oceanpty's picture
Upload trainer_state.json with huggingface_hub
4ff8912 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 500,
"global_step": 468,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.004273504273504274,
"grad_norm": 20.463779905967794,
"learning_rate": 4.2553191489361704e-07,
"loss": 1.8792,
"step": 1
},
{
"epoch": 0.021367521367521368,
"grad_norm": 18.25002365272532,
"learning_rate": 2.1276595744680853e-06,
"loss": 1.8169,
"step": 5
},
{
"epoch": 0.042735042735042736,
"grad_norm": 5.520763657053264,
"learning_rate": 4.255319148936171e-06,
"loss": 1.5621,
"step": 10
},
{
"epoch": 0.0641025641025641,
"grad_norm": 2.4039272335616273,
"learning_rate": 6.382978723404256e-06,
"loss": 1.4414,
"step": 15
},
{
"epoch": 0.08547008547008547,
"grad_norm": 1.5018627664657522,
"learning_rate": 8.510638297872341e-06,
"loss": 1.3849,
"step": 20
},
{
"epoch": 0.10683760683760683,
"grad_norm": 1.2879097291220103,
"learning_rate": 1.0638297872340426e-05,
"loss": 1.3222,
"step": 25
},
{
"epoch": 0.1282051282051282,
"grad_norm": 1.2033621208548797,
"learning_rate": 1.2765957446808513e-05,
"loss": 1.3365,
"step": 30
},
{
"epoch": 0.14957264957264957,
"grad_norm": 1.1255514254267025,
"learning_rate": 1.4893617021276596e-05,
"loss": 1.2732,
"step": 35
},
{
"epoch": 0.17094017094017094,
"grad_norm": 1.243442983004785,
"learning_rate": 1.7021276595744682e-05,
"loss": 1.2952,
"step": 40
},
{
"epoch": 0.19230769230769232,
"grad_norm": 1.398459861930405,
"learning_rate": 1.914893617021277e-05,
"loss": 1.2762,
"step": 45
},
{
"epoch": 0.21367521367521367,
"grad_norm": 1.871011686158811,
"learning_rate": 1.999749429505675e-05,
"loss": 1.2997,
"step": 50
},
{
"epoch": 0.23504273504273504,
"grad_norm": 1.2331867317142813,
"learning_rate": 1.9982186200932964e-05,
"loss": 1.2568,
"step": 55
},
{
"epoch": 0.2564102564102564,
"grad_norm": 1.1946705653350014,
"learning_rate": 1.9952983353325358e-05,
"loss": 1.2763,
"step": 60
},
{
"epoch": 0.2777777777777778,
"grad_norm": 1.1214723834130367,
"learning_rate": 1.990992640128218e-05,
"loss": 1.2938,
"step": 65
},
{
"epoch": 0.29914529914529914,
"grad_norm": 1.119663106979562,
"learning_rate": 1.9853075278140913e-05,
"loss": 1.2598,
"step": 70
},
{
"epoch": 0.32051282051282054,
"grad_norm": 1.1303932474940224,
"learning_rate": 1.9782509118103773e-05,
"loss": 1.2489,
"step": 75
},
{
"epoch": 0.3418803418803419,
"grad_norm": 1.2099240945757408,
"learning_rate": 1.9698326146086446e-05,
"loss": 1.2813,
"step": 80
},
{
"epoch": 0.36324786324786323,
"grad_norm": 1.108377660801764,
"learning_rate": 1.9600643540993453e-05,
"loss": 1.2296,
"step": 85
},
{
"epoch": 0.38461538461538464,
"grad_norm": 1.1652590169175916,
"learning_rate": 1.9489597272610377e-05,
"loss": 1.2367,
"step": 90
},
{
"epoch": 0.405982905982906,
"grad_norm": 1.144744441272463,
"learning_rate": 1.936534191234006e-05,
"loss": 1.2497,
"step": 95
},
{
"epoch": 0.42735042735042733,
"grad_norm": 1.0797546591912566,
"learning_rate": 1.922805041804617e-05,
"loss": 1.2157,
"step": 100
},
{
"epoch": 0.44871794871794873,
"grad_norm": 1.1997371054541615,
"learning_rate": 1.907791389330363e-05,
"loss": 1.2393,
"step": 105
},
{
"epoch": 0.4700854700854701,
"grad_norm": 1.234499931127894,
"learning_rate": 1.8915141321391083e-05,
"loss": 1.268,
"step": 110
},
{
"epoch": 0.49145299145299143,
"grad_norm": 1.2719307847654406,
"learning_rate": 1.873995927439555e-05,
"loss": 1.2318,
"step": 115
},
{
"epoch": 0.5128205128205128,
"grad_norm": 1.0803159349159561,
"learning_rate": 1.855261159783432e-05,
"loss": 1.2422,
"step": 120
},
{
"epoch": 0.5341880341880342,
"grad_norm": 1.1126726338850874,
"learning_rate": 1.8353359071232954e-05,
"loss": 1.2341,
"step": 125
},
{
"epoch": 0.5555555555555556,
"grad_norm": 1.141289352623837,
"learning_rate": 1.8142479045131956e-05,
"loss": 1.2172,
"step": 130
},
{
"epoch": 0.5769230769230769,
"grad_norm": 1.0891200836049277,
"learning_rate": 1.7920265055027285e-05,
"loss": 1.2147,
"step": 135
},
{
"epoch": 0.5982905982905983,
"grad_norm": 0.9983723250381306,
"learning_rate": 1.76870264127822e-05,
"loss": 1.2087,
"step": 140
},
{
"epoch": 0.6196581196581197,
"grad_norm": 1.0642854505735857,
"learning_rate": 1.7443087776079068e-05,
"loss": 1.1872,
"step": 145
},
{
"epoch": 0.6410256410256411,
"grad_norm": 1.0890040938005288,
"learning_rate": 1.7188788696510477e-05,
"loss": 1.2431,
"step": 150
},
{
"epoch": 0.6623931623931624,
"grad_norm": 1.0196805310002042,
"learning_rate": 1.6924483146938756e-05,
"loss": 1.2133,
"step": 155
},
{
"epoch": 0.6837606837606838,
"grad_norm": 1.0422167588733457,
"learning_rate": 1.665053902878167e-05,
"loss": 1.2275,
"step": 160
},
{
"epoch": 0.7051282051282052,
"grad_norm": 1.0099548152705635,
"learning_rate": 1.6367337659910223e-05,
"loss": 1.1997,
"step": 165
},
{
"epoch": 0.7264957264957265,
"grad_norm": 1.034450507226083,
"learning_rate": 1.607527324387137e-05,
"loss": 1.1952,
"step": 170
},
{
"epoch": 0.7478632478632479,
"grad_norm": 1.01064689098683,
"learning_rate": 1.5774752321174428e-05,
"loss": 1.2142,
"step": 175
},
{
"epoch": 0.7692307692307693,
"grad_norm": 1.2440710808413185,
"learning_rate": 1.5466193203405017e-05,
"loss": 1.2272,
"step": 180
},
{
"epoch": 0.7905982905982906,
"grad_norm": 0.9538688514209636,
"learning_rate": 1.5150025390954153e-05,
"loss": 1.1797,
"step": 185
},
{
"epoch": 0.811965811965812,
"grad_norm": 1.0457627221644799,
"learning_rate": 1.4826688975173085e-05,
"loss": 1.1834,
"step": 190
},
{
"epoch": 0.8333333333333334,
"grad_norm": 1.0494277738904705,
"learning_rate": 1.4496634025785938e-05,
"loss": 1.2098,
"step": 195
},
{
"epoch": 0.8547008547008547,
"grad_norm": 0.979634991944023,
"learning_rate": 1.4160319964412943e-05,
"loss": 1.1936,
"step": 200
},
{
"epoch": 0.8760683760683761,
"grad_norm": 1.0707731906559956,
"learning_rate": 1.3818214925076226e-05,
"loss": 1.1934,
"step": 205
},
{
"epoch": 0.8974358974358975,
"grad_norm": 0.9902950125875686,
"learning_rate": 1.3470795102578358e-05,
"loss": 1.1875,
"step": 210
},
{
"epoch": 0.9188034188034188,
"grad_norm": 1.1906219730782999,
"learning_rate": 1.3118544089660635e-05,
"loss": 1.1828,
"step": 215
},
{
"epoch": 0.9401709401709402,
"grad_norm": 1.029497385097088,
"learning_rate": 1.2761952203863759e-05,
"loss": 1.2032,
"step": 220
},
{
"epoch": 0.9615384615384616,
"grad_norm": 1.0145349544318898,
"learning_rate": 1.2401515805027924e-05,
"loss": 1.1918,
"step": 225
},
{
"epoch": 0.9829059829059829,
"grad_norm": 0.9338647888184574,
"learning_rate": 1.2037736604382279e-05,
"loss": 1.1667,
"step": 230
},
{
"epoch": 1.0,
"eval_loss": 1.1897046566009521,
"eval_runtime": 4.2537,
"eval_samples_per_second": 34.323,
"eval_steps_per_second": 0.705,
"step": 234
},
{
"epoch": 1.0042735042735043,
"grad_norm": 2.061617781988495,
"learning_rate": 1.1671120966185486e-05,
"loss": 1.1272,
"step": 235
},
{
"epoch": 1.0256410256410255,
"grad_norm": 1.5757999937786025,
"learning_rate": 1.1302179202889505e-05,
"loss": 0.8684,
"step": 240
},
{
"epoch": 1.047008547008547,
"grad_norm": 1.162411965496565,
"learning_rate": 1.0931424864807624e-05,
"loss": 0.8433,
"step": 245
},
{
"epoch": 1.0683760683760684,
"grad_norm": 1.083844459735895,
"learning_rate": 1.0559374025275597e-05,
"loss": 0.8588,
"step": 250
},
{
"epoch": 1.0897435897435896,
"grad_norm": 1.0166749425497479,
"learning_rate": 1.0186544562300766e-05,
"loss": 0.8936,
"step": 255
},
{
"epoch": 1.1111111111111112,
"grad_norm": 1.0711811120340167,
"learning_rate": 9.813455437699238e-06,
"loss": 0.8633,
"step": 260
},
{
"epoch": 1.1324786324786325,
"grad_norm": 1.0038627368222364,
"learning_rate": 9.440625974724408e-06,
"loss": 0.8821,
"step": 265
},
{
"epoch": 1.1538461538461537,
"grad_norm": 1.0431997146297058,
"learning_rate": 9.068575135192377e-06,
"loss": 0.8856,
"step": 270
},
{
"epoch": 1.1752136752136753,
"grad_norm": 1.4331559261347666,
"learning_rate": 8.697820797110499e-06,
"loss": 0.8645,
"step": 275
},
{
"epoch": 1.1965811965811965,
"grad_norm": 1.0197402946112883,
"learning_rate": 8.328879033814516e-06,
"loss": 0.8512,
"step": 280
},
{
"epoch": 1.217948717948718,
"grad_norm": 1.01821032251223,
"learning_rate": 7.962263395617724e-06,
"loss": 0.8661,
"step": 285
},
{
"epoch": 1.2393162393162394,
"grad_norm": 1.0267748605334936,
"learning_rate": 7.598484194972076e-06,
"loss": 0.8601,
"step": 290
},
{
"epoch": 1.2606837606837606,
"grad_norm": 1.0208240145129162,
"learning_rate": 7.238047796136247e-06,
"loss": 0.8627,
"step": 295
},
{
"epoch": 1.282051282051282,
"grad_norm": 1.003007647188531,
"learning_rate": 6.881455910339369e-06,
"loss": 0.8463,
"step": 300
},
{
"epoch": 1.3034188034188035,
"grad_norm": 1.0588099942878915,
"learning_rate": 6.529204897421644e-06,
"loss": 0.8591,
"step": 305
},
{
"epoch": 1.3247863247863247,
"grad_norm": 0.9819416599015215,
"learning_rate": 6.181785074923778e-06,
"loss": 0.863,
"step": 310
},
{
"epoch": 1.3461538461538463,
"grad_norm": 0.9892062975951394,
"learning_rate": 5.839680035587061e-06,
"loss": 0.8594,
"step": 315
},
{
"epoch": 1.3675213675213675,
"grad_norm": 0.9795643152120956,
"learning_rate": 5.503365974214059e-06,
"loss": 0.8613,
"step": 320
},
{
"epoch": 1.3888888888888888,
"grad_norm": 0.9542734758696676,
"learning_rate": 5.173311024826916e-06,
"loss": 0.866,
"step": 325
},
{
"epoch": 1.4102564102564101,
"grad_norm": 0.9352942170714407,
"learning_rate": 4.849974609045849e-06,
"loss": 0.8469,
"step": 330
},
{
"epoch": 1.4316239316239316,
"grad_norm": 0.943859757278146,
"learning_rate": 4.533806796594989e-06,
"loss": 0.8729,
"step": 335
},
{
"epoch": 1.452991452991453,
"grad_norm": 1.058117869970705,
"learning_rate": 4.2252476788255735e-06,
"loss": 0.8614,
"step": 340
},
{
"epoch": 1.4743589743589745,
"grad_norm": 1.007136340214763,
"learning_rate": 3.924726756128632e-06,
"loss": 0.8314,
"step": 345
},
{
"epoch": 1.4957264957264957,
"grad_norm": 1.0001072453743785,
"learning_rate": 3.6326623400897797e-06,
"loss": 0.8263,
"step": 350
},
{
"epoch": 1.517094017094017,
"grad_norm": 11.67014141174618,
"learning_rate": 3.3494609712183323e-06,
"loss": 0.9014,
"step": 355
},
{
"epoch": 1.5384615384615383,
"grad_norm": 0.9396806102918359,
"learning_rate": 3.0755168530612444e-06,
"loss": 0.8294,
"step": 360
},
{
"epoch": 1.5598290598290598,
"grad_norm": 0.9899965091834676,
"learning_rate": 2.8112113034895273e-06,
"loss": 0.8451,
"step": 365
},
{
"epoch": 1.5811965811965814,
"grad_norm": 1.0046619245072979,
"learning_rate": 2.5569122239209366e-06,
"loss": 0.8635,
"step": 370
},
{
"epoch": 1.6025641025641026,
"grad_norm": 0.9398590773976044,
"learning_rate": 2.312973587217798e-06,
"loss": 0.8468,
"step": 375
},
{
"epoch": 1.623931623931624,
"grad_norm": 0.9897283589814032,
"learning_rate": 2.079734944972717e-06,
"loss": 0.8615,
"step": 380
},
{
"epoch": 1.6452991452991452,
"grad_norm": 0.9311555025619238,
"learning_rate": 1.8575209548680472e-06,
"loss": 0.8616,
"step": 385
},
{
"epoch": 1.6666666666666665,
"grad_norm": 0.9902450799068546,
"learning_rate": 1.646640928767047e-06,
"loss": 0.8401,
"step": 390
},
{
"epoch": 1.688034188034188,
"grad_norm": 0.9397904063208168,
"learning_rate": 1.447388402165686e-06,
"loss": 0.8287,
"step": 395
},
{
"epoch": 1.7094017094017095,
"grad_norm": 0.9334825682417511,
"learning_rate": 1.2600407256044544e-06,
"loss": 0.8492,
"step": 400
},
{
"epoch": 1.7307692307692308,
"grad_norm": 0.9901247743535753,
"learning_rate": 1.084858678608922e-06,
"loss": 0.8695,
"step": 405
},
{
"epoch": 1.7521367521367521,
"grad_norm": 0.9223418850643341,
"learning_rate": 9.220861066963715e-07,
"loss": 0.8476,
"step": 410
},
{
"epoch": 1.7735042735042734,
"grad_norm": 0.9421948230776865,
"learning_rate": 7.719495819538325e-07,
"loss": 0.8412,
"step": 415
},
{
"epoch": 1.7948717948717947,
"grad_norm": 0.9548113796103942,
"learning_rate": 6.346580876599395e-07,
"loss": 0.8633,
"step": 420
},
{
"epoch": 1.8162393162393162,
"grad_norm": 0.9286412348527092,
"learning_rate": 5.104027273896239e-07,
"loss": 0.8659,
"step": 425
},
{
"epoch": 1.8376068376068377,
"grad_norm": 0.9726444202093633,
"learning_rate": 3.9935645900654906e-07,
"loss": 0.8533,
"step": 430
},
{
"epoch": 1.858974358974359,
"grad_norm": 0.9864530246870579,
"learning_rate": 3.016738539135566e-07,
"loss": 0.8377,
"step": 435
},
{
"epoch": 1.8803418803418803,
"grad_norm": 0.9665706648338857,
"learning_rate": 2.1749088189622848e-07,
"loss": 0.8411,
"step": 440
},
{
"epoch": 1.9017094017094016,
"grad_norm": 0.8848822721798258,
"learning_rate": 1.4692472185908635e-07,
"loss": 0.8615,
"step": 445
},
{
"epoch": 1.9230769230769231,
"grad_norm": 0.9643097064713656,
"learning_rate": 9.00735987178214e-08,
"loss": 0.8367,
"step": 450
},
{
"epoch": 1.9444444444444444,
"grad_norm": 0.9452651983857008,
"learning_rate": 4.701664667464245e-08,
"loss": 0.8577,
"step": 455
},
{
"epoch": 1.965811965811966,
"grad_norm": 0.9405976480323978,
"learning_rate": 1.781379906703573e-08,
"loss": 0.8518,
"step": 460
},
{
"epoch": 1.9871794871794872,
"grad_norm": 0.9339891238206331,
"learning_rate": 2.5057049432519744e-09,
"loss": 0.8465,
"step": 465
},
{
"epoch": 2.0,
"eval_loss": 1.2036917209625244,
"eval_runtime": 4.1091,
"eval_samples_per_second": 35.531,
"eval_steps_per_second": 0.73,
"step": 468
},
{
"epoch": 2.0,
"step": 468,
"total_flos": 97989678858240.0,
"train_loss": 1.058635287050508,
"train_runtime": 3412.8477,
"train_samples_per_second": 8.744,
"train_steps_per_second": 0.137
}
],
"logging_steps": 5,
"max_steps": 468,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 97989678858240.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}