SG_X9e / trainer_state.json
tzchen07's picture
Upload folder using huggingface_hub
1efb839 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 500,
"global_step": 498,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02009545340366742,
"grad_norm": 101.4629135131836,
"learning_rate": 4.0000000000000003e-07,
"loss": 2.9256,
"step": 5
},
{
"epoch": 0.04019090680733484,
"grad_norm": 83.51904296875,
"learning_rate": 9.000000000000001e-07,
"loss": 2.7459,
"step": 10
},
{
"epoch": 0.06028636021100226,
"grad_norm": 25.10388946533203,
"learning_rate": 1.4000000000000001e-06,
"loss": 1.637,
"step": 15
},
{
"epoch": 0.08038181361466969,
"grad_norm": 13.024300575256348,
"learning_rate": 1.9000000000000002e-06,
"loss": 1.1459,
"step": 20
},
{
"epoch": 0.1004772670183371,
"grad_norm": 8.315956115722656,
"learning_rate": 2.4000000000000003e-06,
"loss": 0.7456,
"step": 25
},
{
"epoch": 0.12057272042200452,
"grad_norm": 8.930346488952637,
"learning_rate": 2.9e-06,
"loss": 0.5717,
"step": 30
},
{
"epoch": 0.14066817382567195,
"grad_norm": 7.356456756591797,
"learning_rate": 3.4000000000000005e-06,
"loss": 0.414,
"step": 35
},
{
"epoch": 0.16076362722933937,
"grad_norm": 5.648008346557617,
"learning_rate": 3.900000000000001e-06,
"loss": 0.2577,
"step": 40
},
{
"epoch": 0.1808590806330068,
"grad_norm": 6.329988956451416,
"learning_rate": 4.4e-06,
"loss": 0.2394,
"step": 45
},
{
"epoch": 0.2009545340366742,
"grad_norm": 5.1738080978393555,
"learning_rate": 4.9000000000000005e-06,
"loss": 0.1848,
"step": 50
},
{
"epoch": 0.22104998744034163,
"grad_norm": 4.86478853225708,
"learning_rate": 4.999016565957633e-06,
"loss": 0.2195,
"step": 55
},
{
"epoch": 0.24114544084400905,
"grad_norm": 4.442976474761963,
"learning_rate": 4.995022691166621e-06,
"loss": 0.1582,
"step": 60
},
{
"epoch": 0.26124089424767644,
"grad_norm": 3.704345941543579,
"learning_rate": 4.987961816680493e-06,
"loss": 0.183,
"step": 65
},
{
"epoch": 0.2813363476513439,
"grad_norm": 3.772160768508911,
"learning_rate": 4.977842622059546e-06,
"loss": 0.164,
"step": 70
},
{
"epoch": 0.30143180105501133,
"grad_norm": 3.2532081604003906,
"learning_rate": 4.96467754629559e-06,
"loss": 0.1781,
"step": 75
},
{
"epoch": 0.32152725445867875,
"grad_norm": 2.893615484237671,
"learning_rate": 4.948482772521346e-06,
"loss": 0.1288,
"step": 80
},
{
"epoch": 0.34162270786234616,
"grad_norm": 4.654979705810547,
"learning_rate": 4.929278208117378e-06,
"loss": 0.1444,
"step": 85
},
{
"epoch": 0.3617181612660136,
"grad_norm": 2.8989882469177246,
"learning_rate": 4.907087460240999e-06,
"loss": 0.1151,
"step": 90
},
{
"epoch": 0.381813614669681,
"grad_norm": 3.7547988891601562,
"learning_rate": 4.881937806807241e-06,
"loss": 0.1197,
"step": 95
},
{
"epoch": 0.4019090680733484,
"grad_norm": 2.273831605911255,
"learning_rate": 4.8538601629575525e-06,
"loss": 0.0966,
"step": 100
},
{
"epoch": 0.42200452147701584,
"grad_norm": 2.4642996788024902,
"learning_rate": 4.822889043057446e-06,
"loss": 0.1088,
"step": 105
},
{
"epoch": 0.44209997488068326,
"grad_norm": 3.29301381111145,
"learning_rate": 4.789062518269812e-06,
"loss": 0.1163,
"step": 110
},
{
"epoch": 0.4621954282843507,
"grad_norm": 2.45603084564209,
"learning_rate": 4.752422169756048e-06,
"loss": 0.1151,
"step": 115
},
{
"epoch": 0.4822908816880181,
"grad_norm": 3.199894666671753,
"learning_rate": 4.713013037562531e-06,
"loss": 0.098,
"step": 120
},
{
"epoch": 0.5023863350916855,
"grad_norm": 1.7128061056137085,
"learning_rate": 4.670883565255264e-06,
"loss": 0.0968,
"step": 125
},
{
"epoch": 0.5224817884953529,
"grad_norm": 2.645235776901245,
"learning_rate": 4.6260855403707625e-06,
"loss": 0.1068,
"step": 130
},
{
"epoch": 0.5425772418990203,
"grad_norm": 2.3140530586242676,
"learning_rate": 4.578674030756364e-06,
"loss": 0.0914,
"step": 135
},
{
"epoch": 0.5626726953026878,
"grad_norm": 1.8588067293167114,
"learning_rate": 4.528707316878233e-06,
"loss": 0.0995,
"step": 140
},
{
"epoch": 0.5827681487063552,
"grad_norm": 1.9172967672348022,
"learning_rate": 4.476246820180259e-06,
"loss": 0.08,
"step": 145
},
{
"epoch": 0.6028636021100227,
"grad_norm": 2.9082584381103516,
"learning_rate": 4.421357027581921e-06,
"loss": 0.1066,
"step": 150
},
{
"epoch": 0.62295905551369,
"grad_norm": 3.6944031715393066,
"learning_rate": 4.364105412207914e-06,
"loss": 0.1124,
"step": 155
},
{
"epoch": 0.6430545089173575,
"grad_norm": 1.5622600317001343,
"learning_rate": 4.304562350447008e-06,
"loss": 0.0856,
"step": 160
},
{
"epoch": 0.6631499623210249,
"grad_norm": 2.388239860534668,
"learning_rate": 4.242801035442059e-06,
"loss": 0.0766,
"step": 165
},
{
"epoch": 0.6832454157246923,
"grad_norm": 1.7182718515396118,
"learning_rate": 4.178897387117547e-06,
"loss": 0.104,
"step": 170
},
{
"epoch": 0.7033408691283597,
"grad_norm": 2.2367119789123535,
"learning_rate": 4.11292995885522e-06,
"loss": 0.0737,
"step": 175
},
{
"epoch": 0.7234363225320272,
"grad_norm": 2.007200241088867,
"learning_rate": 4.044979840932567e-06,
"loss": 0.0893,
"step": 180
},
{
"epoch": 0.7435317759356945,
"grad_norm": 2.6910905838012695,
"learning_rate": 3.975130560842821e-06,
"loss": 0.0944,
"step": 185
},
{
"epoch": 0.763627229339362,
"grad_norm": 2.042320489883423,
"learning_rate": 3.9034679806190204e-06,
"loss": 0.0843,
"step": 190
},
{
"epoch": 0.7837226827430294,
"grad_norm": 2.700977087020874,
"learning_rate": 3.830080191288342e-06,
"loss": 0.0669,
"step": 195
},
{
"epoch": 0.8038181361466968,
"grad_norm": 3.0307390689849854,
"learning_rate": 3.755057404586455e-06,
"loss": 0.0955,
"step": 200
},
{
"epoch": 0.8239135895503642,
"grad_norm": 1.11714506149292,
"learning_rate": 4.0000000000000003e-07,
"loss": 0.0956,
"step": 205
},
{
"epoch": 0.8440090429540317,
"grad_norm": 1.5246130228042603,
"learning_rate": 9.000000000000001e-07,
"loss": 0.0755,
"step": 210
},
{
"epoch": 0.864104496357699,
"grad_norm": 2.0117733478546143,
"learning_rate": 1.4000000000000001e-06,
"loss": 0.0894,
"step": 215
},
{
"epoch": 0.8841999497613665,
"grad_norm": 2.038092613220215,
"learning_rate": 1.9000000000000002e-06,
"loss": 0.074,
"step": 220
},
{
"epoch": 0.9042954031650339,
"grad_norm": 1.607172966003418,
"learning_rate": 2.4000000000000003e-06,
"loss": 0.0612,
"step": 225
},
{
"epoch": 0.9243908565687013,
"grad_norm": 1.643001914024353,
"learning_rate": 2.9e-06,
"loss": 0.0967,
"step": 230
},
{
"epoch": 0.9444863099723687,
"grad_norm": 1.5271589756011963,
"learning_rate": 3.4000000000000005e-06,
"loss": 0.1008,
"step": 235
},
{
"epoch": 0.9645817633760362,
"grad_norm": 2.2744393348693848,
"learning_rate": 3.900000000000001e-06,
"loss": 0.0846,
"step": 240
},
{
"epoch": 0.9846772167797035,
"grad_norm": 1.2268872261047363,
"learning_rate": 4.4e-06,
"loss": 0.0889,
"step": 245
},
{
"epoch": 1.0040190906807336,
"grad_norm": 1.971510648727417,
"learning_rate": 4.9000000000000005e-06,
"loss": 0.1021,
"step": 250
},
{
"epoch": 1.0241145440844008,
"grad_norm": 0.6695238947868347,
"learning_rate": 4.999016565957633e-06,
"loss": 0.057,
"step": 255
},
{
"epoch": 1.0442099974880683,
"grad_norm": 3.379134178161621,
"learning_rate": 4.995022691166621e-06,
"loss": 0.0695,
"step": 260
},
{
"epoch": 1.0643054508917358,
"grad_norm": 2.573274850845337,
"learning_rate": 4.987961816680493e-06,
"loss": 0.0713,
"step": 265
},
{
"epoch": 1.0844009042954033,
"grad_norm": 1.3487026691436768,
"learning_rate": 4.977842622059546e-06,
"loss": 0.0704,
"step": 270
},
{
"epoch": 1.1044963576990705,
"grad_norm": 1.7525826692581177,
"learning_rate": 4.96467754629559e-06,
"loss": 0.0615,
"step": 275
},
{
"epoch": 1.124591811102738,
"grad_norm": 1.1195745468139648,
"learning_rate": 4.948482772521346e-06,
"loss": 0.0616,
"step": 280
},
{
"epoch": 1.1446872645064055,
"grad_norm": 2.203016996383667,
"learning_rate": 4.929278208117378e-06,
"loss": 0.0627,
"step": 285
},
{
"epoch": 1.164782717910073,
"grad_norm": 3.2196788787841797,
"learning_rate": 4.907087460240999e-06,
"loss": 0.0707,
"step": 290
},
{
"epoch": 1.1848781713137402,
"grad_norm": 2.4914467334747314,
"learning_rate": 4.881937806807241e-06,
"loss": 0.0758,
"step": 295
},
{
"epoch": 1.2049736247174077,
"grad_norm": 2.223809242248535,
"learning_rate": 4.8538601629575525e-06,
"loss": 0.0698,
"step": 300
},
{
"epoch": 1.2250690781210751,
"grad_norm": 1.5360513925552368,
"learning_rate": 4.822889043057446e-06,
"loss": 0.0593,
"step": 305
},
{
"epoch": 1.2451645315247426,
"grad_norm": 1.8444727659225464,
"learning_rate": 4.789062518269812e-06,
"loss": 0.0635,
"step": 310
},
{
"epoch": 1.2652599849284099,
"grad_norm": 1.5122318267822266,
"learning_rate": 4.752422169756048e-06,
"loss": 0.0737,
"step": 315
},
{
"epoch": 1.2853554383320773,
"grad_norm": 2.0612282752990723,
"learning_rate": 4.713013037562531e-06,
"loss": 0.065,
"step": 320
},
{
"epoch": 1.3054508917357448,
"grad_norm": 1.4917356967926025,
"learning_rate": 4.670883565255264e-06,
"loss": 0.0563,
"step": 325
},
{
"epoch": 1.3255463451394123,
"grad_norm": 1.861807942390442,
"learning_rate": 4.6260855403707625e-06,
"loss": 0.0654,
"step": 330
},
{
"epoch": 1.3456417985430797,
"grad_norm": 2.3603355884552,
"learning_rate": 4.578674030756364e-06,
"loss": 0.0616,
"step": 335
},
{
"epoch": 1.365737251946747,
"grad_norm": 1.4312632083892822,
"learning_rate": 4.528707316878233e-06,
"loss": 0.0608,
"step": 340
},
{
"epoch": 1.3858327053504145,
"grad_norm": 3.3819150924682617,
"learning_rate": 4.476246820180259e-06,
"loss": 0.0573,
"step": 345
},
{
"epoch": 1.405928158754082,
"grad_norm": 2.076028347015381,
"learning_rate": 4.421357027581921e-06,
"loss": 0.0648,
"step": 350
},
{
"epoch": 1.4260236121577492,
"grad_norm": 2.0433411598205566,
"learning_rate": 4.364105412207914e-06,
"loss": 0.0679,
"step": 355
},
{
"epoch": 1.4461190655614167,
"grad_norm": 1.695204496383667,
"learning_rate": 4.304562350447008e-06,
"loss": 0.0655,
"step": 360
},
{
"epoch": 1.4662145189650841,
"grad_norm": 0.7300482988357544,
"learning_rate": 4.242801035442059e-06,
"loss": 0.0662,
"step": 365
},
{
"epoch": 1.4863099723687516,
"grad_norm": 1.8220871686935425,
"learning_rate": 4.178897387117547e-06,
"loss": 0.0659,
"step": 370
},
{
"epoch": 1.506405425772419,
"grad_norm": 1.4738329648971558,
"learning_rate": 4.11292995885522e-06,
"loss": 0.0605,
"step": 375
},
{
"epoch": 1.5265008791760866,
"grad_norm": 1.562551736831665,
"learning_rate": 4.044979840932567e-06,
"loss": 0.0741,
"step": 380
},
{
"epoch": 1.5465963325797538,
"grad_norm": 1.5520535707473755,
"learning_rate": 3.975130560842821e-06,
"loss": 0.058,
"step": 385
},
{
"epoch": 1.5666917859834213,
"grad_norm": 1.29172682762146,
"learning_rate": 3.9034679806190204e-06,
"loss": 0.0584,
"step": 390
},
{
"epoch": 1.5867872393870885,
"grad_norm": 1.9488056898117065,
"learning_rate": 3.830080191288342e-06,
"loss": 0.0582,
"step": 395
},
{
"epoch": 1.606882692790756,
"grad_norm": 1.6518131494522095,
"learning_rate": 3.755057404586455e-06,
"loss": 0.0634,
"step": 400
},
{
"epoch": 1.6269781461944235,
"grad_norm": 1.5398550033569336,
"learning_rate": 3.6784918420649952e-06,
"loss": 0.0525,
"step": 405
},
{
"epoch": 1.647073599598091,
"grad_norm": 1.6156771183013916,
"learning_rate": 3.600477621728473e-06,
"loss": 0.0645,
"step": 410
},
{
"epoch": 1.6671690530017584,
"grad_norm": 1.564670205116272,
"learning_rate": 3.521110642339991e-06,
"loss": 0.0526,
"step": 415
},
{
"epoch": 1.687264506405426,
"grad_norm": 1.2277319431304932,
"learning_rate": 3.4404884655379433e-06,
"loss": 0.0616,
"step": 420
},
{
"epoch": 1.7073599598090932,
"grad_norm": 1.1757029294967651,
"learning_rate": 3.358710195908653e-06,
"loss": 0.0537,
"step": 425
},
{
"epoch": 1.7274554132127606,
"grad_norm": 1.0405977964401245,
"learning_rate": 3.27587635916233e-06,
"loss": 0.0619,
"step": 430
},
{
"epoch": 1.747550866616428,
"grad_norm": 1.5975450277328491,
"learning_rate": 3.1920887785621233e-06,
"loss": 0.0603,
"step": 435
},
{
"epoch": 1.7676463200200954,
"grad_norm": 1.7237313985824585,
"learning_rate": 3.10745044975816e-06,
"loss": 0.0594,
"step": 440
},
{
"epoch": 1.7877417734237628,
"grad_norm": 1.7574973106384277,
"learning_rate": 3.022065414180425e-06,
"loss": 0.0608,
"step": 445
},
{
"epoch": 1.8078372268274303,
"grad_norm": 1.450028419494629,
"learning_rate": 2.9360386311461276e-06,
"loss": 0.0505,
"step": 450
},
{
"epoch": 1.8279326802310978,
"grad_norm": 1.0331708192825317,
"learning_rate": 2.849475848838749e-06,
"loss": 0.0497,
"step": 455
},
{
"epoch": 1.8480281336347653,
"grad_norm": 1.5370794534683228,
"learning_rate": 2.762483474317387e-06,
"loss": 0.0625,
"step": 460
},
{
"epoch": 1.8681235870384325,
"grad_norm": 2.073357582092285,
"learning_rate": 2.6751684427161684e-06,
"loss": 0.0448,
"step": 465
},
{
"epoch": 1.8882190404421,
"grad_norm": 1.4379805326461792,
"learning_rate": 2.587638085794541e-06,
"loss": 0.0588,
"step": 470
},
{
"epoch": 1.9083144938457672,
"grad_norm": 1.8600538969039917,
"learning_rate": 2.5e-06,
"loss": 0.0511,
"step": 475
},
{
"epoch": 1.9284099472494347,
"grad_norm": 1.2249418497085571,
"learning_rate": 2.41236191420546e-06,
"loss": 0.0497,
"step": 480
},
{
"epoch": 1.9485054006531022,
"grad_norm": 0.8812041282653809,
"learning_rate": 2.3248315572838316e-06,
"loss": 0.0498,
"step": 485
},
{
"epoch": 1.9686008540567697,
"grad_norm": 0.8966412544250488,
"learning_rate": 2.237516525682614e-06,
"loss": 0.0459,
"step": 490
},
{
"epoch": 1.9886963074604371,
"grad_norm": 1.238738775253296,
"learning_rate": 2.1505241511612522e-06,
"loss": 0.052,
"step": 495
},
{
"epoch": 2.0,
"step": 498,
"total_flos": 1.28494219771102e+18,
"train_loss": 0.03900693407858232,
"train_runtime": 6158.7829,
"train_samples_per_second": 5.17,
"train_steps_per_second": 0.081
}
],
"logging_steps": 5,
"max_steps": 498,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 200,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.28494219771102e+18,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}