dchen0's picture
Upload folder using huggingface_hub
73dcdfc verified
{
"best_global_step": 2000,
"best_metric": 0.6596935206968907,
"best_model_checkpoint": "/workspace/output/resnet50/checkpoint-2000",
"epoch": 0.28388928317955997,
"eval_steps": 500,
"global_step": 2000,
"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
}
],
"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
}