PromptCoT / coding-0.2 /joint /checkpoint-689 /trainer_state.json
PanzerBread's picture
Upload folder using huggingface_hub
3cb4965 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 689,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01451378809869376,
"grad_norm": 2.8285412788391113,
"learning_rate": 1.8e-05,
"loss": 1.1057,
"step": 10
},
{
"epoch": 0.02902757619738752,
"grad_norm": 1.1285754442214966,
"learning_rate": 3.8e-05,
"loss": 0.9694,
"step": 20
},
{
"epoch": 0.04354136429608128,
"grad_norm": 0.8574178218841553,
"learning_rate": 5.8e-05,
"loss": 0.7341,
"step": 30
},
{
"epoch": 0.05805515239477504,
"grad_norm": 0.53108811378479,
"learning_rate": 7.800000000000001e-05,
"loss": 0.6017,
"step": 40
},
{
"epoch": 0.07256894049346879,
"grad_norm": 0.40395280718803406,
"learning_rate": 9.8e-05,
"loss": 0.534,
"step": 50
},
{
"epoch": 0.08708272859216255,
"grad_norm": 0.4184938073158264,
"learning_rate": 0.000118,
"loss": 0.5018,
"step": 60
},
{
"epoch": 0.10159651669085631,
"grad_norm": 0.3326551616191864,
"learning_rate": 0.000138,
"loss": 0.4807,
"step": 70
},
{
"epoch": 0.11611030478955008,
"grad_norm": 0.3530741333961487,
"learning_rate": 0.00015800000000000002,
"loss": 0.462,
"step": 80
},
{
"epoch": 0.13062409288824384,
"grad_norm": 0.3607262670993805,
"learning_rate": 0.00017800000000000002,
"loss": 0.4492,
"step": 90
},
{
"epoch": 0.14513788098693758,
"grad_norm": 0.37283945083618164,
"learning_rate": 0.00019800000000000002,
"loss": 0.4436,
"step": 100
},
{
"epoch": 0.15965166908563136,
"grad_norm": 0.3210872709751129,
"learning_rate": 0.00019694397283531408,
"loss": 0.4338,
"step": 110
},
{
"epoch": 0.1741654571843251,
"grad_norm": 0.2939835488796234,
"learning_rate": 0.00019354838709677422,
"loss": 0.4279,
"step": 120
},
{
"epoch": 0.18867924528301888,
"grad_norm": 0.3203432857990265,
"learning_rate": 0.0001901528013582343,
"loss": 0.4177,
"step": 130
},
{
"epoch": 0.20319303338171263,
"grad_norm": 0.2840735614299774,
"learning_rate": 0.00018675721561969442,
"loss": 0.4157,
"step": 140
},
{
"epoch": 0.21770682148040638,
"grad_norm": 0.29428958892822266,
"learning_rate": 0.0001833616298811545,
"loss": 0.4133,
"step": 150
},
{
"epoch": 0.23222060957910015,
"grad_norm": 0.2704876661300659,
"learning_rate": 0.00017996604414261463,
"loss": 0.4095,
"step": 160
},
{
"epoch": 0.2467343976777939,
"grad_norm": 0.29016420245170593,
"learning_rate": 0.0001765704584040747,
"loss": 0.4036,
"step": 170
},
{
"epoch": 0.2612481857764877,
"grad_norm": 0.26832008361816406,
"learning_rate": 0.0001731748726655348,
"loss": 0.4057,
"step": 180
},
{
"epoch": 0.2757619738751814,
"grad_norm": 0.280130535364151,
"learning_rate": 0.00016977928692699492,
"loss": 0.3996,
"step": 190
},
{
"epoch": 0.29027576197387517,
"grad_norm": 0.2216828167438507,
"learning_rate": 0.00016638370118845502,
"loss": 0.3999,
"step": 200
},
{
"epoch": 0.3047895500725689,
"grad_norm": 0.2544555962085724,
"learning_rate": 0.00016298811544991512,
"loss": 0.394,
"step": 210
},
{
"epoch": 0.3193033381712627,
"grad_norm": 0.26161113381385803,
"learning_rate": 0.00015959252971137523,
"loss": 0.3918,
"step": 220
},
{
"epoch": 0.33381712626995647,
"grad_norm": 0.22447264194488525,
"learning_rate": 0.00015619694397283533,
"loss": 0.395,
"step": 230
},
{
"epoch": 0.3483309143686502,
"grad_norm": 0.24482668936252594,
"learning_rate": 0.00015280135823429543,
"loss": 0.3842,
"step": 240
},
{
"epoch": 0.36284470246734396,
"grad_norm": 0.2375396192073822,
"learning_rate": 0.00014940577249575554,
"loss": 0.3906,
"step": 250
},
{
"epoch": 0.37735849056603776,
"grad_norm": 0.24287049472332,
"learning_rate": 0.00014601018675721562,
"loss": 0.3838,
"step": 260
},
{
"epoch": 0.3918722786647315,
"grad_norm": 0.24098220467567444,
"learning_rate": 0.00014261460101867572,
"loss": 0.3816,
"step": 270
},
{
"epoch": 0.40638606676342526,
"grad_norm": 0.23136872053146362,
"learning_rate": 0.00013921901528013582,
"loss": 0.3846,
"step": 280
},
{
"epoch": 0.420899854862119,
"grad_norm": 0.23768611252307892,
"learning_rate": 0.00013582342954159593,
"loss": 0.3788,
"step": 290
},
{
"epoch": 0.43541364296081275,
"grad_norm": 0.2431989163160324,
"learning_rate": 0.00013242784380305603,
"loss": 0.3762,
"step": 300
},
{
"epoch": 0.44992743105950656,
"grad_norm": 0.22804555296897888,
"learning_rate": 0.00012903225806451613,
"loss": 0.3745,
"step": 310
},
{
"epoch": 0.4644412191582003,
"grad_norm": 0.22682340443134308,
"learning_rate": 0.00012563667232597624,
"loss": 0.3774,
"step": 320
},
{
"epoch": 0.47895500725689405,
"grad_norm": 0.2583816647529602,
"learning_rate": 0.00012224108658743634,
"loss": 0.3762,
"step": 330
},
{
"epoch": 0.4934687953555878,
"grad_norm": 0.23387964069843292,
"learning_rate": 0.00011884550084889643,
"loss": 0.3753,
"step": 340
},
{
"epoch": 0.5079825834542816,
"grad_norm": 0.21552371978759766,
"learning_rate": 0.00011544991511035655,
"loss": 0.3761,
"step": 350
},
{
"epoch": 0.5224963715529753,
"grad_norm": 0.2177582085132599,
"learning_rate": 0.00011205432937181664,
"loss": 0.3734,
"step": 360
},
{
"epoch": 0.5370101596516691,
"grad_norm": 0.22051909565925598,
"learning_rate": 0.00010865874363327674,
"loss": 0.3717,
"step": 370
},
{
"epoch": 0.5515239477503628,
"grad_norm": 0.21704523265361786,
"learning_rate": 0.00010526315789473685,
"loss": 0.3707,
"step": 380
},
{
"epoch": 0.5660377358490566,
"grad_norm": 0.2447778433561325,
"learning_rate": 0.00010186757215619695,
"loss": 0.3669,
"step": 390
},
{
"epoch": 0.5805515239477503,
"grad_norm": 0.2079760581254959,
"learning_rate": 9.847198641765704e-05,
"loss": 0.3643,
"step": 400
},
{
"epoch": 0.5950653120464441,
"grad_norm": 0.21614719927310944,
"learning_rate": 9.507640067911715e-05,
"loss": 0.3655,
"step": 410
},
{
"epoch": 0.6095791001451378,
"grad_norm": 0.2331458330154419,
"learning_rate": 9.168081494057725e-05,
"loss": 0.363,
"step": 420
},
{
"epoch": 0.6240928882438317,
"grad_norm": 0.23197589814662933,
"learning_rate": 8.828522920203735e-05,
"loss": 0.3611,
"step": 430
},
{
"epoch": 0.6386066763425254,
"grad_norm": 0.21380995213985443,
"learning_rate": 8.488964346349746e-05,
"loss": 0.3656,
"step": 440
},
{
"epoch": 0.6531204644412192,
"grad_norm": 0.21522027254104614,
"learning_rate": 8.149405772495756e-05,
"loss": 0.3622,
"step": 450
},
{
"epoch": 0.6676342525399129,
"grad_norm": 0.23200784623622894,
"learning_rate": 7.809847198641767e-05,
"loss": 0.3652,
"step": 460
},
{
"epoch": 0.6821480406386067,
"grad_norm": 0.20713669061660767,
"learning_rate": 7.470288624787777e-05,
"loss": 0.3577,
"step": 470
},
{
"epoch": 0.6966618287373004,
"grad_norm": 0.2413240522146225,
"learning_rate": 7.130730050933786e-05,
"loss": 0.3605,
"step": 480
},
{
"epoch": 0.7111756168359942,
"grad_norm": 0.23881566524505615,
"learning_rate": 6.791171477079796e-05,
"loss": 0.361,
"step": 490
},
{
"epoch": 0.7256894049346879,
"grad_norm": 0.2193984091281891,
"learning_rate": 6.451612903225807e-05,
"loss": 0.3556,
"step": 500
},
{
"epoch": 0.7402031930333817,
"grad_norm": 0.2159193903207779,
"learning_rate": 6.112054329371817e-05,
"loss": 0.3581,
"step": 510
},
{
"epoch": 0.7547169811320755,
"grad_norm": 0.23495930433273315,
"learning_rate": 5.7724957555178275e-05,
"loss": 0.3572,
"step": 520
},
{
"epoch": 0.7692307692307693,
"grad_norm": 0.2095775455236435,
"learning_rate": 5.432937181663837e-05,
"loss": 0.3548,
"step": 530
},
{
"epoch": 0.783744557329463,
"grad_norm": 0.2108987271785736,
"learning_rate": 5.0933786078098476e-05,
"loss": 0.3586,
"step": 540
},
{
"epoch": 0.7982583454281568,
"grad_norm": 0.21367427706718445,
"learning_rate": 4.753820033955857e-05,
"loss": 0.354,
"step": 550
},
{
"epoch": 0.8127721335268505,
"grad_norm": 0.21299470961093903,
"learning_rate": 4.414261460101868e-05,
"loss": 0.3549,
"step": 560
},
{
"epoch": 0.8272859216255443,
"grad_norm": 0.19568979740142822,
"learning_rate": 4.074702886247878e-05,
"loss": 0.3527,
"step": 570
},
{
"epoch": 0.841799709724238,
"grad_norm": 0.23140305280685425,
"learning_rate": 3.7351443123938885e-05,
"loss": 0.3523,
"step": 580
},
{
"epoch": 0.8563134978229318,
"grad_norm": 0.19580787420272827,
"learning_rate": 3.395585738539898e-05,
"loss": 0.3541,
"step": 590
},
{
"epoch": 0.8708272859216255,
"grad_norm": 0.2059970647096634,
"learning_rate": 3.0560271646859086e-05,
"loss": 0.3572,
"step": 600
},
{
"epoch": 0.8853410740203193,
"grad_norm": 0.2206289917230606,
"learning_rate": 2.7164685908319186e-05,
"loss": 0.3548,
"step": 610
},
{
"epoch": 0.8998548621190131,
"grad_norm": 0.20322079956531525,
"learning_rate": 2.3769100169779286e-05,
"loss": 0.3557,
"step": 620
},
{
"epoch": 0.9143686502177069,
"grad_norm": 0.20411954820156097,
"learning_rate": 2.037351443123939e-05,
"loss": 0.3553,
"step": 630
},
{
"epoch": 0.9288824383164006,
"grad_norm": 0.22070156037807465,
"learning_rate": 1.697792869269949e-05,
"loss": 0.3483,
"step": 640
},
{
"epoch": 0.9433962264150944,
"grad_norm": 0.1965171992778778,
"learning_rate": 1.3582342954159593e-05,
"loss": 0.3555,
"step": 650
},
{
"epoch": 0.9579100145137881,
"grad_norm": 0.19971269369125366,
"learning_rate": 1.0186757215619695e-05,
"loss": 0.3475,
"step": 660
},
{
"epoch": 0.9724238026124818,
"grad_norm": 0.1889594942331314,
"learning_rate": 6.7911714770797965e-06,
"loss": 0.3532,
"step": 670
},
{
"epoch": 0.9869375907111756,
"grad_norm": 0.18607065081596375,
"learning_rate": 3.3955857385398982e-06,
"loss": 0.3492,
"step": 680
}
],
"logging_steps": 10,
"max_steps": 689,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"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": 4.211655017901048e+18,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}