|
{ |
|
"best_metric": 0.9375, |
|
"best_model_checkpoint": "videomae-base-finetuned-kinetics-finetuned-nba-binary-data-2-batch-50-epochs-new-database/checkpoint-6800", |
|
"epoch": 49.02, |
|
"global_step": 10000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 5.000000000000001e-07, |
|
"loss": 0.6874, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 1.0000000000000002e-06, |
|
"loss": 0.6804, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 1.5e-06, |
|
"loss": 0.6966, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 2.0000000000000003e-06, |
|
"loss": 0.6969, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 2.5e-06, |
|
"loss": 0.6994, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 3e-06, |
|
"loss": 0.7038, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 3.5000000000000004e-06, |
|
"loss": 0.7008, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 4.000000000000001e-06, |
|
"loss": 0.7033, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 4.5e-06, |
|
"loss": 0.6754, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 5e-06, |
|
"loss": 0.6911, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 5.500000000000001e-06, |
|
"loss": 0.6836, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 6e-06, |
|
"loss": 0.6869, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 6.5000000000000004e-06, |
|
"loss": 0.6629, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 7.000000000000001e-06, |
|
"loss": 0.7001, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 7.5e-06, |
|
"loss": 0.6755, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 8.000000000000001e-06, |
|
"loss": 0.6481, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 8.500000000000002e-06, |
|
"loss": 0.6, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 9e-06, |
|
"loss": 0.6837, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 9.5e-06, |
|
"loss": 0.5831, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 1e-05, |
|
"loss": 0.6618, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"eval_accuracy": 0.6875, |
|
"eval_loss": 0.6292815208435059, |
|
"eval_runtime": 41.8961, |
|
"eval_samples_per_second": 1.146, |
|
"eval_steps_per_second": 0.573, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 1.05e-05, |
|
"loss": 0.5938, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 1.1000000000000001e-05, |
|
"loss": 0.4928, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 1.1500000000000002e-05, |
|
"loss": 0.5788, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 1.2e-05, |
|
"loss": 0.5877, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 1.25e-05, |
|
"loss": 0.4394, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 1.3000000000000001e-05, |
|
"loss": 0.9105, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 1.3500000000000001e-05, |
|
"loss": 0.355, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 1.4000000000000001e-05, |
|
"loss": 0.4857, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 1.45e-05, |
|
"loss": 1.1395, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 1.5e-05, |
|
"loss": 0.635, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 1.55e-05, |
|
"loss": 0.6305, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 1.6000000000000003e-05, |
|
"loss": 0.807, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 1.65e-05, |
|
"loss": 0.4485, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 1.7000000000000003e-05, |
|
"loss": 0.4862, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 1.75e-05, |
|
"loss": 0.782, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 1.8e-05, |
|
"loss": 0.7402, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 1.85e-05, |
|
"loss": 0.3372, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 1.9e-05, |
|
"loss": 0.7372, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 1.9500000000000003e-05, |
|
"loss": 0.6038, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 2e-05, |
|
"loss": 0.5781, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"eval_accuracy": 0.6041666666666666, |
|
"eval_loss": 1.4659703969955444, |
|
"eval_runtime": 12.3416, |
|
"eval_samples_per_second": 3.889, |
|
"eval_steps_per_second": 1.945, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 2.05e-05, |
|
"loss": 0.4226, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 2.1e-05, |
|
"loss": 0.5528, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 2.15e-05, |
|
"loss": 0.3744, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 2.2000000000000003e-05, |
|
"loss": 1.119, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 2.25e-05, |
|
"loss": 0.4872, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 2.01, |
|
"learning_rate": 2.3000000000000003e-05, |
|
"loss": 0.2642, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 2.01, |
|
"learning_rate": 2.35e-05, |
|
"loss": 0.9276, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 2.01, |
|
"learning_rate": 2.4e-05, |
|
"loss": 0.2525, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 2.01, |
|
"learning_rate": 2.45e-05, |
|
"loss": 1.6111, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 2.01, |
|
"learning_rate": 2.5e-05, |
|
"loss": 0.0984, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 2.01, |
|
"learning_rate": 2.5500000000000003e-05, |
|
"loss": 1.4009, |
|
"step": 510 |
|
}, |
|
{ |
|
"epoch": 2.01, |
|
"learning_rate": 2.6000000000000002e-05, |
|
"loss": 0.7135, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 2.01, |
|
"learning_rate": 2.6500000000000004e-05, |
|
"loss": 0.657, |
|
"step": 530 |
|
}, |
|
{ |
|
"epoch": 2.01, |
|
"learning_rate": 2.7000000000000002e-05, |
|
"loss": 0.3769, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 2.02, |
|
"learning_rate": 2.7500000000000004e-05, |
|
"loss": 0.5822, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 2.02, |
|
"learning_rate": 2.8000000000000003e-05, |
|
"loss": 0.7176, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 2.02, |
|
"learning_rate": 2.8499999999999998e-05, |
|
"loss": 0.2372, |
|
"step": 570 |
|
}, |
|
{ |
|
"epoch": 2.02, |
|
"learning_rate": 2.9e-05, |
|
"loss": 0.5913, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 2.02, |
|
"learning_rate": 2.95e-05, |
|
"loss": 1.3415, |
|
"step": 590 |
|
}, |
|
{ |
|
"epoch": 2.02, |
|
"learning_rate": 3e-05, |
|
"loss": 0.8554, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 2.02, |
|
"eval_accuracy": 0.6666666666666666, |
|
"eval_loss": 0.8739717602729797, |
|
"eval_runtime": 11.7537, |
|
"eval_samples_per_second": 4.084, |
|
"eval_steps_per_second": 2.042, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"learning_rate": 3.05e-05, |
|
"loss": 0.3129, |
|
"step": 610 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"learning_rate": 3.1e-05, |
|
"loss": 0.8611, |
|
"step": 620 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"learning_rate": 3.15e-05, |
|
"loss": 0.7397, |
|
"step": 630 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"learning_rate": 3.2000000000000005e-05, |
|
"loss": 0.6457, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"learning_rate": 3.2500000000000004e-05, |
|
"loss": 0.0948, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 3.01, |
|
"learning_rate": 3.3e-05, |
|
"loss": 0.6953, |
|
"step": 660 |
|
}, |
|
{ |
|
"epoch": 3.01, |
|
"learning_rate": 3.35e-05, |
|
"loss": 0.8116, |
|
"step": 670 |
|
}, |
|
{ |
|
"epoch": 3.01, |
|
"learning_rate": 3.4000000000000007e-05, |
|
"loss": 0.3654, |
|
"step": 680 |
|
}, |
|
{ |
|
"epoch": 3.01, |
|
"learning_rate": 3.45e-05, |
|
"loss": 0.7707, |
|
"step": 690 |
|
}, |
|
{ |
|
"epoch": 3.01, |
|
"learning_rate": 3.5e-05, |
|
"loss": 0.9505, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 3.01, |
|
"learning_rate": 3.55e-05, |
|
"loss": 1.4837, |
|
"step": 710 |
|
}, |
|
{ |
|
"epoch": 3.01, |
|
"learning_rate": 3.6e-05, |
|
"loss": 0.7708, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 3.01, |
|
"learning_rate": 3.65e-05, |
|
"loss": 0.855, |
|
"step": 730 |
|
}, |
|
{ |
|
"epoch": 3.01, |
|
"learning_rate": 3.7e-05, |
|
"loss": 0.2798, |
|
"step": 740 |
|
}, |
|
{ |
|
"epoch": 3.02, |
|
"learning_rate": 3.7500000000000003e-05, |
|
"loss": 1.2943, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 3.02, |
|
"learning_rate": 3.8e-05, |
|
"loss": 1.3738, |
|
"step": 760 |
|
}, |
|
{ |
|
"epoch": 3.02, |
|
"learning_rate": 3.85e-05, |
|
"loss": 0.2935, |
|
"step": 770 |
|
}, |
|
{ |
|
"epoch": 3.02, |
|
"learning_rate": 3.9000000000000006e-05, |
|
"loss": 0.6118, |
|
"step": 780 |
|
}, |
|
{ |
|
"epoch": 3.02, |
|
"learning_rate": 3.9500000000000005e-05, |
|
"loss": 0.4122, |
|
"step": 790 |
|
}, |
|
{ |
|
"epoch": 3.02, |
|
"learning_rate": 4e-05, |
|
"loss": 0.4445, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 3.02, |
|
"eval_accuracy": 0.6666666666666666, |
|
"eval_loss": 1.0660134553909302, |
|
"eval_runtime": 12.6381, |
|
"eval_samples_per_second": 3.798, |
|
"eval_steps_per_second": 1.899, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"learning_rate": 4.05e-05, |
|
"loss": 1.1546, |
|
"step": 810 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"learning_rate": 4.1e-05, |
|
"loss": 0.7915, |
|
"step": 820 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"learning_rate": 4.15e-05, |
|
"loss": 0.936, |
|
"step": 830 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"learning_rate": 4.2e-05, |
|
"loss": 0.4684, |
|
"step": 840 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"learning_rate": 4.25e-05, |
|
"loss": 0.9355, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 4.01, |
|
"learning_rate": 4.3e-05, |
|
"loss": 0.8043, |
|
"step": 860 |
|
}, |
|
{ |
|
"epoch": 4.01, |
|
"learning_rate": 4.35e-05, |
|
"loss": 0.2802, |
|
"step": 870 |
|
}, |
|
{ |
|
"epoch": 4.01, |
|
"learning_rate": 4.4000000000000006e-05, |
|
"loss": 0.5654, |
|
"step": 880 |
|
}, |
|
{ |
|
"epoch": 4.01, |
|
"learning_rate": 4.4500000000000004e-05, |
|
"loss": 1.4987, |
|
"step": 890 |
|
}, |
|
{ |
|
"epoch": 4.01, |
|
"learning_rate": 4.5e-05, |
|
"loss": 0.7365, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 4.01, |
|
"learning_rate": 4.55e-05, |
|
"loss": 0.141, |
|
"step": 910 |
|
}, |
|
{ |
|
"epoch": 4.01, |
|
"learning_rate": 4.600000000000001e-05, |
|
"loss": 0.8596, |
|
"step": 920 |
|
}, |
|
{ |
|
"epoch": 4.01, |
|
"learning_rate": 4.6500000000000005e-05, |
|
"loss": 0.9623, |
|
"step": 930 |
|
}, |
|
{ |
|
"epoch": 4.01, |
|
"learning_rate": 4.7e-05, |
|
"loss": 1.1488, |
|
"step": 940 |
|
}, |
|
{ |
|
"epoch": 4.01, |
|
"learning_rate": 4.75e-05, |
|
"loss": 0.237, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 4.02, |
|
"learning_rate": 4.8e-05, |
|
"loss": 0.9762, |
|
"step": 960 |
|
}, |
|
{ |
|
"epoch": 4.02, |
|
"learning_rate": 4.85e-05, |
|
"loss": 0.7712, |
|
"step": 970 |
|
}, |
|
{ |
|
"epoch": 4.02, |
|
"learning_rate": 4.9e-05, |
|
"loss": 0.9408, |
|
"step": 980 |
|
}, |
|
{ |
|
"epoch": 4.02, |
|
"learning_rate": 4.9500000000000004e-05, |
|
"loss": 0.5351, |
|
"step": 990 |
|
}, |
|
{ |
|
"epoch": 4.02, |
|
"learning_rate": 5e-05, |
|
"loss": 0.3265, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 4.02, |
|
"eval_accuracy": 0.7708333333333334, |
|
"eval_loss": 0.6634658575057983, |
|
"eval_runtime": 11.7099, |
|
"eval_samples_per_second": 4.099, |
|
"eval_steps_per_second": 2.05, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"learning_rate": 4.994444444444445e-05, |
|
"loss": 1.064, |
|
"step": 1010 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"learning_rate": 4.9888888888888894e-05, |
|
"loss": 1.0349, |
|
"step": 1020 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"learning_rate": 4.9833333333333336e-05, |
|
"loss": 1.0541, |
|
"step": 1030 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"learning_rate": 4.977777777777778e-05, |
|
"loss": 0.7495, |
|
"step": 1040 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"learning_rate": 4.972222222222223e-05, |
|
"loss": 0.5859, |
|
"step": 1050 |
|
}, |
|
{ |
|
"epoch": 5.01, |
|
"learning_rate": 4.966666666666667e-05, |
|
"loss": 0.7543, |
|
"step": 1060 |
|
}, |
|
{ |
|
"epoch": 5.01, |
|
"learning_rate": 4.961111111111111e-05, |
|
"loss": 0.9994, |
|
"step": 1070 |
|
}, |
|
{ |
|
"epoch": 5.01, |
|
"learning_rate": 4.955555555555556e-05, |
|
"loss": 0.4021, |
|
"step": 1080 |
|
}, |
|
{ |
|
"epoch": 5.01, |
|
"learning_rate": 4.9500000000000004e-05, |
|
"loss": 0.6197, |
|
"step": 1090 |
|
}, |
|
{ |
|
"epoch": 5.01, |
|
"learning_rate": 4.9444444444444446e-05, |
|
"loss": 0.6279, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 5.01, |
|
"learning_rate": 4.938888888888889e-05, |
|
"loss": 0.598, |
|
"step": 1110 |
|
}, |
|
{ |
|
"epoch": 5.01, |
|
"learning_rate": 4.933333333333334e-05, |
|
"loss": 0.7877, |
|
"step": 1120 |
|
}, |
|
{ |
|
"epoch": 5.01, |
|
"learning_rate": 4.927777777777778e-05, |
|
"loss": 1.4482, |
|
"step": 1130 |
|
}, |
|
{ |
|
"epoch": 5.01, |
|
"learning_rate": 4.922222222222222e-05, |
|
"loss": 0.7729, |
|
"step": 1140 |
|
}, |
|
{ |
|
"epoch": 5.01, |
|
"learning_rate": 4.9166666666666665e-05, |
|
"loss": 0.6785, |
|
"step": 1150 |
|
}, |
|
{ |
|
"epoch": 5.02, |
|
"learning_rate": 4.9111111111111114e-05, |
|
"loss": 0.5642, |
|
"step": 1160 |
|
}, |
|
{ |
|
"epoch": 5.02, |
|
"learning_rate": 4.905555555555556e-05, |
|
"loss": 0.2877, |
|
"step": 1170 |
|
}, |
|
{ |
|
"epoch": 5.02, |
|
"learning_rate": 4.9e-05, |
|
"loss": 1.1808, |
|
"step": 1180 |
|
}, |
|
{ |
|
"epoch": 5.02, |
|
"learning_rate": 4.894444444444445e-05, |
|
"loss": 0.8441, |
|
"step": 1190 |
|
}, |
|
{ |
|
"epoch": 5.02, |
|
"learning_rate": 4.888888888888889e-05, |
|
"loss": 0.5417, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 5.02, |
|
"eval_accuracy": 0.8541666666666666, |
|
"eval_loss": 0.4705321490764618, |
|
"eval_runtime": 12.2541, |
|
"eval_samples_per_second": 3.917, |
|
"eval_steps_per_second": 1.959, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"learning_rate": 4.883333333333334e-05, |
|
"loss": 0.4682, |
|
"step": 1210 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"learning_rate": 4.8777777777777775e-05, |
|
"loss": 1.2522, |
|
"step": 1220 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"learning_rate": 4.8722222222222224e-05, |
|
"loss": 0.8509, |
|
"step": 1230 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"learning_rate": 4.866666666666667e-05, |
|
"loss": 0.4758, |
|
"step": 1240 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"learning_rate": 4.8611111111111115e-05, |
|
"loss": 0.9578, |
|
"step": 1250 |
|
}, |
|
{ |
|
"epoch": 6.01, |
|
"learning_rate": 4.855555555555556e-05, |
|
"loss": 0.6471, |
|
"step": 1260 |
|
}, |
|
{ |
|
"epoch": 6.01, |
|
"learning_rate": 4.85e-05, |
|
"loss": 0.2263, |
|
"step": 1270 |
|
}, |
|
{ |
|
"epoch": 6.01, |
|
"learning_rate": 4.844444444444445e-05, |
|
"loss": 0.8359, |
|
"step": 1280 |
|
}, |
|
{ |
|
"epoch": 6.01, |
|
"learning_rate": 4.838888888888889e-05, |
|
"loss": 0.3426, |
|
"step": 1290 |
|
}, |
|
{ |
|
"epoch": 6.01, |
|
"learning_rate": 4.8333333333333334e-05, |
|
"loss": 0.8537, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 6.01, |
|
"learning_rate": 4.8277777777777776e-05, |
|
"loss": 0.7768, |
|
"step": 1310 |
|
}, |
|
{ |
|
"epoch": 6.01, |
|
"learning_rate": 4.8222222222222225e-05, |
|
"loss": 0.8999, |
|
"step": 1320 |
|
}, |
|
{ |
|
"epoch": 6.01, |
|
"learning_rate": 4.8166666666666674e-05, |
|
"loss": 0.3208, |
|
"step": 1330 |
|
}, |
|
{ |
|
"epoch": 6.01, |
|
"learning_rate": 4.811111111111111e-05, |
|
"loss": 0.6026, |
|
"step": 1340 |
|
}, |
|
{ |
|
"epoch": 6.01, |
|
"learning_rate": 4.805555555555556e-05, |
|
"loss": 0.917, |
|
"step": 1350 |
|
}, |
|
{ |
|
"epoch": 6.02, |
|
"learning_rate": 4.8e-05, |
|
"loss": 0.662, |
|
"step": 1360 |
|
}, |
|
{ |
|
"epoch": 6.02, |
|
"learning_rate": 4.794444444444445e-05, |
|
"loss": 0.4472, |
|
"step": 1370 |
|
}, |
|
{ |
|
"epoch": 6.02, |
|
"learning_rate": 4.7888888888888886e-05, |
|
"loss": 0.9458, |
|
"step": 1380 |
|
}, |
|
{ |
|
"epoch": 6.02, |
|
"learning_rate": 4.7833333333333335e-05, |
|
"loss": 0.6513, |
|
"step": 1390 |
|
}, |
|
{ |
|
"epoch": 6.02, |
|
"learning_rate": 4.7777777777777784e-05, |
|
"loss": 0.5912, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 6.02, |
|
"eval_accuracy": 0.7708333333333334, |
|
"eval_loss": 1.0081998109817505, |
|
"eval_runtime": 11.7409, |
|
"eval_samples_per_second": 4.088, |
|
"eval_steps_per_second": 2.044, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"learning_rate": 4.7722222222222226e-05, |
|
"loss": 0.6759, |
|
"step": 1410 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"learning_rate": 4.766666666666667e-05, |
|
"loss": 0.4469, |
|
"step": 1420 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"learning_rate": 4.761111111111111e-05, |
|
"loss": 0.7664, |
|
"step": 1430 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"learning_rate": 4.755555555555556e-05, |
|
"loss": 0.7224, |
|
"step": 1440 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"learning_rate": 4.75e-05, |
|
"loss": 0.8619, |
|
"step": 1450 |
|
}, |
|
{ |
|
"epoch": 7.01, |
|
"learning_rate": 4.7444444444444445e-05, |
|
"loss": 0.5872, |
|
"step": 1460 |
|
}, |
|
{ |
|
"epoch": 7.01, |
|
"learning_rate": 4.7388888888888894e-05, |
|
"loss": 0.8781, |
|
"step": 1470 |
|
}, |
|
{ |
|
"epoch": 7.01, |
|
"learning_rate": 4.7333333333333336e-05, |
|
"loss": 0.4065, |
|
"step": 1480 |
|
}, |
|
{ |
|
"epoch": 7.01, |
|
"learning_rate": 4.727777777777778e-05, |
|
"loss": 0.7563, |
|
"step": 1490 |
|
}, |
|
{ |
|
"epoch": 7.01, |
|
"learning_rate": 4.722222222222222e-05, |
|
"loss": 0.5345, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 7.01, |
|
"learning_rate": 4.716666666666667e-05, |
|
"loss": 0.5917, |
|
"step": 1510 |
|
}, |
|
{ |
|
"epoch": 7.01, |
|
"learning_rate": 4.711111111111111e-05, |
|
"loss": 0.6414, |
|
"step": 1520 |
|
}, |
|
{ |
|
"epoch": 7.01, |
|
"learning_rate": 4.7055555555555555e-05, |
|
"loss": 0.8291, |
|
"step": 1530 |
|
}, |
|
{ |
|
"epoch": 7.01, |
|
"learning_rate": 4.7e-05, |
|
"loss": 0.7571, |
|
"step": 1540 |
|
}, |
|
{ |
|
"epoch": 7.01, |
|
"learning_rate": 4.6944444444444446e-05, |
|
"loss": 0.1543, |
|
"step": 1550 |
|
}, |
|
{ |
|
"epoch": 7.02, |
|
"learning_rate": 4.6888888888888895e-05, |
|
"loss": 1.3236, |
|
"step": 1560 |
|
}, |
|
{ |
|
"epoch": 7.02, |
|
"learning_rate": 4.683333333333334e-05, |
|
"loss": 0.8399, |
|
"step": 1570 |
|
}, |
|
{ |
|
"epoch": 7.02, |
|
"learning_rate": 4.677777777777778e-05, |
|
"loss": 0.9057, |
|
"step": 1580 |
|
}, |
|
{ |
|
"epoch": 7.02, |
|
"learning_rate": 4.672222222222222e-05, |
|
"loss": 0.6788, |
|
"step": 1590 |
|
}, |
|
{ |
|
"epoch": 7.02, |
|
"learning_rate": 4.666666666666667e-05, |
|
"loss": 0.5918, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 7.02, |
|
"eval_accuracy": 0.5625, |
|
"eval_loss": 2.629246711730957, |
|
"eval_runtime": 12.2894, |
|
"eval_samples_per_second": 3.906, |
|
"eval_steps_per_second": 1.953, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"learning_rate": 4.6611111111111114e-05, |
|
"loss": 2.0891, |
|
"step": 1610 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"learning_rate": 4.6555555555555556e-05, |
|
"loss": 0.5541, |
|
"step": 1620 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"learning_rate": 4.6500000000000005e-05, |
|
"loss": 0.2217, |
|
"step": 1630 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"learning_rate": 4.644444444444445e-05, |
|
"loss": 0.7825, |
|
"step": 1640 |
|
}, |
|
{ |
|
"epoch": 8.01, |
|
"learning_rate": 4.638888888888889e-05, |
|
"loss": 0.0591, |
|
"step": 1650 |
|
}, |
|
{ |
|
"epoch": 8.01, |
|
"learning_rate": 4.633333333333333e-05, |
|
"loss": 0.3167, |
|
"step": 1660 |
|
}, |
|
{ |
|
"epoch": 8.01, |
|
"learning_rate": 4.627777777777778e-05, |
|
"loss": 0.5536, |
|
"step": 1670 |
|
}, |
|
{ |
|
"epoch": 8.01, |
|
"learning_rate": 4.6222222222222224e-05, |
|
"loss": 0.7871, |
|
"step": 1680 |
|
}, |
|
{ |
|
"epoch": 8.01, |
|
"learning_rate": 4.6166666666666666e-05, |
|
"loss": 0.6523, |
|
"step": 1690 |
|
}, |
|
{ |
|
"epoch": 8.01, |
|
"learning_rate": 4.6111111111111115e-05, |
|
"loss": 0.3759, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 8.01, |
|
"learning_rate": 4.605555555555556e-05, |
|
"loss": 0.4117, |
|
"step": 1710 |
|
}, |
|
{ |
|
"epoch": 8.01, |
|
"learning_rate": 4.600000000000001e-05, |
|
"loss": 1.1512, |
|
"step": 1720 |
|
}, |
|
{ |
|
"epoch": 8.01, |
|
"learning_rate": 4.594444444444444e-05, |
|
"loss": 0.841, |
|
"step": 1730 |
|
}, |
|
{ |
|
"epoch": 8.01, |
|
"learning_rate": 4.588888888888889e-05, |
|
"loss": 0.5656, |
|
"step": 1740 |
|
}, |
|
{ |
|
"epoch": 8.02, |
|
"learning_rate": 4.5833333333333334e-05, |
|
"loss": 0.4376, |
|
"step": 1750 |
|
}, |
|
{ |
|
"epoch": 8.02, |
|
"learning_rate": 4.577777777777778e-05, |
|
"loss": 0.9157, |
|
"step": 1760 |
|
}, |
|
{ |
|
"epoch": 8.02, |
|
"learning_rate": 4.572222222222222e-05, |
|
"loss": 0.6012, |
|
"step": 1770 |
|
}, |
|
{ |
|
"epoch": 8.02, |
|
"learning_rate": 4.566666666666667e-05, |
|
"loss": 1.5018, |
|
"step": 1780 |
|
}, |
|
{ |
|
"epoch": 8.02, |
|
"learning_rate": 4.561111111111112e-05, |
|
"loss": 0.4772, |
|
"step": 1790 |
|
}, |
|
{ |
|
"epoch": 8.02, |
|
"learning_rate": 4.555555555555556e-05, |
|
"loss": 0.8992, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 8.02, |
|
"eval_accuracy": 0.7708333333333334, |
|
"eval_loss": 0.851398229598999, |
|
"eval_runtime": 11.9202, |
|
"eval_samples_per_second": 4.027, |
|
"eval_steps_per_second": 2.013, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 9.0, |
|
"learning_rate": 4.55e-05, |
|
"loss": 1.2507, |
|
"step": 1810 |
|
}, |
|
{ |
|
"epoch": 9.0, |
|
"learning_rate": 4.5444444444444444e-05, |
|
"loss": 0.5606, |
|
"step": 1820 |
|
}, |
|
{ |
|
"epoch": 9.0, |
|
"learning_rate": 4.538888888888889e-05, |
|
"loss": 0.2066, |
|
"step": 1830 |
|
}, |
|
{ |
|
"epoch": 9.0, |
|
"learning_rate": 4.5333333333333335e-05, |
|
"loss": 0.2448, |
|
"step": 1840 |
|
}, |
|
{ |
|
"epoch": 9.01, |
|
"learning_rate": 4.527777777777778e-05, |
|
"loss": 0.8724, |
|
"step": 1850 |
|
}, |
|
{ |
|
"epoch": 9.01, |
|
"learning_rate": 4.522222222222223e-05, |
|
"loss": 0.8256, |
|
"step": 1860 |
|
}, |
|
{ |
|
"epoch": 9.01, |
|
"learning_rate": 4.516666666666667e-05, |
|
"loss": 0.3326, |
|
"step": 1870 |
|
}, |
|
{ |
|
"epoch": 9.01, |
|
"learning_rate": 4.511111111111112e-05, |
|
"loss": 0.8212, |
|
"step": 1880 |
|
}, |
|
{ |
|
"epoch": 9.01, |
|
"learning_rate": 4.5055555555555554e-05, |
|
"loss": 0.2155, |
|
"step": 1890 |
|
}, |
|
{ |
|
"epoch": 9.01, |
|
"learning_rate": 4.5e-05, |
|
"loss": 0.3316, |
|
"step": 1900 |
|
}, |
|
{ |
|
"epoch": 9.01, |
|
"learning_rate": 4.4944444444444445e-05, |
|
"loss": 0.6521, |
|
"step": 1910 |
|
}, |
|
{ |
|
"epoch": 9.01, |
|
"learning_rate": 4.4888888888888894e-05, |
|
"loss": 0.5286, |
|
"step": 1920 |
|
}, |
|
{ |
|
"epoch": 9.01, |
|
"learning_rate": 4.483333333333333e-05, |
|
"loss": 0.9271, |
|
"step": 1930 |
|
}, |
|
{ |
|
"epoch": 9.01, |
|
"learning_rate": 4.477777777777778e-05, |
|
"loss": 0.0367, |
|
"step": 1940 |
|
}, |
|
{ |
|
"epoch": 9.02, |
|
"learning_rate": 4.472222222222223e-05, |
|
"loss": 2.0037, |
|
"step": 1950 |
|
}, |
|
{ |
|
"epoch": 9.02, |
|
"learning_rate": 4.466666666666667e-05, |
|
"loss": 0.6484, |
|
"step": 1960 |
|
}, |
|
{ |
|
"epoch": 9.02, |
|
"learning_rate": 4.461111111111111e-05, |
|
"loss": 0.251, |
|
"step": 1970 |
|
}, |
|
{ |
|
"epoch": 9.02, |
|
"learning_rate": 4.4555555555555555e-05, |
|
"loss": 0.4765, |
|
"step": 1980 |
|
}, |
|
{ |
|
"epoch": 9.02, |
|
"learning_rate": 4.4500000000000004e-05, |
|
"loss": 0.7967, |
|
"step": 1990 |
|
}, |
|
{ |
|
"epoch": 9.02, |
|
"learning_rate": 4.4444444444444447e-05, |
|
"loss": 0.172, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 9.02, |
|
"eval_accuracy": 0.875, |
|
"eval_loss": 0.45680248737335205, |
|
"eval_runtime": 12.5869, |
|
"eval_samples_per_second": 3.813, |
|
"eval_steps_per_second": 1.907, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"learning_rate": 4.438888888888889e-05, |
|
"loss": 0.7177, |
|
"step": 2010 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"learning_rate": 4.433333333333334e-05, |
|
"loss": 0.8508, |
|
"step": 2020 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"learning_rate": 4.427777777777778e-05, |
|
"loss": 0.8407, |
|
"step": 2030 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"learning_rate": 4.422222222222222e-05, |
|
"loss": 0.5341, |
|
"step": 2040 |
|
}, |
|
{ |
|
"epoch": 10.01, |
|
"learning_rate": 4.4166666666666665e-05, |
|
"loss": 0.3149, |
|
"step": 2050 |
|
}, |
|
{ |
|
"epoch": 10.01, |
|
"learning_rate": 4.4111111111111114e-05, |
|
"loss": 0.2314, |
|
"step": 2060 |
|
}, |
|
{ |
|
"epoch": 10.01, |
|
"learning_rate": 4.4055555555555557e-05, |
|
"loss": 0.952, |
|
"step": 2070 |
|
}, |
|
{ |
|
"epoch": 10.01, |
|
"learning_rate": 4.4000000000000006e-05, |
|
"loss": 0.428, |
|
"step": 2080 |
|
}, |
|
{ |
|
"epoch": 10.01, |
|
"learning_rate": 4.394444444444445e-05, |
|
"loss": 0.304, |
|
"step": 2090 |
|
}, |
|
{ |
|
"epoch": 10.01, |
|
"learning_rate": 4.388888888888889e-05, |
|
"loss": 0.4067, |
|
"step": 2100 |
|
}, |
|
{ |
|
"epoch": 10.01, |
|
"learning_rate": 4.383333333333334e-05, |
|
"loss": 0.2923, |
|
"step": 2110 |
|
}, |
|
{ |
|
"epoch": 10.01, |
|
"learning_rate": 4.377777777777778e-05, |
|
"loss": 0.2763, |
|
"step": 2120 |
|
}, |
|
{ |
|
"epoch": 10.01, |
|
"learning_rate": 4.3722222222222224e-05, |
|
"loss": 1.4951, |
|
"step": 2130 |
|
}, |
|
{ |
|
"epoch": 10.01, |
|
"learning_rate": 4.3666666666666666e-05, |
|
"loss": 0.7374, |
|
"step": 2140 |
|
}, |
|
{ |
|
"epoch": 10.02, |
|
"learning_rate": 4.3611111111111116e-05, |
|
"loss": 0.8782, |
|
"step": 2150 |
|
}, |
|
{ |
|
"epoch": 10.02, |
|
"learning_rate": 4.355555555555556e-05, |
|
"loss": 0.5374, |
|
"step": 2160 |
|
}, |
|
{ |
|
"epoch": 10.02, |
|
"learning_rate": 4.35e-05, |
|
"loss": 0.6164, |
|
"step": 2170 |
|
}, |
|
{ |
|
"epoch": 10.02, |
|
"learning_rate": 4.344444444444445e-05, |
|
"loss": 0.5851, |
|
"step": 2180 |
|
}, |
|
{ |
|
"epoch": 10.02, |
|
"learning_rate": 4.338888888888889e-05, |
|
"loss": 0.5256, |
|
"step": 2190 |
|
}, |
|
{ |
|
"epoch": 10.02, |
|
"learning_rate": 4.3333333333333334e-05, |
|
"loss": 0.493, |
|
"step": 2200 |
|
}, |
|
{ |
|
"epoch": 10.02, |
|
"eval_accuracy": 0.7916666666666666, |
|
"eval_loss": 0.735382080078125, |
|
"eval_runtime": 12.068, |
|
"eval_samples_per_second": 3.977, |
|
"eval_steps_per_second": 1.989, |
|
"step": 2200 |
|
}, |
|
{ |
|
"epoch": 11.0, |
|
"learning_rate": 4.3277777777777776e-05, |
|
"loss": 0.6347, |
|
"step": 2210 |
|
}, |
|
{ |
|
"epoch": 11.0, |
|
"learning_rate": 4.3222222222222226e-05, |
|
"loss": 1.0816, |
|
"step": 2220 |
|
}, |
|
{ |
|
"epoch": 11.0, |
|
"learning_rate": 4.316666666666667e-05, |
|
"loss": 0.3297, |
|
"step": 2230 |
|
}, |
|
{ |
|
"epoch": 11.0, |
|
"learning_rate": 4.311111111111111e-05, |
|
"loss": 0.438, |
|
"step": 2240 |
|
}, |
|
{ |
|
"epoch": 11.01, |
|
"learning_rate": 4.305555555555556e-05, |
|
"loss": 0.978, |
|
"step": 2250 |
|
}, |
|
{ |
|
"epoch": 11.01, |
|
"learning_rate": 4.3e-05, |
|
"loss": 0.8443, |
|
"step": 2260 |
|
}, |
|
{ |
|
"epoch": 11.01, |
|
"learning_rate": 4.294444444444445e-05, |
|
"loss": 0.1932, |
|
"step": 2270 |
|
}, |
|
{ |
|
"epoch": 11.01, |
|
"learning_rate": 4.2888888888888886e-05, |
|
"loss": 0.1223, |
|
"step": 2280 |
|
}, |
|
{ |
|
"epoch": 11.01, |
|
"learning_rate": 4.2833333333333335e-05, |
|
"loss": 0.6449, |
|
"step": 2290 |
|
}, |
|
{ |
|
"epoch": 11.01, |
|
"learning_rate": 4.277777777777778e-05, |
|
"loss": 0.6536, |
|
"step": 2300 |
|
}, |
|
{ |
|
"epoch": 11.01, |
|
"learning_rate": 4.272222222222223e-05, |
|
"loss": 1.0084, |
|
"step": 2310 |
|
}, |
|
{ |
|
"epoch": 11.01, |
|
"learning_rate": 4.266666666666667e-05, |
|
"loss": 0.5281, |
|
"step": 2320 |
|
}, |
|
{ |
|
"epoch": 11.01, |
|
"learning_rate": 4.261111111111111e-05, |
|
"loss": 0.4767, |
|
"step": 2330 |
|
}, |
|
{ |
|
"epoch": 11.01, |
|
"learning_rate": 4.255555555555556e-05, |
|
"loss": 0.3046, |
|
"step": 2340 |
|
}, |
|
{ |
|
"epoch": 11.02, |
|
"learning_rate": 4.25e-05, |
|
"loss": 0.5255, |
|
"step": 2350 |
|
}, |
|
{ |
|
"epoch": 11.02, |
|
"learning_rate": 4.2444444444444445e-05, |
|
"loss": 0.4564, |
|
"step": 2360 |
|
}, |
|
{ |
|
"epoch": 11.02, |
|
"learning_rate": 4.238888888888889e-05, |
|
"loss": 0.7596, |
|
"step": 2370 |
|
}, |
|
{ |
|
"epoch": 11.02, |
|
"learning_rate": 4.233333333333334e-05, |
|
"loss": 0.8184, |
|
"step": 2380 |
|
}, |
|
{ |
|
"epoch": 11.02, |
|
"learning_rate": 4.227777777777778e-05, |
|
"loss": 0.3929, |
|
"step": 2390 |
|
}, |
|
{ |
|
"epoch": 11.02, |
|
"learning_rate": 4.222222222222222e-05, |
|
"loss": 0.3622, |
|
"step": 2400 |
|
}, |
|
{ |
|
"epoch": 11.02, |
|
"eval_accuracy": 0.7708333333333334, |
|
"eval_loss": 1.038616418838501, |
|
"eval_runtime": 12.2973, |
|
"eval_samples_per_second": 3.903, |
|
"eval_steps_per_second": 1.952, |
|
"step": 2400 |
|
}, |
|
{ |
|
"epoch": 12.0, |
|
"learning_rate": 4.216666666666667e-05, |
|
"loss": 0.3532, |
|
"step": 2410 |
|
}, |
|
{ |
|
"epoch": 12.0, |
|
"learning_rate": 4.211111111111111e-05, |
|
"loss": 1.1891, |
|
"step": 2420 |
|
}, |
|
{ |
|
"epoch": 12.0, |
|
"learning_rate": 4.205555555555556e-05, |
|
"loss": 1.2511, |
|
"step": 2430 |
|
}, |
|
{ |
|
"epoch": 12.0, |
|
"learning_rate": 4.2e-05, |
|
"loss": 0.5967, |
|
"step": 2440 |
|
}, |
|
{ |
|
"epoch": 12.01, |
|
"learning_rate": 4.194444444444445e-05, |
|
"loss": 0.213, |
|
"step": 2450 |
|
}, |
|
{ |
|
"epoch": 12.01, |
|
"learning_rate": 4.188888888888889e-05, |
|
"loss": 0.4385, |
|
"step": 2460 |
|
}, |
|
{ |
|
"epoch": 12.01, |
|
"learning_rate": 4.183333333333334e-05, |
|
"loss": 0.3407, |
|
"step": 2470 |
|
}, |
|
{ |
|
"epoch": 12.01, |
|
"learning_rate": 4.177777777777778e-05, |
|
"loss": 0.6524, |
|
"step": 2480 |
|
}, |
|
{ |
|
"epoch": 12.01, |
|
"learning_rate": 4.172222222222222e-05, |
|
"loss": 0.4037, |
|
"step": 2490 |
|
}, |
|
{ |
|
"epoch": 12.01, |
|
"learning_rate": 4.166666666666667e-05, |
|
"loss": 0.5343, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 12.01, |
|
"learning_rate": 4.1611111111111114e-05, |
|
"loss": 0.8634, |
|
"step": 2510 |
|
}, |
|
{ |
|
"epoch": 12.01, |
|
"learning_rate": 4.155555555555556e-05, |
|
"loss": 0.2486, |
|
"step": 2520 |
|
}, |
|
{ |
|
"epoch": 12.01, |
|
"learning_rate": 4.15e-05, |
|
"loss": 0.0436, |
|
"step": 2530 |
|
}, |
|
{ |
|
"epoch": 12.01, |
|
"learning_rate": 4.144444444444445e-05, |
|
"loss": 0.6587, |
|
"step": 2540 |
|
}, |
|
{ |
|
"epoch": 12.02, |
|
"learning_rate": 4.138888888888889e-05, |
|
"loss": 1.0205, |
|
"step": 2550 |
|
}, |
|
{ |
|
"epoch": 12.02, |
|
"learning_rate": 4.133333333333333e-05, |
|
"loss": 0.0764, |
|
"step": 2560 |
|
}, |
|
{ |
|
"epoch": 12.02, |
|
"learning_rate": 4.127777777777778e-05, |
|
"loss": 0.5688, |
|
"step": 2570 |
|
}, |
|
{ |
|
"epoch": 12.02, |
|
"learning_rate": 4.1222222222222224e-05, |
|
"loss": 0.478, |
|
"step": 2580 |
|
}, |
|
{ |
|
"epoch": 12.02, |
|
"learning_rate": 4.116666666666667e-05, |
|
"loss": 0.3865, |
|
"step": 2590 |
|
}, |
|
{ |
|
"epoch": 12.02, |
|
"learning_rate": 4.111111111111111e-05, |
|
"loss": 0.4966, |
|
"step": 2600 |
|
}, |
|
{ |
|
"epoch": 12.02, |
|
"eval_accuracy": 0.7916666666666666, |
|
"eval_loss": 0.8979193568229675, |
|
"eval_runtime": 12.2264, |
|
"eval_samples_per_second": 3.926, |
|
"eval_steps_per_second": 1.963, |
|
"step": 2600 |
|
}, |
|
{ |
|
"epoch": 13.0, |
|
"learning_rate": 4.105555555555556e-05, |
|
"loss": 0.485, |
|
"step": 2610 |
|
}, |
|
{ |
|
"epoch": 13.0, |
|
"learning_rate": 4.1e-05, |
|
"loss": 0.2967, |
|
"step": 2620 |
|
}, |
|
{ |
|
"epoch": 13.0, |
|
"learning_rate": 4.094444444444445e-05, |
|
"loss": 0.8117, |
|
"step": 2630 |
|
}, |
|
{ |
|
"epoch": 13.0, |
|
"learning_rate": 4.088888888888889e-05, |
|
"loss": 0.3335, |
|
"step": 2640 |
|
}, |
|
{ |
|
"epoch": 13.01, |
|
"learning_rate": 4.0833333333333334e-05, |
|
"loss": 0.524, |
|
"step": 2650 |
|
}, |
|
{ |
|
"epoch": 13.01, |
|
"learning_rate": 4.0777777777777783e-05, |
|
"loss": 0.3098, |
|
"step": 2660 |
|
}, |
|
{ |
|
"epoch": 13.01, |
|
"learning_rate": 4.0722222222222226e-05, |
|
"loss": 0.5006, |
|
"step": 2670 |
|
}, |
|
{ |
|
"epoch": 13.01, |
|
"learning_rate": 4.066666666666667e-05, |
|
"loss": 0.5384, |
|
"step": 2680 |
|
}, |
|
{ |
|
"epoch": 13.01, |
|
"learning_rate": 4.061111111111111e-05, |
|
"loss": 0.2278, |
|
"step": 2690 |
|
}, |
|
{ |
|
"epoch": 13.01, |
|
"learning_rate": 4.055555555555556e-05, |
|
"loss": 0.3817, |
|
"step": 2700 |
|
}, |
|
{ |
|
"epoch": 13.01, |
|
"learning_rate": 4.05e-05, |
|
"loss": 0.5161, |
|
"step": 2710 |
|
}, |
|
{ |
|
"epoch": 13.01, |
|
"learning_rate": 4.0444444444444444e-05, |
|
"loss": 0.9926, |
|
"step": 2720 |
|
}, |
|
{ |
|
"epoch": 13.01, |
|
"learning_rate": 4.038888888888889e-05, |
|
"loss": 0.2719, |
|
"step": 2730 |
|
}, |
|
{ |
|
"epoch": 13.01, |
|
"learning_rate": 4.0333333333333336e-05, |
|
"loss": 1.0233, |
|
"step": 2740 |
|
}, |
|
{ |
|
"epoch": 13.02, |
|
"learning_rate": 4.027777777777778e-05, |
|
"loss": 0.7767, |
|
"step": 2750 |
|
}, |
|
{ |
|
"epoch": 13.02, |
|
"learning_rate": 4.022222222222222e-05, |
|
"loss": 0.5676, |
|
"step": 2760 |
|
}, |
|
{ |
|
"epoch": 13.02, |
|
"learning_rate": 4.016666666666667e-05, |
|
"loss": 0.5567, |
|
"step": 2770 |
|
}, |
|
{ |
|
"epoch": 13.02, |
|
"learning_rate": 4.011111111111111e-05, |
|
"loss": 0.5635, |
|
"step": 2780 |
|
}, |
|
{ |
|
"epoch": 13.02, |
|
"learning_rate": 4.0055555555555554e-05, |
|
"loss": 0.6506, |
|
"step": 2790 |
|
}, |
|
{ |
|
"epoch": 13.02, |
|
"learning_rate": 4e-05, |
|
"loss": 0.3541, |
|
"step": 2800 |
|
}, |
|
{ |
|
"epoch": 13.02, |
|
"eval_accuracy": 0.7708333333333334, |
|
"eval_loss": 0.8220213055610657, |
|
"eval_runtime": 12.3358, |
|
"eval_samples_per_second": 3.891, |
|
"eval_steps_per_second": 1.946, |
|
"step": 2800 |
|
}, |
|
{ |
|
"epoch": 14.0, |
|
"learning_rate": 3.9944444444444446e-05, |
|
"loss": 1.2772, |
|
"step": 2810 |
|
}, |
|
{ |
|
"epoch": 14.0, |
|
"learning_rate": 3.9888888888888895e-05, |
|
"loss": 0.1496, |
|
"step": 2820 |
|
}, |
|
{ |
|
"epoch": 14.0, |
|
"learning_rate": 3.983333333333333e-05, |
|
"loss": 0.4015, |
|
"step": 2830 |
|
}, |
|
{ |
|
"epoch": 14.0, |
|
"learning_rate": 3.977777777777778e-05, |
|
"loss": 0.2116, |
|
"step": 2840 |
|
}, |
|
{ |
|
"epoch": 14.01, |
|
"learning_rate": 3.972222222222222e-05, |
|
"loss": 0.3245, |
|
"step": 2850 |
|
}, |
|
{ |
|
"epoch": 14.01, |
|
"learning_rate": 3.966666666666667e-05, |
|
"loss": 0.2073, |
|
"step": 2860 |
|
}, |
|
{ |
|
"epoch": 14.01, |
|
"learning_rate": 3.961111111111111e-05, |
|
"loss": 0.311, |
|
"step": 2870 |
|
}, |
|
{ |
|
"epoch": 14.01, |
|
"learning_rate": 3.9555555555555556e-05, |
|
"loss": 0.7659, |
|
"step": 2880 |
|
}, |
|
{ |
|
"epoch": 14.01, |
|
"learning_rate": 3.9500000000000005e-05, |
|
"loss": 0.3232, |
|
"step": 2890 |
|
}, |
|
{ |
|
"epoch": 14.01, |
|
"learning_rate": 3.944444444444445e-05, |
|
"loss": 0.3152, |
|
"step": 2900 |
|
}, |
|
{ |
|
"epoch": 14.01, |
|
"learning_rate": 3.938888888888889e-05, |
|
"loss": 0.8308, |
|
"step": 2910 |
|
}, |
|
{ |
|
"epoch": 14.01, |
|
"learning_rate": 3.933333333333333e-05, |
|
"loss": 0.0689, |
|
"step": 2920 |
|
}, |
|
{ |
|
"epoch": 14.01, |
|
"learning_rate": 3.927777777777778e-05, |
|
"loss": 0.361, |
|
"step": 2930 |
|
}, |
|
{ |
|
"epoch": 14.01, |
|
"learning_rate": 3.922222222222223e-05, |
|
"loss": 0.686, |
|
"step": 2940 |
|
}, |
|
{ |
|
"epoch": 14.02, |
|
"learning_rate": 3.9166666666666665e-05, |
|
"loss": 0.4834, |
|
"step": 2950 |
|
}, |
|
{ |
|
"epoch": 14.02, |
|
"learning_rate": 3.9111111111111115e-05, |
|
"loss": 0.382, |
|
"step": 2960 |
|
}, |
|
{ |
|
"epoch": 14.02, |
|
"learning_rate": 3.905555555555556e-05, |
|
"loss": 0.7582, |
|
"step": 2970 |
|
}, |
|
{ |
|
"epoch": 14.02, |
|
"learning_rate": 3.9000000000000006e-05, |
|
"loss": 0.3903, |
|
"step": 2980 |
|
}, |
|
{ |
|
"epoch": 14.02, |
|
"learning_rate": 3.894444444444444e-05, |
|
"loss": 0.2723, |
|
"step": 2990 |
|
}, |
|
{ |
|
"epoch": 14.02, |
|
"learning_rate": 3.888888888888889e-05, |
|
"loss": 0.5386, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 14.02, |
|
"eval_accuracy": 0.7708333333333334, |
|
"eval_loss": 1.0255749225616455, |
|
"eval_runtime": 11.7863, |
|
"eval_samples_per_second": 4.073, |
|
"eval_steps_per_second": 2.036, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 15.0, |
|
"learning_rate": 3.883333333333333e-05, |
|
"loss": 0.1094, |
|
"step": 3010 |
|
}, |
|
{ |
|
"epoch": 15.0, |
|
"learning_rate": 3.877777777777778e-05, |
|
"loss": 0.7977, |
|
"step": 3020 |
|
}, |
|
{ |
|
"epoch": 15.0, |
|
"learning_rate": 3.8722222222222225e-05, |
|
"loss": 0.5661, |
|
"step": 3030 |
|
}, |
|
{ |
|
"epoch": 15.0, |
|
"learning_rate": 3.866666666666667e-05, |
|
"loss": 0.4519, |
|
"step": 3040 |
|
}, |
|
{ |
|
"epoch": 15.01, |
|
"learning_rate": 3.8611111111111116e-05, |
|
"loss": 0.0226, |
|
"step": 3050 |
|
}, |
|
{ |
|
"epoch": 15.01, |
|
"learning_rate": 3.855555555555556e-05, |
|
"loss": 0.8201, |
|
"step": 3060 |
|
}, |
|
{ |
|
"epoch": 15.01, |
|
"learning_rate": 3.85e-05, |
|
"loss": 1.1224, |
|
"step": 3070 |
|
}, |
|
{ |
|
"epoch": 15.01, |
|
"learning_rate": 3.844444444444444e-05, |
|
"loss": 0.4948, |
|
"step": 3080 |
|
}, |
|
{ |
|
"epoch": 15.01, |
|
"learning_rate": 3.838888888888889e-05, |
|
"loss": 0.7494, |
|
"step": 3090 |
|
}, |
|
{ |
|
"epoch": 15.01, |
|
"learning_rate": 3.8333333333333334e-05, |
|
"loss": 0.2823, |
|
"step": 3100 |
|
}, |
|
{ |
|
"epoch": 15.01, |
|
"learning_rate": 3.827777777777778e-05, |
|
"loss": 0.003, |
|
"step": 3110 |
|
}, |
|
{ |
|
"epoch": 15.01, |
|
"learning_rate": 3.8222222222222226e-05, |
|
"loss": 0.2106, |
|
"step": 3120 |
|
}, |
|
{ |
|
"epoch": 15.01, |
|
"learning_rate": 3.816666666666667e-05, |
|
"loss": 0.7284, |
|
"step": 3130 |
|
}, |
|
{ |
|
"epoch": 15.01, |
|
"learning_rate": 3.811111111111112e-05, |
|
"loss": 0.475, |
|
"step": 3140 |
|
}, |
|
{ |
|
"epoch": 15.02, |
|
"learning_rate": 3.805555555555555e-05, |
|
"loss": 0.6231, |
|
"step": 3150 |
|
}, |
|
{ |
|
"epoch": 15.02, |
|
"learning_rate": 3.8e-05, |
|
"loss": 0.2487, |
|
"step": 3160 |
|
}, |
|
{ |
|
"epoch": 15.02, |
|
"learning_rate": 3.7944444444444444e-05, |
|
"loss": 0.8212, |
|
"step": 3170 |
|
}, |
|
{ |
|
"epoch": 15.02, |
|
"learning_rate": 3.7888888888888894e-05, |
|
"loss": 0.6314, |
|
"step": 3180 |
|
}, |
|
{ |
|
"epoch": 15.02, |
|
"learning_rate": 3.7833333333333336e-05, |
|
"loss": 0.8588, |
|
"step": 3190 |
|
}, |
|
{ |
|
"epoch": 15.02, |
|
"learning_rate": 3.777777777777778e-05, |
|
"loss": 0.4615, |
|
"step": 3200 |
|
}, |
|
{ |
|
"epoch": 15.02, |
|
"eval_accuracy": 0.7916666666666666, |
|
"eval_loss": 1.0447040796279907, |
|
"eval_runtime": 11.8354, |
|
"eval_samples_per_second": 4.056, |
|
"eval_steps_per_second": 2.028, |
|
"step": 3200 |
|
}, |
|
{ |
|
"epoch": 16.0, |
|
"learning_rate": 3.772222222222223e-05, |
|
"loss": 0.2494, |
|
"step": 3210 |
|
}, |
|
{ |
|
"epoch": 16.0, |
|
"learning_rate": 3.766666666666667e-05, |
|
"loss": 0.4866, |
|
"step": 3220 |
|
}, |
|
{ |
|
"epoch": 16.0, |
|
"learning_rate": 3.761111111111111e-05, |
|
"loss": 0.6039, |
|
"step": 3230 |
|
}, |
|
{ |
|
"epoch": 16.0, |
|
"learning_rate": 3.7555555555555554e-05, |
|
"loss": 0.8248, |
|
"step": 3240 |
|
}, |
|
{ |
|
"epoch": 16.0, |
|
"learning_rate": 3.7500000000000003e-05, |
|
"loss": 0.5987, |
|
"step": 3250 |
|
}, |
|
{ |
|
"epoch": 16.01, |
|
"learning_rate": 3.7444444444444446e-05, |
|
"loss": 0.3115, |
|
"step": 3260 |
|
}, |
|
{ |
|
"epoch": 16.01, |
|
"learning_rate": 3.738888888888889e-05, |
|
"loss": 0.7818, |
|
"step": 3270 |
|
}, |
|
{ |
|
"epoch": 16.01, |
|
"learning_rate": 3.733333333333334e-05, |
|
"loss": 0.3428, |
|
"step": 3280 |
|
}, |
|
{ |
|
"epoch": 16.01, |
|
"learning_rate": 3.727777777777778e-05, |
|
"loss": 0.291, |
|
"step": 3290 |
|
}, |
|
{ |
|
"epoch": 16.01, |
|
"learning_rate": 3.722222222222222e-05, |
|
"loss": 0.3707, |
|
"step": 3300 |
|
}, |
|
{ |
|
"epoch": 16.01, |
|
"learning_rate": 3.7166666666666664e-05, |
|
"loss": 0.2312, |
|
"step": 3310 |
|
}, |
|
{ |
|
"epoch": 16.01, |
|
"learning_rate": 3.7111111111111113e-05, |
|
"loss": 1.1075, |
|
"step": 3320 |
|
}, |
|
{ |
|
"epoch": 16.01, |
|
"learning_rate": 3.705555555555556e-05, |
|
"loss": 0.6069, |
|
"step": 3330 |
|
}, |
|
{ |
|
"epoch": 16.01, |
|
"learning_rate": 3.7e-05, |
|
"loss": 0.8865, |
|
"step": 3340 |
|
}, |
|
{ |
|
"epoch": 16.02, |
|
"learning_rate": 3.694444444444445e-05, |
|
"loss": 0.9964, |
|
"step": 3350 |
|
}, |
|
{ |
|
"epoch": 16.02, |
|
"learning_rate": 3.688888888888889e-05, |
|
"loss": 0.1496, |
|
"step": 3360 |
|
}, |
|
{ |
|
"epoch": 16.02, |
|
"learning_rate": 3.683333333333334e-05, |
|
"loss": 0.458, |
|
"step": 3370 |
|
}, |
|
{ |
|
"epoch": 16.02, |
|
"learning_rate": 3.677777777777778e-05, |
|
"loss": 0.103, |
|
"step": 3380 |
|
}, |
|
{ |
|
"epoch": 16.02, |
|
"learning_rate": 3.672222222222222e-05, |
|
"loss": 0.1444, |
|
"step": 3390 |
|
}, |
|
{ |
|
"epoch": 16.02, |
|
"learning_rate": 3.6666666666666666e-05, |
|
"loss": 0.1624, |
|
"step": 3400 |
|
}, |
|
{ |
|
"epoch": 16.02, |
|
"eval_accuracy": 0.8541666666666666, |
|
"eval_loss": 0.6448492407798767, |
|
"eval_runtime": 11.8539, |
|
"eval_samples_per_second": 4.049, |
|
"eval_steps_per_second": 2.025, |
|
"step": 3400 |
|
}, |
|
{ |
|
"epoch": 17.0, |
|
"learning_rate": 3.6611111111111115e-05, |
|
"loss": 0.3557, |
|
"step": 3410 |
|
}, |
|
{ |
|
"epoch": 17.0, |
|
"learning_rate": 3.655555555555556e-05, |
|
"loss": 0.2707, |
|
"step": 3420 |
|
}, |
|
{ |
|
"epoch": 17.0, |
|
"learning_rate": 3.65e-05, |
|
"loss": 0.6198, |
|
"step": 3430 |
|
}, |
|
{ |
|
"epoch": 17.0, |
|
"learning_rate": 3.644444444444445e-05, |
|
"loss": 0.4712, |
|
"step": 3440 |
|
}, |
|
{ |
|
"epoch": 17.0, |
|
"learning_rate": 3.638888888888889e-05, |
|
"loss": 0.4232, |
|
"step": 3450 |
|
}, |
|
{ |
|
"epoch": 17.01, |
|
"learning_rate": 3.633333333333333e-05, |
|
"loss": 0.0412, |
|
"step": 3460 |
|
}, |
|
{ |
|
"epoch": 17.01, |
|
"learning_rate": 3.6277777777777776e-05, |
|
"loss": 0.2926, |
|
"step": 3470 |
|
}, |
|
{ |
|
"epoch": 17.01, |
|
"learning_rate": 3.6222222222222225e-05, |
|
"loss": 0.4301, |
|
"step": 3480 |
|
}, |
|
{ |
|
"epoch": 17.01, |
|
"learning_rate": 3.6166666666666674e-05, |
|
"loss": 0.5938, |
|
"step": 3490 |
|
}, |
|
{ |
|
"epoch": 17.01, |
|
"learning_rate": 3.611111111111111e-05, |
|
"loss": 0.2795, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 17.01, |
|
"learning_rate": 3.605555555555556e-05, |
|
"loss": 0.7038, |
|
"step": 3510 |
|
}, |
|
{ |
|
"epoch": 17.01, |
|
"learning_rate": 3.6e-05, |
|
"loss": 0.6683, |
|
"step": 3520 |
|
}, |
|
{ |
|
"epoch": 17.01, |
|
"learning_rate": 3.594444444444445e-05, |
|
"loss": 0.9081, |
|
"step": 3530 |
|
}, |
|
{ |
|
"epoch": 17.01, |
|
"learning_rate": 3.5888888888888886e-05, |
|
"loss": 0.7373, |
|
"step": 3540 |
|
}, |
|
{ |
|
"epoch": 17.02, |
|
"learning_rate": 3.5833333333333335e-05, |
|
"loss": 0.0338, |
|
"step": 3550 |
|
}, |
|
{ |
|
"epoch": 17.02, |
|
"learning_rate": 3.577777777777778e-05, |
|
"loss": 0.7519, |
|
"step": 3560 |
|
}, |
|
{ |
|
"epoch": 17.02, |
|
"learning_rate": 3.5722222222222226e-05, |
|
"loss": 1.1557, |
|
"step": 3570 |
|
}, |
|
{ |
|
"epoch": 17.02, |
|
"learning_rate": 3.566666666666667e-05, |
|
"loss": 0.2387, |
|
"step": 3580 |
|
}, |
|
{ |
|
"epoch": 17.02, |
|
"learning_rate": 3.561111111111111e-05, |
|
"loss": 0.7307, |
|
"step": 3590 |
|
}, |
|
{ |
|
"epoch": 17.02, |
|
"learning_rate": 3.555555555555556e-05, |
|
"loss": 1.0388, |
|
"step": 3600 |
|
}, |
|
{ |
|
"epoch": 17.02, |
|
"eval_accuracy": 0.7708333333333334, |
|
"eval_loss": 0.9992363452911377, |
|
"eval_runtime": 12.4199, |
|
"eval_samples_per_second": 3.865, |
|
"eval_steps_per_second": 1.932, |
|
"step": 3600 |
|
}, |
|
{ |
|
"epoch": 18.0, |
|
"learning_rate": 3.55e-05, |
|
"loss": 0.1617, |
|
"step": 3610 |
|
}, |
|
{ |
|
"epoch": 18.0, |
|
"learning_rate": 3.5444444444444445e-05, |
|
"loss": 0.008, |
|
"step": 3620 |
|
}, |
|
{ |
|
"epoch": 18.0, |
|
"learning_rate": 3.538888888888889e-05, |
|
"loss": 0.6766, |
|
"step": 3630 |
|
}, |
|
{ |
|
"epoch": 18.0, |
|
"learning_rate": 3.5333333333333336e-05, |
|
"loss": 0.6959, |
|
"step": 3640 |
|
}, |
|
{ |
|
"epoch": 18.0, |
|
"learning_rate": 3.527777777777778e-05, |
|
"loss": 0.4455, |
|
"step": 3650 |
|
}, |
|
{ |
|
"epoch": 18.01, |
|
"learning_rate": 3.522222222222222e-05, |
|
"loss": 0.0627, |
|
"step": 3660 |
|
}, |
|
{ |
|
"epoch": 18.01, |
|
"learning_rate": 3.516666666666667e-05, |
|
"loss": 0.4591, |
|
"step": 3670 |
|
}, |
|
{ |
|
"epoch": 18.01, |
|
"learning_rate": 3.511111111111111e-05, |
|
"loss": 0.3082, |
|
"step": 3680 |
|
}, |
|
{ |
|
"epoch": 18.01, |
|
"learning_rate": 3.505555555555556e-05, |
|
"loss": 0.2478, |
|
"step": 3690 |
|
}, |
|
{ |
|
"epoch": 18.01, |
|
"learning_rate": 3.5e-05, |
|
"loss": 0.5041, |
|
"step": 3700 |
|
}, |
|
{ |
|
"epoch": 18.01, |
|
"learning_rate": 3.4944444444444446e-05, |
|
"loss": 0.2401, |
|
"step": 3710 |
|
}, |
|
{ |
|
"epoch": 18.01, |
|
"learning_rate": 3.4888888888888895e-05, |
|
"loss": 0.2564, |
|
"step": 3720 |
|
}, |
|
{ |
|
"epoch": 18.01, |
|
"learning_rate": 3.483333333333334e-05, |
|
"loss": 0.4303, |
|
"step": 3730 |
|
}, |
|
{ |
|
"epoch": 18.01, |
|
"learning_rate": 3.477777777777778e-05, |
|
"loss": 0.2812, |
|
"step": 3740 |
|
}, |
|
{ |
|
"epoch": 18.02, |
|
"learning_rate": 3.472222222222222e-05, |
|
"loss": 0.4144, |
|
"step": 3750 |
|
}, |
|
{ |
|
"epoch": 18.02, |
|
"learning_rate": 3.466666666666667e-05, |
|
"loss": 0.5275, |
|
"step": 3760 |
|
}, |
|
{ |
|
"epoch": 18.02, |
|
"learning_rate": 3.4611111111111114e-05, |
|
"loss": 0.1221, |
|
"step": 3770 |
|
}, |
|
{ |
|
"epoch": 18.02, |
|
"learning_rate": 3.4555555555555556e-05, |
|
"loss": 0.2441, |
|
"step": 3780 |
|
}, |
|
{ |
|
"epoch": 18.02, |
|
"learning_rate": 3.45e-05, |
|
"loss": 0.2515, |
|
"step": 3790 |
|
}, |
|
{ |
|
"epoch": 18.02, |
|
"learning_rate": 3.444444444444445e-05, |
|
"loss": 0.0442, |
|
"step": 3800 |
|
}, |
|
{ |
|
"epoch": 18.02, |
|
"eval_accuracy": 0.7708333333333334, |
|
"eval_loss": 1.1625920534133911, |
|
"eval_runtime": 11.9697, |
|
"eval_samples_per_second": 4.01, |
|
"eval_steps_per_second": 2.005, |
|
"step": 3800 |
|
}, |
|
{ |
|
"epoch": 19.0, |
|
"learning_rate": 3.438888888888889e-05, |
|
"loss": 0.0023, |
|
"step": 3810 |
|
}, |
|
{ |
|
"epoch": 19.0, |
|
"learning_rate": 3.433333333333333e-05, |
|
"loss": 0.3082, |
|
"step": 3820 |
|
}, |
|
{ |
|
"epoch": 19.0, |
|
"learning_rate": 3.427777777777778e-05, |
|
"loss": 0.0907, |
|
"step": 3830 |
|
}, |
|
{ |
|
"epoch": 19.0, |
|
"learning_rate": 3.4222222222222224e-05, |
|
"loss": 0.3014, |
|
"step": 3840 |
|
}, |
|
{ |
|
"epoch": 19.0, |
|
"learning_rate": 3.4166666666666666e-05, |
|
"loss": 0.0267, |
|
"step": 3850 |
|
}, |
|
{ |
|
"epoch": 19.01, |
|
"learning_rate": 3.411111111111111e-05, |
|
"loss": 0.0004, |
|
"step": 3860 |
|
}, |
|
{ |
|
"epoch": 19.01, |
|
"learning_rate": 3.405555555555556e-05, |
|
"loss": 0.8851, |
|
"step": 3870 |
|
}, |
|
{ |
|
"epoch": 19.01, |
|
"learning_rate": 3.4000000000000007e-05, |
|
"loss": 0.3284, |
|
"step": 3880 |
|
}, |
|
{ |
|
"epoch": 19.01, |
|
"learning_rate": 3.394444444444444e-05, |
|
"loss": 0.001, |
|
"step": 3890 |
|
}, |
|
{ |
|
"epoch": 19.01, |
|
"learning_rate": 3.388888888888889e-05, |
|
"loss": 0.8428, |
|
"step": 3900 |
|
}, |
|
{ |
|
"epoch": 19.01, |
|
"learning_rate": 3.3833333333333334e-05, |
|
"loss": 0.3571, |
|
"step": 3910 |
|
}, |
|
{ |
|
"epoch": 19.01, |
|
"learning_rate": 3.377777777777778e-05, |
|
"loss": 0.003, |
|
"step": 3920 |
|
}, |
|
{ |
|
"epoch": 19.01, |
|
"learning_rate": 3.3722222222222225e-05, |
|
"loss": 0.1794, |
|
"step": 3930 |
|
}, |
|
{ |
|
"epoch": 19.01, |
|
"learning_rate": 3.366666666666667e-05, |
|
"loss": 0.9065, |
|
"step": 3940 |
|
}, |
|
{ |
|
"epoch": 19.02, |
|
"learning_rate": 3.3611111111111116e-05, |
|
"loss": 0.4515, |
|
"step": 3950 |
|
}, |
|
{ |
|
"epoch": 19.02, |
|
"learning_rate": 3.355555555555556e-05, |
|
"loss": 0.3212, |
|
"step": 3960 |
|
}, |
|
{ |
|
"epoch": 19.02, |
|
"learning_rate": 3.35e-05, |
|
"loss": 0.3582, |
|
"step": 3970 |
|
}, |
|
{ |
|
"epoch": 19.02, |
|
"learning_rate": 3.3444444444444443e-05, |
|
"loss": 0.299, |
|
"step": 3980 |
|
}, |
|
{ |
|
"epoch": 19.02, |
|
"learning_rate": 3.338888888888889e-05, |
|
"loss": 0.053, |
|
"step": 3990 |
|
}, |
|
{ |
|
"epoch": 19.02, |
|
"learning_rate": 3.3333333333333335e-05, |
|
"loss": 0.2449, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 19.02, |
|
"eval_accuracy": 0.8541666666666666, |
|
"eval_loss": 0.8173995614051819, |
|
"eval_runtime": 12.1319, |
|
"eval_samples_per_second": 3.957, |
|
"eval_steps_per_second": 1.978, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 20.0, |
|
"learning_rate": 3.327777777777778e-05, |
|
"loss": 0.0005, |
|
"step": 4010 |
|
}, |
|
{ |
|
"epoch": 20.0, |
|
"learning_rate": 3.322222222222222e-05, |
|
"loss": 0.7228, |
|
"step": 4020 |
|
}, |
|
{ |
|
"epoch": 20.0, |
|
"learning_rate": 3.316666666666667e-05, |
|
"loss": 0.0022, |
|
"step": 4030 |
|
}, |
|
{ |
|
"epoch": 20.0, |
|
"learning_rate": 3.311111111111112e-05, |
|
"loss": 0.4646, |
|
"step": 4040 |
|
}, |
|
{ |
|
"epoch": 20.0, |
|
"learning_rate": 3.3055555555555553e-05, |
|
"loss": 1.0143, |
|
"step": 4050 |
|
}, |
|
{ |
|
"epoch": 20.01, |
|
"learning_rate": 3.3e-05, |
|
"loss": 0.5995, |
|
"step": 4060 |
|
}, |
|
{ |
|
"epoch": 20.01, |
|
"learning_rate": 3.2944444444444445e-05, |
|
"loss": 0.0007, |
|
"step": 4070 |
|
}, |
|
{ |
|
"epoch": 20.01, |
|
"learning_rate": 3.2888888888888894e-05, |
|
"loss": 0.0003, |
|
"step": 4080 |
|
}, |
|
{ |
|
"epoch": 20.01, |
|
"learning_rate": 3.283333333333333e-05, |
|
"loss": 0.1072, |
|
"step": 4090 |
|
}, |
|
{ |
|
"epoch": 20.01, |
|
"learning_rate": 3.277777777777778e-05, |
|
"loss": 0.0004, |
|
"step": 4100 |
|
}, |
|
{ |
|
"epoch": 20.01, |
|
"learning_rate": 3.272222222222223e-05, |
|
"loss": 0.4676, |
|
"step": 4110 |
|
}, |
|
{ |
|
"epoch": 20.01, |
|
"learning_rate": 3.266666666666667e-05, |
|
"loss": 0.2447, |
|
"step": 4120 |
|
}, |
|
{ |
|
"epoch": 20.01, |
|
"learning_rate": 3.261111111111111e-05, |
|
"loss": 0.0444, |
|
"step": 4130 |
|
}, |
|
{ |
|
"epoch": 20.01, |
|
"learning_rate": 3.2555555555555555e-05, |
|
"loss": 0.0146, |
|
"step": 4140 |
|
}, |
|
{ |
|
"epoch": 20.02, |
|
"learning_rate": 3.2500000000000004e-05, |
|
"loss": 1.0221, |
|
"step": 4150 |
|
}, |
|
{ |
|
"epoch": 20.02, |
|
"learning_rate": 3.2444444444444446e-05, |
|
"loss": 0.9506, |
|
"step": 4160 |
|
}, |
|
{ |
|
"epoch": 20.02, |
|
"learning_rate": 3.238888888888889e-05, |
|
"loss": 0.5168, |
|
"step": 4170 |
|
}, |
|
{ |
|
"epoch": 20.02, |
|
"learning_rate": 3.233333333333333e-05, |
|
"loss": 0.1898, |
|
"step": 4180 |
|
}, |
|
{ |
|
"epoch": 20.02, |
|
"learning_rate": 3.227777777777778e-05, |
|
"loss": 0.4702, |
|
"step": 4190 |
|
}, |
|
{ |
|
"epoch": 20.02, |
|
"learning_rate": 3.222222222222223e-05, |
|
"loss": 0.3024, |
|
"step": 4200 |
|
}, |
|
{ |
|
"epoch": 20.02, |
|
"eval_accuracy": 0.7916666666666666, |
|
"eval_loss": 0.8500446677207947, |
|
"eval_runtime": 12.0251, |
|
"eval_samples_per_second": 3.992, |
|
"eval_steps_per_second": 1.996, |
|
"step": 4200 |
|
}, |
|
{ |
|
"epoch": 21.0, |
|
"learning_rate": 3.2166666666666665e-05, |
|
"loss": 0.3821, |
|
"step": 4210 |
|
}, |
|
{ |
|
"epoch": 21.0, |
|
"learning_rate": 3.2111111111111114e-05, |
|
"loss": 1.171, |
|
"step": 4220 |
|
}, |
|
{ |
|
"epoch": 21.0, |
|
"learning_rate": 3.2055555555555556e-05, |
|
"loss": 0.5253, |
|
"step": 4230 |
|
}, |
|
{ |
|
"epoch": 21.0, |
|
"learning_rate": 3.2000000000000005e-05, |
|
"loss": 0.5947, |
|
"step": 4240 |
|
}, |
|
{ |
|
"epoch": 21.0, |
|
"learning_rate": 3.194444444444444e-05, |
|
"loss": 0.489, |
|
"step": 4250 |
|
}, |
|
{ |
|
"epoch": 21.01, |
|
"learning_rate": 3.188888888888889e-05, |
|
"loss": 0.352, |
|
"step": 4260 |
|
}, |
|
{ |
|
"epoch": 21.01, |
|
"learning_rate": 3.183333333333334e-05, |
|
"loss": 0.3475, |
|
"step": 4270 |
|
}, |
|
{ |
|
"epoch": 21.01, |
|
"learning_rate": 3.177777777777778e-05, |
|
"loss": 0.3498, |
|
"step": 4280 |
|
}, |
|
{ |
|
"epoch": 21.01, |
|
"learning_rate": 3.1722222222222224e-05, |
|
"loss": 0.0222, |
|
"step": 4290 |
|
}, |
|
{ |
|
"epoch": 21.01, |
|
"learning_rate": 3.1666666666666666e-05, |
|
"loss": 0.1436, |
|
"step": 4300 |
|
}, |
|
{ |
|
"epoch": 21.01, |
|
"learning_rate": 3.1611111111111115e-05, |
|
"loss": 0.3364, |
|
"step": 4310 |
|
}, |
|
{ |
|
"epoch": 21.01, |
|
"learning_rate": 3.155555555555556e-05, |
|
"loss": 0.0368, |
|
"step": 4320 |
|
}, |
|
{ |
|
"epoch": 21.01, |
|
"learning_rate": 3.15e-05, |
|
"loss": 0.2799, |
|
"step": 4330 |
|
}, |
|
{ |
|
"epoch": 21.01, |
|
"learning_rate": 3.144444444444445e-05, |
|
"loss": 0.4279, |
|
"step": 4340 |
|
}, |
|
{ |
|
"epoch": 21.02, |
|
"learning_rate": 3.138888888888889e-05, |
|
"loss": 0.2409, |
|
"step": 4350 |
|
}, |
|
{ |
|
"epoch": 21.02, |
|
"learning_rate": 3.1333333333333334e-05, |
|
"loss": 0.0012, |
|
"step": 4360 |
|
}, |
|
{ |
|
"epoch": 21.02, |
|
"learning_rate": 3.1277777777777776e-05, |
|
"loss": 0.0224, |
|
"step": 4370 |
|
}, |
|
{ |
|
"epoch": 21.02, |
|
"learning_rate": 3.1222222222222225e-05, |
|
"loss": 0.2865, |
|
"step": 4380 |
|
}, |
|
{ |
|
"epoch": 21.02, |
|
"learning_rate": 3.116666666666667e-05, |
|
"loss": 0.7114, |
|
"step": 4390 |
|
}, |
|
{ |
|
"epoch": 21.02, |
|
"learning_rate": 3.111111111111111e-05, |
|
"loss": 0.4879, |
|
"step": 4400 |
|
}, |
|
{ |
|
"epoch": 21.02, |
|
"eval_accuracy": 0.7291666666666666, |
|
"eval_loss": 1.2219163179397583, |
|
"eval_runtime": 12.2455, |
|
"eval_samples_per_second": 3.92, |
|
"eval_steps_per_second": 1.96, |
|
"step": 4400 |
|
}, |
|
{ |
|
"epoch": 22.0, |
|
"learning_rate": 3.105555555555555e-05, |
|
"loss": 0.2362, |
|
"step": 4410 |
|
}, |
|
{ |
|
"epoch": 22.0, |
|
"learning_rate": 3.1e-05, |
|
"loss": 0.0008, |
|
"step": 4420 |
|
}, |
|
{ |
|
"epoch": 22.0, |
|
"learning_rate": 3.094444444444445e-05, |
|
"loss": 0.1325, |
|
"step": 4430 |
|
}, |
|
{ |
|
"epoch": 22.0, |
|
"learning_rate": 3.088888888888889e-05, |
|
"loss": 0.0823, |
|
"step": 4440 |
|
}, |
|
{ |
|
"epoch": 22.0, |
|
"learning_rate": 3.0833333333333335e-05, |
|
"loss": 0.7201, |
|
"step": 4450 |
|
}, |
|
{ |
|
"epoch": 22.01, |
|
"learning_rate": 3.077777777777778e-05, |
|
"loss": 0.4, |
|
"step": 4460 |
|
}, |
|
{ |
|
"epoch": 22.01, |
|
"learning_rate": 3.0722222222222227e-05, |
|
"loss": 0.2967, |
|
"step": 4470 |
|
}, |
|
{ |
|
"epoch": 22.01, |
|
"learning_rate": 3.066666666666667e-05, |
|
"loss": 0.4169, |
|
"step": 4480 |
|
}, |
|
{ |
|
"epoch": 22.01, |
|
"learning_rate": 3.061111111111111e-05, |
|
"loss": 0.2798, |
|
"step": 4490 |
|
}, |
|
{ |
|
"epoch": 22.01, |
|
"learning_rate": 3.055555555555556e-05, |
|
"loss": 0.745, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 22.01, |
|
"learning_rate": 3.05e-05, |
|
"loss": 0.0427, |
|
"step": 4510 |
|
}, |
|
{ |
|
"epoch": 22.01, |
|
"learning_rate": 3.044444444444445e-05, |
|
"loss": 0.1328, |
|
"step": 4520 |
|
}, |
|
{ |
|
"epoch": 22.01, |
|
"learning_rate": 3.0388888888888887e-05, |
|
"loss": 0.275, |
|
"step": 4530 |
|
}, |
|
{ |
|
"epoch": 22.01, |
|
"learning_rate": 3.0333333333333337e-05, |
|
"loss": 0.2451, |
|
"step": 4540 |
|
}, |
|
{ |
|
"epoch": 22.02, |
|
"learning_rate": 3.0277777777777776e-05, |
|
"loss": 0.4669, |
|
"step": 4550 |
|
}, |
|
{ |
|
"epoch": 22.02, |
|
"learning_rate": 3.0222222222222225e-05, |
|
"loss": 0.3182, |
|
"step": 4560 |
|
}, |
|
{ |
|
"epoch": 22.02, |
|
"learning_rate": 3.016666666666667e-05, |
|
"loss": 0.293, |
|
"step": 4570 |
|
}, |
|
{ |
|
"epoch": 22.02, |
|
"learning_rate": 3.0111111111111113e-05, |
|
"loss": 0.3155, |
|
"step": 4580 |
|
}, |
|
{ |
|
"epoch": 22.02, |
|
"learning_rate": 3.005555555555556e-05, |
|
"loss": 0.7555, |
|
"step": 4590 |
|
}, |
|
{ |
|
"epoch": 22.02, |
|
"learning_rate": 3e-05, |
|
"loss": 0.4035, |
|
"step": 4600 |
|
}, |
|
{ |
|
"epoch": 22.02, |
|
"eval_accuracy": 0.8333333333333334, |
|
"eval_loss": 0.6436423659324646, |
|
"eval_runtime": 11.8808, |
|
"eval_samples_per_second": 4.04, |
|
"eval_steps_per_second": 2.02, |
|
"step": 4600 |
|
}, |
|
{ |
|
"epoch": 23.0, |
|
"learning_rate": 2.9944444444444446e-05, |
|
"loss": 0.2087, |
|
"step": 4610 |
|
}, |
|
{ |
|
"epoch": 23.0, |
|
"learning_rate": 2.988888888888889e-05, |
|
"loss": 1.0019, |
|
"step": 4620 |
|
}, |
|
{ |
|
"epoch": 23.0, |
|
"learning_rate": 2.9833333333333335e-05, |
|
"loss": 0.0338, |
|
"step": 4630 |
|
}, |
|
{ |
|
"epoch": 23.0, |
|
"learning_rate": 2.9777777777777777e-05, |
|
"loss": 0.0014, |
|
"step": 4640 |
|
}, |
|
{ |
|
"epoch": 23.0, |
|
"learning_rate": 2.9722222222222223e-05, |
|
"loss": 0.096, |
|
"step": 4650 |
|
}, |
|
{ |
|
"epoch": 23.01, |
|
"learning_rate": 2.9666666666666672e-05, |
|
"loss": 0.1689, |
|
"step": 4660 |
|
}, |
|
{ |
|
"epoch": 23.01, |
|
"learning_rate": 2.961111111111111e-05, |
|
"loss": 0.5203, |
|
"step": 4670 |
|
}, |
|
{ |
|
"epoch": 23.01, |
|
"learning_rate": 2.955555555555556e-05, |
|
"loss": 0.2689, |
|
"step": 4680 |
|
}, |
|
{ |
|
"epoch": 23.01, |
|
"learning_rate": 2.95e-05, |
|
"loss": 0.6529, |
|
"step": 4690 |
|
}, |
|
{ |
|
"epoch": 23.01, |
|
"learning_rate": 2.9444444444444448e-05, |
|
"loss": 0.4351, |
|
"step": 4700 |
|
}, |
|
{ |
|
"epoch": 23.01, |
|
"learning_rate": 2.9388888888888887e-05, |
|
"loss": 0.1847, |
|
"step": 4710 |
|
}, |
|
{ |
|
"epoch": 23.01, |
|
"learning_rate": 2.9333333333333336e-05, |
|
"loss": 0.979, |
|
"step": 4720 |
|
}, |
|
{ |
|
"epoch": 23.01, |
|
"learning_rate": 2.927777777777778e-05, |
|
"loss": 0.1496, |
|
"step": 4730 |
|
}, |
|
{ |
|
"epoch": 23.01, |
|
"learning_rate": 2.9222222222222224e-05, |
|
"loss": 0.4046, |
|
"step": 4740 |
|
}, |
|
{ |
|
"epoch": 23.02, |
|
"learning_rate": 2.916666666666667e-05, |
|
"loss": 1.481, |
|
"step": 4750 |
|
}, |
|
{ |
|
"epoch": 23.02, |
|
"learning_rate": 2.9111111111111112e-05, |
|
"loss": 0.1607, |
|
"step": 4760 |
|
}, |
|
{ |
|
"epoch": 23.02, |
|
"learning_rate": 2.9055555555555558e-05, |
|
"loss": 0.3698, |
|
"step": 4770 |
|
}, |
|
{ |
|
"epoch": 23.02, |
|
"learning_rate": 2.9e-05, |
|
"loss": 0.4519, |
|
"step": 4780 |
|
}, |
|
{ |
|
"epoch": 23.02, |
|
"learning_rate": 2.8944444444444446e-05, |
|
"loss": 0.0016, |
|
"step": 4790 |
|
}, |
|
{ |
|
"epoch": 23.02, |
|
"learning_rate": 2.8888888888888888e-05, |
|
"loss": 0.0334, |
|
"step": 4800 |
|
}, |
|
{ |
|
"epoch": 23.02, |
|
"eval_accuracy": 0.8333333333333334, |
|
"eval_loss": 0.7433444857597351, |
|
"eval_runtime": 12.225, |
|
"eval_samples_per_second": 3.926, |
|
"eval_steps_per_second": 1.963, |
|
"step": 4800 |
|
}, |
|
{ |
|
"epoch": 24.0, |
|
"learning_rate": 2.8833333333333334e-05, |
|
"loss": 0.2755, |
|
"step": 4810 |
|
}, |
|
{ |
|
"epoch": 24.0, |
|
"learning_rate": 2.877777777777778e-05, |
|
"loss": 0.0019, |
|
"step": 4820 |
|
}, |
|
{ |
|
"epoch": 24.0, |
|
"learning_rate": 2.8722222222222222e-05, |
|
"loss": 0.5901, |
|
"step": 4830 |
|
}, |
|
{ |
|
"epoch": 24.0, |
|
"learning_rate": 2.8666666666666668e-05, |
|
"loss": 0.2686, |
|
"step": 4840 |
|
}, |
|
{ |
|
"epoch": 24.0, |
|
"learning_rate": 2.861111111111111e-05, |
|
"loss": 0.5917, |
|
"step": 4850 |
|
}, |
|
{ |
|
"epoch": 24.01, |
|
"learning_rate": 2.855555555555556e-05, |
|
"loss": 0.1629, |
|
"step": 4860 |
|
}, |
|
{ |
|
"epoch": 24.01, |
|
"learning_rate": 2.8499999999999998e-05, |
|
"loss": 0.4539, |
|
"step": 4870 |
|
}, |
|
{ |
|
"epoch": 24.01, |
|
"learning_rate": 2.8444444444444447e-05, |
|
"loss": 0.0014, |
|
"step": 4880 |
|
}, |
|
{ |
|
"epoch": 24.01, |
|
"learning_rate": 2.8388888888888893e-05, |
|
"loss": 0.2313, |
|
"step": 4890 |
|
}, |
|
{ |
|
"epoch": 24.01, |
|
"learning_rate": 2.8333333333333335e-05, |
|
"loss": 0.7107, |
|
"step": 4900 |
|
}, |
|
{ |
|
"epoch": 24.01, |
|
"learning_rate": 2.827777777777778e-05, |
|
"loss": 0.5604, |
|
"step": 4910 |
|
}, |
|
{ |
|
"epoch": 24.01, |
|
"learning_rate": 2.8222222222222223e-05, |
|
"loss": 0.2858, |
|
"step": 4920 |
|
}, |
|
{ |
|
"epoch": 24.01, |
|
"learning_rate": 2.816666666666667e-05, |
|
"loss": 0.2374, |
|
"step": 4930 |
|
}, |
|
{ |
|
"epoch": 24.01, |
|
"learning_rate": 2.811111111111111e-05, |
|
"loss": 0.256, |
|
"step": 4940 |
|
}, |
|
{ |
|
"epoch": 24.02, |
|
"learning_rate": 2.8055555555555557e-05, |
|
"loss": 0.1735, |
|
"step": 4950 |
|
}, |
|
{ |
|
"epoch": 24.02, |
|
"learning_rate": 2.8000000000000003e-05, |
|
"loss": 0.0017, |
|
"step": 4960 |
|
}, |
|
{ |
|
"epoch": 24.02, |
|
"learning_rate": 2.7944444444444445e-05, |
|
"loss": 0.4564, |
|
"step": 4970 |
|
}, |
|
{ |
|
"epoch": 24.02, |
|
"learning_rate": 2.788888888888889e-05, |
|
"loss": 0.0009, |
|
"step": 4980 |
|
}, |
|
{ |
|
"epoch": 24.02, |
|
"learning_rate": 2.7833333333333333e-05, |
|
"loss": 1.0652, |
|
"step": 4990 |
|
}, |
|
{ |
|
"epoch": 24.02, |
|
"learning_rate": 2.777777777777778e-05, |
|
"loss": 0.4849, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 24.02, |
|
"eval_accuracy": 0.8125, |
|
"eval_loss": 0.991054117679596, |
|
"eval_runtime": 11.8199, |
|
"eval_samples_per_second": 4.061, |
|
"eval_steps_per_second": 2.03, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 25.0, |
|
"learning_rate": 2.772222222222222e-05, |
|
"loss": 0.4665, |
|
"step": 5010 |
|
}, |
|
{ |
|
"epoch": 25.0, |
|
"learning_rate": 2.7666666666666667e-05, |
|
"loss": 0.0116, |
|
"step": 5020 |
|
}, |
|
{ |
|
"epoch": 25.0, |
|
"learning_rate": 2.761111111111111e-05, |
|
"loss": 0.283, |
|
"step": 5030 |
|
}, |
|
{ |
|
"epoch": 25.0, |
|
"learning_rate": 2.7555555555555555e-05, |
|
"loss": 0.5053, |
|
"step": 5040 |
|
}, |
|
{ |
|
"epoch": 25.0, |
|
"learning_rate": 2.7500000000000004e-05, |
|
"loss": 1.1481, |
|
"step": 5050 |
|
}, |
|
{ |
|
"epoch": 25.01, |
|
"learning_rate": 2.7444444444444443e-05, |
|
"loss": 0.6906, |
|
"step": 5060 |
|
}, |
|
{ |
|
"epoch": 25.01, |
|
"learning_rate": 2.7388888888888892e-05, |
|
"loss": 0.2288, |
|
"step": 5070 |
|
}, |
|
{ |
|
"epoch": 25.01, |
|
"learning_rate": 2.733333333333333e-05, |
|
"loss": 0.2736, |
|
"step": 5080 |
|
}, |
|
{ |
|
"epoch": 25.01, |
|
"learning_rate": 2.727777777777778e-05, |
|
"loss": 0.1634, |
|
"step": 5090 |
|
}, |
|
{ |
|
"epoch": 25.01, |
|
"learning_rate": 2.7222222222222223e-05, |
|
"loss": 0.2221, |
|
"step": 5100 |
|
}, |
|
{ |
|
"epoch": 25.01, |
|
"learning_rate": 2.716666666666667e-05, |
|
"loss": 0.0125, |
|
"step": 5110 |
|
}, |
|
{ |
|
"epoch": 25.01, |
|
"learning_rate": 2.7111111111111114e-05, |
|
"loss": 0.4706, |
|
"step": 5120 |
|
}, |
|
{ |
|
"epoch": 25.01, |
|
"learning_rate": 2.7055555555555557e-05, |
|
"loss": 0.0138, |
|
"step": 5130 |
|
}, |
|
{ |
|
"epoch": 25.01, |
|
"learning_rate": 2.7000000000000002e-05, |
|
"loss": 0.1388, |
|
"step": 5140 |
|
}, |
|
{ |
|
"epoch": 25.02, |
|
"learning_rate": 2.6944444444444445e-05, |
|
"loss": 0.0384, |
|
"step": 5150 |
|
}, |
|
{ |
|
"epoch": 25.02, |
|
"learning_rate": 2.688888888888889e-05, |
|
"loss": 0.3701, |
|
"step": 5160 |
|
}, |
|
{ |
|
"epoch": 25.02, |
|
"learning_rate": 2.6833333333333333e-05, |
|
"loss": 0.9735, |
|
"step": 5170 |
|
}, |
|
{ |
|
"epoch": 25.02, |
|
"learning_rate": 2.677777777777778e-05, |
|
"loss": 0.604, |
|
"step": 5180 |
|
}, |
|
{ |
|
"epoch": 25.02, |
|
"learning_rate": 2.6722222222222228e-05, |
|
"loss": 0.0021, |
|
"step": 5190 |
|
}, |
|
{ |
|
"epoch": 25.02, |
|
"learning_rate": 2.6666666666666667e-05, |
|
"loss": 0.6075, |
|
"step": 5200 |
|
}, |
|
{ |
|
"epoch": 25.02, |
|
"eval_accuracy": 0.7083333333333334, |
|
"eval_loss": 1.2248910665512085, |
|
"eval_runtime": 12.4027, |
|
"eval_samples_per_second": 3.87, |
|
"eval_steps_per_second": 1.935, |
|
"step": 5200 |
|
}, |
|
{ |
|
"epoch": 26.0, |
|
"learning_rate": 2.6611111111111116e-05, |
|
"loss": 0.3497, |
|
"step": 5210 |
|
}, |
|
{ |
|
"epoch": 26.0, |
|
"learning_rate": 2.6555555555555555e-05, |
|
"loss": 0.0025, |
|
"step": 5220 |
|
}, |
|
{ |
|
"epoch": 26.0, |
|
"learning_rate": 2.6500000000000004e-05, |
|
"loss": 0.0021, |
|
"step": 5230 |
|
}, |
|
{ |
|
"epoch": 26.0, |
|
"learning_rate": 2.6444444444444443e-05, |
|
"loss": 0.31, |
|
"step": 5240 |
|
}, |
|
{ |
|
"epoch": 26.0, |
|
"learning_rate": 2.6388888888888892e-05, |
|
"loss": 0.3074, |
|
"step": 5250 |
|
}, |
|
{ |
|
"epoch": 26.01, |
|
"learning_rate": 2.633333333333333e-05, |
|
"loss": 0.0399, |
|
"step": 5260 |
|
}, |
|
{ |
|
"epoch": 26.01, |
|
"learning_rate": 2.627777777777778e-05, |
|
"loss": 0.346, |
|
"step": 5270 |
|
}, |
|
{ |
|
"epoch": 26.01, |
|
"learning_rate": 2.6222222222222226e-05, |
|
"loss": 0.2626, |
|
"step": 5280 |
|
}, |
|
{ |
|
"epoch": 26.01, |
|
"learning_rate": 2.6166666666666668e-05, |
|
"loss": 0.4374, |
|
"step": 5290 |
|
}, |
|
{ |
|
"epoch": 26.01, |
|
"learning_rate": 2.6111111111111114e-05, |
|
"loss": 0.1794, |
|
"step": 5300 |
|
}, |
|
{ |
|
"epoch": 26.01, |
|
"learning_rate": 2.6055555555555556e-05, |
|
"loss": 0.0114, |
|
"step": 5310 |
|
}, |
|
{ |
|
"epoch": 26.01, |
|
"learning_rate": 2.6000000000000002e-05, |
|
"loss": 0.7371, |
|
"step": 5320 |
|
}, |
|
{ |
|
"epoch": 26.01, |
|
"learning_rate": 2.5944444444444444e-05, |
|
"loss": 0.1541, |
|
"step": 5330 |
|
}, |
|
{ |
|
"epoch": 26.01, |
|
"learning_rate": 2.588888888888889e-05, |
|
"loss": 0.3013, |
|
"step": 5340 |
|
}, |
|
{ |
|
"epoch": 26.02, |
|
"learning_rate": 2.5833333333333336e-05, |
|
"loss": 0.0008, |
|
"step": 5350 |
|
}, |
|
{ |
|
"epoch": 26.02, |
|
"learning_rate": 2.5777777777777778e-05, |
|
"loss": 0.2295, |
|
"step": 5360 |
|
}, |
|
{ |
|
"epoch": 26.02, |
|
"learning_rate": 2.5722222222222224e-05, |
|
"loss": 0.0008, |
|
"step": 5370 |
|
}, |
|
{ |
|
"epoch": 26.02, |
|
"learning_rate": 2.5666666666666666e-05, |
|
"loss": 0.0006, |
|
"step": 5380 |
|
}, |
|
{ |
|
"epoch": 26.02, |
|
"learning_rate": 2.5611111111111115e-05, |
|
"loss": 0.0027, |
|
"step": 5390 |
|
}, |
|
{ |
|
"epoch": 26.02, |
|
"learning_rate": 2.5555555555555554e-05, |
|
"loss": 0.3441, |
|
"step": 5400 |
|
}, |
|
{ |
|
"epoch": 26.02, |
|
"eval_accuracy": 0.8333333333333334, |
|
"eval_loss": 0.8563232421875, |
|
"eval_runtime": 12.0153, |
|
"eval_samples_per_second": 3.995, |
|
"eval_steps_per_second": 1.997, |
|
"step": 5400 |
|
}, |
|
{ |
|
"epoch": 27.0, |
|
"learning_rate": 2.5500000000000003e-05, |
|
"loss": 0.3165, |
|
"step": 5410 |
|
}, |
|
{ |
|
"epoch": 27.0, |
|
"learning_rate": 2.5444444444444442e-05, |
|
"loss": 0.0024, |
|
"step": 5420 |
|
}, |
|
{ |
|
"epoch": 27.0, |
|
"learning_rate": 2.538888888888889e-05, |
|
"loss": 0.0005, |
|
"step": 5430 |
|
}, |
|
{ |
|
"epoch": 27.0, |
|
"learning_rate": 2.5333333333333337e-05, |
|
"loss": 0.001, |
|
"step": 5440 |
|
}, |
|
{ |
|
"epoch": 27.0, |
|
"learning_rate": 2.527777777777778e-05, |
|
"loss": 0.0003, |
|
"step": 5450 |
|
}, |
|
{ |
|
"epoch": 27.01, |
|
"learning_rate": 2.5222222222222225e-05, |
|
"loss": 1.448, |
|
"step": 5460 |
|
}, |
|
{ |
|
"epoch": 27.01, |
|
"learning_rate": 2.5166666666666667e-05, |
|
"loss": 0.2954, |
|
"step": 5470 |
|
}, |
|
{ |
|
"epoch": 27.01, |
|
"learning_rate": 2.5111111111111113e-05, |
|
"loss": 0.3194, |
|
"step": 5480 |
|
}, |
|
{ |
|
"epoch": 27.01, |
|
"learning_rate": 2.5055555555555555e-05, |
|
"loss": 0.001, |
|
"step": 5490 |
|
}, |
|
{ |
|
"epoch": 27.01, |
|
"learning_rate": 2.5e-05, |
|
"loss": 0.0388, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 27.01, |
|
"learning_rate": 2.4944444444444447e-05, |
|
"loss": 0.3337, |
|
"step": 5510 |
|
}, |
|
{ |
|
"epoch": 27.01, |
|
"learning_rate": 2.488888888888889e-05, |
|
"loss": 0.2475, |
|
"step": 5520 |
|
}, |
|
{ |
|
"epoch": 27.01, |
|
"learning_rate": 2.4833333333333335e-05, |
|
"loss": 0.401, |
|
"step": 5530 |
|
}, |
|
{ |
|
"epoch": 27.01, |
|
"learning_rate": 2.477777777777778e-05, |
|
"loss": 0.495, |
|
"step": 5540 |
|
}, |
|
{ |
|
"epoch": 27.02, |
|
"learning_rate": 2.4722222222222223e-05, |
|
"loss": 0.2633, |
|
"step": 5550 |
|
}, |
|
{ |
|
"epoch": 27.02, |
|
"learning_rate": 2.466666666666667e-05, |
|
"loss": 0.0965, |
|
"step": 5560 |
|
}, |
|
{ |
|
"epoch": 27.02, |
|
"learning_rate": 2.461111111111111e-05, |
|
"loss": 0.0012, |
|
"step": 5570 |
|
}, |
|
{ |
|
"epoch": 27.02, |
|
"learning_rate": 2.4555555555555557e-05, |
|
"loss": 0.3345, |
|
"step": 5580 |
|
}, |
|
{ |
|
"epoch": 27.02, |
|
"learning_rate": 2.45e-05, |
|
"loss": 0.5968, |
|
"step": 5590 |
|
}, |
|
{ |
|
"epoch": 27.02, |
|
"learning_rate": 2.4444444444444445e-05, |
|
"loss": 0.5653, |
|
"step": 5600 |
|
}, |
|
{ |
|
"epoch": 27.02, |
|
"eval_accuracy": 0.8958333333333334, |
|
"eval_loss": 0.45567557215690613, |
|
"eval_runtime": 12.6471, |
|
"eval_samples_per_second": 3.795, |
|
"eval_steps_per_second": 1.898, |
|
"step": 5600 |
|
}, |
|
{ |
|
"epoch": 28.0, |
|
"learning_rate": 2.4388888888888887e-05, |
|
"loss": 0.3856, |
|
"step": 5610 |
|
}, |
|
{ |
|
"epoch": 28.0, |
|
"learning_rate": 2.4333333333333336e-05, |
|
"loss": 0.0019, |
|
"step": 5620 |
|
}, |
|
{ |
|
"epoch": 28.0, |
|
"learning_rate": 2.427777777777778e-05, |
|
"loss": 0.0011, |
|
"step": 5630 |
|
}, |
|
{ |
|
"epoch": 28.0, |
|
"learning_rate": 2.4222222222222224e-05, |
|
"loss": 0.3706, |
|
"step": 5640 |
|
}, |
|
{ |
|
"epoch": 28.0, |
|
"learning_rate": 2.4166666666666667e-05, |
|
"loss": 0.1063, |
|
"step": 5650 |
|
}, |
|
{ |
|
"epoch": 28.01, |
|
"learning_rate": 2.4111111111111113e-05, |
|
"loss": 0.0004, |
|
"step": 5660 |
|
}, |
|
{ |
|
"epoch": 28.01, |
|
"learning_rate": 2.4055555555555555e-05, |
|
"loss": 0.0073, |
|
"step": 5670 |
|
}, |
|
{ |
|
"epoch": 28.01, |
|
"learning_rate": 2.4e-05, |
|
"loss": 0.6459, |
|
"step": 5680 |
|
}, |
|
{ |
|
"epoch": 28.01, |
|
"learning_rate": 2.3944444444444443e-05, |
|
"loss": 0.3438, |
|
"step": 5690 |
|
}, |
|
{ |
|
"epoch": 28.01, |
|
"learning_rate": 2.3888888888888892e-05, |
|
"loss": 0.1719, |
|
"step": 5700 |
|
}, |
|
{ |
|
"epoch": 28.01, |
|
"learning_rate": 2.3833333333333334e-05, |
|
"loss": 0.3087, |
|
"step": 5710 |
|
}, |
|
{ |
|
"epoch": 28.01, |
|
"learning_rate": 2.377777777777778e-05, |
|
"loss": 0.0012, |
|
"step": 5720 |
|
}, |
|
{ |
|
"epoch": 28.01, |
|
"learning_rate": 2.3722222222222222e-05, |
|
"loss": 0.3797, |
|
"step": 5730 |
|
}, |
|
{ |
|
"epoch": 28.01, |
|
"learning_rate": 2.3666666666666668e-05, |
|
"loss": 0.0867, |
|
"step": 5740 |
|
}, |
|
{ |
|
"epoch": 28.02, |
|
"learning_rate": 2.361111111111111e-05, |
|
"loss": 0.7648, |
|
"step": 5750 |
|
}, |
|
{ |
|
"epoch": 28.02, |
|
"learning_rate": 2.3555555555555556e-05, |
|
"loss": 0.448, |
|
"step": 5760 |
|
}, |
|
{ |
|
"epoch": 28.02, |
|
"learning_rate": 2.35e-05, |
|
"loss": 0.2457, |
|
"step": 5770 |
|
}, |
|
{ |
|
"epoch": 28.02, |
|
"learning_rate": 2.3444444444444448e-05, |
|
"loss": 0.5912, |
|
"step": 5780 |
|
}, |
|
{ |
|
"epoch": 28.02, |
|
"learning_rate": 2.338888888888889e-05, |
|
"loss": 0.3141, |
|
"step": 5790 |
|
}, |
|
{ |
|
"epoch": 28.02, |
|
"learning_rate": 2.3333333333333336e-05, |
|
"loss": 0.196, |
|
"step": 5800 |
|
}, |
|
{ |
|
"epoch": 28.02, |
|
"eval_accuracy": 0.8541666666666666, |
|
"eval_loss": 0.4156099259853363, |
|
"eval_runtime": 11.7855, |
|
"eval_samples_per_second": 4.073, |
|
"eval_steps_per_second": 2.036, |
|
"step": 5800 |
|
}, |
|
{ |
|
"epoch": 29.0, |
|
"learning_rate": 2.3277777777777778e-05, |
|
"loss": 0.0005, |
|
"step": 5810 |
|
}, |
|
{ |
|
"epoch": 29.0, |
|
"learning_rate": 2.3222222222222224e-05, |
|
"loss": 0.5131, |
|
"step": 5820 |
|
}, |
|
{ |
|
"epoch": 29.0, |
|
"learning_rate": 2.3166666666666666e-05, |
|
"loss": 0.1469, |
|
"step": 5830 |
|
}, |
|
{ |
|
"epoch": 29.0, |
|
"learning_rate": 2.3111111111111112e-05, |
|
"loss": 0.4118, |
|
"step": 5840 |
|
}, |
|
{ |
|
"epoch": 29.0, |
|
"learning_rate": 2.3055555555555558e-05, |
|
"loss": 0.2109, |
|
"step": 5850 |
|
}, |
|
{ |
|
"epoch": 29.01, |
|
"learning_rate": 2.3000000000000003e-05, |
|
"loss": 0.3721, |
|
"step": 5860 |
|
}, |
|
{ |
|
"epoch": 29.01, |
|
"learning_rate": 2.2944444444444446e-05, |
|
"loss": 0.0009, |
|
"step": 5870 |
|
}, |
|
{ |
|
"epoch": 29.01, |
|
"learning_rate": 2.288888888888889e-05, |
|
"loss": 0.0822, |
|
"step": 5880 |
|
}, |
|
{ |
|
"epoch": 29.01, |
|
"learning_rate": 2.2833333333333334e-05, |
|
"loss": 0.0004, |
|
"step": 5890 |
|
}, |
|
{ |
|
"epoch": 29.01, |
|
"learning_rate": 2.277777777777778e-05, |
|
"loss": 0.2703, |
|
"step": 5900 |
|
}, |
|
{ |
|
"epoch": 29.01, |
|
"learning_rate": 2.2722222222222222e-05, |
|
"loss": 0.0004, |
|
"step": 5910 |
|
}, |
|
{ |
|
"epoch": 29.01, |
|
"learning_rate": 2.2666666666666668e-05, |
|
"loss": 0.3388, |
|
"step": 5920 |
|
}, |
|
{ |
|
"epoch": 29.01, |
|
"learning_rate": 2.2611111111111113e-05, |
|
"loss": 0.021, |
|
"step": 5930 |
|
}, |
|
{ |
|
"epoch": 29.01, |
|
"learning_rate": 2.255555555555556e-05, |
|
"loss": 0.2202, |
|
"step": 5940 |
|
}, |
|
{ |
|
"epoch": 29.02, |
|
"learning_rate": 2.25e-05, |
|
"loss": 0.0009, |
|
"step": 5950 |
|
}, |
|
{ |
|
"epoch": 29.02, |
|
"learning_rate": 2.2444444444444447e-05, |
|
"loss": 0.001, |
|
"step": 5960 |
|
}, |
|
{ |
|
"epoch": 29.02, |
|
"learning_rate": 2.238888888888889e-05, |
|
"loss": 0.6966, |
|
"step": 5970 |
|
}, |
|
{ |
|
"epoch": 29.02, |
|
"learning_rate": 2.2333333333333335e-05, |
|
"loss": 0.6777, |
|
"step": 5980 |
|
}, |
|
{ |
|
"epoch": 29.02, |
|
"learning_rate": 2.2277777777777778e-05, |
|
"loss": 0.2519, |
|
"step": 5990 |
|
}, |
|
{ |
|
"epoch": 29.02, |
|
"learning_rate": 2.2222222222222223e-05, |
|
"loss": 0.0038, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 29.02, |
|
"eval_accuracy": 0.8541666666666666, |
|
"eval_loss": 0.456225723028183, |
|
"eval_runtime": 12.1414, |
|
"eval_samples_per_second": 3.953, |
|
"eval_steps_per_second": 1.977, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 30.0, |
|
"learning_rate": 2.216666666666667e-05, |
|
"loss": 0.0088, |
|
"step": 6010 |
|
}, |
|
{ |
|
"epoch": 30.0, |
|
"learning_rate": 2.211111111111111e-05, |
|
"loss": 0.518, |
|
"step": 6020 |
|
}, |
|
{ |
|
"epoch": 30.0, |
|
"learning_rate": 2.2055555555555557e-05, |
|
"loss": 0.0655, |
|
"step": 6030 |
|
}, |
|
{ |
|
"epoch": 30.0, |
|
"learning_rate": 2.2000000000000003e-05, |
|
"loss": 0.0809, |
|
"step": 6040 |
|
}, |
|
{ |
|
"epoch": 30.0, |
|
"learning_rate": 2.1944444444444445e-05, |
|
"loss": 0.0007, |
|
"step": 6050 |
|
}, |
|
{ |
|
"epoch": 30.01, |
|
"learning_rate": 2.188888888888889e-05, |
|
"loss": 0.3516, |
|
"step": 6060 |
|
}, |
|
{ |
|
"epoch": 30.01, |
|
"learning_rate": 2.1833333333333333e-05, |
|
"loss": 0.2624, |
|
"step": 6070 |
|
}, |
|
{ |
|
"epoch": 30.01, |
|
"learning_rate": 2.177777777777778e-05, |
|
"loss": 0.3091, |
|
"step": 6080 |
|
}, |
|
{ |
|
"epoch": 30.01, |
|
"learning_rate": 2.1722222222222225e-05, |
|
"loss": 0.2033, |
|
"step": 6090 |
|
}, |
|
{ |
|
"epoch": 30.01, |
|
"learning_rate": 2.1666666666666667e-05, |
|
"loss": 0.0009, |
|
"step": 6100 |
|
}, |
|
{ |
|
"epoch": 30.01, |
|
"learning_rate": 2.1611111111111113e-05, |
|
"loss": 0.0015, |
|
"step": 6110 |
|
}, |
|
{ |
|
"epoch": 30.01, |
|
"learning_rate": 2.1555555555555555e-05, |
|
"loss": 0.0916, |
|
"step": 6120 |
|
}, |
|
{ |
|
"epoch": 30.01, |
|
"learning_rate": 2.15e-05, |
|
"loss": 0.0004, |
|
"step": 6130 |
|
}, |
|
{ |
|
"epoch": 30.01, |
|
"learning_rate": 2.1444444444444443e-05, |
|
"loss": 0.6008, |
|
"step": 6140 |
|
}, |
|
{ |
|
"epoch": 30.02, |
|
"learning_rate": 2.138888888888889e-05, |
|
"loss": 0.0004, |
|
"step": 6150 |
|
}, |
|
{ |
|
"epoch": 30.02, |
|
"learning_rate": 2.1333333333333335e-05, |
|
"loss": 0.336, |
|
"step": 6160 |
|
}, |
|
{ |
|
"epoch": 30.02, |
|
"learning_rate": 2.127777777777778e-05, |
|
"loss": 0.9783, |
|
"step": 6170 |
|
}, |
|
{ |
|
"epoch": 30.02, |
|
"learning_rate": 2.1222222222222223e-05, |
|
"loss": 0.182, |
|
"step": 6180 |
|
}, |
|
{ |
|
"epoch": 30.02, |
|
"learning_rate": 2.116666666666667e-05, |
|
"loss": 0.3465, |
|
"step": 6190 |
|
}, |
|
{ |
|
"epoch": 30.02, |
|
"learning_rate": 2.111111111111111e-05, |
|
"loss": 0.2696, |
|
"step": 6200 |
|
}, |
|
{ |
|
"epoch": 30.02, |
|
"eval_accuracy": 0.7916666666666666, |
|
"eval_loss": 0.8153278231620789, |
|
"eval_runtime": 11.793, |
|
"eval_samples_per_second": 4.07, |
|
"eval_steps_per_second": 2.035, |
|
"step": 6200 |
|
}, |
|
{ |
|
"epoch": 31.0, |
|
"learning_rate": 2.1055555555555556e-05, |
|
"loss": 0.5477, |
|
"step": 6210 |
|
}, |
|
{ |
|
"epoch": 31.0, |
|
"learning_rate": 2.1e-05, |
|
"loss": 0.4015, |
|
"step": 6220 |
|
}, |
|
{ |
|
"epoch": 31.0, |
|
"learning_rate": 2.0944444444444445e-05, |
|
"loss": 0.2602, |
|
"step": 6230 |
|
}, |
|
{ |
|
"epoch": 31.0, |
|
"learning_rate": 2.088888888888889e-05, |
|
"loss": 0.3825, |
|
"step": 6240 |
|
}, |
|
{ |
|
"epoch": 31.0, |
|
"learning_rate": 2.0833333333333336e-05, |
|
"loss": 0.2155, |
|
"step": 6250 |
|
}, |
|
{ |
|
"epoch": 31.01, |
|
"learning_rate": 2.077777777777778e-05, |
|
"loss": 0.0007, |
|
"step": 6260 |
|
}, |
|
{ |
|
"epoch": 31.01, |
|
"learning_rate": 2.0722222222222224e-05, |
|
"loss": 0.6795, |
|
"step": 6270 |
|
}, |
|
{ |
|
"epoch": 31.01, |
|
"learning_rate": 2.0666666666666666e-05, |
|
"loss": 0.0007, |
|
"step": 6280 |
|
}, |
|
{ |
|
"epoch": 31.01, |
|
"learning_rate": 2.0611111111111112e-05, |
|
"loss": 0.3173, |
|
"step": 6290 |
|
}, |
|
{ |
|
"epoch": 31.01, |
|
"learning_rate": 2.0555555555555555e-05, |
|
"loss": 0.2455, |
|
"step": 6300 |
|
}, |
|
{ |
|
"epoch": 31.01, |
|
"learning_rate": 2.05e-05, |
|
"loss": 0.6658, |
|
"step": 6310 |
|
}, |
|
{ |
|
"epoch": 31.01, |
|
"learning_rate": 2.0444444444444446e-05, |
|
"loss": 0.4408, |
|
"step": 6320 |
|
}, |
|
{ |
|
"epoch": 31.01, |
|
"learning_rate": 2.0388888888888892e-05, |
|
"loss": 0.0891, |
|
"step": 6330 |
|
}, |
|
{ |
|
"epoch": 31.01, |
|
"learning_rate": 2.0333333333333334e-05, |
|
"loss": 0.4497, |
|
"step": 6340 |
|
}, |
|
{ |
|
"epoch": 31.02, |
|
"learning_rate": 2.027777777777778e-05, |
|
"loss": 0.2107, |
|
"step": 6350 |
|
}, |
|
{ |
|
"epoch": 31.02, |
|
"learning_rate": 2.0222222222222222e-05, |
|
"loss": 0.0016, |
|
"step": 6360 |
|
}, |
|
{ |
|
"epoch": 31.02, |
|
"learning_rate": 2.0166666666666668e-05, |
|
"loss": 0.5188, |
|
"step": 6370 |
|
}, |
|
{ |
|
"epoch": 31.02, |
|
"learning_rate": 2.011111111111111e-05, |
|
"loss": 0.0017, |
|
"step": 6380 |
|
}, |
|
{ |
|
"epoch": 31.02, |
|
"learning_rate": 2.0055555555555556e-05, |
|
"loss": 0.0122, |
|
"step": 6390 |
|
}, |
|
{ |
|
"epoch": 31.02, |
|
"learning_rate": 2e-05, |
|
"loss": 0.0015, |
|
"step": 6400 |
|
}, |
|
{ |
|
"epoch": 31.02, |
|
"eval_accuracy": 0.8958333333333334, |
|
"eval_loss": 0.5923376679420471, |
|
"eval_runtime": 12.3257, |
|
"eval_samples_per_second": 3.894, |
|
"eval_steps_per_second": 1.947, |
|
"step": 6400 |
|
}, |
|
{ |
|
"epoch": 32.0, |
|
"learning_rate": 1.9944444444444447e-05, |
|
"loss": 0.0014, |
|
"step": 6410 |
|
}, |
|
{ |
|
"epoch": 32.0, |
|
"learning_rate": 1.988888888888889e-05, |
|
"loss": 0.0003, |
|
"step": 6420 |
|
}, |
|
{ |
|
"epoch": 32.0, |
|
"learning_rate": 1.9833333333333335e-05, |
|
"loss": 0.3568, |
|
"step": 6430 |
|
}, |
|
{ |
|
"epoch": 32.0, |
|
"learning_rate": 1.9777777777777778e-05, |
|
"loss": 0.0004, |
|
"step": 6440 |
|
}, |
|
{ |
|
"epoch": 32.01, |
|
"learning_rate": 1.9722222222222224e-05, |
|
"loss": 0.052, |
|
"step": 6450 |
|
}, |
|
{ |
|
"epoch": 32.01, |
|
"learning_rate": 1.9666666666666666e-05, |
|
"loss": 0.405, |
|
"step": 6460 |
|
}, |
|
{ |
|
"epoch": 32.01, |
|
"learning_rate": 1.9611111111111115e-05, |
|
"loss": 0.002, |
|
"step": 6470 |
|
}, |
|
{ |
|
"epoch": 32.01, |
|
"learning_rate": 1.9555555555555557e-05, |
|
"loss": 0.0002, |
|
"step": 6480 |
|
}, |
|
{ |
|
"epoch": 32.01, |
|
"learning_rate": 1.9500000000000003e-05, |
|
"loss": 0.1832, |
|
"step": 6490 |
|
}, |
|
{ |
|
"epoch": 32.01, |
|
"learning_rate": 1.9444444444444445e-05, |
|
"loss": 0.6414, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 32.01, |
|
"learning_rate": 1.938888888888889e-05, |
|
"loss": 0.0003, |
|
"step": 6510 |
|
}, |
|
{ |
|
"epoch": 32.01, |
|
"learning_rate": 1.9333333333333333e-05, |
|
"loss": 0.3833, |
|
"step": 6520 |
|
}, |
|
{ |
|
"epoch": 32.01, |
|
"learning_rate": 1.927777777777778e-05, |
|
"loss": 0.2141, |
|
"step": 6530 |
|
}, |
|
{ |
|
"epoch": 32.01, |
|
"learning_rate": 1.922222222222222e-05, |
|
"loss": 0.3455, |
|
"step": 6540 |
|
}, |
|
{ |
|
"epoch": 32.02, |
|
"learning_rate": 1.9166666666666667e-05, |
|
"loss": 0.0005, |
|
"step": 6550 |
|
}, |
|
{ |
|
"epoch": 32.02, |
|
"learning_rate": 1.9111111111111113e-05, |
|
"loss": 0.3215, |
|
"step": 6560 |
|
}, |
|
{ |
|
"epoch": 32.02, |
|
"learning_rate": 1.905555555555556e-05, |
|
"loss": 0.0014, |
|
"step": 6570 |
|
}, |
|
{ |
|
"epoch": 32.02, |
|
"learning_rate": 1.9e-05, |
|
"loss": 0.7868, |
|
"step": 6580 |
|
}, |
|
{ |
|
"epoch": 32.02, |
|
"learning_rate": 1.8944444444444447e-05, |
|
"loss": 0.8695, |
|
"step": 6590 |
|
}, |
|
{ |
|
"epoch": 32.02, |
|
"learning_rate": 1.888888888888889e-05, |
|
"loss": 0.0036, |
|
"step": 6600 |
|
}, |
|
{ |
|
"epoch": 32.02, |
|
"eval_accuracy": 0.875, |
|
"eval_loss": 0.734348714351654, |
|
"eval_runtime": 11.9584, |
|
"eval_samples_per_second": 4.014, |
|
"eval_steps_per_second": 2.007, |
|
"step": 6600 |
|
}, |
|
{ |
|
"epoch": 33.0, |
|
"learning_rate": 1.8833333333333335e-05, |
|
"loss": 0.3371, |
|
"step": 6610 |
|
}, |
|
{ |
|
"epoch": 33.0, |
|
"learning_rate": 1.8777777777777777e-05, |
|
"loss": 0.273, |
|
"step": 6620 |
|
}, |
|
{ |
|
"epoch": 33.0, |
|
"learning_rate": 1.8722222222222223e-05, |
|
"loss": 0.5335, |
|
"step": 6630 |
|
}, |
|
{ |
|
"epoch": 33.0, |
|
"learning_rate": 1.866666666666667e-05, |
|
"loss": 0.0013, |
|
"step": 6640 |
|
}, |
|
{ |
|
"epoch": 33.01, |
|
"learning_rate": 1.861111111111111e-05, |
|
"loss": 0.3249, |
|
"step": 6650 |
|
}, |
|
{ |
|
"epoch": 33.01, |
|
"learning_rate": 1.8555555555555557e-05, |
|
"loss": 0.0005, |
|
"step": 6660 |
|
}, |
|
{ |
|
"epoch": 33.01, |
|
"learning_rate": 1.85e-05, |
|
"loss": 0.1923, |
|
"step": 6670 |
|
}, |
|
{ |
|
"epoch": 33.01, |
|
"learning_rate": 1.8444444444444445e-05, |
|
"loss": 0.0564, |
|
"step": 6680 |
|
}, |
|
{ |
|
"epoch": 33.01, |
|
"learning_rate": 1.838888888888889e-05, |
|
"loss": 0.0004, |
|
"step": 6690 |
|
}, |
|
{ |
|
"epoch": 33.01, |
|
"learning_rate": 1.8333333333333333e-05, |
|
"loss": 0.1158, |
|
"step": 6700 |
|
}, |
|
{ |
|
"epoch": 33.01, |
|
"learning_rate": 1.827777777777778e-05, |
|
"loss": 0.6012, |
|
"step": 6710 |
|
}, |
|
{ |
|
"epoch": 33.01, |
|
"learning_rate": 1.8222222222222224e-05, |
|
"loss": 0.65, |
|
"step": 6720 |
|
}, |
|
{ |
|
"epoch": 33.01, |
|
"learning_rate": 1.8166666666666667e-05, |
|
"loss": 0.0017, |
|
"step": 6730 |
|
}, |
|
{ |
|
"epoch": 33.01, |
|
"learning_rate": 1.8111111111111112e-05, |
|
"loss": 0.0009, |
|
"step": 6740 |
|
}, |
|
{ |
|
"epoch": 33.02, |
|
"learning_rate": 1.8055555555555555e-05, |
|
"loss": 0.0012, |
|
"step": 6750 |
|
}, |
|
{ |
|
"epoch": 33.02, |
|
"learning_rate": 1.8e-05, |
|
"loss": 0.0008, |
|
"step": 6760 |
|
}, |
|
{ |
|
"epoch": 33.02, |
|
"learning_rate": 1.7944444444444443e-05, |
|
"loss": 0.0043, |
|
"step": 6770 |
|
}, |
|
{ |
|
"epoch": 33.02, |
|
"learning_rate": 1.788888888888889e-05, |
|
"loss": 0.2399, |
|
"step": 6780 |
|
}, |
|
{ |
|
"epoch": 33.02, |
|
"learning_rate": 1.7833333333333334e-05, |
|
"loss": 0.0885, |
|
"step": 6790 |
|
}, |
|
{ |
|
"epoch": 33.02, |
|
"learning_rate": 1.777777777777778e-05, |
|
"loss": 0.3623, |
|
"step": 6800 |
|
}, |
|
{ |
|
"epoch": 33.02, |
|
"eval_accuracy": 0.9375, |
|
"eval_loss": 0.30889853835105896, |
|
"eval_runtime": 13.1578, |
|
"eval_samples_per_second": 3.648, |
|
"eval_steps_per_second": 1.824, |
|
"step": 6800 |
|
}, |
|
{ |
|
"epoch": 34.0, |
|
"learning_rate": 1.7722222222222222e-05, |
|
"loss": 0.0004, |
|
"step": 6810 |
|
}, |
|
{ |
|
"epoch": 34.0, |
|
"learning_rate": 1.7666666666666668e-05, |
|
"loss": 0.0004, |
|
"step": 6820 |
|
}, |
|
{ |
|
"epoch": 34.0, |
|
"learning_rate": 1.761111111111111e-05, |
|
"loss": 0.2989, |
|
"step": 6830 |
|
}, |
|
{ |
|
"epoch": 34.0, |
|
"learning_rate": 1.7555555555555556e-05, |
|
"loss": 0.1982, |
|
"step": 6840 |
|
}, |
|
{ |
|
"epoch": 34.01, |
|
"learning_rate": 1.75e-05, |
|
"loss": 0.0016, |
|
"step": 6850 |
|
}, |
|
{ |
|
"epoch": 34.01, |
|
"learning_rate": 1.7444444444444448e-05, |
|
"loss": 0.0002, |
|
"step": 6860 |
|
}, |
|
{ |
|
"epoch": 34.01, |
|
"learning_rate": 1.738888888888889e-05, |
|
"loss": 0.0018, |
|
"step": 6870 |
|
}, |
|
{ |
|
"epoch": 34.01, |
|
"learning_rate": 1.7333333333333336e-05, |
|
"loss": 0.1795, |
|
"step": 6880 |
|
}, |
|
{ |
|
"epoch": 34.01, |
|
"learning_rate": 1.7277777777777778e-05, |
|
"loss": 0.2938, |
|
"step": 6890 |
|
}, |
|
{ |
|
"epoch": 34.01, |
|
"learning_rate": 1.7222222222222224e-05, |
|
"loss": 0.4597, |
|
"step": 6900 |
|
}, |
|
{ |
|
"epoch": 34.01, |
|
"learning_rate": 1.7166666666666666e-05, |
|
"loss": 0.2432, |
|
"step": 6910 |
|
}, |
|
{ |
|
"epoch": 34.01, |
|
"learning_rate": 1.7111111111111112e-05, |
|
"loss": 0.0025, |
|
"step": 6920 |
|
}, |
|
{ |
|
"epoch": 34.01, |
|
"learning_rate": 1.7055555555555554e-05, |
|
"loss": 0.2494, |
|
"step": 6930 |
|
}, |
|
{ |
|
"epoch": 34.01, |
|
"learning_rate": 1.7000000000000003e-05, |
|
"loss": 0.2388, |
|
"step": 6940 |
|
}, |
|
{ |
|
"epoch": 34.02, |
|
"learning_rate": 1.6944444444444446e-05, |
|
"loss": 0.2193, |
|
"step": 6950 |
|
}, |
|
{ |
|
"epoch": 34.02, |
|
"learning_rate": 1.688888888888889e-05, |
|
"loss": 0.0004, |
|
"step": 6960 |
|
}, |
|
{ |
|
"epoch": 34.02, |
|
"learning_rate": 1.6833333333333334e-05, |
|
"loss": 0.0158, |
|
"step": 6970 |
|
}, |
|
{ |
|
"epoch": 34.02, |
|
"learning_rate": 1.677777777777778e-05, |
|
"loss": 0.1012, |
|
"step": 6980 |
|
}, |
|
{ |
|
"epoch": 34.02, |
|
"learning_rate": 1.6722222222222222e-05, |
|
"loss": 0.0071, |
|
"step": 6990 |
|
}, |
|
{ |
|
"epoch": 34.02, |
|
"learning_rate": 1.6666666666666667e-05, |
|
"loss": 0.2142, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 34.02, |
|
"eval_accuracy": 0.8958333333333334, |
|
"eval_loss": 0.6142041683197021, |
|
"eval_runtime": 12.1703, |
|
"eval_samples_per_second": 3.944, |
|
"eval_steps_per_second": 1.972, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 35.0, |
|
"learning_rate": 1.661111111111111e-05, |
|
"loss": 0.0001, |
|
"step": 7010 |
|
}, |
|
{ |
|
"epoch": 35.0, |
|
"learning_rate": 1.655555555555556e-05, |
|
"loss": 0.0005, |
|
"step": 7020 |
|
}, |
|
{ |
|
"epoch": 35.0, |
|
"learning_rate": 1.65e-05, |
|
"loss": 0.0018, |
|
"step": 7030 |
|
}, |
|
{ |
|
"epoch": 35.0, |
|
"learning_rate": 1.6444444444444447e-05, |
|
"loss": 0.4747, |
|
"step": 7040 |
|
}, |
|
{ |
|
"epoch": 35.01, |
|
"learning_rate": 1.638888888888889e-05, |
|
"loss": 0.1249, |
|
"step": 7050 |
|
}, |
|
{ |
|
"epoch": 35.01, |
|
"learning_rate": 1.6333333333333335e-05, |
|
"loss": 0.6736, |
|
"step": 7060 |
|
}, |
|
{ |
|
"epoch": 35.01, |
|
"learning_rate": 1.6277777777777777e-05, |
|
"loss": 0.3599, |
|
"step": 7070 |
|
}, |
|
{ |
|
"epoch": 35.01, |
|
"learning_rate": 1.6222222222222223e-05, |
|
"loss": 0.0593, |
|
"step": 7080 |
|
}, |
|
{ |
|
"epoch": 35.01, |
|
"learning_rate": 1.6166666666666665e-05, |
|
"loss": 0.0015, |
|
"step": 7090 |
|
}, |
|
{ |
|
"epoch": 35.01, |
|
"learning_rate": 1.6111111111111115e-05, |
|
"loss": 0.3011, |
|
"step": 7100 |
|
}, |
|
{ |
|
"epoch": 35.01, |
|
"learning_rate": 1.6055555555555557e-05, |
|
"loss": 0.0006, |
|
"step": 7110 |
|
}, |
|
{ |
|
"epoch": 35.01, |
|
"learning_rate": 1.6000000000000003e-05, |
|
"loss": 0.0578, |
|
"step": 7120 |
|
}, |
|
{ |
|
"epoch": 35.01, |
|
"learning_rate": 1.5944444444444445e-05, |
|
"loss": 0.3444, |
|
"step": 7130 |
|
}, |
|
{ |
|
"epoch": 35.01, |
|
"learning_rate": 1.588888888888889e-05, |
|
"loss": 0.1937, |
|
"step": 7140 |
|
}, |
|
{ |
|
"epoch": 35.02, |
|
"learning_rate": 1.5833333333333333e-05, |
|
"loss": 0.3914, |
|
"step": 7150 |
|
}, |
|
{ |
|
"epoch": 35.02, |
|
"learning_rate": 1.577777777777778e-05, |
|
"loss": 0.1062, |
|
"step": 7160 |
|
}, |
|
{ |
|
"epoch": 35.02, |
|
"learning_rate": 1.5722222222222225e-05, |
|
"loss": 0.0034, |
|
"step": 7170 |
|
}, |
|
{ |
|
"epoch": 35.02, |
|
"learning_rate": 1.5666666666666667e-05, |
|
"loss": 0.4035, |
|
"step": 7180 |
|
}, |
|
{ |
|
"epoch": 35.02, |
|
"learning_rate": 1.5611111111111113e-05, |
|
"loss": 0.4617, |
|
"step": 7190 |
|
}, |
|
{ |
|
"epoch": 35.02, |
|
"learning_rate": 1.5555555555555555e-05, |
|
"loss": 0.0008, |
|
"step": 7200 |
|
}, |
|
{ |
|
"epoch": 35.02, |
|
"eval_accuracy": 0.875, |
|
"eval_loss": 0.6010245680809021, |
|
"eval_runtime": 12.549, |
|
"eval_samples_per_second": 3.825, |
|
"eval_steps_per_second": 1.913, |
|
"step": 7200 |
|
}, |
|
{ |
|
"epoch": 36.0, |
|
"learning_rate": 1.55e-05, |
|
"loss": 0.0011, |
|
"step": 7210 |
|
}, |
|
{ |
|
"epoch": 36.0, |
|
"learning_rate": 1.5444444444444446e-05, |
|
"loss": 0.0003, |
|
"step": 7220 |
|
}, |
|
{ |
|
"epoch": 36.0, |
|
"learning_rate": 1.538888888888889e-05, |
|
"loss": 0.2107, |
|
"step": 7230 |
|
}, |
|
{ |
|
"epoch": 36.0, |
|
"learning_rate": 1.5333333333333334e-05, |
|
"loss": 0.3339, |
|
"step": 7240 |
|
}, |
|
{ |
|
"epoch": 36.01, |
|
"learning_rate": 1.527777777777778e-05, |
|
"loss": 0.2039, |
|
"step": 7250 |
|
}, |
|
{ |
|
"epoch": 36.01, |
|
"learning_rate": 1.5222222222222224e-05, |
|
"loss": 0.5722, |
|
"step": 7260 |
|
}, |
|
{ |
|
"epoch": 36.01, |
|
"learning_rate": 1.5166666666666668e-05, |
|
"loss": 0.0008, |
|
"step": 7270 |
|
}, |
|
{ |
|
"epoch": 36.01, |
|
"learning_rate": 1.5111111111111112e-05, |
|
"loss": 0.0011, |
|
"step": 7280 |
|
}, |
|
{ |
|
"epoch": 36.01, |
|
"learning_rate": 1.5055555555555556e-05, |
|
"loss": 0.0006, |
|
"step": 7290 |
|
}, |
|
{ |
|
"epoch": 36.01, |
|
"learning_rate": 1.5e-05, |
|
"loss": 0.3744, |
|
"step": 7300 |
|
}, |
|
{ |
|
"epoch": 36.01, |
|
"learning_rate": 1.4944444444444444e-05, |
|
"loss": 0.0012, |
|
"step": 7310 |
|
}, |
|
{ |
|
"epoch": 36.01, |
|
"learning_rate": 1.4888888888888888e-05, |
|
"loss": 0.3035, |
|
"step": 7320 |
|
}, |
|
{ |
|
"epoch": 36.01, |
|
"learning_rate": 1.4833333333333336e-05, |
|
"loss": 0.1144, |
|
"step": 7330 |
|
}, |
|
{ |
|
"epoch": 36.01, |
|
"learning_rate": 1.477777777777778e-05, |
|
"loss": 0.0272, |
|
"step": 7340 |
|
}, |
|
{ |
|
"epoch": 36.02, |
|
"learning_rate": 1.4722222222222224e-05, |
|
"loss": 0.0005, |
|
"step": 7350 |
|
}, |
|
{ |
|
"epoch": 36.02, |
|
"learning_rate": 1.4666666666666668e-05, |
|
"loss": 0.0005, |
|
"step": 7360 |
|
}, |
|
{ |
|
"epoch": 36.02, |
|
"learning_rate": 1.4611111111111112e-05, |
|
"loss": 0.0052, |
|
"step": 7370 |
|
}, |
|
{ |
|
"epoch": 36.02, |
|
"learning_rate": 1.4555555555555556e-05, |
|
"loss": 0.0043, |
|
"step": 7380 |
|
}, |
|
{ |
|
"epoch": 36.02, |
|
"learning_rate": 1.45e-05, |
|
"loss": 0.0001, |
|
"step": 7390 |
|
}, |
|
{ |
|
"epoch": 36.02, |
|
"learning_rate": 1.4444444444444444e-05, |
|
"loss": 0.0005, |
|
"step": 7400 |
|
}, |
|
{ |
|
"epoch": 36.02, |
|
"eval_accuracy": 0.875, |
|
"eval_loss": 0.6238037943840027, |
|
"eval_runtime": 12.0891, |
|
"eval_samples_per_second": 3.971, |
|
"eval_steps_per_second": 1.985, |
|
"step": 7400 |
|
}, |
|
{ |
|
"epoch": 37.0, |
|
"learning_rate": 1.438888888888889e-05, |
|
"loss": 0.2606, |
|
"step": 7410 |
|
}, |
|
{ |
|
"epoch": 37.0, |
|
"learning_rate": 1.4333333333333334e-05, |
|
"loss": 0.0002, |
|
"step": 7420 |
|
}, |
|
{ |
|
"epoch": 37.0, |
|
"learning_rate": 1.427777777777778e-05, |
|
"loss": 0.0001, |
|
"step": 7430 |
|
}, |
|
{ |
|
"epoch": 37.0, |
|
"learning_rate": 1.4222222222222224e-05, |
|
"loss": 0.3046, |
|
"step": 7440 |
|
}, |
|
{ |
|
"epoch": 37.01, |
|
"learning_rate": 1.4166666666666668e-05, |
|
"loss": 0.0002, |
|
"step": 7450 |
|
}, |
|
{ |
|
"epoch": 37.01, |
|
"learning_rate": 1.4111111111111112e-05, |
|
"loss": 0.0008, |
|
"step": 7460 |
|
}, |
|
{ |
|
"epoch": 37.01, |
|
"learning_rate": 1.4055555555555556e-05, |
|
"loss": 0.3541, |
|
"step": 7470 |
|
}, |
|
{ |
|
"epoch": 37.01, |
|
"learning_rate": 1.4000000000000001e-05, |
|
"loss": 0.0001, |
|
"step": 7480 |
|
}, |
|
{ |
|
"epoch": 37.01, |
|
"learning_rate": 1.3944444444444446e-05, |
|
"loss": 0.0113, |
|
"step": 7490 |
|
}, |
|
{ |
|
"epoch": 37.01, |
|
"learning_rate": 1.388888888888889e-05, |
|
"loss": 0.2522, |
|
"step": 7500 |
|
}, |
|
{ |
|
"epoch": 37.01, |
|
"learning_rate": 1.3833333333333334e-05, |
|
"loss": 0.4705, |
|
"step": 7510 |
|
}, |
|
{ |
|
"epoch": 37.01, |
|
"learning_rate": 1.3777777777777778e-05, |
|
"loss": 0.0001, |
|
"step": 7520 |
|
}, |
|
{ |
|
"epoch": 37.01, |
|
"learning_rate": 1.3722222222222222e-05, |
|
"loss": 0.0124, |
|
"step": 7530 |
|
}, |
|
{ |
|
"epoch": 37.01, |
|
"learning_rate": 1.3666666666666666e-05, |
|
"loss": 0.3502, |
|
"step": 7540 |
|
}, |
|
{ |
|
"epoch": 37.02, |
|
"learning_rate": 1.3611111111111111e-05, |
|
"loss": 0.0029, |
|
"step": 7550 |
|
}, |
|
{ |
|
"epoch": 37.02, |
|
"learning_rate": 1.3555555555555557e-05, |
|
"loss": 0.3978, |
|
"step": 7560 |
|
}, |
|
{ |
|
"epoch": 37.02, |
|
"learning_rate": 1.3500000000000001e-05, |
|
"loss": 0.0001, |
|
"step": 7570 |
|
}, |
|
{ |
|
"epoch": 37.02, |
|
"learning_rate": 1.3444444444444445e-05, |
|
"loss": 0.3307, |
|
"step": 7580 |
|
}, |
|
{ |
|
"epoch": 37.02, |
|
"learning_rate": 1.338888888888889e-05, |
|
"loss": 0.0001, |
|
"step": 7590 |
|
}, |
|
{ |
|
"epoch": 37.02, |
|
"learning_rate": 1.3333333333333333e-05, |
|
"loss": 0.0002, |
|
"step": 7600 |
|
}, |
|
{ |
|
"epoch": 37.02, |
|
"eval_accuracy": 0.875, |
|
"eval_loss": 0.5965681076049805, |
|
"eval_runtime": 12.7074, |
|
"eval_samples_per_second": 3.777, |
|
"eval_steps_per_second": 1.889, |
|
"step": 7600 |
|
}, |
|
{ |
|
"epoch": 38.0, |
|
"learning_rate": 1.3277777777777777e-05, |
|
"loss": 0.1374, |
|
"step": 7610 |
|
}, |
|
{ |
|
"epoch": 38.0, |
|
"learning_rate": 1.3222222222222221e-05, |
|
"loss": 0.0001, |
|
"step": 7620 |
|
}, |
|
{ |
|
"epoch": 38.0, |
|
"learning_rate": 1.3166666666666665e-05, |
|
"loss": 0.2238, |
|
"step": 7630 |
|
}, |
|
{ |
|
"epoch": 38.0, |
|
"learning_rate": 1.3111111111111113e-05, |
|
"loss": 0.0002, |
|
"step": 7640 |
|
}, |
|
{ |
|
"epoch": 38.01, |
|
"learning_rate": 1.3055555555555557e-05, |
|
"loss": 0.0003, |
|
"step": 7650 |
|
}, |
|
{ |
|
"epoch": 38.01, |
|
"learning_rate": 1.3000000000000001e-05, |
|
"loss": 0.2966, |
|
"step": 7660 |
|
}, |
|
{ |
|
"epoch": 38.01, |
|
"learning_rate": 1.2944444444444445e-05, |
|
"loss": 0.0001, |
|
"step": 7670 |
|
}, |
|
{ |
|
"epoch": 38.01, |
|
"learning_rate": 1.2888888888888889e-05, |
|
"loss": 0.2405, |
|
"step": 7680 |
|
}, |
|
{ |
|
"epoch": 38.01, |
|
"learning_rate": 1.2833333333333333e-05, |
|
"loss": 0.0002, |
|
"step": 7690 |
|
}, |
|
{ |
|
"epoch": 38.01, |
|
"learning_rate": 1.2777777777777777e-05, |
|
"loss": 0.2149, |
|
"step": 7700 |
|
}, |
|
{ |
|
"epoch": 38.01, |
|
"learning_rate": 1.2722222222222221e-05, |
|
"loss": 0.006, |
|
"step": 7710 |
|
}, |
|
{ |
|
"epoch": 38.01, |
|
"learning_rate": 1.2666666666666668e-05, |
|
"loss": 0.0003, |
|
"step": 7720 |
|
}, |
|
{ |
|
"epoch": 38.01, |
|
"learning_rate": 1.2611111111111113e-05, |
|
"loss": 0.3521, |
|
"step": 7730 |
|
}, |
|
{ |
|
"epoch": 38.01, |
|
"learning_rate": 1.2555555555555557e-05, |
|
"loss": 0.2337, |
|
"step": 7740 |
|
}, |
|
{ |
|
"epoch": 38.02, |
|
"learning_rate": 1.25e-05, |
|
"loss": 0.0003, |
|
"step": 7750 |
|
}, |
|
{ |
|
"epoch": 38.02, |
|
"learning_rate": 1.2444444444444445e-05, |
|
"loss": 0.0011, |
|
"step": 7760 |
|
}, |
|
{ |
|
"epoch": 38.02, |
|
"learning_rate": 1.238888888888889e-05, |
|
"loss": 0.3938, |
|
"step": 7770 |
|
}, |
|
{ |
|
"epoch": 38.02, |
|
"learning_rate": 1.2333333333333334e-05, |
|
"loss": 0.0013, |
|
"step": 7780 |
|
}, |
|
{ |
|
"epoch": 38.02, |
|
"learning_rate": 1.2277777777777778e-05, |
|
"loss": 0.3642, |
|
"step": 7790 |
|
}, |
|
{ |
|
"epoch": 38.02, |
|
"learning_rate": 1.2222222222222222e-05, |
|
"loss": 0.5, |
|
"step": 7800 |
|
}, |
|
{ |
|
"epoch": 38.02, |
|
"eval_accuracy": 0.8541666666666666, |
|
"eval_loss": 0.6370941996574402, |
|
"eval_runtime": 12.1176, |
|
"eval_samples_per_second": 3.961, |
|
"eval_steps_per_second": 1.981, |
|
"step": 7800 |
|
}, |
|
{ |
|
"epoch": 39.0, |
|
"learning_rate": 1.2166666666666668e-05, |
|
"loss": 0.1917, |
|
"step": 7810 |
|
}, |
|
{ |
|
"epoch": 39.0, |
|
"learning_rate": 1.2111111111111112e-05, |
|
"loss": 0.0005, |
|
"step": 7820 |
|
}, |
|
{ |
|
"epoch": 39.0, |
|
"learning_rate": 1.2055555555555556e-05, |
|
"loss": 0.0008, |
|
"step": 7830 |
|
}, |
|
{ |
|
"epoch": 39.0, |
|
"learning_rate": 1.2e-05, |
|
"loss": 0.0003, |
|
"step": 7840 |
|
}, |
|
{ |
|
"epoch": 39.01, |
|
"learning_rate": 1.1944444444444446e-05, |
|
"loss": 0.3156, |
|
"step": 7850 |
|
}, |
|
{ |
|
"epoch": 39.01, |
|
"learning_rate": 1.188888888888889e-05, |
|
"loss": 0.2985, |
|
"step": 7860 |
|
}, |
|
{ |
|
"epoch": 39.01, |
|
"learning_rate": 1.1833333333333334e-05, |
|
"loss": 0.1472, |
|
"step": 7870 |
|
}, |
|
{ |
|
"epoch": 39.01, |
|
"learning_rate": 1.1777777777777778e-05, |
|
"loss": 0.0003, |
|
"step": 7880 |
|
}, |
|
{ |
|
"epoch": 39.01, |
|
"learning_rate": 1.1722222222222224e-05, |
|
"loss": 0.0004, |
|
"step": 7890 |
|
}, |
|
{ |
|
"epoch": 39.01, |
|
"learning_rate": 1.1666666666666668e-05, |
|
"loss": 0.0001, |
|
"step": 7900 |
|
}, |
|
{ |
|
"epoch": 39.01, |
|
"learning_rate": 1.1611111111111112e-05, |
|
"loss": 0.0015, |
|
"step": 7910 |
|
}, |
|
{ |
|
"epoch": 39.01, |
|
"learning_rate": 1.1555555555555556e-05, |
|
"loss": 0.0007, |
|
"step": 7920 |
|
}, |
|
{ |
|
"epoch": 39.01, |
|
"learning_rate": 1.1500000000000002e-05, |
|
"loss": 0.177, |
|
"step": 7930 |
|
}, |
|
{ |
|
"epoch": 39.01, |
|
"learning_rate": 1.1444444444444446e-05, |
|
"loss": 0.4072, |
|
"step": 7940 |
|
}, |
|
{ |
|
"epoch": 39.02, |
|
"learning_rate": 1.138888888888889e-05, |
|
"loss": 0.1378, |
|
"step": 7950 |
|
}, |
|
{ |
|
"epoch": 39.02, |
|
"learning_rate": 1.1333333333333334e-05, |
|
"loss": 0.0117, |
|
"step": 7960 |
|
}, |
|
{ |
|
"epoch": 39.02, |
|
"learning_rate": 1.127777777777778e-05, |
|
"loss": 0.3177, |
|
"step": 7970 |
|
}, |
|
{ |
|
"epoch": 39.02, |
|
"learning_rate": 1.1222222222222224e-05, |
|
"loss": 0.0002, |
|
"step": 7980 |
|
}, |
|
{ |
|
"epoch": 39.02, |
|
"learning_rate": 1.1166666666666668e-05, |
|
"loss": 0.2967, |
|
"step": 7990 |
|
}, |
|
{ |
|
"epoch": 39.02, |
|
"learning_rate": 1.1111111111111112e-05, |
|
"loss": 0.0004, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 39.02, |
|
"eval_accuracy": 0.8541666666666666, |
|
"eval_loss": 0.8514948487281799, |
|
"eval_runtime": 12.3588, |
|
"eval_samples_per_second": 3.884, |
|
"eval_steps_per_second": 1.942, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 40.0, |
|
"learning_rate": 1.1055555555555556e-05, |
|
"loss": 0.4713, |
|
"step": 8010 |
|
}, |
|
{ |
|
"epoch": 40.0, |
|
"learning_rate": 1.1000000000000001e-05, |
|
"loss": 0.0004, |
|
"step": 8020 |
|
}, |
|
{ |
|
"epoch": 40.0, |
|
"learning_rate": 1.0944444444444445e-05, |
|
"loss": 0.0001, |
|
"step": 8030 |
|
}, |
|
{ |
|
"epoch": 40.0, |
|
"learning_rate": 1.088888888888889e-05, |
|
"loss": 0.2562, |
|
"step": 8040 |
|
}, |
|
{ |
|
"epoch": 40.01, |
|
"learning_rate": 1.0833333333333334e-05, |
|
"loss": 0.002, |
|
"step": 8050 |
|
}, |
|
{ |
|
"epoch": 40.01, |
|
"learning_rate": 1.0777777777777778e-05, |
|
"loss": 0.0001, |
|
"step": 8060 |
|
}, |
|
{ |
|
"epoch": 40.01, |
|
"learning_rate": 1.0722222222222222e-05, |
|
"loss": 0.0001, |
|
"step": 8070 |
|
}, |
|
{ |
|
"epoch": 40.01, |
|
"learning_rate": 1.0666666666666667e-05, |
|
"loss": 0.0004, |
|
"step": 8080 |
|
}, |
|
{ |
|
"epoch": 40.01, |
|
"learning_rate": 1.0611111111111111e-05, |
|
"loss": 0.0001, |
|
"step": 8090 |
|
}, |
|
{ |
|
"epoch": 40.01, |
|
"learning_rate": 1.0555555555555555e-05, |
|
"loss": 0.0004, |
|
"step": 8100 |
|
}, |
|
{ |
|
"epoch": 40.01, |
|
"learning_rate": 1.05e-05, |
|
"loss": 0.0003, |
|
"step": 8110 |
|
}, |
|
{ |
|
"epoch": 40.01, |
|
"learning_rate": 1.0444444444444445e-05, |
|
"loss": 0.2269, |
|
"step": 8120 |
|
}, |
|
{ |
|
"epoch": 40.01, |
|
"learning_rate": 1.038888888888889e-05, |
|
"loss": 0.3188, |
|
"step": 8130 |
|
}, |
|
{ |
|
"epoch": 40.01, |
|
"learning_rate": 1.0333333333333333e-05, |
|
"loss": 0.5858, |
|
"step": 8140 |
|
}, |
|
{ |
|
"epoch": 40.02, |
|
"learning_rate": 1.0277777777777777e-05, |
|
"loss": 0.0033, |
|
"step": 8150 |
|
}, |
|
{ |
|
"epoch": 40.02, |
|
"learning_rate": 1.0222222222222223e-05, |
|
"loss": 0.2789, |
|
"step": 8160 |
|
}, |
|
{ |
|
"epoch": 40.02, |
|
"learning_rate": 1.0166666666666667e-05, |
|
"loss": 0.0003, |
|
"step": 8170 |
|
}, |
|
{ |
|
"epoch": 40.02, |
|
"learning_rate": 1.0111111111111111e-05, |
|
"loss": 0.0006, |
|
"step": 8180 |
|
}, |
|
{ |
|
"epoch": 40.02, |
|
"learning_rate": 1.0055555555555555e-05, |
|
"loss": 0.0002, |
|
"step": 8190 |
|
}, |
|
{ |
|
"epoch": 40.02, |
|
"learning_rate": 1e-05, |
|
"loss": 0.0001, |
|
"step": 8200 |
|
}, |
|
{ |
|
"epoch": 40.02, |
|
"eval_accuracy": 0.875, |
|
"eval_loss": 0.5120431780815125, |
|
"eval_runtime": 11.76, |
|
"eval_samples_per_second": 4.082, |
|
"eval_steps_per_second": 2.041, |
|
"step": 8200 |
|
}, |
|
{ |
|
"epoch": 41.0, |
|
"learning_rate": 9.944444444444445e-06, |
|
"loss": 0.0203, |
|
"step": 8210 |
|
}, |
|
{ |
|
"epoch": 41.0, |
|
"learning_rate": 9.888888888888889e-06, |
|
"loss": 0.2243, |
|
"step": 8220 |
|
}, |
|
{ |
|
"epoch": 41.0, |
|
"learning_rate": 9.833333333333333e-06, |
|
"loss": 0.088, |
|
"step": 8230 |
|
}, |
|
{ |
|
"epoch": 41.0, |
|
"learning_rate": 9.777777777777779e-06, |
|
"loss": 0.0001, |
|
"step": 8240 |
|
}, |
|
{ |
|
"epoch": 41.01, |
|
"learning_rate": 9.722222222222223e-06, |
|
"loss": 0.0003, |
|
"step": 8250 |
|
}, |
|
{ |
|
"epoch": 41.01, |
|
"learning_rate": 9.666666666666667e-06, |
|
"loss": 0.0002, |
|
"step": 8260 |
|
}, |
|
{ |
|
"epoch": 41.01, |
|
"learning_rate": 9.61111111111111e-06, |
|
"loss": 0.0001, |
|
"step": 8270 |
|
}, |
|
{ |
|
"epoch": 41.01, |
|
"learning_rate": 9.555555555555556e-06, |
|
"loss": 0.0001, |
|
"step": 8280 |
|
}, |
|
{ |
|
"epoch": 41.01, |
|
"learning_rate": 9.5e-06, |
|
"loss": 0.0005, |
|
"step": 8290 |
|
}, |
|
{ |
|
"epoch": 41.01, |
|
"learning_rate": 9.444444444444445e-06, |
|
"loss": 0.0111, |
|
"step": 8300 |
|
}, |
|
{ |
|
"epoch": 41.01, |
|
"learning_rate": 9.388888888888889e-06, |
|
"loss": 0.0001, |
|
"step": 8310 |
|
}, |
|
{ |
|
"epoch": 41.01, |
|
"learning_rate": 9.333333333333334e-06, |
|
"loss": 0.0001, |
|
"step": 8320 |
|
}, |
|
{ |
|
"epoch": 41.01, |
|
"learning_rate": 9.277777777777778e-06, |
|
"loss": 0.0001, |
|
"step": 8330 |
|
}, |
|
{ |
|
"epoch": 41.01, |
|
"learning_rate": 9.222222222222222e-06, |
|
"loss": 0.2168, |
|
"step": 8340 |
|
}, |
|
{ |
|
"epoch": 41.02, |
|
"learning_rate": 9.166666666666666e-06, |
|
"loss": 0.0002, |
|
"step": 8350 |
|
}, |
|
{ |
|
"epoch": 41.02, |
|
"learning_rate": 9.111111111111112e-06, |
|
"loss": 0.0057, |
|
"step": 8360 |
|
}, |
|
{ |
|
"epoch": 41.02, |
|
"learning_rate": 9.055555555555556e-06, |
|
"loss": 0.4063, |
|
"step": 8370 |
|
}, |
|
{ |
|
"epoch": 41.02, |
|
"learning_rate": 9e-06, |
|
"loss": 0.0005, |
|
"step": 8380 |
|
}, |
|
{ |
|
"epoch": 41.02, |
|
"learning_rate": 8.944444444444444e-06, |
|
"loss": 0.0, |
|
"step": 8390 |
|
}, |
|
{ |
|
"epoch": 41.02, |
|
"learning_rate": 8.88888888888889e-06, |
|
"loss": 0.0069, |
|
"step": 8400 |
|
}, |
|
{ |
|
"epoch": 41.02, |
|
"eval_accuracy": 0.8541666666666666, |
|
"eval_loss": 0.8686442375183105, |
|
"eval_runtime": 12.3031, |
|
"eval_samples_per_second": 3.901, |
|
"eval_steps_per_second": 1.951, |
|
"step": 8400 |
|
}, |
|
{ |
|
"epoch": 42.0, |
|
"learning_rate": 8.833333333333334e-06, |
|
"loss": 0.038, |
|
"step": 8410 |
|
}, |
|
{ |
|
"epoch": 42.0, |
|
"learning_rate": 8.777777777777778e-06, |
|
"loss": 0.0004, |
|
"step": 8420 |
|
}, |
|
{ |
|
"epoch": 42.0, |
|
"learning_rate": 8.722222222222224e-06, |
|
"loss": 0.4298, |
|
"step": 8430 |
|
}, |
|
{ |
|
"epoch": 42.0, |
|
"learning_rate": 8.666666666666668e-06, |
|
"loss": 0.0001, |
|
"step": 8440 |
|
}, |
|
{ |
|
"epoch": 42.01, |
|
"learning_rate": 8.611111111111112e-06, |
|
"loss": 0.0002, |
|
"step": 8450 |
|
}, |
|
{ |
|
"epoch": 42.01, |
|
"learning_rate": 8.555555555555556e-06, |
|
"loss": 0.0001, |
|
"step": 8460 |
|
}, |
|
{ |
|
"epoch": 42.01, |
|
"learning_rate": 8.500000000000002e-06, |
|
"loss": 0.0503, |
|
"step": 8470 |
|
}, |
|
{ |
|
"epoch": 42.01, |
|
"learning_rate": 8.444444444444446e-06, |
|
"loss": 0.1871, |
|
"step": 8480 |
|
}, |
|
{ |
|
"epoch": 42.01, |
|
"learning_rate": 8.38888888888889e-06, |
|
"loss": 0.4466, |
|
"step": 8490 |
|
}, |
|
{ |
|
"epoch": 42.01, |
|
"learning_rate": 8.333333333333334e-06, |
|
"loss": 0.0001, |
|
"step": 8500 |
|
}, |
|
{ |
|
"epoch": 42.01, |
|
"learning_rate": 8.27777777777778e-06, |
|
"loss": 0.0087, |
|
"step": 8510 |
|
}, |
|
{ |
|
"epoch": 42.01, |
|
"learning_rate": 8.222222222222223e-06, |
|
"loss": 0.6041, |
|
"step": 8520 |
|
}, |
|
{ |
|
"epoch": 42.01, |
|
"learning_rate": 8.166666666666668e-06, |
|
"loss": 0.2826, |
|
"step": 8530 |
|
}, |
|
{ |
|
"epoch": 42.01, |
|
"learning_rate": 8.111111111111112e-06, |
|
"loss": 0.0001, |
|
"step": 8540 |
|
}, |
|
{ |
|
"epoch": 42.02, |
|
"learning_rate": 8.055555555555557e-06, |
|
"loss": 0.0001, |
|
"step": 8550 |
|
}, |
|
{ |
|
"epoch": 42.02, |
|
"learning_rate": 8.000000000000001e-06, |
|
"loss": 0.0074, |
|
"step": 8560 |
|
}, |
|
{ |
|
"epoch": 42.02, |
|
"learning_rate": 7.944444444444445e-06, |
|
"loss": 0.0006, |
|
"step": 8570 |
|
}, |
|
{ |
|
"epoch": 42.02, |
|
"learning_rate": 7.88888888888889e-06, |
|
"loss": 0.0001, |
|
"step": 8580 |
|
}, |
|
{ |
|
"epoch": 42.02, |
|
"learning_rate": 7.833333333333333e-06, |
|
"loss": 0.0626, |
|
"step": 8590 |
|
}, |
|
{ |
|
"epoch": 42.02, |
|
"learning_rate": 7.777777777777777e-06, |
|
"loss": 0.0002, |
|
"step": 8600 |
|
}, |
|
{ |
|
"epoch": 42.02, |
|
"eval_accuracy": 0.8541666666666666, |
|
"eval_loss": 0.8800749182701111, |
|
"eval_runtime": 12.0228, |
|
"eval_samples_per_second": 3.992, |
|
"eval_steps_per_second": 1.996, |
|
"step": 8600 |
|
}, |
|
{ |
|
"epoch": 43.0, |
|
"learning_rate": 7.722222222222223e-06, |
|
"loss": 0.0001, |
|
"step": 8610 |
|
}, |
|
{ |
|
"epoch": 43.0, |
|
"learning_rate": 7.666666666666667e-06, |
|
"loss": 0.0879, |
|
"step": 8620 |
|
}, |
|
{ |
|
"epoch": 43.0, |
|
"learning_rate": 7.611111111111112e-06, |
|
"loss": 0.0004, |
|
"step": 8630 |
|
}, |
|
{ |
|
"epoch": 43.0, |
|
"learning_rate": 7.555555555555556e-06, |
|
"loss": 0.0001, |
|
"step": 8640 |
|
}, |
|
{ |
|
"epoch": 43.01, |
|
"learning_rate": 7.5e-06, |
|
"loss": 0.0021, |
|
"step": 8650 |
|
}, |
|
{ |
|
"epoch": 43.01, |
|
"learning_rate": 7.444444444444444e-06, |
|
"loss": 0.0, |
|
"step": 8660 |
|
}, |
|
{ |
|
"epoch": 43.01, |
|
"learning_rate": 7.38888888888889e-06, |
|
"loss": 0.5426, |
|
"step": 8670 |
|
}, |
|
{ |
|
"epoch": 43.01, |
|
"learning_rate": 7.333333333333334e-06, |
|
"loss": 0.5154, |
|
"step": 8680 |
|
}, |
|
{ |
|
"epoch": 43.01, |
|
"learning_rate": 7.277777777777778e-06, |
|
"loss": 0.0004, |
|
"step": 8690 |
|
}, |
|
{ |
|
"epoch": 43.01, |
|
"learning_rate": 7.222222222222222e-06, |
|
"loss": 0.0003, |
|
"step": 8700 |
|
}, |
|
{ |
|
"epoch": 43.01, |
|
"learning_rate": 7.166666666666667e-06, |
|
"loss": 0.2055, |
|
"step": 8710 |
|
}, |
|
{ |
|
"epoch": 43.01, |
|
"learning_rate": 7.111111111111112e-06, |
|
"loss": 0.0274, |
|
"step": 8720 |
|
}, |
|
{ |
|
"epoch": 43.01, |
|
"learning_rate": 7.055555555555556e-06, |
|
"loss": 0.0001, |
|
"step": 8730 |
|
}, |
|
{ |
|
"epoch": 43.01, |
|
"learning_rate": 7.000000000000001e-06, |
|
"loss": 0.0001, |
|
"step": 8740 |
|
}, |
|
{ |
|
"epoch": 43.02, |
|
"learning_rate": 6.944444444444445e-06, |
|
"loss": 0.0001, |
|
"step": 8750 |
|
}, |
|
{ |
|
"epoch": 43.02, |
|
"learning_rate": 6.888888888888889e-06, |
|
"loss": 0.0001, |
|
"step": 8760 |
|
}, |
|
{ |
|
"epoch": 43.02, |
|
"learning_rate": 6.833333333333333e-06, |
|
"loss": 0.0001, |
|
"step": 8770 |
|
}, |
|
{ |
|
"epoch": 43.02, |
|
"learning_rate": 6.777777777777779e-06, |
|
"loss": 0.1058, |
|
"step": 8780 |
|
}, |
|
{ |
|
"epoch": 43.02, |
|
"learning_rate": 6.722222222222223e-06, |
|
"loss": 0.0002, |
|
"step": 8790 |
|
}, |
|
{ |
|
"epoch": 43.02, |
|
"learning_rate": 6.666666666666667e-06, |
|
"loss": 0.0001, |
|
"step": 8800 |
|
}, |
|
{ |
|
"epoch": 43.02, |
|
"eval_accuracy": 0.8541666666666666, |
|
"eval_loss": 0.8995665907859802, |
|
"eval_runtime": 12.4764, |
|
"eval_samples_per_second": 3.847, |
|
"eval_steps_per_second": 1.924, |
|
"step": 8800 |
|
}, |
|
{ |
|
"epoch": 44.0, |
|
"learning_rate": 6.611111111111111e-06, |
|
"loss": 0.0001, |
|
"step": 8810 |
|
}, |
|
{ |
|
"epoch": 44.0, |
|
"learning_rate": 6.555555555555556e-06, |
|
"loss": 0.2998, |
|
"step": 8820 |
|
}, |
|
{ |
|
"epoch": 44.0, |
|
"learning_rate": 6.5000000000000004e-06, |
|
"loss": 0.0001, |
|
"step": 8830 |
|
}, |
|
{ |
|
"epoch": 44.0, |
|
"learning_rate": 6.4444444444444445e-06, |
|
"loss": 0.0002, |
|
"step": 8840 |
|
}, |
|
{ |
|
"epoch": 44.01, |
|
"learning_rate": 6.3888888888888885e-06, |
|
"loss": 0.0002, |
|
"step": 8850 |
|
}, |
|
{ |
|
"epoch": 44.01, |
|
"learning_rate": 6.333333333333334e-06, |
|
"loss": 0.0001, |
|
"step": 8860 |
|
}, |
|
{ |
|
"epoch": 44.01, |
|
"learning_rate": 6.277777777777778e-06, |
|
"loss": 0.4396, |
|
"step": 8870 |
|
}, |
|
{ |
|
"epoch": 44.01, |
|
"learning_rate": 6.222222222222222e-06, |
|
"loss": 0.002, |
|
"step": 8880 |
|
}, |
|
{ |
|
"epoch": 44.01, |
|
"learning_rate": 6.166666666666667e-06, |
|
"loss": 0.0002, |
|
"step": 8890 |
|
}, |
|
{ |
|
"epoch": 44.01, |
|
"learning_rate": 6.111111111111111e-06, |
|
"loss": 0.0001, |
|
"step": 8900 |
|
}, |
|
{ |
|
"epoch": 44.01, |
|
"learning_rate": 6.055555555555556e-06, |
|
"loss": 0.0433, |
|
"step": 8910 |
|
}, |
|
{ |
|
"epoch": 44.01, |
|
"learning_rate": 6e-06, |
|
"loss": 0.0002, |
|
"step": 8920 |
|
}, |
|
{ |
|
"epoch": 44.01, |
|
"learning_rate": 5.944444444444445e-06, |
|
"loss": 0.0001, |
|
"step": 8930 |
|
}, |
|
{ |
|
"epoch": 44.01, |
|
"learning_rate": 5.888888888888889e-06, |
|
"loss": 0.0004, |
|
"step": 8940 |
|
}, |
|
{ |
|
"epoch": 44.02, |
|
"learning_rate": 5.833333333333334e-06, |
|
"loss": 0.2249, |
|
"step": 8950 |
|
}, |
|
{ |
|
"epoch": 44.02, |
|
"learning_rate": 5.777777777777778e-06, |
|
"loss": 0.0001, |
|
"step": 8960 |
|
}, |
|
{ |
|
"epoch": 44.02, |
|
"learning_rate": 5.722222222222223e-06, |
|
"loss": 0.0001, |
|
"step": 8970 |
|
}, |
|
{ |
|
"epoch": 44.02, |
|
"learning_rate": 5.666666666666667e-06, |
|
"loss": 0.0, |
|
"step": 8980 |
|
}, |
|
{ |
|
"epoch": 44.02, |
|
"learning_rate": 5.611111111111112e-06, |
|
"loss": 0.0004, |
|
"step": 8990 |
|
}, |
|
{ |
|
"epoch": 44.02, |
|
"learning_rate": 5.555555555555556e-06, |
|
"loss": 0.0067, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 44.02, |
|
"eval_accuracy": 0.8541666666666666, |
|
"eval_loss": 0.7670348286628723, |
|
"eval_runtime": 11.9175, |
|
"eval_samples_per_second": 4.028, |
|
"eval_steps_per_second": 2.014, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 45.0, |
|
"learning_rate": 5.500000000000001e-06, |
|
"loss": 0.0001, |
|
"step": 9010 |
|
}, |
|
{ |
|
"epoch": 45.0, |
|
"learning_rate": 5.444444444444445e-06, |
|
"loss": 0.3147, |
|
"step": 9020 |
|
}, |
|
{ |
|
"epoch": 45.0, |
|
"learning_rate": 5.388888888888889e-06, |
|
"loss": 0.4242, |
|
"step": 9030 |
|
}, |
|
{ |
|
"epoch": 45.0, |
|
"learning_rate": 5.333333333333334e-06, |
|
"loss": 0.0001, |
|
"step": 9040 |
|
}, |
|
{ |
|
"epoch": 45.01, |
|
"learning_rate": 5.277777777777778e-06, |
|
"loss": 0.0403, |
|
"step": 9050 |
|
}, |
|
{ |
|
"epoch": 45.01, |
|
"learning_rate": 5.2222222222222226e-06, |
|
"loss": 0.0006, |
|
"step": 9060 |
|
}, |
|
{ |
|
"epoch": 45.01, |
|
"learning_rate": 5.166666666666667e-06, |
|
"loss": 0.0001, |
|
"step": 9070 |
|
}, |
|
{ |
|
"epoch": 45.01, |
|
"learning_rate": 5.1111111111111115e-06, |
|
"loss": 0.0145, |
|
"step": 9080 |
|
}, |
|
{ |
|
"epoch": 45.01, |
|
"learning_rate": 5.0555555555555555e-06, |
|
"loss": 0.0001, |
|
"step": 9090 |
|
}, |
|
{ |
|
"epoch": 45.01, |
|
"learning_rate": 5e-06, |
|
"loss": 0.2499, |
|
"step": 9100 |
|
}, |
|
{ |
|
"epoch": 45.01, |
|
"learning_rate": 4.9444444444444444e-06, |
|
"loss": 0.4483, |
|
"step": 9110 |
|
}, |
|
{ |
|
"epoch": 45.01, |
|
"learning_rate": 4.888888888888889e-06, |
|
"loss": 0.0001, |
|
"step": 9120 |
|
}, |
|
{ |
|
"epoch": 45.01, |
|
"learning_rate": 4.833333333333333e-06, |
|
"loss": 0.1297, |
|
"step": 9130 |
|
}, |
|
{ |
|
"epoch": 45.01, |
|
"learning_rate": 4.777777777777778e-06, |
|
"loss": 0.0002, |
|
"step": 9140 |
|
}, |
|
{ |
|
"epoch": 45.02, |
|
"learning_rate": 4.722222222222222e-06, |
|
"loss": 0.0001, |
|
"step": 9150 |
|
}, |
|
{ |
|
"epoch": 45.02, |
|
"learning_rate": 4.666666666666667e-06, |
|
"loss": 0.3679, |
|
"step": 9160 |
|
}, |
|
{ |
|
"epoch": 45.02, |
|
"learning_rate": 4.611111111111111e-06, |
|
"loss": 0.0001, |
|
"step": 9170 |
|
}, |
|
{ |
|
"epoch": 45.02, |
|
"learning_rate": 4.555555555555556e-06, |
|
"loss": 0.003, |
|
"step": 9180 |
|
}, |
|
{ |
|
"epoch": 45.02, |
|
"learning_rate": 4.5e-06, |
|
"loss": 0.0014, |
|
"step": 9190 |
|
}, |
|
{ |
|
"epoch": 45.02, |
|
"learning_rate": 4.444444444444445e-06, |
|
"loss": 0.0001, |
|
"step": 9200 |
|
}, |
|
{ |
|
"epoch": 45.02, |
|
"eval_accuracy": 0.8333333333333334, |
|
"eval_loss": 0.9936349987983704, |
|
"eval_runtime": 12.6658, |
|
"eval_samples_per_second": 3.79, |
|
"eval_steps_per_second": 1.895, |
|
"step": 9200 |
|
}, |
|
{ |
|
"epoch": 46.0, |
|
"learning_rate": 4.388888888888889e-06, |
|
"loss": 0.0001, |
|
"step": 9210 |
|
}, |
|
{ |
|
"epoch": 46.0, |
|
"learning_rate": 4.333333333333334e-06, |
|
"loss": 0.0004, |
|
"step": 9220 |
|
}, |
|
{ |
|
"epoch": 46.0, |
|
"learning_rate": 4.277777777777778e-06, |
|
"loss": 0.0003, |
|
"step": 9230 |
|
}, |
|
{ |
|
"epoch": 46.0, |
|
"learning_rate": 4.222222222222223e-06, |
|
"loss": 0.0942, |
|
"step": 9240 |
|
}, |
|
{ |
|
"epoch": 46.01, |
|
"learning_rate": 4.166666666666667e-06, |
|
"loss": 0.0001, |
|
"step": 9250 |
|
}, |
|
{ |
|
"epoch": 46.01, |
|
"learning_rate": 4.111111111111112e-06, |
|
"loss": 0.0001, |
|
"step": 9260 |
|
}, |
|
{ |
|
"epoch": 46.01, |
|
"learning_rate": 4.055555555555556e-06, |
|
"loss": 0.0001, |
|
"step": 9270 |
|
}, |
|
{ |
|
"epoch": 46.01, |
|
"learning_rate": 4.000000000000001e-06, |
|
"loss": 0.0002, |
|
"step": 9280 |
|
}, |
|
{ |
|
"epoch": 46.01, |
|
"learning_rate": 3.944444444444445e-06, |
|
"loss": 0.246, |
|
"step": 9290 |
|
}, |
|
{ |
|
"epoch": 46.01, |
|
"learning_rate": 3.888888888888889e-06, |
|
"loss": 0.0005, |
|
"step": 9300 |
|
}, |
|
{ |
|
"epoch": 46.01, |
|
"learning_rate": 3.833333333333334e-06, |
|
"loss": 0.0001, |
|
"step": 9310 |
|
}, |
|
{ |
|
"epoch": 46.01, |
|
"learning_rate": 3.777777777777778e-06, |
|
"loss": 0.3834, |
|
"step": 9320 |
|
}, |
|
{ |
|
"epoch": 46.01, |
|
"learning_rate": 3.722222222222222e-06, |
|
"loss": 0.0001, |
|
"step": 9330 |
|
}, |
|
{ |
|
"epoch": 46.01, |
|
"learning_rate": 3.666666666666667e-06, |
|
"loss": 0.5107, |
|
"step": 9340 |
|
}, |
|
{ |
|
"epoch": 46.02, |
|
"learning_rate": 3.611111111111111e-06, |
|
"loss": 0.0701, |
|
"step": 9350 |
|
}, |
|
{ |
|
"epoch": 46.02, |
|
"learning_rate": 3.555555555555556e-06, |
|
"loss": 0.0001, |
|
"step": 9360 |
|
}, |
|
{ |
|
"epoch": 46.02, |
|
"learning_rate": 3.5000000000000004e-06, |
|
"loss": 0.0003, |
|
"step": 9370 |
|
}, |
|
{ |
|
"epoch": 46.02, |
|
"learning_rate": 3.4444444444444444e-06, |
|
"loss": 0.0002, |
|
"step": 9380 |
|
}, |
|
{ |
|
"epoch": 46.02, |
|
"learning_rate": 3.3888888888888893e-06, |
|
"loss": 0.003, |
|
"step": 9390 |
|
}, |
|
{ |
|
"epoch": 46.02, |
|
"learning_rate": 3.3333333333333333e-06, |
|
"loss": 0.0638, |
|
"step": 9400 |
|
}, |
|
{ |
|
"epoch": 46.02, |
|
"eval_accuracy": 0.875, |
|
"eval_loss": 0.6616021990776062, |
|
"eval_runtime": 12.2174, |
|
"eval_samples_per_second": 3.929, |
|
"eval_steps_per_second": 1.964, |
|
"step": 9400 |
|
}, |
|
{ |
|
"epoch": 47.0, |
|
"learning_rate": 3.277777777777778e-06, |
|
"loss": 0.0001, |
|
"step": 9410 |
|
}, |
|
{ |
|
"epoch": 47.0, |
|
"learning_rate": 3.2222222222222222e-06, |
|
"loss": 0.0002, |
|
"step": 9420 |
|
}, |
|
{ |
|
"epoch": 47.0, |
|
"learning_rate": 3.166666666666667e-06, |
|
"loss": 0.0002, |
|
"step": 9430 |
|
}, |
|
{ |
|
"epoch": 47.0, |
|
"learning_rate": 3.111111111111111e-06, |
|
"loss": 0.5827, |
|
"step": 9440 |
|
}, |
|
{ |
|
"epoch": 47.01, |
|
"learning_rate": 3.0555555555555556e-06, |
|
"loss": 0.0002, |
|
"step": 9450 |
|
}, |
|
{ |
|
"epoch": 47.01, |
|
"learning_rate": 3e-06, |
|
"loss": 0.0001, |
|
"step": 9460 |
|
}, |
|
{ |
|
"epoch": 47.01, |
|
"learning_rate": 2.9444444444444445e-06, |
|
"loss": 0.0264, |
|
"step": 9470 |
|
}, |
|
{ |
|
"epoch": 47.01, |
|
"learning_rate": 2.888888888888889e-06, |
|
"loss": 0.0001, |
|
"step": 9480 |
|
}, |
|
{ |
|
"epoch": 47.01, |
|
"learning_rate": 2.8333333333333335e-06, |
|
"loss": 0.0001, |
|
"step": 9490 |
|
}, |
|
{ |
|
"epoch": 47.01, |
|
"learning_rate": 2.777777777777778e-06, |
|
"loss": 0.0001, |
|
"step": 9500 |
|
}, |
|
{ |
|
"epoch": 47.01, |
|
"learning_rate": 2.7222222222222224e-06, |
|
"loss": 0.0391, |
|
"step": 9510 |
|
}, |
|
{ |
|
"epoch": 47.01, |
|
"learning_rate": 2.666666666666667e-06, |
|
"loss": 0.0001, |
|
"step": 9520 |
|
}, |
|
{ |
|
"epoch": 47.01, |
|
"learning_rate": 2.6111111111111113e-06, |
|
"loss": 0.0001, |
|
"step": 9530 |
|
}, |
|
{ |
|
"epoch": 47.01, |
|
"learning_rate": 2.5555555555555557e-06, |
|
"loss": 0.3777, |
|
"step": 9540 |
|
}, |
|
{ |
|
"epoch": 47.02, |
|
"learning_rate": 2.5e-06, |
|
"loss": 0.0001, |
|
"step": 9550 |
|
}, |
|
{ |
|
"epoch": 47.02, |
|
"learning_rate": 2.4444444444444447e-06, |
|
"loss": 0.0001, |
|
"step": 9560 |
|
}, |
|
{ |
|
"epoch": 47.02, |
|
"learning_rate": 2.388888888888889e-06, |
|
"loss": 0.0002, |
|
"step": 9570 |
|
}, |
|
{ |
|
"epoch": 47.02, |
|
"learning_rate": 2.3333333333333336e-06, |
|
"loss": 0.085, |
|
"step": 9580 |
|
}, |
|
{ |
|
"epoch": 47.02, |
|
"learning_rate": 2.277777777777778e-06, |
|
"loss": 0.0001, |
|
"step": 9590 |
|
}, |
|
{ |
|
"epoch": 47.02, |
|
"learning_rate": 2.2222222222222225e-06, |
|
"loss": 0.0001, |
|
"step": 9600 |
|
}, |
|
{ |
|
"epoch": 47.02, |
|
"eval_accuracy": 0.8541666666666666, |
|
"eval_loss": 0.7978042960166931, |
|
"eval_runtime": 12.8106, |
|
"eval_samples_per_second": 3.747, |
|
"eval_steps_per_second": 1.873, |
|
"step": 9600 |
|
}, |
|
{ |
|
"epoch": 48.0, |
|
"learning_rate": 2.166666666666667e-06, |
|
"loss": 0.599, |
|
"step": 9610 |
|
}, |
|
{ |
|
"epoch": 48.0, |
|
"learning_rate": 2.1111111111111114e-06, |
|
"loss": 0.0017, |
|
"step": 9620 |
|
}, |
|
{ |
|
"epoch": 48.0, |
|
"learning_rate": 2.055555555555556e-06, |
|
"loss": 0.0003, |
|
"step": 9630 |
|
}, |
|
{ |
|
"epoch": 48.0, |
|
"learning_rate": 2.0000000000000003e-06, |
|
"loss": 0.0001, |
|
"step": 9640 |
|
}, |
|
{ |
|
"epoch": 48.01, |
|
"learning_rate": 1.9444444444444444e-06, |
|
"loss": 0.0001, |
|
"step": 9650 |
|
}, |
|
{ |
|
"epoch": 48.01, |
|
"learning_rate": 1.888888888888889e-06, |
|
"loss": 0.0001, |
|
"step": 9660 |
|
}, |
|
{ |
|
"epoch": 48.01, |
|
"learning_rate": 1.8333333333333335e-06, |
|
"loss": 0.0001, |
|
"step": 9670 |
|
}, |
|
{ |
|
"epoch": 48.01, |
|
"learning_rate": 1.777777777777778e-06, |
|
"loss": 0.2912, |
|
"step": 9680 |
|
}, |
|
{ |
|
"epoch": 48.01, |
|
"learning_rate": 1.7222222222222222e-06, |
|
"loss": 0.0001, |
|
"step": 9690 |
|
}, |
|
{ |
|
"epoch": 48.01, |
|
"learning_rate": 1.6666666666666667e-06, |
|
"loss": 0.0001, |
|
"step": 9700 |
|
}, |
|
{ |
|
"epoch": 48.01, |
|
"learning_rate": 1.6111111111111111e-06, |
|
"loss": 0.0001, |
|
"step": 9710 |
|
}, |
|
{ |
|
"epoch": 48.01, |
|
"learning_rate": 1.5555555555555556e-06, |
|
"loss": 0.0193, |
|
"step": 9720 |
|
}, |
|
{ |
|
"epoch": 48.01, |
|
"learning_rate": 1.5e-06, |
|
"loss": 0.0002, |
|
"step": 9730 |
|
}, |
|
{ |
|
"epoch": 48.01, |
|
"learning_rate": 1.4444444444444445e-06, |
|
"loss": 0.0, |
|
"step": 9740 |
|
}, |
|
{ |
|
"epoch": 48.02, |
|
"learning_rate": 1.388888888888889e-06, |
|
"loss": 0.3547, |
|
"step": 9750 |
|
}, |
|
{ |
|
"epoch": 48.02, |
|
"learning_rate": 1.3333333333333334e-06, |
|
"loss": 0.0001, |
|
"step": 9760 |
|
}, |
|
{ |
|
"epoch": 48.02, |
|
"learning_rate": 1.2777777777777779e-06, |
|
"loss": 0.0001, |
|
"step": 9770 |
|
}, |
|
{ |
|
"epoch": 48.02, |
|
"learning_rate": 1.2222222222222223e-06, |
|
"loss": 0.0001, |
|
"step": 9780 |
|
}, |
|
{ |
|
"epoch": 48.02, |
|
"learning_rate": 1.1666666666666668e-06, |
|
"loss": 0.0132, |
|
"step": 9790 |
|
}, |
|
{ |
|
"epoch": 48.02, |
|
"learning_rate": 1.1111111111111112e-06, |
|
"loss": 0.0001, |
|
"step": 9800 |
|
}, |
|
{ |
|
"epoch": 48.02, |
|
"eval_accuracy": 0.8541666666666666, |
|
"eval_loss": 0.6736838817596436, |
|
"eval_runtime": 12.1656, |
|
"eval_samples_per_second": 3.946, |
|
"eval_steps_per_second": 1.973, |
|
"step": 9800 |
|
}, |
|
{ |
|
"epoch": 49.0, |
|
"learning_rate": 1.0555555555555557e-06, |
|
"loss": 0.0001, |
|
"step": 9810 |
|
}, |
|
{ |
|
"epoch": 49.0, |
|
"learning_rate": 1.0000000000000002e-06, |
|
"loss": 0.0, |
|
"step": 9820 |
|
}, |
|
{ |
|
"epoch": 49.0, |
|
"learning_rate": 9.444444444444445e-07, |
|
"loss": 0.0001, |
|
"step": 9830 |
|
}, |
|
{ |
|
"epoch": 49.0, |
|
"learning_rate": 8.88888888888889e-07, |
|
"loss": 0.119, |
|
"step": 9840 |
|
}, |
|
{ |
|
"epoch": 49.01, |
|
"learning_rate": 8.333333333333333e-07, |
|
"loss": 0.0002, |
|
"step": 9850 |
|
}, |
|
{ |
|
"epoch": 49.01, |
|
"learning_rate": 7.777777777777778e-07, |
|
"loss": 0.0001, |
|
"step": 9860 |
|
}, |
|
{ |
|
"epoch": 49.01, |
|
"learning_rate": 7.222222222222222e-07, |
|
"loss": 0.0028, |
|
"step": 9870 |
|
}, |
|
{ |
|
"epoch": 49.01, |
|
"learning_rate": 6.666666666666667e-07, |
|
"loss": 0.0001, |
|
"step": 9880 |
|
}, |
|
{ |
|
"epoch": 49.01, |
|
"learning_rate": 6.111111111111112e-07, |
|
"loss": 0.0001, |
|
"step": 9890 |
|
}, |
|
{ |
|
"epoch": 49.01, |
|
"learning_rate": 5.555555555555556e-07, |
|
"loss": 0.366, |
|
"step": 9900 |
|
}, |
|
{ |
|
"epoch": 49.01, |
|
"learning_rate": 5.000000000000001e-07, |
|
"loss": 0.4115, |
|
"step": 9910 |
|
}, |
|
{ |
|
"epoch": 49.01, |
|
"learning_rate": 4.444444444444445e-07, |
|
"loss": 0.0, |
|
"step": 9920 |
|
}, |
|
{ |
|
"epoch": 49.01, |
|
"learning_rate": 3.888888888888889e-07, |
|
"loss": 0.0001, |
|
"step": 9930 |
|
}, |
|
{ |
|
"epoch": 49.01, |
|
"learning_rate": 3.3333333333333335e-07, |
|
"loss": 0.1473, |
|
"step": 9940 |
|
}, |
|
{ |
|
"epoch": 49.02, |
|
"learning_rate": 2.777777777777778e-07, |
|
"loss": 0.0, |
|
"step": 9950 |
|
}, |
|
{ |
|
"epoch": 49.02, |
|
"learning_rate": 2.2222222222222224e-07, |
|
"loss": 0.0, |
|
"step": 9960 |
|
}, |
|
{ |
|
"epoch": 49.02, |
|
"learning_rate": 1.6666666666666668e-07, |
|
"loss": 0.0001, |
|
"step": 9970 |
|
}, |
|
{ |
|
"epoch": 49.02, |
|
"learning_rate": 1.1111111111111112e-07, |
|
"loss": 0.0001, |
|
"step": 9980 |
|
}, |
|
{ |
|
"epoch": 49.02, |
|
"learning_rate": 5.555555555555556e-08, |
|
"loss": 0.0049, |
|
"step": 9990 |
|
}, |
|
{ |
|
"epoch": 49.02, |
|
"learning_rate": 0.0, |
|
"loss": 0.0001, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 49.02, |
|
"eval_accuracy": 0.875, |
|
"eval_loss": 0.5887275338172913, |
|
"eval_runtime": 12.575, |
|
"eval_samples_per_second": 3.817, |
|
"eval_steps_per_second": 1.909, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 49.02, |
|
"step": 10000, |
|
"total_flos": 2.492129178943488e+19, |
|
"train_loss": 0.3473788271739875, |
|
"train_runtime": 6088.9476, |
|
"train_samples_per_second": 3.285, |
|
"train_steps_per_second": 1.642 |
|
}, |
|
{ |
|
"epoch": 49.02, |
|
"eval_accuracy": 0.9166666666666666, |
|
"eval_loss": 0.591888427734375, |
|
"eval_runtime": 48.9212, |
|
"eval_samples_per_second": 0.981, |
|
"eval_steps_per_second": 0.491, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 49.02, |
|
"eval_accuracy": 0.9375, |
|
"eval_loss": 0.30889856815338135, |
|
"eval_runtime": 12.2829, |
|
"eval_samples_per_second": 3.908, |
|
"eval_steps_per_second": 1.954, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 49.02, |
|
"eval_accuracy": 0.965, |
|
"eval_loss": 0.17441120743751526, |
|
"eval_runtime": 62.983, |
|
"eval_samples_per_second": 6.351, |
|
"eval_steps_per_second": 3.175, |
|
"step": 10000 |
|
} |
|
], |
|
"max_steps": 10000, |
|
"num_train_epochs": 9223372036854775807, |
|
"total_flos": 2.492129178943488e+19, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|