videomae-base-finetuned-ucf101 / trainer_state.json
feliciaaaluo's picture
End of training
58b0d79 verified
{
"best_metric": 0.9837157660991858,
"best_model_checkpoint": "videomae-base-finetuned-ucf101\\checkpoint-8320",
"epoch": 9.098918269230769,
"eval_steps": 500,
"global_step": 8320,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 6.009615384615385e-07,
"loss": 4.0127,
"step": 10
},
{
"epoch": 0.0,
"learning_rate": 1.201923076923077e-06,
"loss": 4.0116,
"step": 20
},
{
"epoch": 0.0,
"learning_rate": 1.8028846153846153e-06,
"loss": 3.9416,
"step": 30
},
{
"epoch": 0.0,
"learning_rate": 2.403846153846154e-06,
"loss": 3.954,
"step": 40
},
{
"epoch": 0.01,
"learning_rate": 3.0048076923076927e-06,
"loss": 4.0102,
"step": 50
},
{
"epoch": 0.01,
"learning_rate": 3.6057692307692307e-06,
"loss": 3.9791,
"step": 60
},
{
"epoch": 0.01,
"learning_rate": 4.20673076923077e-06,
"loss": 3.9077,
"step": 70
},
{
"epoch": 0.01,
"learning_rate": 4.807692307692308e-06,
"loss": 3.9278,
"step": 80
},
{
"epoch": 0.01,
"learning_rate": 5.408653846153847e-06,
"loss": 3.9414,
"step": 90
},
{
"epoch": 0.01,
"learning_rate": 6.0096153846153855e-06,
"loss": 3.992,
"step": 100
},
{
"epoch": 0.01,
"learning_rate": 6.610576923076923e-06,
"loss": 3.9291,
"step": 110
},
{
"epoch": 0.01,
"learning_rate": 7.211538461538461e-06,
"loss": 3.9836,
"step": 120
},
{
"epoch": 0.02,
"learning_rate": 7.8125e-06,
"loss": 3.914,
"step": 130
},
{
"epoch": 0.02,
"learning_rate": 8.41346153846154e-06,
"loss": 3.8372,
"step": 140
},
{
"epoch": 0.02,
"learning_rate": 9.014423076923078e-06,
"loss": 3.8477,
"step": 150
},
{
"epoch": 0.02,
"learning_rate": 9.615384615384616e-06,
"loss": 3.7954,
"step": 160
},
{
"epoch": 0.02,
"learning_rate": 1.0216346153846154e-05,
"loss": 3.8203,
"step": 170
},
{
"epoch": 0.02,
"learning_rate": 1.0817307692307693e-05,
"loss": 3.8033,
"step": 180
},
{
"epoch": 0.02,
"learning_rate": 1.1418269230769231e-05,
"loss": 3.7756,
"step": 190
},
{
"epoch": 0.02,
"learning_rate": 1.2019230769230771e-05,
"loss": 3.8827,
"step": 200
},
{
"epoch": 0.03,
"learning_rate": 1.2620192307692307e-05,
"loss": 3.7937,
"step": 210
},
{
"epoch": 0.03,
"learning_rate": 1.3221153846153847e-05,
"loss": 3.7683,
"step": 220
},
{
"epoch": 0.03,
"learning_rate": 1.3822115384615386e-05,
"loss": 3.6827,
"step": 230
},
{
"epoch": 0.03,
"learning_rate": 1.4423076923076923e-05,
"loss": 3.6884,
"step": 240
},
{
"epoch": 0.03,
"learning_rate": 1.5024038461538462e-05,
"loss": 3.6489,
"step": 250
},
{
"epoch": 0.03,
"learning_rate": 1.5625e-05,
"loss": 3.6757,
"step": 260
},
{
"epoch": 0.03,
"learning_rate": 1.6225961538461538e-05,
"loss": 3.5549,
"step": 270
},
{
"epoch": 0.03,
"learning_rate": 1.682692307692308e-05,
"loss": 3.509,
"step": 280
},
{
"epoch": 0.03,
"learning_rate": 1.7427884615384614e-05,
"loss": 3.4363,
"step": 290
},
{
"epoch": 0.04,
"learning_rate": 1.8028846153846156e-05,
"loss": 3.4794,
"step": 300
},
{
"epoch": 0.04,
"learning_rate": 1.8629807692307693e-05,
"loss": 3.4726,
"step": 310
},
{
"epoch": 0.04,
"learning_rate": 1.923076923076923e-05,
"loss": 3.3436,
"step": 320
},
{
"epoch": 0.04,
"learning_rate": 1.983173076923077e-05,
"loss": 3.3382,
"step": 330
},
{
"epoch": 0.04,
"learning_rate": 2.0432692307692307e-05,
"loss": 3.1034,
"step": 340
},
{
"epoch": 0.04,
"learning_rate": 2.103365384615385e-05,
"loss": 3.151,
"step": 350
},
{
"epoch": 0.04,
"learning_rate": 2.1634615384615387e-05,
"loss": 3.1399,
"step": 360
},
{
"epoch": 0.04,
"learning_rate": 2.223557692307692e-05,
"loss": 3.1325,
"step": 370
},
{
"epoch": 0.05,
"learning_rate": 2.2836538461538463e-05,
"loss": 3.214,
"step": 380
},
{
"epoch": 0.05,
"learning_rate": 2.34375e-05,
"loss": 2.9566,
"step": 390
},
{
"epoch": 0.05,
"learning_rate": 2.4038461538461542e-05,
"loss": 2.8413,
"step": 400
},
{
"epoch": 0.05,
"learning_rate": 2.463942307692308e-05,
"loss": 2.769,
"step": 410
},
{
"epoch": 0.05,
"learning_rate": 2.5240384615384614e-05,
"loss": 2.8527,
"step": 420
},
{
"epoch": 0.05,
"learning_rate": 2.584134615384616e-05,
"loss": 2.7911,
"step": 430
},
{
"epoch": 0.05,
"learning_rate": 2.6442307692307694e-05,
"loss": 2.4166,
"step": 440
},
{
"epoch": 0.05,
"learning_rate": 2.704326923076923e-05,
"loss": 2.7125,
"step": 450
},
{
"epoch": 0.06,
"learning_rate": 2.7644230769230773e-05,
"loss": 2.4932,
"step": 460
},
{
"epoch": 0.06,
"learning_rate": 2.8245192307692307e-05,
"loss": 2.454,
"step": 470
},
{
"epoch": 0.06,
"learning_rate": 2.8846153846153845e-05,
"loss": 2.2737,
"step": 480
},
{
"epoch": 0.06,
"learning_rate": 2.9447115384615387e-05,
"loss": 2.316,
"step": 490
},
{
"epoch": 0.06,
"learning_rate": 3.0048076923076925e-05,
"loss": 2.538,
"step": 500
},
{
"epoch": 0.06,
"learning_rate": 3.064903846153846e-05,
"loss": 2.1644,
"step": 510
},
{
"epoch": 0.06,
"learning_rate": 3.125e-05,
"loss": 2.1932,
"step": 520
},
{
"epoch": 0.06,
"learning_rate": 3.185096153846154e-05,
"loss": 2.1082,
"step": 530
},
{
"epoch": 0.06,
"learning_rate": 3.2451923076923077e-05,
"loss": 2.2554,
"step": 540
},
{
"epoch": 0.07,
"learning_rate": 3.3052884615384615e-05,
"loss": 2.1601,
"step": 550
},
{
"epoch": 0.07,
"learning_rate": 3.365384615384616e-05,
"loss": 2.0342,
"step": 560
},
{
"epoch": 0.07,
"learning_rate": 3.42548076923077e-05,
"loss": 1.9706,
"step": 570
},
{
"epoch": 0.07,
"learning_rate": 3.485576923076923e-05,
"loss": 2.0727,
"step": 580
},
{
"epoch": 0.07,
"learning_rate": 3.545673076923077e-05,
"loss": 1.8431,
"step": 590
},
{
"epoch": 0.07,
"learning_rate": 3.605769230769231e-05,
"loss": 1.9603,
"step": 600
},
{
"epoch": 0.07,
"learning_rate": 3.665865384615384e-05,
"loss": 1.9677,
"step": 610
},
{
"epoch": 0.07,
"learning_rate": 3.725961538461539e-05,
"loss": 1.7238,
"step": 620
},
{
"epoch": 0.08,
"learning_rate": 3.7860576923076925e-05,
"loss": 1.8137,
"step": 630
},
{
"epoch": 0.08,
"learning_rate": 3.846153846153846e-05,
"loss": 1.5439,
"step": 640
},
{
"epoch": 0.08,
"learning_rate": 3.90625e-05,
"loss": 1.7736,
"step": 650
},
{
"epoch": 0.08,
"learning_rate": 3.966346153846154e-05,
"loss": 1.7694,
"step": 660
},
{
"epoch": 0.08,
"learning_rate": 4.0264423076923083e-05,
"loss": 1.5685,
"step": 670
},
{
"epoch": 0.08,
"learning_rate": 4.0865384615384615e-05,
"loss": 1.3912,
"step": 680
},
{
"epoch": 0.08,
"learning_rate": 4.146634615384616e-05,
"loss": 1.3916,
"step": 690
},
{
"epoch": 0.08,
"learning_rate": 4.20673076923077e-05,
"loss": 1.5716,
"step": 700
},
{
"epoch": 0.09,
"learning_rate": 4.266826923076923e-05,
"loss": 1.7127,
"step": 710
},
{
"epoch": 0.09,
"learning_rate": 4.326923076923077e-05,
"loss": 1.6191,
"step": 720
},
{
"epoch": 0.09,
"learning_rate": 4.387019230769231e-05,
"loss": 1.53,
"step": 730
},
{
"epoch": 0.09,
"learning_rate": 4.447115384615384e-05,
"loss": 1.3601,
"step": 740
},
{
"epoch": 0.09,
"learning_rate": 4.507211538461539e-05,
"loss": 1.5335,
"step": 750
},
{
"epoch": 0.09,
"learning_rate": 4.5673076923076925e-05,
"loss": 1.5374,
"step": 760
},
{
"epoch": 0.09,
"learning_rate": 4.627403846153846e-05,
"loss": 1.4242,
"step": 770
},
{
"epoch": 0.09,
"learning_rate": 4.6875e-05,
"loss": 1.3306,
"step": 780
},
{
"epoch": 0.09,
"learning_rate": 4.747596153846154e-05,
"loss": 1.1707,
"step": 790
},
{
"epoch": 0.1,
"learning_rate": 4.8076923076923084e-05,
"loss": 1.3212,
"step": 800
},
{
"epoch": 0.1,
"learning_rate": 4.8677884615384615e-05,
"loss": 1.0776,
"step": 810
},
{
"epoch": 0.1,
"learning_rate": 4.927884615384616e-05,
"loss": 1.1776,
"step": 820
},
{
"epoch": 0.1,
"learning_rate": 4.98798076923077e-05,
"loss": 1.1009,
"step": 830
},
{
"epoch": 0.1,
"eval_accuracy": 0.6558105107327905,
"eval_loss": 1.2521276473999023,
"eval_runtime": 89.0403,
"eval_samples_per_second": 15.173,
"eval_steps_per_second": 2.538,
"step": 833
},
{
"epoch": 1.0,
"learning_rate": 4.99465811965812e-05,
"loss": 1.2513,
"step": 840
},
{
"epoch": 1.0,
"learning_rate": 4.98798076923077e-05,
"loss": 1.2784,
"step": 850
},
{
"epoch": 1.0,
"learning_rate": 4.981303418803419e-05,
"loss": 1.0356,
"step": 860
},
{
"epoch": 1.0,
"learning_rate": 4.9746260683760685e-05,
"loss": 1.2674,
"step": 870
},
{
"epoch": 1.01,
"learning_rate": 4.9679487179487185e-05,
"loss": 1.2378,
"step": 880
},
{
"epoch": 1.01,
"learning_rate": 4.961271367521368e-05,
"loss": 1.0986,
"step": 890
},
{
"epoch": 1.01,
"learning_rate": 4.954594017094017e-05,
"loss": 0.9062,
"step": 900
},
{
"epoch": 1.01,
"learning_rate": 4.947916666666667e-05,
"loss": 1.0728,
"step": 910
},
{
"epoch": 1.01,
"learning_rate": 4.9412393162393166e-05,
"loss": 1.12,
"step": 920
},
{
"epoch": 1.01,
"learning_rate": 4.9345619658119666e-05,
"loss": 1.2067,
"step": 930
},
{
"epoch": 1.01,
"learning_rate": 4.927884615384616e-05,
"loss": 1.1527,
"step": 940
},
{
"epoch": 1.01,
"learning_rate": 4.9212072649572646e-05,
"loss": 1.1009,
"step": 950
},
{
"epoch": 1.02,
"learning_rate": 4.9145299145299147e-05,
"loss": 0.9438,
"step": 960
},
{
"epoch": 1.02,
"learning_rate": 4.907852564102564e-05,
"loss": 0.8438,
"step": 970
},
{
"epoch": 1.02,
"learning_rate": 4.901175213675214e-05,
"loss": 0.7278,
"step": 980
},
{
"epoch": 1.02,
"learning_rate": 4.8944978632478634e-05,
"loss": 0.8685,
"step": 990
},
{
"epoch": 1.02,
"learning_rate": 4.887820512820513e-05,
"loss": 1.0214,
"step": 1000
},
{
"epoch": 1.02,
"learning_rate": 4.881143162393163e-05,
"loss": 0.9312,
"step": 1010
},
{
"epoch": 1.02,
"learning_rate": 4.874465811965812e-05,
"loss": 0.8984,
"step": 1020
},
{
"epoch": 1.02,
"learning_rate": 4.8677884615384615e-05,
"loss": 0.8442,
"step": 1030
},
{
"epoch": 1.02,
"learning_rate": 4.8611111111111115e-05,
"loss": 0.6382,
"step": 1040
},
{
"epoch": 1.03,
"learning_rate": 4.854433760683761e-05,
"loss": 0.6792,
"step": 1050
},
{
"epoch": 1.03,
"learning_rate": 4.84775641025641e-05,
"loss": 0.8806,
"step": 1060
},
{
"epoch": 1.03,
"learning_rate": 4.84107905982906e-05,
"loss": 0.9612,
"step": 1070
},
{
"epoch": 1.03,
"learning_rate": 4.8344017094017096e-05,
"loss": 0.8101,
"step": 1080
},
{
"epoch": 1.03,
"learning_rate": 4.827724358974359e-05,
"loss": 0.7791,
"step": 1090
},
{
"epoch": 1.03,
"learning_rate": 4.821047008547009e-05,
"loss": 0.8231,
"step": 1100
},
{
"epoch": 1.03,
"learning_rate": 4.814369658119658e-05,
"loss": 0.6457,
"step": 1110
},
{
"epoch": 1.03,
"learning_rate": 4.8076923076923084e-05,
"loss": 0.5397,
"step": 1120
},
{
"epoch": 1.04,
"learning_rate": 4.801014957264958e-05,
"loss": 0.7663,
"step": 1130
},
{
"epoch": 1.04,
"learning_rate": 4.794337606837607e-05,
"loss": 1.0645,
"step": 1140
},
{
"epoch": 1.04,
"learning_rate": 4.787660256410257e-05,
"loss": 1.0223,
"step": 1150
},
{
"epoch": 1.04,
"learning_rate": 4.7809829059829065e-05,
"loss": 1.0806,
"step": 1160
},
{
"epoch": 1.04,
"learning_rate": 4.774305555555556e-05,
"loss": 0.9156,
"step": 1170
},
{
"epoch": 1.04,
"learning_rate": 4.767628205128206e-05,
"loss": 0.7737,
"step": 1180
},
{
"epoch": 1.04,
"learning_rate": 4.7609508547008545e-05,
"loss": 0.6834,
"step": 1190
},
{
"epoch": 1.04,
"learning_rate": 4.7542735042735045e-05,
"loss": 0.808,
"step": 1200
},
{
"epoch": 1.05,
"learning_rate": 4.747596153846154e-05,
"loss": 0.9556,
"step": 1210
},
{
"epoch": 1.05,
"learning_rate": 4.740918803418803e-05,
"loss": 0.5992,
"step": 1220
},
{
"epoch": 1.05,
"learning_rate": 4.734241452991453e-05,
"loss": 0.6876,
"step": 1230
},
{
"epoch": 1.05,
"learning_rate": 4.7275641025641026e-05,
"loss": 0.7753,
"step": 1240
},
{
"epoch": 1.05,
"learning_rate": 4.720886752136752e-05,
"loss": 0.6666,
"step": 1250
},
{
"epoch": 1.05,
"learning_rate": 4.714209401709402e-05,
"loss": 0.4952,
"step": 1260
},
{
"epoch": 1.05,
"learning_rate": 4.7075320512820514e-05,
"loss": 0.9254,
"step": 1270
},
{
"epoch": 1.05,
"learning_rate": 4.700854700854701e-05,
"loss": 0.8664,
"step": 1280
},
{
"epoch": 1.05,
"learning_rate": 4.694177350427351e-05,
"loss": 0.6691,
"step": 1290
},
{
"epoch": 1.06,
"learning_rate": 4.6875e-05,
"loss": 0.7406,
"step": 1300
},
{
"epoch": 1.06,
"learning_rate": 4.68082264957265e-05,
"loss": 0.6539,
"step": 1310
},
{
"epoch": 1.06,
"learning_rate": 4.6741452991452995e-05,
"loss": 0.9185,
"step": 1320
},
{
"epoch": 1.06,
"learning_rate": 4.667467948717949e-05,
"loss": 0.7776,
"step": 1330
},
{
"epoch": 1.06,
"learning_rate": 4.660790598290599e-05,
"loss": 0.8129,
"step": 1340
},
{
"epoch": 1.06,
"learning_rate": 4.654113247863248e-05,
"loss": 0.4696,
"step": 1350
},
{
"epoch": 1.06,
"learning_rate": 4.6474358974358976e-05,
"loss": 0.4895,
"step": 1360
},
{
"epoch": 1.06,
"learning_rate": 4.6407585470085476e-05,
"loss": 0.6573,
"step": 1370
},
{
"epoch": 1.07,
"learning_rate": 4.634081196581197e-05,
"loss": 0.6352,
"step": 1380
},
{
"epoch": 1.07,
"learning_rate": 4.627403846153846e-05,
"loss": 0.4662,
"step": 1390
},
{
"epoch": 1.07,
"learning_rate": 4.620726495726496e-05,
"loss": 0.6592,
"step": 1400
},
{
"epoch": 1.07,
"learning_rate": 4.614049145299146e-05,
"loss": 0.6501,
"step": 1410
},
{
"epoch": 1.07,
"learning_rate": 4.607371794871795e-05,
"loss": 0.5648,
"step": 1420
},
{
"epoch": 1.07,
"learning_rate": 4.6006944444444444e-05,
"loss": 0.7981,
"step": 1430
},
{
"epoch": 1.07,
"learning_rate": 4.594017094017094e-05,
"loss": 0.573,
"step": 1440
},
{
"epoch": 1.07,
"learning_rate": 4.587339743589744e-05,
"loss": 0.6546,
"step": 1450
},
{
"epoch": 1.08,
"learning_rate": 4.580662393162393e-05,
"loss": 0.5825,
"step": 1460
},
{
"epoch": 1.08,
"learning_rate": 4.5739850427350425e-05,
"loss": 0.5756,
"step": 1470
},
{
"epoch": 1.08,
"learning_rate": 4.5673076923076925e-05,
"loss": 0.5927,
"step": 1480
},
{
"epoch": 1.08,
"learning_rate": 4.560630341880342e-05,
"loss": 0.577,
"step": 1490
},
{
"epoch": 1.08,
"learning_rate": 4.553952991452992e-05,
"loss": 0.726,
"step": 1500
},
{
"epoch": 1.08,
"learning_rate": 4.547275641025641e-05,
"loss": 0.5516,
"step": 1510
},
{
"epoch": 1.08,
"learning_rate": 4.5405982905982906e-05,
"loss": 0.5479,
"step": 1520
},
{
"epoch": 1.08,
"learning_rate": 4.5339209401709406e-05,
"loss": 0.4325,
"step": 1530
},
{
"epoch": 1.08,
"learning_rate": 4.52724358974359e-05,
"loss": 0.4567,
"step": 1540
},
{
"epoch": 1.09,
"learning_rate": 4.520566239316239e-05,
"loss": 0.5283,
"step": 1550
},
{
"epoch": 1.09,
"learning_rate": 4.5138888888888894e-05,
"loss": 0.3399,
"step": 1560
},
{
"epoch": 1.09,
"learning_rate": 4.507211538461539e-05,
"loss": 0.5445,
"step": 1570
},
{
"epoch": 1.09,
"learning_rate": 4.500534188034188e-05,
"loss": 0.3424,
"step": 1580
},
{
"epoch": 1.09,
"learning_rate": 4.493856837606838e-05,
"loss": 0.624,
"step": 1590
},
{
"epoch": 1.09,
"learning_rate": 4.4871794871794874e-05,
"loss": 0.529,
"step": 1600
},
{
"epoch": 1.09,
"learning_rate": 4.4805021367521375e-05,
"loss": 0.5173,
"step": 1610
},
{
"epoch": 1.09,
"learning_rate": 4.473824786324787e-05,
"loss": 0.5501,
"step": 1620
},
{
"epoch": 1.1,
"learning_rate": 4.467147435897436e-05,
"loss": 0.3545,
"step": 1630
},
{
"epoch": 1.1,
"learning_rate": 4.460470085470086e-05,
"loss": 0.5297,
"step": 1640
},
{
"epoch": 1.1,
"learning_rate": 4.4537927350427356e-05,
"loss": 0.3494,
"step": 1650
},
{
"epoch": 1.1,
"learning_rate": 4.447115384615384e-05,
"loss": 0.2821,
"step": 1660
},
{
"epoch": 1.1,
"eval_accuracy": 0.8623242042931162,
"eval_loss": 0.43101879954338074,
"eval_runtime": 85.5894,
"eval_samples_per_second": 15.785,
"eval_steps_per_second": 2.641,
"step": 1666
},
{
"epoch": 2.0,
"learning_rate": 4.440438034188034e-05,
"loss": 0.4212,
"step": 1670
},
{
"epoch": 2.0,
"learning_rate": 4.4337606837606836e-05,
"loss": 0.4583,
"step": 1680
},
{
"epoch": 2.0,
"learning_rate": 4.4270833333333337e-05,
"loss": 0.2378,
"step": 1690
},
{
"epoch": 2.0,
"learning_rate": 4.420405982905983e-05,
"loss": 0.4887,
"step": 1700
},
{
"epoch": 2.01,
"learning_rate": 4.4137286324786324e-05,
"loss": 0.312,
"step": 1710
},
{
"epoch": 2.01,
"learning_rate": 4.4070512820512824e-05,
"loss": 0.3402,
"step": 1720
},
{
"epoch": 2.01,
"learning_rate": 4.400373931623932e-05,
"loss": 0.2723,
"step": 1730
},
{
"epoch": 2.01,
"learning_rate": 4.393696581196581e-05,
"loss": 0.2785,
"step": 1740
},
{
"epoch": 2.01,
"learning_rate": 4.387019230769231e-05,
"loss": 0.187,
"step": 1750
},
{
"epoch": 2.01,
"learning_rate": 4.3803418803418805e-05,
"loss": 0.2831,
"step": 1760
},
{
"epoch": 2.01,
"learning_rate": 4.37366452991453e-05,
"loss": 0.6487,
"step": 1770
},
{
"epoch": 2.01,
"learning_rate": 4.36698717948718e-05,
"loss": 0.3937,
"step": 1780
},
{
"epoch": 2.01,
"learning_rate": 4.360309829059829e-05,
"loss": 0.2464,
"step": 1790
},
{
"epoch": 2.02,
"learning_rate": 4.353632478632479e-05,
"loss": 0.1763,
"step": 1800
},
{
"epoch": 2.02,
"learning_rate": 4.3469551282051286e-05,
"loss": 0.5681,
"step": 1810
},
{
"epoch": 2.02,
"learning_rate": 4.340277777777778e-05,
"loss": 0.3058,
"step": 1820
},
{
"epoch": 2.02,
"learning_rate": 4.333600427350428e-05,
"loss": 0.4737,
"step": 1830
},
{
"epoch": 2.02,
"learning_rate": 4.326923076923077e-05,
"loss": 0.2714,
"step": 1840
},
{
"epoch": 2.02,
"learning_rate": 4.320245726495727e-05,
"loss": 0.2996,
"step": 1850
},
{
"epoch": 2.02,
"learning_rate": 4.313568376068377e-05,
"loss": 0.1767,
"step": 1860
},
{
"epoch": 2.02,
"learning_rate": 4.306891025641026e-05,
"loss": 0.3166,
"step": 1870
},
{
"epoch": 2.03,
"learning_rate": 4.3002136752136754e-05,
"loss": 0.6681,
"step": 1880
},
{
"epoch": 2.03,
"learning_rate": 4.293536324786325e-05,
"loss": 0.271,
"step": 1890
},
{
"epoch": 2.03,
"learning_rate": 4.286858974358974e-05,
"loss": 0.2432,
"step": 1900
},
{
"epoch": 2.03,
"learning_rate": 4.280181623931624e-05,
"loss": 0.3976,
"step": 1910
},
{
"epoch": 2.03,
"learning_rate": 4.2735042735042735e-05,
"loss": 0.4972,
"step": 1920
},
{
"epoch": 2.03,
"learning_rate": 4.266826923076923e-05,
"loss": 0.4663,
"step": 1930
},
{
"epoch": 2.03,
"learning_rate": 4.260149572649573e-05,
"loss": 0.456,
"step": 1940
},
{
"epoch": 2.03,
"learning_rate": 4.253472222222222e-05,
"loss": 0.5133,
"step": 1950
},
{
"epoch": 2.04,
"learning_rate": 4.2467948717948716e-05,
"loss": 0.2464,
"step": 1960
},
{
"epoch": 2.04,
"learning_rate": 4.2401175213675216e-05,
"loss": 0.2097,
"step": 1970
},
{
"epoch": 2.04,
"learning_rate": 4.233440170940171e-05,
"loss": 0.479,
"step": 1980
},
{
"epoch": 2.04,
"learning_rate": 4.226762820512821e-05,
"loss": 0.2995,
"step": 1990
},
{
"epoch": 2.04,
"learning_rate": 4.2200854700854704e-05,
"loss": 0.5557,
"step": 2000
},
{
"epoch": 2.04,
"learning_rate": 4.21340811965812e-05,
"loss": 0.572,
"step": 2010
},
{
"epoch": 2.04,
"learning_rate": 4.20673076923077e-05,
"loss": 0.5636,
"step": 2020
},
{
"epoch": 2.04,
"learning_rate": 4.200053418803419e-05,
"loss": 0.2179,
"step": 2030
},
{
"epoch": 2.04,
"learning_rate": 4.1933760683760684e-05,
"loss": 0.3565,
"step": 2040
},
{
"epoch": 2.05,
"learning_rate": 4.1866987179487185e-05,
"loss": 0.2154,
"step": 2050
},
{
"epoch": 2.05,
"learning_rate": 4.180021367521368e-05,
"loss": 0.2826,
"step": 2060
},
{
"epoch": 2.05,
"learning_rate": 4.173344017094017e-05,
"loss": 0.3187,
"step": 2070
},
{
"epoch": 2.05,
"learning_rate": 4.166666666666667e-05,
"loss": 0.356,
"step": 2080
},
{
"epoch": 2.05,
"learning_rate": 4.1599893162393166e-05,
"loss": 0.1521,
"step": 2090
},
{
"epoch": 2.05,
"learning_rate": 4.153311965811966e-05,
"loss": 0.2919,
"step": 2100
},
{
"epoch": 2.05,
"learning_rate": 4.146634615384616e-05,
"loss": 0.2014,
"step": 2110
},
{
"epoch": 2.05,
"learning_rate": 4.1399572649572646e-05,
"loss": 0.535,
"step": 2120
},
{
"epoch": 2.06,
"learning_rate": 4.1332799145299146e-05,
"loss": 0.2376,
"step": 2130
},
{
"epoch": 2.06,
"learning_rate": 4.126602564102564e-05,
"loss": 0.3963,
"step": 2140
},
{
"epoch": 2.06,
"learning_rate": 4.1199252136752133e-05,
"loss": 0.3987,
"step": 2150
},
{
"epoch": 2.06,
"learning_rate": 4.1132478632478634e-05,
"loss": 0.3923,
"step": 2160
},
{
"epoch": 2.06,
"learning_rate": 4.106570512820513e-05,
"loss": 0.5621,
"step": 2170
},
{
"epoch": 2.06,
"learning_rate": 4.099893162393163e-05,
"loss": 0.3855,
"step": 2180
},
{
"epoch": 2.06,
"learning_rate": 4.093215811965812e-05,
"loss": 0.369,
"step": 2190
},
{
"epoch": 2.06,
"learning_rate": 4.0865384615384615e-05,
"loss": 0.1231,
"step": 2200
},
{
"epoch": 2.07,
"learning_rate": 4.0798611111111115e-05,
"loss": 0.1671,
"step": 2210
},
{
"epoch": 2.07,
"learning_rate": 4.073183760683761e-05,
"loss": 0.1788,
"step": 2220
},
{
"epoch": 2.07,
"learning_rate": 4.06650641025641e-05,
"loss": 0.5884,
"step": 2230
},
{
"epoch": 2.07,
"learning_rate": 4.05982905982906e-05,
"loss": 0.2911,
"step": 2240
},
{
"epoch": 2.07,
"learning_rate": 4.0531517094017096e-05,
"loss": 0.1407,
"step": 2250
},
{
"epoch": 2.07,
"learning_rate": 4.046474358974359e-05,
"loss": 0.4743,
"step": 2260
},
{
"epoch": 2.07,
"learning_rate": 4.039797008547009e-05,
"loss": 0.2106,
"step": 2270
},
{
"epoch": 2.07,
"learning_rate": 4.033119658119658e-05,
"loss": 0.4062,
"step": 2280
},
{
"epoch": 2.08,
"learning_rate": 4.0264423076923083e-05,
"loss": 0.195,
"step": 2290
},
{
"epoch": 2.08,
"learning_rate": 4.019764957264958e-05,
"loss": 0.1114,
"step": 2300
},
{
"epoch": 2.08,
"learning_rate": 4.013087606837607e-05,
"loss": 0.368,
"step": 2310
},
{
"epoch": 2.08,
"learning_rate": 4.006410256410257e-05,
"loss": 0.2268,
"step": 2320
},
{
"epoch": 2.08,
"learning_rate": 3.9997329059829064e-05,
"loss": 0.4106,
"step": 2330
},
{
"epoch": 2.08,
"learning_rate": 3.993055555555556e-05,
"loss": 0.2388,
"step": 2340
},
{
"epoch": 2.08,
"learning_rate": 3.986378205128206e-05,
"loss": 0.085,
"step": 2350
},
{
"epoch": 2.08,
"learning_rate": 3.9797008547008545e-05,
"loss": 0.1083,
"step": 2360
},
{
"epoch": 2.08,
"learning_rate": 3.9730235042735045e-05,
"loss": 0.1683,
"step": 2370
},
{
"epoch": 2.09,
"learning_rate": 3.966346153846154e-05,
"loss": 0.0891,
"step": 2380
},
{
"epoch": 2.09,
"learning_rate": 3.959668803418803e-05,
"loss": 0.0728,
"step": 2390
},
{
"epoch": 2.09,
"learning_rate": 3.952991452991453e-05,
"loss": 0.1584,
"step": 2400
},
{
"epoch": 2.09,
"learning_rate": 3.9463141025641026e-05,
"loss": 0.2689,
"step": 2410
},
{
"epoch": 2.09,
"learning_rate": 3.939636752136752e-05,
"loss": 0.1891,
"step": 2420
},
{
"epoch": 2.09,
"learning_rate": 3.932959401709402e-05,
"loss": 0.3679,
"step": 2430
},
{
"epoch": 2.09,
"learning_rate": 3.9262820512820513e-05,
"loss": 0.1882,
"step": 2440
},
{
"epoch": 2.09,
"learning_rate": 3.919604700854701e-05,
"loss": 0.2205,
"step": 2450
},
{
"epoch": 2.1,
"learning_rate": 3.912927350427351e-05,
"loss": 0.1591,
"step": 2460
},
{
"epoch": 2.1,
"learning_rate": 3.90625e-05,
"loss": 0.1836,
"step": 2470
},
{
"epoch": 2.1,
"learning_rate": 3.89957264957265e-05,
"loss": 0.0979,
"step": 2480
},
{
"epoch": 2.1,
"learning_rate": 3.8928952991452995e-05,
"loss": 0.4519,
"step": 2490
},
{
"epoch": 2.1,
"eval_accuracy": 0.9222797927461139,
"eval_loss": 0.26454582810401917,
"eval_runtime": 85.593,
"eval_samples_per_second": 15.784,
"eval_steps_per_second": 2.64,
"step": 2499
},
{
"epoch": 3.0,
"learning_rate": 3.886217948717949e-05,
"loss": 0.2009,
"step": 2500
},
{
"epoch": 3.0,
"learning_rate": 3.879540598290599e-05,
"loss": 0.1853,
"step": 2510
},
{
"epoch": 3.0,
"learning_rate": 3.872863247863248e-05,
"loss": 0.0564,
"step": 2520
},
{
"epoch": 3.0,
"learning_rate": 3.8661858974358976e-05,
"loss": 0.2384,
"step": 2530
},
{
"epoch": 3.0,
"learning_rate": 3.8595085470085476e-05,
"loss": 0.2116,
"step": 2540
},
{
"epoch": 3.01,
"learning_rate": 3.852831196581197e-05,
"loss": 0.2025,
"step": 2550
},
{
"epoch": 3.01,
"learning_rate": 3.846153846153846e-05,
"loss": 0.453,
"step": 2560
},
{
"epoch": 3.01,
"learning_rate": 3.839476495726496e-05,
"loss": 0.1854,
"step": 2570
},
{
"epoch": 3.01,
"learning_rate": 3.832799145299146e-05,
"loss": 0.1525,
"step": 2580
},
{
"epoch": 3.01,
"learning_rate": 3.826121794871795e-05,
"loss": 0.1236,
"step": 2590
},
{
"epoch": 3.01,
"learning_rate": 3.8194444444444444e-05,
"loss": 0.1181,
"step": 2600
},
{
"epoch": 3.01,
"learning_rate": 3.812767094017094e-05,
"loss": 0.1242,
"step": 2610
},
{
"epoch": 3.01,
"learning_rate": 3.806089743589744e-05,
"loss": 0.1651,
"step": 2620
},
{
"epoch": 3.02,
"learning_rate": 3.799412393162393e-05,
"loss": 0.1342,
"step": 2630
},
{
"epoch": 3.02,
"learning_rate": 3.7927350427350425e-05,
"loss": 0.1438,
"step": 2640
},
{
"epoch": 3.02,
"learning_rate": 3.7860576923076925e-05,
"loss": 0.0986,
"step": 2650
},
{
"epoch": 3.02,
"learning_rate": 3.779380341880342e-05,
"loss": 0.1217,
"step": 2660
},
{
"epoch": 3.02,
"learning_rate": 3.772702991452992e-05,
"loss": 0.1621,
"step": 2670
},
{
"epoch": 3.02,
"learning_rate": 3.766025641025641e-05,
"loss": 0.105,
"step": 2680
},
{
"epoch": 3.02,
"learning_rate": 3.7593482905982906e-05,
"loss": 0.234,
"step": 2690
},
{
"epoch": 3.02,
"learning_rate": 3.7526709401709406e-05,
"loss": 0.2106,
"step": 2700
},
{
"epoch": 3.03,
"learning_rate": 3.74599358974359e-05,
"loss": 0.1273,
"step": 2710
},
{
"epoch": 3.03,
"learning_rate": 3.739316239316239e-05,
"loss": 0.0124,
"step": 2720
},
{
"epoch": 3.03,
"learning_rate": 3.7326388888888893e-05,
"loss": 0.045,
"step": 2730
},
{
"epoch": 3.03,
"learning_rate": 3.725961538461539e-05,
"loss": 0.1901,
"step": 2740
},
{
"epoch": 3.03,
"learning_rate": 3.719284188034188e-05,
"loss": 0.1012,
"step": 2750
},
{
"epoch": 3.03,
"learning_rate": 3.712606837606838e-05,
"loss": 0.2435,
"step": 2760
},
{
"epoch": 3.03,
"learning_rate": 3.7059294871794874e-05,
"loss": 0.0302,
"step": 2770
},
{
"epoch": 3.03,
"learning_rate": 3.699252136752137e-05,
"loss": 0.1433,
"step": 2780
},
{
"epoch": 3.03,
"learning_rate": 3.692574786324787e-05,
"loss": 0.1693,
"step": 2790
},
{
"epoch": 3.04,
"learning_rate": 3.685897435897436e-05,
"loss": 0.2665,
"step": 2800
},
{
"epoch": 3.04,
"learning_rate": 3.679220085470086e-05,
"loss": 0.2381,
"step": 2810
},
{
"epoch": 3.04,
"learning_rate": 3.6725427350427355e-05,
"loss": 0.1251,
"step": 2820
},
{
"epoch": 3.04,
"learning_rate": 3.665865384615384e-05,
"loss": 0.1623,
"step": 2830
},
{
"epoch": 3.04,
"learning_rate": 3.659188034188034e-05,
"loss": 0.139,
"step": 2840
},
{
"epoch": 3.04,
"learning_rate": 3.6525106837606836e-05,
"loss": 0.0755,
"step": 2850
},
{
"epoch": 3.04,
"learning_rate": 3.6458333333333336e-05,
"loss": 0.265,
"step": 2860
},
{
"epoch": 3.04,
"learning_rate": 3.639155982905983e-05,
"loss": 0.3092,
"step": 2870
},
{
"epoch": 3.05,
"learning_rate": 3.6324786324786323e-05,
"loss": 0.134,
"step": 2880
},
{
"epoch": 3.05,
"learning_rate": 3.6258012820512824e-05,
"loss": 0.0111,
"step": 2890
},
{
"epoch": 3.05,
"learning_rate": 3.619123931623932e-05,
"loss": 0.154,
"step": 2900
},
{
"epoch": 3.05,
"learning_rate": 3.612446581196581e-05,
"loss": 0.0385,
"step": 2910
},
{
"epoch": 3.05,
"learning_rate": 3.605769230769231e-05,
"loss": 0.1979,
"step": 2920
},
{
"epoch": 3.05,
"learning_rate": 3.5990918803418805e-05,
"loss": 0.1618,
"step": 2930
},
{
"epoch": 3.05,
"learning_rate": 3.59241452991453e-05,
"loss": 0.1044,
"step": 2940
},
{
"epoch": 3.05,
"learning_rate": 3.58573717948718e-05,
"loss": 0.1899,
"step": 2950
},
{
"epoch": 3.06,
"learning_rate": 3.579059829059829e-05,
"loss": 0.1188,
"step": 2960
},
{
"epoch": 3.06,
"learning_rate": 3.5723824786324785e-05,
"loss": 0.3025,
"step": 2970
},
{
"epoch": 3.06,
"learning_rate": 3.5657051282051286e-05,
"loss": 0.1551,
"step": 2980
},
{
"epoch": 3.06,
"learning_rate": 3.559027777777778e-05,
"loss": 0.272,
"step": 2990
},
{
"epoch": 3.06,
"learning_rate": 3.552350427350428e-05,
"loss": 0.2863,
"step": 3000
},
{
"epoch": 3.06,
"learning_rate": 3.545673076923077e-05,
"loss": 0.1508,
"step": 3010
},
{
"epoch": 3.06,
"learning_rate": 3.538995726495727e-05,
"loss": 0.3007,
"step": 3020
},
{
"epoch": 3.06,
"learning_rate": 3.532318376068377e-05,
"loss": 0.256,
"step": 3030
},
{
"epoch": 3.07,
"learning_rate": 3.525641025641026e-05,
"loss": 0.0253,
"step": 3040
},
{
"epoch": 3.07,
"learning_rate": 3.5189636752136754e-05,
"loss": 0.0563,
"step": 3050
},
{
"epoch": 3.07,
"learning_rate": 3.512286324786325e-05,
"loss": 0.2547,
"step": 3060
},
{
"epoch": 3.07,
"learning_rate": 3.505608974358974e-05,
"loss": 0.1,
"step": 3070
},
{
"epoch": 3.07,
"learning_rate": 3.498931623931624e-05,
"loss": 0.1087,
"step": 3080
},
{
"epoch": 3.07,
"learning_rate": 3.4922542735042735e-05,
"loss": 0.0982,
"step": 3090
},
{
"epoch": 3.07,
"learning_rate": 3.485576923076923e-05,
"loss": 0.0756,
"step": 3100
},
{
"epoch": 3.07,
"learning_rate": 3.478899572649573e-05,
"loss": 0.1787,
"step": 3110
},
{
"epoch": 3.07,
"learning_rate": 3.472222222222222e-05,
"loss": 0.1296,
"step": 3120
},
{
"epoch": 3.08,
"learning_rate": 3.4655448717948716e-05,
"loss": 0.1278,
"step": 3130
},
{
"epoch": 3.08,
"learning_rate": 3.4588675213675216e-05,
"loss": 0.2712,
"step": 3140
},
{
"epoch": 3.08,
"learning_rate": 3.452190170940171e-05,
"loss": 0.1053,
"step": 3150
},
{
"epoch": 3.08,
"learning_rate": 3.445512820512821e-05,
"loss": 0.0271,
"step": 3160
},
{
"epoch": 3.08,
"learning_rate": 3.43883547008547e-05,
"loss": 0.1143,
"step": 3170
},
{
"epoch": 3.08,
"learning_rate": 3.43215811965812e-05,
"loss": 0.2631,
"step": 3180
},
{
"epoch": 3.08,
"learning_rate": 3.42548076923077e-05,
"loss": 0.3132,
"step": 3190
},
{
"epoch": 3.08,
"learning_rate": 3.418803418803419e-05,
"loss": 0.3753,
"step": 3200
},
{
"epoch": 3.09,
"learning_rate": 3.4121260683760684e-05,
"loss": 0.1488,
"step": 3210
},
{
"epoch": 3.09,
"learning_rate": 3.4054487179487185e-05,
"loss": 0.1837,
"step": 3220
},
{
"epoch": 3.09,
"learning_rate": 3.398771367521368e-05,
"loss": 0.0834,
"step": 3230
},
{
"epoch": 3.09,
"learning_rate": 3.392094017094017e-05,
"loss": 0.1418,
"step": 3240
},
{
"epoch": 3.09,
"learning_rate": 3.385416666666667e-05,
"loss": 0.2449,
"step": 3250
},
{
"epoch": 3.09,
"learning_rate": 3.3787393162393165e-05,
"loss": 0.3223,
"step": 3260
},
{
"epoch": 3.09,
"learning_rate": 3.372061965811966e-05,
"loss": 0.0967,
"step": 3270
},
{
"epoch": 3.09,
"learning_rate": 3.365384615384616e-05,
"loss": 0.0662,
"step": 3280
},
{
"epoch": 3.1,
"learning_rate": 3.3587072649572646e-05,
"loss": 0.1879,
"step": 3290
},
{
"epoch": 3.1,
"learning_rate": 3.3520299145299146e-05,
"loss": 0.1226,
"step": 3300
},
{
"epoch": 3.1,
"learning_rate": 3.345352564102564e-05,
"loss": 0.1606,
"step": 3310
},
{
"epoch": 3.1,
"learning_rate": 3.338675213675213e-05,
"loss": 0.0107,
"step": 3320
},
{
"epoch": 3.1,
"learning_rate": 3.3319978632478634e-05,
"loss": 0.137,
"step": 3330
},
{
"epoch": 3.1,
"eval_accuracy": 0.9370836417468542,
"eval_loss": 0.22310341894626617,
"eval_runtime": 85.6004,
"eval_samples_per_second": 15.783,
"eval_steps_per_second": 2.64,
"step": 3332
},
{
"epoch": 4.0,
"learning_rate": 3.325320512820513e-05,
"loss": 0.247,
"step": 3340
},
{
"epoch": 4.0,
"learning_rate": 3.318643162393163e-05,
"loss": 0.0202,
"step": 3350
},
{
"epoch": 4.0,
"learning_rate": 3.311965811965812e-05,
"loss": 0.1689,
"step": 3360
},
{
"epoch": 4.0,
"learning_rate": 3.3052884615384615e-05,
"loss": 0.334,
"step": 3370
},
{
"epoch": 4.01,
"learning_rate": 3.2986111111111115e-05,
"loss": 0.1227,
"step": 3380
},
{
"epoch": 4.01,
"learning_rate": 3.291933760683761e-05,
"loss": 0.05,
"step": 3390
},
{
"epoch": 4.01,
"learning_rate": 3.28525641025641e-05,
"loss": 0.0551,
"step": 3400
},
{
"epoch": 4.01,
"learning_rate": 3.27857905982906e-05,
"loss": 0.0999,
"step": 3410
},
{
"epoch": 4.01,
"learning_rate": 3.2719017094017096e-05,
"loss": 0.1259,
"step": 3420
},
{
"epoch": 4.01,
"learning_rate": 3.265224358974359e-05,
"loss": 0.0748,
"step": 3430
},
{
"epoch": 4.01,
"learning_rate": 3.258547008547009e-05,
"loss": 0.0967,
"step": 3440
},
{
"epoch": 4.01,
"learning_rate": 3.251869658119658e-05,
"loss": 0.0372,
"step": 3450
},
{
"epoch": 4.02,
"learning_rate": 3.2451923076923077e-05,
"loss": 0.1477,
"step": 3460
},
{
"epoch": 4.02,
"learning_rate": 3.238514957264958e-05,
"loss": 0.0598,
"step": 3470
},
{
"epoch": 4.02,
"learning_rate": 3.231837606837607e-05,
"loss": 0.0092,
"step": 3480
},
{
"epoch": 4.02,
"learning_rate": 3.225160256410257e-05,
"loss": 0.0115,
"step": 3490
},
{
"epoch": 4.02,
"learning_rate": 3.2184829059829064e-05,
"loss": 0.0084,
"step": 3500
},
{
"epoch": 4.02,
"learning_rate": 3.211805555555556e-05,
"loss": 0.1052,
"step": 3510
},
{
"epoch": 4.02,
"learning_rate": 3.205128205128206e-05,
"loss": 0.0335,
"step": 3520
},
{
"epoch": 4.02,
"learning_rate": 3.1984508547008545e-05,
"loss": 0.1715,
"step": 3530
},
{
"epoch": 4.03,
"learning_rate": 3.1917735042735045e-05,
"loss": 0.0244,
"step": 3540
},
{
"epoch": 4.03,
"learning_rate": 3.185096153846154e-05,
"loss": 0.0322,
"step": 3550
},
{
"epoch": 4.03,
"learning_rate": 3.178418803418803e-05,
"loss": 0.0308,
"step": 3560
},
{
"epoch": 4.03,
"learning_rate": 3.171741452991453e-05,
"loss": 0.0982,
"step": 3570
},
{
"epoch": 4.03,
"learning_rate": 3.1650641025641026e-05,
"loss": 0.0419,
"step": 3580
},
{
"epoch": 4.03,
"learning_rate": 3.158386752136752e-05,
"loss": 0.0448,
"step": 3590
},
{
"epoch": 4.03,
"learning_rate": 3.151709401709402e-05,
"loss": 0.082,
"step": 3600
},
{
"epoch": 4.03,
"learning_rate": 3.145032051282051e-05,
"loss": 0.1413,
"step": 3610
},
{
"epoch": 4.03,
"learning_rate": 3.138354700854701e-05,
"loss": 0.0035,
"step": 3620
},
{
"epoch": 4.04,
"learning_rate": 3.131677350427351e-05,
"loss": 0.0325,
"step": 3630
},
{
"epoch": 4.04,
"learning_rate": 3.125e-05,
"loss": 0.1028,
"step": 3640
},
{
"epoch": 4.04,
"learning_rate": 3.1183226495726494e-05,
"loss": 0.0111,
"step": 3650
},
{
"epoch": 4.04,
"learning_rate": 3.1116452991452994e-05,
"loss": 0.0263,
"step": 3660
},
{
"epoch": 4.04,
"learning_rate": 3.104967948717949e-05,
"loss": 0.0666,
"step": 3670
},
{
"epoch": 4.04,
"learning_rate": 3.098290598290599e-05,
"loss": 0.0059,
"step": 3680
},
{
"epoch": 4.04,
"learning_rate": 3.091613247863248e-05,
"loss": 0.0704,
"step": 3690
},
{
"epoch": 4.04,
"learning_rate": 3.0849358974358975e-05,
"loss": 0.1522,
"step": 3700
},
{
"epoch": 4.05,
"learning_rate": 3.0782585470085476e-05,
"loss": 0.0377,
"step": 3710
},
{
"epoch": 4.05,
"learning_rate": 3.071581196581197e-05,
"loss": 0.1819,
"step": 3720
},
{
"epoch": 4.05,
"learning_rate": 3.064903846153846e-05,
"loss": 0.0209,
"step": 3730
},
{
"epoch": 4.05,
"learning_rate": 3.058226495726496e-05,
"loss": 0.0196,
"step": 3740
},
{
"epoch": 4.05,
"learning_rate": 3.0515491452991457e-05,
"loss": 0.1089,
"step": 3750
},
{
"epoch": 4.05,
"learning_rate": 3.0448717948717947e-05,
"loss": 0.3502,
"step": 3760
},
{
"epoch": 4.05,
"learning_rate": 3.0381944444444444e-05,
"loss": 0.0047,
"step": 3770
},
{
"epoch": 4.05,
"learning_rate": 3.031517094017094e-05,
"loss": 0.0927,
"step": 3780
},
{
"epoch": 4.06,
"learning_rate": 3.0248397435897434e-05,
"loss": 0.0115,
"step": 3790
},
{
"epoch": 4.06,
"learning_rate": 3.018162393162393e-05,
"loss": 0.0098,
"step": 3800
},
{
"epoch": 4.06,
"learning_rate": 3.0114850427350428e-05,
"loss": 0.2128,
"step": 3810
},
{
"epoch": 4.06,
"learning_rate": 3.0048076923076925e-05,
"loss": 0.1717,
"step": 3820
},
{
"epoch": 4.06,
"learning_rate": 2.9981303418803418e-05,
"loss": 0.0731,
"step": 3830
},
{
"epoch": 4.06,
"learning_rate": 2.9914529914529915e-05,
"loss": 0.0716,
"step": 3840
},
{
"epoch": 4.06,
"learning_rate": 2.9847756410256412e-05,
"loss": 0.0211,
"step": 3850
},
{
"epoch": 4.06,
"learning_rate": 2.9780982905982906e-05,
"loss": 0.0054,
"step": 3860
},
{
"epoch": 4.06,
"learning_rate": 2.9714209401709403e-05,
"loss": 0.2639,
"step": 3870
},
{
"epoch": 4.07,
"learning_rate": 2.96474358974359e-05,
"loss": 0.0827,
"step": 3880
},
{
"epoch": 4.07,
"learning_rate": 2.9580662393162396e-05,
"loss": 0.2148,
"step": 3890
},
{
"epoch": 4.07,
"learning_rate": 2.951388888888889e-05,
"loss": 0.007,
"step": 3900
},
{
"epoch": 4.07,
"learning_rate": 2.9447115384615387e-05,
"loss": 0.143,
"step": 3910
},
{
"epoch": 4.07,
"learning_rate": 2.9380341880341884e-05,
"loss": 0.0107,
"step": 3920
},
{
"epoch": 4.07,
"learning_rate": 2.9313568376068377e-05,
"loss": 0.0062,
"step": 3930
},
{
"epoch": 4.07,
"learning_rate": 2.9246794871794874e-05,
"loss": 0.1301,
"step": 3940
},
{
"epoch": 4.07,
"learning_rate": 2.918002136752137e-05,
"loss": 0.0108,
"step": 3950
},
{
"epoch": 4.08,
"learning_rate": 2.9113247863247868e-05,
"loss": 0.0731,
"step": 3960
},
{
"epoch": 4.08,
"learning_rate": 2.904647435897436e-05,
"loss": 0.0286,
"step": 3970
},
{
"epoch": 4.08,
"learning_rate": 2.897970085470086e-05,
"loss": 0.008,
"step": 3980
},
{
"epoch": 4.08,
"learning_rate": 2.8912927350427355e-05,
"loss": 0.0894,
"step": 3990
},
{
"epoch": 4.08,
"learning_rate": 2.8846153846153845e-05,
"loss": 0.0484,
"step": 4000
},
{
"epoch": 4.08,
"learning_rate": 2.8779380341880342e-05,
"loss": 0.1517,
"step": 4010
},
{
"epoch": 4.08,
"learning_rate": 2.8712606837606836e-05,
"loss": 0.0369,
"step": 4020
},
{
"epoch": 4.08,
"learning_rate": 2.8645833333333333e-05,
"loss": 0.1208,
"step": 4030
},
{
"epoch": 4.09,
"learning_rate": 2.857905982905983e-05,
"loss": 0.1447,
"step": 4040
},
{
"epoch": 4.09,
"learning_rate": 2.8512286324786323e-05,
"loss": 0.0959,
"step": 4050
},
{
"epoch": 4.09,
"learning_rate": 2.844551282051282e-05,
"loss": 0.021,
"step": 4060
},
{
"epoch": 4.09,
"learning_rate": 2.8378739316239317e-05,
"loss": 0.2013,
"step": 4070
},
{
"epoch": 4.09,
"learning_rate": 2.8311965811965814e-05,
"loss": 0.0673,
"step": 4080
},
{
"epoch": 4.09,
"learning_rate": 2.8245192307692307e-05,
"loss": 0.0502,
"step": 4090
},
{
"epoch": 4.09,
"learning_rate": 2.8178418803418804e-05,
"loss": 0.0796,
"step": 4100
},
{
"epoch": 4.09,
"learning_rate": 2.81116452991453e-05,
"loss": 0.3334,
"step": 4110
},
{
"epoch": 4.09,
"learning_rate": 2.8044871794871795e-05,
"loss": 0.1535,
"step": 4120
},
{
"epoch": 4.1,
"learning_rate": 2.7978098290598292e-05,
"loss": 0.1823,
"step": 4130
},
{
"epoch": 4.1,
"learning_rate": 2.791132478632479e-05,
"loss": 0.0254,
"step": 4140
},
{
"epoch": 4.1,
"learning_rate": 2.7844551282051286e-05,
"loss": 0.125,
"step": 4150
},
{
"epoch": 4.1,
"learning_rate": 2.777777777777778e-05,
"loss": 0.1014,
"step": 4160
},
{
"epoch": 4.1,
"eval_accuracy": 0.9592894152479645,
"eval_loss": 0.15163935720920563,
"eval_runtime": 85.5792,
"eval_samples_per_second": 15.787,
"eval_steps_per_second": 2.641,
"step": 4165
},
{
"epoch": 5.0,
"learning_rate": 2.7711004273504276e-05,
"loss": 0.2326,
"step": 4170
},
{
"epoch": 5.0,
"learning_rate": 2.7644230769230773e-05,
"loss": 0.07,
"step": 4180
},
{
"epoch": 5.0,
"learning_rate": 2.757745726495727e-05,
"loss": 0.0832,
"step": 4190
},
{
"epoch": 5.0,
"learning_rate": 2.7510683760683763e-05,
"loss": 0.1114,
"step": 4200
},
{
"epoch": 5.01,
"learning_rate": 2.744391025641026e-05,
"loss": 0.0198,
"step": 4210
},
{
"epoch": 5.01,
"learning_rate": 2.7377136752136757e-05,
"loss": 0.0039,
"step": 4220
},
{
"epoch": 5.01,
"learning_rate": 2.7310363247863247e-05,
"loss": 0.2082,
"step": 4230
},
{
"epoch": 5.01,
"learning_rate": 2.724358974358974e-05,
"loss": 0.1341,
"step": 4240
},
{
"epoch": 5.01,
"learning_rate": 2.7176816239316238e-05,
"loss": 0.1808,
"step": 4250
},
{
"epoch": 5.01,
"learning_rate": 2.7110042735042735e-05,
"loss": 0.1818,
"step": 4260
},
{
"epoch": 5.01,
"learning_rate": 2.704326923076923e-05,
"loss": 0.019,
"step": 4270
},
{
"epoch": 5.01,
"learning_rate": 2.6976495726495725e-05,
"loss": 0.005,
"step": 4280
},
{
"epoch": 5.02,
"learning_rate": 2.6909722222222222e-05,
"loss": 0.0053,
"step": 4290
},
{
"epoch": 5.02,
"learning_rate": 2.684294871794872e-05,
"loss": 0.0751,
"step": 4300
},
{
"epoch": 5.02,
"learning_rate": 2.6776175213675216e-05,
"loss": 0.2481,
"step": 4310
},
{
"epoch": 5.02,
"learning_rate": 2.670940170940171e-05,
"loss": 0.0346,
"step": 4320
},
{
"epoch": 5.02,
"learning_rate": 2.6642628205128206e-05,
"loss": 0.1085,
"step": 4330
},
{
"epoch": 5.02,
"learning_rate": 2.6575854700854703e-05,
"loss": 0.2827,
"step": 4340
},
{
"epoch": 5.02,
"learning_rate": 2.6509081196581197e-05,
"loss": 0.2162,
"step": 4350
},
{
"epoch": 5.02,
"learning_rate": 2.6442307692307694e-05,
"loss": 0.1607,
"step": 4360
},
{
"epoch": 5.02,
"learning_rate": 2.637553418803419e-05,
"loss": 0.0169,
"step": 4370
},
{
"epoch": 5.03,
"learning_rate": 2.6308760683760687e-05,
"loss": 0.0122,
"step": 4380
},
{
"epoch": 5.03,
"learning_rate": 2.624198717948718e-05,
"loss": 0.1715,
"step": 4390
},
{
"epoch": 5.03,
"learning_rate": 2.6175213675213678e-05,
"loss": 0.0114,
"step": 4400
},
{
"epoch": 5.03,
"learning_rate": 2.6108440170940175e-05,
"loss": 0.0156,
"step": 4410
},
{
"epoch": 5.03,
"learning_rate": 2.604166666666667e-05,
"loss": 0.0948,
"step": 4420
},
{
"epoch": 5.03,
"learning_rate": 2.5974893162393165e-05,
"loss": 0.1142,
"step": 4430
},
{
"epoch": 5.03,
"learning_rate": 2.5908119658119662e-05,
"loss": 0.0091,
"step": 4440
},
{
"epoch": 5.03,
"learning_rate": 2.584134615384616e-05,
"loss": 0.0021,
"step": 4450
},
{
"epoch": 5.04,
"learning_rate": 2.577457264957265e-05,
"loss": 0.0513,
"step": 4460
},
{
"epoch": 5.04,
"learning_rate": 2.5707799145299143e-05,
"loss": 0.002,
"step": 4470
},
{
"epoch": 5.04,
"learning_rate": 2.564102564102564e-05,
"loss": 0.0016,
"step": 4480
},
{
"epoch": 5.04,
"learning_rate": 2.5574252136752137e-05,
"loss": 0.062,
"step": 4490
},
{
"epoch": 5.04,
"learning_rate": 2.5507478632478633e-05,
"loss": 0.0168,
"step": 4500
},
{
"epoch": 5.04,
"learning_rate": 2.5440705128205127e-05,
"loss": 0.1189,
"step": 4510
},
{
"epoch": 5.04,
"learning_rate": 2.5373931623931624e-05,
"loss": 0.0289,
"step": 4520
},
{
"epoch": 5.04,
"learning_rate": 2.530715811965812e-05,
"loss": 0.0263,
"step": 4530
},
{
"epoch": 5.05,
"learning_rate": 2.5240384615384614e-05,
"loss": 0.022,
"step": 4540
},
{
"epoch": 5.05,
"learning_rate": 2.517361111111111e-05,
"loss": 0.1551,
"step": 4550
},
{
"epoch": 5.05,
"learning_rate": 2.5106837606837608e-05,
"loss": 0.1103,
"step": 4560
},
{
"epoch": 5.05,
"learning_rate": 2.5040064102564105e-05,
"loss": 0.1434,
"step": 4570
},
{
"epoch": 5.05,
"learning_rate": 2.49732905982906e-05,
"loss": 0.2635,
"step": 4580
},
{
"epoch": 5.05,
"learning_rate": 2.4906517094017096e-05,
"loss": 0.0956,
"step": 4590
},
{
"epoch": 5.05,
"learning_rate": 2.4839743589743592e-05,
"loss": 0.0518,
"step": 4600
},
{
"epoch": 5.05,
"learning_rate": 2.4772970085470086e-05,
"loss": 0.1728,
"step": 4610
},
{
"epoch": 5.05,
"learning_rate": 2.4706196581196583e-05,
"loss": 0.0058,
"step": 4620
},
{
"epoch": 5.06,
"learning_rate": 2.463942307692308e-05,
"loss": 0.1515,
"step": 4630
},
{
"epoch": 5.06,
"learning_rate": 2.4572649572649573e-05,
"loss": 0.0366,
"step": 4640
},
{
"epoch": 5.06,
"learning_rate": 2.450587606837607e-05,
"loss": 0.003,
"step": 4650
},
{
"epoch": 5.06,
"learning_rate": 2.4439102564102564e-05,
"loss": 0.0561,
"step": 4660
},
{
"epoch": 5.06,
"learning_rate": 2.437232905982906e-05,
"loss": 0.0039,
"step": 4670
},
{
"epoch": 5.06,
"learning_rate": 2.4305555555555558e-05,
"loss": 0.0052,
"step": 4680
},
{
"epoch": 5.06,
"learning_rate": 2.423878205128205e-05,
"loss": 0.0821,
"step": 4690
},
{
"epoch": 5.06,
"learning_rate": 2.4172008547008548e-05,
"loss": 0.0126,
"step": 4700
},
{
"epoch": 5.07,
"learning_rate": 2.4105235042735045e-05,
"loss": 0.0093,
"step": 4710
},
{
"epoch": 5.07,
"learning_rate": 2.4038461538461542e-05,
"loss": 0.2059,
"step": 4720
},
{
"epoch": 5.07,
"learning_rate": 2.3971688034188035e-05,
"loss": 0.0528,
"step": 4730
},
{
"epoch": 5.07,
"learning_rate": 2.3904914529914532e-05,
"loss": 0.0022,
"step": 4740
},
{
"epoch": 5.07,
"learning_rate": 2.383814102564103e-05,
"loss": 0.0969,
"step": 4750
},
{
"epoch": 5.07,
"learning_rate": 2.3771367521367523e-05,
"loss": 0.0024,
"step": 4760
},
{
"epoch": 5.07,
"learning_rate": 2.3704594017094016e-05,
"loss": 0.0674,
"step": 4770
},
{
"epoch": 5.07,
"learning_rate": 2.3637820512820513e-05,
"loss": 0.007,
"step": 4780
},
{
"epoch": 5.08,
"learning_rate": 2.357104700854701e-05,
"loss": 0.0121,
"step": 4790
},
{
"epoch": 5.08,
"learning_rate": 2.3504273504273504e-05,
"loss": 0.1585,
"step": 4800
},
{
"epoch": 5.08,
"learning_rate": 2.34375e-05,
"loss": 0.1726,
"step": 4810
},
{
"epoch": 5.08,
"learning_rate": 2.3370726495726497e-05,
"loss": 0.0053,
"step": 4820
},
{
"epoch": 5.08,
"learning_rate": 2.3303952991452994e-05,
"loss": 0.0597,
"step": 4830
},
{
"epoch": 5.08,
"learning_rate": 2.3237179487179488e-05,
"loss": 0.0105,
"step": 4840
},
{
"epoch": 5.08,
"learning_rate": 2.3170405982905985e-05,
"loss": 0.002,
"step": 4850
},
{
"epoch": 5.08,
"learning_rate": 2.310363247863248e-05,
"loss": 0.0019,
"step": 4860
},
{
"epoch": 5.08,
"learning_rate": 2.3036858974358975e-05,
"loss": 0.2447,
"step": 4870
},
{
"epoch": 5.09,
"learning_rate": 2.297008547008547e-05,
"loss": 0.0584,
"step": 4880
},
{
"epoch": 5.09,
"learning_rate": 2.2903311965811966e-05,
"loss": 0.0955,
"step": 4890
},
{
"epoch": 5.09,
"learning_rate": 2.2836538461538463e-05,
"loss": 0.0293,
"step": 4900
},
{
"epoch": 5.09,
"learning_rate": 2.276976495726496e-05,
"loss": 0.0053,
"step": 4910
},
{
"epoch": 5.09,
"learning_rate": 2.2702991452991453e-05,
"loss": 0.0666,
"step": 4920
},
{
"epoch": 5.09,
"learning_rate": 2.263621794871795e-05,
"loss": 0.0213,
"step": 4930
},
{
"epoch": 5.09,
"learning_rate": 2.2569444444444447e-05,
"loss": 0.0668,
"step": 4940
},
{
"epoch": 5.09,
"learning_rate": 2.250267094017094e-05,
"loss": 0.0146,
"step": 4950
},
{
"epoch": 5.1,
"learning_rate": 2.2435897435897437e-05,
"loss": 0.0046,
"step": 4960
},
{
"epoch": 5.1,
"learning_rate": 2.2369123931623934e-05,
"loss": 0.0884,
"step": 4970
},
{
"epoch": 5.1,
"learning_rate": 2.230235042735043e-05,
"loss": 0.0072,
"step": 4980
},
{
"epoch": 5.1,
"learning_rate": 2.223557692307692e-05,
"loss": 0.0084,
"step": 4990
},
{
"epoch": 5.1,
"eval_accuracy": 0.9681717246484086,
"eval_loss": 0.147811621427536,
"eval_runtime": 85.8137,
"eval_samples_per_second": 15.743,
"eval_steps_per_second": 2.634,
"step": 4998
},
{
"epoch": 6.0,
"learning_rate": 2.2168803418803418e-05,
"loss": 0.1845,
"step": 5000
},
{
"epoch": 6.0,
"learning_rate": 2.2102029914529915e-05,
"loss": 0.0636,
"step": 5010
},
{
"epoch": 6.0,
"learning_rate": 2.2035256410256412e-05,
"loss": 0.0051,
"step": 5020
},
{
"epoch": 6.0,
"learning_rate": 2.1968482905982905e-05,
"loss": 0.0027,
"step": 5030
},
{
"epoch": 6.01,
"learning_rate": 2.1901709401709402e-05,
"loss": 0.0974,
"step": 5040
},
{
"epoch": 6.01,
"learning_rate": 2.18349358974359e-05,
"loss": 0.0281,
"step": 5050
},
{
"epoch": 6.01,
"learning_rate": 2.1768162393162396e-05,
"loss": 0.1491,
"step": 5060
},
{
"epoch": 6.01,
"learning_rate": 2.170138888888889e-05,
"loss": 0.0247,
"step": 5070
},
{
"epoch": 6.01,
"learning_rate": 2.1634615384615387e-05,
"loss": 0.0898,
"step": 5080
},
{
"epoch": 6.01,
"learning_rate": 2.1567841880341884e-05,
"loss": 0.0053,
"step": 5090
},
{
"epoch": 6.01,
"learning_rate": 2.1501068376068377e-05,
"loss": 0.0295,
"step": 5100
},
{
"epoch": 6.01,
"learning_rate": 2.143429487179487e-05,
"loss": 0.0022,
"step": 5110
},
{
"epoch": 6.01,
"learning_rate": 2.1367521367521368e-05,
"loss": 0.0016,
"step": 5120
},
{
"epoch": 6.02,
"learning_rate": 2.1300747863247864e-05,
"loss": 0.0012,
"step": 5130
},
{
"epoch": 6.02,
"learning_rate": 2.1233974358974358e-05,
"loss": 0.003,
"step": 5140
},
{
"epoch": 6.02,
"learning_rate": 2.1167200854700855e-05,
"loss": 0.0022,
"step": 5150
},
{
"epoch": 6.02,
"learning_rate": 2.1100427350427352e-05,
"loss": 0.0743,
"step": 5160
},
{
"epoch": 6.02,
"learning_rate": 2.103365384615385e-05,
"loss": 0.0254,
"step": 5170
},
{
"epoch": 6.02,
"learning_rate": 2.0966880341880342e-05,
"loss": 0.1902,
"step": 5180
},
{
"epoch": 6.02,
"learning_rate": 2.090010683760684e-05,
"loss": 0.0027,
"step": 5190
},
{
"epoch": 6.02,
"learning_rate": 2.0833333333333336e-05,
"loss": 0.0041,
"step": 5200
},
{
"epoch": 6.03,
"learning_rate": 2.076655982905983e-05,
"loss": 0.1141,
"step": 5210
},
{
"epoch": 6.03,
"learning_rate": 2.0699786324786323e-05,
"loss": 0.0124,
"step": 5220
},
{
"epoch": 6.03,
"learning_rate": 2.063301282051282e-05,
"loss": 0.0542,
"step": 5230
},
{
"epoch": 6.03,
"learning_rate": 2.0566239316239317e-05,
"loss": 0.0032,
"step": 5240
},
{
"epoch": 6.03,
"learning_rate": 2.0499465811965814e-05,
"loss": 0.1405,
"step": 5250
},
{
"epoch": 6.03,
"learning_rate": 2.0432692307692307e-05,
"loss": 0.1003,
"step": 5260
},
{
"epoch": 6.03,
"learning_rate": 2.0365918803418804e-05,
"loss": 0.0025,
"step": 5270
},
{
"epoch": 6.03,
"learning_rate": 2.02991452991453e-05,
"loss": 0.2127,
"step": 5280
},
{
"epoch": 6.04,
"learning_rate": 2.0232371794871795e-05,
"loss": 0.0047,
"step": 5290
},
{
"epoch": 6.04,
"learning_rate": 2.016559829059829e-05,
"loss": 0.0746,
"step": 5300
},
{
"epoch": 6.04,
"learning_rate": 2.009882478632479e-05,
"loss": 0.0381,
"step": 5310
},
{
"epoch": 6.04,
"learning_rate": 2.0032051282051285e-05,
"loss": 0.0017,
"step": 5320
},
{
"epoch": 6.04,
"learning_rate": 1.996527777777778e-05,
"loss": 0.0261,
"step": 5330
},
{
"epoch": 6.04,
"learning_rate": 1.9898504273504272e-05,
"loss": 0.0052,
"step": 5340
},
{
"epoch": 6.04,
"learning_rate": 1.983173076923077e-05,
"loss": 0.0011,
"step": 5350
},
{
"epoch": 6.04,
"learning_rate": 1.9764957264957266e-05,
"loss": 0.1598,
"step": 5360
},
{
"epoch": 6.04,
"learning_rate": 1.969818376068376e-05,
"loss": 0.0089,
"step": 5370
},
{
"epoch": 6.05,
"learning_rate": 1.9631410256410257e-05,
"loss": 0.0011,
"step": 5380
},
{
"epoch": 6.05,
"learning_rate": 1.9564636752136754e-05,
"loss": 0.0036,
"step": 5390
},
{
"epoch": 6.05,
"learning_rate": 1.949786324786325e-05,
"loss": 0.0014,
"step": 5400
},
{
"epoch": 6.05,
"learning_rate": 1.9431089743589744e-05,
"loss": 0.0031,
"step": 5410
},
{
"epoch": 6.05,
"learning_rate": 1.936431623931624e-05,
"loss": 0.1976,
"step": 5420
},
{
"epoch": 6.05,
"learning_rate": 1.9297542735042738e-05,
"loss": 0.0014,
"step": 5430
},
{
"epoch": 6.05,
"learning_rate": 1.923076923076923e-05,
"loss": 0.0037,
"step": 5440
},
{
"epoch": 6.05,
"learning_rate": 1.916399572649573e-05,
"loss": 0.0055,
"step": 5450
},
{
"epoch": 6.06,
"learning_rate": 1.9097222222222222e-05,
"loss": 0.1296,
"step": 5460
},
{
"epoch": 6.06,
"learning_rate": 1.903044871794872e-05,
"loss": 0.003,
"step": 5470
},
{
"epoch": 6.06,
"learning_rate": 1.8963675213675212e-05,
"loss": 0.0843,
"step": 5480
},
{
"epoch": 6.06,
"learning_rate": 1.889690170940171e-05,
"loss": 0.2126,
"step": 5490
},
{
"epoch": 6.06,
"learning_rate": 1.8830128205128206e-05,
"loss": 0.0305,
"step": 5500
},
{
"epoch": 6.06,
"learning_rate": 1.8763354700854703e-05,
"loss": 0.0941,
"step": 5510
},
{
"epoch": 6.06,
"learning_rate": 1.8696581196581197e-05,
"loss": 0.0868,
"step": 5520
},
{
"epoch": 6.06,
"learning_rate": 1.8629807692307693e-05,
"loss": 0.0875,
"step": 5530
},
{
"epoch": 6.07,
"learning_rate": 1.856303418803419e-05,
"loss": 0.0053,
"step": 5540
},
{
"epoch": 6.07,
"learning_rate": 1.8496260683760684e-05,
"loss": 0.0012,
"step": 5550
},
{
"epoch": 6.07,
"learning_rate": 1.842948717948718e-05,
"loss": 0.0017,
"step": 5560
},
{
"epoch": 6.07,
"learning_rate": 1.8362713675213678e-05,
"loss": 0.0043,
"step": 5570
},
{
"epoch": 6.07,
"learning_rate": 1.829594017094017e-05,
"loss": 0.1032,
"step": 5580
},
{
"epoch": 6.07,
"learning_rate": 1.8229166666666668e-05,
"loss": 0.0109,
"step": 5590
},
{
"epoch": 6.07,
"learning_rate": 1.8162393162393162e-05,
"loss": 0.0018,
"step": 5600
},
{
"epoch": 6.07,
"learning_rate": 1.809561965811966e-05,
"loss": 0.0017,
"step": 5610
},
{
"epoch": 6.07,
"learning_rate": 1.8028846153846156e-05,
"loss": 0.0011,
"step": 5620
},
{
"epoch": 6.08,
"learning_rate": 1.796207264957265e-05,
"loss": 0.1335,
"step": 5630
},
{
"epoch": 6.08,
"learning_rate": 1.7895299145299146e-05,
"loss": 0.0011,
"step": 5640
},
{
"epoch": 6.08,
"learning_rate": 1.7828525641025643e-05,
"loss": 0.0019,
"step": 5650
},
{
"epoch": 6.08,
"learning_rate": 1.776175213675214e-05,
"loss": 0.0012,
"step": 5660
},
{
"epoch": 6.08,
"learning_rate": 1.7694978632478633e-05,
"loss": 0.0063,
"step": 5670
},
{
"epoch": 6.08,
"learning_rate": 1.762820512820513e-05,
"loss": 0.0036,
"step": 5680
},
{
"epoch": 6.08,
"learning_rate": 1.7561431623931624e-05,
"loss": 0.0293,
"step": 5690
},
{
"epoch": 6.08,
"learning_rate": 1.749465811965812e-05,
"loss": 0.1403,
"step": 5700
},
{
"epoch": 6.09,
"learning_rate": 1.7427884615384614e-05,
"loss": 0.0012,
"step": 5710
},
{
"epoch": 6.09,
"learning_rate": 1.736111111111111e-05,
"loss": 0.1275,
"step": 5720
},
{
"epoch": 6.09,
"learning_rate": 1.7294337606837608e-05,
"loss": 0.0219,
"step": 5730
},
{
"epoch": 6.09,
"learning_rate": 1.7227564102564105e-05,
"loss": 0.0883,
"step": 5740
},
{
"epoch": 6.09,
"learning_rate": 1.71607905982906e-05,
"loss": 0.003,
"step": 5750
},
{
"epoch": 6.09,
"learning_rate": 1.7094017094017095e-05,
"loss": 0.1378,
"step": 5760
},
{
"epoch": 6.09,
"learning_rate": 1.7027243589743592e-05,
"loss": 0.344,
"step": 5770
},
{
"epoch": 6.09,
"learning_rate": 1.6960470085470086e-05,
"loss": 0.0294,
"step": 5780
},
{
"epoch": 6.1,
"learning_rate": 1.6893696581196583e-05,
"loss": 0.0099,
"step": 5790
},
{
"epoch": 6.1,
"learning_rate": 1.682692307692308e-05,
"loss": 0.3121,
"step": 5800
},
{
"epoch": 6.1,
"learning_rate": 1.6760149572649573e-05,
"loss": 0.0649,
"step": 5810
},
{
"epoch": 6.1,
"learning_rate": 1.6693376068376067e-05,
"loss": 0.1054,
"step": 5820
},
{
"epoch": 6.1,
"learning_rate": 1.6626602564102564e-05,
"loss": 0.0041,
"step": 5830
},
{
"epoch": 6.1,
"eval_accuracy": 0.9652109548482606,
"eval_loss": 0.12842880189418793,
"eval_runtime": 86.1673,
"eval_samples_per_second": 15.679,
"eval_steps_per_second": 2.623,
"step": 5831
},
{
"epoch": 7.0,
"learning_rate": 1.655982905982906e-05,
"loss": 0.0289,
"step": 5840
},
{
"epoch": 7.0,
"learning_rate": 1.6493055555555557e-05,
"loss": 0.0019,
"step": 5850
},
{
"epoch": 7.0,
"learning_rate": 1.642628205128205e-05,
"loss": 0.013,
"step": 5860
},
{
"epoch": 7.0,
"learning_rate": 1.6359508547008548e-05,
"loss": 0.0072,
"step": 5870
},
{
"epoch": 7.01,
"learning_rate": 1.6292735042735045e-05,
"loss": 0.0014,
"step": 5880
},
{
"epoch": 7.01,
"learning_rate": 1.6225961538461538e-05,
"loss": 0.0454,
"step": 5890
},
{
"epoch": 7.01,
"learning_rate": 1.6159188034188035e-05,
"loss": 0.007,
"step": 5900
},
{
"epoch": 7.01,
"learning_rate": 1.6092414529914532e-05,
"loss": 0.087,
"step": 5910
},
{
"epoch": 7.01,
"learning_rate": 1.602564102564103e-05,
"loss": 0.0044,
"step": 5920
},
{
"epoch": 7.01,
"learning_rate": 1.5958867521367523e-05,
"loss": 0.0058,
"step": 5930
},
{
"epoch": 7.01,
"learning_rate": 1.5892094017094016e-05,
"loss": 0.0405,
"step": 5940
},
{
"epoch": 7.01,
"learning_rate": 1.5825320512820513e-05,
"loss": 0.0724,
"step": 5950
},
{
"epoch": 7.02,
"learning_rate": 1.575854700854701e-05,
"loss": 0.0014,
"step": 5960
},
{
"epoch": 7.02,
"learning_rate": 1.5691773504273503e-05,
"loss": 0.0546,
"step": 5970
},
{
"epoch": 7.02,
"learning_rate": 1.5625e-05,
"loss": 0.0016,
"step": 5980
},
{
"epoch": 7.02,
"learning_rate": 1.5558226495726497e-05,
"loss": 0.0296,
"step": 5990
},
{
"epoch": 7.02,
"learning_rate": 1.5491452991452994e-05,
"loss": 0.0905,
"step": 6000
},
{
"epoch": 7.02,
"learning_rate": 1.5424679487179488e-05,
"loss": 0.0015,
"step": 6010
},
{
"epoch": 7.02,
"learning_rate": 1.5357905982905985e-05,
"loss": 0.057,
"step": 6020
},
{
"epoch": 7.02,
"learning_rate": 1.529113247863248e-05,
"loss": 0.1189,
"step": 6030
},
{
"epoch": 7.03,
"learning_rate": 1.5224358974358973e-05,
"loss": 0.0133,
"step": 6040
},
{
"epoch": 7.03,
"learning_rate": 1.515758547008547e-05,
"loss": 0.001,
"step": 6050
},
{
"epoch": 7.03,
"learning_rate": 1.5090811965811965e-05,
"loss": 0.0947,
"step": 6060
},
{
"epoch": 7.03,
"learning_rate": 1.5024038461538462e-05,
"loss": 0.0056,
"step": 6070
},
{
"epoch": 7.03,
"learning_rate": 1.4957264957264958e-05,
"loss": 0.0015,
"step": 6080
},
{
"epoch": 7.03,
"learning_rate": 1.4890491452991453e-05,
"loss": 0.11,
"step": 6090
},
{
"epoch": 7.03,
"learning_rate": 1.482371794871795e-05,
"loss": 0.1273,
"step": 6100
},
{
"epoch": 7.03,
"learning_rate": 1.4756944444444445e-05,
"loss": 0.1319,
"step": 6110
},
{
"epoch": 7.03,
"learning_rate": 1.4690170940170942e-05,
"loss": 0.0055,
"step": 6120
},
{
"epoch": 7.04,
"learning_rate": 1.4623397435897437e-05,
"loss": 0.001,
"step": 6130
},
{
"epoch": 7.04,
"learning_rate": 1.4556623931623934e-05,
"loss": 0.002,
"step": 6140
},
{
"epoch": 7.04,
"learning_rate": 1.448985042735043e-05,
"loss": 0.0008,
"step": 6150
},
{
"epoch": 7.04,
"learning_rate": 1.4423076923076923e-05,
"loss": 0.0841,
"step": 6160
},
{
"epoch": 7.04,
"learning_rate": 1.4356303418803418e-05,
"loss": 0.001,
"step": 6170
},
{
"epoch": 7.04,
"learning_rate": 1.4289529914529915e-05,
"loss": 0.0016,
"step": 6180
},
{
"epoch": 7.04,
"learning_rate": 1.422275641025641e-05,
"loss": 0.0305,
"step": 6190
},
{
"epoch": 7.04,
"learning_rate": 1.4155982905982907e-05,
"loss": 0.0007,
"step": 6200
},
{
"epoch": 7.05,
"learning_rate": 1.4089209401709402e-05,
"loss": 0.0857,
"step": 6210
},
{
"epoch": 7.05,
"learning_rate": 1.4022435897435897e-05,
"loss": 0.004,
"step": 6220
},
{
"epoch": 7.05,
"learning_rate": 1.3955662393162394e-05,
"loss": 0.001,
"step": 6230
},
{
"epoch": 7.05,
"learning_rate": 1.388888888888889e-05,
"loss": 0.0008,
"step": 6240
},
{
"epoch": 7.05,
"learning_rate": 1.3822115384615386e-05,
"loss": 0.0025,
"step": 6250
},
{
"epoch": 7.05,
"learning_rate": 1.3755341880341882e-05,
"loss": 0.003,
"step": 6260
},
{
"epoch": 7.05,
"learning_rate": 1.3688568376068379e-05,
"loss": 0.0075,
"step": 6270
},
{
"epoch": 7.05,
"learning_rate": 1.362179487179487e-05,
"loss": 0.0183,
"step": 6280
},
{
"epoch": 7.06,
"learning_rate": 1.3555021367521367e-05,
"loss": 0.066,
"step": 6290
},
{
"epoch": 7.06,
"learning_rate": 1.3488247863247863e-05,
"loss": 0.0021,
"step": 6300
},
{
"epoch": 7.06,
"learning_rate": 1.342147435897436e-05,
"loss": 0.0009,
"step": 6310
},
{
"epoch": 7.06,
"learning_rate": 1.3354700854700855e-05,
"loss": 0.0016,
"step": 6320
},
{
"epoch": 7.06,
"learning_rate": 1.3287927350427352e-05,
"loss": 0.0017,
"step": 6330
},
{
"epoch": 7.06,
"learning_rate": 1.3221153846153847e-05,
"loss": 0.0045,
"step": 6340
},
{
"epoch": 7.06,
"learning_rate": 1.3154380341880344e-05,
"loss": 0.0012,
"step": 6350
},
{
"epoch": 7.06,
"learning_rate": 1.3087606837606839e-05,
"loss": 0.0057,
"step": 6360
},
{
"epoch": 7.06,
"learning_rate": 1.3020833333333334e-05,
"loss": 0.0008,
"step": 6370
},
{
"epoch": 7.07,
"learning_rate": 1.2954059829059831e-05,
"loss": 0.0183,
"step": 6380
},
{
"epoch": 7.07,
"learning_rate": 1.2887286324786325e-05,
"loss": 0.0011,
"step": 6390
},
{
"epoch": 7.07,
"learning_rate": 1.282051282051282e-05,
"loss": 0.0027,
"step": 6400
},
{
"epoch": 7.07,
"learning_rate": 1.2753739316239317e-05,
"loss": 0.0384,
"step": 6410
},
{
"epoch": 7.07,
"learning_rate": 1.2686965811965812e-05,
"loss": 0.0027,
"step": 6420
},
{
"epoch": 7.07,
"learning_rate": 1.2620192307692307e-05,
"loss": 0.001,
"step": 6430
},
{
"epoch": 7.07,
"learning_rate": 1.2553418803418804e-05,
"loss": 0.0296,
"step": 6440
},
{
"epoch": 7.07,
"learning_rate": 1.24866452991453e-05,
"loss": 0.0008,
"step": 6450
},
{
"epoch": 7.08,
"learning_rate": 1.2419871794871796e-05,
"loss": 0.1594,
"step": 6460
},
{
"epoch": 7.08,
"learning_rate": 1.2353098290598291e-05,
"loss": 0.0579,
"step": 6470
},
{
"epoch": 7.08,
"learning_rate": 1.2286324786324787e-05,
"loss": 0.001,
"step": 6480
},
{
"epoch": 7.08,
"learning_rate": 1.2219551282051282e-05,
"loss": 0.0251,
"step": 6490
},
{
"epoch": 7.08,
"learning_rate": 1.2152777777777779e-05,
"loss": 0.1325,
"step": 6500
},
{
"epoch": 7.08,
"learning_rate": 1.2086004273504274e-05,
"loss": 0.0598,
"step": 6510
},
{
"epoch": 7.08,
"learning_rate": 1.2019230769230771e-05,
"loss": 0.0009,
"step": 6520
},
{
"epoch": 7.08,
"learning_rate": 1.1952457264957266e-05,
"loss": 0.0392,
"step": 6530
},
{
"epoch": 7.09,
"learning_rate": 1.1885683760683761e-05,
"loss": 0.0009,
"step": 6540
},
{
"epoch": 7.09,
"learning_rate": 1.1818910256410257e-05,
"loss": 0.1047,
"step": 6550
},
{
"epoch": 7.09,
"learning_rate": 1.1752136752136752e-05,
"loss": 0.0196,
"step": 6560
},
{
"epoch": 7.09,
"learning_rate": 1.1685363247863249e-05,
"loss": 0.0022,
"step": 6570
},
{
"epoch": 7.09,
"learning_rate": 1.1618589743589744e-05,
"loss": 0.0411,
"step": 6580
},
{
"epoch": 7.09,
"learning_rate": 1.155181623931624e-05,
"loss": 0.0023,
"step": 6590
},
{
"epoch": 7.09,
"learning_rate": 1.1485042735042734e-05,
"loss": 0.0009,
"step": 6600
},
{
"epoch": 7.09,
"learning_rate": 1.1418269230769231e-05,
"loss": 0.0007,
"step": 6610
},
{
"epoch": 7.09,
"learning_rate": 1.1351495726495726e-05,
"loss": 0.0008,
"step": 6620
},
{
"epoch": 7.1,
"learning_rate": 1.1284722222222223e-05,
"loss": 0.0008,
"step": 6630
},
{
"epoch": 7.1,
"learning_rate": 1.1217948717948719e-05,
"loss": 0.0012,
"step": 6640
},
{
"epoch": 7.1,
"learning_rate": 1.1151175213675216e-05,
"loss": 0.1342,
"step": 6650
},
{
"epoch": 7.1,
"learning_rate": 1.1084401709401709e-05,
"loss": 0.006,
"step": 6660
},
{
"epoch": 7.1,
"eval_accuracy": 0.9726128793486306,
"eval_loss": 0.12144625186920166,
"eval_runtime": 86.0938,
"eval_samples_per_second": 15.692,
"eval_steps_per_second": 2.625,
"step": 6664
},
{
"epoch": 8.0,
"learning_rate": 1.1017628205128206e-05,
"loss": 0.002,
"step": 6670
},
{
"epoch": 8.0,
"learning_rate": 1.0950854700854701e-05,
"loss": 0.0011,
"step": 6680
},
{
"epoch": 8.0,
"learning_rate": 1.0884081196581198e-05,
"loss": 0.0076,
"step": 6690
},
{
"epoch": 8.0,
"learning_rate": 1.0817307692307693e-05,
"loss": 0.0339,
"step": 6700
},
{
"epoch": 8.01,
"learning_rate": 1.0750534188034189e-05,
"loss": 0.0542,
"step": 6710
},
{
"epoch": 8.01,
"learning_rate": 1.0683760683760684e-05,
"loss": 0.0536,
"step": 6720
},
{
"epoch": 8.01,
"learning_rate": 1.0616987179487179e-05,
"loss": 0.0007,
"step": 6730
},
{
"epoch": 8.01,
"learning_rate": 1.0550213675213676e-05,
"loss": 0.001,
"step": 6740
},
{
"epoch": 8.01,
"learning_rate": 1.0483440170940171e-05,
"loss": 0.0227,
"step": 6750
},
{
"epoch": 8.01,
"learning_rate": 1.0416666666666668e-05,
"loss": 0.0667,
"step": 6760
},
{
"epoch": 8.01,
"learning_rate": 1.0349893162393162e-05,
"loss": 0.0143,
"step": 6770
},
{
"epoch": 8.01,
"learning_rate": 1.0283119658119658e-05,
"loss": 0.0007,
"step": 6780
},
{
"epoch": 8.02,
"learning_rate": 1.0216346153846154e-05,
"loss": 0.0007,
"step": 6790
},
{
"epoch": 8.02,
"learning_rate": 1.014957264957265e-05,
"loss": 0.0008,
"step": 6800
},
{
"epoch": 8.02,
"learning_rate": 1.0082799145299146e-05,
"loss": 0.0013,
"step": 6810
},
{
"epoch": 8.02,
"learning_rate": 1.0016025641025643e-05,
"loss": 0.1765,
"step": 6820
},
{
"epoch": 8.02,
"learning_rate": 9.949252136752136e-06,
"loss": 0.0007,
"step": 6830
},
{
"epoch": 8.02,
"learning_rate": 9.882478632478633e-06,
"loss": 0.0031,
"step": 6840
},
{
"epoch": 8.02,
"learning_rate": 9.815705128205128e-06,
"loss": 0.0006,
"step": 6850
},
{
"epoch": 8.02,
"learning_rate": 9.748931623931625e-06,
"loss": 0.0021,
"step": 6860
},
{
"epoch": 8.02,
"learning_rate": 9.68215811965812e-06,
"loss": 0.0503,
"step": 6870
},
{
"epoch": 8.03,
"learning_rate": 9.615384615384616e-06,
"loss": 0.0007,
"step": 6880
},
{
"epoch": 8.03,
"learning_rate": 9.548611111111111e-06,
"loss": 0.0009,
"step": 6890
},
{
"epoch": 8.03,
"learning_rate": 9.481837606837606e-06,
"loss": 0.1196,
"step": 6900
},
{
"epoch": 8.03,
"learning_rate": 9.415064102564103e-06,
"loss": 0.0008,
"step": 6910
},
{
"epoch": 8.03,
"learning_rate": 9.348290598290598e-06,
"loss": 0.0041,
"step": 6920
},
{
"epoch": 8.03,
"learning_rate": 9.281517094017095e-06,
"loss": 0.0012,
"step": 6930
},
{
"epoch": 8.03,
"learning_rate": 9.21474358974359e-06,
"loss": 0.0011,
"step": 6940
},
{
"epoch": 8.03,
"learning_rate": 9.147970085470086e-06,
"loss": 0.1124,
"step": 6950
},
{
"epoch": 8.04,
"learning_rate": 9.081196581196581e-06,
"loss": 0.1116,
"step": 6960
},
{
"epoch": 8.04,
"learning_rate": 9.014423076923078e-06,
"loss": 0.0171,
"step": 6970
},
{
"epoch": 8.04,
"learning_rate": 8.947649572649573e-06,
"loss": 0.002,
"step": 6980
},
{
"epoch": 8.04,
"learning_rate": 8.88087606837607e-06,
"loss": 0.0688,
"step": 6990
},
{
"epoch": 8.04,
"learning_rate": 8.814102564102565e-06,
"loss": 0.0007,
"step": 7000
},
{
"epoch": 8.04,
"learning_rate": 8.74732905982906e-06,
"loss": 0.0006,
"step": 7010
},
{
"epoch": 8.04,
"learning_rate": 8.680555555555556e-06,
"loss": 0.1653,
"step": 7020
},
{
"epoch": 8.04,
"learning_rate": 8.613782051282052e-06,
"loss": 0.0007,
"step": 7030
},
{
"epoch": 8.05,
"learning_rate": 8.547008547008548e-06,
"loss": 0.0101,
"step": 7040
},
{
"epoch": 8.05,
"learning_rate": 8.480235042735043e-06,
"loss": 0.0005,
"step": 7050
},
{
"epoch": 8.05,
"learning_rate": 8.41346153846154e-06,
"loss": 0.001,
"step": 7060
},
{
"epoch": 8.05,
"learning_rate": 8.346688034188033e-06,
"loss": 0.0007,
"step": 7070
},
{
"epoch": 8.05,
"learning_rate": 8.27991452991453e-06,
"loss": 0.0314,
"step": 7080
},
{
"epoch": 8.05,
"learning_rate": 8.213141025641025e-06,
"loss": 0.0194,
"step": 7090
},
{
"epoch": 8.05,
"learning_rate": 8.146367521367522e-06,
"loss": 0.0008,
"step": 7100
},
{
"epoch": 8.05,
"learning_rate": 8.079594017094018e-06,
"loss": 0.0185,
"step": 7110
},
{
"epoch": 8.05,
"learning_rate": 8.012820512820515e-06,
"loss": 0.0006,
"step": 7120
},
{
"epoch": 8.06,
"learning_rate": 7.946047008547008e-06,
"loss": 0.0777,
"step": 7130
},
{
"epoch": 8.06,
"learning_rate": 7.879273504273505e-06,
"loss": 0.0006,
"step": 7140
},
{
"epoch": 8.06,
"learning_rate": 7.8125e-06,
"loss": 0.0008,
"step": 7150
},
{
"epoch": 8.06,
"learning_rate": 7.745726495726497e-06,
"loss": 0.0284,
"step": 7160
},
{
"epoch": 8.06,
"learning_rate": 7.678952991452992e-06,
"loss": 0.0006,
"step": 7170
},
{
"epoch": 8.06,
"learning_rate": 7.612179487179487e-06,
"loss": 0.0011,
"step": 7180
},
{
"epoch": 8.06,
"learning_rate": 7.545405982905983e-06,
"loss": 0.0007,
"step": 7190
},
{
"epoch": 8.06,
"learning_rate": 7.478632478632479e-06,
"loss": 0.0008,
"step": 7200
},
{
"epoch": 8.07,
"learning_rate": 7.411858974358975e-06,
"loss": 0.0011,
"step": 7210
},
{
"epoch": 8.07,
"learning_rate": 7.345085470085471e-06,
"loss": 0.0011,
"step": 7220
},
{
"epoch": 8.07,
"learning_rate": 7.278311965811967e-06,
"loss": 0.0012,
"step": 7230
},
{
"epoch": 8.07,
"learning_rate": 7.211538461538461e-06,
"loss": 0.001,
"step": 7240
},
{
"epoch": 8.07,
"learning_rate": 7.1447649572649574e-06,
"loss": 0.0006,
"step": 7250
},
{
"epoch": 8.07,
"learning_rate": 7.0779914529914535e-06,
"loss": 0.0026,
"step": 7260
},
{
"epoch": 8.07,
"learning_rate": 7.011217948717949e-06,
"loss": 0.001,
"step": 7270
},
{
"epoch": 8.07,
"learning_rate": 6.944444444444445e-06,
"loss": 0.0005,
"step": 7280
},
{
"epoch": 8.08,
"learning_rate": 6.877670940170941e-06,
"loss": 0.0011,
"step": 7290
},
{
"epoch": 8.08,
"learning_rate": 6.810897435897435e-06,
"loss": 0.0005,
"step": 7300
},
{
"epoch": 8.08,
"learning_rate": 6.744123931623931e-06,
"loss": 0.0026,
"step": 7310
},
{
"epoch": 8.08,
"learning_rate": 6.677350427350427e-06,
"loss": 0.0016,
"step": 7320
},
{
"epoch": 8.08,
"learning_rate": 6.610576923076923e-06,
"loss": 0.0029,
"step": 7330
},
{
"epoch": 8.08,
"learning_rate": 6.5438034188034195e-06,
"loss": 0.0005,
"step": 7340
},
{
"epoch": 8.08,
"learning_rate": 6.4770299145299155e-06,
"loss": 0.0099,
"step": 7350
},
{
"epoch": 8.08,
"learning_rate": 6.41025641025641e-06,
"loss": 0.0007,
"step": 7360
},
{
"epoch": 8.08,
"learning_rate": 6.343482905982906e-06,
"loss": 0.0018,
"step": 7370
},
{
"epoch": 8.09,
"learning_rate": 6.276709401709402e-06,
"loss": 0.001,
"step": 7380
},
{
"epoch": 8.09,
"learning_rate": 6.209935897435898e-06,
"loss": 0.0008,
"step": 7390
},
{
"epoch": 8.09,
"learning_rate": 6.143162393162393e-06,
"loss": 0.0011,
"step": 7400
},
{
"epoch": 8.09,
"learning_rate": 6.076388888888889e-06,
"loss": 0.0098,
"step": 7410
},
{
"epoch": 8.09,
"learning_rate": 6.0096153846153855e-06,
"loss": 0.0005,
"step": 7420
},
{
"epoch": 8.09,
"learning_rate": 5.942841880341881e-06,
"loss": 0.0006,
"step": 7430
},
{
"epoch": 8.09,
"learning_rate": 5.876068376068376e-06,
"loss": 0.0009,
"step": 7440
},
{
"epoch": 8.09,
"learning_rate": 5.809294871794872e-06,
"loss": 0.0008,
"step": 7450
},
{
"epoch": 8.1,
"learning_rate": 5.742521367521367e-06,
"loss": 0.0007,
"step": 7460
},
{
"epoch": 8.1,
"learning_rate": 5.675747863247863e-06,
"loss": 0.0006,
"step": 7470
},
{
"epoch": 8.1,
"learning_rate": 5.608974358974359e-06,
"loss": 0.0007,
"step": 7480
},
{
"epoch": 8.1,
"learning_rate": 5.5422008547008545e-06,
"loss": 0.001,
"step": 7490
},
{
"epoch": 8.1,
"eval_accuracy": 0.9822353811991118,
"eval_loss": 0.07449387013912201,
"eval_runtime": 85.6508,
"eval_samples_per_second": 15.773,
"eval_steps_per_second": 2.639,
"step": 7497
},
{
"epoch": 9.0,
"learning_rate": 5.475427350427351e-06,
"loss": 0.0022,
"step": 7500
},
{
"epoch": 9.0,
"learning_rate": 5.408653846153847e-06,
"loss": 0.0181,
"step": 7510
},
{
"epoch": 9.0,
"learning_rate": 5.341880341880342e-06,
"loss": 0.0153,
"step": 7520
},
{
"epoch": 9.0,
"learning_rate": 5.275106837606838e-06,
"loss": 0.0246,
"step": 7530
},
{
"epoch": 9.01,
"learning_rate": 5.208333333333334e-06,
"loss": 0.0006,
"step": 7540
},
{
"epoch": 9.01,
"learning_rate": 5.141559829059829e-06,
"loss": 0.0717,
"step": 7550
},
{
"epoch": 9.01,
"learning_rate": 5.074786324786325e-06,
"loss": 0.0007,
"step": 7560
},
{
"epoch": 9.01,
"learning_rate": 5.008012820512821e-06,
"loss": 0.0005,
"step": 7570
},
{
"epoch": 9.01,
"learning_rate": 4.9412393162393166e-06,
"loss": 0.0009,
"step": 7580
},
{
"epoch": 9.01,
"learning_rate": 4.874465811965813e-06,
"loss": 0.0005,
"step": 7590
},
{
"epoch": 9.01,
"learning_rate": 4.807692307692308e-06,
"loss": 0.0005,
"step": 7600
},
{
"epoch": 9.01,
"learning_rate": 4.740918803418803e-06,
"loss": 0.0005,
"step": 7610
},
{
"epoch": 9.01,
"learning_rate": 4.674145299145299e-06,
"loss": 0.1065,
"step": 7620
},
{
"epoch": 9.02,
"learning_rate": 4.607371794871795e-06,
"loss": 0.0561,
"step": 7630
},
{
"epoch": 9.02,
"learning_rate": 4.5405982905982904e-06,
"loss": 0.0006,
"step": 7640
},
{
"epoch": 9.02,
"learning_rate": 4.4738247863247865e-06,
"loss": 0.0006,
"step": 7650
},
{
"epoch": 9.02,
"learning_rate": 4.4070512820512826e-06,
"loss": 0.0009,
"step": 7660
},
{
"epoch": 9.02,
"learning_rate": 4.340277777777778e-06,
"loss": 0.0006,
"step": 7670
},
{
"epoch": 9.02,
"learning_rate": 4.273504273504274e-06,
"loss": 0.0006,
"step": 7680
},
{
"epoch": 9.02,
"learning_rate": 4.20673076923077e-06,
"loss": 0.0005,
"step": 7690
},
{
"epoch": 9.02,
"learning_rate": 4.139957264957265e-06,
"loss": 0.0006,
"step": 7700
},
{
"epoch": 9.03,
"learning_rate": 4.073183760683761e-06,
"loss": 0.0009,
"step": 7710
},
{
"epoch": 9.03,
"learning_rate": 4.006410256410257e-06,
"loss": 0.1264,
"step": 7720
},
{
"epoch": 9.03,
"learning_rate": 3.9396367521367525e-06,
"loss": 0.0008,
"step": 7730
},
{
"epoch": 9.03,
"learning_rate": 3.8728632478632485e-06,
"loss": 0.0005,
"step": 7740
},
{
"epoch": 9.03,
"learning_rate": 3.8060897435897433e-06,
"loss": 0.0009,
"step": 7750
},
{
"epoch": 9.03,
"learning_rate": 3.7393162393162394e-06,
"loss": 0.0009,
"step": 7760
},
{
"epoch": 9.03,
"learning_rate": 3.6725427350427355e-06,
"loss": 0.0005,
"step": 7770
},
{
"epoch": 9.03,
"learning_rate": 3.6057692307692307e-06,
"loss": 0.0427,
"step": 7780
},
{
"epoch": 9.04,
"learning_rate": 3.5389957264957267e-06,
"loss": 0.0005,
"step": 7790
},
{
"epoch": 9.04,
"learning_rate": 3.4722222222222224e-06,
"loss": 0.0696,
"step": 7800
},
{
"epoch": 9.04,
"learning_rate": 3.4054487179487176e-06,
"loss": 0.0006,
"step": 7810
},
{
"epoch": 9.04,
"learning_rate": 3.3386752136752137e-06,
"loss": 0.0006,
"step": 7820
},
{
"epoch": 9.04,
"learning_rate": 3.2719017094017097e-06,
"loss": 0.005,
"step": 7830
},
{
"epoch": 9.04,
"learning_rate": 3.205128205128205e-06,
"loss": 0.0022,
"step": 7840
},
{
"epoch": 9.04,
"learning_rate": 3.138354700854701e-06,
"loss": 0.0006,
"step": 7850
},
{
"epoch": 9.04,
"learning_rate": 3.0715811965811967e-06,
"loss": 0.0093,
"step": 7860
},
{
"epoch": 9.04,
"learning_rate": 3.0048076923076927e-06,
"loss": 0.0007,
"step": 7870
},
{
"epoch": 9.05,
"learning_rate": 2.938034188034188e-06,
"loss": 0.0006,
"step": 7880
},
{
"epoch": 9.05,
"learning_rate": 2.8712606837606836e-06,
"loss": 0.0152,
"step": 7890
},
{
"epoch": 9.05,
"learning_rate": 2.8044871794871797e-06,
"loss": 0.0005,
"step": 7900
},
{
"epoch": 9.05,
"learning_rate": 2.7377136752136753e-06,
"loss": 0.0071,
"step": 7910
},
{
"epoch": 9.05,
"learning_rate": 2.670940170940171e-06,
"loss": 0.1172,
"step": 7920
},
{
"epoch": 9.05,
"learning_rate": 2.604166666666667e-06,
"loss": 0.0031,
"step": 7930
},
{
"epoch": 9.05,
"learning_rate": 2.5373931623931626e-06,
"loss": 0.0005,
"step": 7940
},
{
"epoch": 9.05,
"learning_rate": 2.4706196581196583e-06,
"loss": 0.0006,
"step": 7950
},
{
"epoch": 9.06,
"learning_rate": 2.403846153846154e-06,
"loss": 0.0108,
"step": 7960
},
{
"epoch": 9.06,
"learning_rate": 2.3370726495726496e-06,
"loss": 0.0005,
"step": 7970
},
{
"epoch": 9.06,
"learning_rate": 2.2702991452991452e-06,
"loss": 0.0005,
"step": 7980
},
{
"epoch": 9.06,
"learning_rate": 2.2035256410256413e-06,
"loss": 0.0005,
"step": 7990
},
{
"epoch": 9.06,
"learning_rate": 2.136752136752137e-06,
"loss": 0.0005,
"step": 8000
},
{
"epoch": 9.06,
"learning_rate": 2.0699786324786326e-06,
"loss": 0.0009,
"step": 8010
},
{
"epoch": 9.06,
"learning_rate": 2.0032051282051286e-06,
"loss": 0.0006,
"step": 8020
},
{
"epoch": 9.06,
"learning_rate": 1.9364316239316243e-06,
"loss": 0.0005,
"step": 8030
},
{
"epoch": 9.07,
"learning_rate": 1.8696581196581197e-06,
"loss": 0.001,
"step": 8040
},
{
"epoch": 9.07,
"learning_rate": 1.8028846153846153e-06,
"loss": 0.0005,
"step": 8050
},
{
"epoch": 9.07,
"learning_rate": 1.7361111111111112e-06,
"loss": 0.0005,
"step": 8060
},
{
"epoch": 9.07,
"learning_rate": 1.6693376068376068e-06,
"loss": 0.0005,
"step": 8070
},
{
"epoch": 9.07,
"learning_rate": 1.6025641025641025e-06,
"loss": 0.0008,
"step": 8080
},
{
"epoch": 9.07,
"learning_rate": 1.5357905982905983e-06,
"loss": 0.0005,
"step": 8090
},
{
"epoch": 9.07,
"learning_rate": 1.469017094017094e-06,
"loss": 0.0005,
"step": 8100
},
{
"epoch": 9.07,
"learning_rate": 1.4022435897435898e-06,
"loss": 0.0089,
"step": 8110
},
{
"epoch": 9.07,
"learning_rate": 1.3354700854700855e-06,
"loss": 0.0009,
"step": 8120
},
{
"epoch": 9.08,
"learning_rate": 1.2686965811965813e-06,
"loss": 0.001,
"step": 8130
},
{
"epoch": 9.08,
"learning_rate": 1.201923076923077e-06,
"loss": 0.0005,
"step": 8140
},
{
"epoch": 9.08,
"learning_rate": 1.1351495726495726e-06,
"loss": 0.0006,
"step": 8150
},
{
"epoch": 9.08,
"learning_rate": 1.0683760683760685e-06,
"loss": 0.0005,
"step": 8160
},
{
"epoch": 9.08,
"learning_rate": 1.0016025641025643e-06,
"loss": 0.0005,
"step": 8170
},
{
"epoch": 9.08,
"learning_rate": 9.348290598290598e-07,
"loss": 0.0005,
"step": 8180
},
{
"epoch": 9.08,
"learning_rate": 8.680555555555556e-07,
"loss": 0.0005,
"step": 8190
},
{
"epoch": 9.08,
"learning_rate": 8.012820512820512e-07,
"loss": 0.0006,
"step": 8200
},
{
"epoch": 9.09,
"learning_rate": 7.34508547008547e-07,
"loss": 0.0005,
"step": 8210
},
{
"epoch": 9.09,
"learning_rate": 6.677350427350427e-07,
"loss": 0.0005,
"step": 8220
},
{
"epoch": 9.09,
"learning_rate": 6.009615384615385e-07,
"loss": 0.0004,
"step": 8230
},
{
"epoch": 9.09,
"learning_rate": 5.341880341880342e-07,
"loss": 0.0049,
"step": 8240
},
{
"epoch": 9.09,
"learning_rate": 4.674145299145299e-07,
"loss": 0.0011,
"step": 8250
},
{
"epoch": 9.09,
"learning_rate": 4.006410256410256e-07,
"loss": 0.0007,
"step": 8260
},
{
"epoch": 9.09,
"learning_rate": 3.3386752136752137e-07,
"loss": 0.0005,
"step": 8270
},
{
"epoch": 9.09,
"learning_rate": 2.670940170940171e-07,
"loss": 0.0006,
"step": 8280
},
{
"epoch": 9.1,
"learning_rate": 2.003205128205128e-07,
"loss": 0.0008,
"step": 8290
},
{
"epoch": 9.1,
"learning_rate": 1.3354700854700856e-07,
"loss": 0.0676,
"step": 8300
},
{
"epoch": 9.1,
"learning_rate": 6.677350427350428e-08,
"loss": 0.0005,
"step": 8310
},
{
"epoch": 9.1,
"learning_rate": 0.0,
"loss": 0.0005,
"step": 8320
},
{
"epoch": 9.1,
"eval_accuracy": 0.9837157660991858,
"eval_loss": 0.0756925716996193,
"eval_runtime": 86.0742,
"eval_samples_per_second": 15.696,
"eval_steps_per_second": 2.626,
"step": 8320
},
{
"epoch": 9.1,
"step": 8320,
"total_flos": 6.218584863603543e+19,
"train_loss": 0.42279570934445543,
"train_runtime": 6828.4751,
"train_samples_per_second": 7.311,
"train_steps_per_second": 1.218
},
{
"epoch": 9.1,
"eval_accuracy": 0.9837157660991858,
"eval_loss": 0.0756925716996193,
"eval_runtime": 86.0371,
"eval_samples_per_second": 15.703,
"eval_steps_per_second": 2.627,
"step": 8320
},
{
"epoch": 9.1,
"eval_accuracy": 0.0,
"eval_loss": 9.850842475891113,
"eval_runtime": 334.1168,
"eval_samples_per_second": 14.612,
"eval_steps_per_second": 2.436,
"step": 8320
},
{
"epoch": 9.1,
"eval_accuracy": 0.9837157660991858,
"eval_loss": 0.0756925716996193,
"eval_runtime": 85.3939,
"eval_samples_per_second": 15.821,
"eval_steps_per_second": 2.647,
"step": 8320
}
],
"logging_steps": 10,
"max_steps": 8320,
"num_input_tokens_seen": 0,
"num_train_epochs": 9223372036854775807,
"save_steps": 500,
"total_flos": 6.218584863603543e+19,
"train_batch_size": 6,
"trial_name": null,
"trial_params": null
}