dchen0's picture
Upload folder using huggingface_hub
682446e verified
{
"best_global_step": 6500,
"best_metric": 0.9011890379601959,
"best_model_checkpoint": "/workspace/output/resnet50/checkpoint-6500",
"epoch": 0.9226401703335699,
"eval_steps": 500,
"global_step": 6500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0014194464158978,
"grad_norm": 3.2342276573181152,
"learning_rate": 9.999872249822569e-05,
"loss": 5.98863525390625,
"step": 10
},
{
"epoch": 0.0028388928317956,
"grad_norm": 3.3994972705841064,
"learning_rate": 9.99973030518098e-05,
"loss": 5.97633056640625,
"step": 20
},
{
"epoch": 0.0042583392476933995,
"grad_norm": 3.3180341720581055,
"learning_rate": 9.99958836053939e-05,
"loss": 5.97711181640625,
"step": 30
},
{
"epoch": 0.0056777856635912,
"grad_norm": 2.9379143714904785,
"learning_rate": 9.999446415897801e-05,
"loss": 5.9991455078125,
"step": 40
},
{
"epoch": 0.007097232079488999,
"grad_norm": 2.2698018550872803,
"learning_rate": 9.99930447125621e-05,
"loss": 5.96363525390625,
"step": 50
},
{
"epoch": 0.008516678495386799,
"grad_norm": 2.0626659393310547,
"learning_rate": 9.99916252661462e-05,
"loss": 5.96995849609375,
"step": 60
},
{
"epoch": 0.0099361249112846,
"grad_norm": 2.814460277557373,
"learning_rate": 9.999020581973031e-05,
"loss": 5.9493408203125,
"step": 70
},
{
"epoch": 0.0113555713271824,
"grad_norm": 2.871051788330078,
"learning_rate": 9.998878637331441e-05,
"loss": 5.9510498046875,
"step": 80
},
{
"epoch": 0.0127750177430802,
"grad_norm": 2.3897151947021484,
"learning_rate": 9.998736692689852e-05,
"loss": 5.94254150390625,
"step": 90
},
{
"epoch": 0.014194464158977998,
"grad_norm": 2.9910531044006348,
"learning_rate": 9.99859474804826e-05,
"loss": 5.9062255859375,
"step": 100
},
{
"epoch": 0.015613910574875798,
"grad_norm": 3.137518882751465,
"learning_rate": 9.998452803406672e-05,
"loss": 5.9070068359375,
"step": 110
},
{
"epoch": 0.017033356990773598,
"grad_norm": 3.021024703979492,
"learning_rate": 9.998310858765082e-05,
"loss": 5.87197265625,
"step": 120
},
{
"epoch": 0.018452803406671398,
"grad_norm": 3.499450445175171,
"learning_rate": 9.998168914123493e-05,
"loss": 5.8237548828125,
"step": 130
},
{
"epoch": 0.0198722498225692,
"grad_norm": 3.87576961517334,
"learning_rate": 9.998026969481902e-05,
"loss": 5.754150390625,
"step": 140
},
{
"epoch": 0.021291696238467,
"grad_norm": 3.9846458435058594,
"learning_rate": 9.997885024840313e-05,
"loss": 5.697198486328125,
"step": 150
},
{
"epoch": 0.0227111426543648,
"grad_norm": 4.339130878448486,
"learning_rate": 9.997743080198723e-05,
"loss": 5.63760986328125,
"step": 160
},
{
"epoch": 0.0241305890702626,
"grad_norm": 4.891483783721924,
"learning_rate": 9.997601135557133e-05,
"loss": 5.5271728515625,
"step": 170
},
{
"epoch": 0.0255500354861604,
"grad_norm": 5.147222995758057,
"learning_rate": 9.997459190915544e-05,
"loss": 5.45938720703125,
"step": 180
},
{
"epoch": 0.0269694819020582,
"grad_norm": 5.365755558013916,
"learning_rate": 9.997317246273954e-05,
"loss": 5.355255126953125,
"step": 190
},
{
"epoch": 0.028388928317955996,
"grad_norm": 5.888001918792725,
"learning_rate": 9.997175301632365e-05,
"loss": 5.1554931640625,
"step": 200
},
{
"epoch": 0.029808374733853796,
"grad_norm": 6.100172996520996,
"learning_rate": 9.997033356990773e-05,
"loss": 5.035284423828125,
"step": 210
},
{
"epoch": 0.031227821149751596,
"grad_norm": 6.491486549377441,
"learning_rate": 9.996891412349184e-05,
"loss": 4.899530029296875,
"step": 220
},
{
"epoch": 0.032647267565649396,
"grad_norm": 6.916806697845459,
"learning_rate": 9.996749467707594e-05,
"loss": 4.851350402832031,
"step": 230
},
{
"epoch": 0.034066713981547196,
"grad_norm": 6.837950706481934,
"learning_rate": 9.996607523066005e-05,
"loss": 4.726431274414063,
"step": 240
},
{
"epoch": 0.035486160397444996,
"grad_norm": 7.554074287414551,
"learning_rate": 9.996465578424415e-05,
"loss": 4.4839630126953125,
"step": 250
},
{
"epoch": 0.036905606813342796,
"grad_norm": 7.574995994567871,
"learning_rate": 9.996323633782825e-05,
"loss": 4.506732177734375,
"step": 260
},
{
"epoch": 0.0383250532292406,
"grad_norm": 7.498238563537598,
"learning_rate": 9.996181689141236e-05,
"loss": 4.319998168945313,
"step": 270
},
{
"epoch": 0.0397444996451384,
"grad_norm": 7.978142261505127,
"learning_rate": 9.996039744499645e-05,
"loss": 4.214613342285157,
"step": 280
},
{
"epoch": 0.0411639460610362,
"grad_norm": 8.194511413574219,
"learning_rate": 9.995897799858057e-05,
"loss": 4.212762451171875,
"step": 290
},
{
"epoch": 0.042583392476934,
"grad_norm": 8.136639595031738,
"learning_rate": 9.995755855216466e-05,
"loss": 4.009028625488281,
"step": 300
},
{
"epoch": 0.0440028388928318,
"grad_norm": 8.684012413024902,
"learning_rate": 9.995613910574876e-05,
"loss": 3.9817459106445314,
"step": 310
},
{
"epoch": 0.0454222853087296,
"grad_norm": 8.888952255249023,
"learning_rate": 9.995471965933286e-05,
"loss": 3.94019775390625,
"step": 320
},
{
"epoch": 0.0468417317246274,
"grad_norm": 8.79919719696045,
"learning_rate": 9.995330021291697e-05,
"loss": 3.9265777587890627,
"step": 330
},
{
"epoch": 0.0482611781405252,
"grad_norm": 8.571785926818848,
"learning_rate": 9.995188076650107e-05,
"loss": 3.7262115478515625,
"step": 340
},
{
"epoch": 0.049680624556423,
"grad_norm": 8.640142440795898,
"learning_rate": 9.995046132008518e-05,
"loss": 3.644915771484375,
"step": 350
},
{
"epoch": 0.0511000709723208,
"grad_norm": 9.322779655456543,
"learning_rate": 9.994904187366927e-05,
"loss": 3.644049072265625,
"step": 360
},
{
"epoch": 0.0525195173882186,
"grad_norm": 8.790424346923828,
"learning_rate": 9.994762242725337e-05,
"loss": 3.4869285583496095,
"step": 370
},
{
"epoch": 0.0539389638041164,
"grad_norm": 9.344154357910156,
"learning_rate": 9.994620298083748e-05,
"loss": 3.55142822265625,
"step": 380
},
{
"epoch": 0.05535841022001419,
"grad_norm": 8.807840347290039,
"learning_rate": 9.994478353442158e-05,
"loss": 3.4293190002441407,
"step": 390
},
{
"epoch": 0.05677785663591199,
"grad_norm": 9.36971378326416,
"learning_rate": 9.994336408800569e-05,
"loss": 3.429082489013672,
"step": 400
},
{
"epoch": 0.05819730305180979,
"grad_norm": 9.73521900177002,
"learning_rate": 9.994194464158977e-05,
"loss": 3.408639907836914,
"step": 410
},
{
"epoch": 0.05961674946770759,
"grad_norm": 9.646844863891602,
"learning_rate": 9.994052519517389e-05,
"loss": 3.1950119018554686,
"step": 420
},
{
"epoch": 0.06103619588360539,
"grad_norm": 9.722207069396973,
"learning_rate": 9.993910574875798e-05,
"loss": 3.4140243530273438,
"step": 430
},
{
"epoch": 0.06245564229950319,
"grad_norm": 10.609601020812988,
"learning_rate": 9.99376863023421e-05,
"loss": 3.320109558105469,
"step": 440
},
{
"epoch": 0.063875088715401,
"grad_norm": 10.271575927734375,
"learning_rate": 9.993626685592619e-05,
"loss": 3.232251739501953,
"step": 450
},
{
"epoch": 0.06529453513129879,
"grad_norm": 9.766585350036621,
"learning_rate": 9.993484740951029e-05,
"loss": 3.149517059326172,
"step": 460
},
{
"epoch": 0.0667139815471966,
"grad_norm": 10.358244895935059,
"learning_rate": 9.99334279630944e-05,
"loss": 3.1863967895507814,
"step": 470
},
{
"epoch": 0.06813342796309439,
"grad_norm": 10.473136901855469,
"learning_rate": 9.99320085166785e-05,
"loss": 3.222390365600586,
"step": 480
},
{
"epoch": 0.0695528743789922,
"grad_norm": 9.905110359191895,
"learning_rate": 9.993058907026261e-05,
"loss": 3.1823768615722656,
"step": 490
},
{
"epoch": 0.07097232079488999,
"grad_norm": 9.858973503112793,
"learning_rate": 9.99291696238467e-05,
"loss": 2.9202560424804687,
"step": 500
},
{
"epoch": 0.07097232079488999,
"eval_accuracy": 0.1867489031601704,
"eval_loss": 3.0744524002075195,
"eval_runtime": 31.2289,
"eval_samples_per_second": 503.605,
"eval_steps_per_second": 15.755,
"step": 500
},
{
"epoch": 0.0723917672107878,
"grad_norm": 10.224215507507324,
"learning_rate": 9.992775017743082e-05,
"loss": 3.0410499572753906,
"step": 510
},
{
"epoch": 0.07381121362668559,
"grad_norm": 9.867650032043457,
"learning_rate": 9.99263307310149e-05,
"loss": 3.116912078857422,
"step": 520
},
{
"epoch": 0.07523066004258339,
"grad_norm": 10.343064308166504,
"learning_rate": 9.992491128459901e-05,
"loss": 3.06390266418457,
"step": 530
},
{
"epoch": 0.0766501064584812,
"grad_norm": 10.38116455078125,
"learning_rate": 9.992349183818311e-05,
"loss": 2.973680114746094,
"step": 540
},
{
"epoch": 0.07806955287437899,
"grad_norm": 10.979643821716309,
"learning_rate": 9.992207239176722e-05,
"loss": 3.0906436920166014,
"step": 550
},
{
"epoch": 0.0794889992902768,
"grad_norm": 10.06657886505127,
"learning_rate": 9.992065294535132e-05,
"loss": 3.0091484069824217,
"step": 560
},
{
"epoch": 0.08090844570617459,
"grad_norm": 10.663322448730469,
"learning_rate": 9.991923349893541e-05,
"loss": 2.862255859375,
"step": 570
},
{
"epoch": 0.0823278921220724,
"grad_norm": 9.277785301208496,
"learning_rate": 9.991781405251952e-05,
"loss": 2.8638259887695314,
"step": 580
},
{
"epoch": 0.08374733853797019,
"grad_norm": 10.807332038879395,
"learning_rate": 9.991639460610362e-05,
"loss": 2.732352066040039,
"step": 590
},
{
"epoch": 0.085166784953868,
"grad_norm": 9.970373153686523,
"learning_rate": 9.991497515968773e-05,
"loss": 2.736968231201172,
"step": 600
},
{
"epoch": 0.08658623136976579,
"grad_norm": 11.008269309997559,
"learning_rate": 9.991355571327183e-05,
"loss": 2.7735246658325194,
"step": 610
},
{
"epoch": 0.0880056777856636,
"grad_norm": 8.758193969726562,
"learning_rate": 9.991213626685593e-05,
"loss": 2.5436214447021483,
"step": 620
},
{
"epoch": 0.08942512420156139,
"grad_norm": 11.253259658813477,
"learning_rate": 9.991071682044003e-05,
"loss": 2.748835563659668,
"step": 630
},
{
"epoch": 0.0908445706174592,
"grad_norm": 10.979547500610352,
"learning_rate": 9.990929737402414e-05,
"loss": 2.7314834594726562,
"step": 640
},
{
"epoch": 0.09226401703335699,
"grad_norm": 11.182887077331543,
"learning_rate": 9.990787792760823e-05,
"loss": 2.645678901672363,
"step": 650
},
{
"epoch": 0.0936834634492548,
"grad_norm": 10.636208534240723,
"learning_rate": 9.990645848119234e-05,
"loss": 2.5704013824462892,
"step": 660
},
{
"epoch": 0.09510290986515259,
"grad_norm": 10.351170539855957,
"learning_rate": 9.990503903477644e-05,
"loss": 2.5628406524658205,
"step": 670
},
{
"epoch": 0.0965223562810504,
"grad_norm": 9.914809226989746,
"learning_rate": 9.990361958836054e-05,
"loss": 2.5872230529785156,
"step": 680
},
{
"epoch": 0.09794180269694819,
"grad_norm": 10.839837074279785,
"learning_rate": 9.990220014194465e-05,
"loss": 2.490940475463867,
"step": 690
},
{
"epoch": 0.099361249112846,
"grad_norm": 11.259613990783691,
"learning_rate": 9.990078069552875e-05,
"loss": 2.64483585357666,
"step": 700
},
{
"epoch": 0.10078069552874379,
"grad_norm": 11.213078498840332,
"learning_rate": 9.989936124911286e-05,
"loss": 2.5397150039672853,
"step": 710
},
{
"epoch": 0.1022001419446416,
"grad_norm": 10.366206169128418,
"learning_rate": 9.989794180269694e-05,
"loss": 2.457781219482422,
"step": 720
},
{
"epoch": 0.10361958836053939,
"grad_norm": 11.44458293914795,
"learning_rate": 9.989652235628105e-05,
"loss": 2.5090484619140625,
"step": 730
},
{
"epoch": 0.1050390347764372,
"grad_norm": 11.689805030822754,
"learning_rate": 9.989510290986515e-05,
"loss": 2.409171485900879,
"step": 740
},
{
"epoch": 0.10645848119233499,
"grad_norm": 10.568279266357422,
"learning_rate": 9.989368346344926e-05,
"loss": 2.3308380126953123,
"step": 750
},
{
"epoch": 0.1078779276082328,
"grad_norm": 11.917696952819824,
"learning_rate": 9.989226401703337e-05,
"loss": 2.3733493804931642,
"step": 760
},
{
"epoch": 0.10929737402413059,
"grad_norm": 9.960722923278809,
"learning_rate": 9.989098651525906e-05,
"loss": 2.4058095932006838,
"step": 770
},
{
"epoch": 0.11071682044002838,
"grad_norm": 11.068999290466309,
"learning_rate": 9.988956706884315e-05,
"loss": 2.4371658325195313,
"step": 780
},
{
"epoch": 0.11213626685592619,
"grad_norm": 10.340009689331055,
"learning_rate": 9.988814762242725e-05,
"loss": 2.2587520599365236,
"step": 790
},
{
"epoch": 0.11355571327182398,
"grad_norm": 9.941303253173828,
"learning_rate": 9.988672817601136e-05,
"loss": 2.268446350097656,
"step": 800
},
{
"epoch": 0.11497515968772179,
"grad_norm": 11.490272521972656,
"learning_rate": 9.988530872959546e-05,
"loss": 2.471067428588867,
"step": 810
},
{
"epoch": 0.11639460610361958,
"grad_norm": 10.67241382598877,
"learning_rate": 9.988388928317957e-05,
"loss": 2.3497791290283203,
"step": 820
},
{
"epoch": 0.11781405251951739,
"grad_norm": 10.710894584655762,
"learning_rate": 9.988246983676367e-05,
"loss": 2.1724626541137697,
"step": 830
},
{
"epoch": 0.11923349893541518,
"grad_norm": 10.985452651977539,
"learning_rate": 9.988105039034778e-05,
"loss": 2.1848114013671873,
"step": 840
},
{
"epoch": 0.12065294535131299,
"grad_norm": 10.063145637512207,
"learning_rate": 9.987963094393186e-05,
"loss": 2.180558776855469,
"step": 850
},
{
"epoch": 0.12207239176721078,
"grad_norm": 11.236614227294922,
"learning_rate": 9.987821149751597e-05,
"loss": 2.282668876647949,
"step": 860
},
{
"epoch": 0.12349183818310859,
"grad_norm": 10.98898983001709,
"learning_rate": 9.987679205110007e-05,
"loss": 2.235186767578125,
"step": 870
},
{
"epoch": 0.12491128459900638,
"grad_norm": 11.805492401123047,
"learning_rate": 9.987537260468418e-05,
"loss": 2.2264921188354494,
"step": 880
},
{
"epoch": 0.1263307310149042,
"grad_norm": 10.717041015625,
"learning_rate": 9.987395315826828e-05,
"loss": 2.1385255813598634,
"step": 890
},
{
"epoch": 0.127750177430802,
"grad_norm": 9.613192558288574,
"learning_rate": 9.987253371185238e-05,
"loss": 2.1964336395263673,
"step": 900
},
{
"epoch": 0.12916962384669978,
"grad_norm": 10.594833374023438,
"learning_rate": 9.987111426543649e-05,
"loss": 2.050688362121582,
"step": 910
},
{
"epoch": 0.13058907026259758,
"grad_norm": 11.596671104431152,
"learning_rate": 9.986969481902059e-05,
"loss": 2.077385139465332,
"step": 920
},
{
"epoch": 0.1320085166784954,
"grad_norm": 10.779032707214355,
"learning_rate": 9.98682753726047e-05,
"loss": 2.0280479431152343,
"step": 930
},
{
"epoch": 0.1334279630943932,
"grad_norm": 10.522924423217773,
"learning_rate": 9.98668559261888e-05,
"loss": 1.9384689331054688,
"step": 940
},
{
"epoch": 0.13484740951029098,
"grad_norm": 9.86844539642334,
"learning_rate": 9.986543647977289e-05,
"loss": 2.0612548828125,
"step": 950
},
{
"epoch": 0.13626685592618878,
"grad_norm": 12.521405220031738,
"learning_rate": 9.986401703335699e-05,
"loss": 2.139466094970703,
"step": 960
},
{
"epoch": 0.1376863023420866,
"grad_norm": 11.292656898498535,
"learning_rate": 9.98625975869411e-05,
"loss": 2.077956199645996,
"step": 970
},
{
"epoch": 0.1391057487579844,
"grad_norm": 11.186986923217773,
"learning_rate": 9.98611781405252e-05,
"loss": 2.028730010986328,
"step": 980
},
{
"epoch": 0.14052519517388218,
"grad_norm": 10.553022384643555,
"learning_rate": 9.985975869410931e-05,
"loss": 1.9375551223754883,
"step": 990
},
{
"epoch": 0.14194464158977999,
"grad_norm": 11.089204788208008,
"learning_rate": 9.98583392476934e-05,
"loss": 2.0689823150634767,
"step": 1000
},
{
"epoch": 0.14194464158977999,
"eval_accuracy": 0.42239460799898265,
"eval_loss": 1.9010688066482544,
"eval_runtime": 31.4593,
"eval_samples_per_second": 499.916,
"eval_steps_per_second": 15.639,
"step": 1000
},
{
"epoch": 0.1433640880056778,
"grad_norm": 10.988676071166992,
"learning_rate": 9.98569198012775e-05,
"loss": 1.9830604553222657,
"step": 1010
},
{
"epoch": 0.1447835344215756,
"grad_norm": 11.2459077835083,
"learning_rate": 9.985550035486161e-05,
"loss": 1.9190074920654296,
"step": 1020
},
{
"epoch": 0.14620298083747338,
"grad_norm": 10.437894821166992,
"learning_rate": 9.985408090844571e-05,
"loss": 1.8999460220336915,
"step": 1030
},
{
"epoch": 0.14762242725337119,
"grad_norm": 10.94793701171875,
"learning_rate": 9.985266146202982e-05,
"loss": 1.8579456329345703,
"step": 1040
},
{
"epoch": 0.149041873669269,
"grad_norm": 11.168233871459961,
"learning_rate": 9.98512420156139e-05,
"loss": 1.8979732513427734,
"step": 1050
},
{
"epoch": 0.15046132008516677,
"grad_norm": 10.14195728302002,
"learning_rate": 9.984982256919802e-05,
"loss": 1.7833553314208985,
"step": 1060
},
{
"epoch": 0.15188076650106458,
"grad_norm": 9.160737991333008,
"learning_rate": 9.984840312278211e-05,
"loss": 1.8624576568603515,
"step": 1070
},
{
"epoch": 0.1533002129169624,
"grad_norm": 11.151049613952637,
"learning_rate": 9.984698367636623e-05,
"loss": 1.8210905075073243,
"step": 1080
},
{
"epoch": 0.1547196593328602,
"grad_norm": 10.053725242614746,
"learning_rate": 9.984556422995032e-05,
"loss": 1.7738643646240235,
"step": 1090
},
{
"epoch": 0.15613910574875797,
"grad_norm": 10.97727108001709,
"learning_rate": 9.984414478353442e-05,
"loss": 1.866429328918457,
"step": 1100
},
{
"epoch": 0.15755855216465578,
"grad_norm": 12.384384155273438,
"learning_rate": 9.984272533711853e-05,
"loss": 1.8680984497070312,
"step": 1110
},
{
"epoch": 0.1589779985805536,
"grad_norm": 11.387879371643066,
"learning_rate": 9.984130589070263e-05,
"loss": 1.8034194946289062,
"step": 1120
},
{
"epoch": 0.1603974449964514,
"grad_norm": 10.6587495803833,
"learning_rate": 9.983988644428674e-05,
"loss": 1.772690773010254,
"step": 1130
},
{
"epoch": 0.16181689141234917,
"grad_norm": 12.721858024597168,
"learning_rate": 9.983846699787084e-05,
"loss": 1.7724496841430664,
"step": 1140
},
{
"epoch": 0.16323633782824698,
"grad_norm": 11.116838455200195,
"learning_rate": 9.983704755145493e-05,
"loss": 1.7527042388916017,
"step": 1150
},
{
"epoch": 0.1646557842441448,
"grad_norm": 10.033406257629395,
"learning_rate": 9.983562810503903e-05,
"loss": 1.674898338317871,
"step": 1160
},
{
"epoch": 0.1660752306600426,
"grad_norm": 11.121773719787598,
"learning_rate": 9.983420865862314e-05,
"loss": 1.741505241394043,
"step": 1170
},
{
"epoch": 0.16749467707594037,
"grad_norm": 11.052094459533691,
"learning_rate": 9.983278921220724e-05,
"loss": 1.7749841690063477,
"step": 1180
},
{
"epoch": 0.16891412349183818,
"grad_norm": 10.183452606201172,
"learning_rate": 9.983136976579135e-05,
"loss": 1.6881484985351562,
"step": 1190
},
{
"epoch": 0.170333569907736,
"grad_norm": 11.106999397277832,
"learning_rate": 9.982995031937545e-05,
"loss": 1.814961051940918,
"step": 1200
},
{
"epoch": 0.1717530163236338,
"grad_norm": 12.08647632598877,
"learning_rate": 9.982853087295955e-05,
"loss": 1.682515525817871,
"step": 1210
},
{
"epoch": 0.17317246273953157,
"grad_norm": 13.744584083557129,
"learning_rate": 9.982711142654366e-05,
"loss": 1.6713733673095703,
"step": 1220
},
{
"epoch": 0.17459190915542938,
"grad_norm": 9.970173835754395,
"learning_rate": 9.982569198012775e-05,
"loss": 1.711156463623047,
"step": 1230
},
{
"epoch": 0.1760113555713272,
"grad_norm": 11.027495384216309,
"learning_rate": 9.982427253371186e-05,
"loss": 1.759619140625,
"step": 1240
},
{
"epoch": 0.177430801987225,
"grad_norm": 10.876315116882324,
"learning_rate": 9.982285308729596e-05,
"loss": 1.618482780456543,
"step": 1250
},
{
"epoch": 0.17885024840312277,
"grad_norm": 10.26490592956543,
"learning_rate": 9.982143364088006e-05,
"loss": 1.6674427032470702,
"step": 1260
},
{
"epoch": 0.18026969481902058,
"grad_norm": 11.872292518615723,
"learning_rate": 9.982001419446416e-05,
"loss": 1.6325908660888673,
"step": 1270
},
{
"epoch": 0.1816891412349184,
"grad_norm": 9.946234703063965,
"learning_rate": 9.981859474804827e-05,
"loss": 1.5453743934631348,
"step": 1280
},
{
"epoch": 0.18310858765081617,
"grad_norm": 11.03128719329834,
"learning_rate": 9.981717530163236e-05,
"loss": 1.658684539794922,
"step": 1290
},
{
"epoch": 0.18452803406671398,
"grad_norm": 12.145915031433105,
"learning_rate": 9.981575585521648e-05,
"loss": 1.5792274475097656,
"step": 1300
},
{
"epoch": 0.18594748048261178,
"grad_norm": 11.820379257202148,
"learning_rate": 9.981433640880057e-05,
"loss": 1.5301803588867187,
"step": 1310
},
{
"epoch": 0.1873669268985096,
"grad_norm": 11.046746253967285,
"learning_rate": 9.981291696238467e-05,
"loss": 1.6124080657958983,
"step": 1320
},
{
"epoch": 0.18878637331440737,
"grad_norm": 9.545868873596191,
"learning_rate": 9.981149751596878e-05,
"loss": 1.5502593994140625,
"step": 1330
},
{
"epoch": 0.19020581973030518,
"grad_norm": 11.999979019165039,
"learning_rate": 9.981007806955288e-05,
"loss": 1.5360203742980958,
"step": 1340
},
{
"epoch": 0.19162526614620298,
"grad_norm": 9.949675559997559,
"learning_rate": 9.980865862313699e-05,
"loss": 1.353858470916748,
"step": 1350
},
{
"epoch": 0.1930447125621008,
"grad_norm": 11.573400497436523,
"learning_rate": 9.980723917672107e-05,
"loss": 1.3946660995483398,
"step": 1360
},
{
"epoch": 0.19446415897799857,
"grad_norm": 10.249485969543457,
"learning_rate": 9.980581973030518e-05,
"loss": 1.518262004852295,
"step": 1370
},
{
"epoch": 0.19588360539389638,
"grad_norm": 10.011629104614258,
"learning_rate": 9.980440028388928e-05,
"loss": 1.5000194549560546,
"step": 1380
},
{
"epoch": 0.19730305180979418,
"grad_norm": 12.186440467834473,
"learning_rate": 9.980298083747339e-05,
"loss": 1.554741382598877,
"step": 1390
},
{
"epoch": 0.198722498225692,
"grad_norm": 11.845844268798828,
"learning_rate": 9.980156139105749e-05,
"loss": 1.4599843978881837,
"step": 1400
},
{
"epoch": 0.20014194464158977,
"grad_norm": 10.98592472076416,
"learning_rate": 9.980014194464159e-05,
"loss": 1.4062080383300781,
"step": 1410
},
{
"epoch": 0.20156139105748758,
"grad_norm": 11.54171371459961,
"learning_rate": 9.97987224982257e-05,
"loss": 1.5128003120422364,
"step": 1420
},
{
"epoch": 0.20298083747338538,
"grad_norm": 10.248682022094727,
"learning_rate": 9.97973030518098e-05,
"loss": 1.5022719383239747,
"step": 1430
},
{
"epoch": 0.2044002838892832,
"grad_norm": 8.78536319732666,
"learning_rate": 9.97958836053939e-05,
"loss": 1.4118841171264649,
"step": 1440
},
{
"epoch": 0.20581973030518097,
"grad_norm": 9.993626594543457,
"learning_rate": 9.9794464158978e-05,
"loss": 1.3945957183837892,
"step": 1450
},
{
"epoch": 0.20723917672107878,
"grad_norm": 11.31412124633789,
"learning_rate": 9.97930447125621e-05,
"loss": 1.26229887008667,
"step": 1460
},
{
"epoch": 0.20865862313697658,
"grad_norm": 11.182840347290039,
"learning_rate": 9.97916252661462e-05,
"loss": 1.3171740531921388,
"step": 1470
},
{
"epoch": 0.2100780695528744,
"grad_norm": 12.25224781036377,
"learning_rate": 9.979020581973031e-05,
"loss": 1.3310781478881837,
"step": 1480
},
{
"epoch": 0.21149751596877217,
"grad_norm": 11.81201457977295,
"learning_rate": 9.978878637331441e-05,
"loss": 1.3043070793151856,
"step": 1490
},
{
"epoch": 0.21291696238466998,
"grad_norm": 10.484480857849121,
"learning_rate": 9.978736692689852e-05,
"loss": 1.2629288673400878,
"step": 1500
},
{
"epoch": 0.21291696238466998,
"eval_accuracy": 0.5395180263241559,
"eval_loss": 1.438815712928772,
"eval_runtime": 32.1456,
"eval_samples_per_second": 489.242,
"eval_steps_per_second": 15.305,
"step": 1500
},
{
"epoch": 0.21433640880056778,
"grad_norm": 10.796157836914062,
"learning_rate": 9.978594748048262e-05,
"loss": 1.3752121925354004,
"step": 1510
},
{
"epoch": 0.2157558552164656,
"grad_norm": 10.1256742477417,
"learning_rate": 9.978452803406671e-05,
"loss": 1.3005435943603516,
"step": 1520
},
{
"epoch": 0.21717530163236337,
"grad_norm": 11.182530403137207,
"learning_rate": 9.978310858765082e-05,
"loss": 1.3048934936523438,
"step": 1530
},
{
"epoch": 0.21859474804826118,
"grad_norm": 10.190278053283691,
"learning_rate": 9.978168914123492e-05,
"loss": 1.3993605613708495,
"step": 1540
},
{
"epoch": 0.22001419446415899,
"grad_norm": 10.497735977172852,
"learning_rate": 9.978026969481903e-05,
"loss": 1.303945541381836,
"step": 1550
},
{
"epoch": 0.22143364088005676,
"grad_norm": 10.535606384277344,
"learning_rate": 9.977885024840313e-05,
"loss": 1.2210904121398927,
"step": 1560
},
{
"epoch": 0.22285308729595457,
"grad_norm": 11.385029792785645,
"learning_rate": 9.977743080198723e-05,
"loss": 1.3508376121520995,
"step": 1570
},
{
"epoch": 0.22427253371185238,
"grad_norm": 9.528643608093262,
"learning_rate": 9.977601135557132e-05,
"loss": 1.2278815269470216,
"step": 1580
},
{
"epoch": 0.22569198012775019,
"grad_norm": 13.161009788513184,
"learning_rate": 9.977459190915544e-05,
"loss": 1.254448413848877,
"step": 1590
},
{
"epoch": 0.22711142654364797,
"grad_norm": 11.288809776306152,
"learning_rate": 9.977317246273953e-05,
"loss": 1.271047878265381,
"step": 1600
},
{
"epoch": 0.22853087295954577,
"grad_norm": 11.30105209350586,
"learning_rate": 9.977175301632364e-05,
"loss": 1.3242988586425781,
"step": 1610
},
{
"epoch": 0.22995031937544358,
"grad_norm": 10.600774765014648,
"learning_rate": 9.977033356990774e-05,
"loss": 1.3170942306518554,
"step": 1620
},
{
"epoch": 0.2313697657913414,
"grad_norm": 10.652543067932129,
"learning_rate": 9.976891412349184e-05,
"loss": 1.3998719215393067,
"step": 1630
},
{
"epoch": 0.23278921220723917,
"grad_norm": 11.354793548583984,
"learning_rate": 9.976749467707595e-05,
"loss": 1.270443820953369,
"step": 1640
},
{
"epoch": 0.23420865862313697,
"grad_norm": 9.926568031311035,
"learning_rate": 9.976607523066005e-05,
"loss": 1.117215347290039,
"step": 1650
},
{
"epoch": 0.23562810503903478,
"grad_norm": 11.167335510253906,
"learning_rate": 9.976465578424416e-05,
"loss": 1.348717212677002,
"step": 1660
},
{
"epoch": 0.2370475514549326,
"grad_norm": 11.364425659179688,
"learning_rate": 9.976323633782824e-05,
"loss": 1.2113998413085938,
"step": 1670
},
{
"epoch": 0.23846699787083037,
"grad_norm": 10.315034866333008,
"learning_rate": 9.976181689141235e-05,
"loss": 1.2621678352355956,
"step": 1680
},
{
"epoch": 0.23988644428672817,
"grad_norm": 11.332146644592285,
"learning_rate": 9.976039744499645e-05,
"loss": 1.2919418334960937,
"step": 1690
},
{
"epoch": 0.24130589070262598,
"grad_norm": 9.863037109375,
"learning_rate": 9.975897799858056e-05,
"loss": 1.262222957611084,
"step": 1700
},
{
"epoch": 0.2427253371185238,
"grad_norm": 13.898163795471191,
"learning_rate": 9.975755855216467e-05,
"loss": 1.349098300933838,
"step": 1710
},
{
"epoch": 0.24414478353442157,
"grad_norm": 9.008386611938477,
"learning_rate": 9.975613910574876e-05,
"loss": 1.1653017044067382,
"step": 1720
},
{
"epoch": 0.24556422995031937,
"grad_norm": 9.755669593811035,
"learning_rate": 9.975471965933287e-05,
"loss": 1.304057788848877,
"step": 1730
},
{
"epoch": 0.24698367636621718,
"grad_norm": 10.742278099060059,
"learning_rate": 9.975330021291696e-05,
"loss": 1.1656038284301757,
"step": 1740
},
{
"epoch": 0.248403122782115,
"grad_norm": 11.937880516052246,
"learning_rate": 9.975188076650107e-05,
"loss": 1.2565963745117188,
"step": 1750
},
{
"epoch": 0.24982256919801277,
"grad_norm": 9.80545711517334,
"learning_rate": 9.975046132008517e-05,
"loss": 1.1316876411437988,
"step": 1760
},
{
"epoch": 0.2512420156139106,
"grad_norm": 11.162557601928711,
"learning_rate": 9.974904187366927e-05,
"loss": 1.2094581604003907,
"step": 1770
},
{
"epoch": 0.2526614620298084,
"grad_norm": 12.278450965881348,
"learning_rate": 9.974762242725337e-05,
"loss": 1.2499947547912598,
"step": 1780
},
{
"epoch": 0.2540809084457062,
"grad_norm": 10.95953369140625,
"learning_rate": 9.974620298083748e-05,
"loss": 1.1540046691894532,
"step": 1790
},
{
"epoch": 0.255500354861604,
"grad_norm": 7.865696430206299,
"learning_rate": 9.974478353442159e-05,
"loss": 1.1665989875793457,
"step": 1800
},
{
"epoch": 0.25691980127750175,
"grad_norm": 12.1609468460083,
"learning_rate": 9.974336408800569e-05,
"loss": 1.120746898651123,
"step": 1810
},
{
"epoch": 0.25833924769339955,
"grad_norm": 9.554359436035156,
"learning_rate": 9.974194464158978e-05,
"loss": 1.3381189346313476,
"step": 1820
},
{
"epoch": 0.25975869410929736,
"grad_norm": 9.497129440307617,
"learning_rate": 9.974052519517388e-05,
"loss": 1.1758546829223633,
"step": 1830
},
{
"epoch": 0.26117814052519517,
"grad_norm": 10.584992408752441,
"learning_rate": 9.973910574875799e-05,
"loss": 1.0787659645080567,
"step": 1840
},
{
"epoch": 0.262597586941093,
"grad_norm": 9.558980941772461,
"learning_rate": 9.973768630234209e-05,
"loss": 0.9334567070007325,
"step": 1850
},
{
"epoch": 0.2640170333569908,
"grad_norm": 9.41112995147705,
"learning_rate": 9.97362668559262e-05,
"loss": 1.1376053810119628,
"step": 1860
},
{
"epoch": 0.2654364797728886,
"grad_norm": 11.666831970214844,
"learning_rate": 9.973484740951028e-05,
"loss": 1.207914447784424,
"step": 1870
},
{
"epoch": 0.2668559261887864,
"grad_norm": 11.217955589294434,
"learning_rate": 9.97334279630944e-05,
"loss": 1.052849578857422,
"step": 1880
},
{
"epoch": 0.26827537260468415,
"grad_norm": 8.3615083694458,
"learning_rate": 9.97320085166785e-05,
"loss": 0.9782976150512696,
"step": 1890
},
{
"epoch": 0.26969481902058196,
"grad_norm": 10.69944953918457,
"learning_rate": 9.97305890702626e-05,
"loss": 0.9639101982116699,
"step": 1900
},
{
"epoch": 0.27111426543647976,
"grad_norm": 11.15194034576416,
"learning_rate": 9.972916962384671e-05,
"loss": 1.0744239807128906,
"step": 1910
},
{
"epoch": 0.27253371185237757,
"grad_norm": 10.363690376281738,
"learning_rate": 9.972775017743081e-05,
"loss": 1.1180108070373536,
"step": 1920
},
{
"epoch": 0.2739531582682754,
"grad_norm": 10.816513061523438,
"learning_rate": 9.972633073101491e-05,
"loss": 1.118791103363037,
"step": 1930
},
{
"epoch": 0.2753726046841732,
"grad_norm": 8.64388656616211,
"learning_rate": 9.9724911284599e-05,
"loss": 1.1368459701538085,
"step": 1940
},
{
"epoch": 0.276792051100071,
"grad_norm": 9.002252578735352,
"learning_rate": 9.972349183818312e-05,
"loss": 1.1344121932983398,
"step": 1950
},
{
"epoch": 0.2782114975159688,
"grad_norm": 11.083386421203613,
"learning_rate": 9.972207239176721e-05,
"loss": 1.1827295303344727,
"step": 1960
},
{
"epoch": 0.27963094393186655,
"grad_norm": 8.360145568847656,
"learning_rate": 9.972065294535133e-05,
"loss": 0.9954969406127929,
"step": 1970
},
{
"epoch": 0.28105039034776436,
"grad_norm": 12.982026100158691,
"learning_rate": 9.971923349893542e-05,
"loss": 0.9865982055664062,
"step": 1980
},
{
"epoch": 0.28246983676366216,
"grad_norm": 9.3854341506958,
"learning_rate": 9.971781405251952e-05,
"loss": 0.9238475799560547,
"step": 1990
},
{
"epoch": 0.28388928317955997,
"grad_norm": 10.693597793579102,
"learning_rate": 9.971639460610363e-05,
"loss": 0.9660484313964843,
"step": 2000
},
{
"epoch": 0.28388928317955997,
"eval_accuracy": 0.6596935206968907,
"eval_loss": 1.0827350616455078,
"eval_runtime": 31.44,
"eval_samples_per_second": 500.222,
"eval_steps_per_second": 15.649,
"step": 2000
},
{
"epoch": 0.2853087295954578,
"grad_norm": 11.403952598571777,
"learning_rate": 9.971497515968773e-05,
"loss": 0.987885856628418,
"step": 2010
},
{
"epoch": 0.2867281760113556,
"grad_norm": 11.068461418151855,
"learning_rate": 9.971355571327184e-05,
"loss": 1.0180384635925293,
"step": 2020
},
{
"epoch": 0.2881476224272534,
"grad_norm": 10.536505699157715,
"learning_rate": 9.971213626685592e-05,
"loss": 1.0148059844970703,
"step": 2030
},
{
"epoch": 0.2895670688431512,
"grad_norm": 9.358129501342773,
"learning_rate": 9.971071682044003e-05,
"loss": 0.9920819282531739,
"step": 2040
},
{
"epoch": 0.29098651525904895,
"grad_norm": 10.33521842956543,
"learning_rate": 9.970929737402413e-05,
"loss": 1.0010162353515626,
"step": 2050
},
{
"epoch": 0.29240596167494676,
"grad_norm": 10.490190505981445,
"learning_rate": 9.970787792760824e-05,
"loss": 0.9781021118164063,
"step": 2060
},
{
"epoch": 0.29382540809084456,
"grad_norm": 9.507524490356445,
"learning_rate": 9.970645848119234e-05,
"loss": 0.9722440719604493,
"step": 2070
},
{
"epoch": 0.29524485450674237,
"grad_norm": 10.77835464477539,
"learning_rate": 9.970503903477644e-05,
"loss": 0.9851055145263672,
"step": 2080
},
{
"epoch": 0.2966643009226402,
"grad_norm": 9.847874641418457,
"learning_rate": 9.970361958836055e-05,
"loss": 0.8958380699157715,
"step": 2090
},
{
"epoch": 0.298083747338538,
"grad_norm": 11.703569412231445,
"learning_rate": 9.970220014194465e-05,
"loss": 0.9267073631286621,
"step": 2100
},
{
"epoch": 0.2995031937544358,
"grad_norm": 6.974740028381348,
"learning_rate": 9.970078069552876e-05,
"loss": 0.787592887878418,
"step": 2110
},
{
"epoch": 0.30092264017033354,
"grad_norm": 5.989770889282227,
"learning_rate": 9.969936124911285e-05,
"loss": 0.8309663772583008,
"step": 2120
},
{
"epoch": 0.30234208658623135,
"grad_norm": 8.477362632751465,
"learning_rate": 9.969794180269695e-05,
"loss": 0.8926510810852051,
"step": 2130
},
{
"epoch": 0.30376153300212916,
"grad_norm": 8.412622451782227,
"learning_rate": 9.969652235628105e-05,
"loss": 0.8592344284057617,
"step": 2140
},
{
"epoch": 0.30518097941802697,
"grad_norm": 10.356178283691406,
"learning_rate": 9.969510290986516e-05,
"loss": 0.8827583312988281,
"step": 2150
},
{
"epoch": 0.3066004258339248,
"grad_norm": 7.666086673736572,
"learning_rate": 9.969368346344926e-05,
"loss": 0.9427967071533203,
"step": 2160
},
{
"epoch": 0.3080198722498226,
"grad_norm": 11.2577486038208,
"learning_rate": 9.969226401703337e-05,
"loss": 0.8580154418945313,
"step": 2170
},
{
"epoch": 0.3094393186657204,
"grad_norm": 10.915003776550293,
"learning_rate": 9.969084457061746e-05,
"loss": 0.9019613265991211,
"step": 2180
},
{
"epoch": 0.3108587650816182,
"grad_norm": 9.683639526367188,
"learning_rate": 9.968942512420156e-05,
"loss": 0.8982448577880859,
"step": 2190
},
{
"epoch": 0.31227821149751595,
"grad_norm": 8.5520601272583,
"learning_rate": 9.968800567778567e-05,
"loss": 0.7967979431152343,
"step": 2200
},
{
"epoch": 0.31369765791341375,
"grad_norm": 11.931614875793457,
"learning_rate": 9.968658623136977e-05,
"loss": 0.9725972175598144,
"step": 2210
},
{
"epoch": 0.31511710432931156,
"grad_norm": 11.004504203796387,
"learning_rate": 9.968516678495388e-05,
"loss": 0.9189895629882813,
"step": 2220
},
{
"epoch": 0.31653655074520937,
"grad_norm": 9.460184097290039,
"learning_rate": 9.968374733853797e-05,
"loss": 0.9253165245056152,
"step": 2230
},
{
"epoch": 0.3179559971611072,
"grad_norm": 9.675958633422852,
"learning_rate": 9.968232789212208e-05,
"loss": 0.7977495670318604,
"step": 2240
},
{
"epoch": 0.319375443577005,
"grad_norm": 8.858159065246582,
"learning_rate": 9.968090844570617e-05,
"loss": 0.9056186676025391,
"step": 2250
},
{
"epoch": 0.3207948899929028,
"grad_norm": 10.144878387451172,
"learning_rate": 9.967948899929028e-05,
"loss": 0.9273244857788085,
"step": 2260
},
{
"epoch": 0.3222143364088006,
"grad_norm": 9.78799819946289,
"learning_rate": 9.967806955287438e-05,
"loss": 0.8192936897277832,
"step": 2270
},
{
"epoch": 0.32363378282469835,
"grad_norm": 8.891179084777832,
"learning_rate": 9.967665010645849e-05,
"loss": 0.8823507308959961,
"step": 2280
},
{
"epoch": 0.32505322924059615,
"grad_norm": 9.303411483764648,
"learning_rate": 9.967523066004259e-05,
"loss": 0.8374591827392578,
"step": 2290
},
{
"epoch": 0.32647267565649396,
"grad_norm": 8.408880233764648,
"learning_rate": 9.967381121362669e-05,
"loss": 0.849891471862793,
"step": 2300
},
{
"epoch": 0.32789212207239177,
"grad_norm": 9.384819030761719,
"learning_rate": 9.96723917672108e-05,
"loss": 0.7750972747802735,
"step": 2310
},
{
"epoch": 0.3293115684882896,
"grad_norm": 9.170500755310059,
"learning_rate": 9.96709723207949e-05,
"loss": 0.7687624454498291,
"step": 2320
},
{
"epoch": 0.3307310149041874,
"grad_norm": 8.488929748535156,
"learning_rate": 9.966955287437901e-05,
"loss": 0.8498885154724121,
"step": 2330
},
{
"epoch": 0.3321504613200852,
"grad_norm": 10.291971206665039,
"learning_rate": 9.966813342796309e-05,
"loss": 0.7807302474975586,
"step": 2340
},
{
"epoch": 0.33356990773598294,
"grad_norm": 11.644806861877441,
"learning_rate": 9.96667139815472e-05,
"loss": 0.7917065143585205,
"step": 2350
},
{
"epoch": 0.33498935415188075,
"grad_norm": 13.938374519348145,
"learning_rate": 9.96652945351313e-05,
"loss": 0.8718063354492187,
"step": 2360
},
{
"epoch": 0.33640880056777855,
"grad_norm": 10.399706840515137,
"learning_rate": 9.966387508871541e-05,
"loss": 0.8703582763671875,
"step": 2370
},
{
"epoch": 0.33782824698367636,
"grad_norm": 7.870115756988525,
"learning_rate": 9.966245564229951e-05,
"loss": 0.8549924850463867,
"step": 2380
},
{
"epoch": 0.33924769339957417,
"grad_norm": 9.777918815612793,
"learning_rate": 9.96610361958836e-05,
"loss": 1.0234166145324708,
"step": 2390
},
{
"epoch": 0.340667139815472,
"grad_norm": 10.103452682495117,
"learning_rate": 9.965961674946772e-05,
"loss": 0.9040670394897461,
"step": 2400
},
{
"epoch": 0.3420865862313698,
"grad_norm": 10.497400283813477,
"learning_rate": 9.965819730305181e-05,
"loss": 0.7955552577972412,
"step": 2410
},
{
"epoch": 0.3435060326472676,
"grad_norm": 8.0149564743042,
"learning_rate": 9.965677785663592e-05,
"loss": 0.856791877746582,
"step": 2420
},
{
"epoch": 0.34492547906316534,
"grad_norm": 8.111480712890625,
"learning_rate": 9.965535841022002e-05,
"loss": 0.8129085540771485,
"step": 2430
},
{
"epoch": 0.34634492547906315,
"grad_norm": 7.93813419342041,
"learning_rate": 9.965393896380412e-05,
"loss": 0.809941291809082,
"step": 2440
},
{
"epoch": 0.34776437189496096,
"grad_norm": 10.88427448272705,
"learning_rate": 9.965251951738822e-05,
"loss": 0.7622882843017578,
"step": 2450
},
{
"epoch": 0.34918381831085876,
"grad_norm": 9.509648323059082,
"learning_rate": 9.965110007097233e-05,
"loss": 0.7235064029693603,
"step": 2460
},
{
"epoch": 0.35060326472675657,
"grad_norm": 10.343646049499512,
"learning_rate": 9.964968062455642e-05,
"loss": 0.7792426586151123,
"step": 2470
},
{
"epoch": 0.3520227111426544,
"grad_norm": 11.936261177062988,
"learning_rate": 9.964826117814054e-05,
"loss": 0.8023401260375976,
"step": 2480
},
{
"epoch": 0.3534421575585522,
"grad_norm": 8.382633209228516,
"learning_rate": 9.964684173172463e-05,
"loss": 0.7960898399353027,
"step": 2490
},
{
"epoch": 0.35486160397445,
"grad_norm": 11.01586627960205,
"learning_rate": 9.964542228530873e-05,
"loss": 0.7975746631622315,
"step": 2500
},
{
"epoch": 0.35486160397445,
"eval_accuracy": 0.730527118967381,
"eval_loss": 0.8166059255599976,
"eval_runtime": 32.3274,
"eval_samples_per_second": 486.491,
"eval_steps_per_second": 15.219,
"step": 2500
},
{
"epoch": 0.35628105039034774,
"grad_norm": 8.113981246948242,
"learning_rate": 9.964400283889284e-05,
"loss": 0.7863178253173828,
"step": 2510
},
{
"epoch": 0.35770049680624555,
"grad_norm": 9.127975463867188,
"learning_rate": 9.964258339247694e-05,
"loss": 0.8487259864807128,
"step": 2520
},
{
"epoch": 0.35911994322214336,
"grad_norm": 8.597822189331055,
"learning_rate": 9.964116394606105e-05,
"loss": 0.8151129722595215,
"step": 2530
},
{
"epoch": 0.36053938963804116,
"grad_norm": 8.069273948669434,
"learning_rate": 9.963974449964513e-05,
"loss": 0.6664574623107911,
"step": 2540
},
{
"epoch": 0.36195883605393897,
"grad_norm": 8.314419746398926,
"learning_rate": 9.963832505322924e-05,
"loss": 0.8365516662597656,
"step": 2550
},
{
"epoch": 0.3633782824698368,
"grad_norm": 9.172304153442383,
"learning_rate": 9.963690560681334e-05,
"loss": 0.7865428924560547,
"step": 2560
},
{
"epoch": 0.3647977288857346,
"grad_norm": 9.639200210571289,
"learning_rate": 9.963548616039745e-05,
"loss": 0.7925633430480957,
"step": 2570
},
{
"epoch": 0.36621717530163234,
"grad_norm": 8.856132507324219,
"learning_rate": 9.963406671398155e-05,
"loss": 0.7005198955535888,
"step": 2580
},
{
"epoch": 0.36763662171753014,
"grad_norm": 7.9700422286987305,
"learning_rate": 9.963264726756566e-05,
"loss": 0.6712905883789062,
"step": 2590
},
{
"epoch": 0.36905606813342795,
"grad_norm": 9.465399742126465,
"learning_rate": 9.963122782114976e-05,
"loss": 0.7288703441619873,
"step": 2600
},
{
"epoch": 0.37047551454932576,
"grad_norm": 8.769003868103027,
"learning_rate": 9.962980837473386e-05,
"loss": 0.7671696662902832,
"step": 2610
},
{
"epoch": 0.37189496096522356,
"grad_norm": 6.981420040130615,
"learning_rate": 9.962838892831797e-05,
"loss": 0.6548487663269043,
"step": 2620
},
{
"epoch": 0.37331440738112137,
"grad_norm": 8.440009117126465,
"learning_rate": 9.962696948190206e-05,
"loss": 0.705223274230957,
"step": 2630
},
{
"epoch": 0.3747338537970192,
"grad_norm": 12.392814636230469,
"learning_rate": 9.962555003548617e-05,
"loss": 0.8219353675842285,
"step": 2640
},
{
"epoch": 0.376153300212917,
"grad_norm": 9.1260404586792,
"learning_rate": 9.962413058907026e-05,
"loss": 0.7202134132385254,
"step": 2650
},
{
"epoch": 0.37757274662881474,
"grad_norm": 9.437945365905762,
"learning_rate": 9.962271114265437e-05,
"loss": 0.7196836471557617,
"step": 2660
},
{
"epoch": 0.37899219304471254,
"grad_norm": 8.03176212310791,
"learning_rate": 9.962129169623847e-05,
"loss": 0.6017679214477539,
"step": 2670
},
{
"epoch": 0.38041163946061035,
"grad_norm": 11.21246337890625,
"learning_rate": 9.961987224982258e-05,
"loss": 0.8073585510253907,
"step": 2680
},
{
"epoch": 0.38183108587650816,
"grad_norm": 8.937601089477539,
"learning_rate": 9.961845280340667e-05,
"loss": 0.5765426635742188,
"step": 2690
},
{
"epoch": 0.38325053229240597,
"grad_norm": 10.750785827636719,
"learning_rate": 9.961703335699077e-05,
"loss": 0.850700569152832,
"step": 2700
},
{
"epoch": 0.3846699787083038,
"grad_norm": 8.476407051086426,
"learning_rate": 9.961561391057488e-05,
"loss": 0.6841172695159912,
"step": 2710
},
{
"epoch": 0.3860894251242016,
"grad_norm": 8.174555778503418,
"learning_rate": 9.961419446415898e-05,
"loss": 0.6521795272827149,
"step": 2720
},
{
"epoch": 0.3875088715400994,
"grad_norm": 6.744903564453125,
"learning_rate": 9.961277501774309e-05,
"loss": 0.7194175720214844,
"step": 2730
},
{
"epoch": 0.38892831795599714,
"grad_norm": 7.107284069061279,
"learning_rate": 9.961135557132719e-05,
"loss": 0.7437104701995849,
"step": 2740
},
{
"epoch": 0.39034776437189495,
"grad_norm": 12.026649475097656,
"learning_rate": 9.960993612491129e-05,
"loss": 0.7481307029724121,
"step": 2750
},
{
"epoch": 0.39176721078779275,
"grad_norm": 10.131022453308105,
"learning_rate": 9.960851667849538e-05,
"loss": 0.6669661521911621,
"step": 2760
},
{
"epoch": 0.39318665720369056,
"grad_norm": 7.589590072631836,
"learning_rate": 9.96070972320795e-05,
"loss": 0.5883037567138671,
"step": 2770
},
{
"epoch": 0.39460610361958837,
"grad_norm": 8.32777214050293,
"learning_rate": 9.960567778566359e-05,
"loss": 0.6772464752197266,
"step": 2780
},
{
"epoch": 0.3960255500354862,
"grad_norm": 6.111226558685303,
"learning_rate": 9.96042583392477e-05,
"loss": 0.6943521976470948,
"step": 2790
},
{
"epoch": 0.397444996451384,
"grad_norm": 10.40073299407959,
"learning_rate": 9.96028388928318e-05,
"loss": 0.6597262382507324,
"step": 2800
},
{
"epoch": 0.3988644428672818,
"grad_norm": 11.990081787109375,
"learning_rate": 9.96014194464159e-05,
"loss": 0.6846660614013672,
"step": 2810
},
{
"epoch": 0.40028388928317954,
"grad_norm": 7.820896625518799,
"learning_rate": 9.960000000000001e-05,
"loss": 0.5972445487976075,
"step": 2820
},
{
"epoch": 0.40170333569907735,
"grad_norm": 9.078740119934082,
"learning_rate": 9.95985805535841e-05,
"loss": 0.7440935611724854,
"step": 2830
},
{
"epoch": 0.40312278211497515,
"grad_norm": 8.869423866271973,
"learning_rate": 9.959716110716822e-05,
"loss": 0.7406916141510009,
"step": 2840
},
{
"epoch": 0.40454222853087296,
"grad_norm": 9.250556945800781,
"learning_rate": 9.95957416607523e-05,
"loss": 0.6444163799285889,
"step": 2850
},
{
"epoch": 0.40596167494677077,
"grad_norm": 12.534906387329102,
"learning_rate": 9.959432221433641e-05,
"loss": 0.7008297920227051,
"step": 2860
},
{
"epoch": 0.4073811213626686,
"grad_norm": 10.320120811462402,
"learning_rate": 9.959290276792051e-05,
"loss": 0.6261786460876465,
"step": 2870
},
{
"epoch": 0.4088005677785664,
"grad_norm": 7.483973979949951,
"learning_rate": 9.959148332150462e-05,
"loss": 0.6434149742126465,
"step": 2880
},
{
"epoch": 0.41022001419446413,
"grad_norm": 9.007946014404297,
"learning_rate": 9.959006387508872e-05,
"loss": 0.6796345233917236,
"step": 2890
},
{
"epoch": 0.41163946061036194,
"grad_norm": 8.191641807556152,
"learning_rate": 9.958864442867281e-05,
"loss": 0.5003190994262695,
"step": 2900
},
{
"epoch": 0.41305890702625975,
"grad_norm": 9.307744979858398,
"learning_rate": 9.958722498225693e-05,
"loss": 0.6988365173339843,
"step": 2910
},
{
"epoch": 0.41447835344215755,
"grad_norm": 6.16031551361084,
"learning_rate": 9.958580553584102e-05,
"loss": 0.6487136840820312,
"step": 2920
},
{
"epoch": 0.41589779985805536,
"grad_norm": 9.785910606384277,
"learning_rate": 9.958438608942513e-05,
"loss": 0.6544306755065918,
"step": 2930
},
{
"epoch": 0.41731724627395317,
"grad_norm": 12.08917236328125,
"learning_rate": 9.958296664300923e-05,
"loss": 0.6119012832641602,
"step": 2940
},
{
"epoch": 0.418736692689851,
"grad_norm": 10.118932723999023,
"learning_rate": 9.958154719659334e-05,
"loss": 0.5515688896179199,
"step": 2950
},
{
"epoch": 0.4201561391057488,
"grad_norm": 10.645463943481445,
"learning_rate": 9.958012775017743e-05,
"loss": 0.6795665740966796,
"step": 2960
},
{
"epoch": 0.42157558552164653,
"grad_norm": 8.745086669921875,
"learning_rate": 9.957870830376154e-05,
"loss": 0.6612170219421387,
"step": 2970
},
{
"epoch": 0.42299503193754434,
"grad_norm": 7.060173511505127,
"learning_rate": 9.957728885734563e-05,
"loss": 0.635819387435913,
"step": 2980
},
{
"epoch": 0.42441447835344215,
"grad_norm": 11.630016326904297,
"learning_rate": 9.957586941092975e-05,
"loss": 0.5891122341156005,
"step": 2990
},
{
"epoch": 0.42583392476933996,
"grad_norm": 11.667549133300781,
"learning_rate": 9.957444996451386e-05,
"loss": 0.7183985233306884,
"step": 3000
},
{
"epoch": 0.42583392476933996,
"eval_accuracy": 0.7175557957652445,
"eval_loss": 0.8312568068504333,
"eval_runtime": 32.7465,
"eval_samples_per_second": 480.265,
"eval_steps_per_second": 15.024,
"step": 3000
},
{
"epoch": 0.42725337118523776,
"grad_norm": 10.770739555358887,
"learning_rate": 9.957303051809794e-05,
"loss": 0.606045913696289,
"step": 3010
},
{
"epoch": 0.42867281760113557,
"grad_norm": 8.715160369873047,
"learning_rate": 9.957161107168205e-05,
"loss": 0.6968401908874512,
"step": 3020
},
{
"epoch": 0.4300922640170334,
"grad_norm": 10.227581977844238,
"learning_rate": 9.957019162526615e-05,
"loss": 0.5089622497558594,
"step": 3030
},
{
"epoch": 0.4315117104329312,
"grad_norm": 8.32385540008545,
"learning_rate": 9.956877217885026e-05,
"loss": 0.6402715682983399,
"step": 3040
},
{
"epoch": 0.43293115684882894,
"grad_norm": 10.973727226257324,
"learning_rate": 9.956735273243436e-05,
"loss": 0.7282869338989257,
"step": 3050
},
{
"epoch": 0.43435060326472674,
"grad_norm": 8.994437217712402,
"learning_rate": 9.956593328601845e-05,
"loss": 0.5776423454284668,
"step": 3060
},
{
"epoch": 0.43577004968062455,
"grad_norm": 7.597539901733398,
"learning_rate": 9.956451383960255e-05,
"loss": 0.5537106990814209,
"step": 3070
},
{
"epoch": 0.43718949609652236,
"grad_norm": 7.695132732391357,
"learning_rate": 9.956309439318666e-05,
"loss": 0.5561283588409424,
"step": 3080
},
{
"epoch": 0.43860894251242016,
"grad_norm": 10.008833885192871,
"learning_rate": 9.956167494677077e-05,
"loss": 0.6571722030639648,
"step": 3090
},
{
"epoch": 0.44002838892831797,
"grad_norm": 6.440252304077148,
"learning_rate": 9.956025550035487e-05,
"loss": 0.4972050189971924,
"step": 3100
},
{
"epoch": 0.4414478353442158,
"grad_norm": 11.92957878112793,
"learning_rate": 9.955883605393897e-05,
"loss": 0.6483690738677979,
"step": 3110
},
{
"epoch": 0.44286728176011353,
"grad_norm": 8.40812873840332,
"learning_rate": 9.955741660752307e-05,
"loss": 0.602755069732666,
"step": 3120
},
{
"epoch": 0.44428672817601134,
"grad_norm": 6.782786846160889,
"learning_rate": 9.955599716110718e-05,
"loss": 0.6320923328399658,
"step": 3130
},
{
"epoch": 0.44570617459190914,
"grad_norm": 12.326107025146484,
"learning_rate": 9.955457771469127e-05,
"loss": 0.5779653549194336,
"step": 3140
},
{
"epoch": 0.44712562100780695,
"grad_norm": 12.876483917236328,
"learning_rate": 9.955315826827538e-05,
"loss": 0.7216415882110596,
"step": 3150
},
{
"epoch": 0.44854506742370476,
"grad_norm": 6.984850883483887,
"learning_rate": 9.955173882185947e-05,
"loss": 0.4415611267089844,
"step": 3160
},
{
"epoch": 0.44996451383960256,
"grad_norm": 6.711297512054443,
"learning_rate": 9.955031937544358e-05,
"loss": 0.5505913734436035,
"step": 3170
},
{
"epoch": 0.45138396025550037,
"grad_norm": 7.127682685852051,
"learning_rate": 9.954889992902769e-05,
"loss": 0.5563027858734131,
"step": 3180
},
{
"epoch": 0.4528034066713982,
"grad_norm": 9.826492309570312,
"learning_rate": 9.954748048261179e-05,
"loss": 0.5204686641693115,
"step": 3190
},
{
"epoch": 0.45422285308729593,
"grad_norm": 14.011224746704102,
"learning_rate": 9.95460610361959e-05,
"loss": 0.5676139831542969,
"step": 3200
},
{
"epoch": 0.45564229950319374,
"grad_norm": 10.502514839172363,
"learning_rate": 9.954464158977998e-05,
"loss": 0.6593122482299805,
"step": 3210
},
{
"epoch": 0.45706174591909154,
"grad_norm": 9.966157913208008,
"learning_rate": 9.95432221433641e-05,
"loss": 0.5757305145263671,
"step": 3220
},
{
"epoch": 0.45848119233498935,
"grad_norm": 7.551996231079102,
"learning_rate": 9.954180269694819e-05,
"loss": 0.5537711620330811,
"step": 3230
},
{
"epoch": 0.45990063875088716,
"grad_norm": 10.630086898803711,
"learning_rate": 9.95403832505323e-05,
"loss": 0.5302771091461181,
"step": 3240
},
{
"epoch": 0.46132008516678497,
"grad_norm": 12.471774101257324,
"learning_rate": 9.95389638041164e-05,
"loss": 0.6347667694091796,
"step": 3250
},
{
"epoch": 0.4627395315826828,
"grad_norm": 9.668441772460938,
"learning_rate": 9.95375443577005e-05,
"loss": 0.5615960121154785,
"step": 3260
},
{
"epoch": 0.4641589779985806,
"grad_norm": 9.092421531677246,
"learning_rate": 9.953612491128461e-05,
"loss": 0.5531889438629151,
"step": 3270
},
{
"epoch": 0.46557842441447833,
"grad_norm": 8.55390453338623,
"learning_rate": 9.95347054648687e-05,
"loss": 0.5149998188018798,
"step": 3280
},
{
"epoch": 0.46699787083037614,
"grad_norm": 9.092056274414062,
"learning_rate": 9.953328601845282e-05,
"loss": 0.49632701873779295,
"step": 3290
},
{
"epoch": 0.46841731724627395,
"grad_norm": 9.66268253326416,
"learning_rate": 9.953186657203691e-05,
"loss": 0.5612505912780762,
"step": 3300
},
{
"epoch": 0.46983676366217175,
"grad_norm": 6.583611011505127,
"learning_rate": 9.953044712562102e-05,
"loss": 0.5805669307708741,
"step": 3310
},
{
"epoch": 0.47125621007806956,
"grad_norm": 8.160282135009766,
"learning_rate": 9.952902767920511e-05,
"loss": 0.4320365428924561,
"step": 3320
},
{
"epoch": 0.47267565649396737,
"grad_norm": 10.05884075164795,
"learning_rate": 9.952760823278922e-05,
"loss": 0.5736487865447998,
"step": 3330
},
{
"epoch": 0.4740951029098652,
"grad_norm": 9.000593185424805,
"learning_rate": 9.952618878637332e-05,
"loss": 0.5238205432891846,
"step": 3340
},
{
"epoch": 0.4755145493257629,
"grad_norm": 9.076302528381348,
"learning_rate": 9.952476933995743e-05,
"loss": 0.5925283432006836,
"step": 3350
},
{
"epoch": 0.47693399574166073,
"grad_norm": 8.275947570800781,
"learning_rate": 9.952334989354152e-05,
"loss": 0.4787450313568115,
"step": 3360
},
{
"epoch": 0.47835344215755854,
"grad_norm": 12.550822257995605,
"learning_rate": 9.952193044712562e-05,
"loss": 0.49250407218933107,
"step": 3370
},
{
"epoch": 0.47977288857345635,
"grad_norm": 6.8708176612854,
"learning_rate": 9.952051100070973e-05,
"loss": 0.585394811630249,
"step": 3380
},
{
"epoch": 0.48119233498935415,
"grad_norm": 6.129304885864258,
"learning_rate": 9.951909155429383e-05,
"loss": 0.5862763881683349,
"step": 3390
},
{
"epoch": 0.48261178140525196,
"grad_norm": 7.1515045166015625,
"learning_rate": 9.951767210787794e-05,
"loss": 0.46143798828125,
"step": 3400
},
{
"epoch": 0.48403122782114977,
"grad_norm": 5.421439170837402,
"learning_rate": 9.951625266146204e-05,
"loss": 0.6040849685668945,
"step": 3410
},
{
"epoch": 0.4854506742370476,
"grad_norm": 10.418113708496094,
"learning_rate": 9.951483321504614e-05,
"loss": 0.55996732711792,
"step": 3420
},
{
"epoch": 0.4868701206529453,
"grad_norm": 9.697559356689453,
"learning_rate": 9.951341376863023e-05,
"loss": 0.5332645893096923,
"step": 3430
},
{
"epoch": 0.48828956706884313,
"grad_norm": 9.79345703125,
"learning_rate": 9.951199432221434e-05,
"loss": 0.5983724117279052,
"step": 3440
},
{
"epoch": 0.48970901348474094,
"grad_norm": 7.977105617523193,
"learning_rate": 9.951057487579844e-05,
"loss": 0.6096511840820312,
"step": 3450
},
{
"epoch": 0.49112845990063875,
"grad_norm": 6.851355075836182,
"learning_rate": 9.950915542938255e-05,
"loss": 0.4748993396759033,
"step": 3460
},
{
"epoch": 0.49254790631653655,
"grad_norm": 4.706153392791748,
"learning_rate": 9.950773598296665e-05,
"loss": 0.544727087020874,
"step": 3470
},
{
"epoch": 0.49396735273243436,
"grad_norm": 9.061712265014648,
"learning_rate": 9.950631653655075e-05,
"loss": 0.5076655387878418,
"step": 3480
},
{
"epoch": 0.49538679914833217,
"grad_norm": 7.619383335113525,
"learning_rate": 9.950489709013486e-05,
"loss": 0.5011069297790527,
"step": 3490
},
{
"epoch": 0.49680624556423,
"grad_norm": 6.629651069641113,
"learning_rate": 9.950347764371896e-05,
"loss": 0.5038942337036133,
"step": 3500
},
{
"epoch": 0.49680624556423,
"eval_accuracy": 0.8245056272652127,
"eval_loss": 0.526730477809906,
"eval_runtime": 32.5263,
"eval_samples_per_second": 483.517,
"eval_steps_per_second": 15.126,
"step": 3500
},
{
"epoch": 0.4982256919801277,
"grad_norm": 6.535589694976807,
"learning_rate": 9.950205819730307e-05,
"loss": 0.5255190849304199,
"step": 3510
},
{
"epoch": 0.49964513839602553,
"grad_norm": 10.481846809387207,
"learning_rate": 9.950063875088715e-05,
"loss": 0.4977625846862793,
"step": 3520
},
{
"epoch": 0.5010645848119234,
"grad_norm": 6.455493450164795,
"learning_rate": 9.949921930447126e-05,
"loss": 0.4624650955200195,
"step": 3530
},
{
"epoch": 0.5024840312278211,
"grad_norm": 12.190658569335938,
"learning_rate": 9.949779985805536e-05,
"loss": 0.45445499420166013,
"step": 3540
},
{
"epoch": 0.5039034776437189,
"grad_norm": 6.512971878051758,
"learning_rate": 9.949638041163947e-05,
"loss": 0.48822684288024903,
"step": 3550
},
{
"epoch": 0.5053229240596168,
"grad_norm": 8.259076118469238,
"learning_rate": 9.949496096522357e-05,
"loss": 0.4896749496459961,
"step": 3560
},
{
"epoch": 0.5067423704755145,
"grad_norm": 10.809083938598633,
"learning_rate": 9.949354151880766e-05,
"loss": 0.5267855644226074,
"step": 3570
},
{
"epoch": 0.5081618168914124,
"grad_norm": 11.164665222167969,
"learning_rate": 9.949212207239178e-05,
"loss": 0.6478964328765869,
"step": 3580
},
{
"epoch": 0.5095812633073101,
"grad_norm": 10.553145408630371,
"learning_rate": 9.949070262597587e-05,
"loss": 0.5322469711303711,
"step": 3590
},
{
"epoch": 0.511000709723208,
"grad_norm": 12.578235626220703,
"learning_rate": 9.948928317955998e-05,
"loss": 0.559388542175293,
"step": 3600
},
{
"epoch": 0.5124201561391057,
"grad_norm": 7.2467474937438965,
"learning_rate": 9.948786373314408e-05,
"loss": 0.5477664470672607,
"step": 3610
},
{
"epoch": 0.5138396025550035,
"grad_norm": 5.959977626800537,
"learning_rate": 9.948644428672818e-05,
"loss": 0.41798744201660154,
"step": 3620
},
{
"epoch": 0.5152590489709014,
"grad_norm": 11.72385025024414,
"learning_rate": 9.948502484031228e-05,
"loss": 0.5879819869995118,
"step": 3630
},
{
"epoch": 0.5166784953867991,
"grad_norm": 7.881444454193115,
"learning_rate": 9.948360539389639e-05,
"loss": 0.5005061149597168,
"step": 3640
},
{
"epoch": 0.518097941802697,
"grad_norm": 7.005399703979492,
"learning_rate": 9.948218594748048e-05,
"loss": 0.5412337303161621,
"step": 3650
},
{
"epoch": 0.5195173882185947,
"grad_norm": 13.495038032531738,
"learning_rate": 9.94807665010646e-05,
"loss": 0.5668565273284912,
"step": 3660
},
{
"epoch": 0.5209368346344926,
"grad_norm": 8.42395305633545,
"learning_rate": 9.947934705464869e-05,
"loss": 0.6085368633270264,
"step": 3670
},
{
"epoch": 0.5223562810503903,
"grad_norm": 8.754134178161621,
"learning_rate": 9.947792760823279e-05,
"loss": 0.5360457420349121,
"step": 3680
},
{
"epoch": 0.5237757274662882,
"grad_norm": 5.868712425231934,
"learning_rate": 9.94765081618169e-05,
"loss": 0.6166606903076172,
"step": 3690
},
{
"epoch": 0.525195173882186,
"grad_norm": 4.342434883117676,
"learning_rate": 9.9475088715401e-05,
"loss": 0.4890284061431885,
"step": 3700
},
{
"epoch": 0.5266146202980837,
"grad_norm": 8.200478553771973,
"learning_rate": 9.947366926898511e-05,
"loss": 0.5135448455810547,
"step": 3710
},
{
"epoch": 0.5280340667139816,
"grad_norm": 6.076674938201904,
"learning_rate": 9.94722498225692e-05,
"loss": 0.37685840129852294,
"step": 3720
},
{
"epoch": 0.5294535131298793,
"grad_norm": 8.206668853759766,
"learning_rate": 9.94708303761533e-05,
"loss": 0.43741750717163086,
"step": 3730
},
{
"epoch": 0.5308729595457772,
"grad_norm": 8.284717559814453,
"learning_rate": 9.94694109297374e-05,
"loss": 0.46701841354370116,
"step": 3740
},
{
"epoch": 0.5322924059616749,
"grad_norm": 8.111977577209473,
"learning_rate": 9.946799148332151e-05,
"loss": 0.5564829349517822,
"step": 3750
},
{
"epoch": 0.5337118523775728,
"grad_norm": 10.037016868591309,
"learning_rate": 9.946657203690561e-05,
"loss": 0.4543320655822754,
"step": 3760
},
{
"epoch": 0.5351312987934705,
"grad_norm": 6.1391191482543945,
"learning_rate": 9.946515259048972e-05,
"loss": 0.43409008979797364,
"step": 3770
},
{
"epoch": 0.5365507452093683,
"grad_norm": 9.031709671020508,
"learning_rate": 9.946373314407382e-05,
"loss": 0.45609292984008787,
"step": 3780
},
{
"epoch": 0.5379701916252662,
"grad_norm": 10.507880210876465,
"learning_rate": 9.946231369765791e-05,
"loss": 0.49566287994384767,
"step": 3790
},
{
"epoch": 0.5393896380411639,
"grad_norm": 7.94572114944458,
"learning_rate": 9.946089425124203e-05,
"loss": 0.43464975357055663,
"step": 3800
},
{
"epoch": 0.5408090844570618,
"grad_norm": 11.292725563049316,
"learning_rate": 9.945947480482612e-05,
"loss": 0.4976043224334717,
"step": 3810
},
{
"epoch": 0.5422285308729595,
"grad_norm": 9.720746040344238,
"learning_rate": 9.945805535841023e-05,
"loss": 0.44420394897460935,
"step": 3820
},
{
"epoch": 0.5436479772888574,
"grad_norm": 10.859402656555176,
"learning_rate": 9.945663591199432e-05,
"loss": 0.47884187698364256,
"step": 3830
},
{
"epoch": 0.5450674237047551,
"grad_norm": 10.234602928161621,
"learning_rate": 9.945521646557843e-05,
"loss": 0.4273094654083252,
"step": 3840
},
{
"epoch": 0.5464868701206529,
"grad_norm": 10.073461532592773,
"learning_rate": 9.945379701916253e-05,
"loss": 0.4809098243713379,
"step": 3850
},
{
"epoch": 0.5479063165365508,
"grad_norm": 8.402386665344238,
"learning_rate": 9.945237757274664e-05,
"loss": 0.5075035572052002,
"step": 3860
},
{
"epoch": 0.5493257629524485,
"grad_norm": 8.385801315307617,
"learning_rate": 9.945095812633073e-05,
"loss": 0.42679743766784667,
"step": 3870
},
{
"epoch": 0.5507452093683464,
"grad_norm": 8.214275360107422,
"learning_rate": 9.944953867991483e-05,
"loss": 0.42831969261169434,
"step": 3880
},
{
"epoch": 0.5521646557842441,
"grad_norm": 6.777364730834961,
"learning_rate": 9.944811923349894e-05,
"loss": 0.37784249782562257,
"step": 3890
},
{
"epoch": 0.553584102200142,
"grad_norm": 7.4766011238098145,
"learning_rate": 9.944669978708304e-05,
"loss": 0.5389047622680664,
"step": 3900
},
{
"epoch": 0.5550035486160397,
"grad_norm": 7.167613983154297,
"learning_rate": 9.944528034066715e-05,
"loss": 0.4535686492919922,
"step": 3910
},
{
"epoch": 0.5564229950319376,
"grad_norm": 3.94936203956604,
"learning_rate": 9.944386089425125e-05,
"loss": 0.392999267578125,
"step": 3920
},
{
"epoch": 0.5578424414478353,
"grad_norm": 7.909378528594971,
"learning_rate": 9.944244144783535e-05,
"loss": 0.4675307750701904,
"step": 3930
},
{
"epoch": 0.5592618878637331,
"grad_norm": 8.253449440002441,
"learning_rate": 9.944102200141944e-05,
"loss": 0.515011215209961,
"step": 3940
},
{
"epoch": 0.560681334279631,
"grad_norm": 5.535346984863281,
"learning_rate": 9.943960255500355e-05,
"loss": 0.35612196922302247,
"step": 3950
},
{
"epoch": 0.5621007806955287,
"grad_norm": 5.621975898742676,
"learning_rate": 9.943818310858765e-05,
"loss": 0.3292267322540283,
"step": 3960
},
{
"epoch": 0.5635202271114266,
"grad_norm": 8.432771682739258,
"learning_rate": 9.943676366217176e-05,
"loss": 0.44489707946777346,
"step": 3970
},
{
"epoch": 0.5649396735273243,
"grad_norm": 5.422188758850098,
"learning_rate": 9.943534421575586e-05,
"loss": 0.4312278270721436,
"step": 3980
},
{
"epoch": 0.5663591199432222,
"grad_norm": 6.463229179382324,
"learning_rate": 9.943392476933996e-05,
"loss": 0.4469761371612549,
"step": 3990
},
{
"epoch": 0.5677785663591199,
"grad_norm": 12.039133071899414,
"learning_rate": 9.943250532292407e-05,
"loss": 0.5653008937835693,
"step": 4000
},
{
"epoch": 0.5677785663591199,
"eval_accuracy": 0.8540726139759649,
"eval_loss": 0.4309617578983307,
"eval_runtime": 32.698,
"eval_samples_per_second": 480.977,
"eval_steps_per_second": 15.047,
"step": 4000
},
{
"epoch": 0.5691980127750177,
"grad_norm": 12.185803413391113,
"learning_rate": 9.943108587650817e-05,
"loss": 0.4458905220031738,
"step": 4010
},
{
"epoch": 0.5706174591909156,
"grad_norm": 9.691877365112305,
"learning_rate": 9.942966643009228e-05,
"loss": 0.39486720561981203,
"step": 4020
},
{
"epoch": 0.5720369056068133,
"grad_norm": 8.106902122497559,
"learning_rate": 9.942824698367637e-05,
"loss": 0.49444093704223635,
"step": 4030
},
{
"epoch": 0.5734563520227112,
"grad_norm": 9.14234447479248,
"learning_rate": 9.942682753726047e-05,
"loss": 0.43038039207458495,
"step": 4040
},
{
"epoch": 0.5748757984386089,
"grad_norm": 4.6097588539123535,
"learning_rate": 9.942540809084457e-05,
"loss": 0.4118741512298584,
"step": 4050
},
{
"epoch": 0.5762952448545068,
"grad_norm": 6.0909881591796875,
"learning_rate": 9.942398864442868e-05,
"loss": 0.4245272159576416,
"step": 4060
},
{
"epoch": 0.5777146912704045,
"grad_norm": 10.82681941986084,
"learning_rate": 9.942256919801278e-05,
"loss": 0.43029065132141114,
"step": 4070
},
{
"epoch": 0.5791341376863024,
"grad_norm": 7.2398481369018555,
"learning_rate": 9.942114975159689e-05,
"loss": 0.4268779277801514,
"step": 4080
},
{
"epoch": 0.5805535841022001,
"grad_norm": 12.160025596618652,
"learning_rate": 9.941973030518099e-05,
"loss": 0.45933380126953127,
"step": 4090
},
{
"epoch": 0.5819730305180979,
"grad_norm": 8.116787910461426,
"learning_rate": 9.941831085876508e-05,
"loss": 0.3810285568237305,
"step": 4100
},
{
"epoch": 0.5833924769339958,
"grad_norm": 7.5045037269592285,
"learning_rate": 9.94168914123492e-05,
"loss": 0.48673238754272463,
"step": 4110
},
{
"epoch": 0.5848119233498935,
"grad_norm": 10.9375581741333,
"learning_rate": 9.941547196593329e-05,
"loss": 0.5465658664703369,
"step": 4120
},
{
"epoch": 0.5862313697657914,
"grad_norm": 9.211751937866211,
"learning_rate": 9.94140525195174e-05,
"loss": 0.46831202507019043,
"step": 4130
},
{
"epoch": 0.5876508161816891,
"grad_norm": 7.636734485626221,
"learning_rate": 9.941263307310149e-05,
"loss": 0.3928233623504639,
"step": 4140
},
{
"epoch": 0.589070262597587,
"grad_norm": 7.125626564025879,
"learning_rate": 9.94112136266856e-05,
"loss": 0.40816364288330076,
"step": 4150
},
{
"epoch": 0.5904897090134847,
"grad_norm": 5.0693888664245605,
"learning_rate": 9.94097941802697e-05,
"loss": 0.3931445837020874,
"step": 4160
},
{
"epoch": 0.5919091554293825,
"grad_norm": 8.10261058807373,
"learning_rate": 9.94083747338538e-05,
"loss": 0.4498757839202881,
"step": 4170
},
{
"epoch": 0.5933286018452804,
"grad_norm": 9.593578338623047,
"learning_rate": 9.94069552874379e-05,
"loss": 0.46671414375305176,
"step": 4180
},
{
"epoch": 0.5947480482611781,
"grad_norm": 10.025617599487305,
"learning_rate": 9.9405535841022e-05,
"loss": 0.42932772636413574,
"step": 4190
},
{
"epoch": 0.596167494677076,
"grad_norm": 9.828198432922363,
"learning_rate": 9.940411639460611e-05,
"loss": 0.4723196506500244,
"step": 4200
},
{
"epoch": 0.5975869410929737,
"grad_norm": 7.570648193359375,
"learning_rate": 9.940269694819021e-05,
"loss": 0.4049358367919922,
"step": 4210
},
{
"epoch": 0.5990063875088716,
"grad_norm": 6.280502796173096,
"learning_rate": 9.940127750177432e-05,
"loss": 0.4247574806213379,
"step": 4220
},
{
"epoch": 0.6004258339247693,
"grad_norm": 8.619515419006348,
"learning_rate": 9.939985805535842e-05,
"loss": 0.3778993606567383,
"step": 4230
},
{
"epoch": 0.6018452803406671,
"grad_norm": 7.0030059814453125,
"learning_rate": 9.939843860894251e-05,
"loss": 0.4360033988952637,
"step": 4240
},
{
"epoch": 0.603264726756565,
"grad_norm": 6.206148624420166,
"learning_rate": 9.939701916252661e-05,
"loss": 0.4114119529724121,
"step": 4250
},
{
"epoch": 0.6046841731724627,
"grad_norm": 4.982306003570557,
"learning_rate": 9.939559971611072e-05,
"loss": 0.36019244194030764,
"step": 4260
},
{
"epoch": 0.6061036195883606,
"grad_norm": 7.193652153015137,
"learning_rate": 9.939418026969482e-05,
"loss": 0.47596259117126466,
"step": 4270
},
{
"epoch": 0.6075230660042583,
"grad_norm": 9.371147155761719,
"learning_rate": 9.939276082327893e-05,
"loss": 0.42912769317626953,
"step": 4280
},
{
"epoch": 0.6089425124201562,
"grad_norm": 8.962141036987305,
"learning_rate": 9.939134137686303e-05,
"loss": 0.42342243194580076,
"step": 4290
},
{
"epoch": 0.6103619588360539,
"grad_norm": 7.575186252593994,
"learning_rate": 9.938992193044712e-05,
"loss": 0.4972747802734375,
"step": 4300
},
{
"epoch": 0.6117814052519518,
"grad_norm": 6.965094566345215,
"learning_rate": 9.938850248403124e-05,
"loss": 0.3489841938018799,
"step": 4310
},
{
"epoch": 0.6132008516678495,
"grad_norm": 8.466391563415527,
"learning_rate": 9.938708303761533e-05,
"loss": 0.3544389009475708,
"step": 4320
},
{
"epoch": 0.6146202980837473,
"grad_norm": 6.5821123123168945,
"learning_rate": 9.938566359119944e-05,
"loss": 0.4732979297637939,
"step": 4330
},
{
"epoch": 0.6160397444996452,
"grad_norm": 6.803234100341797,
"learning_rate": 9.938424414478353e-05,
"loss": 0.39069912433624265,
"step": 4340
},
{
"epoch": 0.6174591909155429,
"grad_norm": 10.069840431213379,
"learning_rate": 9.938282469836764e-05,
"loss": 0.4592564582824707,
"step": 4350
},
{
"epoch": 0.6188786373314408,
"grad_norm": 9.41560173034668,
"learning_rate": 9.938140525195174e-05,
"loss": 0.45508289337158203,
"step": 4360
},
{
"epoch": 0.6202980837473385,
"grad_norm": 8.344886779785156,
"learning_rate": 9.937998580553585e-05,
"loss": 0.41198153495788575,
"step": 4370
},
{
"epoch": 0.6217175301632364,
"grad_norm": 9.129981994628906,
"learning_rate": 9.937856635911994e-05,
"loss": 0.33535902500152587,
"step": 4380
},
{
"epoch": 0.6231369765791341,
"grad_norm": 6.8436455726623535,
"learning_rate": 9.937714691270406e-05,
"loss": 0.3965883493423462,
"step": 4390
},
{
"epoch": 0.6245564229950319,
"grad_norm": 6.954466342926025,
"learning_rate": 9.937572746628815e-05,
"loss": 0.3352261304855347,
"step": 4400
},
{
"epoch": 0.6259758694109298,
"grad_norm": 8.227835655212402,
"learning_rate": 9.937430801987225e-05,
"loss": 0.4205745220184326,
"step": 4410
},
{
"epoch": 0.6273953158268275,
"grad_norm": 8.202418327331543,
"learning_rate": 9.937288857345636e-05,
"loss": 0.3927265405654907,
"step": 4420
},
{
"epoch": 0.6288147622427254,
"grad_norm": 9.406537055969238,
"learning_rate": 9.937146912704046e-05,
"loss": 0.4481183052062988,
"step": 4430
},
{
"epoch": 0.6302342086586231,
"grad_norm": 8.330412864685059,
"learning_rate": 9.937004968062457e-05,
"loss": 0.37030580043792727,
"step": 4440
},
{
"epoch": 0.631653655074521,
"grad_norm": 5.601277828216553,
"learning_rate": 9.936863023420865e-05,
"loss": 0.35557353496551514,
"step": 4450
},
{
"epoch": 0.6330731014904187,
"grad_norm": 11.551403999328613,
"learning_rate": 9.936721078779276e-05,
"loss": 0.3718759536743164,
"step": 4460
},
{
"epoch": 0.6344925479063165,
"grad_norm": 5.961857318878174,
"learning_rate": 9.936579134137686e-05,
"loss": 0.3828912258148193,
"step": 4470
},
{
"epoch": 0.6359119943222143,
"grad_norm": 6.173798561096191,
"learning_rate": 9.936437189496097e-05,
"loss": 0.392284631729126,
"step": 4480
},
{
"epoch": 0.6373314407381121,
"grad_norm": 8.952240943908691,
"learning_rate": 9.936295244854508e-05,
"loss": 0.41978960037231444,
"step": 4490
},
{
"epoch": 0.63875088715401,
"grad_norm": 9.86811637878418,
"learning_rate": 9.936153300212917e-05,
"loss": 0.42105417251586913,
"step": 4500
},
{
"epoch": 0.63875088715401,
"eval_accuracy": 0.8225344948178293,
"eval_loss": 0.5203356146812439,
"eval_runtime": 33.0374,
"eval_samples_per_second": 476.036,
"eval_steps_per_second": 14.892,
"step": 4500
},
{
"epoch": 0.6401703335699077,
"grad_norm": 10.036981582641602,
"learning_rate": 9.936011355571328e-05,
"loss": 0.41321401596069335,
"step": 4510
},
{
"epoch": 0.6415897799858056,
"grad_norm": 6.618304252624512,
"learning_rate": 9.935869410929738e-05,
"loss": 0.43657841682434084,
"step": 4520
},
{
"epoch": 0.6430092264017033,
"grad_norm": 9.975127220153809,
"learning_rate": 9.935727466288149e-05,
"loss": 0.3949880838394165,
"step": 4530
},
{
"epoch": 0.6444286728176012,
"grad_norm": 8.210672378540039,
"learning_rate": 9.935585521646558e-05,
"loss": 0.4280043125152588,
"step": 4540
},
{
"epoch": 0.6458481192334989,
"grad_norm": 12.055879592895508,
"learning_rate": 9.935443577004968e-05,
"loss": 0.39465947151184083,
"step": 4550
},
{
"epoch": 0.6472675656493967,
"grad_norm": 7.540829658508301,
"learning_rate": 9.935301632363378e-05,
"loss": 0.3965680837631226,
"step": 4560
},
{
"epoch": 0.6486870120652946,
"grad_norm": 9.717781066894531,
"learning_rate": 9.935159687721789e-05,
"loss": 0.40194106101989746,
"step": 4570
},
{
"epoch": 0.6501064584811923,
"grad_norm": 10.271167755126953,
"learning_rate": 9.9350177430802e-05,
"loss": 0.4726293087005615,
"step": 4580
},
{
"epoch": 0.6515259048970902,
"grad_norm": 7.158174514770508,
"learning_rate": 9.93487579843861e-05,
"loss": 0.40993413925170896,
"step": 4590
},
{
"epoch": 0.6529453513129879,
"grad_norm": 10.536994934082031,
"learning_rate": 9.93473385379702e-05,
"loss": 0.4424222469329834,
"step": 4600
},
{
"epoch": 0.6543647977288858,
"grad_norm": 7.256109714508057,
"learning_rate": 9.934591909155429e-05,
"loss": 0.388359522819519,
"step": 4610
},
{
"epoch": 0.6557842441447835,
"grad_norm": 8.278726577758789,
"learning_rate": 9.93444996451384e-05,
"loss": 0.3513230085372925,
"step": 4620
},
{
"epoch": 0.6572036905606813,
"grad_norm": 7.767818927764893,
"learning_rate": 9.93430801987225e-05,
"loss": 0.42050671577453613,
"step": 4630
},
{
"epoch": 0.6586231369765791,
"grad_norm": 3.4903321266174316,
"learning_rate": 9.934166075230661e-05,
"loss": 0.3255154609680176,
"step": 4640
},
{
"epoch": 0.6600425833924769,
"grad_norm": 8.193768501281738,
"learning_rate": 9.93402413058907e-05,
"loss": 0.34639596939086914,
"step": 4650
},
{
"epoch": 0.6614620298083748,
"grad_norm": 6.168176651000977,
"learning_rate": 9.93388218594748e-05,
"loss": 0.3619822025299072,
"step": 4660
},
{
"epoch": 0.6628814762242725,
"grad_norm": 4.793501853942871,
"learning_rate": 9.933740241305892e-05,
"loss": 0.3441330909729004,
"step": 4670
},
{
"epoch": 0.6643009226401704,
"grad_norm": 7.100066184997559,
"learning_rate": 9.933598296664301e-05,
"loss": 0.41966400146484373,
"step": 4680
},
{
"epoch": 0.6657203690560681,
"grad_norm": 8.032003402709961,
"learning_rate": 9.933456352022713e-05,
"loss": 0.39086959362030027,
"step": 4690
},
{
"epoch": 0.6671398154719659,
"grad_norm": 5.533408164978027,
"learning_rate": 9.933314407381121e-05,
"loss": 0.455733060836792,
"step": 4700
},
{
"epoch": 0.6685592618878637,
"grad_norm": 6.478943347930908,
"learning_rate": 9.933172462739532e-05,
"loss": 0.3870114326477051,
"step": 4710
},
{
"epoch": 0.6699787083037615,
"grad_norm": 8.963722229003906,
"learning_rate": 9.933030518097942e-05,
"loss": 0.4041899681091309,
"step": 4720
},
{
"epoch": 0.6713981547196594,
"grad_norm": 4.072963714599609,
"learning_rate": 9.932888573456353e-05,
"loss": 0.35542023181915283,
"step": 4730
},
{
"epoch": 0.6728176011355571,
"grad_norm": 6.834389686584473,
"learning_rate": 9.932746628814763e-05,
"loss": 0.34830470085144044,
"step": 4740
},
{
"epoch": 0.674237047551455,
"grad_norm": 7.003122329711914,
"learning_rate": 9.932604684173174e-05,
"loss": 0.3465887069702148,
"step": 4750
},
{
"epoch": 0.6756564939673527,
"grad_norm": 8.914156913757324,
"learning_rate": 9.932462739531583e-05,
"loss": 0.44321861267089846,
"step": 4760
},
{
"epoch": 0.6770759403832506,
"grad_norm": 7.6024627685546875,
"learning_rate": 9.932320794889993e-05,
"loss": 0.40067334175109864,
"step": 4770
},
{
"epoch": 0.6784953867991483,
"grad_norm": 8.667821884155273,
"learning_rate": 9.932178850248404e-05,
"loss": 0.371229887008667,
"step": 4780
},
{
"epoch": 0.6799148332150461,
"grad_norm": 9.355796813964844,
"learning_rate": 9.932036905606814e-05,
"loss": 0.3920291900634766,
"step": 4790
},
{
"epoch": 0.681334279630944,
"grad_norm": 6.767845153808594,
"learning_rate": 9.931894960965225e-05,
"loss": 0.3848612070083618,
"step": 4800
},
{
"epoch": 0.6827537260468417,
"grad_norm": 8.195937156677246,
"learning_rate": 9.931767210787794e-05,
"loss": 0.5190616607666015,
"step": 4810
},
{
"epoch": 0.6841731724627396,
"grad_norm": 6.033681869506836,
"learning_rate": 9.931625266146203e-05,
"loss": 0.39132606983184814,
"step": 4820
},
{
"epoch": 0.6855926188786373,
"grad_norm": 8.469270706176758,
"learning_rate": 9.931483321504613e-05,
"loss": 0.3626258850097656,
"step": 4830
},
{
"epoch": 0.6870120652945352,
"grad_norm": 4.255542278289795,
"learning_rate": 9.931341376863024e-05,
"loss": 0.31856842041015626,
"step": 4840
},
{
"epoch": 0.6884315117104329,
"grad_norm": 9.191469192504883,
"learning_rate": 9.931199432221434e-05,
"loss": 0.3280362367630005,
"step": 4850
},
{
"epoch": 0.6898509581263307,
"grad_norm": 8.94046688079834,
"learning_rate": 9.931057487579845e-05,
"loss": 0.39851620197296145,
"step": 4860
},
{
"epoch": 0.6912704045422285,
"grad_norm": 7.770534992218018,
"learning_rate": 9.930915542938255e-05,
"loss": 0.33825528621673584,
"step": 4870
},
{
"epoch": 0.6926898509581263,
"grad_norm": 6.560062885284424,
"learning_rate": 9.930773598296664e-05,
"loss": 0.35839481353759767,
"step": 4880
},
{
"epoch": 0.6941092973740242,
"grad_norm": 9.24365520477295,
"learning_rate": 9.930631653655074e-05,
"loss": 0.39770119190216063,
"step": 4890
},
{
"epoch": 0.6955287437899219,
"grad_norm": 11.744332313537598,
"learning_rate": 9.930489709013485e-05,
"loss": 0.4902297019958496,
"step": 4900
},
{
"epoch": 0.6969481902058198,
"grad_norm": 7.251524448394775,
"learning_rate": 9.930347764371895e-05,
"loss": 0.40317511558532715,
"step": 4910
},
{
"epoch": 0.6983676366217175,
"grad_norm": 8.896724700927734,
"learning_rate": 9.930205819730306e-05,
"loss": 0.44049978256225586,
"step": 4920
},
{
"epoch": 0.6997870830376153,
"grad_norm": 7.477156162261963,
"learning_rate": 9.930063875088716e-05,
"loss": 0.3586245536804199,
"step": 4930
},
{
"epoch": 0.7012065294535131,
"grad_norm": 6.159836769104004,
"learning_rate": 9.929921930447126e-05,
"loss": 0.32783629894256594,
"step": 4940
},
{
"epoch": 0.7026259758694109,
"grad_norm": 6.85299825668335,
"learning_rate": 9.929779985805537e-05,
"loss": 0.30911822319030763,
"step": 4950
},
{
"epoch": 0.7040454222853088,
"grad_norm": 7.820040225982666,
"learning_rate": 9.929638041163946e-05,
"loss": 0.36734838485717775,
"step": 4960
},
{
"epoch": 0.7054648687012065,
"grad_norm": 6.66180944442749,
"learning_rate": 9.929496096522358e-05,
"loss": 0.37120904922485354,
"step": 4970
},
{
"epoch": 0.7068843151171044,
"grad_norm": 7.3861775398254395,
"learning_rate": 9.929354151880766e-05,
"loss": 0.4064349174499512,
"step": 4980
},
{
"epoch": 0.7083037615330021,
"grad_norm": 7.068629741668701,
"learning_rate": 9.929212207239177e-05,
"loss": 0.36406426429748534,
"step": 4990
},
{
"epoch": 0.7097232079489,
"grad_norm": 7.482442378997803,
"learning_rate": 9.929070262597587e-05,
"loss": 0.40763154029846194,
"step": 5000
},
{
"epoch": 0.7097232079489,
"eval_accuracy": 0.8707954473198957,
"eval_loss": 0.37987253069877625,
"eval_runtime": 33.0642,
"eval_samples_per_second": 475.651,
"eval_steps_per_second": 14.88,
"step": 5000
},
{
"epoch": 0.7111426543647977,
"grad_norm": 5.368759632110596,
"learning_rate": 9.928928317955998e-05,
"loss": 0.40792322158813477,
"step": 5010
},
{
"epoch": 0.7125621007806955,
"grad_norm": 3.8395280838012695,
"learning_rate": 9.928786373314408e-05,
"loss": 0.45433621406555175,
"step": 5020
},
{
"epoch": 0.7139815471965933,
"grad_norm": 7.884678840637207,
"learning_rate": 9.928644428672817e-05,
"loss": 0.3092354774475098,
"step": 5030
},
{
"epoch": 0.7154009936124911,
"grad_norm": 9.11925983428955,
"learning_rate": 9.928502484031228e-05,
"loss": 0.3887113094329834,
"step": 5040
},
{
"epoch": 0.716820440028389,
"grad_norm": 8.5901517868042,
"learning_rate": 9.928360539389638e-05,
"loss": 0.3938072443008423,
"step": 5050
},
{
"epoch": 0.7182398864442867,
"grad_norm": 4.011209011077881,
"learning_rate": 9.928218594748049e-05,
"loss": 0.3140719890594482,
"step": 5060
},
{
"epoch": 0.7196593328601846,
"grad_norm": 9.04295825958252,
"learning_rate": 9.928076650106459e-05,
"loss": 0.37023751735687255,
"step": 5070
},
{
"epoch": 0.7210787792760823,
"grad_norm": 7.336644649505615,
"learning_rate": 9.92793470546487e-05,
"loss": 0.3326029539108276,
"step": 5080
},
{
"epoch": 0.7224982256919801,
"grad_norm": 6.824075698852539,
"learning_rate": 9.927792760823278e-05,
"loss": 0.31377925872802737,
"step": 5090
},
{
"epoch": 0.7239176721078779,
"grad_norm": 6.152795314788818,
"learning_rate": 9.92765081618169e-05,
"loss": 0.4362512111663818,
"step": 5100
},
{
"epoch": 0.7253371185237757,
"grad_norm": 7.997036457061768,
"learning_rate": 9.927508871540099e-05,
"loss": 0.39910459518432617,
"step": 5110
},
{
"epoch": 0.7267565649396736,
"grad_norm": 7.5024309158325195,
"learning_rate": 9.92736692689851e-05,
"loss": 0.3690288305282593,
"step": 5120
},
{
"epoch": 0.7281760113555713,
"grad_norm": 9.340811729431152,
"learning_rate": 9.92722498225692e-05,
"loss": 0.28037595748901367,
"step": 5130
},
{
"epoch": 0.7295954577714692,
"grad_norm": 6.796107292175293,
"learning_rate": 9.92708303761533e-05,
"loss": 0.2862435817718506,
"step": 5140
},
{
"epoch": 0.7310149041873669,
"grad_norm": 6.0283379554748535,
"learning_rate": 9.926941092973741e-05,
"loss": 0.351378345489502,
"step": 5150
},
{
"epoch": 0.7324343506032647,
"grad_norm": 6.880161762237549,
"learning_rate": 9.926799148332151e-05,
"loss": 0.3127347230911255,
"step": 5160
},
{
"epoch": 0.7338537970191625,
"grad_norm": 7.761416912078857,
"learning_rate": 9.926657203690562e-05,
"loss": 0.3232876777648926,
"step": 5170
},
{
"epoch": 0.7352732434350603,
"grad_norm": 8.840635299682617,
"learning_rate": 9.926515259048972e-05,
"loss": 0.36195032596588134,
"step": 5180
},
{
"epoch": 0.7366926898509581,
"grad_norm": 10.067350387573242,
"learning_rate": 9.926373314407381e-05,
"loss": 0.33318257331848145,
"step": 5190
},
{
"epoch": 0.7381121362668559,
"grad_norm": 4.935089111328125,
"learning_rate": 9.926231369765791e-05,
"loss": 0.3263442039489746,
"step": 5200
},
{
"epoch": 0.7395315826827538,
"grad_norm": 6.868301868438721,
"learning_rate": 9.926089425124202e-05,
"loss": 0.4087569236755371,
"step": 5210
},
{
"epoch": 0.7409510290986515,
"grad_norm": 7.978097915649414,
"learning_rate": 9.925947480482612e-05,
"loss": 0.33616573810577394,
"step": 5220
},
{
"epoch": 0.7423704755145494,
"grad_norm": 11.391094207763672,
"learning_rate": 9.925805535841023e-05,
"loss": 0.33483550548553465,
"step": 5230
},
{
"epoch": 0.7437899219304471,
"grad_norm": 5.558361530303955,
"learning_rate": 9.925663591199433e-05,
"loss": 0.38994641304016114,
"step": 5240
},
{
"epoch": 0.7452093683463449,
"grad_norm": 2.6022746562957764,
"learning_rate": 9.925521646557842e-05,
"loss": 0.2801194429397583,
"step": 5250
},
{
"epoch": 0.7466288147622427,
"grad_norm": 10.395146369934082,
"learning_rate": 9.925379701916253e-05,
"loss": 0.45772466659545896,
"step": 5260
},
{
"epoch": 0.7480482611781405,
"grad_norm": 10.162497520446777,
"learning_rate": 9.925237757274663e-05,
"loss": 0.3906741142272949,
"step": 5270
},
{
"epoch": 0.7494677075940384,
"grad_norm": 7.618703365325928,
"learning_rate": 9.925095812633074e-05,
"loss": 0.3549813747406006,
"step": 5280
},
{
"epoch": 0.7508871540099361,
"grad_norm": 6.407444953918457,
"learning_rate": 9.924953867991483e-05,
"loss": 0.3040858268737793,
"step": 5290
},
{
"epoch": 0.752306600425834,
"grad_norm": 7.738057613372803,
"learning_rate": 9.924811923349894e-05,
"loss": 0.39499850273132325,
"step": 5300
},
{
"epoch": 0.7537260468417317,
"grad_norm": 7.237374782562256,
"learning_rate": 9.924669978708304e-05,
"loss": 0.3085558652877808,
"step": 5310
},
{
"epoch": 0.7551454932576295,
"grad_norm": 6.442776203155518,
"learning_rate": 9.924528034066715e-05,
"loss": 0.40102262496948243,
"step": 5320
},
{
"epoch": 0.7565649396735273,
"grad_norm": 10.280111312866211,
"learning_rate": 9.924386089425126e-05,
"loss": 0.3338863611221313,
"step": 5330
},
{
"epoch": 0.7579843860894251,
"grad_norm": 8.590238571166992,
"learning_rate": 9.924244144783534e-05,
"loss": 0.48393831253051756,
"step": 5340
},
{
"epoch": 0.759403832505323,
"grad_norm": 4.818009376525879,
"learning_rate": 9.924102200141945e-05,
"loss": 0.31519811153411864,
"step": 5350
},
{
"epoch": 0.7608232789212207,
"grad_norm": 7.284486293792725,
"learning_rate": 9.923960255500355e-05,
"loss": 0.3537211179733276,
"step": 5360
},
{
"epoch": 0.7622427253371186,
"grad_norm": 8.618793487548828,
"learning_rate": 9.923818310858766e-05,
"loss": 0.34086947441101073,
"step": 5370
},
{
"epoch": 0.7636621717530163,
"grad_norm": 8.162178039550781,
"learning_rate": 9.923676366217176e-05,
"loss": 0.38811311721801756,
"step": 5380
},
{
"epoch": 0.7650816181689141,
"grad_norm": 7.360818386077881,
"learning_rate": 9.923534421575587e-05,
"loss": 0.30603010654449464,
"step": 5390
},
{
"epoch": 0.7665010645848119,
"grad_norm": 4.011861801147461,
"learning_rate": 9.923392476933995e-05,
"loss": 0.23683266639709472,
"step": 5400
},
{
"epoch": 0.7679205110007097,
"grad_norm": 5.943147659301758,
"learning_rate": 9.923250532292406e-05,
"loss": 0.34063313007354734,
"step": 5410
},
{
"epoch": 0.7693399574166075,
"grad_norm": 7.751121997833252,
"learning_rate": 9.923108587650817e-05,
"loss": 0.36524248123168945,
"step": 5420
},
{
"epoch": 0.7707594038325053,
"grad_norm": 8.413863182067871,
"learning_rate": 9.922966643009227e-05,
"loss": 0.3002290725708008,
"step": 5430
},
{
"epoch": 0.7721788502484032,
"grad_norm": 7.4792280197143555,
"learning_rate": 9.922824698367638e-05,
"loss": 0.2858253240585327,
"step": 5440
},
{
"epoch": 0.7735982966643009,
"grad_norm": 4.943634986877441,
"learning_rate": 9.922682753726047e-05,
"loss": 0.3922913074493408,
"step": 5450
},
{
"epoch": 0.7750177430801988,
"grad_norm": 9.556757926940918,
"learning_rate": 9.922540809084458e-05,
"loss": 0.32624542713165283,
"step": 5460
},
{
"epoch": 0.7764371894960965,
"grad_norm": 6.306029319763184,
"learning_rate": 9.922398864442867e-05,
"loss": 0.32522106170654297,
"step": 5470
},
{
"epoch": 0.7778566359119943,
"grad_norm": 9.622481346130371,
"learning_rate": 9.922256919801279e-05,
"loss": 0.32840585708618164,
"step": 5480
},
{
"epoch": 0.7792760823278921,
"grad_norm": 6.480415344238281,
"learning_rate": 9.922114975159688e-05,
"loss": 0.31494650840759275,
"step": 5490
},
{
"epoch": 0.7806955287437899,
"grad_norm": 9.822346687316895,
"learning_rate": 9.921973030518098e-05,
"loss": 0.3520227909088135,
"step": 5500
},
{
"epoch": 0.7806955287437899,
"eval_accuracy": 0.8887263940993196,
"eval_loss": 0.331625759601593,
"eval_runtime": 33.1217,
"eval_samples_per_second": 474.825,
"eval_steps_per_second": 14.854,
"step": 5500
},
{
"epoch": 0.7821149751596878,
"grad_norm": 8.544402122497559,
"learning_rate": 9.921831085876508e-05,
"loss": 0.3386709451675415,
"step": 5510
},
{
"epoch": 0.7835344215755855,
"grad_norm": 6.877591133117676,
"learning_rate": 9.921689141234919e-05,
"loss": 0.3577073574066162,
"step": 5520
},
{
"epoch": 0.7849538679914834,
"grad_norm": 8.182839393615723,
"learning_rate": 9.92154719659333e-05,
"loss": 0.33861188888549804,
"step": 5530
},
{
"epoch": 0.7863733144073811,
"grad_norm": 7.762393474578857,
"learning_rate": 9.92140525195174e-05,
"loss": 0.2913277387619019,
"step": 5540
},
{
"epoch": 0.7877927608232789,
"grad_norm": 9.238672256469727,
"learning_rate": 9.92126330731015e-05,
"loss": 0.27555758953094484,
"step": 5550
},
{
"epoch": 0.7892122072391767,
"grad_norm": 8.316729545593262,
"learning_rate": 9.921121362668559e-05,
"loss": 0.3221546411514282,
"step": 5560
},
{
"epoch": 0.7906316536550745,
"grad_norm": 5.685539245605469,
"learning_rate": 9.92097941802697e-05,
"loss": 0.335821533203125,
"step": 5570
},
{
"epoch": 0.7920511000709723,
"grad_norm": 9.121819496154785,
"learning_rate": 9.92083747338538e-05,
"loss": 0.41519789695739745,
"step": 5580
},
{
"epoch": 0.7934705464868701,
"grad_norm": 10.83812141418457,
"learning_rate": 9.920695528743791e-05,
"loss": 0.30081839561462403,
"step": 5590
},
{
"epoch": 0.794889992902768,
"grad_norm": 3.7030341625213623,
"learning_rate": 9.9205535841022e-05,
"loss": 0.3369245767593384,
"step": 5600
},
{
"epoch": 0.7963094393186657,
"grad_norm": 3.8987886905670166,
"learning_rate": 9.92041163946061e-05,
"loss": 0.3294223785400391,
"step": 5610
},
{
"epoch": 0.7977288857345636,
"grad_norm": 4.1831207275390625,
"learning_rate": 9.920269694819022e-05,
"loss": 0.2734922170639038,
"step": 5620
},
{
"epoch": 0.7991483321504613,
"grad_norm": 7.363320827484131,
"learning_rate": 9.920127750177431e-05,
"loss": 0.3629761219024658,
"step": 5630
},
{
"epoch": 0.8005677785663591,
"grad_norm": 3.947075366973877,
"learning_rate": 9.919985805535842e-05,
"loss": 0.24655752182006835,
"step": 5640
},
{
"epoch": 0.8019872249822569,
"grad_norm": 7.183192253112793,
"learning_rate": 9.919843860894251e-05,
"loss": 0.3074009895324707,
"step": 5650
},
{
"epoch": 0.8034066713981547,
"grad_norm": 9.004253387451172,
"learning_rate": 9.919701916252662e-05,
"loss": 0.38861281871795655,
"step": 5660
},
{
"epoch": 0.8048261178140526,
"grad_norm": 7.553649425506592,
"learning_rate": 9.919559971611072e-05,
"loss": 0.4247180461883545,
"step": 5670
},
{
"epoch": 0.8062455642299503,
"grad_norm": 6.382741928100586,
"learning_rate": 9.919418026969483e-05,
"loss": 0.304930305480957,
"step": 5680
},
{
"epoch": 0.8076650106458482,
"grad_norm": 5.102434158325195,
"learning_rate": 9.919276082327893e-05,
"loss": 0.38076980113983155,
"step": 5690
},
{
"epoch": 0.8090844570617459,
"grad_norm": 6.131350517272949,
"learning_rate": 9.919134137686302e-05,
"loss": 0.40895967483520507,
"step": 5700
},
{
"epoch": 0.8105039034776437,
"grad_norm": 7.717721939086914,
"learning_rate": 9.918992193044713e-05,
"loss": 0.34289727210998533,
"step": 5710
},
{
"epoch": 0.8119233498935415,
"grad_norm": 7.452071189880371,
"learning_rate": 9.918850248403123e-05,
"loss": 0.26248266696929934,
"step": 5720
},
{
"epoch": 0.8133427963094393,
"grad_norm": 4.934199333190918,
"learning_rate": 9.918708303761534e-05,
"loss": 0.2918365478515625,
"step": 5730
},
{
"epoch": 0.8147622427253371,
"grad_norm": 3.497220993041992,
"learning_rate": 9.918566359119944e-05,
"loss": 0.27859480381011964,
"step": 5740
},
{
"epoch": 0.8161816891412349,
"grad_norm": 9.320852279663086,
"learning_rate": 9.918424414478355e-05,
"loss": 0.34371328353881836,
"step": 5750
},
{
"epoch": 0.8176011355571328,
"grad_norm": 10.081619262695312,
"learning_rate": 9.918282469836763e-05,
"loss": 0.36181211471557617,
"step": 5760
},
{
"epoch": 0.8190205819730305,
"grad_norm": 7.466938018798828,
"learning_rate": 9.918140525195174e-05,
"loss": 0.34078028202056887,
"step": 5770
},
{
"epoch": 0.8204400283889283,
"grad_norm": 4.303114414215088,
"learning_rate": 9.917998580553584e-05,
"loss": 0.34729723930358886,
"step": 5780
},
{
"epoch": 0.8218594748048261,
"grad_norm": 9.38592529296875,
"learning_rate": 9.917856635911995e-05,
"loss": 0.4285425662994385,
"step": 5790
},
{
"epoch": 0.8232789212207239,
"grad_norm": 9.465388298034668,
"learning_rate": 9.917714691270405e-05,
"loss": 0.3501663446426392,
"step": 5800
},
{
"epoch": 0.8246983676366217,
"grad_norm": 5.500204086303711,
"learning_rate": 9.917572746628815e-05,
"loss": 0.3102808952331543,
"step": 5810
},
{
"epoch": 0.8261178140525195,
"grad_norm": 4.572218894958496,
"learning_rate": 9.917430801987226e-05,
"loss": 0.2433872938156128,
"step": 5820
},
{
"epoch": 0.8275372604684174,
"grad_norm": 9.858591079711914,
"learning_rate": 9.917288857345636e-05,
"loss": 0.30695419311523436,
"step": 5830
},
{
"epoch": 0.8289567068843151,
"grad_norm": 6.843176364898682,
"learning_rate": 9.917146912704047e-05,
"loss": 0.35634801387786863,
"step": 5840
},
{
"epoch": 0.830376153300213,
"grad_norm": 10.634949684143066,
"learning_rate": 9.917004968062456e-05,
"loss": 0.3107039451599121,
"step": 5850
},
{
"epoch": 0.8317955997161107,
"grad_norm": 8.44272518157959,
"learning_rate": 9.916863023420866e-05,
"loss": 0.3672316551208496,
"step": 5860
},
{
"epoch": 0.8332150461320085,
"grad_norm": 5.4848785400390625,
"learning_rate": 9.916721078779276e-05,
"loss": 0.4015390872955322,
"step": 5870
},
{
"epoch": 0.8346344925479063,
"grad_norm": 7.271710395812988,
"learning_rate": 9.916579134137687e-05,
"loss": 0.23676373958587646,
"step": 5880
},
{
"epoch": 0.8360539389638041,
"grad_norm": 4.376358509063721,
"learning_rate": 9.916437189496097e-05,
"loss": 0.2711988687515259,
"step": 5890
},
{
"epoch": 0.837473385379702,
"grad_norm": 6.931346416473389,
"learning_rate": 9.916295244854508e-05,
"loss": 0.2837867021560669,
"step": 5900
},
{
"epoch": 0.8388928317955997,
"grad_norm": 7.611521244049072,
"learning_rate": 9.916153300212918e-05,
"loss": 0.315134072303772,
"step": 5910
},
{
"epoch": 0.8403122782114976,
"grad_norm": 7.071038722991943,
"learning_rate": 9.916011355571327e-05,
"loss": 0.3368415594100952,
"step": 5920
},
{
"epoch": 0.8417317246273953,
"grad_norm": 4.1825056076049805,
"learning_rate": 9.915869410929738e-05,
"loss": 0.3074488162994385,
"step": 5930
},
{
"epoch": 0.8431511710432931,
"grad_norm": 6.3160929679870605,
"learning_rate": 9.915727466288148e-05,
"loss": 0.3252119541168213,
"step": 5940
},
{
"epoch": 0.8445706174591909,
"grad_norm": 8.007182121276855,
"learning_rate": 9.915585521646559e-05,
"loss": 0.23286638259887696,
"step": 5950
},
{
"epoch": 0.8459900638750887,
"grad_norm": 7.93002986907959,
"learning_rate": 9.915443577004968e-05,
"loss": 0.2870266199111938,
"step": 5960
},
{
"epoch": 0.8474095102909865,
"grad_norm": 5.426539897918701,
"learning_rate": 9.915301632363379e-05,
"loss": 0.29859611988067625,
"step": 5970
},
{
"epoch": 0.8488289567068843,
"grad_norm": 4.294735908508301,
"learning_rate": 9.915159687721788e-05,
"loss": 0.24727118015289307,
"step": 5980
},
{
"epoch": 0.8502484031227822,
"grad_norm": 8.501158714294434,
"learning_rate": 9.9150177430802e-05,
"loss": 0.3406102657318115,
"step": 5990
},
{
"epoch": 0.8516678495386799,
"grad_norm": 8.125472068786621,
"learning_rate": 9.914875798438609e-05,
"loss": 0.3179450273513794,
"step": 6000
},
{
"epoch": 0.8516678495386799,
"eval_accuracy": 0.8626565778597317,
"eval_loss": 0.4082823693752289,
"eval_runtime": 33.3539,
"eval_samples_per_second": 471.52,
"eval_steps_per_second": 14.751,
"step": 6000
},
{
"epoch": 0.8530872959545777,
"grad_norm": 4.980500221252441,
"learning_rate": 9.914733853797019e-05,
"loss": 0.3588885307312012,
"step": 6010
},
{
"epoch": 0.8545067423704755,
"grad_norm": 5.385146617889404,
"learning_rate": 9.91459190915543e-05,
"loss": 0.28512775897979736,
"step": 6020
},
{
"epoch": 0.8559261887863733,
"grad_norm": 8.24423599243164,
"learning_rate": 9.91444996451384e-05,
"loss": 0.32922515869140623,
"step": 6030
},
{
"epoch": 0.8573456352022711,
"grad_norm": 6.568521499633789,
"learning_rate": 9.914308019872251e-05,
"loss": 0.24458625316619872,
"step": 6040
},
{
"epoch": 0.8587650816181689,
"grad_norm": 6.268226146697998,
"learning_rate": 9.914166075230661e-05,
"loss": 0.30663580894470216,
"step": 6050
},
{
"epoch": 0.8601845280340668,
"grad_norm": 5.911208152770996,
"learning_rate": 9.91402413058907e-05,
"loss": 0.38018484115600587,
"step": 6060
},
{
"epoch": 0.8616039744499645,
"grad_norm": 5.170897483825684,
"learning_rate": 9.91388218594748e-05,
"loss": 0.22591965198516845,
"step": 6070
},
{
"epoch": 0.8630234208658624,
"grad_norm": 5.716799736022949,
"learning_rate": 9.913740241305891e-05,
"loss": 0.2626305103302002,
"step": 6080
},
{
"epoch": 0.8644428672817601,
"grad_norm": 6.144148349761963,
"learning_rate": 9.913598296664301e-05,
"loss": 0.23459088802337646,
"step": 6090
},
{
"epoch": 0.8658623136976579,
"grad_norm": 8.506244659423828,
"learning_rate": 9.913456352022712e-05,
"loss": 0.36330761909484866,
"step": 6100
},
{
"epoch": 0.8672817601135557,
"grad_norm": 9.882643699645996,
"learning_rate": 9.913314407381122e-05,
"loss": 0.32826101779937744,
"step": 6110
},
{
"epoch": 0.8687012065294535,
"grad_norm": 8.62743091583252,
"learning_rate": 9.913172462739532e-05,
"loss": 0.30355727672576904,
"step": 6120
},
{
"epoch": 0.8701206529453513,
"grad_norm": 11.726634979248047,
"learning_rate": 9.913030518097943e-05,
"loss": 0.280806303024292,
"step": 6130
},
{
"epoch": 0.8715400993612491,
"grad_norm": 7.7827839851379395,
"learning_rate": 9.912888573456352e-05,
"loss": 0.3389289855957031,
"step": 6140
},
{
"epoch": 0.872959545777147,
"grad_norm": 12.07807731628418,
"learning_rate": 9.912746628814764e-05,
"loss": 0.31570281982421877,
"step": 6150
},
{
"epoch": 0.8743789921930447,
"grad_norm": 4.949673652648926,
"learning_rate": 9.912604684173173e-05,
"loss": 0.269368839263916,
"step": 6160
},
{
"epoch": 0.8757984386089425,
"grad_norm": 6.946098327636719,
"learning_rate": 9.912462739531583e-05,
"loss": 0.33236119747161863,
"step": 6170
},
{
"epoch": 0.8772178850248403,
"grad_norm": 7.137246131896973,
"learning_rate": 9.912320794889993e-05,
"loss": 0.3343817710876465,
"step": 6180
},
{
"epoch": 0.8786373314407381,
"grad_norm": 4.929990768432617,
"learning_rate": 9.912178850248404e-05,
"loss": 0.23963472843170167,
"step": 6190
},
{
"epoch": 0.8800567778566359,
"grad_norm": 10.46869945526123,
"learning_rate": 9.912036905606814e-05,
"loss": 0.2913534641265869,
"step": 6200
},
{
"epoch": 0.8814762242725337,
"grad_norm": 7.179393291473389,
"learning_rate": 9.911894960965225e-05,
"loss": 0.27806806564331055,
"step": 6210
},
{
"epoch": 0.8828956706884316,
"grad_norm": 5.430668830871582,
"learning_rate": 9.911753016323634e-05,
"loss": 0.2537125587463379,
"step": 6220
},
{
"epoch": 0.8843151171043293,
"grad_norm": 7.001239776611328,
"learning_rate": 9.911611071682044e-05,
"loss": 0.2821568489074707,
"step": 6230
},
{
"epoch": 0.8857345635202271,
"grad_norm": 10.218942642211914,
"learning_rate": 9.911469127040455e-05,
"loss": 0.30785112380981444,
"step": 6240
},
{
"epoch": 0.8871540099361249,
"grad_norm": 3.9179635047912598,
"learning_rate": 9.911327182398865e-05,
"loss": 0.3376051902770996,
"step": 6250
},
{
"epoch": 0.8885734563520227,
"grad_norm": 7.35114049911499,
"learning_rate": 9.911185237757276e-05,
"loss": 0.2029582977294922,
"step": 6260
},
{
"epoch": 0.8899929027679205,
"grad_norm": 7.477942943572998,
"learning_rate": 9.911043293115684e-05,
"loss": 0.31639838218688965,
"step": 6270
},
{
"epoch": 0.8914123491838183,
"grad_norm": 6.479630470275879,
"learning_rate": 9.910901348474096e-05,
"loss": 0.35874156951904296,
"step": 6280
},
{
"epoch": 0.8928317955997161,
"grad_norm": 5.139812469482422,
"learning_rate": 9.910759403832505e-05,
"loss": 0.23642609119415284,
"step": 6290
},
{
"epoch": 0.8942512420156139,
"grad_norm": 7.17330265045166,
"learning_rate": 9.910617459190916e-05,
"loss": 0.27939982414245607,
"step": 6300
},
{
"epoch": 0.8956706884315118,
"grad_norm": 8.804689407348633,
"learning_rate": 9.910475514549326e-05,
"loss": 0.3722469568252563,
"step": 6310
},
{
"epoch": 0.8970901348474095,
"grad_norm": 2.958435297012329,
"learning_rate": 9.910333569907736e-05,
"loss": 0.23576738834381103,
"step": 6320
},
{
"epoch": 0.8985095812633073,
"grad_norm": 10.53680419921875,
"learning_rate": 9.910191625266147e-05,
"loss": 0.4027998447418213,
"step": 6330
},
{
"epoch": 0.8999290276792051,
"grad_norm": 5.857926368713379,
"learning_rate": 9.910049680624557e-05,
"loss": 0.29457688331604004,
"step": 6340
},
{
"epoch": 0.9013484740951029,
"grad_norm": 1.7572773694992065,
"learning_rate": 9.909907735982968e-05,
"loss": 0.2572882890701294,
"step": 6350
},
{
"epoch": 0.9027679205110007,
"grad_norm": 4.274378299713135,
"learning_rate": 9.909765791341377e-05,
"loss": 0.23681292533874512,
"step": 6360
},
{
"epoch": 0.9041873669268985,
"grad_norm": 7.596087455749512,
"learning_rate": 9.909623846699787e-05,
"loss": 0.23812153339385986,
"step": 6370
},
{
"epoch": 0.9056068133427964,
"grad_norm": 5.59556770324707,
"learning_rate": 9.909481902058197e-05,
"loss": 0.29871695041656493,
"step": 6380
},
{
"epoch": 0.9070262597586941,
"grad_norm": 4.671100616455078,
"learning_rate": 9.909339957416608e-05,
"loss": 0.23768167495727538,
"step": 6390
},
{
"epoch": 0.9084457061745919,
"grad_norm": 6.55142068862915,
"learning_rate": 9.909198012775018e-05,
"loss": 0.2650206804275513,
"step": 6400
},
{
"epoch": 0.9098651525904897,
"grad_norm": 7.774087429046631,
"learning_rate": 9.909056068133429e-05,
"loss": 0.2898139238357544,
"step": 6410
},
{
"epoch": 0.9112845990063875,
"grad_norm": 6.386779308319092,
"learning_rate": 9.908914123491839e-05,
"loss": 0.26163647174835203,
"step": 6420
},
{
"epoch": 0.9127040454222853,
"grad_norm": 7.33029317855835,
"learning_rate": 9.908772178850248e-05,
"loss": 0.2447366952896118,
"step": 6430
},
{
"epoch": 0.9141234918381831,
"grad_norm": 10.35724925994873,
"learning_rate": 9.90863023420866e-05,
"loss": 0.2560460329055786,
"step": 6440
},
{
"epoch": 0.915542938254081,
"grad_norm": 9.2293062210083,
"learning_rate": 9.908488289567069e-05,
"loss": 0.3864759922027588,
"step": 6450
},
{
"epoch": 0.9169623846699787,
"grad_norm": 8.472285270690918,
"learning_rate": 9.90834634492548e-05,
"loss": 0.2888746976852417,
"step": 6460
},
{
"epoch": 0.9183818310858765,
"grad_norm": 6.22374153137207,
"learning_rate": 9.90820440028389e-05,
"loss": 0.2505399942398071,
"step": 6470
},
{
"epoch": 0.9198012775017743,
"grad_norm": 7.827479839324951,
"learning_rate": 9.9080624556423e-05,
"loss": 0.2327653408050537,
"step": 6480
},
{
"epoch": 0.9212207239176721,
"grad_norm": 7.873356819152832,
"learning_rate": 9.90792051100071e-05,
"loss": 0.2565167903900146,
"step": 6490
},
{
"epoch": 0.9226401703335699,
"grad_norm": 4.665884494781494,
"learning_rate": 9.90777856635912e-05,
"loss": 0.2404710292816162,
"step": 6500
},
{
"epoch": 0.9226401703335699,
"eval_accuracy": 0.9011890379601959,
"eval_loss": 0.29011303186416626,
"eval_runtime": 34.6022,
"eval_samples_per_second": 454.509,
"eval_steps_per_second": 14.219,
"step": 6500
}
],
"logging_steps": 10,
"max_steps": 704500,
"num_input_tokens_seen": 0,
"num_train_epochs": 100,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 0.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}