss": 1.3604, "step": 1021 }, { "epoch": 0.4281524926686217, "grad_norm": 0.6780356764793396, "learning_rate": 1.8289065772936743e-05, "loss": 1.3237, "step": 1022 }, { "epoch": 0.42857142857142855, "grad_norm": 0.6781860589981079, "learning_rate": 1.8287390029325517e-05, "loss": 1.2915, "step": 1023 }, { "epoch": 0.42899036447423544, "grad_norm": 0.7052691578865051, "learning_rate": 1.8285714285714288e-05, "loss": 1.3323, "step": 1024 }, { "epoch": 0.42940930037704234, "grad_norm": 0.5380198955535889, "learning_rate": 1.828403854210306e-05, "loss": 1.2701, "step": 1025 }, { "epoch": 0.4298282362798492, "grad_norm": 1.0681602954864502, "learning_rate": 1.8282362798491833e-05, "loss": 1.2479, "step": 1026 }, { "epoch": 0.43024717218265607, "grad_norm": 0.6280472874641418, "learning_rate": 1.8280687054880603e-05, "loss": 1.3451, "step": 1027 }, { "epoch": 0.4306661080854629, "grad_norm": 0.6782708764076233, "learning_rate": 1.8279011311269378e-05, "loss": 1.2888, "step": 1028 }, { "epoch": 0.4310850439882698, "grad_norm": 0.5504584908485413, "learning_rate": 1.8277335567658148e-05, "loss": 1.3863, "step": 1029 }, { "epoch": 0.43150397989107664, "grad_norm": 0.557868242263794, "learning_rate": 1.8275659824046922e-05, "loss": 1.3399, "step": 1030 }, { "epoch": 0.43192291579388353, "grad_norm": 1.2210026979446411, "learning_rate": 1.8273984080435693e-05, "loss": 1.2104, "step": 1031 }, { "epoch": 0.4323418516966904, "grad_norm": 0.6031039357185364, "learning_rate": 1.8272308336824467e-05, "loss": 1.4665, "step": 1032 }, { "epoch": 0.43276078759949727, "grad_norm": 0.9053773283958435, "learning_rate": 1.827063259321324e-05, "loss": 1.3219, "step": 1033 }, { "epoch": 0.43317972350230416, "grad_norm": 0.7819105386734009, "learning_rate": 1.8268956849602012e-05, "loss": 1.3573, "step": 1034 }, { "epoch": 0.433598659405111, "grad_norm": 0.967070996761322, "learning_rate": 1.8267281105990783e-05, "loss": 1.4162, "step": 1035 }, { "epoch": 0.4340175953079179, "grad_norm": 1.1320526599884033, "learning_rate": 1.8265605362379557e-05, "loss": 1.4091, "step": 1036 }, { "epoch": 0.4344365312107248, "grad_norm": 0.7298519611358643, "learning_rate": 1.826392961876833e-05, "loss": 1.2992, "step": 1037 }, { "epoch": 0.4348554671135316, "grad_norm": 1.2868174314498901, "learning_rate": 1.8262253875157102e-05, "loss": 1.2175, "step": 1038 }, { "epoch": 0.4352744030163385, "grad_norm": 0.5379632711410522, "learning_rate": 1.8260578131545873e-05, "loss": 1.4073, "step": 1039 }, { "epoch": 0.43569333891914536, "grad_norm": 1.5946475267410278, "learning_rate": 1.8258902387934647e-05, "loss": 1.2777, "step": 1040 }, { "epoch": 0.43611227482195225, "grad_norm": 0.7467783093452454, "learning_rate": 1.825722664432342e-05, "loss": 1.3326, "step": 1041 }, { "epoch": 0.4365312107247591, "grad_norm": 0.8855487108230591, "learning_rate": 1.8255550900712195e-05, "loss": 1.2844, "step": 1042 }, { "epoch": 0.436950146627566, "grad_norm": 0.9139724969863892, "learning_rate": 1.8253875157100966e-05, "loss": 1.2526, "step": 1043 }, { "epoch": 0.4373690825303729, "grad_norm": 0.6316019892692566, "learning_rate": 1.8252199413489736e-05, "loss": 1.2152, "step": 1044 }, { "epoch": 0.4377880184331797, "grad_norm": 1.1355504989624023, "learning_rate": 1.825052366987851e-05, "loss": 1.3436, "step": 1045 }, { "epoch": 0.4382069543359866, "grad_norm": 0.5658217668533325, "learning_rate": 1.8248847926267285e-05, "loss": 1.2746, "step": 1046 }, { "epoch": 0.43862589023879345, "grad_norm": 1.0458660125732422, "learning_rate": 1.8247172182656055e-05, "loss": 1.2238, "step": 1047 }, { "epoch": 0.43904482614160034, "grad_norm": 0.6728708744049072, "learning_rate": 1.8245496439044826e-05, "loss": 1.2646, "step": 1048 }, { "epoch": 0.4394637620444072, "grad_norm": 0.6456686854362488, "learning_rate": 1.82438206954336e-05, "loss": 1.4044, "step": 1049 }, { "epoch": 0.4398826979472141, "grad_norm": 0.7611178755760193, "learning_rate": 1.8242144951822374e-05, "loss": 1.3145, "step": 1050 }, { "epoch": 0.44030163385002097, "grad_norm": 0.5446016192436218, "learning_rate": 1.8240469208211145e-05, "loss": 1.2648, "step": 1051 }, { "epoch": 0.4407205697528278, "grad_norm": 0.6662243604660034, "learning_rate": 1.8238793464599916e-05, "loss": 1.3399, "step": 1052 }, { "epoch": 0.4411395056556347, "grad_norm": 0.6562479138374329, "learning_rate": 1.823711772098869e-05, "loss": 1.3618, "step": 1053 }, { "epoch": 0.44155844155844154, "grad_norm": 0.5235145688056946, "learning_rate": 1.8235441977377464e-05, "loss": 1.386, "step": 1054 }, { "epoch": 0.44197737746124843, "grad_norm": 0.6828937530517578, "learning_rate": 1.8233766233766235e-05, "loss": 1.3648, "step": 1055 }, { "epoch": 0.4423963133640553, "grad_norm": 0.6108437776565552, "learning_rate": 1.823209049015501e-05, "loss": 1.3764, "step": 1056 }, { "epoch": 0.44281524926686217, "grad_norm": 0.5251436233520508, "learning_rate": 1.823041474654378e-05, "loss": 1.3468, "step": 1057 }, { "epoch": 0.44323418516966906, "grad_norm": 0.6740531921386719, "learning_rate": 1.822873900293255e-05, "loss": 1.3186, "step": 1058 }, { "epoch": 0.4436531210724759, "grad_norm": 0.5247359275817871, "learning_rate": 1.8227063259321325e-05, "loss": 1.3343, "step": 1059 }, { "epoch": 0.4440720569752828, "grad_norm": 0.821925938129425, "learning_rate": 1.82253875157101e-05, "loss": 1.224, "step": 1060 }, { "epoch": 0.44449099287808963, "grad_norm": 0.5397830009460449, "learning_rate": 1.822371177209887e-05, "loss": 1.3741, "step": 1061 }, { "epoch": 0.4449099287808965, "grad_norm": 0.5710780024528503, "learning_rate": 1.822203602848764e-05, "loss": 1.2652, "step": 1062 }, { "epoch": 0.4453288646837034, "grad_norm": 0.5801980495452881, "learning_rate": 1.8220360284876414e-05, "loss": 1.3644, "step": 1063 }, { "epoch": 0.44574780058651026, "grad_norm": 0.5152921080589294, "learning_rate": 1.821868454126519e-05, "loss": 1.3002, "step": 1064 }, { "epoch": 0.44616673648931715, "grad_norm": 0.6770956516265869, "learning_rate": 1.8217008797653963e-05, "loss": 1.3419, "step": 1065 }, { "epoch": 0.446585672392124, "grad_norm": 0.5643904209136963, "learning_rate": 1.8215333054042733e-05, "loss": 1.2847, "step": 1066 }, { "epoch": 0.4470046082949309, "grad_norm": 0.4762922525405884, "learning_rate": 1.8213657310431504e-05, "loss": 1.4463, "step": 1067 }, { "epoch": 0.4474235441977377, "grad_norm": 0.7292268872261047, "learning_rate": 1.8211981566820278e-05, "loss": 1.3816, "step": 1068 }, { "epoch": 0.4478424801005446, "grad_norm": 0.5174683928489685, "learning_rate": 1.8210305823209052e-05, "loss": 1.3471, "step": 1069 }, { "epoch": 0.4482614160033515, "grad_norm": 0.6858307719230652, "learning_rate": 1.8208630079597823e-05, "loss": 1.2831, "step": 1070 }, { "epoch": 0.44868035190615835, "grad_norm": 0.5826430320739746, "learning_rate": 1.8206954335986594e-05, "loss": 1.2377, "step": 1071 }, { "epoch": 0.44909928780896524, "grad_norm": 0.8610800504684448, "learning_rate": 1.8205278592375368e-05, "loss": 1.3182, "step": 1072 }, { "epoch": 0.4495182237117721, "grad_norm": 0.5191478133201599, "learning_rate": 1.8203602848764142e-05, "loss": 1.3731, "step": 1073 }, { "epoch": 0.449937159614579, "grad_norm": 0.625361979007721, "learning_rate": 1.8201927105152913e-05, "loss": 1.3104, "step": 1074 }, { "epoch": 0.4503560955173858, "grad_norm": 0.5182881951332092, "learning_rate": 1.8200251361541687e-05, "loss": 1.2699, "step": 1075 }, { "epoch": 0.4507750314201927, "grad_norm": 0.5343324542045593, "learning_rate": 1.8198575617930458e-05, "loss": 1.2777, "step": 1076 }, { "epoch": 0.4511939673229996, "grad_norm": 0.5854357481002808, "learning_rate": 1.8196899874319232e-05, "loss": 1.37, "step": 1077 }, { "epoch": 0.45161290322580644, "grad_norm": 0.6107653379440308, "learning_rate": 1.8195224130708003e-05, "loss": 1.2805, "step": 1078 }, { "epoch": 0.45203183912861333, "grad_norm": 0.5591204762458801, "learning_rate": 1.8193548387096777e-05, "loss": 1.3273, "step": 1079 }, { "epoch": 0.45245077503142017, "grad_norm": 0.5599054098129272, "learning_rate": 1.8191872643485547e-05, "loss": 1.383, "step": 1080 }, { "epoch": 0.45286971093422707, "grad_norm": 0.7507011294364929, "learning_rate": 1.819019689987432e-05, "loss": 1.3572, "step": 1081 }, { "epoch": 0.45328864683703396, "grad_norm": 0.5637994408607483, "learning_rate": 1.8188521156263092e-05, "loss": 1.3475, "step": 1082 }, { "epoch": 0.4537075827398408, "grad_norm": 0.5319277048110962, "learning_rate": 1.8186845412651866e-05, "loss": 1.3858, "step": 1083 }, { "epoch": 0.4541265186426477, "grad_norm": 0.48302850127220154, "learning_rate": 1.8185169669040637e-05, "loss": 1.4242, "step": 1084 }, { "epoch": 0.45454545454545453, "grad_norm": 0.7405598759651184, "learning_rate": 1.818349392542941e-05, "loss": 1.2827, "step": 1085 }, { "epoch": 0.4549643904482614, "grad_norm": 0.6391623020172119, "learning_rate": 1.8181818181818182e-05, "loss": 1.2835, "step": 1086 }, { "epoch": 0.45538332635106826, "grad_norm": 0.667966365814209, "learning_rate": 1.8180142438206956e-05, "loss": 1.3476, "step": 1087 }, { "epoch": 0.45580226225387516, "grad_norm": 0.5612936019897461, "learning_rate": 1.817846669459573e-05, "loss": 1.4179, "step": 1088 }, { "epoch": 0.45622119815668205, "grad_norm": 0.6100994944572449, "learning_rate": 1.81767909509845e-05, "loss": 1.3792, "step": 1089 }, { "epoch": 0.4566401340594889, "grad_norm": 0.5509599447250366, "learning_rate": 1.8175115207373272e-05, "loss": 1.2592, "step": 1090 }, { "epoch": 0.4570590699622958, "grad_norm": 0.6930477619171143, "learning_rate": 1.8173439463762046e-05, "loss": 1.4418, "step": 1091 }, { "epoch": 0.4574780058651026, "grad_norm": 0.5277242064476013, "learning_rate": 1.817176372015082e-05, "loss": 1.2418, "step": 1092 }, { "epoch": 0.4578969417679095, "grad_norm": 0.605899453163147, "learning_rate": 1.817008797653959e-05, "loss": 1.3442, "step": 1093 }, { "epoch": 0.45831587767071635, "grad_norm": 0.5759694576263428, "learning_rate": 1.816841223292836e-05, "loss": 1.2769, "step": 1094 }, { "epoch": 0.45873481357352325, "grad_norm": 0.676699161529541, "learning_rate": 1.8166736489317136e-05, "loss": 1.3406, "step": 1095 }, { "epoch": 0.45915374947633014, "grad_norm": 0.5942062139511108, "learning_rate": 1.816506074570591e-05, "loss": 1.3825, "step": 1096 }, { "epoch": 0.459572685379137, "grad_norm": 0.5384318828582764, "learning_rate": 1.816338500209468e-05, "loss": 1.4372, "step": 1097 }, { "epoch": 0.4599916212819439, "grad_norm": 0.6452490091323853, "learning_rate": 1.8161709258483455e-05, "loss": 1.1995, "step": 1098 }, { "epoch": 0.4604105571847507, "grad_norm": 0.7278120517730713, "learning_rate": 1.8160033514872225e-05, "loss": 1.2887, "step": 1099 }, { "epoch": 0.4608294930875576, "grad_norm": 0.5139358043670654, "learning_rate": 1.8158357771261e-05, "loss": 1.3544, "step": 1100 }, { "epoch": 0.4612484289903645, "grad_norm": 0.5915756225585938, "learning_rate": 1.815668202764977e-05, "loss": 1.3052, "step": 1101 }, { "epoch": 0.46166736489317134, "grad_norm": 0.6267953515052795, "learning_rate": 1.8155006284038544e-05, "loss": 1.2779, "step": 1102 }, { "epoch": 0.46208630079597823, "grad_norm": 0.4867702126502991, "learning_rate": 1.8153330540427315e-05, "loss": 1.3432, "step": 1103 }, { "epoch": 0.46250523669878507, "grad_norm": 0.7477414011955261, "learning_rate": 1.815165479681609e-05, "loss": 1.3504, "step": 1104 }, { "epoch": 0.46292417260159197, "grad_norm": 0.5418640375137329, "learning_rate": 1.814997905320486e-05, "loss": 1.3845, "step": 1105 }, { "epoch": 0.4633431085043988, "grad_norm": 0.6884581446647644, "learning_rate": 1.8148303309593634e-05, "loss": 1.3813, "step": 1106 }, { "epoch": 0.4637620444072057, "grad_norm": 0.47973325848579407, "learning_rate": 1.8146627565982405e-05, "loss": 1.3473, "step": 1107 }, { "epoch": 0.4641809803100126, "grad_norm": 0.6327143311500549, "learning_rate": 1.814495182237118e-05, "loss": 1.3873, "step": 1108 }, { "epoch": 0.46459991621281943, "grad_norm": 0.5946708917617798, "learning_rate": 1.814327607875995e-05, "loss": 1.4171, "step": 1109 }, { "epoch": 0.4650188521156263, "grad_norm": 0.5836149454116821, "learning_rate": 1.8141600335148724e-05, "loss": 1.3661, "step": 1110 }, { "epoch": 0.46543778801843316, "grad_norm": 0.5664911866188049, "learning_rate": 1.8139924591537498e-05, "loss": 1.3206, "step": 1111 }, { "epoch": 0.46585672392124006, "grad_norm": 0.5648526549339294, "learning_rate": 1.813824884792627e-05, "loss": 1.291, "step": 1112 }, { "epoch": 0.4662756598240469, "grad_norm": 0.5593236088752747, "learning_rate": 1.813657310431504e-05, "loss": 1.2954, "step": 1113 }, { "epoch": 0.4666945957268538, "grad_norm": 0.6017231345176697, "learning_rate": 1.8134897360703814e-05, "loss": 1.3553, "step": 1114 }, { "epoch": 0.4671135316296607, "grad_norm": 0.5916247963905334, "learning_rate": 1.8133221617092588e-05, "loss": 1.3504, "step": 1115 }, { "epoch": 0.4675324675324675, "grad_norm": 0.5841718912124634, "learning_rate": 1.813154587348136e-05, "loss": 1.3576, "step": 1116 }, { "epoch": 0.4679514034352744, "grad_norm": 0.5624353289604187, "learning_rate": 1.812987012987013e-05, "loss": 1.2994, "step": 1117 }, { "epoch": 0.46837033933808125, "grad_norm": 0.5776383280754089, "learning_rate": 1.8128194386258903e-05, "loss": 1.2497, "step": 1118 }, { "epoch": 0.46878927524088815, "grad_norm": 0.5227569341659546, "learning_rate": 1.8126518642647677e-05, "loss": 1.2978, "step": 1119 }, { "epoch": 0.46920821114369504, "grad_norm": 0.5693500638008118, "learning_rate": 1.812484289903645e-05, "loss": 1.2476, "step": 1120 }, { "epoch": 0.4696271470465019, "grad_norm": 0.5316402912139893, "learning_rate": 1.8123167155425222e-05, "loss": 1.356, "step": 1121 }, { "epoch": 0.4700460829493088, "grad_norm": 0.5823123455047607, "learning_rate": 1.8121491411813993e-05, "loss": 1.357, "step": 1122 }, { "epoch": 0.4704650188521156, "grad_norm": 0.6034800410270691, "learning_rate": 1.8119815668202767e-05, "loss": 1.4305, "step": 1123 }, { "epoch": 0.4708839547549225, "grad_norm": 0.5354906916618347, "learning_rate": 1.8118139924591538e-05, "loss": 1.3806, "step": 1124 }, { "epoch": 0.47130289065772935, "grad_norm": 0.5435880422592163, "learning_rate": 1.8116464180980312e-05, "loss": 1.3818, "step": 1125 }, { "epoch": 0.47172182656053624, "grad_norm": 0.540764570236206, "learning_rate": 1.8114788437369083e-05, "loss": 1.3036, "step": 1126 }, { "epoch": 0.47214076246334313, "grad_norm": 0.5142596364021301, "learning_rate": 1.8113112693757857e-05, "loss": 1.3244, "step": 1127 }, { "epoch": 0.47255969836614997, "grad_norm": 0.6185094714164734, "learning_rate": 1.8111436950146628e-05, "loss": 1.1574, "step": 1128 }, { "epoch": 0.47297863426895687, "grad_norm": 0.5076654553413391, "learning_rate": 1.8109761206535402e-05, "loss": 1.4598, "step": 1129 }, { "epoch": 0.4733975701717637, "grad_norm": 0.6925384402275085, "learning_rate": 1.8108085462924173e-05, "loss": 1.2539, "step": 1130 }, { "epoch": 0.4738165060745706, "grad_norm": 0.5750361680984497, "learning_rate": 1.8106409719312947e-05, "loss": 1.3353, "step": 1131 }, { "epoch": 0.47423544197737744, "grad_norm": 0.7001599669456482, "learning_rate": 1.8104733975701717e-05, "loss": 1.1343, "step": 1132 }, { "epoch": 0.47465437788018433, "grad_norm": 0.6924251914024353, "learning_rate": 1.810305823209049e-05, "loss": 1.3168, "step": 1133 }, { "epoch": 0.4750733137829912, "grad_norm": 0.5786885023117065, "learning_rate": 1.8101382488479266e-05, "loss": 1.305, "step": 1134 }, { "epoch": 0.47549224968579806, "grad_norm": 0.5598960518836975, "learning_rate": 1.8099706744868036e-05, "loss": 1.3827, "step": 1135 }, { "epoch": 0.47591118558860496, "grad_norm": 0.6162183284759521, "learning_rate": 1.8098031001256807e-05, "loss": 1.336, "step": 1136 }, { "epoch": 0.4763301214914118, "grad_norm": 0.5528692603111267, "learning_rate": 1.809635525764558e-05, "loss": 1.3069, "step": 1137 }, { "epoch": 0.4767490573942187, "grad_norm": 0.5544486045837402, "learning_rate": 1.8094679514034355e-05, "loss": 1.4149, "step": 1138 }, { "epoch": 0.47716799329702553, "grad_norm": 0.6026493310928345, "learning_rate": 1.8093003770423126e-05, "loss": 1.3589, "step": 1139 }, { "epoch": 0.4775869291998324, "grad_norm": 0.7158576846122742, "learning_rate": 1.8091328026811897e-05, "loss": 1.2462, "step": 1140 }, { "epoch": 0.4780058651026393, "grad_norm": 0.6430186629295349, "learning_rate": 1.808965228320067e-05, "loss": 1.2165, "step": 1141 }, { "epoch": 0.47842480100544615, "grad_norm": 0.6099768877029419, "learning_rate": 1.8087976539589445e-05, "loss": 1.2787, "step": 1142 }, { "epoch": 0.47884373690825305, "grad_norm": 0.5819302201271057, "learning_rate": 1.808630079597822e-05, "loss": 1.3125, "step": 1143 }, { "epoch": 0.4792626728110599, "grad_norm": 0.609936535358429, "learning_rate": 1.808462505236699e-05, "loss": 1.359, "step": 1144 }, { "epoch": 0.4796816087138668, "grad_norm": 0.6110237836837769, "learning_rate": 1.808294930875576e-05, "loss": 1.354, "step": 1145 }, { "epoch": 0.4801005446166737, "grad_norm": 0.6096034646034241, "learning_rate": 1.8081273565144535e-05, "loss": 1.3211, "step": 1146 }, { "epoch": 0.4805194805194805, "grad_norm": 0.6327634453773499, "learning_rate": 1.807959782153331e-05, "loss": 1.2609, "step": 1147 }, { "epoch": 0.4809384164222874, "grad_norm": 0.48535141348838806, "learning_rate": 1.807792207792208e-05, "loss": 1.4099, "step": 1148 }, { "epoch": 0.48135735232509425, "grad_norm": 0.7460819482803345, "learning_rate": 1.807624633431085e-05, "loss": 1.2552, "step": 1149 }, { "epoch": 0.48177628822790114, "grad_norm": 0.5781182646751404, "learning_rate": 1.8074570590699625e-05, "loss": 1.3387, "step": 1150 }, { "epoch": 0.482195224130708, "grad_norm": 0.47077783942222595, "learning_rate": 1.80728948470884e-05, "loss": 1.3174, "step": 1151 }, { "epoch": 0.48261416003351487, "grad_norm": 0.5862193703651428, "learning_rate": 1.807121910347717e-05, "loss": 1.3355, "step": 1152 }, { "epoch": 0.48303309593632177, "grad_norm": 0.681327223777771, "learning_rate": 1.8069543359865944e-05, "loss": 1.3116, "step": 1153 }, { "epoch": 0.4834520318391286, "grad_norm": 0.6501558423042297, "learning_rate": 1.8067867616254714e-05, "loss": 1.2705, "step": 1154 }, { "epoch": 0.4838709677419355, "grad_norm": 0.6103442311286926, "learning_rate": 1.8066191872643485e-05, "loss": 1.4161, "step": 1155 }, { "epoch": 0.48428990364474234, "grad_norm": 0.7739853858947754, "learning_rate": 1.806451612903226e-05, "loss": 1.2534, "step": 1156 }, { "epoch": 0.48470883954754923, "grad_norm": 0.7075815200805664, "learning_rate": 1.8062840385421033e-05, "loss": 1.3316, "step": 1157 }, { "epoch": 0.48512777545035607, "grad_norm": 0.7182810306549072, "learning_rate": 1.8061164641809804e-05, "loss": 1.2406, "step": 1158 }, { "epoch": 0.48554671135316296, "grad_norm": 0.6222896575927734, "learning_rate": 1.8059488898198575e-05, "loss": 1.232, "step": 1159 }, { "epoch": 0.48596564725596986, "grad_norm": 0.6076582074165344, "learning_rate": 1.805781315458735e-05, "loss": 1.3484, "step": 1160 }, { "epoch": 0.4863845831587767, "grad_norm": 0.8611488342285156, "learning_rate": 1.8056137410976123e-05, "loss": 1.2146, "step": 1161 }, { "epoch": 0.4868035190615836, "grad_norm": 0.5255362391471863, "learning_rate": 1.8054461667364894e-05, "loss": 1.4347, "step": 1162 }, { "epoch": 0.48722245496439043, "grad_norm": 0.8451843857765198, "learning_rate": 1.8052785923753665e-05, "loss": 1.3022, "step": 1163 }, { "epoch": 0.4876413908671973, "grad_norm": 0.6206266283988953, "learning_rate": 1.805111018014244e-05, "loss": 1.2237, "step": 1164 }, { "epoch": 0.4880603267700042, "grad_norm": 0.5774354338645935, "learning_rate": 1.8049434436531213e-05, "loss": 1.268, "step": 1165 }, { "epoch": 0.48847926267281105, "grad_norm": 0.9592013955116272, "learning_rate": 1.8047758692919987e-05, "loss": 1.2488, "step": 1166 }, { "epoch": 0.48889819857561795, "grad_norm": 0.759455144405365, "learning_rate": 1.8046082949308758e-05, "loss": 1.2773, "step": 1167 }, { "epoch": 0.4893171344784248, "grad_norm": 0.5964170694351196, "learning_rate": 1.804440720569753e-05, "loss": 1.3743, "step": 1168 }, { "epoch": 0.4897360703812317, "grad_norm": 0.7656179070472717, "learning_rate": 1.8042731462086303e-05, "loss": 1.355, "step": 1169 }, { "epoch": 0.4901550062840385, "grad_norm": 0.6207166314125061, "learning_rate": 1.8041055718475077e-05, "loss": 1.2902, "step": 1170 }, { "epoch": 0.4905739421868454, "grad_norm": 0.6878586411476135, "learning_rate": 1.8039379974863847e-05, "loss": 1.3046, "step": 1171 }, { "epoch": 0.4909928780896523, "grad_norm": 0.5206657648086548, "learning_rate": 1.8037704231252618e-05, "loss": 1.3606, "step": 1172 }, { "epoch": 0.49141181399245915, "grad_norm": 0.6583306789398193, "learning_rate": 1.8036028487641392e-05, "loss": 1.3502, "step": 1173 }, { "epoch": 0.49183074989526604, "grad_norm": 0.6136510968208313, "learning_rate": 1.8034352744030166e-05, "loss": 1.2949, "step": 1174 }, { "epoch": 0.4922496857980729, "grad_norm": 0.8145105838775635, "learning_rate": 1.8032677000418937e-05, "loss": 1.3587, "step": 1175 }, { "epoch": 0.49266862170087977, "grad_norm": 0.6916869282722473, "learning_rate": 1.803100125680771e-05, "loss": 1.3045, "step": 1176 }, { "epoch": 0.4930875576036866, "grad_norm": 0.6330479979515076, "learning_rate": 1.8029325513196482e-05, "loss": 1.3547, "step": 1177 }, { "epoch": 0.4935064935064935, "grad_norm": 0.5480479598045349, "learning_rate": 1.8027649769585256e-05, "loss": 1.3268, "step": 1178 }, { "epoch": 0.4939254294093004, "grad_norm": 0.5610688328742981, "learning_rate": 1.8025974025974027e-05, "loss": 1.341, "step": 1179 }, { "epoch": 0.49434436531210724, "grad_norm": 0.5203456282615662, "learning_rate": 1.80242982823628e-05, "loss": 1.3454, "step": 1180 }, { "epoch": 0.49476330121491413, "grad_norm": 0.5318114161491394, "learning_rate": 1.8022622538751572e-05, "loss": 1.3553, "step": 1181 }, { "epoch": 0.49518223711772097, "grad_norm": 0.7349583506584167, "learning_rate": 1.8020946795140346e-05, "loss": 1.3107, "step": 1182 }, { "epoch": 0.49560117302052786, "grad_norm": 0.5046969056129456, "learning_rate": 1.8019271051529117e-05, "loss": 1.2994, "step": 1183 }, { "epoch": 0.49602010892333476, "grad_norm": 0.6813132166862488, "learning_rate": 1.801759530791789e-05, "loss": 1.198, "step": 1184 }, { "epoch": 0.4964390448261416, "grad_norm": 0.6181411147117615, "learning_rate": 1.801591956430666e-05, "loss": 1.2702, "step": 1185 }, { "epoch": 0.4968579807289485, "grad_norm": 0.5381226539611816, "learning_rate": 1.8014243820695436e-05, "loss": 1.4557, "step": 1186 }, { "epoch": 0.49727691663175533, "grad_norm": 0.6054872870445251, "learning_rate": 1.8012568077084206e-05, "loss": 1.4159, "step": 1187 }, { "epoch": 0.4976958525345622, "grad_norm": 0.5704550743103027, "learning_rate": 1.801089233347298e-05, "loss": 1.3056, "step": 1188 }, { "epoch": 0.49811478843736906, "grad_norm": 0.6517187356948853, "learning_rate": 1.8009216589861755e-05, "loss": 1.2846, "step": 1189 }, { "epoch": 0.49853372434017595, "grad_norm": 0.5502644181251526, "learning_rate": 1.8007540846250525e-05, "loss": 1.3019, "step": 1190 }, { "epoch": 0.49895266024298285, "grad_norm": 0.8192209601402283, "learning_rate": 1.8005865102639296e-05, "loss": 1.3248, "step": 1191 }, { "epoch": 0.4993715961457897, "grad_norm": 0.6397109627723694, "learning_rate": 1.800418935902807e-05, "loss": 1.3134, "step": 1192 }, { "epoch": 0.4997905320485966, "grad_norm": 0.6563698649406433, "learning_rate": 1.8002513615416844e-05, "loss": 1.3183, "step": 1193 }, { "epoch": 0.5002094679514034, "grad_norm": 0.5266475081443787, "learning_rate": 1.8000837871805615e-05, "loss": 1.3474, "step": 1194 }, { "epoch": 0.5006284038542103, "grad_norm": 0.6310097575187683, "learning_rate": 1.7999162128194386e-05, "loss": 1.3524, "step": 1195 }, { "epoch": 0.5010473397570172, "grad_norm": 0.6334779262542725, "learning_rate": 1.799748638458316e-05, "loss": 1.2801, "step": 1196 }, { "epoch": 0.501466275659824, "grad_norm": 0.663242518901825, "learning_rate": 1.7995810640971934e-05, "loss": 1.4329, "step": 1197 }, { "epoch": 0.5018852115626309, "grad_norm": 0.5669201612472534, "learning_rate": 1.7994134897360705e-05, "loss": 1.3236, "step": 1198 }, { "epoch": 0.5023041474654378, "grad_norm": 0.6204095482826233, "learning_rate": 1.799245915374948e-05, "loss": 1.3376, "step": 1199 }, { "epoch": 0.5027230833682447, "grad_norm": 0.5199185609817505, "learning_rate": 1.799078341013825e-05, "loss": 1.3079, "step": 1200 }, { "epoch": 0.5031420192710515, "grad_norm": 0.5151832699775696, "learning_rate": 1.7989107666527024e-05, "loss": 1.3648, "step": 1201 }, { "epoch": 0.5035609551738583, "grad_norm": 0.46930187940597534, "learning_rate": 1.7987431922915795e-05, "loss": 1.2752, "step": 1202 }, { "epoch": 0.5039798910766653, "grad_norm": 0.5534581542015076, "learning_rate": 1.798575617930457e-05, "loss": 1.2502, "step": 1203 }, { "epoch": 0.5043988269794721, "grad_norm": 0.640783965587616, "learning_rate": 1.798408043569334e-05, "loss": 1.3008, "step": 1204 }, { "epoch": 0.504817762882279, "grad_norm": 0.5893279314041138, "learning_rate": 1.7982404692082114e-05, "loss": 1.3014, "step": 1205 }, { "epoch": 0.5052366987850859, "grad_norm": 0.49928784370422363, "learning_rate": 1.7980728948470884e-05, "loss": 1.3347, "step": 1206 }, { "epoch": 0.5056556346878928, "grad_norm": 0.5527677536010742, "learning_rate": 1.797905320485966e-05, "loss": 1.3459, "step": 1207 }, { "epoch": 0.5060745705906996, "grad_norm": 0.5975616574287415, "learning_rate": 1.7977377461248433e-05, "loss": 1.3116, "step": 1208 }, { "epoch": 0.5064935064935064, "grad_norm": 0.5838543176651001, "learning_rate": 1.7975701717637203e-05, "loss": 1.2198, "step": 1209 }, { "epoch": 0.5069124423963134, "grad_norm": 0.619463324546814, "learning_rate": 1.7974025974025974e-05, "loss": 1.302, "step": 1210 }, { "epoch": 0.5073313782991202, "grad_norm": 0.5463703274726868, "learning_rate": 1.7972350230414748e-05, "loss": 1.2406, "step": 1211 }, { "epoch": 0.5077503142019271, "grad_norm": 0.5434020161628723, "learning_rate": 1.7970674486803522e-05, "loss": 1.335, "step": 1212 }, { "epoch": 0.508169250104734, "grad_norm": 0.5855716466903687, "learning_rate": 1.7968998743192293e-05, "loss": 1.3243, "step": 1213 }, { "epoch": 0.5085881860075409, "grad_norm": 0.49900901317596436, "learning_rate": 1.7967322999581064e-05, "loss": 1.3723, "step": 1214 }, { "epoch": 0.5090071219103477, "grad_norm": 0.48565396666526794, "learning_rate": 1.7965647255969838e-05, "loss": 1.3522, "step": 1215 }, { "epoch": 0.5094260578131546, "grad_norm": 0.643878698348999, "learning_rate": 1.7963971512358612e-05, "loss": 1.2914, "step": 1216 }, { "epoch": 0.5098449937159615, "grad_norm": 0.46946290135383606, "learning_rate": 1.7962295768747383e-05, "loss": 1.4005, "step": 1217 }, { "epoch": 0.5102639296187683, "grad_norm": 0.5753692388534546, "learning_rate": 1.7960620025136153e-05, "loss": 1.2426, "step": 1218 }, { "epoch": 0.5106828655215752, "grad_norm": 0.49606966972351074, "learning_rate": 1.7958944281524928e-05, "loss": 1.4139, "step": 1219 }, { "epoch": 0.5111018014243821, "grad_norm": 0.599481999874115, "learning_rate": 1.7957268537913702e-05, "loss": 1.2502, "step": 1220 }, { "epoch": 0.511520737327189, "grad_norm": 0.6043007373809814, "learning_rate": 1.7955592794302472e-05, "loss": 1.3828, "step": 1221 }, { "epoch": 0.5119396732299958, "grad_norm": 0.5853987336158752, "learning_rate": 1.7953917050691247e-05, "loss": 1.4044, "step": 1222 }, { "epoch": 0.5123586091328027, "grad_norm": 0.616538405418396, "learning_rate": 1.7952241307080017e-05, "loss": 1.2093, "step": 1223 }, { "epoch": 0.5127775450356096, "grad_norm": 0.5173774361610413, "learning_rate": 1.795056556346879e-05, "loss": 1.4132, "step": 1224 }, { "epoch": 0.5131964809384164, "grad_norm": 0.5851691961288452, "learning_rate": 1.7948889819857562e-05, "loss": 1.3407, "step": 1225 }, { "epoch": 0.5136154168412232, "grad_norm": 0.545215368270874, "learning_rate": 1.7947214076246336e-05, "loss": 1.2557, "step": 1226 }, { "epoch": 0.5140343527440302, "grad_norm": 0.5817573070526123, "learning_rate": 1.7945538332635107e-05, "loss": 1.4913, "step": 1227 }, { "epoch": 0.514453288646837, "grad_norm": 0.6271103620529175, "learning_rate": 1.794386258902388e-05, "loss": 1.3123, "step": 1228 }, { "epoch": 0.5148722245496439, "grad_norm": 0.5343185067176819, "learning_rate": 1.7942186845412652e-05, "loss": 1.2736, "step": 1229 }, { "epoch": 0.5152911604524508, "grad_norm": 0.568390965461731, "learning_rate": 1.7940511101801426e-05, "loss": 1.2693, "step": 1230 }, { "epoch": 0.5157100963552577, "grad_norm": 0.8113637566566467, "learning_rate": 1.79388353581902e-05, "loss": 1.1909, "step": 1231 }, { "epoch": 0.5161290322580645, "grad_norm": 0.5547187328338623, "learning_rate": 1.793715961457897e-05, "loss": 1.3286, "step": 1232 }, { "epoch": 0.5165479681608713, "grad_norm": 0.7221224904060364, "learning_rate": 1.7935483870967742e-05, "loss": 1.2616, "step": 1233 }, { "epoch": 0.5169669040636783, "grad_norm": 0.5355010628700256, "learning_rate": 1.7933808127356516e-05, "loss": 1.2733, "step": 1234 }, { "epoch": 0.5173858399664851, "grad_norm": 0.5288854837417603, "learning_rate": 1.793213238374529e-05, "loss": 1.2773, "step": 1235 }, { "epoch": 0.517804775869292, "grad_norm": 0.6158447265625, "learning_rate": 1.793045664013406e-05, "loss": 1.2732, "step": 1236 }, { "epoch": 0.5182237117720989, "grad_norm": 0.5706437826156616, "learning_rate": 1.792878089652283e-05, "loss": 1.3005, "step": 1237 }, { "epoch": 0.5186426476749058, "grad_norm": 0.7265235185623169, "learning_rate": 1.7927105152911606e-05, "loss": 1.258, "step": 1238 }, { "epoch": 0.5190615835777126, "grad_norm": 0.59310382604599, "learning_rate": 1.792542940930038e-05, "loss": 1.2875, "step": 1239 }, { "epoch": 0.5194805194805194, "grad_norm": 0.531716525554657, "learning_rate": 1.792375366568915e-05, "loss": 1.2751, "step": 1240 }, { "epoch": 0.5198994553833264, "grad_norm": 1.1989325284957886, "learning_rate": 1.792207792207792e-05, "loss": 1.2632, "step": 1241 }, { "epoch": 0.5203183912861332, "grad_norm": 0.5530804991722107, "learning_rate": 1.7920402178466695e-05, "loss": 1.3474, "step": 1242 }, { "epoch": 0.5207373271889401, "grad_norm": 0.6528697609901428, "learning_rate": 1.791872643485547e-05, "loss": 1.2502, "step": 1243 }, { "epoch": 0.521156263091747, "grad_norm": 0.6965655088424683, "learning_rate": 1.7917050691244244e-05, "loss": 1.2548, "step": 1244 }, { "epoch": 0.5215751989945538, "grad_norm": 0.521445095539093, "learning_rate": 1.7915374947633014e-05, "loss": 1.3501, "step": 1245 }, { "epoch": 0.5219941348973607, "grad_norm": 0.7838431000709534, "learning_rate": 1.7913699204021785e-05, "loss": 1.3237, "step": 1246 }, { "epoch": 0.5224130708001675, "grad_norm": 0.5507728457450867, "learning_rate": 1.791202346041056e-05, "loss": 1.3779, "step": 1247 }, { "epoch": 0.5228320067029745, "grad_norm": 0.8786928653717041, "learning_rate": 1.7910347716799333e-05, "loss": 1.2335, "step": 1248 }, { "epoch": 0.5232509426057813, "grad_norm": 0.6260472536087036, "learning_rate": 1.7908671973188104e-05, "loss": 1.2753, "step": 1249 }, { "epoch": 0.5236698785085881, "grad_norm": 0.6856904029846191, "learning_rate": 1.7906996229576875e-05, "loss": 1.2704, "step": 1250 }, { "epoch": 0.5240888144113951, "grad_norm": 0.5970323085784912, "learning_rate": 1.790532048596565e-05, "loss": 1.3673, "step": 1251 }, { "epoch": 0.5245077503142019, "grad_norm": 0.5879629254341125, "learning_rate": 1.790364474235442e-05, "loss": 1.3472, "step": 1252 }, { "epoch": 0.5249266862170088, "grad_norm": 0.6091963648796082, "learning_rate": 1.7901968998743194e-05, "loss": 1.3109, "step": 1253 }, { "epoch": 0.5253456221198156, "grad_norm": 0.5746055841445923, "learning_rate": 1.7900293255131968e-05, "loss": 1.3595, "step": 1254 }, { "epoch": 0.5257645580226226, "grad_norm": 0.6204288005828857, "learning_rate": 1.789861751152074e-05, "loss": 1.2801, "step": 1255 }, { "epoch": 0.5261834939254294, "grad_norm": 0.5878499746322632, "learning_rate": 1.789694176790951e-05, "loss": 1.3157, "step": 1256 }, { "epoch": 0.5266024298282362, "grad_norm": 0.5726604461669922, "learning_rate": 1.7895266024298283e-05, "loss": 1.3268, "step": 1257 }, { "epoch": 0.5270213657310432, "grad_norm": 0.5824220180511475, "learning_rate": 1.7893590280687058e-05, "loss": 1.2098, "step": 1258 }, { "epoch": 0.52744030163385, "grad_norm": 0.5844467878341675, "learning_rate": 1.789191453707583e-05, "loss": 1.2789, "step": 1259 }, { "epoch": 0.5278592375366569, "grad_norm": 0.8804576992988586, "learning_rate": 1.78902387934646e-05, "loss": 1.236, "step": 1260 }, { "epoch": 0.5282781734394638, "grad_norm": 0.6094422936439514, "learning_rate": 1.7888563049853373e-05, "loss": 1.2946, "step": 1261 }, { "epoch": 0.5286971093422707, "grad_norm": 0.9808681011199951, "learning_rate": 1.7886887306242147e-05, "loss": 1.2285, "step": 1262 }, { "epoch": 0.5291160452450775, "grad_norm": 0.9245563745498657, "learning_rate": 1.7885211562630918e-05, "loss": 1.2421, "step": 1263 }, { "epoch": 0.5295349811478843, "grad_norm": 0.5571091175079346, "learning_rate": 1.7883535819019692e-05, "loss": 1.2987, "step": 1264 }, { "epoch": 0.5299539170506913, "grad_norm": 0.48179373145103455, "learning_rate": 1.7881860075408463e-05, "loss": 1.4172, "step": 1265 }, { "epoch": 0.5303728529534981, "grad_norm": 0.9155369997024536, "learning_rate": 1.7880184331797237e-05, "loss": 1.3419, "step": 1266 }, { "epoch": 0.530791788856305, "grad_norm": 0.6026879549026489, "learning_rate": 1.787850858818601e-05, "loss": 1.2469, "step": 1267 }, { "epoch": 0.5312107247591119, "grad_norm": 0.9528511762619019, "learning_rate": 1.7876832844574782e-05, "loss": 1.2443, "step": 1268 }, { "epoch": 0.5316296606619187, "grad_norm": 0.5990762114524841, "learning_rate": 1.7875157100963553e-05, "loss": 1.3168, "step": 1269 }, { "epoch": 0.5320485965647256, "grad_norm": 1.0758265256881714, "learning_rate": 1.7873481357352327e-05, "loss": 1.3656, "step": 1270 }, { "epoch": 0.5324675324675324, "grad_norm": 0.5298543572425842, "learning_rate": 1.78718056137411e-05, "loss": 1.4026, "step": 1271 }, { "epoch": 0.5328864683703394, "grad_norm": 0.7479298710823059, "learning_rate": 1.7870129870129872e-05, "loss": 1.3189, "step": 1272 }, { "epoch": 0.5333054042731462, "grad_norm": 0.8419678807258606, "learning_rate": 1.7868454126518642e-05, "loss": 1.3479, "step": 1273 }, { "epoch": 0.533724340175953, "grad_norm": 0.6195015907287598, "learning_rate": 1.7866778382907417e-05, "loss": 1.2711, "step": 1274 }, { "epoch": 0.53414327607876, "grad_norm": 0.9979670643806458, "learning_rate": 1.786510263929619e-05, "loss": 1.3364, "step": 1275 }, { "epoch": 0.5345622119815668, "grad_norm": 0.5945103168487549, "learning_rate": 1.786342689568496e-05, "loss": 1.3895, "step": 1276 }, { "epoch": 0.5349811478843737, "grad_norm": 0.8684617877006531, "learning_rate": 1.7861751152073736e-05, "loss": 1.3637, "step": 1277 }, { "epoch": 0.5354000837871805, "grad_norm": 0.7205759882926941, "learning_rate": 1.7860075408462506e-05, "loss": 1.2979, "step": 1278 }, { "epoch": 0.5358190196899875, "grad_norm": 0.6859915852546692, "learning_rate": 1.785839966485128e-05, "loss": 1.3394, "step": 1279 }, { "epoch": 0.5362379555927943, "grad_norm": 0.6070793867111206, "learning_rate": 1.785672392124005e-05, "loss": 1.4482, "step": 1280 }, { "epoch": 0.5366568914956011, "grad_norm": 0.5955244302749634, "learning_rate": 1.7855048177628825e-05, "loss": 1.2846, "step": 1281 }, { "epoch": 0.5370758273984081, "grad_norm": 0.589763879776001, "learning_rate": 1.7853372434017596e-05, "loss": 1.2811, "step": 1282 }, { "epoch": 0.5374947633012149, "grad_norm": 0.6333023905754089, "learning_rate": 1.7851696690406367e-05, "loss": 1.369, "step": 1283 }, { "epoch": 0.5379136992040218, "grad_norm": 0.6410380601882935, "learning_rate": 1.785002094679514e-05, "loss": 1.2449, "step": 1284 }, { "epoch": 0.5383326351068286, "grad_norm": 0.6279928684234619, "learning_rate": 1.7848345203183915e-05, "loss": 1.3662, "step": 1285 }, { "epoch": 0.5387515710096356, "grad_norm": 0.6539936065673828, "learning_rate": 1.784666945957269e-05, "loss": 1.3048, "step": 1286 }, { "epoch": 0.5391705069124424, "grad_norm": 0.6298508048057556, "learning_rate": 1.784499371596146e-05, "loss": 1.1403, "step": 1287 }, { "epoch": 0.5395894428152492, "grad_norm": 0.4872311055660248, "learning_rate": 1.784331797235023e-05, "loss": 1.3026, "step": 1288 }, { "epoch": 0.5400083787180562, "grad_norm": 0.5511845350265503, "learning_rate": 1.7841642228739005e-05, "loss": 1.2766, "step": 1289 }, { "epoch": 0.540427314620863, "grad_norm": 0.5141856074333191, "learning_rate": 1.783996648512778e-05, "loss": 1.2894, "step": 1290 }, { "epoch": 0.5408462505236699, "grad_norm": 0.5504962801933289, "learning_rate": 1.783829074151655e-05, "loss": 1.3424, "step": 1291 }, { "epoch": 0.5412651864264767, "grad_norm": 0.6576582193374634, "learning_rate": 1.783661499790532e-05, "loss": 1.3112, "step": 1292 }, { "epoch": 0.5416841223292836, "grad_norm": 0.6444346308708191, "learning_rate": 1.7834939254294095e-05, "loss": 1.3218, "step": 1293 }, { "epoch": 0.5421030582320905, "grad_norm": 0.6057987809181213, "learning_rate": 1.783326351068287e-05, "loss": 1.3376, "step": 1294 }, { "epoch": 0.5425219941348973, "grad_norm": 0.5632282495498657, "learning_rate": 1.783158776707164e-05, "loss": 1.3227, "step": 1295 }, { "epoch": 0.5429409300377043, "grad_norm": 0.6084432601928711, "learning_rate": 1.782991202346041e-05, "loss": 1.3502, "step": 1296 }, { "epoch": 0.5433598659405111, "grad_norm": 0.5181003212928772, "learning_rate": 1.7828236279849184e-05, "loss": 1.3187, "step": 1297 }, { "epoch": 0.543778801843318, "grad_norm": 0.557337760925293, "learning_rate": 1.782656053623796e-05, "loss": 1.2896, "step": 1298 }, { "epoch": 0.5441977377461248, "grad_norm": 0.5090380311012268, "learning_rate": 1.782488479262673e-05, "loss": 1.3751, "step": 1299 }, { "epoch": 0.5446166736489317, "grad_norm": 0.4427342414855957, "learning_rate": 1.7823209049015503e-05, "loss": 1.2677, "step": 1300 }, { "epoch": 0.5450356095517386, "grad_norm": 0.5770323276519775, "learning_rate": 1.7821533305404274e-05, "loss": 1.2184, "step": 1301 }, { "epoch": 0.5454545454545454, "grad_norm": 0.540174663066864, "learning_rate": 1.7819857561793048e-05, "loss": 1.2702, "step": 1302 }, { "epoch": 0.5458734813573524, "grad_norm": 0.5589969754219055, "learning_rate": 1.781818181818182e-05, "loss": 1.2704, "step": 1303 }, { "epoch": 0.5462924172601592, "grad_norm": 0.7074076533317566, "learning_rate": 1.7816506074570593e-05, "loss": 1.2282, "step": 1304 }, { "epoch": 0.546711353162966, "grad_norm": 0.7852111458778381, "learning_rate": 1.7814830330959364e-05, "loss": 1.3629, "step": 1305 }, { "epoch": 0.547130289065773, "grad_norm": 0.6004078388214111, "learning_rate": 1.7813154587348138e-05, "loss": 1.3622, "step": 1306 }, { "epoch": 0.5475492249685798, "grad_norm": 0.580603301525116, "learning_rate": 1.781147884373691e-05, "loss": 1.3708, "step": 1307 }, { "epoch": 0.5479681608713867, "grad_norm": 0.47281673550605774, "learning_rate": 1.7809803100125683e-05, "loss": 1.3041, "step": 1308 }, { "epoch": 0.5483870967741935, "grad_norm": 0.6532759070396423, "learning_rate": 1.7808127356514457e-05, "loss": 1.2522, "step": 1309 }, { "epoch": 0.5488060326770005, "grad_norm": 0.49898192286491394, "learning_rate": 1.7806451612903228e-05, "loss": 1.3681, "step": 1310 }, { "epoch": 0.5492249685798073, "grad_norm": 0.6004270911216736, "learning_rate": 1.7804775869292e-05, "loss": 1.3283, "step": 1311 }, { "epoch": 0.5496439044826141, "grad_norm": 0.5629726648330688, "learning_rate": 1.7803100125680772e-05, "loss": 1.2727, "step": 1312 }, { "epoch": 0.5500628403854211, "grad_norm": 0.522528886795044, "learning_rate": 1.7801424382069547e-05, "loss": 1.3387, "step": 1313 }, { "epoch": 0.5504817762882279, "grad_norm": 0.7877100110054016, "learning_rate": 1.7799748638458317e-05, "loss": 1.2532, "step": 1314 }, { "epoch": 0.5509007121910348, "grad_norm": 0.618849515914917, "learning_rate": 1.7798072894847088e-05, "loss": 1.3294, "step": 1315 }, { "epoch": 0.5513196480938416, "grad_norm": 0.6938259601593018, "learning_rate": 1.7796397151235862e-05, "loss": 1.2652, "step": 1316 }, { "epoch": 0.5517385839966485, "grad_norm": 0.6753324866294861, "learning_rate": 1.7794721407624636e-05, "loss": 1.2993, "step": 1317 }, { "epoch": 0.5521575198994554, "grad_norm": 0.672173798084259, "learning_rate": 1.7793045664013407e-05, "loss": 1.2273, "step": 1318 }, { "epoch": 0.5525764558022622, "grad_norm": 0.7571685910224915, "learning_rate": 1.7791369920402178e-05, "loss": 1.2485, "step": 1319 }, { "epoch": 0.5529953917050692, "grad_norm": 0.7524890303611755, "learning_rate": 1.7789694176790952e-05, "loss": 1.2561, "step": 1320 }, { "epoch": 0.553414327607876, "grad_norm": 0.5704642534255981, "learning_rate": 1.7788018433179726e-05, "loss": 1.2137, "step": 1321 }, { "epoch": 0.5538332635106828, "grad_norm": 0.6099104285240173, "learning_rate": 1.7786342689568497e-05, "loss": 1.2967, "step": 1322 }, { "epoch": 0.5542521994134897, "grad_norm": 0.7786707878112793, "learning_rate": 1.778466694595727e-05, "loss": 1.3484, "step": 1323 }, { "epoch": 0.5546711353162966, "grad_norm": 0.58577561378479, "learning_rate": 1.778299120234604e-05, "loss": 1.3022, "step": 1324 }, { "epoch": 0.5550900712191035, "grad_norm": 0.6437436938285828, "learning_rate": 1.7781315458734816e-05, "loss": 1.2531, "step": 1325 }, { "epoch": 0.5555090071219103, "grad_norm": 0.5521140694618225, "learning_rate": 1.7779639715123587e-05, "loss": 1.263, "step": 1326 }, { "epoch": 0.5559279430247173, "grad_norm": 0.5403952598571777, "learning_rate": 1.777796397151236e-05, "loss": 1.3847, "step": 1327 }, { "epoch": 0.5563468789275241, "grad_norm": 0.5262768864631653, "learning_rate": 1.777628822790113e-05, "loss": 1.2899, "step": 1328 }, { "epoch": 0.5567658148303309, "grad_norm": 0.5134794116020203, "learning_rate": 1.7774612484289906e-05, "loss": 1.296, "step": 1329 }, { "epoch": 0.5571847507331378, "grad_norm": 0.7250348925590515, "learning_rate": 1.7772936740678676e-05, "loss": 1.1893, "step": 1330 }, { "epoch": 0.5576036866359447, "grad_norm": 0.5694870352745056, "learning_rate": 1.777126099706745e-05, "loss": 1.2385, "step": 1331 }, { "epoch": 0.5580226225387516, "grad_norm": 0.5638760924339294, "learning_rate": 1.7769585253456225e-05, "loss": 1.3243, "step": 1332 }, { "epoch": 0.5584415584415584, "grad_norm": 0.5992881655693054, "learning_rate": 1.7767909509844995e-05, "loss": 1.274, "step": 1333 }, { "epoch": 0.5588604943443654, "grad_norm": 0.5909237861633301, "learning_rate": 1.7766233766233766e-05, "loss": 1.312, "step": 1334 }, { "epoch": 0.5592794302471722, "grad_norm": 0.5980368256568909, "learning_rate": 1.776455802262254e-05, "loss": 1.3217, "step": 1335 }, { "epoch": 0.559698366149979, "grad_norm": 0.5618941187858582, "learning_rate": 1.7762882279011314e-05, "loss": 1.3995, "step": 1336 }, { "epoch": 0.5601173020527859, "grad_norm": 0.6140932440757751, "learning_rate": 1.7761206535400085e-05, "loss": 1.2923, "step": 1337 }, { "epoch": 0.5605362379555928, "grad_norm": 0.5023322701454163, "learning_rate": 1.7759530791788856e-05, "loss": 1.3629, "step": 1338 }, { "epoch": 0.5609551738583997, "grad_norm": 0.8366364240646362, "learning_rate": 1.775785504817763e-05, "loss": 1.2134, "step": 1339 }, { "epoch": 0.5613741097612065, "grad_norm": 0.5725075602531433, "learning_rate": 1.7756179304566404e-05, "loss": 1.3453, "step": 1340 }, { "epoch": 0.5617930456640134, "grad_norm": 0.6364545822143555, "learning_rate": 1.7754503560955175e-05, "loss": 1.3534, "step": 1341 }, { "epoch": 0.5622119815668203, "grad_norm": 0.47016751766204834, "learning_rate": 1.775282781734395e-05, "loss": 1.3539, "step": 1342 }, { "epoch": 0.5626309174696271, "grad_norm": 0.7295567393302917, "learning_rate": 1.775115207373272e-05, "loss": 1.2121, "step": 1343 }, { "epoch": 0.5630498533724341, "grad_norm": 0.4686662256717682, "learning_rate": 1.7749476330121494e-05, "loss": 1.2573, "step": 1344 }, { "epoch": 0.5634687892752409, "grad_norm": 0.8124600648880005, "learning_rate": 1.7747800586510264e-05, "loss": 1.279, "step": 1345 }, { "epoch": 0.5638877251780477, "grad_norm": 0.5149720907211304, "learning_rate": 1.774612484289904e-05, "loss": 1.3532, "step": 1346 }, { "epoch": 0.5643066610808546, "grad_norm": 0.6438298225402832, "learning_rate": 1.774444909928781e-05, "loss": 1.3306, "step": 1347 }, { "epoch": 0.5647255969836615, "grad_norm": 0.55132657289505, "learning_rate": 1.7742773355676583e-05, "loss": 1.3445, "step": 1348 }, { "epoch": 0.5651445328864684, "grad_norm": 0.5063762664794922, "learning_rate": 1.7741097612065354e-05, "loss": 1.3279, "step": 1349 }, { "epoch": 0.5655634687892752, "grad_norm": 0.6811251044273376, "learning_rate": 1.773942186845413e-05, "loss": 1.2465, "step": 1350 }, { "epoch": 0.5659824046920822, "grad_norm": 0.4949902892112732, "learning_rate": 1.77377461248429e-05, "loss": 1.3781, "step": 1351 }, { "epoch": 0.566401340594889, "grad_norm": 0.7091349959373474, "learning_rate": 1.7736070381231673e-05, "loss": 1.2983, "step": 1352 }, { "epoch": 0.5668202764976958, "grad_norm": 0.6150912642478943, "learning_rate": 1.7734394637620444e-05, "loss": 1.2282, "step": 1353 }, { "epoch": 0.5672392124005027, "grad_norm": 0.5687617063522339, "learning_rate": 1.7732718894009218e-05, "loss": 1.3661, "step": 1354 }, { "epoch": 0.5676581483033096, "grad_norm": 0.572397768497467, "learning_rate": 1.7731043150397992e-05, "loss": 1.318, "step": 1355 }, { "epoch": 0.5680770842061165, "grad_norm": 0.641722559928894, "learning_rate": 1.7729367406786763e-05, "loss": 1.1789, "step": 1356 }, { "epoch": 0.5684960201089233, "grad_norm": 0.602450430393219, "learning_rate": 1.7727691663175534e-05, "loss": 1.2984, "step": 1357 }, { "epoch": 0.5689149560117303, "grad_norm": 0.5990121960639954, "learning_rate": 1.7726015919564308e-05, "loss": 1.2426, "step": 1358 }, { "epoch": 0.5693338919145371, "grad_norm": 0.5589391589164734, "learning_rate": 1.7724340175953082e-05, "loss": 1.2307, "step": 1359 }, { "epoch": 0.5697528278173439, "grad_norm": 0.5923172831535339, "learning_rate": 1.7722664432341853e-05, "loss": 1.3518, "step": 1360 }, { "epoch": 0.5701717637201508, "grad_norm": 0.6326620578765869, "learning_rate": 1.7720988688730623e-05, "loss": 1.2997, "step": 1361 }, { "epoch": 0.5705906996229577, "grad_norm": 0.5241389274597168, "learning_rate": 1.7719312945119398e-05, "loss": 1.2879, "step": 1362 }, { "epoch": 0.5710096355257646, "grad_norm": 0.6092697978019714, "learning_rate": 1.771763720150817e-05, "loss": 1.1733, "step": 1363 }, { "epoch": 0.5714285714285714, "grad_norm": 0.5929474830627441, "learning_rate": 1.7715961457896946e-05, "loss": 1.234, "step": 1364 }, { "epoch": 0.5718475073313783, "grad_norm": 0.5177587270736694, "learning_rate": 1.7714285714285717e-05, "loss": 1.1916, "step": 1365 }, { "epoch": 0.5722664432341852, "grad_norm": 0.46039918065071106, "learning_rate": 1.7712609970674487e-05, "loss": 1.3104, "step": 1366 }, { "epoch": 0.572685379136992, "grad_norm": 0.7256949543952942, "learning_rate": 1.771093422706326e-05, "loss": 1.2367, "step": 1367 }, { "epoch": 0.5731043150397989, "grad_norm": 0.6082541942596436, "learning_rate": 1.7709258483452036e-05, "loss": 1.1881, "step": 1368 }, { "epoch": 0.5735232509426058, "grad_norm": 0.5321600437164307, "learning_rate": 1.7707582739840806e-05, "loss": 1.3489, "step": 1369 }, { "epoch": 0.5739421868454126, "grad_norm": 0.49927499890327454, "learning_rate": 1.7705906996229577e-05, "loss": 1.3246, "step": 1370 }, { "epoch": 0.5743611227482195, "grad_norm": 0.5813378691673279, "learning_rate": 1.770423125261835e-05, "loss": 1.3584, "step": 1371 }, { "epoch": 0.5747800586510264, "grad_norm": 0.5608190298080444, "learning_rate": 1.7702555509007125e-05, "loss": 1.3295, "step": 1372 }, { "epoch": 0.5751989945538333, "grad_norm": 0.5132695436477661, "learning_rate": 1.7700879765395896e-05, "loss": 1.3377, "step": 1373 }, { "epoch": 0.5756179304566401, "grad_norm": 0.6476346254348755, "learning_rate": 1.7699204021784667e-05, "loss": 1.256, "step": 1374 }, { "epoch": 0.576036866359447, "grad_norm": 0.6513397097587585, "learning_rate": 1.769752827817344e-05, "loss": 1.2072, "step": 1375 }, { "epoch": 0.5764558022622539, "grad_norm": 0.5437568426132202, "learning_rate": 1.7695852534562215e-05, "loss": 1.3622, "step": 1376 }, { "epoch": 0.5768747381650607, "grad_norm": 0.5718775391578674, "learning_rate": 1.7694176790950986e-05, "loss": 1.303, "step": 1377 }, { "epoch": 0.5772936740678676, "grad_norm": 0.5105891823768616, "learning_rate": 1.769250104733976e-05, "loss": 1.2018, "step": 1378 }, { "epoch": 0.5777126099706745, "grad_norm": 0.4863736033439636, "learning_rate": 1.769082530372853e-05, "loss": 1.3418, "step": 1379 }, { "epoch": 0.5781315458734814, "grad_norm": 0.524736225605011, "learning_rate": 1.76891495601173e-05, "loss": 1.3157, "step": 1380 }, { "epoch": 0.5785504817762882, "grad_norm": 0.586323618888855, "learning_rate": 1.7687473816506075e-05, "loss": 1.129, "step": 1381 }, { "epoch": 0.578969417679095, "grad_norm": 0.5248963236808777, "learning_rate": 1.768579807289485e-05, "loss": 1.2874, "step": 1382 }, { "epoch": 0.579388353581902, "grad_norm": 0.7849308848381042, "learning_rate": 1.768412232928362e-05, "loss": 1.2379, "step": 1383 }, { "epoch": 0.5798072894847088, "grad_norm": 0.6613582372665405, "learning_rate": 1.768244658567239e-05, "loss": 1.2307, "step": 1384 }, { "epoch": 0.5802262253875157, "grad_norm": 0.6964359283447266, "learning_rate": 1.7680770842061165e-05, "loss": 1.1884, "step": 1385 }, { "epoch": 0.5806451612903226, "grad_norm": 0.5994036793708801, "learning_rate": 1.767909509844994e-05, "loss": 1.4359, "step": 1386 }, { "epoch": 0.5810640971931295, "grad_norm": 0.6720858216285706, "learning_rate": 1.7677419354838713e-05, "loss": 1.2907, "step": 1387 }, { "epoch": 0.5814830330959363, "grad_norm": 0.5898488163948059, "learning_rate": 1.7675743611227484e-05, "loss": 1.2874, "step": 1388 }, { "epoch": 0.5819019689987432, "grad_norm": 0.5976569652557373, "learning_rate": 1.7674067867616255e-05, "loss": 1.2797, "step": 1389 }, { "epoch": 0.5823209049015501, "grad_norm": 0.5499746799468994, "learning_rate": 1.767239212400503e-05, "loss": 1.3146, "step": 1390 }, { "epoch": 0.5827398408043569, "grad_norm": 0.5343840718269348, "learning_rate": 1.7670716380393803e-05, "loss": 1.3176, "step": 1391 }, { "epoch": 0.5831587767071638, "grad_norm": 0.6499097943305969, "learning_rate": 1.7669040636782574e-05, "loss": 1.3002, "step": 1392 }, { "epoch": 0.5835777126099707, "grad_norm": 0.603602945804596, "learning_rate": 1.7667364893171345e-05, "loss": 1.4287, "step": 1393 }, { "epoch": 0.5839966485127775, "grad_norm": 0.5224370360374451, "learning_rate": 1.766568914956012e-05, "loss": 1.3491, "step": 1394 }, { "epoch": 0.5844155844155844, "grad_norm": 0.46926870942115784, "learning_rate": 1.7664013405948893e-05, "loss": 1.3291, "step": 1395 }, { "epoch": 0.5848345203183913, "grad_norm": 0.5736171007156372, "learning_rate": 1.7662337662337664e-05, "loss": 1.3047, "step": 1396 }, { "epoch": 0.5852534562211982, "grad_norm": 0.6868048310279846, "learning_rate": 1.7660661918726438e-05, "loss": 1.2734, "step": 1397 }, { "epoch": 0.585672392124005, "grad_norm": 0.5861262679100037, "learning_rate": 1.765898617511521e-05, "loss": 1.3646, "step": 1398 }, { "epoch": 0.5860913280268119, "grad_norm": 0.7702271938323975, "learning_rate": 1.7657310431503983e-05, "loss": 1.2546, "step": 1399 }, { "epoch": 0.5865102639296188, "grad_norm": 0.5478736162185669, "learning_rate": 1.7655634687892753e-05, "loss": 1.3133, "step": 1400 }, { "epoch": 0.5869291998324256, "grad_norm": 0.6259478330612183, "learning_rate": 1.7653958944281528e-05, "loss": 1.2667, "step": 1401 }, { "epoch": 0.5873481357352325, "grad_norm": 0.6237809062004089, "learning_rate": 1.7652283200670298e-05, "loss": 1.3433, "step": 1402 }, { "epoch": 0.5877670716380394, "grad_norm": 0.5308570265769958, "learning_rate": 1.7650607457059072e-05, "loss": 1.294, "step": 1403 }, { "epoch": 0.5881860075408463, "grad_norm": 0.8674180507659912, "learning_rate": 1.7648931713447843e-05, "loss": 1.152, "step": 1404 }, { "epoch": 0.5886049434436531, "grad_norm": 0.7068473696708679, "learning_rate": 1.7647255969836617e-05, "loss": 1.2811, "step": 1405 }, { "epoch": 0.5890238793464599, "grad_norm": 0.7270013093948364, "learning_rate": 1.7645580226225388e-05, "loss": 1.2351, "step": 1406 }, { "epoch": 0.5894428152492669, "grad_norm": 0.8010975122451782, "learning_rate": 1.7643904482614162e-05, "loss": 1.2329, "step": 1407 }, { "epoch": 0.5898617511520737, "grad_norm": 0.5183730125427246, "learning_rate": 1.7642228739002933e-05, "loss": 1.3412, "step": 1408 }, { "epoch": 0.5902806870548806, "grad_norm": 0.533948540687561, "learning_rate": 1.7640552995391707e-05, "loss": 1.3028, "step": 1409 }, { "epoch": 0.5906996229576875, "grad_norm": 1.0180015563964844, "learning_rate": 1.763887725178048e-05, "loss": 1.3279, "step": 1410 }, { "epoch": 0.5911185588604944, "grad_norm": 0.532831609249115, "learning_rate": 1.7637201508169252e-05, "loss": 1.3554, "step": 1411 }, { "epoch": 0.5915374947633012, "grad_norm": 1.325769066810608, "learning_rate": 1.7635525764558023e-05, "loss": 1.3021, "step": 1412 }, { "epoch": 0.591956430666108, "grad_norm": 0.7403219938278198, "learning_rate": 1.7633850020946797e-05, "loss": 1.2408, "step": 1413 }, { "epoch": 0.592375366568915, "grad_norm": 0.583234965801239, "learning_rate": 1.763217427733557e-05, "loss": 1.2485, "step": 1414 }, { "epoch": 0.5927943024717218, "grad_norm": 0.9657902121543884, "learning_rate": 1.763049853372434e-05, "loss": 1.2624, "step": 1415 }, { "epoch": 0.5932132383745287, "grad_norm": 0.7484773397445679, "learning_rate": 1.7628822790113112e-05, "loss": 1.3705, "step": 1416 }, { "epoch": 0.5936321742773356, "grad_norm": 0.8081579804420471, "learning_rate": 1.7627147046501886e-05, "loss": 1.3092, "step": 1417 }, { "epoch": 0.5940511101801424, "grad_norm": 0.886363685131073, "learning_rate": 1.762547130289066e-05, "loss": 1.2326, "step": 1418 }, { "epoch": 0.5944700460829493, "grad_norm": 0.5585987567901611, "learning_rate": 1.762379555927943e-05, "loss": 1.4129, "step": 1419 }, { "epoch": 0.5948889819857561, "grad_norm": 0.8939359784126282, "learning_rate": 1.7622119815668205e-05, "loss": 1.2419, "step": 1420 }, { "epoch": 0.5953079178885631, "grad_norm": 0.6043072938919067, "learning_rate": 1.7620444072056976e-05, "loss": 1.2339, "step": 1421 }, { "epoch": 0.5957268537913699, "grad_norm": 0.7984194159507751, "learning_rate": 1.761876832844575e-05, "loss": 1.3355, "step": 1422 }, { "epoch": 0.5961457896941768, "grad_norm": 0.6863401532173157, "learning_rate": 1.761709258483452e-05, "loss": 1.3458, "step": 1423 }, { "epoch": 0.5965647255969837, "grad_norm": 0.6445105075836182, "learning_rate": 1.7615416841223295e-05, "loss": 1.3068, "step": 1424 }, { "epoch": 0.5969836614997905, "grad_norm": 0.6716631650924683, "learning_rate": 1.7613741097612066e-05, "loss": 1.3329, "step": 1425 }, { "epoch": 0.5974025974025974, "grad_norm": 0.5903627872467041, "learning_rate": 1.761206535400084e-05, "loss": 1.3227, "step": 1426 }, { "epoch": 0.5978215333054042, "grad_norm": 0.7775170803070068, "learning_rate": 1.761038961038961e-05, "loss": 1.3057, "step": 1427 }, { "epoch": 0.5982404692082112, "grad_norm": 0.5707830786705017, "learning_rate": 1.7608713866778385e-05, "loss": 1.2764, "step": 1428 }, { "epoch": 0.598659405111018, "grad_norm": 0.6048703193664551, "learning_rate": 1.7607038123167156e-05, "loss": 1.3569, "step": 1429 }, { "epoch": 0.5990783410138248, "grad_norm": 0.6078689694404602, "learning_rate": 1.760536237955593e-05, "loss": 1.2632, "step": 1430 }, { "epoch": 0.5994972769166318, "grad_norm": 0.5716987252235413, "learning_rate": 1.76036866359447e-05, "loss": 1.3327, "step": 1431 }, { "epoch": 0.5999162128194386, "grad_norm": 0.774499773979187, "learning_rate": 1.7602010892333475e-05, "loss": 1.2911, "step": 1432 }, { "epoch": 0.6003351487222455, "grad_norm": 0.7096041440963745, "learning_rate": 1.760033514872225e-05, "loss": 1.2939, "step": 1433 }, { "epoch": 0.6007540846250524, "grad_norm": 0.5483337640762329, "learning_rate": 1.759865940511102e-05, "loss": 1.3376, "step": 1434 }, { "epoch": 0.6011730205278593, "grad_norm": 0.5955720543861389, "learning_rate": 1.759698366149979e-05, "loss": 1.2184, "step": 1435 }, { "epoch": 0.6015919564306661, "grad_norm": 0.5347083806991577, "learning_rate": 1.7595307917888564e-05, "loss": 1.3402, "step": 1436 }, { "epoch": 0.6020108923334729, "grad_norm": 0.5615149140357971, "learning_rate": 1.759363217427734e-05, "loss": 1.3472, "step": 1437 }, { "epoch": 0.6024298282362799, "grad_norm": 0.6356179714202881, "learning_rate": 1.759195643066611e-05, "loss": 1.32, "step": 1438 }, { "epoch": 0.6028487641390867, "grad_norm": 0.49199768900871277, "learning_rate": 1.759028068705488e-05, "loss": 1.3055, "step": 1439 }, { "epoch": 0.6032677000418936, "grad_norm": 0.5339782238006592, "learning_rate": 1.7588604943443654e-05, "loss": 1.2481, "step": 1440 }, { "epoch": 0.6036866359447005, "grad_norm": 0.6259820461273193, "learning_rate": 1.7586929199832428e-05, "loss": 1.2562, "step": 1441 }, { "epoch": 0.6041055718475073, "grad_norm": 0.5217363834381104, "learning_rate": 1.75852534562212e-05, "loss": 1.2375, "step": 1442 }, { "epoch": 0.6045245077503142, "grad_norm": 0.5084887742996216, "learning_rate": 1.7583577712609973e-05, "loss": 1.4266, "step": 1443 }, { "epoch": 0.604943443653121, "grad_norm": 0.7613831758499146, "learning_rate": 1.7581901968998744e-05, "loss": 1.2659, "step": 1444 }, { "epoch": 0.605362379555928, "grad_norm": 0.6611988544464111, "learning_rate": 1.7580226225387518e-05, "loss": 1.2508, "step": 1445 }, { "epoch": 0.6057813154587348, "grad_norm": 0.6269226670265198, "learning_rate": 1.757855048177629e-05, "loss": 1.2864, "step": 1446 }, { "epoch": 0.6062002513615417, "grad_norm": 0.5842568874359131, "learning_rate": 1.7576874738165063e-05, "loss": 1.2311, "step": 1447 }, { "epoch": 0.6066191872643486, "grad_norm": 0.5638346076011658, "learning_rate": 1.7575198994553834e-05, "loss": 1.2736, "step": 1448 }, { "epoch": 0.6070381231671554, "grad_norm": 0.6111261248588562, "learning_rate": 1.7573523250942608e-05, "loss": 1.3012, "step": 1449 }, { "epoch": 0.6074570590699623, "grad_norm": 0.638558030128479, "learning_rate": 1.757184750733138e-05, "loss": 1.2249, "step": 1450 }, { "epoch": 0.6078759949727691, "grad_norm": 0.5452461242675781, "learning_rate": 1.7570171763720153e-05, "loss": 1.268, "step": 1451 }, { "epoch": 0.6082949308755761, "grad_norm": 0.5750777125358582, "learning_rate": 1.7568496020108923e-05, "loss": 1.2969, "step": 1452 }, { "epoch": 0.6087138667783829, "grad_norm": 0.7092899680137634, "learning_rate": 1.7566820276497697e-05, "loss": 1.2295, "step": 1453 }, { "epoch": 0.6091328026811897, "grad_norm": 0.5270527005195618, "learning_rate": 1.7565144532886468e-05, "loss": 1.3078, "step": 1454 }, { "epoch": 0.6095517385839967, "grad_norm": 0.6084786057472229, "learning_rate": 1.7563468789275242e-05, "loss": 1.3357, "step": 1455 }, { "epoch": 0.6099706744868035, "grad_norm": 0.5139050483703613, "learning_rate": 1.7561793045664016e-05, "loss": 1.2415, "step": 1456 }, { "epoch": 0.6103896103896104, "grad_norm": 0.5369597673416138, "learning_rate": 1.7560117302052787e-05, "loss": 1.3545, "step": 1457 }, { "epoch": 0.6108085462924172, "grad_norm": 0.6347735524177551, "learning_rate": 1.7558441558441558e-05, "loss": 1.3302, "step": 1458 }, { "epoch": 0.6112274821952242, "grad_norm": 0.4786611795425415, "learning_rate": 1.7556765814830332e-05, "loss": 1.294, "step": 1459 }, { "epoch": 0.611646418098031, "grad_norm": 0.5806422233581543, "learning_rate": 1.7555090071219106e-05, "loss": 1.2353, "step": 1460 }, { "epoch": 0.6120653540008378, "grad_norm": 0.5411217212677002, "learning_rate": 1.7553414327607877e-05, "loss": 1.1271, "step": 1461 }, { "epoch": 0.6124842899036448, "grad_norm": 0.5744215846061707, "learning_rate": 1.7551738583996648e-05, "loss": 1.247, "step": 1462 }, { "epoch": 0.6129032258064516, "grad_norm": 0.70229172706604, "learning_rate": 1.7550062840385422e-05, "loss": 1.2619, "step": 1463 }, { "epoch": 0.6133221617092585, "grad_norm": 0.5091577768325806, "learning_rate": 1.7548387096774196e-05, "loss": 1.3551, "step": 1464 }, { "epoch": 0.6137410976120653, "grad_norm": 0.6974036693572998, "learning_rate": 1.754671135316297e-05, "loss": 1.2444, "step": 1465 }, { "epoch": 0.6141600335148723, "grad_norm": 0.4749530255794525, "learning_rate": 1.754503560955174e-05, "loss": 1.4273, "step": 1466 }, { "epoch": 0.6145789694176791, "grad_norm": 0.7062107920646667, "learning_rate": 1.754335986594051e-05, "loss": 1.2427, "step": 1467 }, { "epoch": 0.6149979053204859, "grad_norm": 0.5904315114021301, "learning_rate": 1.7541684122329286e-05, "loss": 1.0986, "step": 1468 }, { "epoch": 0.6154168412232929, "grad_norm": 0.7046118378639221, "learning_rate": 1.754000837871806e-05, "loss": 1.2727, "step": 1469 }, { "epoch": 0.6158357771260997, "grad_norm": 0.6088693141937256, "learning_rate": 1.753833263510683e-05, "loss": 1.3275, "step": 1470 }, { "epoch": 0.6162547130289066, "grad_norm": 0.9204738140106201, "learning_rate": 1.75366568914956e-05, "loss": 1.162, "step": 1471 }, { "epoch": 0.6166736489317135, "grad_norm": 0.7253133058547974, "learning_rate": 1.7534981147884375e-05, "loss": 1.2053, "step": 1472 }, { "epoch": 0.6170925848345203, "grad_norm": 0.6671650409698486, "learning_rate": 1.7533305404273146e-05, "loss": 1.1794, "step": 1473 }, { "epoch": 0.6175115207373272, "grad_norm": 0.6576147675514221, "learning_rate": 1.753162966066192e-05, "loss": 1.2733, "step": 1474 }, { "epoch": 0.617930456640134, "grad_norm": 0.5231505036354065, "learning_rate": 1.7529953917050694e-05, "loss": 1.2902, "step": 1475 }, { "epoch": 0.618349392542941, "grad_norm": 0.819714367389679, "learning_rate": 1.7528278173439465e-05, "loss": 1.2889, "step": 1476 }, { "epoch": 0.6187683284457478, "grad_norm": 0.5911850333213806, "learning_rate": 1.7526602429828236e-05, "loss": 1.4209, "step": 1477 }, { "epoch": 0.6191872643485546, "grad_norm": 0.5521571040153503, "learning_rate": 1.752492668621701e-05, "loss": 1.2546, "step": 1478 }, { "epoch": 0.6196062002513616, "grad_norm": 0.5246455073356628, "learning_rate": 1.7523250942605784e-05, "loss": 1.2895, "step": 1479 }, { "epoch": 0.6200251361541684, "grad_norm": 0.5842067003250122, "learning_rate": 1.7521575198994555e-05, "loss": 1.3116, "step": 1480 }, { "epoch": 0.6204440720569753, "grad_norm": 0.5627856254577637, "learning_rate": 1.7519899455383326e-05, "loss": 1.2929, "step": 1481 }, { "epoch": 0.6208630079597821, "grad_norm": 0.5394353270530701, "learning_rate": 1.75182237117721e-05, "loss": 1.2859, "step": 1482 }, { "epoch": 0.6212819438625891, "grad_norm": 0.5626618266105652, "learning_rate": 1.7516547968160874e-05, "loss": 1.3232, "step": 1483 }, { "epoch": 0.6217008797653959, "grad_norm": 0.5217122435569763, "learning_rate": 1.7514872224549645e-05, "loss": 1.2423, "step": 1484 }, { "epoch": 0.6221198156682027, "grad_norm": 0.5902916193008423, "learning_rate": 1.7513196480938415e-05, "loss": 1.3052, "step": 1485 }, { "epoch": 0.6225387515710097, "grad_norm": 0.5527148842811584, "learning_rate": 1.751152073732719e-05, "loss": 1.3064, "step": 1486 }, { "epoch": 0.6229576874738165, "grad_norm": 0.5452631711959839, "learning_rate": 1.7509844993715964e-05, "loss": 1.261, "step": 1487 }, { "epoch": 0.6233766233766234, "grad_norm": 0.4810452461242676, "learning_rate": 1.7508169250104738e-05, "loss": 1.1981, "step": 1488 }, { "epoch": 0.6237955592794302, "grad_norm": 0.5459185242652893, "learning_rate": 1.750649350649351e-05, "loss": 1.2797, "step": 1489 }, { "epoch": 0.6242144951822372, "grad_norm": 0.5386171340942383, "learning_rate": 1.750481776288228e-05, "loss": 1.2305, "step": 1490 }, { "epoch": 0.624633431085044, "grad_norm": 0.5805650949478149, "learning_rate": 1.7503142019271053e-05, "loss": 1.1928, "step": 1491 }, { "epoch": 0.6250523669878508, "grad_norm": 0.47368550300598145, "learning_rate": 1.7501466275659827e-05, "loss": 1.3869, "step": 1492 }, { "epoch": 0.6254713028906578, "grad_norm": 0.4864535331726074, "learning_rate": 1.7499790532048598e-05, "loss": 1.2916, "step": 1493 }, { "epoch": 0.6258902387934646, "grad_norm": 0.5703107118606567, "learning_rate": 1.749811478843737e-05, "loss": 1.2615, "step": 1494 }, { "epoch": 0.6263091746962715, "grad_norm": 0.48528942465782166, "learning_rate": 1.7496439044826143e-05, "loss": 1.3371, "step": 1495 }, { "epoch": 0.6267281105990783, "grad_norm": 0.5472234487533569, "learning_rate": 1.7494763301214917e-05, "loss": 1.2084, "step": 1496 }, { "epoch": 0.6271470465018852, "grad_norm": 0.4904332160949707, "learning_rate": 1.7493087557603688e-05, "loss": 1.2047, "step": 1497 }, { "epoch": 0.6275659824046921, "grad_norm": 0.4984428882598877, "learning_rate": 1.7491411813992462e-05, "loss": 1.282, "step": 1498 }, { "epoch": 0.6279849183074989, "grad_norm": 0.4487931430339813, "learning_rate": 1.7489736070381233e-05, "loss": 1.3188, "step": 1499 }, { "epoch": 0.6284038542103059, "grad_norm": 0.49845385551452637, "learning_rate": 1.7488060326770007e-05, "loss": 1.2363, "step": 1500 }, { "epoch": 0.6288227901131127, "grad_norm": 0.6113477945327759, "learning_rate": 1.7486384583158778e-05, "loss": 1.2071, "step": 1501 }, { "epoch": 0.6292417260159195, "grad_norm": 0.5518938302993774, "learning_rate": 1.7484708839547552e-05, "loss": 1.2193, "step": 1502 }, { "epoch": 0.6296606619187264, "grad_norm": 0.520671010017395, "learning_rate": 1.7483033095936323e-05, "loss": 1.3355, "step": 1503 }, { "epoch": 0.6300795978215333, "grad_norm": 0.6091256141662598, "learning_rate": 1.7481357352325097e-05, "loss": 1.2425, "step": 1504 }, { "epoch": 0.6304985337243402, "grad_norm": 0.5465255379676819, "learning_rate": 1.7479681608713867e-05, "loss": 1.2527, "step": 1505 }, { "epoch": 0.630917469627147, "grad_norm": 0.5501901507377625, "learning_rate": 1.747800586510264e-05, "loss": 1.3464, "step": 1506 }, { "epoch": 0.631336405529954, "grad_norm": 0.5364275574684143, "learning_rate": 1.7476330121491412e-05, "loss": 1.2586, "step": 1507 }, { "epoch": 0.6317553414327608, "grad_norm": 0.49916544556617737, "learning_rate": 1.7474654377880186e-05, "loss": 1.3149, "step": 1508 }, { "epoch": 0.6321742773355676, "grad_norm": 0.6720826625823975, "learning_rate": 1.7472978634268957e-05, "loss": 1.2215, "step": 1509 }, { "epoch": 0.6325932132383745, "grad_norm": 0.5754246115684509, "learning_rate": 1.747130289065773e-05, "loss": 1.2664, "step": 1510 }, { "epoch": 0.6330121491411814, "grad_norm": 0.8120757341384888, "learning_rate": 1.7469627147046505e-05, "loss": 1.2591, "step": 1511 }, { "epoch": 0.6334310850439883, "grad_norm": 0.5973666906356812, "learning_rate": 1.7467951403435276e-05, "loss": 1.2822, "step": 1512 }, { "epoch": 0.6338500209467951, "grad_norm": 0.5217477679252625, "learning_rate": 1.7466275659824047e-05, "loss": 1.2437, "step": 1513 }, { "epoch": 0.634268956849602, "grad_norm": 0.5776591897010803, "learning_rate": 1.746459991621282e-05, "loss": 1.3109, "step": 1514 }, { "epoch": 0.6346878927524089, "grad_norm": 0.4742058515548706, "learning_rate": 1.7462924172601595e-05, "loss": 1.2598, "step": 1515 }, { "epoch": 0.6351068286552157, "grad_norm": 0.5587383508682251, "learning_rate": 1.7461248428990366e-05, "loss": 1.216, "step": 1516 }, { "epoch": 0.6355257645580227, "grad_norm": 0.5540397763252258, "learning_rate": 1.7459572685379137e-05, "loss": 1.2225, "step": 1517 }, { "epoch": 0.6359447004608295, "grad_norm": 0.5670872926712036, "learning_rate": 1.745789694176791e-05, "loss": 1.2483, "step": 1518 }, { "epoch": 0.6363636363636364, "grad_norm": 0.5158231258392334, "learning_rate": 1.7456221198156685e-05, "loss": 1.3408, "step": 1519 }, { "epoch": 0.6367825722664432, "grad_norm": 0.5994433760643005, "learning_rate": 1.7454545454545456e-05, "loss": 1.2345, "step": 1520 }, { "epoch": 0.6372015081692501, "grad_norm": 0.5295534729957581, "learning_rate": 1.745286971093423e-05, "loss": 1.2741, "step": 1521 }, { "epoch": 0.637620444072057, "grad_norm": 0.5199494361877441, "learning_rate": 1.7451193967323e-05, "loss": 1.3688, "step": 1522 }, { "epoch": 0.6380393799748638, "grad_norm": 0.5227517485618591, "learning_rate": 1.7449518223711775e-05, "loss": 1.2398, "step": 1523 }, { "epoch": 0.6384583158776708, "grad_norm": 0.5629118084907532, "learning_rate": 1.7447842480100545e-05, "loss": 1.2596, "step": 1524 }, { "epoch": 0.6388772517804776, "grad_norm": 0.4980710744857788, "learning_rate": 1.744616673648932e-05, "loss": 1.1964, "step": 1525 }, { "epoch": 0.6392961876832844, "grad_norm": 0.49469640851020813, "learning_rate": 1.744449099287809e-05, "loss": 1.2965, "step": 1526 }, { "epoch": 0.6397151235860913, "grad_norm": 0.6014249920845032, "learning_rate": 1.7442815249266864e-05, "loss": 1.3071, "step": 1527 }, { "epoch": 0.6401340594888982, "grad_norm": 0.5421773195266724, "learning_rate": 1.7441139505655635e-05, "loss": 1.2539, "step": 1528 }, { "epoch": 0.6405529953917051, "grad_norm": 0.5878353714942932, "learning_rate": 1.743946376204441e-05, "loss": 1.2987, "step": 1529 }, { "epoch": 0.6409719312945119, "grad_norm": 0.5377175211906433, "learning_rate": 1.743778801843318e-05, "loss": 1.3148, "step": 1530 }, { "epoch": 0.6413908671973189, "grad_norm": 0.6132928133010864, "learning_rate": 1.7436112274821954e-05, "loss": 1.1882, "step": 1531 }, { "epoch": 0.6418098031001257, "grad_norm": 0.6469982862472534, "learning_rate": 1.7434436531210725e-05, "loss": 1.3413, "step": 1532 }, { "epoch": 0.6422287390029325, "grad_norm": 0.5469098091125488, "learning_rate": 1.74327607875995e-05, "loss": 1.2409, "step": 1533 }, { "epoch": 0.6426476749057394, "grad_norm": 0.5009613633155823, "learning_rate": 1.7431085043988273e-05, "loss": 1.1982, "step": 1534 }, { "epoch": 0.6430666108085463, "grad_norm": 0.4895801842212677, "learning_rate": 1.7429409300377044e-05, "loss": 1.2447, "step": 1535 }, { "epoch": 0.6434855467113532, "grad_norm": 0.5704910755157471, "learning_rate": 1.7427733556765815e-05, "loss": 1.2583, "step": 1536 }, { "epoch": 0.64390448261416, "grad_norm": 0.6943588256835938, "learning_rate": 1.742605781315459e-05, "loss": 1.2028, "step": 1537 }, { "epoch": 0.644323418516967, "grad_norm": 0.6675198078155518, "learning_rate": 1.7424382069543363e-05, "loss": 1.3155, "step": 1538 }, { "epoch": 0.6447423544197738, "grad_norm": 0.859157145023346, "learning_rate": 1.7422706325932134e-05, "loss": 1.1978, "step": 1539 }, { "epoch": 0.6451612903225806, "grad_norm": 0.7588547468185425, "learning_rate": 1.7421030582320904e-05, "loss": 1.2953, "step": 1540 }, { "epoch": 0.6455802262253875, "grad_norm": 0.8984459638595581, "learning_rate": 1.741935483870968e-05, "loss": 1.2223, "step": 1541 }, { "epoch": 0.6459991621281944, "grad_norm": 0.5515475869178772, "learning_rate": 1.7417679095098453e-05, "loss": 1.3219, "step": 1542 }, { "epoch": 0.6464180980310013, "grad_norm": 1.025132417678833, "learning_rate": 1.7416003351487223e-05, "loss": 1.354, "step": 1543 }, { "epoch": 0.6468370339338081, "grad_norm": 0.49314528703689575, "learning_rate": 1.7414327607875997e-05, "loss": 1.3079, "step": 1544 }, { "epoch": 0.647255969836615, "grad_norm": 0.7344246506690979, "learning_rate": 1.7412651864264768e-05, "loss": 1.2536, "step": 1545 }, { "epoch": 0.6476749057394219, "grad_norm": 0.6492268443107605, "learning_rate": 1.7410976120653542e-05, "loss": 1.2377, "step": 1546 }, { "epoch": 0.6480938416422287, "grad_norm": 0.5386174321174622, "learning_rate": 1.7409300377042313e-05, "loss": 1.2613, "step": 1547 }, { "epoch": 0.6485127775450356, "grad_norm": 0.9705476760864258, "learning_rate": 1.7407624633431087e-05, "loss": 1.2825, "step": 1548 }, { "epoch": 0.6489317134478425, "grad_norm": 0.5176243185997009, "learning_rate": 1.7405948889819858e-05, "loss": 1.2194, "step": 1549 }, { "epoch": 0.6493506493506493, "grad_norm": 0.5973585247993469, "learning_rate": 1.7404273146208632e-05, "loss": 1.3198, "step": 1550 }, { "epoch": 0.6497695852534562, "grad_norm": 0.9663310050964355, "learning_rate": 1.7402597402597403e-05, "loss": 1.2926, "step": 1551 }, { "epoch": 0.6501885211562631, "grad_norm": 0.6832008361816406, "learning_rate": 1.7400921658986177e-05, "loss": 1.2851, "step": 1552 }, { "epoch": 0.65060745705907, "grad_norm": 1.1678398847579956, "learning_rate": 1.739924591537495e-05, "loss": 1.2651, "step": 1553 }, { "epoch": 0.6510263929618768, "grad_norm": 0.47856616973876953, "learning_rate": 1.7397570171763722e-05, "loss": 1.2733, "step": 1554 }, { "epoch": 0.6514453288646836, "grad_norm": 1.2439031600952148, "learning_rate": 1.7395894428152492e-05, "loss": 1.209, "step": 1555 }, { "epoch": 0.6518642647674906, "grad_norm": 0.5588659644126892, "learning_rate": 1.7394218684541267e-05, "loss": 1.3742, "step": 1556 }, { "epoch": 0.6522832006702974, "grad_norm": 0.7374033331871033, "learning_rate": 1.739254294093004e-05, "loss": 1.3262, "step": 1557 }, { "epoch": 0.6527021365731043, "grad_norm": 0.953170657157898, "learning_rate": 1.739086719731881e-05, "loss": 1.1881, "step": 1558 }, { "epoch": 0.6531210724759112, "grad_norm": 0.7037895917892456, "learning_rate": 1.7389191453707582e-05, "loss": 1.2947, "step": 1559 }, { "epoch": 0.6535400083787181, "grad_norm": 0.6454088687896729, "learning_rate": 1.7387515710096356e-05, "loss": 1.3331, "step": 1560 }, { "epoch": 0.6539589442815249, "grad_norm": 0.7377892732620239, "learning_rate": 1.738583996648513e-05, "loss": 1.3209, "step": 1561 }, { "epoch": 0.6543778801843319, "grad_norm": 0.7061387300491333, "learning_rate": 1.73841642228739e-05, "loss": 1.2548, "step": 1562 }, { "epoch": 0.6547968160871387, "grad_norm": 0.8009461164474487, "learning_rate": 1.7382488479262672e-05, "loss": 1.2247, "step": 1563 }, { "epoch": 0.6552157519899455, "grad_norm": 0.5684537887573242, "learning_rate": 1.7380812735651446e-05, "loss": 1.2864, "step": 1564 }, { "epoch": 0.6556346878927524, "grad_norm": 0.6873291730880737, "learning_rate": 1.737913699204022e-05, "loss": 1.3885, "step": 1565 }, { "epoch": 0.6560536237955593, "grad_norm": 0.6990252137184143, "learning_rate": 1.7377461248428994e-05, "loss": 1.3005, "step": 1566 }, { "epoch": 0.6564725596983662, "grad_norm": 0.5901041626930237, "learning_rate": 1.7375785504817765e-05, "loss": 1.2479, "step": 1567 }, { "epoch": 0.656891495601173, "grad_norm": 0.9423961639404297, "learning_rate": 1.7374109761206536e-05, "loss": 1.2718, "step": 1568 }, { "epoch": 0.6573104315039799, "grad_norm": 0.5136571526527405, "learning_rate": 1.737243401759531e-05, "loss": 1.3148, "step": 1569 }, { "epoch": 0.6577293674067868, "grad_norm": 0.6433159708976746, "learning_rate": 1.737075827398408e-05, "loss": 1.2464, "step": 1570 }, { "epoch": 0.6581483033095936, "grad_norm": 0.6043862104415894, "learning_rate": 1.7369082530372855e-05, "loss": 1.2172, "step": 1571 }, { "epoch": 0.6585672392124005, "grad_norm": 0.6085765957832336, "learning_rate": 1.7367406786761626e-05, "loss": 1.2423, "step": 1572 }, { "epoch": 0.6589861751152074, "grad_norm": 0.6748076677322388, "learning_rate": 1.73657310431504e-05, "loss": 1.3026, "step": 1573 }, { "epoch": 0.6594051110180142, "grad_norm": 0.4812471866607666, "learning_rate": 1.736405529953917e-05, "loss": 1.2811, "step": 1574 }, { "epoch": 0.6598240469208211, "grad_norm": 0.5828402638435364, "learning_rate": 1.7362379555927945e-05, "loss": 1.3127, "step": 1575 }, { "epoch": 0.660242982823628, "grad_norm": 0.6135497689247131, "learning_rate": 1.736070381231672e-05, "loss": 1.28, "step": 1576 }, { "epoch": 0.6606619187264349, "grad_norm": 0.48049458861351013, "learning_rate": 1.735902806870549e-05, "loss": 1.1707, "step": 1577 }, { "epoch": 0.6610808546292417, "grad_norm": 0.7727789282798767, "learning_rate": 1.735735232509426e-05, "loss": 1.2463, "step": 1578 }, { "epoch": 0.6614997905320485, "grad_norm": 0.5606263279914856, "learning_rate": 1.7355676581483034e-05, "loss": 1.2281, "step": 1579 }, { "epoch": 0.6619187264348555, "grad_norm": 0.5121038556098938, "learning_rate": 1.735400083787181e-05, "loss": 1.2504, "step": 1580 }, { "epoch": 0.6623376623376623, "grad_norm": 0.524918258190155, "learning_rate": 1.735232509426058e-05, "loss": 1.3432, "step": 1581 }, { "epoch": 0.6627565982404692, "grad_norm": 0.4484054446220398, "learning_rate": 1.735064935064935e-05, "loss": 1.3139, "step": 1582 }, { "epoch": 0.6631755341432761, "grad_norm": 0.6086823344230652, "learning_rate": 1.7348973607038124e-05, "loss": 1.3486, "step": 1583 }, { "epoch": 0.663594470046083, "grad_norm": 0.4744013845920563, "learning_rate": 1.7347297863426898e-05, "loss": 1.2417, "step": 1584 }, { "epoch": 0.6640134059488898, "grad_norm": 0.5900630354881287, "learning_rate": 1.734562211981567e-05, "loss": 1.2843, "step": 1585 }, { "epoch": 0.6644323418516966, "grad_norm": 0.5374463200569153, "learning_rate": 1.7343946376204443e-05, "loss": 1.2745, "step": 1586 }, { "epoch": 0.6648512777545036, "grad_norm": 0.5678898692131042, "learning_rate": 1.7342270632593214e-05, "loss": 1.1963, "step": 1587 }, { "epoch": 0.6652702136573104, "grad_norm": 0.610619068145752, "learning_rate": 1.7340594888981988e-05, "loss": 1.2486, "step": 1588 }, { "epoch": 0.6656891495601173, "grad_norm": 0.5179247260093689, "learning_rate": 1.7338919145370762e-05, "loss": 1.3829, "step": 1589 }, { "epoch": 0.6661080854629242, "grad_norm": 0.7143780589103699, "learning_rate": 1.7337243401759533e-05, "loss": 1.3163, "step": 1590 }, { "epoch": 0.666527021365731, "grad_norm": 0.5332823991775513, "learning_rate": 1.7335567658148303e-05, "loss": 1.1521, "step": 1591 }, { "epoch": 0.6669459572685379, "grad_norm": 0.8212310671806335, "learning_rate": 1.7333891914537078e-05, "loss": 1.2814, "step": 1592 }, { "epoch": 0.6673648931713447, "grad_norm": 0.5446910858154297, "learning_rate": 1.7332216170925852e-05, "loss": 1.2418, "step": 1593 }, { "epoch": 0.6677838290741517, "grad_norm": 0.5743156671524048, "learning_rate": 1.7330540427314622e-05, "loss": 1.2805, "step": 1594 }, { "epoch": 0.6682027649769585, "grad_norm": 0.6170635223388672, "learning_rate": 1.7328864683703393e-05, "loss": 1.2869, "step": 1595 }, { "epoch": 0.6686217008797654, "grad_norm": 0.5196903944015503, "learning_rate": 1.7327188940092167e-05, "loss": 1.2035, "step": 1596 }, { "epoch": 0.6690406367825723, "grad_norm": 0.7136192321777344, "learning_rate": 1.732551319648094e-05, "loss": 1.3023, "step": 1597 }, { "epoch": 0.6694595726853791, "grad_norm": 0.6154776811599731, "learning_rate": 1.7323837452869712e-05, "loss": 1.3178, "step": 1598 }, { "epoch": 0.669878508588186, "grad_norm": 0.6418588757514954, "learning_rate": 1.7322161709258486e-05, "loss": 1.2213, "step": 1599 }, { "epoch": 0.6702974444909929, "grad_norm": 0.6044167876243591, "learning_rate": 1.7320485965647257e-05, "loss": 1.1615, "step": 1600 }, { "epoch": 0.6707163803937998, "grad_norm": 0.5364164113998413, "learning_rate": 1.7318810222036028e-05, "loss": 1.2073, "step": 1601 }, { "epoch": 0.6711353162966066, "grad_norm": 0.5845683813095093, "learning_rate": 1.7317134478424802e-05, "loss": 1.289, "step": 1602 }, { "epoch": 0.6715542521994134, "grad_norm": 0.6288013458251953, "learning_rate": 1.7315458734813576e-05, "loss": 1.198, "step": 1603 }, { "epoch": 0.6719731881022204, "grad_norm": 0.5680230259895325, "learning_rate": 1.7313782991202347e-05, "loss": 1.281, "step": 1604 }, { "epoch": 0.6723921240050272, "grad_norm": 0.5734537839889526, "learning_rate": 1.7312107247591118e-05, "loss": 1.1509, "step": 1605 }, { "epoch": 0.6728110599078341, "grad_norm": 0.5385348796844482, "learning_rate": 1.731043150397989e-05, "loss": 1.2579, "step": 1606 }, { "epoch": 0.673229995810641, "grad_norm": 0.612383246421814, "learning_rate": 1.7308755760368666e-05, "loss": 1.2323, "step": 1607 }, { "epoch": 0.6736489317134479, "grad_norm": 0.5109977126121521, "learning_rate": 1.7307080016757437e-05, "loss": 1.2353, "step": 1608 }, { "epoch": 0.6740678676162547, "grad_norm": 0.5794051289558411, "learning_rate": 1.730540427314621e-05, "loss": 1.2557, "step": 1609 }, { "epoch": 0.6744868035190615, "grad_norm": 0.5295030474662781, "learning_rate": 1.730372852953498e-05, "loss": 1.1772, "step": 1610 }, { "epoch": 0.6749057394218685, "grad_norm": 0.5550644397735596, "learning_rate": 1.7302052785923756e-05, "loss": 1.2747, "step": 1611 }, { "epoch": 0.6753246753246753, "grad_norm": 0.6166117787361145, "learning_rate": 1.730037704231253e-05, "loss": 1.2975, "step": 1612 }, { "epoch": 0.6757436112274822, "grad_norm": 0.5740583539009094, "learning_rate": 1.72987012987013e-05, "loss": 1.2304, "step": 1613 }, { "epoch": 0.6761625471302891, "grad_norm": 0.6105713248252869, "learning_rate": 1.729702555509007e-05, "loss": 1.2092, "step": 1614 }, { "epoch": 0.676581483033096, "grad_norm": 0.5549275279045105, "learning_rate": 1.7295349811478845e-05, "loss": 1.1993, "step": 1615 }, { "epoch": 0.6770004189359028, "grad_norm": 0.48317986726760864, "learning_rate": 1.729367406786762e-05, "loss": 1.2793, "step": 1616 }, { "epoch": 0.6774193548387096, "grad_norm": 0.6312034726142883, "learning_rate": 1.729199832425639e-05, "loss": 1.2385, "step": 1617 }, { "epoch": 0.6778382907415166, "grad_norm": 0.5260562300682068, "learning_rate": 1.729032258064516e-05, "loss": 1.112, "step": 1618 }, { "epoch": 0.6782572266443234, "grad_norm": 0.473259299993515, "learning_rate": 1.7288646837033935e-05, "loss": 1.2807, "step": 1619 }, { "epoch": 0.6786761625471303, "grad_norm": 0.5537641048431396, "learning_rate": 1.728697109342271e-05, "loss": 1.2886, "step": 1620 }, { "epoch": 0.6790950984499372, "grad_norm": 0.5721163749694824, "learning_rate": 1.728529534981148e-05, "loss": 1.2336, "step": 1621 }, { "epoch": 0.679514034352744, "grad_norm": 0.4833151698112488, "learning_rate": 1.7283619606200254e-05, "loss": 1.2387, "step": 1622 }, { "epoch": 0.6799329702555509, "grad_norm": 0.5541830658912659, "learning_rate": 1.7281943862589025e-05, "loss": 1.2588, "step": 1623 }, { "epoch": 0.6803519061583577, "grad_norm": 0.523709237575531, "learning_rate": 1.72802681189778e-05, "loss": 1.3332, "step": 1624 }, { "epoch": 0.6807708420611647, "grad_norm": 0.6294167637825012, "learning_rate": 1.727859237536657e-05, "loss": 1.2496, "step": 1625 }, { "epoch": 0.6811897779639715, "grad_norm": 0.605088472366333, "learning_rate": 1.7276916631755344e-05, "loss": 1.2834, "step": 1626 }, { "epoch": 0.6816087138667783, "grad_norm": 0.4962644577026367, "learning_rate": 1.7275240888144114e-05, "loss": 1.1532, "step": 1627 }, { "epoch": 0.6820276497695853, "grad_norm": 0.5658184289932251, "learning_rate": 1.727356514453289e-05, "loss": 1.3236, "step": 1628 }, { "epoch": 0.6824465856723921, "grad_norm": 0.6022571921348572, "learning_rate": 1.727188940092166e-05, "loss": 1.1745, "step": 1629 }, { "epoch": 0.682865521575199, "grad_norm": 0.5666802525520325, "learning_rate": 1.7270213657310433e-05, "loss": 1.3137, "step": 1630 }, { "epoch": 0.6832844574780058, "grad_norm": 0.6718252897262573, "learning_rate": 1.7268537913699208e-05, "loss": 1.2308, "step": 1631 }, { "epoch": 0.6837033933808128, "grad_norm": 0.5680360198020935, "learning_rate": 1.726686217008798e-05, "loss": 1.2927, "step": 1632 }, { "epoch": 0.6841223292836196, "grad_norm": 0.6257114410400391, "learning_rate": 1.726518642647675e-05, "loss": 1.1433, "step": 1633 }, { "epoch": 0.6845412651864264, "grad_norm": 0.5863735675811768, "learning_rate": 1.7263510682865523e-05, "loss": 1.1972, "step": 1634 }, { "epoch": 0.6849602010892334, "grad_norm": 0.5488491654396057, "learning_rate": 1.7261834939254297e-05, "loss": 1.1822, "step": 1635 }, { "epoch": 0.6853791369920402, "grad_norm": 0.602595329284668, "learning_rate": 1.7260159195643068e-05, "loss": 1.2805, "step": 1636 }, { "epoch": 0.6857980728948471, "grad_norm": 0.5142866969108582, "learning_rate": 1.725848345203184e-05, "loss": 1.1667, "step": 1637 }, { "epoch": 0.6862170087976539, "grad_norm": 0.5898123383522034, "learning_rate": 1.7256807708420613e-05, "loss": 1.3527, "step": 1638 }, { "epoch": 0.6866359447004609, "grad_norm": 0.5275459289550781, "learning_rate": 1.7255131964809387e-05, "loss": 1.3093, "step": 1639 }, { "epoch": 0.6870548806032677, "grad_norm": 0.5887928605079651, "learning_rate": 1.7253456221198158e-05, "loss": 1.1204, "step": 1640 }, { "epoch": 0.6874738165060745, "grad_norm": 0.5470407605171204, "learning_rate": 1.725178047758693e-05, "loss": 1.2592, "step": 1641 }, { "epoch": 0.6878927524088815, "grad_norm": 0.5267928838729858, "learning_rate": 1.7250104733975703e-05, "loss": 1.1619, "step": 1642 }, { "epoch": 0.6883116883116883, "grad_norm": 0.44696980714797974, "learning_rate": 1.7248428990364477e-05, "loss": 1.2691, "step": 1643 }, { "epoch": 0.6887306242144952, "grad_norm": 0.6417440176010132, "learning_rate": 1.7246753246753248e-05, "loss": 1.2228, "step": 1644 }, { "epoch": 0.6891495601173021, "grad_norm": 0.4743337333202362, "learning_rate": 1.724507750314202e-05, "loss": 1.2839, "step": 1645 }, { "epoch": 0.689568496020109, "grad_norm": 0.5349746942520142, "learning_rate": 1.7243401759530792e-05, "loss": 1.3472, "step": 1646 }, { "epoch": 0.6899874319229158, "grad_norm": 0.48241063952445984, "learning_rate": 1.7241726015919567e-05, "loss": 1.3452, "step": 1647 }, { "epoch": 0.6904063678257226, "grad_norm": 0.635733962059021, "learning_rate": 1.7240050272308337e-05, "loss": 1.2961, "step": 1648 }, { "epoch": 0.6908253037285296, "grad_norm": 0.5365099310874939, "learning_rate": 1.723837452869711e-05, "loss": 1.311, "step": 1649 }, { "epoch": 0.6912442396313364, "grad_norm": 0.6021907329559326, "learning_rate": 1.7236698785085882e-05, "loss": 1.3043, "step": 1650 }, { "epoch": 0.6916631755341432, "grad_norm": 0.5134010910987854, "learning_rate": 1.7235023041474656e-05, "loss": 1.2888, "step": 1651 }, { "epoch": 0.6920821114369502, "grad_norm": 0.5248516798019409, "learning_rate": 1.7233347297863427e-05, "loss": 1.2437, "step": 1652 }, { "epoch": 0.692501047339757, "grad_norm": 0.598885715007782, "learning_rate": 1.72316715542522e-05, "loss": 1.212, "step": 1653 }, { "epoch": 0.6929199832425639, "grad_norm": 0.523899257183075, "learning_rate": 1.7229995810640975e-05, "loss": 1.3648, "step": 1654 }, { "epoch": 0.6933389191453707, "grad_norm": 0.5873257517814636, "learning_rate": 1.7228320067029746e-05, "loss": 1.3036, "step": 1655 }, { "epoch": 0.6937578550481777, "grad_norm": 0.5090556144714355, "learning_rate": 1.7226644323418517e-05, "loss": 1.276, "step": 1656 }, { "epoch": 0.6941767909509845, "grad_norm": 0.5350027084350586, "learning_rate": 1.722496857980729e-05, "loss": 1.2506, "step": 1657 }, { "epoch": 0.6945957268537913, "grad_norm": 0.5707224607467651, "learning_rate": 1.7223292836196065e-05, "loss": 1.3632, "step": 1658 }, { "epoch": 0.6950146627565983, "grad_norm": 0.6017513275146484, "learning_rate": 1.7221617092584836e-05, "loss": 1.1615, "step": 1659 }, { "epoch": 0.6954335986594051, "grad_norm": 0.5692595839500427, "learning_rate": 1.7219941348973606e-05, "loss": 1.2463, "step": 1660 }, { "epoch": 0.695852534562212, "grad_norm": 0.510615885257721, "learning_rate": 1.721826560536238e-05, "loss": 1.1989, "step": 1661 }, { "epoch": 0.6962714704650188, "grad_norm": 0.5171481370925903, "learning_rate": 1.7216589861751155e-05, "loss": 1.255, "step": 1662 }, { "epoch": 0.6966904063678258, "grad_norm": 0.5737592577934265, "learning_rate": 1.7214914118139925e-05, "loss": 1.2769, "step": 1663 }, { "epoch": 0.6971093422706326, "grad_norm": 0.4949120879173279, "learning_rate": 1.72132383745287e-05, "loss": 1.2456, "step": 1664 }, { "epoch": 0.6975282781734394, "grad_norm": 0.5995522737503052, "learning_rate": 1.721156263091747e-05, "loss": 1.279, "step": 1665 }, { "epoch": 0.6979472140762464, "grad_norm": 0.5222731828689575, "learning_rate": 1.7209886887306244e-05, "loss": 1.3125, "step": 1666 }, { "epoch": 0.6983661499790532, "grad_norm": 0.5995374917984009, "learning_rate": 1.7208211143695015e-05, "loss": 1.2573, "step": 1667 }, { "epoch": 0.6987850858818601, "grad_norm": 0.785426676273346, "learning_rate": 1.720653540008379e-05, "loss": 1.3187, "step": 1668 }, { "epoch": 0.6992040217846669, "grad_norm": 0.5812617540359497, "learning_rate": 1.720485965647256e-05, "loss": 1.1975, "step": 1669 }, { "epoch": 0.6996229576874738, "grad_norm": 0.5140098333358765, "learning_rate": 1.7203183912861334e-05, "loss": 1.2337, "step": 1670 }, { "epoch": 0.7000418935902807, "grad_norm": 0.5543442964553833, "learning_rate": 1.7201508169250105e-05, "loss": 1.2744, "step": 1671 }, { "epoch": 0.7004608294930875, "grad_norm": 0.502113401889801, "learning_rate": 1.719983242563888e-05, "loss": 1.2963, "step": 1672 }, { "epoch": 0.7008797653958945, "grad_norm": 0.4547468423843384, "learning_rate": 1.719815668202765e-05, "loss": 1.3182, "step": 1673 }, { "epoch": 0.7012987012987013, "grad_norm": 0.5855655670166016, "learning_rate": 1.7196480938416424e-05, "loss": 1.1446, "step": 1674 }, { "epoch": 0.7017176372015081, "grad_norm": 0.5127655863761902, "learning_rate": 1.7194805194805195e-05, "loss": 1.2076, "step": 1675 }, { "epoch": 0.702136573104315, "grad_norm": 0.47787871956825256, "learning_rate": 1.719312945119397e-05, "loss": 1.2506, "step": 1676 }, { "epoch": 0.7025555090071219, "grad_norm": 0.6545142531394958, "learning_rate": 1.7191453707582743e-05, "loss": 1.3022, "step": 1677 }, { "epoch": 0.7029744449099288, "grad_norm": 0.605778694152832, "learning_rate": 1.7189777963971514e-05, "loss": 1.1821, "step": 1678 }, { "epoch": 0.7033933808127356, "grad_norm": 0.5241637229919434, "learning_rate": 1.7188102220360284e-05, "loss": 1.2444, "step": 1679 }, { "epoch": 0.7038123167155426, "grad_norm": 0.5467069745063782, "learning_rate": 1.718642647674906e-05, "loss": 1.4042, "step": 1680 }, { "epoch": 0.7042312526183494, "grad_norm": 0.7407732009887695, "learning_rate": 1.7184750733137833e-05, "loss": 1.2168, "step": 1681 }, { "epoch": 0.7046501885211562, "grad_norm": 0.49953165650367737, "learning_rate": 1.7183074989526603e-05, "loss": 1.1827, "step": 1682 }, { "epoch": 0.7050691244239631, "grad_norm": 0.5572872161865234, "learning_rate": 1.7181399245915374e-05, "loss": 1.3108, "step": 1683 }, { "epoch": 0.70548806032677, "grad_norm": 0.5294314622879028, "learning_rate": 1.7179723502304148e-05, "loss": 1.2085, "step": 1684 }, { "epoch": 0.7059069962295769, "grad_norm": 0.5524981617927551, "learning_rate": 1.7178047758692922e-05, "loss": 1.2358, "step": 1685 }, { "epoch": 0.7063259321323837, "grad_norm": 0.5647136569023132, "learning_rate": 1.7176372015081693e-05, "loss": 1.1825, "step": 1686 }, { "epoch": 0.7067448680351907, "grad_norm": 0.5697317719459534, "learning_rate": 1.7174696271470467e-05, "loss": 1.2713, "step": 1687 }, { "epoch": 0.7071638039379975, "grad_norm": 0.49558648467063904, "learning_rate": 1.7173020527859238e-05, "loss": 1.2092, "step": 1688 }, { "epoch": 0.7075827398408043, "grad_norm": 0.544297993183136, "learning_rate": 1.7171344784248012e-05, "loss": 1.4236, "step": 1689 }, { "epoch": 0.7080016757436113, "grad_norm": 0.597606360912323, "learning_rate": 1.7169669040636786e-05, "loss": 1.1613, "step": 1690 }, { "epoch": 0.7084206116464181, "grad_norm": 0.5814008712768555, "learning_rate": 1.7167993297025557e-05, "loss": 1.2945, "step": 1691 }, { "epoch": 0.708839547549225, "grad_norm": 0.5905143022537231, "learning_rate": 1.7166317553414328e-05, "loss": 1.2577, "step": 1692 }, { "epoch": 0.7092584834520318, "grad_norm": 0.5997274518013, "learning_rate": 1.7164641809803102e-05, "loss": 1.1853, "step": 1693 }, { "epoch": 0.7096774193548387, "grad_norm": 0.553175151348114, "learning_rate": 1.7162966066191876e-05, "loss": 1.3054, "step": 1694 }, { "epoch": 0.7100963552576456, "grad_norm": 0.6180306673049927, "learning_rate": 1.7161290322580647e-05, "loss": 1.2171, "step": 1695 }, { "epoch": 0.7105152911604524, "grad_norm": 0.5355980396270752, "learning_rate": 1.7159614578969418e-05, "loss": 1.3762, "step": 1696 }, { "epoch": 0.7109342270632594, "grad_norm": 0.5476637482643127, "learning_rate": 1.715793883535819e-05, "loss": 1.3788, "step": 1697 }, { "epoch": 0.7113531629660662, "grad_norm": 0.6408981084823608, "learning_rate": 1.7156263091746962e-05, "loss": 1.2557, "step": 1698 }, { "epoch": 0.711772098868873, "grad_norm": 0.6191065311431885, "learning_rate": 1.7154587348135736e-05, "loss": 1.1302, "step": 1699 }, { "epoch": 0.7121910347716799, "grad_norm": 0.5354841947555542, "learning_rate": 1.715291160452451e-05, "loss": 1.2238, "step": 1700 }, { "epoch": 0.7126099706744868, "grad_norm": 0.6878061890602112, "learning_rate": 1.715123586091328e-05, "loss": 1.2419, "step": 1701 }, { "epoch": 0.7130289065772937, "grad_norm": 0.5311233997344971, "learning_rate": 1.7149560117302052e-05, "loss": 1.2638, "step": 1702 }, { "epoch": 0.7134478424801005, "grad_norm": 0.501001238822937, "learning_rate": 1.7147884373690826e-05, "loss": 1.2798, "step": 1703 }, { "epoch": 0.7138667783829075, "grad_norm": 0.7188606858253479, "learning_rate": 1.71462086300796e-05, "loss": 1.2297, "step": 1704 }, { "epoch": 0.7142857142857143, "grad_norm": 0.6224846243858337, "learning_rate": 1.714453288646837e-05, "loss": 1.1887, "step": 1705 }, { "epoch": 0.7147046501885211, "grad_norm": 0.5109125971794128, "learning_rate": 1.7142857142857142e-05, "loss": 1.2833, "step": 1706 }, { "epoch": 0.715123586091328, "grad_norm": 0.6017783880233765, "learning_rate": 1.7141181399245916e-05, "loss": 1.3166, "step": 1707 }, { "epoch": 0.7155425219941349, "grad_norm": 0.5881832838058472, "learning_rate": 1.713950565563469e-05, "loss": 1.2493, "step": 1708 }, { "epoch": 0.7159614578969418, "grad_norm": 0.5642807483673096, "learning_rate": 1.7137829912023464e-05, "loss": 1.2963, "step": 1709 }, { "epoch": 0.7163803937997486, "grad_norm": 0.4961249828338623, "learning_rate": 1.7136154168412235e-05, "loss": 1.3942, "step": 1710 }, { "epoch": 0.7167993297025556, "grad_norm": 0.5828210711479187, "learning_rate": 1.7134478424801006e-05, "loss": 1.225, "step": 1711 }, { "epoch": 0.7172182656053624, "grad_norm": 0.6071931719779968, "learning_rate": 1.713280268118978e-05, "loss": 1.2534, "step": 1712 }, { "epoch": 0.7176372015081692, "grad_norm": 0.5025401711463928, "learning_rate": 1.7131126937578554e-05, "loss": 1.2501, "step": 1713 }, { "epoch": 0.7180561374109761, "grad_norm": 0.6149885654449463, "learning_rate": 1.7129451193967325e-05, "loss": 1.4251, "step": 1714 }, { "epoch": 0.718475073313783, "grad_norm": 0.5417464375495911, "learning_rate": 1.7127775450356095e-05, "loss": 1.2254, "step": 1715 }, { "epoch": 0.7188940092165899, "grad_norm": 0.5729048848152161, "learning_rate": 1.712609970674487e-05, "loss": 1.261, "step": 1716 }, { "epoch": 0.7193129451193967, "grad_norm": 0.6352499127388, "learning_rate": 1.7124423963133644e-05, "loss": 1.2938, "step": 1717 }, { "epoch": 0.7197318810222036, "grad_norm": 0.408060759305954, "learning_rate": 1.7122748219522414e-05, "loss": 1.2557, "step": 1718 }, { "epoch": 0.7201508169250105, "grad_norm": 0.5684776902198792, "learning_rate": 1.7121072475911185e-05, "loss": 1.1974, "step": 1719 }, { "epoch": 0.7205697528278173, "grad_norm": 0.5312014818191528, "learning_rate": 1.711939673229996e-05, "loss": 1.3399, "step": 1720 }, { "epoch": 0.7209886887306242, "grad_norm": 0.5885863900184631, "learning_rate": 1.7117720988688733e-05, "loss": 1.3291, "step": 1721 }, { "epoch": 0.7214076246334311, "grad_norm": 0.5011883974075317, "learning_rate": 1.7116045245077504e-05, "loss": 1.1517, "step": 1722 }, { "epoch": 0.721826560536238, "grad_norm": 0.5285312533378601, "learning_rate": 1.7114369501466278e-05, "loss": 1.3462, "step": 1723 }, { "epoch": 0.7222454964390448, "grad_norm": 0.5525001883506775, "learning_rate": 1.711269375785505e-05, "loss": 1.1781, "step": 1724 }, { "epoch": 0.7226644323418517, "grad_norm": 0.5384438633918762, "learning_rate": 1.7111018014243823e-05, "loss": 1.2977, "step": 1725 }, { "epoch": 0.7230833682446586, "grad_norm": 0.529953122138977, "learning_rate": 1.7109342270632594e-05, "loss": 1.2906, "step": 1726 }, { "epoch": 0.7235023041474654, "grad_norm": 0.5288045406341553, "learning_rate": 1.7107666527021368e-05, "loss": 1.2025, "step": 1727 }, { "epoch": 0.7239212400502724, "grad_norm": 0.5070176124572754, "learning_rate": 1.710599078341014e-05, "loss": 1.2482, "step": 1728 }, { "epoch": 0.7243401759530792, "grad_norm": 0.5584984421730042, "learning_rate": 1.710431503979891e-05, "loss": 1.2481, "step": 1729 }, { "epoch": 0.724759111855886, "grad_norm": 0.4968102276325226, "learning_rate": 1.7102639296187684e-05, "loss": 1.3021, "step": 1730 }, { "epoch": 0.7251780477586929, "grad_norm": 0.5356294512748718, "learning_rate": 1.7100963552576458e-05, "loss": 1.2596, "step": 1731 }, { "epoch": 0.7255969836614998, "grad_norm": 0.47836199402809143, "learning_rate": 1.7099287808965232e-05, "loss": 1.2804, "step": 1732 }, { "epoch": 0.7260159195643067, "grad_norm": 0.5201926231384277, "learning_rate": 1.7097612065354003e-05, "loss": 1.2224, "step": 1733 }, { "epoch": 0.7264348554671135, "grad_norm": 0.5267103314399719, "learning_rate": 1.7095936321742773e-05, "loss": 1.2194, "step": 1734 }, { "epoch": 0.7268537913699205, "grad_norm": 0.5259394645690918, "learning_rate": 1.7094260578131548e-05, "loss": 1.3688, "step": 1735 }, { "epoch": 0.7272727272727273, "grad_norm": 0.5294287800788879, "learning_rate": 1.709258483452032e-05, "loss": 1.4251, "step": 1736 }, { "epoch": 0.7276916631755341, "grad_norm": 1.0120165348052979, "learning_rate": 1.7090909090909092e-05, "loss": 1.2244, "step": 1737 }, { "epoch": 0.728110599078341, "grad_norm": 0.5795239806175232, "learning_rate": 1.7089233347297863e-05, "loss": 1.2523, "step": 1738 }, { "epoch": 0.7285295349811479, "grad_norm": 0.6280587911605835, "learning_rate": 1.7087557603686637e-05, "loss": 1.2335, "step": 1739 }, { "epoch": 0.7289484708839548, "grad_norm": 0.5002269744873047, "learning_rate": 1.708588186007541e-05, "loss": 1.2827, "step": 1740 }, { "epoch": 0.7293674067867616, "grad_norm": 0.4950065612792969, "learning_rate": 1.7084206116464182e-05, "loss": 1.3038, "step": 1741 }, { "epoch": 0.7297863426895685, "grad_norm": 0.460224449634552, "learning_rate": 1.7082530372852956e-05, "loss": 1.1836, "step": 1742 }, { "epoch": 0.7302052785923754, "grad_norm": 0.6309815049171448, "learning_rate": 1.7080854629241727e-05, "loss": 1.2557, "step": 1743 }, { "epoch": 0.7306242144951822, "grad_norm": 0.5564061999320984, "learning_rate": 1.70791788856305e-05, "loss": 1.1424, "step": 1744 }, { "epoch": 0.7310431503979891, "grad_norm": 0.5185852646827698, "learning_rate": 1.7077503142019272e-05, "loss": 1.3146, "step": 1745 }, { "epoch": 0.731462086300796, "grad_norm": 0.5451443195343018, "learning_rate": 1.7075827398408046e-05, "loss": 1.3612, "step": 1746 }, { "epoch": 0.7318810222036028, "grad_norm": 0.5353172421455383, "learning_rate": 1.7074151654796817e-05, "loss": 1.2761, "step": 1747 }, { "epoch": 0.7322999581064097, "grad_norm": 0.5700138807296753, "learning_rate": 1.707247591118559e-05, "loss": 1.3542, "step": 1748 }, { "epoch": 0.7327188940092166, "grad_norm": 0.5654558539390564, "learning_rate": 1.707080016757436e-05, "loss": 1.3026, "step": 1749 }, { "epoch": 0.7331378299120235, "grad_norm": 0.5688120722770691, "learning_rate": 1.7069124423963136e-05, "loss": 1.2222, "step": 1750 }, { "epoch": 0.7335567658148303, "grad_norm": 0.6359266638755798, "learning_rate": 1.7067448680351906e-05, "loss": 1.2349, "step": 1751 }, { "epoch": 0.7339757017176372, "grad_norm": 0.5078823566436768, "learning_rate": 1.706577293674068e-05, "loss": 1.3657, "step": 1752 }, { "epoch": 0.7343946376204441, "grad_norm": 0.4946519732475281, "learning_rate": 1.706409719312945e-05, "loss": 1.2786, "step": 1753 }, { "epoch": 0.7348135735232509, "grad_norm": 0.5672724843025208, "learning_rate": 1.7062421449518225e-05, "loss": 1.3489, "step": 1754 }, { "epoch": 0.7352325094260578, "grad_norm": 0.5652905702590942, "learning_rate": 1.7060745705907e-05, "loss": 1.3327, "step": 1755 }, { "epoch": 0.7356514453288647, "grad_norm": 0.6232276558876038, "learning_rate": 1.705906996229577e-05, "loss": 1.2631, "step": 1756 }, { "epoch": 0.7360703812316716, "grad_norm": 0.5762819051742554, "learning_rate": 1.705739421868454e-05, "loss": 1.2234, "step": 1757 }, { "epoch": 0.7364893171344784, "grad_norm": 0.5793471932411194, "learning_rate": 1.7055718475073315e-05, "loss": 1.2623, "step": 1758 }, { "epoch": 0.7369082530372852, "grad_norm": 0.7222926616668701, "learning_rate": 1.705404273146209e-05, "loss": 1.205, "step": 1759 }, { "epoch": 0.7373271889400922, "grad_norm": 0.5097273588180542, "learning_rate": 1.705236698785086e-05, "loss": 1.2533, "step": 1760 }, { "epoch": 0.737746124842899, "grad_norm": 0.4821189045906067, "learning_rate": 1.705069124423963e-05, "loss": 1.2594, "step": 1761 }, { "epoch": 0.7381650607457059, "grad_norm": 0.5130928158760071, "learning_rate": 1.7049015500628405e-05, "loss": 1.3752, "step": 1762 }, { "epoch": 0.7385839966485128, "grad_norm": 0.5549164414405823, "learning_rate": 1.704733975701718e-05, "loss": 1.2113, "step": 1763 }, { "epoch": 0.7390029325513197, "grad_norm": 0.5267959237098694, "learning_rate": 1.704566401340595e-05, "loss": 1.2232, "step": 1764 }, { "epoch": 0.7394218684541265, "grad_norm": 0.48591282963752747, "learning_rate": 1.7043988269794724e-05, "loss": 1.2446, "step": 1765 }, { "epoch": 0.7398408043569333, "grad_norm": 0.5370330214500427, "learning_rate": 1.7042312526183495e-05, "loss": 1.2324, "step": 1766 }, { "epoch": 0.7402597402597403, "grad_norm": 0.619137167930603, "learning_rate": 1.704063678257227e-05, "loss": 1.2344, "step": 1767 }, { "epoch": 0.7406786761625471, "grad_norm": 0.5225730538368225, "learning_rate": 1.703896103896104e-05, "loss": 1.2983, "step": 1768 }, { "epoch": 0.741097612065354, "grad_norm": 0.5694467425346375, "learning_rate": 1.7037285295349814e-05, "loss": 1.2372, "step": 1769 }, { "epoch": 0.7415165479681609, "grad_norm": 0.6075475215911865, "learning_rate": 1.7035609551738584e-05, "loss": 1.2245, "step": 1770 }, { "epoch": 0.7419354838709677, "grad_norm": 0.5353560447692871, "learning_rate": 1.703393380812736e-05, "loss": 1.2692, "step": 1771 }, { "epoch": 0.7423544197737746, "grad_norm": 0.46673157811164856, "learning_rate": 1.703225806451613e-05, "loss": 1.3435, "step": 1772 }, { "epoch": 0.7427733556765815, "grad_norm": 0.6203951239585876, "learning_rate": 1.7030582320904903e-05, "loss": 1.2308, "step": 1773 }, { "epoch": 0.7431922915793884, "grad_norm": 0.5227031707763672, "learning_rate": 1.7028906577293674e-05, "loss": 1.2218, "step": 1774 }, { "epoch": 0.7436112274821952, "grad_norm": 0.6431291699409485, "learning_rate": 1.7027230833682448e-05, "loss": 1.1401, "step": 1775 }, { "epoch": 0.744030163385002, "grad_norm": 0.5463534593582153, "learning_rate": 1.702555509007122e-05, "loss": 1.2503, "step": 1776 }, { "epoch": 0.744449099287809, "grad_norm": 0.47505325078964233, "learning_rate": 1.7023879346459993e-05, "loss": 1.3313, "step": 1777 }, { "epoch": 0.7448680351906158, "grad_norm": 0.5586497783660889, "learning_rate": 1.7022203602848767e-05, "loss": 1.3529, "step": 1778 }, { "epoch": 0.7452869710934227, "grad_norm": 0.5530198216438293, "learning_rate": 1.7020527859237538e-05, "loss": 1.2551, "step": 1779 }, { "epoch": 0.7457059069962296, "grad_norm": 0.47585368156433105, "learning_rate": 1.701885211562631e-05, "loss": 1.308, "step": 1780 }, { "epoch": 0.7461248428990365, "grad_norm": 0.6783473491668701, "learning_rate": 1.7017176372015083e-05, "loss": 1.1153, "step": 1781 }, { "epoch": 0.7465437788018433, "grad_norm": 0.7258354425430298, "learning_rate": 1.7015500628403857e-05, "loss": 1.1545, "step": 1782 }, { "epoch": 0.7469627147046501, "grad_norm": 0.5559289455413818, "learning_rate": 1.7013824884792628e-05, "loss": 1.2177, "step": 1783 }, { "epoch": 0.7473816506074571, "grad_norm": 0.6248336434364319, "learning_rate": 1.70121491411814e-05, "loss": 1.1779, "step": 1784 }, { "epoch": 0.7478005865102639, "grad_norm": 0.5044069886207581, "learning_rate": 1.7010473397570173e-05, "loss": 1.2339, "step": 1785 }, { "epoch": 0.7482195224130708, "grad_norm": 0.6619997024536133, "learning_rate": 1.7008797653958947e-05, "loss": 1.2339, "step": 1786 }, { "epoch": 0.7486384583158777, "grad_norm": 0.5197588205337524, "learning_rate": 1.700712191034772e-05, "loss": 1.3281, "step": 1787 }, { "epoch": 0.7490573942186846, "grad_norm": 0.5700135231018066, "learning_rate": 1.700544616673649e-05, "loss": 1.1831, "step": 1788 }, { "epoch": 0.7494763301214914, "grad_norm": 0.5550621747970581, "learning_rate": 1.7003770423125262e-05, "loss": 1.197, "step": 1789 }, { "epoch": 0.7498952660242982, "grad_norm": 0.5478520393371582, "learning_rate": 1.7002094679514036e-05, "loss": 1.1966, "step": 1790 }, { "epoch": 0.7503142019271052, "grad_norm": 0.5300833582878113, "learning_rate": 1.700041893590281e-05, "loss": 1.2662, "step": 1791 }, { "epoch": 0.750733137829912, "grad_norm": 0.5896236300468445, "learning_rate": 1.699874319229158e-05, "loss": 1.1974, "step": 1792 }, { "epoch": 0.7511520737327189, "grad_norm": 0.5021079182624817, "learning_rate": 1.6997067448680352e-05, "loss": 1.2768, "step": 1793 }, { "epoch": 0.7515710096355258, "grad_norm": 0.5327545404434204, "learning_rate": 1.6995391705069126e-05, "loss": 1.2256, "step": 1794 }, { "epoch": 0.7519899455383326, "grad_norm": 0.530438244342804, "learning_rate": 1.6993715961457897e-05, "loss": 1.2859, "step": 1795 }, { "epoch": 0.7524088814411395, "grad_norm": 0.5752853751182556, "learning_rate": 1.699204021784667e-05, "loss": 1.2283, "step": 1796 }, { "epoch": 0.7528278173439463, "grad_norm": 0.4446302056312561, "learning_rate": 1.6990364474235442e-05, "loss": 1.1558, "step": 1797 }, { "epoch": 0.7532467532467533, "grad_norm": 0.5090763568878174, "learning_rate": 1.6988688730624216e-05, "loss": 1.2972, "step": 1798 }, { "epoch": 0.7536656891495601, "grad_norm": 0.5295231342315674, "learning_rate": 1.6987012987012987e-05, "loss": 1.3101, "step": 1799 }, { "epoch": 0.754084625052367, "grad_norm": 0.4900513291358948, "learning_rate": 1.698533724340176e-05, "loss": 1.2525, "step": 1800 } ], "logging_steps": 1.0, "max_steps": 11935, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 3.6932387271081984e+18, "train_batch_size": 12, "trial_name": null, "trial_params": null }