HYPJUDY's picture
add
6661811
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 100.0,
"global_step": 1000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 2.0,
"eval_accuracy": 0.7733118971061094,
"eval_f1": 0.7518500246669956,
"eval_loss": 0.8074839115142822,
"eval_precision": 0.7419668938656281,
"eval_recall": 0.762,
"eval_runtime": 2.1702,
"eval_samples_per_second": 24.883,
"eval_steps_per_second": 0.461,
"step": 20
},
{
"epoch": 4.0,
"eval_accuracy": 0.8378502526412495,
"eval_f1": 0.8489243413101281,
"eval_loss": 0.6263514161109924,
"eval_precision": 0.8217126813289658,
"eval_recall": 0.878,
"eval_runtime": 1.8285,
"eval_samples_per_second": 29.533,
"eval_steps_per_second": 0.547,
"step": 40
},
{
"epoch": 6.0,
"eval_accuracy": 0.8375057418465779,
"eval_f1": 0.8824383164005806,
"eval_loss": 0.5844890475273132,
"eval_precision": 0.8547328959700093,
"eval_recall": 0.912,
"eval_runtime": 1.6994,
"eval_samples_per_second": 31.775,
"eval_steps_per_second": 0.588,
"step": 60
},
{
"epoch": 8.0,
"eval_accuracy": 0.8396876435461644,
"eval_f1": 0.8708251473477405,
"eval_loss": 0.7096832990646362,
"eval_precision": 0.8556949806949807,
"eval_recall": 0.8865,
"eval_runtime": 1.9498,
"eval_samples_per_second": 27.695,
"eval_steps_per_second": 0.513,
"step": 80
},
{
"epoch": 10.0,
"eval_accuracy": 0.8438217730822233,
"eval_f1": 0.8839153959665518,
"eval_loss": 0.7337720394134521,
"eval_precision": 0.8697967086156825,
"eval_recall": 0.8985,
"eval_runtime": 1.6222,
"eval_samples_per_second": 33.289,
"eval_steps_per_second": 0.616,
"step": 100
},
{
"epoch": 12.0,
"eval_accuracy": 0.8494487827285255,
"eval_f1": 0.8967391304347826,
"eval_loss": 0.8648139238357544,
"eval_precision": 0.88623046875,
"eval_recall": 0.9075,
"eval_runtime": 1.6638,
"eval_samples_per_second": 32.455,
"eval_steps_per_second": 0.601,
"step": 120
},
{
"epoch": 14.0,
"eval_accuracy": 0.8330271015158475,
"eval_f1": 0.8940709501364426,
"eval_loss": 0.8960414528846741,
"eval_precision": 0.8872476612506155,
"eval_recall": 0.901,
"eval_runtime": 1.8377,
"eval_samples_per_second": 29.384,
"eval_steps_per_second": 0.544,
"step": 140
},
{
"epoch": 16.0,
"eval_accuracy": 0.8408360128617364,
"eval_f1": 0.897062453715132,
"eval_loss": 0.9291977882385254,
"eval_precision": 0.8859093125304729,
"eval_recall": 0.9085,
"eval_runtime": 2.2856,
"eval_samples_per_second": 23.626,
"eval_steps_per_second": 0.438,
"step": 160
},
{
"epoch": 18.0,
"eval_accuracy": 0.8530087276067984,
"eval_f1": 0.9070520807376028,
"eval_loss": 0.956124484539032,
"eval_precision": 0.9041231992051664,
"eval_recall": 0.91,
"eval_runtime": 2.1004,
"eval_samples_per_second": 25.71,
"eval_steps_per_second": 0.476,
"step": 180
},
{
"epoch": 20.0,
"eval_accuracy": 0.8460036747818098,
"eval_f1": 0.9054455445544554,
"eval_loss": 1.1085299253463745,
"eval_precision": 0.8965686274509804,
"eval_recall": 0.9145,
"eval_runtime": 1.9718,
"eval_samples_per_second": 27.386,
"eval_steps_per_second": 0.507,
"step": 200
},
{
"epoch": 22.0,
"eval_accuracy": 0.8494487827285255,
"eval_f1": 0.9123157631776169,
"eval_loss": 1.1246980428695679,
"eval_precision": 0.9116325511732402,
"eval_recall": 0.913,
"eval_runtime": 2.2938,
"eval_samples_per_second": 23.541,
"eval_steps_per_second": 0.436,
"step": 220
},
{
"epoch": 24.0,
"eval_accuracy": 0.8488745980707395,
"eval_f1": 0.9118450459399057,
"eval_loss": 1.2039830684661865,
"eval_precision": 0.9057720769610261,
"eval_recall": 0.918,
"eval_runtime": 2.3959,
"eval_samples_per_second": 22.539,
"eval_steps_per_second": 0.417,
"step": 240
},
{
"epoch": 26.0,
"eval_accuracy": 0.8449701423977951,
"eval_f1": 0.9141426783479348,
"eval_loss": 1.2313123941421509,
"eval_precision": 0.9152882205513785,
"eval_recall": 0.913,
"eval_runtime": 1.8248,
"eval_samples_per_second": 29.592,
"eval_steps_per_second": 0.548,
"step": 260
},
{
"epoch": 28.0,
"eval_accuracy": 0.8450849793293523,
"eval_f1": 0.9095876800794833,
"eval_loss": 1.2972946166992188,
"eval_precision": 0.903751233958539,
"eval_recall": 0.9155,
"eval_runtime": 2.3256,
"eval_samples_per_second": 23.219,
"eval_steps_per_second": 0.43,
"step": 280
},
{
"epoch": 30.0,
"eval_accuracy": 0.8516306844281121,
"eval_f1": 0.9177467597208374,
"eval_loss": 1.27461838722229,
"eval_precision": 0.9150099403578529,
"eval_recall": 0.9205,
"eval_runtime": 2.085,
"eval_samples_per_second": 25.899,
"eval_steps_per_second": 0.48,
"step": 300
},
{
"epoch": 32.0,
"eval_accuracy": 0.8451998162609095,
"eval_f1": 0.9093167701863354,
"eval_loss": 1.3256772756576538,
"eval_precision": 0.9037037037037037,
"eval_recall": 0.915,
"eval_runtime": 1.6622,
"eval_samples_per_second": 32.487,
"eval_steps_per_second": 0.602,
"step": 320
},
{
"epoch": 34.0,
"eval_accuracy": 0.8609324758842444,
"eval_f1": 0.9068725099601593,
"eval_loss": 1.1881499290466309,
"eval_precision": 0.9032738095238095,
"eval_recall": 0.9105,
"eval_runtime": 1.8765,
"eval_samples_per_second": 28.777,
"eval_steps_per_second": 0.533,
"step": 340
},
{
"epoch": 36.0,
"eval_accuracy": 0.8310748736793753,
"eval_f1": 0.9006986027944112,
"eval_loss": 1.4595391750335693,
"eval_precision": 0.8989043824701195,
"eval_recall": 0.9025,
"eval_runtime": 1.593,
"eval_samples_per_second": 33.898,
"eval_steps_per_second": 0.628,
"step": 360
},
{
"epoch": 38.0,
"eval_accuracy": 0.8542719338539274,
"eval_f1": 0.9134879082523062,
"eval_loss": 1.3311606645584106,
"eval_precision": 0.9109895574341124,
"eval_recall": 0.916,
"eval_runtime": 2.269,
"eval_samples_per_second": 23.799,
"eval_steps_per_second": 0.441,
"step": 380
},
{
"epoch": 40.0,
"eval_accuracy": 0.8555351401010565,
"eval_f1": 0.9195,
"eval_loss": 1.2927559614181519,
"eval_precision": 0.9195,
"eval_recall": 0.9195,
"eval_runtime": 1.8831,
"eval_samples_per_second": 28.676,
"eval_steps_per_second": 0.531,
"step": 400
},
{
"epoch": 42.0,
"eval_accuracy": 0.8598989435002297,
"eval_f1": 0.9248439450686643,
"eval_loss": 1.3193974494934082,
"eval_precision": 0.9236907730673317,
"eval_recall": 0.926,
"eval_runtime": 1.733,
"eval_samples_per_second": 31.16,
"eval_steps_per_second": 0.577,
"step": 420
},
{
"epoch": 44.0,
"eval_accuracy": 0.8456591639871383,
"eval_f1": 0.9162290572643161,
"eval_loss": 1.455527424812317,
"eval_precision": 0.9164582291145573,
"eval_recall": 0.916,
"eval_runtime": 2.5054,
"eval_samples_per_second": 21.554,
"eval_steps_per_second": 0.399,
"step": 440
},
{
"epoch": 46.0,
"eval_accuracy": 0.8541570969223702,
"eval_f1": 0.916729182295574,
"eval_loss": 1.4188611507415771,
"eval_precision": 0.9169584792396198,
"eval_recall": 0.9165,
"eval_runtime": 2.3672,
"eval_samples_per_second": 22.811,
"eval_steps_per_second": 0.422,
"step": 460
},
{
"epoch": 48.0,
"eval_accuracy": 0.8516306844281121,
"eval_f1": 0.9209932279909707,
"eval_loss": 1.462133765220642,
"eval_precision": 0.9240060392551586,
"eval_recall": 0.918,
"eval_runtime": 2.0221,
"eval_samples_per_second": 26.705,
"eval_steps_per_second": 0.495,
"step": 480
},
{
"epoch": 50.0,
"learning_rate": 5e-06,
"loss": 0.1212,
"step": 500
},
{
"epoch": 50.0,
"eval_accuracy": 0.8492191088654111,
"eval_f1": 0.9188919391065635,
"eval_loss": 1.5107489824295044,
"eval_precision": 0.9172894867962132,
"eval_recall": 0.9205,
"eval_runtime": 2.2455,
"eval_samples_per_second": 24.048,
"eval_steps_per_second": 0.445,
"step": 500
},
{
"epoch": 52.0,
"eval_accuracy": 0.8520900321543409,
"eval_f1": 0.9225037257824144,
"eval_loss": 1.3997772932052612,
"eval_precision": 0.9165844027640672,
"eval_recall": 0.9285,
"eval_runtime": 1.6019,
"eval_samples_per_second": 33.711,
"eval_steps_per_second": 0.624,
"step": 520
},
{
"epoch": 54.0,
"eval_accuracy": 0.8531235645383556,
"eval_f1": 0.9185,
"eval_loss": 1.3953099250793457,
"eval_precision": 0.9185,
"eval_recall": 0.9185,
"eval_runtime": 2.4867,
"eval_samples_per_second": 21.715,
"eval_steps_per_second": 0.402,
"step": 540
},
{
"epoch": 56.0,
"eval_accuracy": 0.8493339457969683,
"eval_f1": 0.9165622650964669,
"eval_loss": 1.424229621887207,
"eval_precision": 0.9186338523355098,
"eval_recall": 0.9145,
"eval_runtime": 2.2429,
"eval_samples_per_second": 24.076,
"eval_steps_per_second": 0.446,
"step": 560
},
{
"epoch": 58.0,
"eval_accuracy": 0.8508268259072118,
"eval_f1": 0.9144851657940662,
"eval_loss": 1.4575742483139038,
"eval_precision": 0.9119840875186475,
"eval_recall": 0.917,
"eval_runtime": 1.7215,
"eval_samples_per_second": 31.368,
"eval_steps_per_second": 0.581,
"step": 580
},
{
"epoch": 60.0,
"eval_accuracy": 0.8524345429490124,
"eval_f1": 0.9176001991535974,
"eval_loss": 1.469473123550415,
"eval_precision": 0.9137332672285573,
"eval_recall": 0.9215,
"eval_runtime": 2.1512,
"eval_samples_per_second": 25.102,
"eval_steps_per_second": 0.465,
"step": 600
},
{
"epoch": 62.0,
"eval_accuracy": 0.8517455213596693,
"eval_f1": 0.918474195961107,
"eval_loss": 1.4966249465942383,
"eval_precision": 0.9159622078567876,
"eval_recall": 0.921,
"eval_runtime": 2.0241,
"eval_samples_per_second": 26.678,
"eval_steps_per_second": 0.494,
"step": 620
},
{
"epoch": 64.0,
"eval_accuracy": 0.8484152503445108,
"eval_f1": 0.92,
"eval_loss": 1.5030325651168823,
"eval_precision": 0.92,
"eval_recall": 0.92,
"eval_runtime": 2.1745,
"eval_samples_per_second": 24.834,
"eval_steps_per_second": 0.46,
"step": 640
},
{
"epoch": 66.0,
"eval_accuracy": 0.8462333486449242,
"eval_f1": 0.9175591531755916,
"eval_loss": 1.4818426370620728,
"eval_precision": 0.9141439205955335,
"eval_recall": 0.921,
"eval_runtime": 2.068,
"eval_samples_per_second": 26.112,
"eval_steps_per_second": 0.484,
"step": 660
},
{
"epoch": 68.0,
"eval_accuracy": 0.8497932935231971,
"eval_f1": 0.9201501877346684,
"eval_loss": 1.4994901418685913,
"eval_precision": 0.9213032581453634,
"eval_recall": 0.919,
"eval_runtime": 1.5887,
"eval_samples_per_second": 33.99,
"eval_steps_per_second": 0.629,
"step": 680
},
{
"epoch": 70.0,
"eval_accuracy": 0.8501378043178687,
"eval_f1": 0.9175180662845751,
"eval_loss": 1.52091383934021,
"eval_precision": 0.914555389965226,
"eval_recall": 0.9205,
"eval_runtime": 2.0412,
"eval_samples_per_second": 26.455,
"eval_steps_per_second": 0.49,
"step": 700
},
{
"epoch": 72.0,
"eval_accuracy": 0.8465778594395957,
"eval_f1": 0.9170633926334252,
"eval_loss": 1.54710054397583,
"eval_precision": 0.9191361125062782,
"eval_recall": 0.915,
"eval_runtime": 1.9021,
"eval_samples_per_second": 28.39,
"eval_steps_per_second": 0.526,
"step": 720
},
{
"epoch": 74.0,
"eval_accuracy": 0.8531235645383556,
"eval_f1": 0.919080919080919,
"eval_loss": 1.5027331113815308,
"eval_precision": 0.9181636726546906,
"eval_recall": 0.92,
"eval_runtime": 2.6669,
"eval_samples_per_second": 20.248,
"eval_steps_per_second": 0.375,
"step": 740
},
{
"epoch": 76.0,
"eval_accuracy": 0.8531235645383556,
"eval_f1": 0.9171464330413016,
"eval_loss": 1.5013470649719238,
"eval_precision": 0.9182957393483709,
"eval_recall": 0.916,
"eval_runtime": 2.1913,
"eval_samples_per_second": 24.643,
"eval_steps_per_second": 0.456,
"step": 760
},
{
"epoch": 78.0,
"eval_accuracy": 0.8509416628387689,
"eval_f1": 0.9218045112781955,
"eval_loss": 1.5246856212615967,
"eval_precision": 0.9241206030150754,
"eval_recall": 0.9195,
"eval_runtime": 1.7299,
"eval_samples_per_second": 31.215,
"eval_steps_per_second": 0.578,
"step": 780
},
{
"epoch": 80.0,
"eval_accuracy": 0.8507119889756546,
"eval_f1": 0.9178286852589641,
"eval_loss": 1.5289556980133057,
"eval_precision": 0.9141865079365079,
"eval_recall": 0.9215,
"eval_runtime": 1.9199,
"eval_samples_per_second": 28.126,
"eval_steps_per_second": 0.521,
"step": 800
},
{
"epoch": 82.0,
"eval_accuracy": 0.852779053743684,
"eval_f1": 0.9211576846307385,
"eval_loss": 1.523385763168335,
"eval_precision": 0.9193227091633466,
"eval_recall": 0.923,
"eval_runtime": 1.6928,
"eval_samples_per_second": 31.899,
"eval_steps_per_second": 0.591,
"step": 820
},
{
"epoch": 84.0,
"eval_accuracy": 0.8535829122645843,
"eval_f1": 0.9211183225162256,
"eval_loss": 1.5238100290298462,
"eval_precision": 0.919740777666999,
"eval_recall": 0.9225,
"eval_runtime": 1.7587,
"eval_samples_per_second": 30.704,
"eval_steps_per_second": 0.569,
"step": 840
},
{
"epoch": 86.0,
"eval_accuracy": 0.8497932935231971,
"eval_f1": 0.9178116412690482,
"eval_loss": 1.52961266040802,
"eval_precision": 0.9171243135297055,
"eval_recall": 0.9185,
"eval_runtime": 2.2872,
"eval_samples_per_second": 23.609,
"eval_steps_per_second": 0.437,
"step": 860
},
{
"epoch": 88.0,
"eval_accuracy": 0.8484152503445108,
"eval_f1": 0.9172293073268317,
"eval_loss": 1.5319523811340332,
"eval_precision": 0.9174587293646823,
"eval_recall": 0.917,
"eval_runtime": 1.8758,
"eval_samples_per_second": 28.788,
"eval_steps_per_second": 0.533,
"step": 880
},
{
"epoch": 90.0,
"eval_accuracy": 0.8516306844281121,
"eval_f1": 0.9216520650813517,
"eval_loss": 1.5241385698318481,
"eval_precision": 0.9228070175438596,
"eval_recall": 0.9205,
"eval_runtime": 2.319,
"eval_samples_per_second": 23.286,
"eval_steps_per_second": 0.431,
"step": 900
},
{
"epoch": 92.0,
"eval_accuracy": 0.8524345429490124,
"eval_f1": 0.922,
"eval_loss": 1.5183860063552856,
"eval_precision": 0.922,
"eval_recall": 0.922,
"eval_runtime": 1.8138,
"eval_samples_per_second": 29.771,
"eval_steps_per_second": 0.551,
"step": 920
},
{
"epoch": 94.0,
"eval_accuracy": 0.8526642168121268,
"eval_f1": 0.9215,
"eval_loss": 1.5182560682296753,
"eval_precision": 0.9215,
"eval_recall": 0.9215,
"eval_runtime": 2.1167,
"eval_samples_per_second": 25.511,
"eval_steps_per_second": 0.472,
"step": 940
},
{
"epoch": 96.0,
"eval_accuracy": 0.8523197060174552,
"eval_f1": 0.9209999999999999,
"eval_loss": 1.519921898841858,
"eval_precision": 0.921,
"eval_recall": 0.921,
"eval_runtime": 2.4525,
"eval_samples_per_second": 22.018,
"eval_steps_per_second": 0.408,
"step": 960
},
{
"epoch": 98.0,
"eval_accuracy": 0.8520900321543409,
"eval_f1": 0.9214607303651825,
"eval_loss": 1.5220308303833008,
"eval_precision": 0.9219219219219219,
"eval_recall": 0.921,
"eval_runtime": 2.2195,
"eval_samples_per_second": 24.33,
"eval_steps_per_second": 0.451,
"step": 980
},
{
"epoch": 100.0,
"learning_rate": 0.0,
"loss": 0.0007,
"step": 1000
},
{
"epoch": 100.0,
"eval_accuracy": 0.8518603582912264,
"eval_f1": 0.9214607303651825,
"eval_loss": 1.5228424072265625,
"eval_precision": 0.9219219219219219,
"eval_recall": 0.921,
"eval_runtime": 2.3676,
"eval_samples_per_second": 22.808,
"eval_steps_per_second": 0.422,
"step": 1000
},
{
"epoch": 100.0,
"step": 1000,
"total_flos": 1.4163133547413504e+16,
"train_loss": 0.06096216064691544,
"train_runtime": 422.6711,
"train_samples_per_second": 37.854,
"train_steps_per_second": 2.366
}
],
"max_steps": 1000,
"num_train_epochs": 100,
"total_flos": 1.4163133547413504e+16,
"trial_name": null,
"trial_params": null
}