roberta-base-mean-400 / trainer_state.json
sobamchan's picture
Upload folder using huggingface_hub
cc27512 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.09176416609314063,
"eval_steps": 5,
"global_step": 400,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0011470520761642578,
"eval_loss": 5.131626605987549,
"eval_runtime": 13.4035,
"eval_samples_per_second": 491.214,
"eval_steps_per_second": 3.88,
"step": 5
},
{
"epoch": 0.0022941041523285156,
"eval_loss": 5.129306316375732,
"eval_runtime": 13.1975,
"eval_samples_per_second": 498.881,
"eval_steps_per_second": 3.94,
"step": 10
},
{
"epoch": 0.0034411562284927736,
"eval_loss": 5.125307559967041,
"eval_runtime": 13.3602,
"eval_samples_per_second": 492.806,
"eval_steps_per_second": 3.892,
"step": 15
},
{
"epoch": 0.004588208304657031,
"eval_loss": 5.1195783615112305,
"eval_runtime": 13.3732,
"eval_samples_per_second": 492.33,
"eval_steps_per_second": 3.888,
"step": 20
},
{
"epoch": 0.005735260380821289,
"eval_loss": 5.11201286315918,
"eval_runtime": 13.3238,
"eval_samples_per_second": 494.153,
"eval_steps_per_second": 3.903,
"step": 25
},
{
"epoch": 0.006882312456985547,
"eval_loss": 5.102468967437744,
"eval_runtime": 13.3391,
"eval_samples_per_second": 493.586,
"eval_steps_per_second": 3.898,
"step": 30
},
{
"epoch": 0.008029364533149804,
"eval_loss": 5.090775012969971,
"eval_runtime": 15.3552,
"eval_samples_per_second": 428.779,
"eval_steps_per_second": 3.386,
"step": 35
},
{
"epoch": 0.009176416609314062,
"eval_loss": 5.0768303871154785,
"eval_runtime": 13.4109,
"eval_samples_per_second": 490.945,
"eval_steps_per_second": 3.877,
"step": 40
},
{
"epoch": 0.01032346868547832,
"eval_loss": 5.0602593421936035,
"eval_runtime": 13.4714,
"eval_samples_per_second": 488.739,
"eval_steps_per_second": 3.86,
"step": 45
},
{
"epoch": 0.011470520761642579,
"eval_loss": 5.04086446762085,
"eval_runtime": 13.4864,
"eval_samples_per_second": 488.195,
"eval_steps_per_second": 3.856,
"step": 50
},
{
"epoch": 0.012617572837806837,
"eval_loss": 5.0182952880859375,
"eval_runtime": 13.4428,
"eval_samples_per_second": 489.78,
"eval_steps_per_second": 3.868,
"step": 55
},
{
"epoch": 0.013764624913971095,
"eval_loss": 4.992081165313721,
"eval_runtime": 13.4681,
"eval_samples_per_second": 488.859,
"eval_steps_per_second": 3.861,
"step": 60
},
{
"epoch": 0.014911676990135353,
"eval_loss": 4.961635112762451,
"eval_runtime": 15.9825,
"eval_samples_per_second": 411.952,
"eval_steps_per_second": 3.254,
"step": 65
},
{
"epoch": 0.01605872906629961,
"eval_loss": 4.926206111907959,
"eval_runtime": 13.4532,
"eval_samples_per_second": 489.402,
"eval_steps_per_second": 3.865,
"step": 70
},
{
"epoch": 0.017205781142463867,
"eval_loss": 4.884685516357422,
"eval_runtime": 13.4162,
"eval_samples_per_second": 490.749,
"eval_steps_per_second": 3.876,
"step": 75
},
{
"epoch": 0.018352833218628125,
"eval_loss": 4.835946559906006,
"eval_runtime": 13.4384,
"eval_samples_per_second": 489.94,
"eval_steps_per_second": 3.87,
"step": 80
},
{
"epoch": 0.019499885294792383,
"eval_loss": 4.778928279876709,
"eval_runtime": 13.3937,
"eval_samples_per_second": 491.575,
"eval_steps_per_second": 3.882,
"step": 85
},
{
"epoch": 0.02064693737095664,
"eval_loss": 4.713075637817383,
"eval_runtime": 13.6158,
"eval_samples_per_second": 483.557,
"eval_steps_per_second": 3.819,
"step": 90
},
{
"epoch": 0.0217939894471209,
"eval_loss": 4.6366777420043945,
"eval_runtime": 13.625,
"eval_samples_per_second": 483.231,
"eval_steps_per_second": 3.817,
"step": 95
},
{
"epoch": 0.022941041523285157,
"grad_norm": 20.385936737060547,
"learning_rate": 7.645259938837921e-07,
"loss": 5.1885,
"step": 100
},
{
"epoch": 0.022941041523285157,
"eval_loss": 4.546780586242676,
"eval_runtime": 15.8199,
"eval_samples_per_second": 416.184,
"eval_steps_per_second": 3.287,
"step": 100
},
{
"epoch": 0.024088093599449415,
"eval_loss": 4.440257549285889,
"eval_runtime": 13.483,
"eval_samples_per_second": 488.317,
"eval_steps_per_second": 3.857,
"step": 105
},
{
"epoch": 0.025235145675613673,
"eval_loss": 4.314813613891602,
"eval_runtime": 13.4631,
"eval_samples_per_second": 489.041,
"eval_steps_per_second": 3.862,
"step": 110
},
{
"epoch": 0.02638219775177793,
"eval_loss": 4.167805194854736,
"eval_runtime": 13.5041,
"eval_samples_per_second": 487.554,
"eval_steps_per_second": 3.851,
"step": 115
},
{
"epoch": 0.02752924982794219,
"eval_loss": 3.996023178100586,
"eval_runtime": 13.5215,
"eval_samples_per_second": 486.928,
"eval_steps_per_second": 3.846,
"step": 120
},
{
"epoch": 0.028676301904106447,
"eval_loss": 3.7965035438537598,
"eval_runtime": 13.6803,
"eval_samples_per_second": 481.276,
"eval_steps_per_second": 3.801,
"step": 125
},
{
"epoch": 0.029823353980270705,
"eval_loss": 3.5700390338897705,
"eval_runtime": 15.357,
"eval_samples_per_second": 428.73,
"eval_steps_per_second": 3.386,
"step": 130
},
{
"epoch": 0.030970406056434963,
"eval_loss": 3.31830096244812,
"eval_runtime": 13.401,
"eval_samples_per_second": 491.308,
"eval_steps_per_second": 3.88,
"step": 135
},
{
"epoch": 0.03211745813259922,
"eval_loss": 3.043388605117798,
"eval_runtime": 13.559,
"eval_samples_per_second": 485.582,
"eval_steps_per_second": 3.835,
"step": 140
},
{
"epoch": 0.033264510208763476,
"eval_loss": 2.758207082748413,
"eval_runtime": 13.5114,
"eval_samples_per_second": 487.293,
"eval_steps_per_second": 3.849,
"step": 145
},
{
"epoch": 0.034411562284927734,
"eval_loss": 2.478577136993408,
"eval_runtime": 13.4468,
"eval_samples_per_second": 489.632,
"eval_steps_per_second": 3.867,
"step": 150
},
{
"epoch": 0.03555861436109199,
"eval_loss": 2.221748113632202,
"eval_runtime": 13.4408,
"eval_samples_per_second": 489.852,
"eval_steps_per_second": 3.869,
"step": 155
},
{
"epoch": 0.03670566643725625,
"eval_loss": 1.9959131479263306,
"eval_runtime": 13.4211,
"eval_samples_per_second": 490.571,
"eval_steps_per_second": 3.874,
"step": 160
},
{
"epoch": 0.03785271851342051,
"eval_loss": 1.808205485343933,
"eval_runtime": 15.751,
"eval_samples_per_second": 418.006,
"eval_steps_per_second": 3.301,
"step": 165
},
{
"epoch": 0.038999770589584766,
"eval_loss": 1.6610738039016724,
"eval_runtime": 13.4476,
"eval_samples_per_second": 489.605,
"eval_steps_per_second": 3.867,
"step": 170
},
{
"epoch": 0.040146822665749024,
"eval_loss": 1.5397450923919678,
"eval_runtime": 13.4818,
"eval_samples_per_second": 488.362,
"eval_steps_per_second": 3.857,
"step": 175
},
{
"epoch": 0.04129387474191328,
"eval_loss": 1.4406381845474243,
"eval_runtime": 13.504,
"eval_samples_per_second": 487.561,
"eval_steps_per_second": 3.851,
"step": 180
},
{
"epoch": 0.04244092681807754,
"eval_loss": 1.3591890335083008,
"eval_runtime": 13.625,
"eval_samples_per_second": 483.229,
"eval_steps_per_second": 3.817,
"step": 185
},
{
"epoch": 0.0435879788942418,
"eval_loss": 1.2934887409210205,
"eval_runtime": 13.5014,
"eval_samples_per_second": 487.654,
"eval_steps_per_second": 3.851,
"step": 190
},
{
"epoch": 0.044735030970406056,
"eval_loss": 1.239295244216919,
"eval_runtime": 15.0045,
"eval_samples_per_second": 438.802,
"eval_steps_per_second": 3.466,
"step": 195
},
{
"epoch": 0.045882083046570314,
"grad_norm": 16.567819595336914,
"learning_rate": 1.5290519877675841e-06,
"loss": 3.2102,
"step": 200
},
{
"epoch": 0.045882083046570314,
"eval_loss": 1.193471074104309,
"eval_runtime": 13.501,
"eval_samples_per_second": 487.667,
"eval_steps_per_second": 3.852,
"step": 200
},
{
"epoch": 0.04702913512273457,
"eval_loss": 1.1555341482162476,
"eval_runtime": 13.5207,
"eval_samples_per_second": 486.957,
"eval_steps_per_second": 3.846,
"step": 205
},
{
"epoch": 0.04817618719889883,
"eval_loss": 1.122100830078125,
"eval_runtime": 13.4164,
"eval_samples_per_second": 490.744,
"eval_steps_per_second": 3.876,
"step": 210
},
{
"epoch": 0.04932323927506309,
"eval_loss": 1.094680666923523,
"eval_runtime": 13.481,
"eval_samples_per_second": 488.39,
"eval_steps_per_second": 3.857,
"step": 215
},
{
"epoch": 0.050470291351227346,
"eval_loss": 1.070283055305481,
"eval_runtime": 13.3745,
"eval_samples_per_second": 492.28,
"eval_steps_per_second": 3.888,
"step": 220
},
{
"epoch": 0.051617343427391604,
"eval_loss": 1.0504087209701538,
"eval_runtime": 13.4482,
"eval_samples_per_second": 489.582,
"eval_steps_per_second": 3.867,
"step": 225
},
{
"epoch": 0.05276439550355586,
"eval_loss": 1.0318756103515625,
"eval_runtime": 15.662,
"eval_samples_per_second": 420.38,
"eval_steps_per_second": 3.32,
"step": 230
},
{
"epoch": 0.05391144757972012,
"eval_loss": 1.016467809677124,
"eval_runtime": 13.3562,
"eval_samples_per_second": 492.953,
"eval_steps_per_second": 3.893,
"step": 235
},
{
"epoch": 0.05505849965588438,
"eval_loss": 1.001065969467163,
"eval_runtime": 13.3769,
"eval_samples_per_second": 492.191,
"eval_steps_per_second": 3.887,
"step": 240
},
{
"epoch": 0.056205551732048636,
"eval_loss": 0.9873594641685486,
"eval_runtime": 13.3634,
"eval_samples_per_second": 492.689,
"eval_steps_per_second": 3.891,
"step": 245
},
{
"epoch": 0.057352603808212894,
"eval_loss": 0.9738806486129761,
"eval_runtime": 13.459,
"eval_samples_per_second": 489.188,
"eval_steps_per_second": 3.864,
"step": 250
},
{
"epoch": 0.05849965588437715,
"eval_loss": 0.9596067667007446,
"eval_runtime": 13.4244,
"eval_samples_per_second": 490.45,
"eval_steps_per_second": 3.874,
"step": 255
},
{
"epoch": 0.05964670796054141,
"eval_loss": 0.9462383389472961,
"eval_runtime": 15.5509,
"eval_samples_per_second": 423.385,
"eval_steps_per_second": 3.344,
"step": 260
},
{
"epoch": 0.06079376003670567,
"eval_loss": 0.9348104000091553,
"eval_runtime": 13.4171,
"eval_samples_per_second": 490.719,
"eval_steps_per_second": 3.876,
"step": 265
},
{
"epoch": 0.06194081211286993,
"eval_loss": 0.9236851334571838,
"eval_runtime": 13.3864,
"eval_samples_per_second": 491.843,
"eval_steps_per_second": 3.885,
"step": 270
},
{
"epoch": 0.06308786418903418,
"eval_loss": 0.9135666489601135,
"eval_runtime": 13.3843,
"eval_samples_per_second": 491.921,
"eval_steps_per_second": 3.885,
"step": 275
},
{
"epoch": 0.06423491626519844,
"eval_loss": 0.9035711884498596,
"eval_runtime": 13.3926,
"eval_samples_per_second": 491.615,
"eval_steps_per_second": 3.883,
"step": 280
},
{
"epoch": 0.0653819683413627,
"eval_loss": 0.8937642574310303,
"eval_runtime": 13.377,
"eval_samples_per_second": 492.19,
"eval_steps_per_second": 3.887,
"step": 285
},
{
"epoch": 0.06652902041752695,
"eval_loss": 0.8842311501502991,
"eval_runtime": 13.4213,
"eval_samples_per_second": 490.562,
"eval_steps_per_second": 3.874,
"step": 290
},
{
"epoch": 0.06767607249369122,
"eval_loss": 0.8754573464393616,
"eval_runtime": 15.0312,
"eval_samples_per_second": 438.022,
"eval_steps_per_second": 3.459,
"step": 295
},
{
"epoch": 0.06882312456985547,
"grad_norm": 14.458847045898438,
"learning_rate": 2.2935779816513764e-06,
"loss": 1.6043,
"step": 300
},
{
"epoch": 0.06882312456985547,
"eval_loss": 0.86653071641922,
"eval_runtime": 13.3572,
"eval_samples_per_second": 492.918,
"eval_steps_per_second": 3.893,
"step": 300
},
{
"epoch": 0.06997017664601973,
"eval_loss": 0.8553701043128967,
"eval_runtime": 13.3944,
"eval_samples_per_second": 491.55,
"eval_steps_per_second": 3.882,
"step": 305
},
{
"epoch": 0.07111722872218398,
"eval_loss": 0.8429736495018005,
"eval_runtime": 13.4704,
"eval_samples_per_second": 488.775,
"eval_steps_per_second": 3.86,
"step": 310
},
{
"epoch": 0.07226428079834825,
"eval_loss": 0.8302232027053833,
"eval_runtime": 13.4048,
"eval_samples_per_second": 491.167,
"eval_steps_per_second": 3.879,
"step": 315
},
{
"epoch": 0.0734113328745125,
"eval_loss": 0.8176185488700867,
"eval_runtime": 13.4173,
"eval_samples_per_second": 490.708,
"eval_steps_per_second": 3.876,
"step": 320
},
{
"epoch": 0.07455838495067676,
"eval_loss": 0.807856559753418,
"eval_runtime": 15.1229,
"eval_samples_per_second": 435.365,
"eval_steps_per_second": 3.438,
"step": 325
},
{
"epoch": 0.07570543702684102,
"eval_loss": 0.7993234992027283,
"eval_runtime": 13.3669,
"eval_samples_per_second": 492.561,
"eval_steps_per_second": 3.89,
"step": 330
},
{
"epoch": 0.07685248910300528,
"eval_loss": 0.7926596999168396,
"eval_runtime": 13.3308,
"eval_samples_per_second": 493.893,
"eval_steps_per_second": 3.901,
"step": 335
},
{
"epoch": 0.07799954117916953,
"eval_loss": 0.7863820195198059,
"eval_runtime": 13.3923,
"eval_samples_per_second": 491.625,
"eval_steps_per_second": 3.883,
"step": 340
},
{
"epoch": 0.0791465932553338,
"eval_loss": 0.7796701192855835,
"eval_runtime": 13.3306,
"eval_samples_per_second": 493.901,
"eval_steps_per_second": 3.901,
"step": 345
},
{
"epoch": 0.08029364533149805,
"eval_loss": 0.7713186740875244,
"eval_runtime": 13.3598,
"eval_samples_per_second": 492.823,
"eval_steps_per_second": 3.892,
"step": 350
},
{
"epoch": 0.08144069740766231,
"eval_loss": 0.7634887099266052,
"eval_runtime": 13.3643,
"eval_samples_per_second": 492.655,
"eval_steps_per_second": 3.891,
"step": 355
},
{
"epoch": 0.08258774948382656,
"eval_loss": 0.7564072012901306,
"eval_runtime": 15.6052,
"eval_samples_per_second": 421.911,
"eval_steps_per_second": 3.332,
"step": 360
},
{
"epoch": 0.08373480155999083,
"eval_loss": 0.7483786940574646,
"eval_runtime": 13.4372,
"eval_samples_per_second": 489.984,
"eval_steps_per_second": 3.87,
"step": 365
},
{
"epoch": 0.08488185363615508,
"eval_loss": 0.7417900562286377,
"eval_runtime": 13.5648,
"eval_samples_per_second": 485.373,
"eval_steps_per_second": 3.833,
"step": 370
},
{
"epoch": 0.08602890571231935,
"eval_loss": 0.732896089553833,
"eval_runtime": 13.4173,
"eval_samples_per_second": 490.71,
"eval_steps_per_second": 3.876,
"step": 375
},
{
"epoch": 0.0871759577884836,
"eval_loss": 0.72364342212677,
"eval_runtime": 13.3644,
"eval_samples_per_second": 492.652,
"eval_steps_per_second": 3.891,
"step": 380
},
{
"epoch": 0.08832300986464786,
"eval_loss": 0.7141902446746826,
"eval_runtime": 13.5373,
"eval_samples_per_second": 486.362,
"eval_steps_per_second": 3.841,
"step": 385
},
{
"epoch": 0.08947006194081211,
"eval_loss": 0.7049544453620911,
"eval_runtime": 15.6105,
"eval_samples_per_second": 421.767,
"eval_steps_per_second": 3.331,
"step": 390
},
{
"epoch": 0.09061711401697638,
"eval_loss": 0.6963789463043213,
"eval_runtime": 13.3674,
"eval_samples_per_second": 492.541,
"eval_steps_per_second": 3.89,
"step": 395
},
{
"epoch": 0.09176416609314063,
"grad_norm": 12.008614540100098,
"learning_rate": 3.0581039755351682e-06,
"loss": 1.3624,
"step": 400
},
{
"epoch": 0.09176416609314063,
"eval_loss": 0.6888003349304199,
"eval_runtime": 13.4558,
"eval_samples_per_second": 489.308,
"eval_steps_per_second": 3.865,
"step": 400
}
],
"logging_steps": 100,
"max_steps": 13077,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 5,
"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": 128,
"trial_name": null,
"trial_params": null
}