venkateshtata's picture
End of training
ed848b3
raw
history blame
198 kB
{
"best_metric": 0.868421052631579,
"best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-2736",
"epoch": 49.02,
"global_step": 15200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 3.2894736842105264e-07,
"loss": 1.2842,
"step": 10
},
{
"epoch": 0.0,
"learning_rate": 6.578947368421053e-07,
"loss": 1.2399,
"step": 20
},
{
"epoch": 0.0,
"learning_rate": 9.868421052631579e-07,
"loss": 1.0408,
"step": 30
},
{
"epoch": 0.0,
"learning_rate": 1.3157894736842106e-06,
"loss": 1.2339,
"step": 40
},
{
"epoch": 0.0,
"learning_rate": 1.6447368421052632e-06,
"loss": 1.0752,
"step": 50
},
{
"epoch": 0.0,
"learning_rate": 1.9736842105263157e-06,
"loss": 1.021,
"step": 60
},
{
"epoch": 0.0,
"learning_rate": 2.3026315789473684e-06,
"loss": 0.9774,
"step": 70
},
{
"epoch": 0.01,
"learning_rate": 2.631578947368421e-06,
"loss": 0.9841,
"step": 80
},
{
"epoch": 0.01,
"learning_rate": 2.960526315789474e-06,
"loss": 1.0497,
"step": 90
},
{
"epoch": 0.01,
"learning_rate": 3.2894736842105265e-06,
"loss": 1.0385,
"step": 100
},
{
"epoch": 0.01,
"learning_rate": 3.618421052631579e-06,
"loss": 1.0994,
"step": 110
},
{
"epoch": 0.01,
"learning_rate": 3.9473684210526315e-06,
"loss": 1.0264,
"step": 120
},
{
"epoch": 0.01,
"learning_rate": 4.276315789473684e-06,
"loss": 1.0597,
"step": 130
},
{
"epoch": 0.01,
"learning_rate": 4.605263157894737e-06,
"loss": 1.2615,
"step": 140
},
{
"epoch": 0.01,
"learning_rate": 4.9342105263157895e-06,
"loss": 1.055,
"step": 150
},
{
"epoch": 0.01,
"learning_rate": 5.263157894736842e-06,
"loss": 0.9867,
"step": 160
},
{
"epoch": 0.01,
"learning_rate": 5.592105263157895e-06,
"loss": 0.9432,
"step": 170
},
{
"epoch": 0.01,
"learning_rate": 5.921052631578948e-06,
"loss": 0.9125,
"step": 180
},
{
"epoch": 0.01,
"learning_rate": 6.25e-06,
"loss": 0.9441,
"step": 190
},
{
"epoch": 0.01,
"learning_rate": 6.578947368421053e-06,
"loss": 1.0888,
"step": 200
},
{
"epoch": 0.01,
"learning_rate": 6.9078947368421065e-06,
"loss": 0.6684,
"step": 210
},
{
"epoch": 0.01,
"learning_rate": 7.236842105263158e-06,
"loss": 0.7666,
"step": 220
},
{
"epoch": 0.02,
"learning_rate": 7.565789473684211e-06,
"loss": 1.1011,
"step": 230
},
{
"epoch": 0.02,
"learning_rate": 7.894736842105263e-06,
"loss": 1.2508,
"step": 240
},
{
"epoch": 0.02,
"learning_rate": 8.223684210526317e-06,
"loss": 0.7559,
"step": 250
},
{
"epoch": 0.02,
"learning_rate": 8.552631578947368e-06,
"loss": 0.7981,
"step": 260
},
{
"epoch": 0.02,
"learning_rate": 8.881578947368421e-06,
"loss": 0.8126,
"step": 270
},
{
"epoch": 0.02,
"learning_rate": 9.210526315789474e-06,
"loss": 0.8424,
"step": 280
},
{
"epoch": 0.02,
"learning_rate": 9.539473684210528e-06,
"loss": 0.8065,
"step": 290
},
{
"epoch": 0.02,
"learning_rate": 9.868421052631579e-06,
"loss": 0.3638,
"step": 300
},
{
"epoch": 0.02,
"eval_accuracy": 0.6118421052631579,
"eval_loss": 0.9849972128868103,
"eval_runtime": 47.5094,
"eval_samples_per_second": 3.199,
"eval_steps_per_second": 3.199,
"step": 304
},
{
"epoch": 1.0,
"learning_rate": 1.0197368421052632e-05,
"loss": 0.5547,
"step": 310
},
{
"epoch": 1.0,
"learning_rate": 1.0526315789473684e-05,
"loss": 1.1807,
"step": 320
},
{
"epoch": 1.0,
"learning_rate": 1.0855263157894737e-05,
"loss": 1.0746,
"step": 330
},
{
"epoch": 1.0,
"learning_rate": 1.118421052631579e-05,
"loss": 0.9188,
"step": 340
},
{
"epoch": 1.0,
"learning_rate": 1.1513157894736843e-05,
"loss": 0.521,
"step": 350
},
{
"epoch": 1.0,
"learning_rate": 1.1842105263157895e-05,
"loss": 1.458,
"step": 360
},
{
"epoch": 1.0,
"learning_rate": 1.2171052631578948e-05,
"loss": 0.6086,
"step": 370
},
{
"epoch": 1.0,
"learning_rate": 1.25e-05,
"loss": 0.485,
"step": 380
},
{
"epoch": 1.01,
"learning_rate": 1.2828947368421055e-05,
"loss": 0.915,
"step": 390
},
{
"epoch": 1.01,
"learning_rate": 1.3157894736842106e-05,
"loss": 0.6617,
"step": 400
},
{
"epoch": 1.01,
"learning_rate": 1.3486842105263159e-05,
"loss": 0.7925,
"step": 410
},
{
"epoch": 1.01,
"learning_rate": 1.3815789473684213e-05,
"loss": 0.8223,
"step": 420
},
{
"epoch": 1.01,
"learning_rate": 1.4144736842105264e-05,
"loss": 0.715,
"step": 430
},
{
"epoch": 1.01,
"learning_rate": 1.4473684210526317e-05,
"loss": 0.2803,
"step": 440
},
{
"epoch": 1.01,
"learning_rate": 1.4802631578947368e-05,
"loss": 2.2789,
"step": 450
},
{
"epoch": 1.01,
"learning_rate": 1.5131578947368422e-05,
"loss": 0.4357,
"step": 460
},
{
"epoch": 1.01,
"learning_rate": 1.5460526315789475e-05,
"loss": 1.8673,
"step": 470
},
{
"epoch": 1.01,
"learning_rate": 1.5789473684210526e-05,
"loss": 0.8523,
"step": 480
},
{
"epoch": 1.01,
"learning_rate": 1.611842105263158e-05,
"loss": 1.5552,
"step": 490
},
{
"epoch": 1.01,
"learning_rate": 1.6447368421052635e-05,
"loss": 0.4041,
"step": 500
},
{
"epoch": 1.01,
"learning_rate": 1.6776315789473686e-05,
"loss": 0.806,
"step": 510
},
{
"epoch": 1.01,
"learning_rate": 1.7105263157894737e-05,
"loss": 1.4332,
"step": 520
},
{
"epoch": 1.01,
"learning_rate": 1.7434210526315788e-05,
"loss": 0.4385,
"step": 530
},
{
"epoch": 1.02,
"learning_rate": 1.7763157894736842e-05,
"loss": 0.0892,
"step": 540
},
{
"epoch": 1.02,
"learning_rate": 1.8092105263157896e-05,
"loss": 1.0792,
"step": 550
},
{
"epoch": 1.02,
"learning_rate": 1.8421052631578947e-05,
"loss": 1.8701,
"step": 560
},
{
"epoch": 1.02,
"learning_rate": 1.8750000000000002e-05,
"loss": 0.7174,
"step": 570
},
{
"epoch": 1.02,
"learning_rate": 1.9078947368421056e-05,
"loss": 0.6888,
"step": 580
},
{
"epoch": 1.02,
"learning_rate": 1.9407894736842107e-05,
"loss": 0.5572,
"step": 590
},
{
"epoch": 1.02,
"learning_rate": 1.9736842105263158e-05,
"loss": 0.9176,
"step": 600
},
{
"epoch": 1.02,
"eval_accuracy": 0.3881578947368421,
"eval_loss": 1.699346899986267,
"eval_runtime": 46.9111,
"eval_samples_per_second": 3.24,
"eval_steps_per_second": 3.24,
"step": 608
},
{
"epoch": 2.0,
"learning_rate": 2.0065789473684213e-05,
"loss": 0.8356,
"step": 610
},
{
"epoch": 2.0,
"learning_rate": 2.0394736842105264e-05,
"loss": 0.5238,
"step": 620
},
{
"epoch": 2.0,
"learning_rate": 2.0723684210526318e-05,
"loss": 1.4221,
"step": 630
},
{
"epoch": 2.0,
"learning_rate": 2.105263157894737e-05,
"loss": 0.4492,
"step": 640
},
{
"epoch": 2.0,
"learning_rate": 2.1381578947368423e-05,
"loss": 0.851,
"step": 650
},
{
"epoch": 2.0,
"learning_rate": 2.1710526315789474e-05,
"loss": 1.4773,
"step": 660
},
{
"epoch": 2.0,
"learning_rate": 2.2039473684210525e-05,
"loss": 0.8735,
"step": 670
},
{
"epoch": 2.0,
"learning_rate": 2.236842105263158e-05,
"loss": 1.3409,
"step": 680
},
{
"epoch": 2.01,
"learning_rate": 2.2697368421052634e-05,
"loss": 0.3808,
"step": 690
},
{
"epoch": 2.01,
"learning_rate": 2.3026315789473685e-05,
"loss": 0.5506,
"step": 700
},
{
"epoch": 2.01,
"learning_rate": 2.335526315789474e-05,
"loss": 0.7331,
"step": 710
},
{
"epoch": 2.01,
"learning_rate": 2.368421052631579e-05,
"loss": 0.5069,
"step": 720
},
{
"epoch": 2.01,
"learning_rate": 2.401315789473684e-05,
"loss": 1.0407,
"step": 730
},
{
"epoch": 2.01,
"learning_rate": 2.4342105263157896e-05,
"loss": 1.5007,
"step": 740
},
{
"epoch": 2.01,
"learning_rate": 2.4671052631578947e-05,
"loss": 0.5833,
"step": 750
},
{
"epoch": 2.01,
"learning_rate": 2.5e-05,
"loss": 0.4673,
"step": 760
},
{
"epoch": 2.01,
"learning_rate": 2.5328947368421052e-05,
"loss": 0.5077,
"step": 770
},
{
"epoch": 2.01,
"learning_rate": 2.565789473684211e-05,
"loss": 0.4603,
"step": 780
},
{
"epoch": 2.01,
"learning_rate": 2.598684210526316e-05,
"loss": 0.504,
"step": 790
},
{
"epoch": 2.01,
"learning_rate": 2.6315789473684212e-05,
"loss": 1.396,
"step": 800
},
{
"epoch": 2.01,
"learning_rate": 2.6644736842105266e-05,
"loss": 0.9688,
"step": 810
},
{
"epoch": 2.01,
"learning_rate": 2.6973684210526317e-05,
"loss": 0.6205,
"step": 820
},
{
"epoch": 2.01,
"learning_rate": 2.730263157894737e-05,
"loss": 1.6556,
"step": 830
},
{
"epoch": 2.02,
"learning_rate": 2.7631578947368426e-05,
"loss": 0.8885,
"step": 840
},
{
"epoch": 2.02,
"learning_rate": 2.7960526315789477e-05,
"loss": 0.4772,
"step": 850
},
{
"epoch": 2.02,
"learning_rate": 2.8289473684210528e-05,
"loss": 0.711,
"step": 860
},
{
"epoch": 2.02,
"learning_rate": 2.861842105263158e-05,
"loss": 0.2489,
"step": 870
},
{
"epoch": 2.02,
"learning_rate": 2.8947368421052634e-05,
"loss": 0.0055,
"step": 880
},
{
"epoch": 2.02,
"learning_rate": 2.9276315789473684e-05,
"loss": 1.384,
"step": 890
},
{
"epoch": 2.02,
"learning_rate": 2.9605263157894735e-05,
"loss": 0.2934,
"step": 900
},
{
"epoch": 2.02,
"learning_rate": 2.9934210526315793e-05,
"loss": 0.5243,
"step": 910
},
{
"epoch": 2.02,
"eval_accuracy": 0.8026315789473685,
"eval_loss": 1.1637039184570312,
"eval_runtime": 46.7503,
"eval_samples_per_second": 3.251,
"eval_steps_per_second": 3.251,
"step": 912
},
{
"epoch": 3.0,
"learning_rate": 3.0263157894736844e-05,
"loss": 0.0107,
"step": 920
},
{
"epoch": 3.0,
"learning_rate": 3.059210526315789e-05,
"loss": 0.8036,
"step": 930
},
{
"epoch": 3.0,
"learning_rate": 3.092105263157895e-05,
"loss": 0.4714,
"step": 940
},
{
"epoch": 3.0,
"learning_rate": 3.125e-05,
"loss": 0.4808,
"step": 950
},
{
"epoch": 3.0,
"learning_rate": 3.157894736842105e-05,
"loss": 0.0305,
"step": 960
},
{
"epoch": 3.0,
"learning_rate": 3.190789473684211e-05,
"loss": 0.1903,
"step": 970
},
{
"epoch": 3.0,
"learning_rate": 3.223684210526316e-05,
"loss": 0.4268,
"step": 980
},
{
"epoch": 3.01,
"learning_rate": 3.256578947368421e-05,
"loss": 0.0024,
"step": 990
},
{
"epoch": 3.01,
"learning_rate": 3.289473684210527e-05,
"loss": 0.3301,
"step": 1000
},
{
"epoch": 3.01,
"learning_rate": 3.322368421052632e-05,
"loss": 1.2106,
"step": 1010
},
{
"epoch": 3.01,
"learning_rate": 3.355263157894737e-05,
"loss": 0.0053,
"step": 1020
},
{
"epoch": 3.01,
"learning_rate": 3.388157894736842e-05,
"loss": 1.3356,
"step": 1030
},
{
"epoch": 3.01,
"learning_rate": 3.421052631578947e-05,
"loss": 0.0472,
"step": 1040
},
{
"epoch": 3.01,
"learning_rate": 3.4539473684210524e-05,
"loss": 0.0016,
"step": 1050
},
{
"epoch": 3.01,
"learning_rate": 3.4868421052631575e-05,
"loss": 1.5885,
"step": 1060
},
{
"epoch": 3.01,
"learning_rate": 3.519736842105263e-05,
"loss": 0.0053,
"step": 1070
},
{
"epoch": 3.01,
"learning_rate": 3.5526315789473684e-05,
"loss": 0.0009,
"step": 1080
},
{
"epoch": 3.01,
"learning_rate": 3.5855263157894735e-05,
"loss": 0.6742,
"step": 1090
},
{
"epoch": 3.01,
"learning_rate": 3.618421052631579e-05,
"loss": 0.5319,
"step": 1100
},
{
"epoch": 3.01,
"learning_rate": 3.6513157894736844e-05,
"loss": 0.2172,
"step": 1110
},
{
"epoch": 3.01,
"learning_rate": 3.6842105263157895e-05,
"loss": 0.0053,
"step": 1120
},
{
"epoch": 3.01,
"learning_rate": 3.717105263157895e-05,
"loss": 0.0028,
"step": 1130
},
{
"epoch": 3.02,
"learning_rate": 3.7500000000000003e-05,
"loss": 0.0011,
"step": 1140
},
{
"epoch": 3.02,
"learning_rate": 3.7828947368421054e-05,
"loss": 0.0006,
"step": 1150
},
{
"epoch": 3.02,
"learning_rate": 3.815789473684211e-05,
"loss": 0.6256,
"step": 1160
},
{
"epoch": 3.02,
"learning_rate": 3.848684210526316e-05,
"loss": 0.7554,
"step": 1170
},
{
"epoch": 3.02,
"learning_rate": 3.8815789473684214e-05,
"loss": 0.6128,
"step": 1180
},
{
"epoch": 3.02,
"learning_rate": 3.9144736842105265e-05,
"loss": 0.5144,
"step": 1190
},
{
"epoch": 3.02,
"learning_rate": 3.9473684210526316e-05,
"loss": 0.0872,
"step": 1200
},
{
"epoch": 3.02,
"learning_rate": 3.980263157894737e-05,
"loss": 0.0005,
"step": 1210
},
{
"epoch": 3.02,
"eval_accuracy": 0.8092105263157895,
"eval_loss": 0.8619503974914551,
"eval_runtime": 47.1275,
"eval_samples_per_second": 3.225,
"eval_steps_per_second": 3.225,
"step": 1216
},
{
"epoch": 4.0,
"learning_rate": 4.0131578947368425e-05,
"loss": 0.7373,
"step": 1220
},
{
"epoch": 4.0,
"learning_rate": 4.0460526315789476e-05,
"loss": 0.6908,
"step": 1230
},
{
"epoch": 4.0,
"learning_rate": 4.078947368421053e-05,
"loss": 0.0091,
"step": 1240
},
{
"epoch": 4.0,
"learning_rate": 4.111842105263158e-05,
"loss": 0.002,
"step": 1250
},
{
"epoch": 4.0,
"learning_rate": 4.1447368421052636e-05,
"loss": 0.0942,
"step": 1260
},
{
"epoch": 4.0,
"learning_rate": 4.177631578947369e-05,
"loss": 0.0576,
"step": 1270
},
{
"epoch": 4.0,
"learning_rate": 4.210526315789474e-05,
"loss": 0.6502,
"step": 1280
},
{
"epoch": 4.0,
"learning_rate": 4.2434210526315796e-05,
"loss": 0.0007,
"step": 1290
},
{
"epoch": 4.01,
"learning_rate": 4.2763157894736847e-05,
"loss": 0.506,
"step": 1300
},
{
"epoch": 4.01,
"learning_rate": 4.30921052631579e-05,
"loss": 0.601,
"step": 1310
},
{
"epoch": 4.01,
"learning_rate": 4.342105263157895e-05,
"loss": 0.0578,
"step": 1320
},
{
"epoch": 4.01,
"learning_rate": 4.375e-05,
"loss": 0.699,
"step": 1330
},
{
"epoch": 4.01,
"learning_rate": 4.407894736842105e-05,
"loss": 0.686,
"step": 1340
},
{
"epoch": 4.01,
"learning_rate": 4.440789473684211e-05,
"loss": 0.8831,
"step": 1350
},
{
"epoch": 4.01,
"learning_rate": 4.473684210526316e-05,
"loss": 0.0036,
"step": 1360
},
{
"epoch": 4.01,
"learning_rate": 4.506578947368421e-05,
"loss": 0.0007,
"step": 1370
},
{
"epoch": 4.01,
"learning_rate": 4.539473684210527e-05,
"loss": 0.0046,
"step": 1380
},
{
"epoch": 4.01,
"learning_rate": 4.572368421052632e-05,
"loss": 0.3732,
"step": 1390
},
{
"epoch": 4.01,
"learning_rate": 4.605263157894737e-05,
"loss": 0.0006,
"step": 1400
},
{
"epoch": 4.01,
"learning_rate": 4.638157894736843e-05,
"loss": 0.0005,
"step": 1410
},
{
"epoch": 4.01,
"learning_rate": 4.671052631578948e-05,
"loss": 0.0464,
"step": 1420
},
{
"epoch": 4.01,
"learning_rate": 4.703947368421053e-05,
"loss": 0.0006,
"step": 1430
},
{
"epoch": 4.01,
"learning_rate": 4.736842105263158e-05,
"loss": 0.0005,
"step": 1440
},
{
"epoch": 4.02,
"learning_rate": 4.769736842105263e-05,
"loss": 0.0006,
"step": 1450
},
{
"epoch": 4.02,
"learning_rate": 4.802631578947368e-05,
"loss": 0.0004,
"step": 1460
},
{
"epoch": 4.02,
"learning_rate": 4.8355263157894734e-05,
"loss": 0.0004,
"step": 1470
},
{
"epoch": 4.02,
"learning_rate": 4.868421052631579e-05,
"loss": 0.8033,
"step": 1480
},
{
"epoch": 4.02,
"learning_rate": 4.901315789473684e-05,
"loss": 0.7132,
"step": 1490
},
{
"epoch": 4.02,
"learning_rate": 4.9342105263157894e-05,
"loss": 0.0012,
"step": 1500
},
{
"epoch": 4.02,
"learning_rate": 4.967105263157895e-05,
"loss": 1.6084,
"step": 1510
},
{
"epoch": 4.02,
"learning_rate": 5e-05,
"loss": 0.5382,
"step": 1520
},
{
"epoch": 4.02,
"eval_accuracy": 0.8092105263157895,
"eval_loss": 0.9102385640144348,
"eval_runtime": 46.8785,
"eval_samples_per_second": 3.242,
"eval_steps_per_second": 3.242,
"step": 1520
},
{
"epoch": 5.0,
"learning_rate": 4.9963450292397664e-05,
"loss": 0.6373,
"step": 1530
},
{
"epoch": 5.0,
"learning_rate": 4.992690058479532e-05,
"loss": 1.0287,
"step": 1540
},
{
"epoch": 5.0,
"learning_rate": 4.989035087719299e-05,
"loss": 0.0504,
"step": 1550
},
{
"epoch": 5.0,
"learning_rate": 4.985380116959065e-05,
"loss": 0.5377,
"step": 1560
},
{
"epoch": 5.0,
"learning_rate": 4.9817251461988304e-05,
"loss": 0.0006,
"step": 1570
},
{
"epoch": 5.0,
"learning_rate": 4.9780701754385966e-05,
"loss": 0.8738,
"step": 1580
},
{
"epoch": 5.0,
"learning_rate": 4.974415204678363e-05,
"loss": 0.1781,
"step": 1590
},
{
"epoch": 5.01,
"learning_rate": 4.970760233918128e-05,
"loss": 0.0008,
"step": 1600
},
{
"epoch": 5.01,
"learning_rate": 4.967105263157895e-05,
"loss": 0.0008,
"step": 1610
},
{
"epoch": 5.01,
"learning_rate": 4.963450292397661e-05,
"loss": 0.8045,
"step": 1620
},
{
"epoch": 5.01,
"learning_rate": 4.959795321637427e-05,
"loss": 1.3749,
"step": 1630
},
{
"epoch": 5.01,
"learning_rate": 4.956140350877193e-05,
"loss": 0.0063,
"step": 1640
},
{
"epoch": 5.01,
"learning_rate": 4.952485380116959e-05,
"loss": 0.7926,
"step": 1650
},
{
"epoch": 5.01,
"learning_rate": 4.948830409356725e-05,
"loss": 0.5013,
"step": 1660
},
{
"epoch": 5.01,
"learning_rate": 4.9451754385964915e-05,
"loss": 0.0031,
"step": 1670
},
{
"epoch": 5.01,
"learning_rate": 4.941520467836258e-05,
"loss": 0.3503,
"step": 1680
},
{
"epoch": 5.01,
"learning_rate": 4.937865497076024e-05,
"loss": 0.0015,
"step": 1690
},
{
"epoch": 5.01,
"learning_rate": 4.9342105263157894e-05,
"loss": 0.3504,
"step": 1700
},
{
"epoch": 5.01,
"learning_rate": 4.930555555555556e-05,
"loss": 0.182,
"step": 1710
},
{
"epoch": 5.01,
"learning_rate": 4.926900584795322e-05,
"loss": 1.3018,
"step": 1720
},
{
"epoch": 5.01,
"learning_rate": 4.923245614035088e-05,
"loss": 2.0085,
"step": 1730
},
{
"epoch": 5.01,
"learning_rate": 4.919590643274854e-05,
"loss": 0.3176,
"step": 1740
},
{
"epoch": 5.02,
"learning_rate": 4.91593567251462e-05,
"loss": 0.184,
"step": 1750
},
{
"epoch": 5.02,
"learning_rate": 4.912280701754386e-05,
"loss": 0.0046,
"step": 1760
},
{
"epoch": 5.02,
"learning_rate": 4.9086257309941526e-05,
"loss": 1.1569,
"step": 1770
},
{
"epoch": 5.02,
"learning_rate": 4.904970760233919e-05,
"loss": 0.0039,
"step": 1780
},
{
"epoch": 5.02,
"learning_rate": 4.901315789473684e-05,
"loss": 0.0022,
"step": 1790
},
{
"epoch": 5.02,
"learning_rate": 4.8976608187134504e-05,
"loss": 0.0016,
"step": 1800
},
{
"epoch": 5.02,
"learning_rate": 4.8940058479532166e-05,
"loss": 0.001,
"step": 1810
},
{
"epoch": 5.02,
"learning_rate": 4.890350877192983e-05,
"loss": 0.0009,
"step": 1820
},
{
"epoch": 5.02,
"eval_accuracy": 0.8355263157894737,
"eval_loss": 1.262323021888733,
"eval_runtime": 47.0551,
"eval_samples_per_second": 3.23,
"eval_steps_per_second": 3.23,
"step": 1824
},
{
"epoch": 6.0,
"learning_rate": 4.886695906432749e-05,
"loss": 0.0011,
"step": 1830
},
{
"epoch": 6.0,
"learning_rate": 4.883040935672515e-05,
"loss": 0.9887,
"step": 1840
},
{
"epoch": 6.0,
"learning_rate": 4.8793859649122806e-05,
"loss": 3.7173,
"step": 1850
},
{
"epoch": 6.0,
"learning_rate": 4.875730994152047e-05,
"loss": 0.0016,
"step": 1860
},
{
"epoch": 6.0,
"learning_rate": 4.872076023391814e-05,
"loss": 0.3775,
"step": 1870
},
{
"epoch": 6.0,
"learning_rate": 4.868421052631579e-05,
"loss": 0.0019,
"step": 1880
},
{
"epoch": 6.0,
"learning_rate": 4.864766081871345e-05,
"loss": 0.6058,
"step": 1890
},
{
"epoch": 6.0,
"learning_rate": 4.8611111111111115e-05,
"loss": 0.0043,
"step": 1900
},
{
"epoch": 6.01,
"learning_rate": 4.857456140350877e-05,
"loss": 0.0245,
"step": 1910
},
{
"epoch": 6.01,
"learning_rate": 4.853801169590643e-05,
"loss": 0.6827,
"step": 1920
},
{
"epoch": 6.01,
"learning_rate": 4.85014619883041e-05,
"loss": 0.0009,
"step": 1930
},
{
"epoch": 6.01,
"learning_rate": 4.8464912280701755e-05,
"loss": 0.0012,
"step": 1940
},
{
"epoch": 6.01,
"learning_rate": 4.842836257309942e-05,
"loss": 0.903,
"step": 1950
},
{
"epoch": 6.01,
"learning_rate": 4.839181286549708e-05,
"loss": 0.0007,
"step": 1960
},
{
"epoch": 6.01,
"learning_rate": 4.8355263157894734e-05,
"loss": 0.0013,
"step": 1970
},
{
"epoch": 6.01,
"learning_rate": 4.83187134502924e-05,
"loss": 0.4422,
"step": 1980
},
{
"epoch": 6.01,
"learning_rate": 4.8282163742690064e-05,
"loss": 0.5191,
"step": 1990
},
{
"epoch": 6.01,
"learning_rate": 4.824561403508772e-05,
"loss": 0.9422,
"step": 2000
},
{
"epoch": 6.01,
"learning_rate": 4.820906432748538e-05,
"loss": 0.0007,
"step": 2010
},
{
"epoch": 6.01,
"learning_rate": 4.817251461988304e-05,
"loss": 0.0007,
"step": 2020
},
{
"epoch": 6.01,
"learning_rate": 4.8135964912280704e-05,
"loss": 3.1307,
"step": 2030
},
{
"epoch": 6.01,
"learning_rate": 4.8099415204678366e-05,
"loss": 0.0096,
"step": 2040
},
{
"epoch": 6.01,
"learning_rate": 4.806286549707603e-05,
"loss": 0.0084,
"step": 2050
},
{
"epoch": 6.02,
"learning_rate": 4.802631578947368e-05,
"loss": 0.5807,
"step": 2060
},
{
"epoch": 6.02,
"learning_rate": 4.7989766081871345e-05,
"loss": 0.0027,
"step": 2070
},
{
"epoch": 6.02,
"learning_rate": 4.7953216374269006e-05,
"loss": 0.0034,
"step": 2080
},
{
"epoch": 6.02,
"learning_rate": 4.791666666666667e-05,
"loss": 0.0014,
"step": 2090
},
{
"epoch": 6.02,
"learning_rate": 4.788011695906433e-05,
"loss": 0.0468,
"step": 2100
},
{
"epoch": 6.02,
"learning_rate": 4.784356725146199e-05,
"loss": 0.0009,
"step": 2110
},
{
"epoch": 6.02,
"learning_rate": 4.780701754385965e-05,
"loss": 0.0007,
"step": 2120
},
{
"epoch": 6.02,
"eval_accuracy": 0.7828947368421053,
"eval_loss": 1.4006696939468384,
"eval_runtime": 47.2096,
"eval_samples_per_second": 3.22,
"eval_steps_per_second": 3.22,
"step": 2128
},
{
"epoch": 7.0,
"learning_rate": 4.777046783625731e-05,
"loss": 0.0008,
"step": 2130
},
{
"epoch": 7.0,
"learning_rate": 4.773391812865498e-05,
"loss": 0.0006,
"step": 2140
},
{
"epoch": 7.0,
"learning_rate": 4.769736842105263e-05,
"loss": 0.0005,
"step": 2150
},
{
"epoch": 7.0,
"learning_rate": 4.7660818713450294e-05,
"loss": 0.0006,
"step": 2160
},
{
"epoch": 7.0,
"learning_rate": 4.7624269005847955e-05,
"loss": 0.0008,
"step": 2170
},
{
"epoch": 7.0,
"learning_rate": 4.758771929824562e-05,
"loss": 0.0006,
"step": 2180
},
{
"epoch": 7.0,
"learning_rate": 4.755116959064328e-05,
"loss": 0.0006,
"step": 2190
},
{
"epoch": 7.0,
"learning_rate": 4.751461988304094e-05,
"loss": 0.0157,
"step": 2200
},
{
"epoch": 7.01,
"learning_rate": 4.74780701754386e-05,
"loss": 0.0004,
"step": 2210
},
{
"epoch": 7.01,
"learning_rate": 4.744152046783626e-05,
"loss": 0.1968,
"step": 2220
},
{
"epoch": 7.01,
"learning_rate": 4.740497076023392e-05,
"loss": 0.6604,
"step": 2230
},
{
"epoch": 7.01,
"learning_rate": 4.736842105263158e-05,
"loss": 0.0014,
"step": 2240
},
{
"epoch": 7.01,
"learning_rate": 4.733187134502924e-05,
"loss": 0.462,
"step": 2250
},
{
"epoch": 7.01,
"learning_rate": 4.7295321637426904e-05,
"loss": 0.0004,
"step": 2260
},
{
"epoch": 7.01,
"learning_rate": 4.7258771929824566e-05,
"loss": 0.0003,
"step": 2270
},
{
"epoch": 7.01,
"learning_rate": 4.722222222222222e-05,
"loss": 0.0004,
"step": 2280
},
{
"epoch": 7.01,
"learning_rate": 4.718567251461988e-05,
"loss": 0.0008,
"step": 2290
},
{
"epoch": 7.01,
"learning_rate": 4.714912280701755e-05,
"loss": 0.3205,
"step": 2300
},
{
"epoch": 7.01,
"learning_rate": 4.7112573099415206e-05,
"loss": 0.0014,
"step": 2310
},
{
"epoch": 7.01,
"learning_rate": 4.707602339181287e-05,
"loss": 0.0003,
"step": 2320
},
{
"epoch": 7.01,
"learning_rate": 4.703947368421053e-05,
"loss": 0.0003,
"step": 2330
},
{
"epoch": 7.01,
"learning_rate": 4.7002923976608185e-05,
"loss": 0.7616,
"step": 2340
},
{
"epoch": 7.01,
"learning_rate": 4.696637426900585e-05,
"loss": 0.7425,
"step": 2350
},
{
"epoch": 7.02,
"learning_rate": 4.6929824561403515e-05,
"loss": 1.4038,
"step": 2360
},
{
"epoch": 7.02,
"learning_rate": 4.689327485380117e-05,
"loss": 1.2103,
"step": 2370
},
{
"epoch": 7.02,
"learning_rate": 4.685672514619883e-05,
"loss": 0.2394,
"step": 2380
},
{
"epoch": 7.02,
"learning_rate": 4.6820175438596494e-05,
"loss": 0.0039,
"step": 2390
},
{
"epoch": 7.02,
"learning_rate": 4.678362573099415e-05,
"loss": 0.0005,
"step": 2400
},
{
"epoch": 7.02,
"learning_rate": 4.674707602339182e-05,
"loss": 0.0006,
"step": 2410
},
{
"epoch": 7.02,
"learning_rate": 4.671052631578948e-05,
"loss": 0.6908,
"step": 2420
},
{
"epoch": 7.02,
"learning_rate": 4.6673976608187134e-05,
"loss": 0.254,
"step": 2430
},
{
"epoch": 7.02,
"eval_accuracy": 0.48026315789473684,
"eval_loss": 3.325760841369629,
"eval_runtime": 46.9127,
"eval_samples_per_second": 3.24,
"eval_steps_per_second": 3.24,
"step": 2432
},
{
"epoch": 8.0,
"learning_rate": 4.6637426900584796e-05,
"loss": 1.9359,
"step": 2440
},
{
"epoch": 8.0,
"learning_rate": 4.660087719298246e-05,
"loss": 0.2486,
"step": 2450
},
{
"epoch": 8.0,
"learning_rate": 4.656432748538012e-05,
"loss": 0.7505,
"step": 2460
},
{
"epoch": 8.0,
"learning_rate": 4.652777777777778e-05,
"loss": 0.0036,
"step": 2470
},
{
"epoch": 8.0,
"learning_rate": 4.649122807017544e-05,
"loss": 0.0443,
"step": 2480
},
{
"epoch": 8.0,
"learning_rate": 4.64546783625731e-05,
"loss": 0.0008,
"step": 2490
},
{
"epoch": 8.0,
"learning_rate": 4.641812865497076e-05,
"loss": 0.8541,
"step": 2500
},
{
"epoch": 8.01,
"learning_rate": 4.638157894736843e-05,
"loss": 0.4268,
"step": 2510
},
{
"epoch": 8.01,
"learning_rate": 4.634502923976608e-05,
"loss": 0.689,
"step": 2520
},
{
"epoch": 8.01,
"learning_rate": 4.6308479532163745e-05,
"loss": 0.0007,
"step": 2530
},
{
"epoch": 8.01,
"learning_rate": 4.6271929824561406e-05,
"loss": 0.0019,
"step": 2540
},
{
"epoch": 8.01,
"learning_rate": 4.623538011695907e-05,
"loss": 0.0006,
"step": 2550
},
{
"epoch": 8.01,
"learning_rate": 4.619883040935672e-05,
"loss": 0.0006,
"step": 2560
},
{
"epoch": 8.01,
"learning_rate": 4.616228070175439e-05,
"loss": 0.0003,
"step": 2570
},
{
"epoch": 8.01,
"learning_rate": 4.6125730994152047e-05,
"loss": 0.0005,
"step": 2580
},
{
"epoch": 8.01,
"learning_rate": 4.608918128654971e-05,
"loss": 0.0003,
"step": 2590
},
{
"epoch": 8.01,
"learning_rate": 4.605263157894737e-05,
"loss": 0.0005,
"step": 2600
},
{
"epoch": 8.01,
"learning_rate": 4.601608187134503e-05,
"loss": 0.0005,
"step": 2610
},
{
"epoch": 8.01,
"learning_rate": 4.5979532163742694e-05,
"loss": 0.0003,
"step": 2620
},
{
"epoch": 8.01,
"learning_rate": 4.5942982456140355e-05,
"loss": 0.0003,
"step": 2630
},
{
"epoch": 8.01,
"learning_rate": 4.590643274853802e-05,
"loss": 0.0003,
"step": 2640
},
{
"epoch": 8.01,
"learning_rate": 4.586988304093567e-05,
"loss": 0.0003,
"step": 2650
},
{
"epoch": 8.02,
"learning_rate": 4.5833333333333334e-05,
"loss": 0.0002,
"step": 2660
},
{
"epoch": 8.02,
"learning_rate": 4.5796783625731e-05,
"loss": 0.6512,
"step": 2670
},
{
"epoch": 8.02,
"learning_rate": 4.576023391812866e-05,
"loss": 0.0005,
"step": 2680
},
{
"epoch": 8.02,
"learning_rate": 4.572368421052632e-05,
"loss": 0.0013,
"step": 2690
},
{
"epoch": 8.02,
"learning_rate": 4.568713450292398e-05,
"loss": 0.0002,
"step": 2700
},
{
"epoch": 8.02,
"learning_rate": 4.5650584795321636e-05,
"loss": 0.3564,
"step": 2710
},
{
"epoch": 8.02,
"learning_rate": 4.56140350877193e-05,
"loss": 0.8226,
"step": 2720
},
{
"epoch": 8.02,
"learning_rate": 4.5577485380116966e-05,
"loss": 0.0005,
"step": 2730
},
{
"epoch": 8.02,
"eval_accuracy": 0.868421052631579,
"eval_loss": 1.0089633464813232,
"eval_runtime": 47.3161,
"eval_samples_per_second": 3.212,
"eval_steps_per_second": 3.212,
"step": 2736
},
{
"epoch": 9.0,
"learning_rate": 4.554093567251462e-05,
"loss": 0.0007,
"step": 2740
},
{
"epoch": 9.0,
"learning_rate": 4.550438596491228e-05,
"loss": 0.0003,
"step": 2750
},
{
"epoch": 9.0,
"learning_rate": 4.5467836257309945e-05,
"loss": 0.0007,
"step": 2760
},
{
"epoch": 9.0,
"learning_rate": 4.54312865497076e-05,
"loss": 0.0005,
"step": 2770
},
{
"epoch": 9.0,
"learning_rate": 4.539473684210527e-05,
"loss": 0.0003,
"step": 2780
},
{
"epoch": 9.0,
"learning_rate": 4.535818713450293e-05,
"loss": 0.0003,
"step": 2790
},
{
"epoch": 9.0,
"learning_rate": 4.5321637426900585e-05,
"loss": 0.0002,
"step": 2800
},
{
"epoch": 9.0,
"learning_rate": 4.5285087719298247e-05,
"loss": 0.0003,
"step": 2810
},
{
"epoch": 9.01,
"learning_rate": 4.524853801169591e-05,
"loss": 0.0009,
"step": 2820
},
{
"epoch": 9.01,
"learning_rate": 4.521198830409357e-05,
"loss": 0.0002,
"step": 2830
},
{
"epoch": 9.01,
"learning_rate": 4.517543859649123e-05,
"loss": 0.7,
"step": 2840
},
{
"epoch": 9.01,
"learning_rate": 4.5138888888888894e-05,
"loss": 0.0003,
"step": 2850
},
{
"epoch": 9.01,
"learning_rate": 4.510233918128655e-05,
"loss": 0.0009,
"step": 2860
},
{
"epoch": 9.01,
"learning_rate": 4.506578947368421e-05,
"loss": 0.0002,
"step": 2870
},
{
"epoch": 9.01,
"learning_rate": 4.502923976608187e-05,
"loss": 0.0003,
"step": 2880
},
{
"epoch": 9.01,
"learning_rate": 4.4992690058479534e-05,
"loss": 0.0002,
"step": 2890
},
{
"epoch": 9.01,
"learning_rate": 4.4956140350877196e-05,
"loss": 0.0002,
"step": 2900
},
{
"epoch": 9.01,
"learning_rate": 4.491959064327486e-05,
"loss": 0.0002,
"step": 2910
},
{
"epoch": 9.01,
"learning_rate": 4.488304093567251e-05,
"loss": 0.0003,
"step": 2920
},
{
"epoch": 9.01,
"learning_rate": 4.4846491228070174e-05,
"loss": 0.0004,
"step": 2930
},
{
"epoch": 9.01,
"learning_rate": 4.480994152046784e-05,
"loss": 0.5635,
"step": 2940
},
{
"epoch": 9.01,
"learning_rate": 4.47733918128655e-05,
"loss": 0.8468,
"step": 2950
},
{
"epoch": 9.01,
"learning_rate": 4.473684210526316e-05,
"loss": 0.0018,
"step": 2960
},
{
"epoch": 9.02,
"learning_rate": 4.470029239766082e-05,
"loss": 0.0003,
"step": 2970
},
{
"epoch": 9.02,
"learning_rate": 4.466374269005848e-05,
"loss": 0.0003,
"step": 2980
},
{
"epoch": 9.02,
"learning_rate": 4.4627192982456145e-05,
"loss": 0.0005,
"step": 2990
},
{
"epoch": 9.02,
"learning_rate": 4.4590643274853806e-05,
"loss": 0.0002,
"step": 3000
},
{
"epoch": 9.02,
"learning_rate": 4.455409356725147e-05,
"loss": 0.0002,
"step": 3010
},
{
"epoch": 9.02,
"learning_rate": 4.451754385964912e-05,
"loss": 0.0003,
"step": 3020
},
{
"epoch": 9.02,
"learning_rate": 4.4480994152046785e-05,
"loss": 0.0002,
"step": 3030
},
{
"epoch": 9.02,
"learning_rate": 4.4444444444444447e-05,
"loss": 0.0003,
"step": 3040
},
{
"epoch": 9.02,
"eval_accuracy": 0.7631578947368421,
"eval_loss": 1.6321797370910645,
"eval_runtime": 47.0818,
"eval_samples_per_second": 3.228,
"eval_steps_per_second": 3.228,
"step": 3040
},
{
"epoch": 10.0,
"learning_rate": 4.440789473684211e-05,
"loss": 0.0002,
"step": 3050
},
{
"epoch": 10.0,
"learning_rate": 4.437134502923977e-05,
"loss": 0.0002,
"step": 3060
},
{
"epoch": 10.0,
"learning_rate": 4.433479532163743e-05,
"loss": 0.0003,
"step": 3070
},
{
"epoch": 10.0,
"learning_rate": 4.429824561403509e-05,
"loss": 0.0002,
"step": 3080
},
{
"epoch": 10.0,
"learning_rate": 4.426169590643275e-05,
"loss": 0.0002,
"step": 3090
},
{
"epoch": 10.0,
"learning_rate": 4.422514619883042e-05,
"loss": 0.0002,
"step": 3100
},
{
"epoch": 10.0,
"learning_rate": 4.418859649122807e-05,
"loss": 0.0002,
"step": 3110
},
{
"epoch": 10.01,
"learning_rate": 4.4152046783625734e-05,
"loss": 0.0002,
"step": 3120
},
{
"epoch": 10.01,
"learning_rate": 4.4115497076023396e-05,
"loss": 0.0001,
"step": 3130
},
{
"epoch": 10.01,
"learning_rate": 4.407894736842105e-05,
"loss": 0.0002,
"step": 3140
},
{
"epoch": 10.01,
"learning_rate": 4.404239766081872e-05,
"loss": 0.0002,
"step": 3150
},
{
"epoch": 10.01,
"learning_rate": 4.400584795321638e-05,
"loss": 0.0001,
"step": 3160
},
{
"epoch": 10.01,
"learning_rate": 4.3969298245614036e-05,
"loss": 0.0001,
"step": 3170
},
{
"epoch": 10.01,
"learning_rate": 4.39327485380117e-05,
"loss": 0.0001,
"step": 3180
},
{
"epoch": 10.01,
"learning_rate": 4.389619883040936e-05,
"loss": 0.0002,
"step": 3190
},
{
"epoch": 10.01,
"learning_rate": 4.3859649122807014e-05,
"loss": 0.0002,
"step": 3200
},
{
"epoch": 10.01,
"learning_rate": 4.382309941520468e-05,
"loss": 0.0002,
"step": 3210
},
{
"epoch": 10.01,
"learning_rate": 4.3786549707602345e-05,
"loss": 0.0002,
"step": 3220
},
{
"epoch": 10.01,
"learning_rate": 4.375e-05,
"loss": 0.0001,
"step": 3230
},
{
"epoch": 10.01,
"learning_rate": 4.371345029239766e-05,
"loss": 0.0001,
"step": 3240
},
{
"epoch": 10.01,
"learning_rate": 4.367690058479532e-05,
"loss": 0.0001,
"step": 3250
},
{
"epoch": 10.01,
"learning_rate": 4.3640350877192985e-05,
"loss": 0.0001,
"step": 3260
},
{
"epoch": 10.02,
"learning_rate": 4.3603801169590647e-05,
"loss": 0.0002,
"step": 3270
},
{
"epoch": 10.02,
"learning_rate": 4.356725146198831e-05,
"loss": 0.0001,
"step": 3280
},
{
"epoch": 10.02,
"learning_rate": 4.353070175438596e-05,
"loss": 0.6381,
"step": 3290
},
{
"epoch": 10.02,
"learning_rate": 4.3494152046783625e-05,
"loss": 0.0002,
"step": 3300
},
{
"epoch": 10.02,
"learning_rate": 4.345760233918129e-05,
"loss": 0.8128,
"step": 3310
},
{
"epoch": 10.02,
"learning_rate": 4.342105263157895e-05,
"loss": 0.3064,
"step": 3320
},
{
"epoch": 10.02,
"learning_rate": 4.338450292397661e-05,
"loss": 0.0002,
"step": 3330
},
{
"epoch": 10.02,
"learning_rate": 4.334795321637427e-05,
"loss": 0.0015,
"step": 3340
},
{
"epoch": 10.02,
"eval_accuracy": 0.5394736842105263,
"eval_loss": 3.1927037239074707,
"eval_runtime": 47.1501,
"eval_samples_per_second": 3.224,
"eval_steps_per_second": 3.224,
"step": 3344
},
{
"epoch": 11.0,
"learning_rate": 4.3311403508771934e-05,
"loss": 0.804,
"step": 3350
},
{
"epoch": 11.0,
"learning_rate": 4.327485380116959e-05,
"loss": 0.0004,
"step": 3360
},
{
"epoch": 11.0,
"learning_rate": 4.323830409356726e-05,
"loss": 0.0455,
"step": 3370
},
{
"epoch": 11.0,
"learning_rate": 4.320175438596491e-05,
"loss": 0.5634,
"step": 3380
},
{
"epoch": 11.0,
"learning_rate": 4.3165204678362574e-05,
"loss": 0.5675,
"step": 3390
},
{
"epoch": 11.0,
"learning_rate": 4.3128654970760236e-05,
"loss": 0.8787,
"step": 3400
},
{
"epoch": 11.0,
"learning_rate": 4.30921052631579e-05,
"loss": 0.6544,
"step": 3410
},
{
"epoch": 11.01,
"learning_rate": 4.305555555555556e-05,
"loss": 0.0004,
"step": 3420
},
{
"epoch": 11.01,
"learning_rate": 4.301900584795322e-05,
"loss": 0.0065,
"step": 3430
},
{
"epoch": 11.01,
"learning_rate": 4.298245614035088e-05,
"loss": 1.5072,
"step": 3440
},
{
"epoch": 11.01,
"learning_rate": 4.294590643274854e-05,
"loss": 0.1934,
"step": 3450
},
{
"epoch": 11.01,
"learning_rate": 4.29093567251462e-05,
"loss": 0.001,
"step": 3460
},
{
"epoch": 11.01,
"learning_rate": 4.287280701754386e-05,
"loss": 0.0015,
"step": 3470
},
{
"epoch": 11.01,
"learning_rate": 4.283625730994152e-05,
"loss": 0.0033,
"step": 3480
},
{
"epoch": 11.01,
"learning_rate": 4.2799707602339185e-05,
"loss": 0.8716,
"step": 3490
},
{
"epoch": 11.01,
"learning_rate": 4.2763157894736847e-05,
"loss": 0.8728,
"step": 3500
},
{
"epoch": 11.01,
"learning_rate": 4.27266081871345e-05,
"loss": 0.0034,
"step": 3510
},
{
"epoch": 11.01,
"learning_rate": 4.269005847953216e-05,
"loss": 0.0015,
"step": 3520
},
{
"epoch": 11.01,
"learning_rate": 4.265350877192983e-05,
"loss": 0.0016,
"step": 3530
},
{
"epoch": 11.01,
"learning_rate": 4.261695906432749e-05,
"loss": 0.4228,
"step": 3540
},
{
"epoch": 11.01,
"learning_rate": 4.258040935672515e-05,
"loss": 0.0006,
"step": 3550
},
{
"epoch": 11.01,
"learning_rate": 4.254385964912281e-05,
"loss": 0.6709,
"step": 3560
},
{
"epoch": 11.01,
"learning_rate": 4.2507309941520465e-05,
"loss": 0.0011,
"step": 3570
},
{
"epoch": 11.02,
"learning_rate": 4.2470760233918134e-05,
"loss": 0.0003,
"step": 3580
},
{
"epoch": 11.02,
"learning_rate": 4.2434210526315796e-05,
"loss": 0.0004,
"step": 3590
},
{
"epoch": 11.02,
"learning_rate": 4.239766081871345e-05,
"loss": 0.0003,
"step": 3600
},
{
"epoch": 11.02,
"learning_rate": 4.236111111111111e-05,
"loss": 0.0003,
"step": 3610
},
{
"epoch": 11.02,
"learning_rate": 4.2324561403508774e-05,
"loss": 0.0003,
"step": 3620
},
{
"epoch": 11.02,
"learning_rate": 4.228801169590643e-05,
"loss": 0.0004,
"step": 3630
},
{
"epoch": 11.02,
"learning_rate": 4.22514619883041e-05,
"loss": 0.0006,
"step": 3640
},
{
"epoch": 11.02,
"eval_accuracy": 0.7236842105263158,
"eval_loss": 2.3243277072906494,
"eval_runtime": 47.1709,
"eval_samples_per_second": 3.222,
"eval_steps_per_second": 3.222,
"step": 3648
},
{
"epoch": 12.0,
"learning_rate": 4.221491228070176e-05,
"loss": 0.0002,
"step": 3650
},
{
"epoch": 12.0,
"learning_rate": 4.2178362573099414e-05,
"loss": 0.7666,
"step": 3660
},
{
"epoch": 12.0,
"learning_rate": 4.2141812865497076e-05,
"loss": 0.0003,
"step": 3670
},
{
"epoch": 12.0,
"learning_rate": 4.210526315789474e-05,
"loss": 0.0102,
"step": 3680
},
{
"epoch": 12.0,
"learning_rate": 4.20687134502924e-05,
"loss": 0.0009,
"step": 3690
},
{
"epoch": 12.0,
"learning_rate": 4.203216374269006e-05,
"loss": 0.0003,
"step": 3700
},
{
"epoch": 12.0,
"learning_rate": 4.199561403508772e-05,
"loss": 0.69,
"step": 3710
},
{
"epoch": 12.0,
"learning_rate": 4.195906432748538e-05,
"loss": 0.0014,
"step": 3720
},
{
"epoch": 12.01,
"learning_rate": 4.192251461988304e-05,
"loss": 0.0004,
"step": 3730
},
{
"epoch": 12.01,
"learning_rate": 4.188596491228071e-05,
"loss": 0.0003,
"step": 3740
},
{
"epoch": 12.01,
"learning_rate": 4.184941520467836e-05,
"loss": 0.0002,
"step": 3750
},
{
"epoch": 12.01,
"learning_rate": 4.1812865497076025e-05,
"loss": 0.0006,
"step": 3760
},
{
"epoch": 12.01,
"learning_rate": 4.177631578947369e-05,
"loss": 0.0003,
"step": 3770
},
{
"epoch": 12.01,
"learning_rate": 4.173976608187135e-05,
"loss": 0.8276,
"step": 3780
},
{
"epoch": 12.01,
"learning_rate": 4.1703216374269004e-05,
"loss": 0.0003,
"step": 3790
},
{
"epoch": 12.01,
"learning_rate": 4.166666666666667e-05,
"loss": 0.0008,
"step": 3800
},
{
"epoch": 12.01,
"learning_rate": 4.163011695906433e-05,
"loss": 0.0002,
"step": 3810
},
{
"epoch": 12.01,
"learning_rate": 4.159356725146199e-05,
"loss": 0.0004,
"step": 3820
},
{
"epoch": 12.01,
"learning_rate": 4.155701754385965e-05,
"loss": 0.0004,
"step": 3830
},
{
"epoch": 12.01,
"learning_rate": 4.152046783625731e-05,
"loss": 0.0003,
"step": 3840
},
{
"epoch": 12.01,
"learning_rate": 4.1483918128654974e-05,
"loss": 0.0002,
"step": 3850
},
{
"epoch": 12.01,
"learning_rate": 4.1447368421052636e-05,
"loss": 0.0003,
"step": 3860
},
{
"epoch": 12.01,
"learning_rate": 4.14108187134503e-05,
"loss": 0.5332,
"step": 3870
},
{
"epoch": 12.02,
"learning_rate": 4.137426900584795e-05,
"loss": 0.018,
"step": 3880
},
{
"epoch": 12.02,
"learning_rate": 4.1337719298245614e-05,
"loss": 0.6836,
"step": 3890
},
{
"epoch": 12.02,
"learning_rate": 4.1301169590643276e-05,
"loss": 1.3227,
"step": 3900
},
{
"epoch": 12.02,
"learning_rate": 4.126461988304094e-05,
"loss": 0.0007,
"step": 3910
},
{
"epoch": 12.02,
"learning_rate": 4.12280701754386e-05,
"loss": 0.0008,
"step": 3920
},
{
"epoch": 12.02,
"learning_rate": 4.119152046783626e-05,
"loss": 0.0003,
"step": 3930
},
{
"epoch": 12.02,
"learning_rate": 4.1154970760233916e-05,
"loss": 0.0005,
"step": 3940
},
{
"epoch": 12.02,
"learning_rate": 4.111842105263158e-05,
"loss": 0.0004,
"step": 3950
},
{
"epoch": 12.02,
"eval_accuracy": 0.7960526315789473,
"eval_loss": 1.4877359867095947,
"eval_runtime": 47.0241,
"eval_samples_per_second": 3.232,
"eval_steps_per_second": 3.232,
"step": 3952
},
{
"epoch": 13.0,
"learning_rate": 4.1081871345029247e-05,
"loss": 0.0009,
"step": 3960
},
{
"epoch": 13.0,
"learning_rate": 4.10453216374269e-05,
"loss": 0.0003,
"step": 3970
},
{
"epoch": 13.0,
"learning_rate": 4.100877192982456e-05,
"loss": 0.0002,
"step": 3980
},
{
"epoch": 13.0,
"learning_rate": 4.0972222222222225e-05,
"loss": 0.0002,
"step": 3990
},
{
"epoch": 13.0,
"learning_rate": 4.093567251461988e-05,
"loss": 0.0003,
"step": 4000
},
{
"epoch": 13.0,
"learning_rate": 4.089912280701755e-05,
"loss": 0.6449,
"step": 4010
},
{
"epoch": 13.0,
"learning_rate": 4.086257309941521e-05,
"loss": 0.0003,
"step": 4020
},
{
"epoch": 13.01,
"learning_rate": 4.0826023391812865e-05,
"loss": 0.0004,
"step": 4030
},
{
"epoch": 13.01,
"learning_rate": 4.078947368421053e-05,
"loss": 0.6987,
"step": 4040
},
{
"epoch": 13.01,
"learning_rate": 4.075292397660819e-05,
"loss": 0.9456,
"step": 4050
},
{
"epoch": 13.01,
"learning_rate": 4.071637426900585e-05,
"loss": 0.0006,
"step": 4060
},
{
"epoch": 13.01,
"learning_rate": 4.067982456140351e-05,
"loss": 0.0004,
"step": 4070
},
{
"epoch": 13.01,
"learning_rate": 4.0643274853801174e-05,
"loss": 0.0003,
"step": 4080
},
{
"epoch": 13.01,
"learning_rate": 4.060672514619883e-05,
"loss": 0.0007,
"step": 4090
},
{
"epoch": 13.01,
"learning_rate": 4.057017543859649e-05,
"loss": 0.0002,
"step": 4100
},
{
"epoch": 13.01,
"learning_rate": 4.053362573099415e-05,
"loss": 0.0003,
"step": 4110
},
{
"epoch": 13.01,
"learning_rate": 4.0497076023391814e-05,
"loss": 0.0002,
"step": 4120
},
{
"epoch": 13.01,
"learning_rate": 4.0460526315789476e-05,
"loss": 0.0002,
"step": 4130
},
{
"epoch": 13.01,
"learning_rate": 4.042397660818714e-05,
"loss": 0.0002,
"step": 4140
},
{
"epoch": 13.01,
"learning_rate": 4.038742690058479e-05,
"loss": 0.0001,
"step": 4150
},
{
"epoch": 13.01,
"learning_rate": 4.0350877192982455e-05,
"loss": 0.0002,
"step": 4160
},
{
"epoch": 13.01,
"learning_rate": 4.031432748538012e-05,
"loss": 0.0002,
"step": 4170
},
{
"epoch": 13.02,
"learning_rate": 4.027777777777778e-05,
"loss": 0.0001,
"step": 4180
},
{
"epoch": 13.02,
"learning_rate": 4.024122807017544e-05,
"loss": 0.0001,
"step": 4190
},
{
"epoch": 13.02,
"learning_rate": 4.02046783625731e-05,
"loss": 0.0001,
"step": 4200
},
{
"epoch": 13.02,
"learning_rate": 4.016812865497076e-05,
"loss": 0.0092,
"step": 4210
},
{
"epoch": 13.02,
"learning_rate": 4.0131578947368425e-05,
"loss": 0.0022,
"step": 4220
},
{
"epoch": 13.02,
"learning_rate": 4.009502923976609e-05,
"loss": 0.0001,
"step": 4230
},
{
"epoch": 13.02,
"learning_rate": 4.005847953216375e-05,
"loss": 0.808,
"step": 4240
},
{
"epoch": 13.02,
"learning_rate": 4.0021929824561404e-05,
"loss": 0.0007,
"step": 4250
},
{
"epoch": 13.02,
"eval_accuracy": 0.8223684210526315,
"eval_loss": 1.4013593196868896,
"eval_runtime": 47.3816,
"eval_samples_per_second": 3.208,
"eval_steps_per_second": 3.208,
"step": 4256
},
{
"epoch": 14.0,
"learning_rate": 3.9985380116959065e-05,
"loss": 0.0001,
"step": 4260
},
{
"epoch": 14.0,
"learning_rate": 3.994883040935673e-05,
"loss": 0.0003,
"step": 4270
},
{
"epoch": 14.0,
"learning_rate": 3.991228070175439e-05,
"loss": 0.0004,
"step": 4280
},
{
"epoch": 14.0,
"learning_rate": 3.987573099415205e-05,
"loss": 0.0001,
"step": 4290
},
{
"epoch": 14.0,
"learning_rate": 3.983918128654971e-05,
"loss": 0.0001,
"step": 4300
},
{
"epoch": 14.0,
"learning_rate": 3.980263157894737e-05,
"loss": 0.0001,
"step": 4310
},
{
"epoch": 14.0,
"learning_rate": 3.976608187134503e-05,
"loss": 0.0001,
"step": 4320
},
{
"epoch": 14.0,
"learning_rate": 3.97295321637427e-05,
"loss": 0.0001,
"step": 4330
},
{
"epoch": 14.01,
"learning_rate": 3.969298245614035e-05,
"loss": 0.0002,
"step": 4340
},
{
"epoch": 14.01,
"learning_rate": 3.9656432748538014e-05,
"loss": 0.0001,
"step": 4350
},
{
"epoch": 14.01,
"learning_rate": 3.9619883040935676e-05,
"loss": 0.0001,
"step": 4360
},
{
"epoch": 14.01,
"learning_rate": 3.958333333333333e-05,
"loss": 0.0001,
"step": 4370
},
{
"epoch": 14.01,
"learning_rate": 3.9546783625731e-05,
"loss": 0.0001,
"step": 4380
},
{
"epoch": 14.01,
"learning_rate": 3.951023391812866e-05,
"loss": 0.0336,
"step": 4390
},
{
"epoch": 14.01,
"learning_rate": 3.9473684210526316e-05,
"loss": 1.5794,
"step": 4400
},
{
"epoch": 14.01,
"learning_rate": 3.943713450292398e-05,
"loss": 0.0002,
"step": 4410
},
{
"epoch": 14.01,
"learning_rate": 3.940058479532164e-05,
"loss": 1.639,
"step": 4420
},
{
"epoch": 14.01,
"learning_rate": 3.9364035087719295e-05,
"loss": 0.639,
"step": 4430
},
{
"epoch": 14.01,
"learning_rate": 3.932748538011696e-05,
"loss": 0.8562,
"step": 4440
},
{
"epoch": 14.01,
"learning_rate": 3.9290935672514625e-05,
"loss": 0.0007,
"step": 4450
},
{
"epoch": 14.01,
"learning_rate": 3.925438596491228e-05,
"loss": 0.0006,
"step": 4460
},
{
"epoch": 14.01,
"learning_rate": 3.921783625730994e-05,
"loss": 0.0004,
"step": 4470
},
{
"epoch": 14.01,
"learning_rate": 3.9181286549707604e-05,
"loss": 0.0002,
"step": 4480
},
{
"epoch": 14.02,
"learning_rate": 3.9144736842105265e-05,
"loss": 0.0002,
"step": 4490
},
{
"epoch": 14.02,
"learning_rate": 3.910818713450293e-05,
"loss": 0.0005,
"step": 4500
},
{
"epoch": 14.02,
"learning_rate": 3.907163742690059e-05,
"loss": 0.7884,
"step": 4510
},
{
"epoch": 14.02,
"learning_rate": 3.9035087719298244e-05,
"loss": 0.0002,
"step": 4520
},
{
"epoch": 14.02,
"learning_rate": 3.8998538011695905e-05,
"loss": 0.0006,
"step": 4530
},
{
"epoch": 14.02,
"learning_rate": 3.8961988304093574e-05,
"loss": 0.0008,
"step": 4540
},
{
"epoch": 14.02,
"learning_rate": 3.892543859649123e-05,
"loss": 0.0002,
"step": 4550
},
{
"epoch": 14.02,
"learning_rate": 3.888888888888889e-05,
"loss": 0.0001,
"step": 4560
},
{
"epoch": 14.02,
"eval_accuracy": 0.8486842105263158,
"eval_loss": 0.9946321249008179,
"eval_runtime": 47.0301,
"eval_samples_per_second": 3.232,
"eval_steps_per_second": 3.232,
"step": 4560
},
{
"epoch": 15.0,
"learning_rate": 3.885233918128655e-05,
"loss": 0.0001,
"step": 4570
},
{
"epoch": 15.0,
"learning_rate": 3.8815789473684214e-05,
"loss": 0.0002,
"step": 4580
},
{
"epoch": 15.0,
"learning_rate": 3.877923976608187e-05,
"loss": 0.0002,
"step": 4590
},
{
"epoch": 15.0,
"learning_rate": 3.874269005847954e-05,
"loss": 0.0001,
"step": 4600
},
{
"epoch": 15.0,
"learning_rate": 3.870614035087719e-05,
"loss": 0.0001,
"step": 4610
},
{
"epoch": 15.0,
"learning_rate": 3.8669590643274854e-05,
"loss": 0.0001,
"step": 4620
},
{
"epoch": 15.0,
"learning_rate": 3.8633040935672516e-05,
"loss": 0.0001,
"step": 4630
},
{
"epoch": 15.01,
"learning_rate": 3.859649122807018e-05,
"loss": 0.0001,
"step": 4640
},
{
"epoch": 15.01,
"learning_rate": 3.855994152046784e-05,
"loss": 0.0001,
"step": 4650
},
{
"epoch": 15.01,
"learning_rate": 3.85233918128655e-05,
"loss": 0.0001,
"step": 4660
},
{
"epoch": 15.01,
"learning_rate": 3.848684210526316e-05,
"loss": 0.0001,
"step": 4670
},
{
"epoch": 15.01,
"learning_rate": 3.845029239766082e-05,
"loss": 0.0001,
"step": 4680
},
{
"epoch": 15.01,
"learning_rate": 3.841374269005848e-05,
"loss": 0.0001,
"step": 4690
},
{
"epoch": 15.01,
"learning_rate": 3.837719298245614e-05,
"loss": 0.0001,
"step": 4700
},
{
"epoch": 15.01,
"learning_rate": 3.8340643274853803e-05,
"loss": 0.0002,
"step": 4710
},
{
"epoch": 15.01,
"learning_rate": 3.8304093567251465e-05,
"loss": 0.0003,
"step": 4720
},
{
"epoch": 15.01,
"learning_rate": 3.826754385964913e-05,
"loss": 0.0001,
"step": 4730
},
{
"epoch": 15.01,
"learning_rate": 3.823099415204678e-05,
"loss": 0.0001,
"step": 4740
},
{
"epoch": 15.01,
"learning_rate": 3.8194444444444444e-05,
"loss": 0.0001,
"step": 4750
},
{
"epoch": 15.01,
"learning_rate": 3.815789473684211e-05,
"loss": 0.0001,
"step": 4760
},
{
"epoch": 15.01,
"learning_rate": 3.812134502923977e-05,
"loss": 0.0001,
"step": 4770
},
{
"epoch": 15.01,
"learning_rate": 3.808479532163743e-05,
"loss": 0.0001,
"step": 4780
},
{
"epoch": 15.02,
"learning_rate": 3.804824561403509e-05,
"loss": 0.0001,
"step": 4790
},
{
"epoch": 15.02,
"learning_rate": 3.8011695906432746e-05,
"loss": 0.0001,
"step": 4800
},
{
"epoch": 15.02,
"learning_rate": 3.7975146198830414e-05,
"loss": 0.7319,
"step": 4810
},
{
"epoch": 15.02,
"learning_rate": 3.7938596491228076e-05,
"loss": 0.0001,
"step": 4820
},
{
"epoch": 15.02,
"learning_rate": 3.790204678362573e-05,
"loss": 0.0029,
"step": 4830
},
{
"epoch": 15.02,
"learning_rate": 3.786549707602339e-05,
"loss": 2.1642,
"step": 4840
},
{
"epoch": 15.02,
"learning_rate": 3.7828947368421054e-05,
"loss": 1.7979,
"step": 4850
},
{
"epoch": 15.02,
"learning_rate": 3.7792397660818716e-05,
"loss": 0.6249,
"step": 4860
},
{
"epoch": 15.02,
"eval_accuracy": 0.7960526315789473,
"eval_loss": 1.284746527671814,
"eval_runtime": 47.2184,
"eval_samples_per_second": 3.219,
"eval_steps_per_second": 3.219,
"step": 4864
},
{
"epoch": 16.0,
"learning_rate": 3.775584795321638e-05,
"loss": 0.8518,
"step": 4870
},
{
"epoch": 16.0,
"learning_rate": 3.771929824561404e-05,
"loss": 0.0018,
"step": 4880
},
{
"epoch": 16.0,
"learning_rate": 3.7682748538011695e-05,
"loss": 0.0003,
"step": 4890
},
{
"epoch": 16.0,
"learning_rate": 3.7646198830409356e-05,
"loss": 0.0003,
"step": 4900
},
{
"epoch": 16.0,
"learning_rate": 3.760964912280702e-05,
"loss": 0.0003,
"step": 4910
},
{
"epoch": 16.0,
"learning_rate": 3.757309941520468e-05,
"loss": 0.0004,
"step": 4920
},
{
"epoch": 16.0,
"learning_rate": 3.753654970760234e-05,
"loss": 0.0002,
"step": 4930
},
{
"epoch": 16.0,
"learning_rate": 3.7500000000000003e-05,
"loss": 0.0002,
"step": 4940
},
{
"epoch": 16.01,
"learning_rate": 3.746345029239766e-05,
"loss": 0.0002,
"step": 4950
},
{
"epoch": 16.01,
"learning_rate": 3.742690058479532e-05,
"loss": 0.0003,
"step": 4960
},
{
"epoch": 16.01,
"learning_rate": 3.739035087719299e-05,
"loss": 0.0003,
"step": 4970
},
{
"epoch": 16.01,
"learning_rate": 3.7353801169590644e-05,
"loss": 0.0003,
"step": 4980
},
{
"epoch": 16.01,
"learning_rate": 3.7317251461988305e-05,
"loss": 0.0002,
"step": 4990
},
{
"epoch": 16.01,
"learning_rate": 3.728070175438597e-05,
"loss": 0.0002,
"step": 5000
},
{
"epoch": 16.01,
"learning_rate": 3.724415204678363e-05,
"loss": 0.0001,
"step": 5010
},
{
"epoch": 16.01,
"learning_rate": 3.7207602339181284e-05,
"loss": 0.0002,
"step": 5020
},
{
"epoch": 16.01,
"learning_rate": 3.717105263157895e-05,
"loss": 0.0002,
"step": 5030
},
{
"epoch": 16.01,
"learning_rate": 3.713450292397661e-05,
"loss": 0.0002,
"step": 5040
},
{
"epoch": 16.01,
"learning_rate": 3.709795321637427e-05,
"loss": 0.0002,
"step": 5050
},
{
"epoch": 16.01,
"learning_rate": 3.706140350877193e-05,
"loss": 0.0002,
"step": 5060
},
{
"epoch": 16.01,
"learning_rate": 3.702485380116959e-05,
"loss": 0.0002,
"step": 5070
},
{
"epoch": 16.01,
"learning_rate": 3.6988304093567254e-05,
"loss": 0.0002,
"step": 5080
},
{
"epoch": 16.01,
"learning_rate": 3.6951754385964916e-05,
"loss": 0.0001,
"step": 5090
},
{
"epoch": 16.02,
"learning_rate": 3.691520467836258e-05,
"loss": 0.8018,
"step": 5100
},
{
"epoch": 16.02,
"learning_rate": 3.687865497076023e-05,
"loss": 0.7197,
"step": 5110
},
{
"epoch": 16.02,
"learning_rate": 3.6842105263157895e-05,
"loss": 0.0004,
"step": 5120
},
{
"epoch": 16.02,
"learning_rate": 3.6805555555555556e-05,
"loss": 0.0003,
"step": 5130
},
{
"epoch": 16.02,
"learning_rate": 3.676900584795322e-05,
"loss": 0.5442,
"step": 5140
},
{
"epoch": 16.02,
"learning_rate": 3.673245614035088e-05,
"loss": 0.8529,
"step": 5150
},
{
"epoch": 16.02,
"learning_rate": 3.669590643274854e-05,
"loss": 3.8326,
"step": 5160
},
{
"epoch": 16.02,
"eval_accuracy": 0.7171052631578947,
"eval_loss": 1.7869735956192017,
"eval_runtime": 46.8923,
"eval_samples_per_second": 3.241,
"eval_steps_per_second": 3.241,
"step": 5168
},
{
"epoch": 17.0,
"learning_rate": 3.66593567251462e-05,
"loss": 1.0,
"step": 5170
},
{
"epoch": 17.0,
"learning_rate": 3.662280701754386e-05,
"loss": 0.7623,
"step": 5180
},
{
"epoch": 17.0,
"learning_rate": 3.658625730994153e-05,
"loss": 0.2525,
"step": 5190
},
{
"epoch": 17.0,
"learning_rate": 3.654970760233918e-05,
"loss": 0.8058,
"step": 5200
},
{
"epoch": 17.0,
"learning_rate": 3.6513157894736844e-05,
"loss": 0.1554,
"step": 5210
},
{
"epoch": 17.0,
"learning_rate": 3.6476608187134505e-05,
"loss": 0.0614,
"step": 5220
},
{
"epoch": 17.0,
"learning_rate": 3.644005847953216e-05,
"loss": 0.6195,
"step": 5230
},
{
"epoch": 17.0,
"learning_rate": 3.640350877192983e-05,
"loss": 0.6076,
"step": 5240
},
{
"epoch": 17.01,
"learning_rate": 3.636695906432749e-05,
"loss": 0.001,
"step": 5250
},
{
"epoch": 17.01,
"learning_rate": 3.6330409356725146e-05,
"loss": 0.0022,
"step": 5260
},
{
"epoch": 17.01,
"learning_rate": 3.629385964912281e-05,
"loss": 0.8601,
"step": 5270
},
{
"epoch": 17.01,
"learning_rate": 3.625730994152047e-05,
"loss": 0.0004,
"step": 5280
},
{
"epoch": 17.01,
"learning_rate": 3.622076023391813e-05,
"loss": 0.5252,
"step": 5290
},
{
"epoch": 17.01,
"learning_rate": 3.618421052631579e-05,
"loss": 0.0032,
"step": 5300
},
{
"epoch": 17.01,
"learning_rate": 3.6147660818713454e-05,
"loss": 0.0008,
"step": 5310
},
{
"epoch": 17.01,
"learning_rate": 3.611111111111111e-05,
"loss": 0.0004,
"step": 5320
},
{
"epoch": 17.01,
"learning_rate": 3.607456140350877e-05,
"loss": 0.0005,
"step": 5330
},
{
"epoch": 17.01,
"learning_rate": 3.603801169590643e-05,
"loss": 0.0004,
"step": 5340
},
{
"epoch": 17.01,
"learning_rate": 3.6001461988304095e-05,
"loss": 0.3297,
"step": 5350
},
{
"epoch": 17.01,
"learning_rate": 3.5964912280701756e-05,
"loss": 0.0003,
"step": 5360
},
{
"epoch": 17.01,
"learning_rate": 3.592836257309942e-05,
"loss": 0.0006,
"step": 5370
},
{
"epoch": 17.01,
"learning_rate": 3.589181286549707e-05,
"loss": 0.5398,
"step": 5380
},
{
"epoch": 17.01,
"learning_rate": 3.5855263157894735e-05,
"loss": 0.0002,
"step": 5390
},
{
"epoch": 17.02,
"learning_rate": 3.5818713450292403e-05,
"loss": 0.2316,
"step": 5400
},
{
"epoch": 17.02,
"learning_rate": 3.578216374269006e-05,
"loss": 0.0003,
"step": 5410
},
{
"epoch": 17.02,
"learning_rate": 3.574561403508772e-05,
"loss": 0.0001,
"step": 5420
},
{
"epoch": 17.02,
"learning_rate": 3.570906432748538e-05,
"loss": 0.0002,
"step": 5430
},
{
"epoch": 17.02,
"learning_rate": 3.5672514619883044e-05,
"loss": 0.0003,
"step": 5440
},
{
"epoch": 17.02,
"learning_rate": 3.5635964912280705e-05,
"loss": 0.7463,
"step": 5450
},
{
"epoch": 17.02,
"learning_rate": 3.559941520467837e-05,
"loss": 0.0002,
"step": 5460
},
{
"epoch": 17.02,
"learning_rate": 3.556286549707602e-05,
"loss": 0.0646,
"step": 5470
},
{
"epoch": 17.02,
"eval_accuracy": 0.6578947368421053,
"eval_loss": 2.3503501415252686,
"eval_runtime": 46.9289,
"eval_samples_per_second": 3.239,
"eval_steps_per_second": 3.239,
"step": 5472
},
{
"epoch": 18.0,
"learning_rate": 3.5526315789473684e-05,
"loss": 0.699,
"step": 5480
},
{
"epoch": 18.0,
"learning_rate": 3.5489766081871346e-05,
"loss": 0.0003,
"step": 5490
},
{
"epoch": 18.0,
"learning_rate": 3.545321637426901e-05,
"loss": 0.0002,
"step": 5500
},
{
"epoch": 18.0,
"learning_rate": 3.541666666666667e-05,
"loss": 0.0007,
"step": 5510
},
{
"epoch": 18.0,
"learning_rate": 3.538011695906433e-05,
"loss": 0.0002,
"step": 5520
},
{
"epoch": 18.0,
"learning_rate": 3.534356725146199e-05,
"loss": 0.0003,
"step": 5530
},
{
"epoch": 18.0,
"learning_rate": 3.530701754385965e-05,
"loss": 0.5871,
"step": 5540
},
{
"epoch": 18.01,
"learning_rate": 3.527046783625731e-05,
"loss": 0.0011,
"step": 5550
},
{
"epoch": 18.01,
"learning_rate": 3.523391812865498e-05,
"loss": 0.7018,
"step": 5560
},
{
"epoch": 18.01,
"learning_rate": 3.519736842105263e-05,
"loss": 0.0005,
"step": 5570
},
{
"epoch": 18.01,
"learning_rate": 3.5160818713450295e-05,
"loss": 0.0003,
"step": 5580
},
{
"epoch": 18.01,
"learning_rate": 3.5124269005847956e-05,
"loss": 0.0002,
"step": 5590
},
{
"epoch": 18.01,
"learning_rate": 3.508771929824561e-05,
"loss": 0.7385,
"step": 5600
},
{
"epoch": 18.01,
"learning_rate": 3.505116959064328e-05,
"loss": 0.0002,
"step": 5610
},
{
"epoch": 18.01,
"learning_rate": 3.501461988304094e-05,
"loss": 0.0004,
"step": 5620
},
{
"epoch": 18.01,
"learning_rate": 3.49780701754386e-05,
"loss": 0.0004,
"step": 5630
},
{
"epoch": 18.01,
"learning_rate": 3.494152046783626e-05,
"loss": 0.0148,
"step": 5640
},
{
"epoch": 18.01,
"learning_rate": 3.490497076023392e-05,
"loss": 0.2118,
"step": 5650
},
{
"epoch": 18.01,
"learning_rate": 3.4868421052631575e-05,
"loss": 0.0004,
"step": 5660
},
{
"epoch": 18.01,
"learning_rate": 3.4831871345029244e-05,
"loss": 0.0003,
"step": 5670
},
{
"epoch": 18.01,
"learning_rate": 3.4795321637426905e-05,
"loss": 0.0003,
"step": 5680
},
{
"epoch": 18.01,
"learning_rate": 3.475877192982456e-05,
"loss": 0.6305,
"step": 5690
},
{
"epoch": 18.02,
"learning_rate": 3.472222222222222e-05,
"loss": 0.0009,
"step": 5700
},
{
"epoch": 18.02,
"learning_rate": 3.4685672514619884e-05,
"loss": 1.0822,
"step": 5710
},
{
"epoch": 18.02,
"learning_rate": 3.4649122807017546e-05,
"loss": 0.0038,
"step": 5720
},
{
"epoch": 18.02,
"learning_rate": 3.461257309941521e-05,
"loss": 1.0141,
"step": 5730
},
{
"epoch": 18.02,
"learning_rate": 3.457602339181287e-05,
"loss": 0.2828,
"step": 5740
},
{
"epoch": 18.02,
"learning_rate": 3.4539473684210524e-05,
"loss": 0.0065,
"step": 5750
},
{
"epoch": 18.02,
"learning_rate": 3.4502923976608186e-05,
"loss": 0.7353,
"step": 5760
},
{
"epoch": 18.02,
"learning_rate": 3.4466374269005854e-05,
"loss": 0.0003,
"step": 5770
},
{
"epoch": 18.02,
"eval_accuracy": 0.8618421052631579,
"eval_loss": 0.9367402791976929,
"eval_runtime": 47.2171,
"eval_samples_per_second": 3.219,
"eval_steps_per_second": 3.219,
"step": 5776
},
{
"epoch": 19.0,
"learning_rate": 3.442982456140351e-05,
"loss": 0.0007,
"step": 5780
},
{
"epoch": 19.0,
"learning_rate": 3.439327485380117e-05,
"loss": 0.0005,
"step": 5790
},
{
"epoch": 19.0,
"learning_rate": 3.435672514619883e-05,
"loss": 0.0003,
"step": 5800
},
{
"epoch": 19.0,
"learning_rate": 3.4320175438596495e-05,
"loss": 0.0004,
"step": 5810
},
{
"epoch": 19.0,
"learning_rate": 3.428362573099415e-05,
"loss": 0.0002,
"step": 5820
},
{
"epoch": 19.0,
"learning_rate": 3.424707602339182e-05,
"loss": 0.6674,
"step": 5830
},
{
"epoch": 19.0,
"learning_rate": 3.421052631578947e-05,
"loss": 0.0002,
"step": 5840
},
{
"epoch": 19.0,
"learning_rate": 3.4173976608187135e-05,
"loss": 0.0013,
"step": 5850
},
{
"epoch": 19.01,
"learning_rate": 3.41374269005848e-05,
"loss": 0.0009,
"step": 5860
},
{
"epoch": 19.01,
"learning_rate": 3.410087719298246e-05,
"loss": 0.7814,
"step": 5870
},
{
"epoch": 19.01,
"learning_rate": 3.406432748538012e-05,
"loss": 0.0003,
"step": 5880
},
{
"epoch": 19.01,
"learning_rate": 3.402777777777778e-05,
"loss": 0.001,
"step": 5890
},
{
"epoch": 19.01,
"learning_rate": 3.3991228070175444e-05,
"loss": 0.0004,
"step": 5900
},
{
"epoch": 19.01,
"learning_rate": 3.39546783625731e-05,
"loss": 0.0002,
"step": 5910
},
{
"epoch": 19.01,
"learning_rate": 3.391812865497076e-05,
"loss": 0.0005,
"step": 5920
},
{
"epoch": 19.01,
"learning_rate": 3.388157894736842e-05,
"loss": 0.0003,
"step": 5930
},
{
"epoch": 19.01,
"learning_rate": 3.3845029239766084e-05,
"loss": 0.0003,
"step": 5940
},
{
"epoch": 19.01,
"learning_rate": 3.3808479532163746e-05,
"loss": 0.0002,
"step": 5950
},
{
"epoch": 19.01,
"learning_rate": 3.377192982456141e-05,
"loss": 0.2685,
"step": 5960
},
{
"epoch": 19.01,
"learning_rate": 3.373538011695906e-05,
"loss": 0.0005,
"step": 5970
},
{
"epoch": 19.01,
"learning_rate": 3.3698830409356724e-05,
"loss": 0.0001,
"step": 5980
},
{
"epoch": 19.01,
"learning_rate": 3.366228070175439e-05,
"loss": 0.0002,
"step": 5990
},
{
"epoch": 19.01,
"learning_rate": 3.362573099415205e-05,
"loss": 0.7894,
"step": 6000
},
{
"epoch": 19.02,
"learning_rate": 3.358918128654971e-05,
"loss": 0.0004,
"step": 6010
},
{
"epoch": 19.02,
"learning_rate": 3.355263157894737e-05,
"loss": 0.0002,
"step": 6020
},
{
"epoch": 19.02,
"learning_rate": 3.3516081871345026e-05,
"loss": 0.0003,
"step": 6030
},
{
"epoch": 19.02,
"learning_rate": 3.3479532163742695e-05,
"loss": 0.7653,
"step": 6040
},
{
"epoch": 19.02,
"learning_rate": 3.3442982456140356e-05,
"loss": 0.0005,
"step": 6050
},
{
"epoch": 19.02,
"learning_rate": 3.340643274853801e-05,
"loss": 0.0016,
"step": 6060
},
{
"epoch": 19.02,
"learning_rate": 3.336988304093567e-05,
"loss": 0.0007,
"step": 6070
},
{
"epoch": 19.02,
"learning_rate": 3.3333333333333335e-05,
"loss": 0.0004,
"step": 6080
},
{
"epoch": 19.02,
"eval_accuracy": 0.631578947368421,
"eval_loss": 2.570972204208374,
"eval_runtime": 47.042,
"eval_samples_per_second": 3.231,
"eval_steps_per_second": 3.231,
"step": 6080
},
{
"epoch": 20.0,
"learning_rate": 3.3296783625731e-05,
"loss": 0.0003,
"step": 6090
},
{
"epoch": 20.0,
"learning_rate": 3.326023391812866e-05,
"loss": 0.5715,
"step": 6100
},
{
"epoch": 20.0,
"learning_rate": 3.322368421052632e-05,
"loss": 0.0003,
"step": 6110
},
{
"epoch": 20.0,
"learning_rate": 3.3187134502923975e-05,
"loss": 0.0002,
"step": 6120
},
{
"epoch": 20.0,
"learning_rate": 3.315058479532164e-05,
"loss": 0.0002,
"step": 6130
},
{
"epoch": 20.0,
"learning_rate": 3.31140350877193e-05,
"loss": 0.0002,
"step": 6140
},
{
"epoch": 20.0,
"learning_rate": 3.307748538011696e-05,
"loss": 0.0003,
"step": 6150
},
{
"epoch": 20.01,
"learning_rate": 3.304093567251462e-05,
"loss": 0.0008,
"step": 6160
},
{
"epoch": 20.01,
"learning_rate": 3.3004385964912284e-05,
"loss": 0.0001,
"step": 6170
},
{
"epoch": 20.01,
"learning_rate": 3.296783625730994e-05,
"loss": 0.3366,
"step": 6180
},
{
"epoch": 20.01,
"learning_rate": 3.29312865497076e-05,
"loss": 0.0002,
"step": 6190
},
{
"epoch": 20.01,
"learning_rate": 3.289473684210527e-05,
"loss": 0.0004,
"step": 6200
},
{
"epoch": 20.01,
"learning_rate": 3.2858187134502924e-05,
"loss": 0.0001,
"step": 6210
},
{
"epoch": 20.01,
"learning_rate": 3.2821637426900586e-05,
"loss": 0.0002,
"step": 6220
},
{
"epoch": 20.01,
"learning_rate": 3.278508771929825e-05,
"loss": 0.0001,
"step": 6230
},
{
"epoch": 20.01,
"learning_rate": 3.274853801169591e-05,
"loss": 0.0001,
"step": 6240
},
{
"epoch": 20.01,
"learning_rate": 3.271198830409357e-05,
"loss": 0.0002,
"step": 6250
},
{
"epoch": 20.01,
"learning_rate": 3.267543859649123e-05,
"loss": 0.6344,
"step": 6260
},
{
"epoch": 20.01,
"learning_rate": 3.263888888888889e-05,
"loss": 0.0001,
"step": 6270
},
{
"epoch": 20.01,
"learning_rate": 3.260233918128655e-05,
"loss": 0.0003,
"step": 6280
},
{
"epoch": 20.01,
"learning_rate": 3.256578947368421e-05,
"loss": 0.0001,
"step": 6290
},
{
"epoch": 20.01,
"learning_rate": 3.252923976608187e-05,
"loss": 0.8859,
"step": 6300
},
{
"epoch": 20.02,
"learning_rate": 3.2492690058479535e-05,
"loss": 0.0002,
"step": 6310
},
{
"epoch": 20.02,
"learning_rate": 3.24561403508772e-05,
"loss": 0.0003,
"step": 6320
},
{
"epoch": 20.02,
"learning_rate": 3.241959064327486e-05,
"loss": 0.0003,
"step": 6330
},
{
"epoch": 20.02,
"learning_rate": 3.2383040935672513e-05,
"loss": 0.7744,
"step": 6340
},
{
"epoch": 20.02,
"learning_rate": 3.2346491228070175e-05,
"loss": 0.6233,
"step": 6350
},
{
"epoch": 20.02,
"learning_rate": 3.230994152046784e-05,
"loss": 0.563,
"step": 6360
},
{
"epoch": 20.02,
"learning_rate": 3.22733918128655e-05,
"loss": 0.0005,
"step": 6370
},
{
"epoch": 20.02,
"learning_rate": 3.223684210526316e-05,
"loss": 0.5626,
"step": 6380
},
{
"epoch": 20.02,
"eval_accuracy": 0.6842105263157895,
"eval_loss": 2.671112537384033,
"eval_runtime": 46.8486,
"eval_samples_per_second": 3.244,
"eval_steps_per_second": 3.244,
"step": 6384
},
{
"epoch": 21.0,
"learning_rate": 3.220029239766082e-05,
"loss": 0.0005,
"step": 6390
},
{
"epoch": 21.0,
"learning_rate": 3.216374269005848e-05,
"loss": 0.001,
"step": 6400
},
{
"epoch": 21.0,
"learning_rate": 3.2127192982456146e-05,
"loss": 0.0002,
"step": 6410
},
{
"epoch": 21.0,
"learning_rate": 3.209064327485381e-05,
"loss": 0.0286,
"step": 6420
},
{
"epoch": 21.0,
"learning_rate": 3.205409356725146e-05,
"loss": 0.0005,
"step": 6430
},
{
"epoch": 21.0,
"learning_rate": 3.2017543859649124e-05,
"loss": 0.0002,
"step": 6440
},
{
"epoch": 21.0,
"learning_rate": 3.1980994152046786e-05,
"loss": 0.5486,
"step": 6450
},
{
"epoch": 21.0,
"learning_rate": 3.194444444444444e-05,
"loss": 0.006,
"step": 6460
},
{
"epoch": 21.01,
"learning_rate": 3.190789473684211e-05,
"loss": 0.0004,
"step": 6470
},
{
"epoch": 21.01,
"learning_rate": 3.187134502923977e-05,
"loss": 0.0003,
"step": 6480
},
{
"epoch": 21.01,
"learning_rate": 3.1834795321637426e-05,
"loss": 0.0003,
"step": 6490
},
{
"epoch": 21.01,
"learning_rate": 3.179824561403509e-05,
"loss": 0.0003,
"step": 6500
},
{
"epoch": 21.01,
"learning_rate": 3.176169590643275e-05,
"loss": 0.0002,
"step": 6510
},
{
"epoch": 21.01,
"learning_rate": 3.172514619883041e-05,
"loss": 0.0002,
"step": 6520
},
{
"epoch": 21.01,
"learning_rate": 3.168859649122807e-05,
"loss": 0.0001,
"step": 6530
},
{
"epoch": 21.01,
"learning_rate": 3.1652046783625735e-05,
"loss": 0.0001,
"step": 6540
},
{
"epoch": 21.01,
"learning_rate": 3.161549707602339e-05,
"loss": 0.0001,
"step": 6550
},
{
"epoch": 21.01,
"learning_rate": 3.157894736842105e-05,
"loss": 0.0001,
"step": 6560
},
{
"epoch": 21.01,
"learning_rate": 3.154239766081872e-05,
"loss": 0.0002,
"step": 6570
},
{
"epoch": 21.01,
"learning_rate": 3.1505847953216375e-05,
"loss": 0.0001,
"step": 6580
},
{
"epoch": 21.01,
"learning_rate": 3.146929824561404e-05,
"loss": 0.0001,
"step": 6590
},
{
"epoch": 21.01,
"learning_rate": 3.14327485380117e-05,
"loss": 0.0001,
"step": 6600
},
{
"epoch": 21.01,
"learning_rate": 3.1396198830409354e-05,
"loss": 0.0002,
"step": 6610
},
{
"epoch": 21.02,
"learning_rate": 3.1359649122807015e-05,
"loss": 0.0001,
"step": 6620
},
{
"epoch": 21.02,
"learning_rate": 3.1323099415204684e-05,
"loss": 0.003,
"step": 6630
},
{
"epoch": 21.02,
"learning_rate": 3.128654970760234e-05,
"loss": 0.6328,
"step": 6640
},
{
"epoch": 21.02,
"learning_rate": 3.125e-05,
"loss": 0.0002,
"step": 6650
},
{
"epoch": 21.02,
"learning_rate": 3.121345029239766e-05,
"loss": 0.0001,
"step": 6660
},
{
"epoch": 21.02,
"learning_rate": 3.1176900584795324e-05,
"loss": 0.0001,
"step": 6670
},
{
"epoch": 21.02,
"learning_rate": 3.1140350877192986e-05,
"loss": 0.9002,
"step": 6680
},
{
"epoch": 21.02,
"eval_accuracy": 0.756578947368421,
"eval_loss": 2.145613431930542,
"eval_runtime": 47.0796,
"eval_samples_per_second": 3.229,
"eval_steps_per_second": 3.229,
"step": 6688
},
{
"epoch": 22.0,
"learning_rate": 3.110380116959065e-05,
"loss": 0.5744,
"step": 6690
},
{
"epoch": 22.0,
"learning_rate": 3.10672514619883e-05,
"loss": 0.0005,
"step": 6700
},
{
"epoch": 22.0,
"learning_rate": 3.1030701754385964e-05,
"loss": 0.2875,
"step": 6710
},
{
"epoch": 22.0,
"learning_rate": 3.0994152046783626e-05,
"loss": 0.0002,
"step": 6720
},
{
"epoch": 22.0,
"learning_rate": 3.095760233918129e-05,
"loss": 0.0002,
"step": 6730
},
{
"epoch": 22.0,
"learning_rate": 3.092105263157895e-05,
"loss": 0.0001,
"step": 6740
},
{
"epoch": 22.0,
"learning_rate": 3.088450292397661e-05,
"loss": 0.0001,
"step": 6750
},
{
"epoch": 22.0,
"learning_rate": 3.084795321637427e-05,
"loss": 0.0001,
"step": 6760
},
{
"epoch": 22.01,
"learning_rate": 3.081140350877193e-05,
"loss": 0.0002,
"step": 6770
},
{
"epoch": 22.01,
"learning_rate": 3.077485380116959e-05,
"loss": 0.0002,
"step": 6780
},
{
"epoch": 22.01,
"learning_rate": 3.073830409356726e-05,
"loss": 0.0001,
"step": 6790
},
{
"epoch": 22.01,
"learning_rate": 3.0701754385964913e-05,
"loss": 0.687,
"step": 6800
},
{
"epoch": 22.01,
"learning_rate": 3.0665204678362575e-05,
"loss": 0.0003,
"step": 6810
},
{
"epoch": 22.01,
"learning_rate": 3.062865497076024e-05,
"loss": 0.0002,
"step": 6820
},
{
"epoch": 22.01,
"learning_rate": 3.059210526315789e-05,
"loss": 0.0001,
"step": 6830
},
{
"epoch": 22.01,
"learning_rate": 3.055555555555556e-05,
"loss": 0.5384,
"step": 6840
},
{
"epoch": 22.01,
"learning_rate": 3.051900584795322e-05,
"loss": 0.0001,
"step": 6850
},
{
"epoch": 22.01,
"learning_rate": 3.048245614035088e-05,
"loss": 0.8885,
"step": 6860
},
{
"epoch": 22.01,
"learning_rate": 3.044590643274854e-05,
"loss": 0.001,
"step": 6870
},
{
"epoch": 22.01,
"learning_rate": 3.0409356725146197e-05,
"loss": 0.0006,
"step": 6880
},
{
"epoch": 22.01,
"learning_rate": 3.037280701754386e-05,
"loss": 0.0001,
"step": 6890
},
{
"epoch": 22.01,
"learning_rate": 3.0336257309941524e-05,
"loss": 0.0006,
"step": 6900
},
{
"epoch": 22.01,
"learning_rate": 3.0299707602339183e-05,
"loss": 0.0001,
"step": 6910
},
{
"epoch": 22.02,
"learning_rate": 3.0263157894736844e-05,
"loss": 0.914,
"step": 6920
},
{
"epoch": 22.02,
"learning_rate": 3.0226608187134503e-05,
"loss": 0.0002,
"step": 6930
},
{
"epoch": 22.02,
"learning_rate": 3.0190058479532164e-05,
"loss": 0.0007,
"step": 6940
},
{
"epoch": 22.02,
"learning_rate": 3.015350877192983e-05,
"loss": 0.0003,
"step": 6950
},
{
"epoch": 22.02,
"learning_rate": 3.0116959064327488e-05,
"loss": 0.0001,
"step": 6960
},
{
"epoch": 22.02,
"learning_rate": 3.0080409356725146e-05,
"loss": 0.0001,
"step": 6970
},
{
"epoch": 22.02,
"learning_rate": 3.0043859649122808e-05,
"loss": 0.0001,
"step": 6980
},
{
"epoch": 22.02,
"learning_rate": 3.0007309941520466e-05,
"loss": 0.0002,
"step": 6990
},
{
"epoch": 22.02,
"eval_accuracy": 0.7236842105263158,
"eval_loss": 2.348767042160034,
"eval_runtime": 47.0604,
"eval_samples_per_second": 3.23,
"eval_steps_per_second": 3.23,
"step": 6992
},
{
"epoch": 23.0,
"learning_rate": 2.997076023391813e-05,
"loss": 0.0001,
"step": 7000
},
{
"epoch": 23.0,
"learning_rate": 2.9934210526315793e-05,
"loss": 0.0001,
"step": 7010
},
{
"epoch": 23.0,
"learning_rate": 2.989766081871345e-05,
"loss": 0.0001,
"step": 7020
},
{
"epoch": 23.0,
"learning_rate": 2.9861111111111113e-05,
"loss": 0.0001,
"step": 7030
},
{
"epoch": 23.0,
"learning_rate": 2.9824561403508772e-05,
"loss": 0.0001,
"step": 7040
},
{
"epoch": 23.0,
"learning_rate": 2.978801169590643e-05,
"loss": 0.0001,
"step": 7050
},
{
"epoch": 23.0,
"learning_rate": 2.9751461988304095e-05,
"loss": 0.0001,
"step": 7060
},
{
"epoch": 23.01,
"learning_rate": 2.9714912280701757e-05,
"loss": 0.0001,
"step": 7070
},
{
"epoch": 23.01,
"learning_rate": 2.9678362573099415e-05,
"loss": 0.0001,
"step": 7080
},
{
"epoch": 23.01,
"learning_rate": 2.9641812865497077e-05,
"loss": 0.0001,
"step": 7090
},
{
"epoch": 23.01,
"learning_rate": 2.9605263157894735e-05,
"loss": 0.0001,
"step": 7100
},
{
"epoch": 23.01,
"learning_rate": 2.95687134502924e-05,
"loss": 0.0001,
"step": 7110
},
{
"epoch": 23.01,
"learning_rate": 2.9532163742690062e-05,
"loss": 0.0001,
"step": 7120
},
{
"epoch": 23.01,
"learning_rate": 2.949561403508772e-05,
"loss": 0.0001,
"step": 7130
},
{
"epoch": 23.01,
"learning_rate": 2.945906432748538e-05,
"loss": 0.0001,
"step": 7140
},
{
"epoch": 23.01,
"learning_rate": 2.942251461988304e-05,
"loss": 0.0001,
"step": 7150
},
{
"epoch": 23.01,
"learning_rate": 2.9385964912280706e-05,
"loss": 0.0001,
"step": 7160
},
{
"epoch": 23.01,
"learning_rate": 2.9349415204678364e-05,
"loss": 0.0001,
"step": 7170
},
{
"epoch": 23.01,
"learning_rate": 2.9312865497076026e-05,
"loss": 0.0001,
"step": 7180
},
{
"epoch": 23.01,
"learning_rate": 2.9276315789473684e-05,
"loss": 0.0001,
"step": 7190
},
{
"epoch": 23.01,
"learning_rate": 2.9239766081871346e-05,
"loss": 0.0001,
"step": 7200
},
{
"epoch": 23.01,
"learning_rate": 2.9203216374269005e-05,
"loss": 0.0001,
"step": 7210
},
{
"epoch": 23.02,
"learning_rate": 2.916666666666667e-05,
"loss": 0.0001,
"step": 7220
},
{
"epoch": 23.02,
"learning_rate": 2.9130116959064328e-05,
"loss": 0.0019,
"step": 7230
},
{
"epoch": 23.02,
"learning_rate": 2.909356725146199e-05,
"loss": 0.0001,
"step": 7240
},
{
"epoch": 23.02,
"learning_rate": 2.9057017543859648e-05,
"loss": 0.0003,
"step": 7250
},
{
"epoch": 23.02,
"learning_rate": 2.902046783625731e-05,
"loss": 0.7434,
"step": 7260
},
{
"epoch": 23.02,
"learning_rate": 2.8983918128654975e-05,
"loss": 0.0001,
"step": 7270
},
{
"epoch": 23.02,
"learning_rate": 2.8947368421052634e-05,
"loss": 0.0001,
"step": 7280
},
{
"epoch": 23.02,
"learning_rate": 2.8910818713450295e-05,
"loss": 0.6977,
"step": 7290
},
{
"epoch": 23.02,
"eval_accuracy": 0.8092105263157895,
"eval_loss": 1.501329779624939,
"eval_runtime": 47.1967,
"eval_samples_per_second": 3.221,
"eval_steps_per_second": 3.221,
"step": 7296
},
{
"epoch": 24.0,
"learning_rate": 2.8874269005847954e-05,
"loss": 0.0001,
"step": 7300
},
{
"epoch": 24.0,
"learning_rate": 2.8837719298245612e-05,
"loss": 0.0003,
"step": 7310
},
{
"epoch": 24.0,
"learning_rate": 2.8801169590643277e-05,
"loss": 0.0001,
"step": 7320
},
{
"epoch": 24.0,
"learning_rate": 2.876461988304094e-05,
"loss": 0.0001,
"step": 7330
},
{
"epoch": 24.0,
"learning_rate": 2.8728070175438597e-05,
"loss": 0.0001,
"step": 7340
},
{
"epoch": 24.0,
"learning_rate": 2.869152046783626e-05,
"loss": 0.0001,
"step": 7350
},
{
"epoch": 24.0,
"learning_rate": 2.8654970760233917e-05,
"loss": 0.0001,
"step": 7360
},
{
"epoch": 24.0,
"learning_rate": 2.861842105263158e-05,
"loss": 0.0001,
"step": 7370
},
{
"epoch": 24.01,
"learning_rate": 2.8581871345029244e-05,
"loss": 0.0001,
"step": 7380
},
{
"epoch": 24.01,
"learning_rate": 2.8545321637426903e-05,
"loss": 0.0001,
"step": 7390
},
{
"epoch": 24.01,
"learning_rate": 2.850877192982456e-05,
"loss": 0.0,
"step": 7400
},
{
"epoch": 24.01,
"learning_rate": 2.8472222222222223e-05,
"loss": 0.0001,
"step": 7410
},
{
"epoch": 24.01,
"learning_rate": 2.843567251461988e-05,
"loss": 0.0001,
"step": 7420
},
{
"epoch": 24.01,
"learning_rate": 2.8399122807017546e-05,
"loss": 0.0001,
"step": 7430
},
{
"epoch": 24.01,
"learning_rate": 2.8362573099415208e-05,
"loss": 0.0001,
"step": 7440
},
{
"epoch": 24.01,
"learning_rate": 2.8326023391812866e-05,
"loss": 0.0001,
"step": 7450
},
{
"epoch": 24.01,
"learning_rate": 2.8289473684210528e-05,
"loss": 0.0001,
"step": 7460
},
{
"epoch": 24.01,
"learning_rate": 2.8252923976608186e-05,
"loss": 0.0001,
"step": 7470
},
{
"epoch": 24.01,
"learning_rate": 2.821637426900585e-05,
"loss": 0.0,
"step": 7480
},
{
"epoch": 24.01,
"learning_rate": 2.817982456140351e-05,
"loss": 0.0001,
"step": 7490
},
{
"epoch": 24.01,
"learning_rate": 2.8143274853801172e-05,
"loss": 0.0001,
"step": 7500
},
{
"epoch": 24.01,
"learning_rate": 2.810672514619883e-05,
"loss": 0.0001,
"step": 7510
},
{
"epoch": 24.01,
"learning_rate": 2.8070175438596492e-05,
"loss": 0.0,
"step": 7520
},
{
"epoch": 24.02,
"learning_rate": 2.803362573099415e-05,
"loss": 0.0001,
"step": 7530
},
{
"epoch": 24.02,
"learning_rate": 2.7997076023391815e-05,
"loss": 0.0001,
"step": 7540
},
{
"epoch": 24.02,
"learning_rate": 2.7960526315789477e-05,
"loss": 0.0001,
"step": 7550
},
{
"epoch": 24.02,
"learning_rate": 2.7923976608187135e-05,
"loss": 0.0,
"step": 7560
},
{
"epoch": 24.02,
"learning_rate": 2.7887426900584794e-05,
"loss": 0.0001,
"step": 7570
},
{
"epoch": 24.02,
"learning_rate": 2.7850877192982456e-05,
"loss": 0.0,
"step": 7580
},
{
"epoch": 24.02,
"learning_rate": 2.781432748538012e-05,
"loss": 0.0001,
"step": 7590
},
{
"epoch": 24.02,
"learning_rate": 2.777777777777778e-05,
"loss": 0.0001,
"step": 7600
},
{
"epoch": 24.02,
"eval_accuracy": 0.7763157894736842,
"eval_loss": 1.9441945552825928,
"eval_runtime": 47.0827,
"eval_samples_per_second": 3.228,
"eval_steps_per_second": 3.228,
"step": 7600
},
{
"epoch": 25.0,
"learning_rate": 2.774122807017544e-05,
"loss": 0.0,
"step": 7610
},
{
"epoch": 25.0,
"learning_rate": 2.77046783625731e-05,
"loss": 0.0,
"step": 7620
},
{
"epoch": 25.0,
"learning_rate": 2.766812865497076e-05,
"loss": 0.0001,
"step": 7630
},
{
"epoch": 25.0,
"learning_rate": 2.7631578947368426e-05,
"loss": 0.0,
"step": 7640
},
{
"epoch": 25.0,
"learning_rate": 2.7595029239766084e-05,
"loss": 0.0,
"step": 7650
},
{
"epoch": 25.0,
"learning_rate": 2.7558479532163746e-05,
"loss": 0.0001,
"step": 7660
},
{
"epoch": 25.0,
"learning_rate": 2.7521929824561405e-05,
"loss": 0.0001,
"step": 7670
},
{
"epoch": 25.01,
"learning_rate": 2.7485380116959063e-05,
"loss": 0.0001,
"step": 7680
},
{
"epoch": 25.01,
"learning_rate": 2.7448830409356725e-05,
"loss": 0.0001,
"step": 7690
},
{
"epoch": 25.01,
"learning_rate": 2.741228070175439e-05,
"loss": 0.0001,
"step": 7700
},
{
"epoch": 25.01,
"learning_rate": 2.7375730994152048e-05,
"loss": 0.0,
"step": 7710
},
{
"epoch": 25.01,
"learning_rate": 2.733918128654971e-05,
"loss": 0.0001,
"step": 7720
},
{
"epoch": 25.01,
"learning_rate": 2.730263157894737e-05,
"loss": 0.0001,
"step": 7730
},
{
"epoch": 25.01,
"learning_rate": 2.7266081871345027e-05,
"loss": 0.0994,
"step": 7740
},
{
"epoch": 25.01,
"learning_rate": 2.7229532163742695e-05,
"loss": 0.116,
"step": 7750
},
{
"epoch": 25.01,
"learning_rate": 2.7192982456140354e-05,
"loss": 1.5749,
"step": 7760
},
{
"epoch": 25.01,
"learning_rate": 2.7156432748538012e-05,
"loss": 0.501,
"step": 7770
},
{
"epoch": 25.01,
"learning_rate": 2.7119883040935674e-05,
"loss": 0.0012,
"step": 7780
},
{
"epoch": 25.01,
"learning_rate": 2.7083333333333332e-05,
"loss": 0.0004,
"step": 7790
},
{
"epoch": 25.01,
"learning_rate": 2.7046783625730997e-05,
"loss": 0.9555,
"step": 7800
},
{
"epoch": 25.01,
"learning_rate": 2.701023391812866e-05,
"loss": 0.0148,
"step": 7810
},
{
"epoch": 25.01,
"learning_rate": 2.6973684210526317e-05,
"loss": 0.0001,
"step": 7820
},
{
"epoch": 25.02,
"learning_rate": 2.693713450292398e-05,
"loss": 0.0001,
"step": 7830
},
{
"epoch": 25.02,
"learning_rate": 2.6900584795321637e-05,
"loss": 0.0002,
"step": 7840
},
{
"epoch": 25.02,
"learning_rate": 2.6864035087719296e-05,
"loss": 0.0001,
"step": 7850
},
{
"epoch": 25.02,
"learning_rate": 2.682748538011696e-05,
"loss": 0.0001,
"step": 7860
},
{
"epoch": 25.02,
"learning_rate": 2.6790935672514623e-05,
"loss": 0.7646,
"step": 7870
},
{
"epoch": 25.02,
"learning_rate": 2.675438596491228e-05,
"loss": 0.001,
"step": 7880
},
{
"epoch": 25.02,
"learning_rate": 2.6717836257309943e-05,
"loss": 0.0006,
"step": 7890
},
{
"epoch": 25.02,
"learning_rate": 2.66812865497076e-05,
"loss": 0.0003,
"step": 7900
},
{
"epoch": 25.02,
"eval_accuracy": 0.8026315789473685,
"eval_loss": 1.8731952905654907,
"eval_runtime": 47.1443,
"eval_samples_per_second": 3.224,
"eval_steps_per_second": 3.224,
"step": 7904
},
{
"epoch": 26.0,
"learning_rate": 2.6644736842105266e-05,
"loss": 0.0001,
"step": 7910
},
{
"epoch": 26.0,
"learning_rate": 2.6608187134502928e-05,
"loss": 0.0002,
"step": 7920
},
{
"epoch": 26.0,
"learning_rate": 2.6571637426900586e-05,
"loss": 0.0006,
"step": 7930
},
{
"epoch": 26.0,
"learning_rate": 2.6535087719298245e-05,
"loss": 0.0002,
"step": 7940
},
{
"epoch": 26.0,
"learning_rate": 2.6498538011695907e-05,
"loss": 0.0001,
"step": 7950
},
{
"epoch": 26.0,
"learning_rate": 2.6461988304093572e-05,
"loss": 0.0002,
"step": 7960
},
{
"epoch": 26.0,
"learning_rate": 2.642543859649123e-05,
"loss": 0.0002,
"step": 7970
},
{
"epoch": 26.0,
"learning_rate": 2.6388888888888892e-05,
"loss": 0.0001,
"step": 7980
},
{
"epoch": 26.01,
"learning_rate": 2.635233918128655e-05,
"loss": 0.0001,
"step": 7990
},
{
"epoch": 26.01,
"learning_rate": 2.6315789473684212e-05,
"loss": 0.0001,
"step": 8000
},
{
"epoch": 26.01,
"learning_rate": 2.627923976608187e-05,
"loss": 0.0001,
"step": 8010
},
{
"epoch": 26.01,
"learning_rate": 2.6242690058479535e-05,
"loss": 0.0001,
"step": 8020
},
{
"epoch": 26.01,
"learning_rate": 2.6206140350877194e-05,
"loss": 0.0001,
"step": 8030
},
{
"epoch": 26.01,
"learning_rate": 2.6169590643274856e-05,
"loss": 0.1822,
"step": 8040
},
{
"epoch": 26.01,
"learning_rate": 2.6133040935672514e-05,
"loss": 0.0001,
"step": 8050
},
{
"epoch": 26.01,
"learning_rate": 2.6096491228070176e-05,
"loss": 0.6617,
"step": 8060
},
{
"epoch": 26.01,
"learning_rate": 2.605994152046784e-05,
"loss": 0.0001,
"step": 8070
},
{
"epoch": 26.01,
"learning_rate": 2.60233918128655e-05,
"loss": 0.0024,
"step": 8080
},
{
"epoch": 26.01,
"learning_rate": 2.598684210526316e-05,
"loss": 0.0002,
"step": 8090
},
{
"epoch": 26.01,
"learning_rate": 2.595029239766082e-05,
"loss": 0.0001,
"step": 8100
},
{
"epoch": 26.01,
"learning_rate": 2.5913742690058478e-05,
"loss": 0.4037,
"step": 8110
},
{
"epoch": 26.01,
"learning_rate": 2.5877192982456143e-05,
"loss": 0.0001,
"step": 8120
},
{
"epoch": 26.01,
"learning_rate": 2.5840643274853805e-05,
"loss": 0.0001,
"step": 8130
},
{
"epoch": 26.02,
"learning_rate": 2.5804093567251463e-05,
"loss": 0.0006,
"step": 8140
},
{
"epoch": 26.02,
"learning_rate": 2.5767543859649125e-05,
"loss": 0.2977,
"step": 8150
},
{
"epoch": 26.02,
"learning_rate": 2.5730994152046783e-05,
"loss": 0.0001,
"step": 8160
},
{
"epoch": 26.02,
"learning_rate": 2.5694444444444445e-05,
"loss": 0.0002,
"step": 8170
},
{
"epoch": 26.02,
"learning_rate": 2.565789473684211e-05,
"loss": 0.0001,
"step": 8180
},
{
"epoch": 26.02,
"learning_rate": 2.562134502923977e-05,
"loss": 0.0001,
"step": 8190
},
{
"epoch": 26.02,
"learning_rate": 2.5584795321637427e-05,
"loss": 0.0001,
"step": 8200
},
{
"epoch": 26.02,
"eval_accuracy": 0.7828947368421053,
"eval_loss": 2.029478073120117,
"eval_runtime": 46.8292,
"eval_samples_per_second": 3.246,
"eval_steps_per_second": 3.246,
"step": 8208
},
{
"epoch": 27.0,
"learning_rate": 2.554824561403509e-05,
"loss": 0.0,
"step": 8210
},
{
"epoch": 27.0,
"learning_rate": 2.5511695906432747e-05,
"loss": 0.0001,
"step": 8220
},
{
"epoch": 27.0,
"learning_rate": 2.5475146198830412e-05,
"loss": 0.0001,
"step": 8230
},
{
"epoch": 27.0,
"learning_rate": 2.5438596491228074e-05,
"loss": 0.0001,
"step": 8240
},
{
"epoch": 27.0,
"learning_rate": 2.5402046783625732e-05,
"loss": 0.0001,
"step": 8250
},
{
"epoch": 27.0,
"learning_rate": 2.5365497076023394e-05,
"loss": 0.0001,
"step": 8260
},
{
"epoch": 27.0,
"learning_rate": 2.5328947368421052e-05,
"loss": 0.0001,
"step": 8270
},
{
"epoch": 27.0,
"learning_rate": 2.5292397660818717e-05,
"loss": 1.0008,
"step": 8280
},
{
"epoch": 27.01,
"learning_rate": 2.5255847953216376e-05,
"loss": 0.0001,
"step": 8290
},
{
"epoch": 27.01,
"learning_rate": 2.5219298245614037e-05,
"loss": 0.0014,
"step": 8300
},
{
"epoch": 27.01,
"learning_rate": 2.5182748538011696e-05,
"loss": 0.0001,
"step": 8310
},
{
"epoch": 27.01,
"learning_rate": 2.5146198830409358e-05,
"loss": 0.0002,
"step": 8320
},
{
"epoch": 27.01,
"learning_rate": 2.5109649122807016e-05,
"loss": 0.0732,
"step": 8330
},
{
"epoch": 27.01,
"learning_rate": 2.507309941520468e-05,
"loss": 0.0001,
"step": 8340
},
{
"epoch": 27.01,
"learning_rate": 2.5036549707602343e-05,
"loss": 0.0001,
"step": 8350
},
{
"epoch": 27.01,
"learning_rate": 2.5e-05,
"loss": 0.9857,
"step": 8360
},
{
"epoch": 27.01,
"learning_rate": 2.496345029239766e-05,
"loss": 0.4604,
"step": 8370
},
{
"epoch": 27.01,
"learning_rate": 2.4926900584795325e-05,
"loss": 0.0008,
"step": 8380
},
{
"epoch": 27.01,
"learning_rate": 2.4890350877192983e-05,
"loss": 0.0005,
"step": 8390
},
{
"epoch": 27.01,
"learning_rate": 2.485380116959064e-05,
"loss": 0.0002,
"step": 8400
},
{
"epoch": 27.01,
"learning_rate": 2.4817251461988307e-05,
"loss": 0.0005,
"step": 8410
},
{
"epoch": 27.01,
"learning_rate": 2.4780701754385965e-05,
"loss": 0.0002,
"step": 8420
},
{
"epoch": 27.01,
"learning_rate": 2.4744152046783627e-05,
"loss": 0.0002,
"step": 8430
},
{
"epoch": 27.02,
"learning_rate": 2.470760233918129e-05,
"loss": 0.0003,
"step": 8440
},
{
"epoch": 27.02,
"learning_rate": 2.4671052631578947e-05,
"loss": 0.0002,
"step": 8450
},
{
"epoch": 27.02,
"learning_rate": 2.463450292397661e-05,
"loss": 0.0001,
"step": 8460
},
{
"epoch": 27.02,
"learning_rate": 2.459795321637427e-05,
"loss": 0.0002,
"step": 8470
},
{
"epoch": 27.02,
"learning_rate": 2.456140350877193e-05,
"loss": 0.0001,
"step": 8480
},
{
"epoch": 27.02,
"learning_rate": 2.4524853801169594e-05,
"loss": 0.0002,
"step": 8490
},
{
"epoch": 27.02,
"learning_rate": 2.4488304093567252e-05,
"loss": 0.0001,
"step": 8500
},
{
"epoch": 27.02,
"learning_rate": 2.4451754385964914e-05,
"loss": 0.0001,
"step": 8510
},
{
"epoch": 27.02,
"eval_accuracy": 0.8092105263157895,
"eval_loss": 1.762253999710083,
"eval_runtime": 47.1322,
"eval_samples_per_second": 3.225,
"eval_steps_per_second": 3.225,
"step": 8512
},
{
"epoch": 28.0,
"learning_rate": 2.4415204678362576e-05,
"loss": 0.0002,
"step": 8520
},
{
"epoch": 28.0,
"learning_rate": 2.4378654970760234e-05,
"loss": 0.6207,
"step": 8530
},
{
"epoch": 28.0,
"learning_rate": 2.4342105263157896e-05,
"loss": 0.0002,
"step": 8540
},
{
"epoch": 28.0,
"learning_rate": 2.4305555555555558e-05,
"loss": 0.0002,
"step": 8550
},
{
"epoch": 28.0,
"learning_rate": 2.4269005847953216e-05,
"loss": 0.8331,
"step": 8560
},
{
"epoch": 28.0,
"learning_rate": 2.4232456140350878e-05,
"loss": 0.0002,
"step": 8570
},
{
"epoch": 28.0,
"learning_rate": 2.419590643274854e-05,
"loss": 0.0002,
"step": 8580
},
{
"epoch": 28.01,
"learning_rate": 2.41593567251462e-05,
"loss": 0.0002,
"step": 8590
},
{
"epoch": 28.01,
"learning_rate": 2.412280701754386e-05,
"loss": 0.0022,
"step": 8600
},
{
"epoch": 28.01,
"learning_rate": 2.408625730994152e-05,
"loss": 0.0005,
"step": 8610
},
{
"epoch": 28.01,
"learning_rate": 2.4049707602339183e-05,
"loss": 0.0001,
"step": 8620
},
{
"epoch": 28.01,
"learning_rate": 2.401315789473684e-05,
"loss": 0.0004,
"step": 8630
},
{
"epoch": 28.01,
"learning_rate": 2.3976608187134503e-05,
"loss": 0.5605,
"step": 8640
},
{
"epoch": 28.01,
"learning_rate": 2.3940058479532165e-05,
"loss": 0.0001,
"step": 8650
},
{
"epoch": 28.01,
"learning_rate": 2.3903508771929827e-05,
"loss": 0.0001,
"step": 8660
},
{
"epoch": 28.01,
"learning_rate": 2.386695906432749e-05,
"loss": 0.0001,
"step": 8670
},
{
"epoch": 28.01,
"learning_rate": 2.3830409356725147e-05,
"loss": 0.0001,
"step": 8680
},
{
"epoch": 28.01,
"learning_rate": 2.379385964912281e-05,
"loss": 0.0001,
"step": 8690
},
{
"epoch": 28.01,
"learning_rate": 2.375730994152047e-05,
"loss": 0.0049,
"step": 8700
},
{
"epoch": 28.01,
"learning_rate": 2.372076023391813e-05,
"loss": 0.0002,
"step": 8710
},
{
"epoch": 28.01,
"learning_rate": 2.368421052631579e-05,
"loss": 0.0001,
"step": 8720
},
{
"epoch": 28.01,
"learning_rate": 2.3647660818713452e-05,
"loss": 1.1019,
"step": 8730
},
{
"epoch": 28.02,
"learning_rate": 2.361111111111111e-05,
"loss": 0.0001,
"step": 8740
},
{
"epoch": 28.02,
"learning_rate": 2.3574561403508776e-05,
"loss": 0.5741,
"step": 8750
},
{
"epoch": 28.02,
"learning_rate": 2.3538011695906434e-05,
"loss": 0.0003,
"step": 8760
},
{
"epoch": 28.02,
"learning_rate": 2.3501461988304092e-05,
"loss": 0.0002,
"step": 8770
},
{
"epoch": 28.02,
"learning_rate": 2.3464912280701758e-05,
"loss": 0.0001,
"step": 8780
},
{
"epoch": 28.02,
"learning_rate": 2.3428362573099416e-05,
"loss": 0.0002,
"step": 8790
},
{
"epoch": 28.02,
"learning_rate": 2.3391812865497074e-05,
"loss": 0.0001,
"step": 8800
},
{
"epoch": 28.02,
"learning_rate": 2.335526315789474e-05,
"loss": 0.0001,
"step": 8810
},
{
"epoch": 28.02,
"eval_accuracy": 0.8026315789473685,
"eval_loss": 1.8034647703170776,
"eval_runtime": 47.216,
"eval_samples_per_second": 3.219,
"eval_steps_per_second": 3.219,
"step": 8816
},
{
"epoch": 29.0,
"learning_rate": 2.3318713450292398e-05,
"loss": 0.0001,
"step": 8820
},
{
"epoch": 29.0,
"learning_rate": 2.328216374269006e-05,
"loss": 0.0001,
"step": 8830
},
{
"epoch": 29.0,
"learning_rate": 2.324561403508772e-05,
"loss": 0.0001,
"step": 8840
},
{
"epoch": 29.0,
"learning_rate": 2.320906432748538e-05,
"loss": 0.0001,
"step": 8850
},
{
"epoch": 29.0,
"learning_rate": 2.317251461988304e-05,
"loss": 0.0001,
"step": 8860
},
{
"epoch": 29.0,
"learning_rate": 2.3135964912280703e-05,
"loss": 0.0001,
"step": 8870
},
{
"epoch": 29.0,
"learning_rate": 2.309941520467836e-05,
"loss": 0.0001,
"step": 8880
},
{
"epoch": 29.0,
"learning_rate": 2.3062865497076023e-05,
"loss": 0.0001,
"step": 8890
},
{
"epoch": 29.01,
"learning_rate": 2.3026315789473685e-05,
"loss": 0.0001,
"step": 8900
},
{
"epoch": 29.01,
"learning_rate": 2.2989766081871347e-05,
"loss": 0.0001,
"step": 8910
},
{
"epoch": 29.01,
"learning_rate": 2.295321637426901e-05,
"loss": 0.0,
"step": 8920
},
{
"epoch": 29.01,
"learning_rate": 2.2916666666666667e-05,
"loss": 0.0001,
"step": 8930
},
{
"epoch": 29.01,
"learning_rate": 2.288011695906433e-05,
"loss": 0.0001,
"step": 8940
},
{
"epoch": 29.01,
"learning_rate": 2.284356725146199e-05,
"loss": 0.0001,
"step": 8950
},
{
"epoch": 29.01,
"learning_rate": 2.280701754385965e-05,
"loss": 0.0001,
"step": 8960
},
{
"epoch": 29.01,
"learning_rate": 2.277046783625731e-05,
"loss": 0.0001,
"step": 8970
},
{
"epoch": 29.01,
"learning_rate": 2.2733918128654972e-05,
"loss": 0.0001,
"step": 8980
},
{
"epoch": 29.01,
"learning_rate": 2.2697368421052634e-05,
"loss": 0.0001,
"step": 8990
},
{
"epoch": 29.01,
"learning_rate": 2.2660818713450292e-05,
"loss": 0.0001,
"step": 9000
},
{
"epoch": 29.01,
"learning_rate": 2.2624269005847954e-05,
"loss": 0.0001,
"step": 9010
},
{
"epoch": 29.01,
"learning_rate": 2.2587719298245616e-05,
"loss": 0.0,
"step": 9020
},
{
"epoch": 29.01,
"learning_rate": 2.2551169590643274e-05,
"loss": 0.0,
"step": 9030
},
{
"epoch": 29.01,
"learning_rate": 2.2514619883040936e-05,
"loss": 0.0001,
"step": 9040
},
{
"epoch": 29.02,
"learning_rate": 2.2478070175438598e-05,
"loss": 0.0001,
"step": 9050
},
{
"epoch": 29.02,
"learning_rate": 2.2441520467836256e-05,
"loss": 0.0001,
"step": 9060
},
{
"epoch": 29.02,
"learning_rate": 2.240497076023392e-05,
"loss": 0.0001,
"step": 9070
},
{
"epoch": 29.02,
"learning_rate": 2.236842105263158e-05,
"loss": 0.0001,
"step": 9080
},
{
"epoch": 29.02,
"learning_rate": 2.233187134502924e-05,
"loss": 0.0,
"step": 9090
},
{
"epoch": 29.02,
"learning_rate": 2.2295321637426903e-05,
"loss": 0.0001,
"step": 9100
},
{
"epoch": 29.02,
"learning_rate": 2.225877192982456e-05,
"loss": 0.0,
"step": 9110
},
{
"epoch": 29.02,
"learning_rate": 2.2222222222222223e-05,
"loss": 0.0,
"step": 9120
},
{
"epoch": 29.02,
"eval_accuracy": 0.8092105263157895,
"eval_loss": 1.7754253149032593,
"eval_runtime": 46.971,
"eval_samples_per_second": 3.236,
"eval_steps_per_second": 3.236,
"step": 9120
},
{
"epoch": 30.0,
"learning_rate": 2.2185672514619885e-05,
"loss": 0.0,
"step": 9130
},
{
"epoch": 30.0,
"learning_rate": 2.2149122807017543e-05,
"loss": 0.0006,
"step": 9140
},
{
"epoch": 30.0,
"learning_rate": 2.211257309941521e-05,
"loss": 0.0001,
"step": 9150
},
{
"epoch": 30.0,
"learning_rate": 2.2076023391812867e-05,
"loss": 0.0001,
"step": 9160
},
{
"epoch": 30.0,
"learning_rate": 2.2039473684210525e-05,
"loss": 0.0001,
"step": 9170
},
{
"epoch": 30.0,
"learning_rate": 2.200292397660819e-05,
"loss": 0.4896,
"step": 9180
},
{
"epoch": 30.0,
"learning_rate": 2.196637426900585e-05,
"loss": 0.0001,
"step": 9190
},
{
"epoch": 30.01,
"learning_rate": 2.1929824561403507e-05,
"loss": 0.9651,
"step": 9200
},
{
"epoch": 30.01,
"learning_rate": 2.1893274853801172e-05,
"loss": 0.7554,
"step": 9210
},
{
"epoch": 30.01,
"learning_rate": 2.185672514619883e-05,
"loss": 0.0002,
"step": 9220
},
{
"epoch": 30.01,
"learning_rate": 2.1820175438596492e-05,
"loss": 0.0006,
"step": 9230
},
{
"epoch": 30.01,
"learning_rate": 2.1783625730994154e-05,
"loss": 0.2298,
"step": 9240
},
{
"epoch": 30.01,
"learning_rate": 2.1747076023391813e-05,
"loss": 0.0128,
"step": 9250
},
{
"epoch": 30.01,
"learning_rate": 2.1710526315789474e-05,
"loss": 0.0014,
"step": 9260
},
{
"epoch": 30.01,
"learning_rate": 2.1673976608187136e-05,
"loss": 0.7423,
"step": 9270
},
{
"epoch": 30.01,
"learning_rate": 2.1637426900584794e-05,
"loss": 0.0003,
"step": 9280
},
{
"epoch": 30.01,
"learning_rate": 2.1600877192982456e-05,
"loss": 0.0001,
"step": 9290
},
{
"epoch": 30.01,
"learning_rate": 2.1564327485380118e-05,
"loss": 0.4934,
"step": 9300
},
{
"epoch": 30.01,
"learning_rate": 2.152777777777778e-05,
"loss": 0.0001,
"step": 9310
},
{
"epoch": 30.01,
"learning_rate": 2.149122807017544e-05,
"loss": 0.0001,
"step": 9320
},
{
"epoch": 30.01,
"learning_rate": 2.14546783625731e-05,
"loss": 0.0001,
"step": 9330
},
{
"epoch": 30.01,
"learning_rate": 2.141812865497076e-05,
"loss": 0.0001,
"step": 9340
},
{
"epoch": 30.02,
"learning_rate": 2.1381578947368423e-05,
"loss": 0.0002,
"step": 9350
},
{
"epoch": 30.02,
"learning_rate": 2.134502923976608e-05,
"loss": 0.0001,
"step": 9360
},
{
"epoch": 30.02,
"learning_rate": 2.1308479532163743e-05,
"loss": 0.0004,
"step": 9370
},
{
"epoch": 30.02,
"learning_rate": 2.1271929824561405e-05,
"loss": 0.0001,
"step": 9380
},
{
"epoch": 30.02,
"learning_rate": 2.1235380116959067e-05,
"loss": 0.0001,
"step": 9390
},
{
"epoch": 30.02,
"learning_rate": 2.1198830409356725e-05,
"loss": 0.0001,
"step": 9400
},
{
"epoch": 30.02,
"learning_rate": 2.1162280701754387e-05,
"loss": 0.0001,
"step": 9410
},
{
"epoch": 30.02,
"learning_rate": 2.112573099415205e-05,
"loss": 0.0001,
"step": 9420
},
{
"epoch": 30.02,
"eval_accuracy": 0.7960526315789473,
"eval_loss": 1.7622146606445312,
"eval_runtime": 47.2771,
"eval_samples_per_second": 3.215,
"eval_steps_per_second": 3.215,
"step": 9424
},
{
"epoch": 31.0,
"learning_rate": 2.1089181286549707e-05,
"loss": 0.0001,
"step": 9430
},
{
"epoch": 31.0,
"learning_rate": 2.105263157894737e-05,
"loss": 0.0001,
"step": 9440
},
{
"epoch": 31.0,
"learning_rate": 2.101608187134503e-05,
"loss": 0.0,
"step": 9450
},
{
"epoch": 31.0,
"learning_rate": 2.097953216374269e-05,
"loss": 0.0001,
"step": 9460
},
{
"epoch": 31.0,
"learning_rate": 2.0942982456140354e-05,
"loss": 0.0001,
"step": 9470
},
{
"epoch": 31.0,
"learning_rate": 2.0906432748538013e-05,
"loss": 0.0001,
"step": 9480
},
{
"epoch": 31.0,
"learning_rate": 2.0869883040935674e-05,
"loss": 0.0001,
"step": 9490
},
{
"epoch": 31.0,
"learning_rate": 2.0833333333333336e-05,
"loss": 0.0001,
"step": 9500
},
{
"epoch": 31.01,
"learning_rate": 2.0796783625730994e-05,
"loss": 0.0001,
"step": 9510
},
{
"epoch": 31.01,
"learning_rate": 2.0760233918128656e-05,
"loss": 0.0001,
"step": 9520
},
{
"epoch": 31.01,
"learning_rate": 2.0723684210526318e-05,
"loss": 0.0001,
"step": 9530
},
{
"epoch": 31.01,
"learning_rate": 2.0687134502923976e-05,
"loss": 0.0,
"step": 9540
},
{
"epoch": 31.01,
"learning_rate": 2.0650584795321638e-05,
"loss": 0.5583,
"step": 9550
},
{
"epoch": 31.01,
"learning_rate": 2.06140350877193e-05,
"loss": 1.1003,
"step": 9560
},
{
"epoch": 31.01,
"learning_rate": 2.0577485380116958e-05,
"loss": 0.0012,
"step": 9570
},
{
"epoch": 31.01,
"learning_rate": 2.0540935672514623e-05,
"loss": 1.0638,
"step": 9580
},
{
"epoch": 31.01,
"learning_rate": 2.050438596491228e-05,
"loss": 0.0002,
"step": 9590
},
{
"epoch": 31.01,
"learning_rate": 2.046783625730994e-05,
"loss": 0.0001,
"step": 9600
},
{
"epoch": 31.01,
"learning_rate": 2.0431286549707605e-05,
"loss": 0.0001,
"step": 9610
},
{
"epoch": 31.01,
"learning_rate": 2.0394736842105264e-05,
"loss": 0.0002,
"step": 9620
},
{
"epoch": 31.01,
"learning_rate": 2.0358187134502925e-05,
"loss": 0.0001,
"step": 9630
},
{
"epoch": 31.01,
"learning_rate": 2.0321637426900587e-05,
"loss": 0.0001,
"step": 9640
},
{
"epoch": 31.01,
"learning_rate": 2.0285087719298245e-05,
"loss": 0.0001,
"step": 9650
},
{
"epoch": 31.02,
"learning_rate": 2.0248538011695907e-05,
"loss": 0.0056,
"step": 9660
},
{
"epoch": 31.02,
"learning_rate": 2.021198830409357e-05,
"loss": 0.0001,
"step": 9670
},
{
"epoch": 31.02,
"learning_rate": 2.0175438596491227e-05,
"loss": 0.9186,
"step": 9680
},
{
"epoch": 31.02,
"learning_rate": 2.013888888888889e-05,
"loss": 0.0001,
"step": 9690
},
{
"epoch": 31.02,
"learning_rate": 2.010233918128655e-05,
"loss": 0.0001,
"step": 9700
},
{
"epoch": 31.02,
"learning_rate": 2.0065789473684213e-05,
"loss": 0.0001,
"step": 9710
},
{
"epoch": 31.02,
"learning_rate": 2.0029239766081874e-05,
"loss": 0.0001,
"step": 9720
},
{
"epoch": 31.02,
"eval_accuracy": 0.7894736842105263,
"eval_loss": 1.7556824684143066,
"eval_runtime": 47.019,
"eval_samples_per_second": 3.233,
"eval_steps_per_second": 3.233,
"step": 9728
},
{
"epoch": 32.0,
"learning_rate": 1.9992690058479533e-05,
"loss": 0.0001,
"step": 9730
},
{
"epoch": 32.0,
"learning_rate": 1.9956140350877194e-05,
"loss": 0.0001,
"step": 9740
},
{
"epoch": 32.0,
"learning_rate": 1.9919590643274856e-05,
"loss": 0.0001,
"step": 9750
},
{
"epoch": 32.0,
"learning_rate": 1.9883040935672515e-05,
"loss": 0.0001,
"step": 9760
},
{
"epoch": 32.0,
"learning_rate": 1.9846491228070176e-05,
"loss": 0.0001,
"step": 9770
},
{
"epoch": 32.0,
"learning_rate": 1.9809941520467838e-05,
"loss": 0.0001,
"step": 9780
},
{
"epoch": 32.0,
"learning_rate": 1.97733918128655e-05,
"loss": 0.0001,
"step": 9790
},
{
"epoch": 32.0,
"learning_rate": 1.9736842105263158e-05,
"loss": 0.0001,
"step": 9800
},
{
"epoch": 32.01,
"learning_rate": 1.970029239766082e-05,
"loss": 0.8799,
"step": 9810
},
{
"epoch": 32.01,
"learning_rate": 1.966374269005848e-05,
"loss": 0.0001,
"step": 9820
},
{
"epoch": 32.01,
"learning_rate": 1.962719298245614e-05,
"loss": 0.0001,
"step": 9830
},
{
"epoch": 32.01,
"learning_rate": 1.9590643274853802e-05,
"loss": 0.0001,
"step": 9840
},
{
"epoch": 32.01,
"learning_rate": 1.9554093567251464e-05,
"loss": 0.8716,
"step": 9850
},
{
"epoch": 32.01,
"learning_rate": 1.9517543859649122e-05,
"loss": 0.0002,
"step": 9860
},
{
"epoch": 32.01,
"learning_rate": 1.9480994152046787e-05,
"loss": 0.0003,
"step": 9870
},
{
"epoch": 32.01,
"learning_rate": 1.9444444444444445e-05,
"loss": 0.0002,
"step": 9880
},
{
"epoch": 32.01,
"learning_rate": 1.9407894736842107e-05,
"loss": 0.0001,
"step": 9890
},
{
"epoch": 32.01,
"learning_rate": 1.937134502923977e-05,
"loss": 0.0001,
"step": 9900
},
{
"epoch": 32.01,
"learning_rate": 1.9334795321637427e-05,
"loss": 0.0002,
"step": 9910
},
{
"epoch": 32.01,
"learning_rate": 1.929824561403509e-05,
"loss": 0.0002,
"step": 9920
},
{
"epoch": 32.01,
"learning_rate": 1.926169590643275e-05,
"loss": 0.0003,
"step": 9930
},
{
"epoch": 32.01,
"learning_rate": 1.922514619883041e-05,
"loss": 0.0001,
"step": 9940
},
{
"epoch": 32.01,
"learning_rate": 1.918859649122807e-05,
"loss": 0.0001,
"step": 9950
},
{
"epoch": 32.02,
"learning_rate": 1.9152046783625733e-05,
"loss": 0.0001,
"step": 9960
},
{
"epoch": 32.02,
"learning_rate": 1.911549707602339e-05,
"loss": 0.0001,
"step": 9970
},
{
"epoch": 32.02,
"learning_rate": 1.9078947368421056e-05,
"loss": 0.0001,
"step": 9980
},
{
"epoch": 32.02,
"learning_rate": 1.9042397660818714e-05,
"loss": 0.409,
"step": 9990
},
{
"epoch": 32.02,
"learning_rate": 1.9005847953216373e-05,
"loss": 0.0005,
"step": 10000
},
{
"epoch": 32.02,
"learning_rate": 1.8969298245614038e-05,
"loss": 0.0002,
"step": 10010
},
{
"epoch": 32.02,
"learning_rate": 1.8932748538011696e-05,
"loss": 0.0001,
"step": 10020
},
{
"epoch": 32.02,
"learning_rate": 1.8896198830409358e-05,
"loss": 0.0002,
"step": 10030
},
{
"epoch": 32.02,
"eval_accuracy": 0.8223684210526315,
"eval_loss": 1.5907264947891235,
"eval_runtime": 47.0219,
"eval_samples_per_second": 3.233,
"eval_steps_per_second": 3.233,
"step": 10032
},
{
"epoch": 33.0,
"learning_rate": 1.885964912280702e-05,
"loss": 0.0001,
"step": 10040
},
{
"epoch": 33.0,
"learning_rate": 1.8823099415204678e-05,
"loss": 0.0001,
"step": 10050
},
{
"epoch": 33.0,
"learning_rate": 1.878654970760234e-05,
"loss": 0.0001,
"step": 10060
},
{
"epoch": 33.0,
"learning_rate": 1.8750000000000002e-05,
"loss": 0.0001,
"step": 10070
},
{
"epoch": 33.0,
"learning_rate": 1.871345029239766e-05,
"loss": 0.0001,
"step": 10080
},
{
"epoch": 33.0,
"learning_rate": 1.8676900584795322e-05,
"loss": 0.0001,
"step": 10090
},
{
"epoch": 33.0,
"learning_rate": 1.8640350877192984e-05,
"loss": 0.0001,
"step": 10100
},
{
"epoch": 33.01,
"learning_rate": 1.8603801169590642e-05,
"loss": 0.0001,
"step": 10110
},
{
"epoch": 33.01,
"learning_rate": 1.8567251461988304e-05,
"loss": 0.0001,
"step": 10120
},
{
"epoch": 33.01,
"learning_rate": 1.8530701754385965e-05,
"loss": 0.0001,
"step": 10130
},
{
"epoch": 33.01,
"learning_rate": 1.8494152046783627e-05,
"loss": 0.0001,
"step": 10140
},
{
"epoch": 33.01,
"learning_rate": 1.845760233918129e-05,
"loss": 0.0001,
"step": 10150
},
{
"epoch": 33.01,
"learning_rate": 1.8421052631578947e-05,
"loss": 0.0001,
"step": 10160
},
{
"epoch": 33.01,
"learning_rate": 1.838450292397661e-05,
"loss": 0.0001,
"step": 10170
},
{
"epoch": 33.01,
"learning_rate": 1.834795321637427e-05,
"loss": 0.0001,
"step": 10180
},
{
"epoch": 33.01,
"learning_rate": 1.831140350877193e-05,
"loss": 0.0,
"step": 10190
},
{
"epoch": 33.01,
"learning_rate": 1.827485380116959e-05,
"loss": 0.0001,
"step": 10200
},
{
"epoch": 33.01,
"learning_rate": 1.8238304093567253e-05,
"loss": 0.0001,
"step": 10210
},
{
"epoch": 33.01,
"learning_rate": 1.8201754385964914e-05,
"loss": 0.0001,
"step": 10220
},
{
"epoch": 33.01,
"learning_rate": 1.8165204678362573e-05,
"loss": 0.0001,
"step": 10230
},
{
"epoch": 33.01,
"learning_rate": 1.8128654970760235e-05,
"loss": 0.0001,
"step": 10240
},
{
"epoch": 33.01,
"learning_rate": 1.8092105263157896e-05,
"loss": 0.0001,
"step": 10250
},
{
"epoch": 33.02,
"learning_rate": 1.8055555555555555e-05,
"loss": 0.0001,
"step": 10260
},
{
"epoch": 33.02,
"learning_rate": 1.8019005847953216e-05,
"loss": 0.0001,
"step": 10270
},
{
"epoch": 33.02,
"learning_rate": 1.7982456140350878e-05,
"loss": 0.0001,
"step": 10280
},
{
"epoch": 33.02,
"learning_rate": 1.7945906432748537e-05,
"loss": 0.0001,
"step": 10290
},
{
"epoch": 33.02,
"learning_rate": 1.7909356725146202e-05,
"loss": 0.0001,
"step": 10300
},
{
"epoch": 33.02,
"learning_rate": 1.787280701754386e-05,
"loss": 0.0001,
"step": 10310
},
{
"epoch": 33.02,
"learning_rate": 1.7836257309941522e-05,
"loss": 0.0001,
"step": 10320
},
{
"epoch": 33.02,
"learning_rate": 1.7799707602339184e-05,
"loss": 0.0001,
"step": 10330
},
{
"epoch": 33.02,
"eval_accuracy": 0.8157894736842105,
"eval_loss": 1.6858829259872437,
"eval_runtime": 47.2739,
"eval_samples_per_second": 3.215,
"eval_steps_per_second": 3.215,
"step": 10336
},
{
"epoch": 34.0,
"learning_rate": 1.7763157894736842e-05,
"loss": 0.0001,
"step": 10340
},
{
"epoch": 34.0,
"learning_rate": 1.7726608187134504e-05,
"loss": 0.0001,
"step": 10350
},
{
"epoch": 34.0,
"learning_rate": 1.7690058479532165e-05,
"loss": 0.0001,
"step": 10360
},
{
"epoch": 34.0,
"learning_rate": 1.7653508771929824e-05,
"loss": 0.0001,
"step": 10370
},
{
"epoch": 34.0,
"learning_rate": 1.761695906432749e-05,
"loss": 0.0001,
"step": 10380
},
{
"epoch": 34.0,
"learning_rate": 1.7580409356725147e-05,
"loss": 0.0001,
"step": 10390
},
{
"epoch": 34.0,
"learning_rate": 1.7543859649122806e-05,
"loss": 0.0001,
"step": 10400
},
{
"epoch": 34.0,
"learning_rate": 1.750730994152047e-05,
"loss": 0.0,
"step": 10410
},
{
"epoch": 34.01,
"learning_rate": 1.747076023391813e-05,
"loss": 0.0,
"step": 10420
},
{
"epoch": 34.01,
"learning_rate": 1.7434210526315788e-05,
"loss": 0.0,
"step": 10430
},
{
"epoch": 34.01,
"learning_rate": 1.7397660818713453e-05,
"loss": 0.0001,
"step": 10440
},
{
"epoch": 34.01,
"learning_rate": 1.736111111111111e-05,
"loss": 0.0001,
"step": 10450
},
{
"epoch": 34.01,
"learning_rate": 1.7324561403508773e-05,
"loss": 0.0001,
"step": 10460
},
{
"epoch": 34.01,
"learning_rate": 1.7288011695906435e-05,
"loss": 0.0001,
"step": 10470
},
{
"epoch": 34.01,
"learning_rate": 1.7251461988304093e-05,
"loss": 0.0,
"step": 10480
},
{
"epoch": 34.01,
"learning_rate": 1.7214912280701755e-05,
"loss": 0.0,
"step": 10490
},
{
"epoch": 34.01,
"learning_rate": 1.7178362573099416e-05,
"loss": 0.0001,
"step": 10500
},
{
"epoch": 34.01,
"learning_rate": 1.7141812865497075e-05,
"loss": 0.0001,
"step": 10510
},
{
"epoch": 34.01,
"learning_rate": 1.7105263157894737e-05,
"loss": 0.0,
"step": 10520
},
{
"epoch": 34.01,
"learning_rate": 1.70687134502924e-05,
"loss": 0.0,
"step": 10530
},
{
"epoch": 34.01,
"learning_rate": 1.703216374269006e-05,
"loss": 0.0001,
"step": 10540
},
{
"epoch": 34.01,
"learning_rate": 1.6995614035087722e-05,
"loss": 0.0001,
"step": 10550
},
{
"epoch": 34.01,
"learning_rate": 1.695906432748538e-05,
"loss": 0.0,
"step": 10560
},
{
"epoch": 34.02,
"learning_rate": 1.6922514619883042e-05,
"loss": 0.0001,
"step": 10570
},
{
"epoch": 34.02,
"learning_rate": 1.6885964912280704e-05,
"loss": 0.0,
"step": 10580
},
{
"epoch": 34.02,
"learning_rate": 1.6849415204678362e-05,
"loss": 0.0001,
"step": 10590
},
{
"epoch": 34.02,
"learning_rate": 1.6812865497076024e-05,
"loss": 0.0002,
"step": 10600
},
{
"epoch": 34.02,
"learning_rate": 1.6776315789473686e-05,
"loss": 0.0,
"step": 10610
},
{
"epoch": 34.02,
"learning_rate": 1.6739766081871347e-05,
"loss": 0.0,
"step": 10620
},
{
"epoch": 34.02,
"learning_rate": 1.6703216374269006e-05,
"loss": 0.0,
"step": 10630
},
{
"epoch": 34.02,
"learning_rate": 1.6666666666666667e-05,
"loss": 0.0,
"step": 10640
},
{
"epoch": 34.02,
"eval_accuracy": 0.7960526315789473,
"eval_loss": 1.8641349077224731,
"eval_runtime": 46.9589,
"eval_samples_per_second": 3.237,
"eval_steps_per_second": 3.237,
"step": 10640
},
{
"epoch": 35.0,
"learning_rate": 1.663011695906433e-05,
"loss": 0.0,
"step": 10650
},
{
"epoch": 35.0,
"learning_rate": 1.6593567251461988e-05,
"loss": 0.0,
"step": 10660
},
{
"epoch": 35.0,
"learning_rate": 1.655701754385965e-05,
"loss": 0.0,
"step": 10670
},
{
"epoch": 35.0,
"learning_rate": 1.652046783625731e-05,
"loss": 0.0,
"step": 10680
},
{
"epoch": 35.0,
"learning_rate": 1.648391812865497e-05,
"loss": 0.0,
"step": 10690
},
{
"epoch": 35.0,
"learning_rate": 1.6447368421052635e-05,
"loss": 0.0,
"step": 10700
},
{
"epoch": 35.0,
"learning_rate": 1.6410818713450293e-05,
"loss": 0.0001,
"step": 10710
},
{
"epoch": 35.01,
"learning_rate": 1.6374269005847955e-05,
"loss": 0.0,
"step": 10720
},
{
"epoch": 35.01,
"learning_rate": 1.6337719298245616e-05,
"loss": 0.0,
"step": 10730
},
{
"epoch": 35.01,
"learning_rate": 1.6301169590643275e-05,
"loss": 0.0,
"step": 10740
},
{
"epoch": 35.01,
"learning_rate": 1.6264619883040937e-05,
"loss": 0.0001,
"step": 10750
},
{
"epoch": 35.01,
"learning_rate": 1.62280701754386e-05,
"loss": 0.0001,
"step": 10760
},
{
"epoch": 35.01,
"learning_rate": 1.6191520467836257e-05,
"loss": 0.0,
"step": 10770
},
{
"epoch": 35.01,
"learning_rate": 1.615497076023392e-05,
"loss": 0.0,
"step": 10780
},
{
"epoch": 35.01,
"learning_rate": 1.611842105263158e-05,
"loss": 0.0,
"step": 10790
},
{
"epoch": 35.01,
"learning_rate": 1.608187134502924e-05,
"loss": 0.0,
"step": 10800
},
{
"epoch": 35.01,
"learning_rate": 1.6045321637426904e-05,
"loss": 0.0,
"step": 10810
},
{
"epoch": 35.01,
"learning_rate": 1.6008771929824562e-05,
"loss": 0.0,
"step": 10820
},
{
"epoch": 35.01,
"learning_rate": 1.597222222222222e-05,
"loss": 0.0,
"step": 10830
},
{
"epoch": 35.01,
"learning_rate": 1.5935672514619886e-05,
"loss": 0.0,
"step": 10840
},
{
"epoch": 35.01,
"learning_rate": 1.5899122807017544e-05,
"loss": 0.0,
"step": 10850
},
{
"epoch": 35.01,
"learning_rate": 1.5862573099415206e-05,
"loss": 0.0001,
"step": 10860
},
{
"epoch": 35.02,
"learning_rate": 1.5826023391812867e-05,
"loss": 0.0,
"step": 10870
},
{
"epoch": 35.02,
"learning_rate": 1.5789473684210526e-05,
"loss": 0.0,
"step": 10880
},
{
"epoch": 35.02,
"learning_rate": 1.5752923976608188e-05,
"loss": 0.0,
"step": 10890
},
{
"epoch": 35.02,
"learning_rate": 1.571637426900585e-05,
"loss": 0.0001,
"step": 10900
},
{
"epoch": 35.02,
"learning_rate": 1.5679824561403508e-05,
"loss": 0.0,
"step": 10910
},
{
"epoch": 35.02,
"learning_rate": 1.564327485380117e-05,
"loss": 0.0,
"step": 10920
},
{
"epoch": 35.02,
"learning_rate": 1.560672514619883e-05,
"loss": 0.0,
"step": 10930
},
{
"epoch": 35.02,
"learning_rate": 1.5570175438596493e-05,
"loss": 0.0,
"step": 10940
},
{
"epoch": 35.02,
"eval_accuracy": 0.8223684210526315,
"eval_loss": 1.7088335752487183,
"eval_runtime": 47.0172,
"eval_samples_per_second": 3.233,
"eval_steps_per_second": 3.233,
"step": 10944
},
{
"epoch": 36.0,
"learning_rate": 1.553362573099415e-05,
"loss": 0.0,
"step": 10950
},
{
"epoch": 36.0,
"learning_rate": 1.5497076023391813e-05,
"loss": 0.0,
"step": 10960
},
{
"epoch": 36.0,
"learning_rate": 1.5460526315789475e-05,
"loss": 0.0,
"step": 10970
},
{
"epoch": 36.0,
"learning_rate": 1.5423976608187137e-05,
"loss": 0.0,
"step": 10980
},
{
"epoch": 36.0,
"learning_rate": 1.5387426900584795e-05,
"loss": 0.0,
"step": 10990
},
{
"epoch": 36.0,
"learning_rate": 1.5350877192982457e-05,
"loss": 0.0,
"step": 11000
},
{
"epoch": 36.0,
"learning_rate": 1.531432748538012e-05,
"loss": 0.0,
"step": 11010
},
{
"epoch": 36.01,
"learning_rate": 1.527777777777778e-05,
"loss": 0.8608,
"step": 11020
},
{
"epoch": 36.01,
"learning_rate": 1.524122807017544e-05,
"loss": 0.0,
"step": 11030
},
{
"epoch": 36.01,
"learning_rate": 1.5204678362573099e-05,
"loss": 0.0007,
"step": 11040
},
{
"epoch": 36.01,
"learning_rate": 1.5168128654970762e-05,
"loss": 0.0001,
"step": 11050
},
{
"epoch": 36.01,
"learning_rate": 1.5131578947368422e-05,
"loss": 0.0001,
"step": 11060
},
{
"epoch": 36.01,
"learning_rate": 1.5095029239766082e-05,
"loss": 0.0001,
"step": 11070
},
{
"epoch": 36.01,
"learning_rate": 1.5058479532163744e-05,
"loss": 0.0,
"step": 11080
},
{
"epoch": 36.01,
"learning_rate": 1.5021929824561404e-05,
"loss": 0.0001,
"step": 11090
},
{
"epoch": 36.01,
"learning_rate": 1.4985380116959066e-05,
"loss": 0.0,
"step": 11100
},
{
"epoch": 36.01,
"learning_rate": 1.4948830409356726e-05,
"loss": 0.0,
"step": 11110
},
{
"epoch": 36.01,
"learning_rate": 1.4912280701754386e-05,
"loss": 0.0,
"step": 11120
},
{
"epoch": 36.01,
"learning_rate": 1.4875730994152048e-05,
"loss": 0.0001,
"step": 11130
},
{
"epoch": 36.01,
"learning_rate": 1.4839181286549708e-05,
"loss": 0.0,
"step": 11140
},
{
"epoch": 36.01,
"learning_rate": 1.4802631578947368e-05,
"loss": 0.0,
"step": 11150
},
{
"epoch": 36.01,
"learning_rate": 1.4766081871345031e-05,
"loss": 0.0,
"step": 11160
},
{
"epoch": 36.01,
"learning_rate": 1.472953216374269e-05,
"loss": 0.0,
"step": 11170
},
{
"epoch": 36.02,
"learning_rate": 1.4692982456140353e-05,
"loss": 0.0,
"step": 11180
},
{
"epoch": 36.02,
"learning_rate": 1.4656432748538013e-05,
"loss": 0.0,
"step": 11190
},
{
"epoch": 36.02,
"learning_rate": 1.4619883040935673e-05,
"loss": 0.0,
"step": 11200
},
{
"epoch": 36.02,
"learning_rate": 1.4583333333333335e-05,
"loss": 0.0,
"step": 11210
},
{
"epoch": 36.02,
"learning_rate": 1.4546783625730995e-05,
"loss": 0.0,
"step": 11220
},
{
"epoch": 36.02,
"learning_rate": 1.4510233918128655e-05,
"loss": 0.0,
"step": 11230
},
{
"epoch": 36.02,
"learning_rate": 1.4473684210526317e-05,
"loss": 0.0,
"step": 11240
},
{
"epoch": 36.02,
"eval_accuracy": 0.8421052631578947,
"eval_loss": 1.6139503717422485,
"eval_runtime": 47.0569,
"eval_samples_per_second": 3.23,
"eval_steps_per_second": 3.23,
"step": 11248
},
{
"epoch": 37.0,
"learning_rate": 1.4437134502923977e-05,
"loss": 0.0,
"step": 11250
},
{
"epoch": 37.0,
"learning_rate": 1.4400584795321639e-05,
"loss": 0.0,
"step": 11260
},
{
"epoch": 37.0,
"learning_rate": 1.4364035087719299e-05,
"loss": 0.0,
"step": 11270
},
{
"epoch": 37.0,
"learning_rate": 1.4327485380116959e-05,
"loss": 0.0,
"step": 11280
},
{
"epoch": 37.0,
"learning_rate": 1.4290935672514622e-05,
"loss": 0.0,
"step": 11290
},
{
"epoch": 37.0,
"learning_rate": 1.425438596491228e-05,
"loss": 0.0,
"step": 11300
},
{
"epoch": 37.0,
"learning_rate": 1.421783625730994e-05,
"loss": 0.0,
"step": 11310
},
{
"epoch": 37.0,
"learning_rate": 1.4181286549707604e-05,
"loss": 0.0,
"step": 11320
},
{
"epoch": 37.01,
"learning_rate": 1.4144736842105264e-05,
"loss": 0.0,
"step": 11330
},
{
"epoch": 37.01,
"learning_rate": 1.4108187134502926e-05,
"loss": 0.0,
"step": 11340
},
{
"epoch": 37.01,
"learning_rate": 1.4071637426900586e-05,
"loss": 0.0,
"step": 11350
},
{
"epoch": 37.01,
"learning_rate": 1.4035087719298246e-05,
"loss": 0.0,
"step": 11360
},
{
"epoch": 37.01,
"learning_rate": 1.3998538011695908e-05,
"loss": 0.0,
"step": 11370
},
{
"epoch": 37.01,
"learning_rate": 1.3961988304093568e-05,
"loss": 0.0,
"step": 11380
},
{
"epoch": 37.01,
"learning_rate": 1.3925438596491228e-05,
"loss": 0.0,
"step": 11390
},
{
"epoch": 37.01,
"learning_rate": 1.388888888888889e-05,
"loss": 0.0,
"step": 11400
},
{
"epoch": 37.01,
"learning_rate": 1.385233918128655e-05,
"loss": 0.0,
"step": 11410
},
{
"epoch": 37.01,
"learning_rate": 1.3815789473684213e-05,
"loss": 0.0,
"step": 11420
},
{
"epoch": 37.01,
"learning_rate": 1.3779239766081873e-05,
"loss": 0.0,
"step": 11430
},
{
"epoch": 37.01,
"learning_rate": 1.3742690058479531e-05,
"loss": 0.0,
"step": 11440
},
{
"epoch": 37.01,
"learning_rate": 1.3706140350877195e-05,
"loss": 0.0,
"step": 11450
},
{
"epoch": 37.01,
"learning_rate": 1.3669590643274855e-05,
"loss": 0.0,
"step": 11460
},
{
"epoch": 37.01,
"learning_rate": 1.3633040935672513e-05,
"loss": 0.0,
"step": 11470
},
{
"epoch": 37.02,
"learning_rate": 1.3596491228070177e-05,
"loss": 0.0,
"step": 11480
},
{
"epoch": 37.02,
"learning_rate": 1.3559941520467837e-05,
"loss": 0.0,
"step": 11490
},
{
"epoch": 37.02,
"learning_rate": 1.3523391812865499e-05,
"loss": 0.0,
"step": 11500
},
{
"epoch": 37.02,
"learning_rate": 1.3486842105263159e-05,
"loss": 0.0,
"step": 11510
},
{
"epoch": 37.02,
"learning_rate": 1.3450292397660819e-05,
"loss": 0.0,
"step": 11520
},
{
"epoch": 37.02,
"learning_rate": 1.341374269005848e-05,
"loss": 0.0,
"step": 11530
},
{
"epoch": 37.02,
"learning_rate": 1.337719298245614e-05,
"loss": 0.0,
"step": 11540
},
{
"epoch": 37.02,
"learning_rate": 1.33406432748538e-05,
"loss": 0.0,
"step": 11550
},
{
"epoch": 37.02,
"eval_accuracy": 0.8355263157894737,
"eval_loss": 1.6678390502929688,
"eval_runtime": 46.9876,
"eval_samples_per_second": 3.235,
"eval_steps_per_second": 3.235,
"step": 11552
},
{
"epoch": 38.0,
"learning_rate": 1.3304093567251464e-05,
"loss": 0.0,
"step": 11560
},
{
"epoch": 38.0,
"learning_rate": 1.3267543859649122e-05,
"loss": 0.0,
"step": 11570
},
{
"epoch": 38.0,
"learning_rate": 1.3230994152046786e-05,
"loss": 0.0,
"step": 11580
},
{
"epoch": 38.0,
"learning_rate": 1.3194444444444446e-05,
"loss": 0.0,
"step": 11590
},
{
"epoch": 38.0,
"learning_rate": 1.3157894736842106e-05,
"loss": 0.0,
"step": 11600
},
{
"epoch": 38.0,
"learning_rate": 1.3121345029239768e-05,
"loss": 0.0,
"step": 11610
},
{
"epoch": 38.0,
"learning_rate": 1.3084795321637428e-05,
"loss": 0.0,
"step": 11620
},
{
"epoch": 38.01,
"learning_rate": 1.3048245614035088e-05,
"loss": 0.0,
"step": 11630
},
{
"epoch": 38.01,
"learning_rate": 1.301169590643275e-05,
"loss": 0.0,
"step": 11640
},
{
"epoch": 38.01,
"learning_rate": 1.297514619883041e-05,
"loss": 0.0,
"step": 11650
},
{
"epoch": 38.01,
"learning_rate": 1.2938596491228071e-05,
"loss": 0.0,
"step": 11660
},
{
"epoch": 38.01,
"learning_rate": 1.2902046783625731e-05,
"loss": 0.0,
"step": 11670
},
{
"epoch": 38.01,
"learning_rate": 1.2865497076023392e-05,
"loss": 0.0,
"step": 11680
},
{
"epoch": 38.01,
"learning_rate": 1.2828947368421055e-05,
"loss": 0.0,
"step": 11690
},
{
"epoch": 38.01,
"learning_rate": 1.2792397660818713e-05,
"loss": 0.0,
"step": 11700
},
{
"epoch": 38.01,
"learning_rate": 1.2755847953216373e-05,
"loss": 0.0,
"step": 11710
},
{
"epoch": 38.01,
"learning_rate": 1.2719298245614037e-05,
"loss": 0.0,
"step": 11720
},
{
"epoch": 38.01,
"learning_rate": 1.2682748538011697e-05,
"loss": 0.0,
"step": 11730
},
{
"epoch": 38.01,
"learning_rate": 1.2646198830409359e-05,
"loss": 0.0,
"step": 11740
},
{
"epoch": 38.01,
"learning_rate": 1.2609649122807019e-05,
"loss": 0.0,
"step": 11750
},
{
"epoch": 38.01,
"learning_rate": 1.2573099415204679e-05,
"loss": 0.0,
"step": 11760
},
{
"epoch": 38.01,
"learning_rate": 1.253654970760234e-05,
"loss": 0.0,
"step": 11770
},
{
"epoch": 38.02,
"learning_rate": 1.25e-05,
"loss": 0.0,
"step": 11780
},
{
"epoch": 38.02,
"learning_rate": 1.2463450292397662e-05,
"loss": 0.0,
"step": 11790
},
{
"epoch": 38.02,
"learning_rate": 1.242690058479532e-05,
"loss": 0.0,
"step": 11800
},
{
"epoch": 38.02,
"learning_rate": 1.2390350877192982e-05,
"loss": 0.0,
"step": 11810
},
{
"epoch": 38.02,
"learning_rate": 1.2353801169590644e-05,
"loss": 0.0,
"step": 11820
},
{
"epoch": 38.02,
"learning_rate": 1.2317251461988304e-05,
"loss": 0.0,
"step": 11830
},
{
"epoch": 38.02,
"learning_rate": 1.2280701754385964e-05,
"loss": 0.0,
"step": 11840
},
{
"epoch": 38.02,
"learning_rate": 1.2244152046783626e-05,
"loss": 0.0,
"step": 11850
},
{
"epoch": 38.02,
"eval_accuracy": 0.8355263157894737,
"eval_loss": 1.6991444826126099,
"eval_runtime": 46.9181,
"eval_samples_per_second": 3.24,
"eval_steps_per_second": 3.24,
"step": 11856
},
{
"epoch": 39.0,
"learning_rate": 1.2207602339181288e-05,
"loss": 0.0,
"step": 11860
},
{
"epoch": 39.0,
"learning_rate": 1.2171052631578948e-05,
"loss": 0.0,
"step": 11870
},
{
"epoch": 39.0,
"learning_rate": 1.2134502923976608e-05,
"loss": 0.0,
"step": 11880
},
{
"epoch": 39.0,
"learning_rate": 1.209795321637427e-05,
"loss": 0.0,
"step": 11890
},
{
"epoch": 39.0,
"learning_rate": 1.206140350877193e-05,
"loss": 0.0,
"step": 11900
},
{
"epoch": 39.0,
"learning_rate": 1.2024853801169592e-05,
"loss": 0.0,
"step": 11910
},
{
"epoch": 39.0,
"learning_rate": 1.1988304093567252e-05,
"loss": 0.0,
"step": 11920
},
{
"epoch": 39.0,
"learning_rate": 1.1951754385964913e-05,
"loss": 0.0,
"step": 11930
},
{
"epoch": 39.01,
"learning_rate": 1.1915204678362573e-05,
"loss": 0.0,
"step": 11940
},
{
"epoch": 39.01,
"learning_rate": 1.1878654970760235e-05,
"loss": 0.0,
"step": 11950
},
{
"epoch": 39.01,
"learning_rate": 1.1842105263157895e-05,
"loss": 0.0001,
"step": 11960
},
{
"epoch": 39.01,
"learning_rate": 1.1805555555555555e-05,
"loss": 0.0,
"step": 11970
},
{
"epoch": 39.01,
"learning_rate": 1.1769005847953217e-05,
"loss": 0.0,
"step": 11980
},
{
"epoch": 39.01,
"learning_rate": 1.1732456140350879e-05,
"loss": 0.0,
"step": 11990
},
{
"epoch": 39.01,
"learning_rate": 1.1695906432748537e-05,
"loss": 0.0,
"step": 12000
},
{
"epoch": 39.01,
"learning_rate": 1.1659356725146199e-05,
"loss": 0.0,
"step": 12010
},
{
"epoch": 39.01,
"learning_rate": 1.162280701754386e-05,
"loss": 0.0,
"step": 12020
},
{
"epoch": 39.01,
"learning_rate": 1.158625730994152e-05,
"loss": 0.0,
"step": 12030
},
{
"epoch": 39.01,
"learning_rate": 1.154970760233918e-05,
"loss": 0.0,
"step": 12040
},
{
"epoch": 39.01,
"learning_rate": 1.1513157894736843e-05,
"loss": 0.0,
"step": 12050
},
{
"epoch": 39.01,
"learning_rate": 1.1476608187134504e-05,
"loss": 0.0,
"step": 12060
},
{
"epoch": 39.01,
"learning_rate": 1.1440058479532164e-05,
"loss": 0.0,
"step": 12070
},
{
"epoch": 39.01,
"learning_rate": 1.1403508771929824e-05,
"loss": 0.0,
"step": 12080
},
{
"epoch": 39.02,
"learning_rate": 1.1366959064327486e-05,
"loss": 0.0,
"step": 12090
},
{
"epoch": 39.02,
"learning_rate": 1.1330409356725146e-05,
"loss": 0.0,
"step": 12100
},
{
"epoch": 39.02,
"learning_rate": 1.1293859649122808e-05,
"loss": 0.0,
"step": 12110
},
{
"epoch": 39.02,
"learning_rate": 1.1257309941520468e-05,
"loss": 0.0,
"step": 12120
},
{
"epoch": 39.02,
"learning_rate": 1.1220760233918128e-05,
"loss": 0.0,
"step": 12130
},
{
"epoch": 39.02,
"learning_rate": 1.118421052631579e-05,
"loss": 0.0,
"step": 12140
},
{
"epoch": 39.02,
"learning_rate": 1.1147660818713452e-05,
"loss": 0.0,
"step": 12150
},
{
"epoch": 39.02,
"learning_rate": 1.1111111111111112e-05,
"loss": 0.0,
"step": 12160
},
{
"epoch": 39.02,
"eval_accuracy": 0.8223684210526315,
"eval_loss": 1.7723265886306763,
"eval_runtime": 47.1637,
"eval_samples_per_second": 3.223,
"eval_steps_per_second": 3.223,
"step": 12160
},
{
"epoch": 40.0,
"learning_rate": 1.1074561403508772e-05,
"loss": 0.0,
"step": 12170
},
{
"epoch": 40.0,
"learning_rate": 1.1038011695906433e-05,
"loss": 0.0,
"step": 12180
},
{
"epoch": 40.0,
"learning_rate": 1.1001461988304095e-05,
"loss": 0.0,
"step": 12190
},
{
"epoch": 40.0,
"learning_rate": 1.0964912280701754e-05,
"loss": 0.0,
"step": 12200
},
{
"epoch": 40.0,
"learning_rate": 1.0928362573099415e-05,
"loss": 0.0,
"step": 12210
},
{
"epoch": 40.0,
"learning_rate": 1.0891812865497077e-05,
"loss": 0.0,
"step": 12220
},
{
"epoch": 40.0,
"learning_rate": 1.0855263157894737e-05,
"loss": 0.0,
"step": 12230
},
{
"epoch": 40.01,
"learning_rate": 1.0818713450292397e-05,
"loss": 0.0,
"step": 12240
},
{
"epoch": 40.01,
"learning_rate": 1.0782163742690059e-05,
"loss": 0.0,
"step": 12250
},
{
"epoch": 40.01,
"learning_rate": 1.074561403508772e-05,
"loss": 0.0,
"step": 12260
},
{
"epoch": 40.01,
"learning_rate": 1.070906432748538e-05,
"loss": 0.0,
"step": 12270
},
{
"epoch": 40.01,
"learning_rate": 1.067251461988304e-05,
"loss": 0.0,
"step": 12280
},
{
"epoch": 40.01,
"learning_rate": 1.0635964912280703e-05,
"loss": 0.0,
"step": 12290
},
{
"epoch": 40.01,
"learning_rate": 1.0599415204678363e-05,
"loss": 0.0,
"step": 12300
},
{
"epoch": 40.01,
"learning_rate": 1.0562865497076024e-05,
"loss": 0.0,
"step": 12310
},
{
"epoch": 40.01,
"learning_rate": 1.0526315789473684e-05,
"loss": 0.0,
"step": 12320
},
{
"epoch": 40.01,
"learning_rate": 1.0489766081871345e-05,
"loss": 0.0,
"step": 12330
},
{
"epoch": 40.01,
"learning_rate": 1.0453216374269006e-05,
"loss": 0.0,
"step": 12340
},
{
"epoch": 40.01,
"learning_rate": 1.0416666666666668e-05,
"loss": 0.0,
"step": 12350
},
{
"epoch": 40.01,
"learning_rate": 1.0380116959064328e-05,
"loss": 0.0,
"step": 12360
},
{
"epoch": 40.01,
"learning_rate": 1.0343567251461988e-05,
"loss": 0.0,
"step": 12370
},
{
"epoch": 40.01,
"learning_rate": 1.030701754385965e-05,
"loss": 0.0,
"step": 12380
},
{
"epoch": 40.02,
"learning_rate": 1.0270467836257312e-05,
"loss": 0.0,
"step": 12390
},
{
"epoch": 40.02,
"learning_rate": 1.023391812865497e-05,
"loss": 0.0,
"step": 12400
},
{
"epoch": 40.02,
"learning_rate": 1.0197368421052632e-05,
"loss": 0.0,
"step": 12410
},
{
"epoch": 40.02,
"learning_rate": 1.0160818713450294e-05,
"loss": 0.0,
"step": 12420
},
{
"epoch": 40.02,
"learning_rate": 1.0124269005847954e-05,
"loss": 0.0,
"step": 12430
},
{
"epoch": 40.02,
"learning_rate": 1.0087719298245614e-05,
"loss": 0.0,
"step": 12440
},
{
"epoch": 40.02,
"learning_rate": 1.0051169590643275e-05,
"loss": 0.0,
"step": 12450
},
{
"epoch": 40.02,
"learning_rate": 1.0014619883040937e-05,
"loss": 0.0,
"step": 12460
},
{
"epoch": 40.02,
"eval_accuracy": 0.8223684210526315,
"eval_loss": 1.786490559577942,
"eval_runtime": 47.0388,
"eval_samples_per_second": 3.231,
"eval_steps_per_second": 3.231,
"step": 12464
},
{
"epoch": 41.0,
"learning_rate": 9.978070175438597e-06,
"loss": 0.0,
"step": 12470
},
{
"epoch": 41.0,
"learning_rate": 9.941520467836257e-06,
"loss": 0.0,
"step": 12480
},
{
"epoch": 41.0,
"learning_rate": 9.904970760233919e-06,
"loss": 0.0,
"step": 12490
},
{
"epoch": 41.0,
"learning_rate": 9.868421052631579e-06,
"loss": 0.0,
"step": 12500
},
{
"epoch": 41.0,
"learning_rate": 9.83187134502924e-06,
"loss": 0.0,
"step": 12510
},
{
"epoch": 41.0,
"learning_rate": 9.795321637426901e-06,
"loss": 0.0,
"step": 12520
},
{
"epoch": 41.0,
"learning_rate": 9.758771929824561e-06,
"loss": 0.0,
"step": 12530
},
{
"epoch": 41.01,
"learning_rate": 9.722222222222223e-06,
"loss": 0.0,
"step": 12540
},
{
"epoch": 41.01,
"learning_rate": 9.685672514619884e-06,
"loss": 0.0,
"step": 12550
},
{
"epoch": 41.01,
"learning_rate": 9.649122807017545e-06,
"loss": 0.0,
"step": 12560
},
{
"epoch": 41.01,
"learning_rate": 9.612573099415205e-06,
"loss": 0.0,
"step": 12570
},
{
"epoch": 41.01,
"learning_rate": 9.576023391812866e-06,
"loss": 0.0,
"step": 12580
},
{
"epoch": 41.01,
"learning_rate": 9.539473684210528e-06,
"loss": 0.0,
"step": 12590
},
{
"epoch": 41.01,
"learning_rate": 9.502923976608186e-06,
"loss": 0.0,
"step": 12600
},
{
"epoch": 41.01,
"learning_rate": 9.466374269005848e-06,
"loss": 0.0,
"step": 12610
},
{
"epoch": 41.01,
"learning_rate": 9.42982456140351e-06,
"loss": 0.0,
"step": 12620
},
{
"epoch": 41.01,
"learning_rate": 9.39327485380117e-06,
"loss": 0.9452,
"step": 12630
},
{
"epoch": 41.01,
"learning_rate": 9.35672514619883e-06,
"loss": 0.7184,
"step": 12640
},
{
"epoch": 41.01,
"learning_rate": 9.320175438596492e-06,
"loss": 0.0,
"step": 12650
},
{
"epoch": 41.01,
"learning_rate": 9.283625730994152e-06,
"loss": 0.0,
"step": 12660
},
{
"epoch": 41.01,
"learning_rate": 9.247076023391814e-06,
"loss": 0.0,
"step": 12670
},
{
"epoch": 41.01,
"learning_rate": 9.210526315789474e-06,
"loss": 0.0,
"step": 12680
},
{
"epoch": 41.01,
"learning_rate": 9.173976608187135e-06,
"loss": 0.0,
"step": 12690
},
{
"epoch": 41.02,
"learning_rate": 9.137426900584795e-06,
"loss": 0.0,
"step": 12700
},
{
"epoch": 41.02,
"learning_rate": 9.100877192982457e-06,
"loss": 0.0,
"step": 12710
},
{
"epoch": 41.02,
"learning_rate": 9.064327485380117e-06,
"loss": 0.0,
"step": 12720
},
{
"epoch": 41.02,
"learning_rate": 9.027777777777777e-06,
"loss": 0.0,
"step": 12730
},
{
"epoch": 41.02,
"learning_rate": 8.991228070175439e-06,
"loss": 0.0,
"step": 12740
},
{
"epoch": 41.02,
"learning_rate": 8.954678362573101e-06,
"loss": 0.0,
"step": 12750
},
{
"epoch": 41.02,
"learning_rate": 8.918128654970761e-06,
"loss": 0.6067,
"step": 12760
},
{
"epoch": 41.02,
"eval_accuracy": 0.7368421052631579,
"eval_loss": 2.684767007827759,
"eval_runtime": 46.953,
"eval_samples_per_second": 3.237,
"eval_steps_per_second": 3.237,
"step": 12768
},
{
"epoch": 42.0,
"learning_rate": 8.881578947368421e-06,
"loss": 0.0,
"step": 12770
},
{
"epoch": 42.0,
"learning_rate": 8.845029239766083e-06,
"loss": 0.0,
"step": 12780
},
{
"epoch": 42.0,
"learning_rate": 8.808479532163744e-06,
"loss": 1.0662,
"step": 12790
},
{
"epoch": 42.0,
"learning_rate": 8.771929824561403e-06,
"loss": 0.0,
"step": 12800
},
{
"epoch": 42.0,
"learning_rate": 8.735380116959065e-06,
"loss": 0.0,
"step": 12810
},
{
"epoch": 42.0,
"learning_rate": 8.698830409356726e-06,
"loss": 0.0,
"step": 12820
},
{
"epoch": 42.0,
"learning_rate": 8.662280701754386e-06,
"loss": 0.0001,
"step": 12830
},
{
"epoch": 42.0,
"learning_rate": 8.625730994152046e-06,
"loss": 0.0,
"step": 12840
},
{
"epoch": 42.01,
"learning_rate": 8.589181286549708e-06,
"loss": 0.0,
"step": 12850
},
{
"epoch": 42.01,
"learning_rate": 8.552631578947368e-06,
"loss": 0.0001,
"step": 12860
},
{
"epoch": 42.01,
"learning_rate": 8.51608187134503e-06,
"loss": 0.0,
"step": 12870
},
{
"epoch": 42.01,
"learning_rate": 8.47953216374269e-06,
"loss": 0.0,
"step": 12880
},
{
"epoch": 42.01,
"learning_rate": 8.442982456140352e-06,
"loss": 0.0,
"step": 12890
},
{
"epoch": 42.01,
"learning_rate": 8.406432748538012e-06,
"loss": 0.0001,
"step": 12900
},
{
"epoch": 42.01,
"learning_rate": 8.369883040935674e-06,
"loss": 0.0,
"step": 12910
},
{
"epoch": 42.01,
"learning_rate": 8.333333333333334e-06,
"loss": 0.0,
"step": 12920
},
{
"epoch": 42.01,
"learning_rate": 8.296783625730994e-06,
"loss": 0.0001,
"step": 12930
},
{
"epoch": 42.01,
"learning_rate": 8.260233918128656e-06,
"loss": 0.0,
"step": 12940
},
{
"epoch": 42.01,
"learning_rate": 8.223684210526317e-06,
"loss": 0.0,
"step": 12950
},
{
"epoch": 42.01,
"learning_rate": 8.187134502923977e-06,
"loss": 0.0,
"step": 12960
},
{
"epoch": 42.01,
"learning_rate": 8.150584795321637e-06,
"loss": 0.0,
"step": 12970
},
{
"epoch": 42.01,
"learning_rate": 8.1140350877193e-06,
"loss": 0.0,
"step": 12980
},
{
"epoch": 42.01,
"learning_rate": 8.07748538011696e-06,
"loss": 0.0,
"step": 12990
},
{
"epoch": 42.02,
"learning_rate": 8.04093567251462e-06,
"loss": 0.0,
"step": 13000
},
{
"epoch": 42.02,
"learning_rate": 8.004385964912281e-06,
"loss": 0.0,
"step": 13010
},
{
"epoch": 42.02,
"learning_rate": 7.967836257309943e-06,
"loss": 0.0,
"step": 13020
},
{
"epoch": 42.02,
"learning_rate": 7.931286549707603e-06,
"loss": 0.0,
"step": 13030
},
{
"epoch": 42.02,
"learning_rate": 7.894736842105263e-06,
"loss": 0.0,
"step": 13040
},
{
"epoch": 42.02,
"learning_rate": 7.858187134502925e-06,
"loss": 0.0,
"step": 13050
},
{
"epoch": 42.02,
"learning_rate": 7.821637426900585e-06,
"loss": 0.0,
"step": 13060
},
{
"epoch": 42.02,
"learning_rate": 7.785087719298246e-06,
"loss": 0.0001,
"step": 13070
},
{
"epoch": 42.02,
"eval_accuracy": 0.8289473684210527,
"eval_loss": 1.6833863258361816,
"eval_runtime": 47.2297,
"eval_samples_per_second": 3.218,
"eval_steps_per_second": 3.218,
"step": 13072
},
{
"epoch": 43.0,
"learning_rate": 7.748538011695907e-06,
"loss": 0.0,
"step": 13080
},
{
"epoch": 43.0,
"learning_rate": 7.711988304093568e-06,
"loss": 0.0,
"step": 13090
},
{
"epoch": 43.0,
"learning_rate": 7.675438596491228e-06,
"loss": 0.0,
"step": 13100
},
{
"epoch": 43.0,
"learning_rate": 7.63888888888889e-06,
"loss": 0.0,
"step": 13110
},
{
"epoch": 43.0,
"learning_rate": 7.602339181286549e-06,
"loss": 0.0,
"step": 13120
},
{
"epoch": 43.0,
"learning_rate": 7.565789473684211e-06,
"loss": 0.0,
"step": 13130
},
{
"epoch": 43.0,
"learning_rate": 7.529239766081872e-06,
"loss": 0.0,
"step": 13140
},
{
"epoch": 43.01,
"learning_rate": 7.492690058479533e-06,
"loss": 0.0,
"step": 13150
},
{
"epoch": 43.01,
"learning_rate": 7.456140350877193e-06,
"loss": 0.0,
"step": 13160
},
{
"epoch": 43.01,
"learning_rate": 7.419590643274854e-06,
"loss": 0.0,
"step": 13170
},
{
"epoch": 43.01,
"learning_rate": 7.383040935672516e-06,
"loss": 0.0,
"step": 13180
},
{
"epoch": 43.01,
"learning_rate": 7.3464912280701765e-06,
"loss": 0.0,
"step": 13190
},
{
"epoch": 43.01,
"learning_rate": 7.3099415204678366e-06,
"loss": 0.0,
"step": 13200
},
{
"epoch": 43.01,
"learning_rate": 7.2733918128654975e-06,
"loss": 0.0,
"step": 13210
},
{
"epoch": 43.01,
"learning_rate": 7.236842105263158e-06,
"loss": 0.0,
"step": 13220
},
{
"epoch": 43.01,
"learning_rate": 7.200292397660819e-06,
"loss": 0.0,
"step": 13230
},
{
"epoch": 43.01,
"learning_rate": 7.163742690058479e-06,
"loss": 0.0,
"step": 13240
},
{
"epoch": 43.01,
"learning_rate": 7.12719298245614e-06,
"loss": 0.0,
"step": 13250
},
{
"epoch": 43.01,
"learning_rate": 7.090643274853802e-06,
"loss": 0.0,
"step": 13260
},
{
"epoch": 43.01,
"learning_rate": 7.054093567251463e-06,
"loss": 0.0,
"step": 13270
},
{
"epoch": 43.01,
"learning_rate": 7.017543859649123e-06,
"loss": 0.0001,
"step": 13280
},
{
"epoch": 43.01,
"learning_rate": 6.980994152046784e-06,
"loss": 0.0,
"step": 13290
},
{
"epoch": 43.02,
"learning_rate": 6.944444444444445e-06,
"loss": 0.0,
"step": 13300
},
{
"epoch": 43.02,
"learning_rate": 6.9078947368421065e-06,
"loss": 0.0,
"step": 13310
},
{
"epoch": 43.02,
"learning_rate": 6.871345029239766e-06,
"loss": 0.0,
"step": 13320
},
{
"epoch": 43.02,
"learning_rate": 6.8347953216374275e-06,
"loss": 0.0,
"step": 13330
},
{
"epoch": 43.02,
"learning_rate": 6.798245614035088e-06,
"loss": 0.0,
"step": 13340
},
{
"epoch": 43.02,
"learning_rate": 6.761695906432749e-06,
"loss": 0.0,
"step": 13350
},
{
"epoch": 43.02,
"learning_rate": 6.725146198830409e-06,
"loss": 0.0,
"step": 13360
},
{
"epoch": 43.02,
"learning_rate": 6.68859649122807e-06,
"loss": 0.0,
"step": 13370
},
{
"epoch": 43.02,
"eval_accuracy": 0.8289473684210527,
"eval_loss": 1.7187632322311401,
"eval_runtime": 47.0191,
"eval_samples_per_second": 3.233,
"eval_steps_per_second": 3.233,
"step": 13376
},
{
"epoch": 44.0,
"learning_rate": 6.652046783625732e-06,
"loss": 0.0,
"step": 13380
},
{
"epoch": 44.0,
"learning_rate": 6.615497076023393e-06,
"loss": 0.0,
"step": 13390
},
{
"epoch": 44.0,
"learning_rate": 6.578947368421053e-06,
"loss": 0.0,
"step": 13400
},
{
"epoch": 44.0,
"learning_rate": 6.542397660818714e-06,
"loss": 0.0,
"step": 13410
},
{
"epoch": 44.0,
"learning_rate": 6.505847953216375e-06,
"loss": 0.0,
"step": 13420
},
{
"epoch": 44.0,
"learning_rate": 6.469298245614036e-06,
"loss": 0.0,
"step": 13430
},
{
"epoch": 44.0,
"learning_rate": 6.432748538011696e-06,
"loss": 0.0,
"step": 13440
},
{
"epoch": 44.0,
"learning_rate": 6.396198830409357e-06,
"loss": 0.0,
"step": 13450
},
{
"epoch": 44.01,
"learning_rate": 6.3596491228070184e-06,
"loss": 0.0,
"step": 13460
},
{
"epoch": 44.01,
"learning_rate": 6.323099415204679e-06,
"loss": 0.0,
"step": 13470
},
{
"epoch": 44.01,
"learning_rate": 6.286549707602339e-06,
"loss": 0.0,
"step": 13480
},
{
"epoch": 44.01,
"learning_rate": 6.25e-06,
"loss": 0.0,
"step": 13490
},
{
"epoch": 44.01,
"learning_rate": 6.21345029239766e-06,
"loss": 0.0,
"step": 13500
},
{
"epoch": 44.01,
"learning_rate": 6.176900584795322e-06,
"loss": 0.0,
"step": 13510
},
{
"epoch": 44.01,
"learning_rate": 6.140350877192982e-06,
"loss": 0.0,
"step": 13520
},
{
"epoch": 44.01,
"learning_rate": 6.103801169590644e-06,
"loss": 0.0,
"step": 13530
},
{
"epoch": 44.01,
"learning_rate": 6.067251461988304e-06,
"loss": 0.0,
"step": 13540
},
{
"epoch": 44.01,
"learning_rate": 6.030701754385965e-06,
"loss": 0.0,
"step": 13550
},
{
"epoch": 44.01,
"learning_rate": 5.994152046783626e-06,
"loss": 0.0,
"step": 13560
},
{
"epoch": 44.01,
"learning_rate": 5.957602339181287e-06,
"loss": 0.0,
"step": 13570
},
{
"epoch": 44.01,
"learning_rate": 5.921052631578948e-06,
"loss": 0.0,
"step": 13580
},
{
"epoch": 44.01,
"learning_rate": 5.8845029239766085e-06,
"loss": 0.0,
"step": 13590
},
{
"epoch": 44.01,
"learning_rate": 5.8479532163742686e-06,
"loss": 0.0,
"step": 13600
},
{
"epoch": 44.02,
"learning_rate": 5.81140350877193e-06,
"loss": 0.0,
"step": 13610
},
{
"epoch": 44.02,
"learning_rate": 5.77485380116959e-06,
"loss": 0.0,
"step": 13620
},
{
"epoch": 44.02,
"learning_rate": 5.738304093567252e-06,
"loss": 0.0,
"step": 13630
},
{
"epoch": 44.02,
"learning_rate": 5.701754385964912e-06,
"loss": 0.0,
"step": 13640
},
{
"epoch": 44.02,
"learning_rate": 5.665204678362573e-06,
"loss": 0.0,
"step": 13650
},
{
"epoch": 44.02,
"learning_rate": 5.628654970760234e-06,
"loss": 0.0,
"step": 13660
},
{
"epoch": 44.02,
"learning_rate": 5.592105263157895e-06,
"loss": 0.0,
"step": 13670
},
{
"epoch": 44.02,
"learning_rate": 5.555555555555556e-06,
"loss": 0.9374,
"step": 13680
},
{
"epoch": 44.02,
"eval_accuracy": 0.8421052631578947,
"eval_loss": 1.5728034973144531,
"eval_runtime": 46.8493,
"eval_samples_per_second": 3.244,
"eval_steps_per_second": 3.244,
"step": 13680
},
{
"epoch": 45.0,
"learning_rate": 5.519005847953217e-06,
"loss": 0.0,
"step": 13690
},
{
"epoch": 45.0,
"learning_rate": 5.482456140350877e-06,
"loss": 0.0,
"step": 13700
},
{
"epoch": 45.0,
"learning_rate": 5.4459064327485385e-06,
"loss": 0.0,
"step": 13710
},
{
"epoch": 45.0,
"learning_rate": 5.409356725146199e-06,
"loss": 0.0861,
"step": 13720
},
{
"epoch": 45.0,
"learning_rate": 5.37280701754386e-06,
"loss": 0.0,
"step": 13730
},
{
"epoch": 45.0,
"learning_rate": 5.33625730994152e-06,
"loss": 0.0,
"step": 13740
},
{
"epoch": 45.0,
"learning_rate": 5.299707602339181e-06,
"loss": 0.0,
"step": 13750
},
{
"epoch": 45.01,
"learning_rate": 5.263157894736842e-06,
"loss": 0.0,
"step": 13760
},
{
"epoch": 45.01,
"learning_rate": 5.226608187134503e-06,
"loss": 0.0,
"step": 13770
},
{
"epoch": 45.01,
"learning_rate": 5.190058479532164e-06,
"loss": 0.0,
"step": 13780
},
{
"epoch": 45.01,
"learning_rate": 5.153508771929825e-06,
"loss": 0.0,
"step": 13790
},
{
"epoch": 45.01,
"learning_rate": 5.116959064327485e-06,
"loss": 0.0,
"step": 13800
},
{
"epoch": 45.01,
"learning_rate": 5.080409356725147e-06,
"loss": 0.0,
"step": 13810
},
{
"epoch": 45.01,
"learning_rate": 5.043859649122807e-06,
"loss": 0.0,
"step": 13820
},
{
"epoch": 45.01,
"learning_rate": 5.0073099415204686e-06,
"loss": 0.0,
"step": 13830
},
{
"epoch": 45.01,
"learning_rate": 4.970760233918129e-06,
"loss": 0.0,
"step": 13840
},
{
"epoch": 45.01,
"learning_rate": 4.9342105263157895e-06,
"loss": 0.0,
"step": 13850
},
{
"epoch": 45.01,
"learning_rate": 4.8976608187134504e-06,
"loss": 0.0,
"step": 13860
},
{
"epoch": 45.01,
"learning_rate": 4.861111111111111e-06,
"loss": 0.0,
"step": 13870
},
{
"epoch": 45.01,
"learning_rate": 4.824561403508772e-06,
"loss": 0.0,
"step": 13880
},
{
"epoch": 45.01,
"learning_rate": 4.788011695906433e-06,
"loss": 0.0,
"step": 13890
},
{
"epoch": 45.01,
"learning_rate": 4.751461988304093e-06,
"loss": 0.0,
"step": 13900
},
{
"epoch": 45.02,
"learning_rate": 4.714912280701755e-06,
"loss": 0.0,
"step": 13910
},
{
"epoch": 45.02,
"learning_rate": 4.678362573099415e-06,
"loss": 0.0,
"step": 13920
},
{
"epoch": 45.02,
"learning_rate": 4.641812865497076e-06,
"loss": 0.0,
"step": 13930
},
{
"epoch": 45.02,
"learning_rate": 4.605263157894737e-06,
"loss": 0.0,
"step": 13940
},
{
"epoch": 45.02,
"learning_rate": 4.568713450292398e-06,
"loss": 0.0,
"step": 13950
},
{
"epoch": 45.02,
"learning_rate": 4.532163742690059e-06,
"loss": 0.0,
"step": 13960
},
{
"epoch": 45.02,
"learning_rate": 4.4956140350877196e-06,
"loss": 0.0,
"step": 13970
},
{
"epoch": 45.02,
"learning_rate": 4.4590643274853805e-06,
"loss": 0.0,
"step": 13980
},
{
"epoch": 45.02,
"eval_accuracy": 0.7894736842105263,
"eval_loss": 2.09879994392395,
"eval_runtime": 47.2927,
"eval_samples_per_second": 3.214,
"eval_steps_per_second": 3.214,
"step": 13984
},
{
"epoch": 46.0,
"learning_rate": 4.422514619883041e-06,
"loss": 0.0001,
"step": 13990
},
{
"epoch": 46.0,
"learning_rate": 4.3859649122807014e-06,
"loss": 0.0,
"step": 14000
},
{
"epoch": 46.0,
"learning_rate": 4.349415204678363e-06,
"loss": 0.0,
"step": 14010
},
{
"epoch": 46.0,
"learning_rate": 4.312865497076023e-06,
"loss": 0.0,
"step": 14020
},
{
"epoch": 46.0,
"learning_rate": 4.276315789473684e-06,
"loss": 0.0,
"step": 14030
},
{
"epoch": 46.0,
"learning_rate": 4.239766081871345e-06,
"loss": 0.0,
"step": 14040
},
{
"epoch": 46.0,
"learning_rate": 4.203216374269006e-06,
"loss": 0.0,
"step": 14050
},
{
"epoch": 46.01,
"learning_rate": 4.166666666666667e-06,
"loss": 0.0,
"step": 14060
},
{
"epoch": 46.01,
"learning_rate": 4.130116959064328e-06,
"loss": 0.0,
"step": 14070
},
{
"epoch": 46.01,
"learning_rate": 4.093567251461989e-06,
"loss": 0.0,
"step": 14080
},
{
"epoch": 46.01,
"learning_rate": 4.05701754385965e-06,
"loss": 0.0,
"step": 14090
},
{
"epoch": 46.01,
"learning_rate": 4.02046783625731e-06,
"loss": 0.0,
"step": 14100
},
{
"epoch": 46.01,
"learning_rate": 3.983918128654971e-06,
"loss": 0.0,
"step": 14110
},
{
"epoch": 46.01,
"learning_rate": 3.9473684210526315e-06,
"loss": 0.0,
"step": 14120
},
{
"epoch": 46.01,
"learning_rate": 3.910818713450292e-06,
"loss": 0.0,
"step": 14130
},
{
"epoch": 46.01,
"learning_rate": 3.874269005847953e-06,
"loss": 0.0001,
"step": 14140
},
{
"epoch": 46.01,
"learning_rate": 3.837719298245614e-06,
"loss": 0.0,
"step": 14150
},
{
"epoch": 46.01,
"learning_rate": 3.8011695906432747e-06,
"loss": 0.0,
"step": 14160
},
{
"epoch": 46.01,
"learning_rate": 3.764619883040936e-06,
"loss": 0.0,
"step": 14170
},
{
"epoch": 46.01,
"learning_rate": 3.7280701754385965e-06,
"loss": 0.0,
"step": 14180
},
{
"epoch": 46.01,
"learning_rate": 3.691520467836258e-06,
"loss": 0.0,
"step": 14190
},
{
"epoch": 46.01,
"learning_rate": 3.6549707602339183e-06,
"loss": 0.0,
"step": 14200
},
{
"epoch": 46.01,
"learning_rate": 3.618421052631579e-06,
"loss": 0.0,
"step": 14210
},
{
"epoch": 46.02,
"learning_rate": 3.5818713450292397e-06,
"loss": 0.0,
"step": 14220
},
{
"epoch": 46.02,
"learning_rate": 3.545321637426901e-06,
"loss": 0.0,
"step": 14230
},
{
"epoch": 46.02,
"learning_rate": 3.5087719298245615e-06,
"loss": 0.0001,
"step": 14240
},
{
"epoch": 46.02,
"learning_rate": 3.4722222222222224e-06,
"loss": 0.0,
"step": 14250
},
{
"epoch": 46.02,
"learning_rate": 3.435672514619883e-06,
"loss": 0.0,
"step": 14260
},
{
"epoch": 46.02,
"learning_rate": 3.399122807017544e-06,
"loss": 0.0,
"step": 14270
},
{
"epoch": 46.02,
"learning_rate": 3.3625730994152047e-06,
"loss": 0.0,
"step": 14280
},
{
"epoch": 46.02,
"eval_accuracy": 0.7828947368421053,
"eval_loss": 2.0841124057769775,
"eval_runtime": 47.1332,
"eval_samples_per_second": 3.225,
"eval_steps_per_second": 3.225,
"step": 14288
},
{
"epoch": 47.0,
"learning_rate": 3.326023391812866e-06,
"loss": 0.0,
"step": 14290
},
{
"epoch": 47.0,
"learning_rate": 3.2894736842105265e-06,
"loss": 0.0,
"step": 14300
},
{
"epoch": 47.0,
"learning_rate": 3.2529239766081874e-06,
"loss": 0.0,
"step": 14310
},
{
"epoch": 47.0,
"learning_rate": 3.216374269005848e-06,
"loss": 0.0,
"step": 14320
},
{
"epoch": 47.0,
"learning_rate": 3.1798245614035092e-06,
"loss": 0.0,
"step": 14330
},
{
"epoch": 47.0,
"learning_rate": 3.1432748538011697e-06,
"loss": 0.0,
"step": 14340
},
{
"epoch": 47.0,
"learning_rate": 3.10672514619883e-06,
"loss": 0.0,
"step": 14350
},
{
"epoch": 47.0,
"learning_rate": 3.070175438596491e-06,
"loss": 0.0,
"step": 14360
},
{
"epoch": 47.01,
"learning_rate": 3.033625730994152e-06,
"loss": 0.0,
"step": 14370
},
{
"epoch": 47.01,
"learning_rate": 2.997076023391813e-06,
"loss": 0.0,
"step": 14380
},
{
"epoch": 47.01,
"learning_rate": 2.960526315789474e-06,
"loss": 0.0,
"step": 14390
},
{
"epoch": 47.01,
"learning_rate": 2.9239766081871343e-06,
"loss": 0.0,
"step": 14400
},
{
"epoch": 47.01,
"learning_rate": 2.887426900584795e-06,
"loss": 0.0,
"step": 14410
},
{
"epoch": 47.01,
"learning_rate": 2.850877192982456e-06,
"loss": 0.0,
"step": 14420
},
{
"epoch": 47.01,
"learning_rate": 2.814327485380117e-06,
"loss": 0.0002,
"step": 14430
},
{
"epoch": 47.01,
"learning_rate": 2.777777777777778e-06,
"loss": 0.0,
"step": 14440
},
{
"epoch": 47.01,
"learning_rate": 2.7412280701754384e-06,
"loss": 0.0,
"step": 14450
},
{
"epoch": 47.01,
"learning_rate": 2.7046783625730993e-06,
"loss": 0.0,
"step": 14460
},
{
"epoch": 47.01,
"learning_rate": 2.66812865497076e-06,
"loss": 0.0,
"step": 14470
},
{
"epoch": 47.01,
"learning_rate": 2.631578947368421e-06,
"loss": 0.0,
"step": 14480
},
{
"epoch": 47.01,
"learning_rate": 2.595029239766082e-06,
"loss": 0.0,
"step": 14490
},
{
"epoch": 47.01,
"learning_rate": 2.5584795321637425e-06,
"loss": 0.0,
"step": 14500
},
{
"epoch": 47.01,
"learning_rate": 2.5219298245614034e-06,
"loss": 0.0,
"step": 14510
},
{
"epoch": 47.02,
"learning_rate": 2.4853801169590643e-06,
"loss": 0.0,
"step": 14520
},
{
"epoch": 47.02,
"learning_rate": 2.4488304093567252e-06,
"loss": 0.0,
"step": 14530
},
{
"epoch": 47.02,
"learning_rate": 2.412280701754386e-06,
"loss": 0.0,
"step": 14540
},
{
"epoch": 47.02,
"learning_rate": 2.3757309941520466e-06,
"loss": 0.0,
"step": 14550
},
{
"epoch": 47.02,
"learning_rate": 2.3391812865497075e-06,
"loss": 0.0,
"step": 14560
},
{
"epoch": 47.02,
"learning_rate": 2.3026315789473684e-06,
"loss": 0.0,
"step": 14570
},
{
"epoch": 47.02,
"learning_rate": 2.2660818713450293e-06,
"loss": 0.0,
"step": 14580
},
{
"epoch": 47.02,
"learning_rate": 2.2295321637426902e-06,
"loss": 0.0,
"step": 14590
},
{
"epoch": 47.02,
"eval_accuracy": 0.7631578947368421,
"eval_loss": 2.219816207885742,
"eval_runtime": 47.1982,
"eval_samples_per_second": 3.22,
"eval_steps_per_second": 3.22,
"step": 14592
},
{
"epoch": 48.0,
"learning_rate": 2.1929824561403507e-06,
"loss": 0.0,
"step": 14600
},
{
"epoch": 48.0,
"learning_rate": 2.1564327485380116e-06,
"loss": 0.0,
"step": 14610
},
{
"epoch": 48.0,
"learning_rate": 2.1198830409356725e-06,
"loss": 0.0,
"step": 14620
},
{
"epoch": 48.0,
"learning_rate": 2.0833333333333334e-06,
"loss": 0.0,
"step": 14630
},
{
"epoch": 48.0,
"learning_rate": 2.0467836257309943e-06,
"loss": 0.0,
"step": 14640
},
{
"epoch": 48.0,
"learning_rate": 2.010233918128655e-06,
"loss": 0.0,
"step": 14650
},
{
"epoch": 48.0,
"learning_rate": 1.9736842105263157e-06,
"loss": 0.0,
"step": 14660
},
{
"epoch": 48.01,
"learning_rate": 1.9371345029239766e-06,
"loss": 0.0,
"step": 14670
},
{
"epoch": 48.01,
"learning_rate": 1.9005847953216373e-06,
"loss": 0.0,
"step": 14680
},
{
"epoch": 48.01,
"learning_rate": 1.8640350877192982e-06,
"loss": 0.0,
"step": 14690
},
{
"epoch": 48.01,
"learning_rate": 1.8274853801169591e-06,
"loss": 0.0,
"step": 14700
},
{
"epoch": 48.01,
"learning_rate": 1.7909356725146198e-06,
"loss": 0.0,
"step": 14710
},
{
"epoch": 48.01,
"learning_rate": 1.7543859649122807e-06,
"loss": 0.0001,
"step": 14720
},
{
"epoch": 48.01,
"learning_rate": 1.7178362573099414e-06,
"loss": 0.0,
"step": 14730
},
{
"epoch": 48.01,
"learning_rate": 1.6812865497076023e-06,
"loss": 0.0,
"step": 14740
},
{
"epoch": 48.01,
"learning_rate": 1.6447368421052632e-06,
"loss": 0.0,
"step": 14750
},
{
"epoch": 48.01,
"learning_rate": 1.608187134502924e-06,
"loss": 0.0,
"step": 14760
},
{
"epoch": 48.01,
"learning_rate": 1.5716374269005848e-06,
"loss": 0.0,
"step": 14770
},
{
"epoch": 48.01,
"learning_rate": 1.5350877192982455e-06,
"loss": 0.0,
"step": 14780
},
{
"epoch": 48.01,
"learning_rate": 1.4985380116959064e-06,
"loss": 0.0,
"step": 14790
},
{
"epoch": 48.01,
"learning_rate": 1.4619883040935671e-06,
"loss": 0.0,
"step": 14800
},
{
"epoch": 48.01,
"learning_rate": 1.425438596491228e-06,
"loss": 0.0,
"step": 14810
},
{
"epoch": 48.02,
"learning_rate": 1.388888888888889e-06,
"loss": 0.0,
"step": 14820
},
{
"epoch": 48.02,
"learning_rate": 1.3523391812865496e-06,
"loss": 0.0,
"step": 14830
},
{
"epoch": 48.02,
"learning_rate": 1.3157894736842106e-06,
"loss": 0.0,
"step": 14840
},
{
"epoch": 48.02,
"learning_rate": 1.2792397660818713e-06,
"loss": 0.0,
"step": 14850
},
{
"epoch": 48.02,
"learning_rate": 1.2426900584795322e-06,
"loss": 0.0,
"step": 14860
},
{
"epoch": 48.02,
"learning_rate": 1.206140350877193e-06,
"loss": 0.0,
"step": 14870
},
{
"epoch": 48.02,
"learning_rate": 1.1695906432748538e-06,
"loss": 0.0,
"step": 14880
},
{
"epoch": 48.02,
"learning_rate": 1.1330409356725147e-06,
"loss": 0.0,
"step": 14890
},
{
"epoch": 48.02,
"eval_accuracy": 0.7631578947368421,
"eval_loss": 2.201960563659668,
"eval_runtime": 47.1144,
"eval_samples_per_second": 3.226,
"eval_steps_per_second": 3.226,
"step": 14896
},
{
"epoch": 49.0,
"learning_rate": 1.0964912280701754e-06,
"loss": 0.0,
"step": 14900
},
{
"epoch": 49.0,
"learning_rate": 1.0599415204678363e-06,
"loss": 0.0,
"step": 14910
},
{
"epoch": 49.0,
"learning_rate": 1.0233918128654972e-06,
"loss": 0.0,
"step": 14920
},
{
"epoch": 49.0,
"learning_rate": 9.868421052631579e-07,
"loss": 0.0,
"step": 14930
},
{
"epoch": 49.0,
"learning_rate": 9.502923976608187e-07,
"loss": 0.0,
"step": 14940
},
{
"epoch": 49.0,
"learning_rate": 9.137426900584796e-07,
"loss": 0.0,
"step": 14950
},
{
"epoch": 49.0,
"learning_rate": 8.771929824561404e-07,
"loss": 0.0,
"step": 14960
},
{
"epoch": 49.0,
"learning_rate": 8.406432748538012e-07,
"loss": 0.0,
"step": 14970
},
{
"epoch": 49.01,
"learning_rate": 8.04093567251462e-07,
"loss": 0.0002,
"step": 14980
},
{
"epoch": 49.01,
"learning_rate": 7.675438596491228e-07,
"loss": 0.0,
"step": 14990
},
{
"epoch": 49.01,
"learning_rate": 7.309941520467836e-07,
"loss": 0.0,
"step": 15000
},
{
"epoch": 49.01,
"learning_rate": 6.944444444444445e-07,
"loss": 0.0,
"step": 15010
},
{
"epoch": 49.01,
"learning_rate": 6.578947368421053e-07,
"loss": 0.0,
"step": 15020
},
{
"epoch": 49.01,
"learning_rate": 6.213450292397661e-07,
"loss": 0.0,
"step": 15030
},
{
"epoch": 49.01,
"learning_rate": 5.847953216374269e-07,
"loss": 0.0,
"step": 15040
},
{
"epoch": 49.01,
"learning_rate": 5.482456140350877e-07,
"loss": 0.0,
"step": 15050
},
{
"epoch": 49.01,
"learning_rate": 5.116959064327486e-07,
"loss": 0.0,
"step": 15060
},
{
"epoch": 49.01,
"learning_rate": 4.7514619883040933e-07,
"loss": 0.0,
"step": 15070
},
{
"epoch": 49.01,
"learning_rate": 4.385964912280702e-07,
"loss": 0.0,
"step": 15080
},
{
"epoch": 49.01,
"learning_rate": 4.02046783625731e-07,
"loss": 0.0,
"step": 15090
},
{
"epoch": 49.01,
"learning_rate": 3.654970760233918e-07,
"loss": 0.0,
"step": 15100
},
{
"epoch": 49.01,
"learning_rate": 3.2894736842105264e-07,
"loss": 0.0,
"step": 15110
},
{
"epoch": 49.01,
"learning_rate": 2.9239766081871344e-07,
"loss": 0.0,
"step": 15120
},
{
"epoch": 49.02,
"learning_rate": 2.558479532163743e-07,
"loss": 0.0,
"step": 15130
},
{
"epoch": 49.02,
"learning_rate": 2.192982456140351e-07,
"loss": 0.0,
"step": 15140
},
{
"epoch": 49.02,
"learning_rate": 1.827485380116959e-07,
"loss": 0.0,
"step": 15150
},
{
"epoch": 49.02,
"learning_rate": 1.4619883040935672e-07,
"loss": 0.0,
"step": 15160
},
{
"epoch": 49.02,
"learning_rate": 1.0964912280701755e-07,
"loss": 0.0,
"step": 15170
},
{
"epoch": 49.02,
"learning_rate": 7.309941520467836e-08,
"loss": 0.0,
"step": 15180
},
{
"epoch": 49.02,
"learning_rate": 3.654970760233918e-08,
"loss": 0.0,
"step": 15190
},
{
"epoch": 49.02,
"learning_rate": 0.0,
"loss": 0.0,
"step": 15200
},
{
"epoch": 49.02,
"eval_accuracy": 0.7763157894736842,
"eval_loss": 2.069334030151367,
"eval_runtime": 47.0129,
"eval_samples_per_second": 3.233,
"eval_steps_per_second": 3.233,
"step": 15200
},
{
"epoch": 49.02,
"step": 15200,
"total_flos": 1.8940350671172403e+19,
"train_loss": 0.15512951662093705,
"train_runtime": 13696.4388,
"train_samples_per_second": 1.11,
"train_steps_per_second": 1.11
},
{
"epoch": 49.02,
"eval_accuracy": 0.8333333333333334,
"eval_loss": 1.1286733150482178,
"eval_runtime": 27.0307,
"eval_samples_per_second": 3.108,
"eval_steps_per_second": 3.108,
"step": 15200
},
{
"epoch": 49.02,
"eval_accuracy": 0.8333333333333334,
"eval_loss": 1.1286733150482178,
"eval_runtime": 26.4415,
"eval_samples_per_second": 3.177,
"eval_steps_per_second": 3.177,
"step": 15200
}
],
"max_steps": 15200,
"num_train_epochs": 9223372036854775807,
"total_flos": 1.8940350671172403e+19,
"trial_name": null,
"trial_params": null
}