| { |
| "best_metric": 0.0, |
| "best_model_checkpoint": "outputs/bitfit/t5-base/mrpc/checkpoint-200", |
| "epoch": 20.0, |
| "global_step": 1160, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.17, |
| "learning_rate": 0.00029741379310344827, |
| "loss": 2.2211, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 0.0002948275862068965, |
| "loss": 0.194, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 0.0002922413793103448, |
| "loss": 0.1031, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.69, |
| "learning_rate": 0.0002896551724137931, |
| "loss": 0.121, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.86, |
| "learning_rate": 0.0002870689655172413, |
| "loss": 0.1258, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.03, |
| "learning_rate": 0.0002844827586206896, |
| "loss": 0.0988, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.21, |
| "learning_rate": 0.0002818965517241379, |
| "loss": 0.0688, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.38, |
| "learning_rate": 0.0002793103448275862, |
| "loss": 0.081, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.55, |
| "learning_rate": 0.0002767241379310345, |
| "loss": 0.0719, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.72, |
| "learning_rate": 0.0002741379310344827, |
| "loss": 0.0606, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.72, |
| "eval_accuracy": 0.0, |
| "eval_average_metrics": 0.0, |
| "eval_f1": 0.0, |
| "eval_loss": 0.157722607254982, |
| "eval_runtime": 1.6787, |
| "eval_samples_per_second": 121.522, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.9, |
| "learning_rate": 0.000271551724137931, |
| "loss": 0.0726, |
| "step": 110 |
| }, |
| { |
| "epoch": 2.07, |
| "learning_rate": 0.0002689655172413793, |
| "loss": 0.0686, |
| "step": 120 |
| }, |
| { |
| "epoch": 2.24, |
| "learning_rate": 0.0002663793103448276, |
| "loss": 0.0445, |
| "step": 130 |
| }, |
| { |
| "epoch": 2.41, |
| "learning_rate": 0.00026379310344827584, |
| "loss": 0.0414, |
| "step": 140 |
| }, |
| { |
| "epoch": 2.59, |
| "learning_rate": 0.00026120689655172413, |
| "loss": 0.0431, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.76, |
| "learning_rate": 0.00025862068965517237, |
| "loss": 0.0274, |
| "step": 160 |
| }, |
| { |
| "epoch": 2.93, |
| "learning_rate": 0.00025603448275862066, |
| "loss": 0.0399, |
| "step": 170 |
| }, |
| { |
| "epoch": 3.1, |
| "learning_rate": 0.00025344827586206895, |
| "loss": 0.032, |
| "step": 180 |
| }, |
| { |
| "epoch": 3.28, |
| "learning_rate": 0.0002508620689655172, |
| "loss": 0.0163, |
| "step": 190 |
| }, |
| { |
| "epoch": 3.45, |
| "learning_rate": 0.0002482758620689655, |
| "loss": 0.0196, |
| "step": 200 |
| }, |
| { |
| "epoch": 3.45, |
| "eval_accuracy": 0.0, |
| "eval_average_metrics": 0.0, |
| "eval_f1": 0.0, |
| "eval_loss": 0.20416393876075745, |
| "eval_runtime": 1.3232, |
| "eval_samples_per_second": 154.176, |
| "step": 200 |
| }, |
| { |
| "epoch": 3.62, |
| "learning_rate": 0.00024568965517241377, |
| "loss": 0.0236, |
| "step": 210 |
| }, |
| { |
| "epoch": 3.79, |
| "learning_rate": 0.00024310344827586203, |
| "loss": 0.0354, |
| "step": 220 |
| }, |
| { |
| "epoch": 3.97, |
| "learning_rate": 0.00024051724137931033, |
| "loss": 0.0277, |
| "step": 230 |
| }, |
| { |
| "epoch": 4.14, |
| "learning_rate": 0.00023793103448275862, |
| "loss": 0.0194, |
| "step": 240 |
| }, |
| { |
| "epoch": 4.31, |
| "learning_rate": 0.00023534482758620685, |
| "loss": 0.0153, |
| "step": 250 |
| }, |
| { |
| "epoch": 4.48, |
| "learning_rate": 0.00023275862068965515, |
| "loss": 0.0129, |
| "step": 260 |
| }, |
| { |
| "epoch": 4.66, |
| "learning_rate": 0.00023017241379310344, |
| "loss": 0.0112, |
| "step": 270 |
| }, |
| { |
| "epoch": 4.83, |
| "learning_rate": 0.0002275862068965517, |
| "loss": 0.0083, |
| "step": 280 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 0.000225, |
| "loss": 0.0167, |
| "step": 290 |
| }, |
| { |
| "epoch": 5.17, |
| "learning_rate": 0.00022241379310344826, |
| "loss": 0.0184, |
| "step": 300 |
| }, |
| { |
| "epoch": 5.17, |
| "eval_accuracy": 0.0, |
| "eval_average_metrics": 0.0, |
| "eval_f1": 0.0, |
| "eval_loss": 0.2221006453037262, |
| "eval_runtime": 1.4478, |
| "eval_samples_per_second": 140.908, |
| "step": 300 |
| }, |
| { |
| "epoch": 5.34, |
| "learning_rate": 0.00021982758620689652, |
| "loss": 0.0053, |
| "step": 310 |
| }, |
| { |
| "epoch": 5.52, |
| "learning_rate": 0.00021724137931034481, |
| "loss": 0.0049, |
| "step": 320 |
| }, |
| { |
| "epoch": 5.69, |
| "learning_rate": 0.0002146551724137931, |
| "loss": 0.0096, |
| "step": 330 |
| }, |
| { |
| "epoch": 5.86, |
| "learning_rate": 0.00021206896551724134, |
| "loss": 0.008, |
| "step": 340 |
| }, |
| { |
| "epoch": 6.03, |
| "learning_rate": 0.00020948275862068963, |
| "loss": 0.0099, |
| "step": 350 |
| }, |
| { |
| "epoch": 6.21, |
| "learning_rate": 0.00020689655172413793, |
| "loss": 0.0128, |
| "step": 360 |
| }, |
| { |
| "epoch": 6.38, |
| "learning_rate": 0.0002043103448275862, |
| "loss": 0.0026, |
| "step": 370 |
| }, |
| { |
| "epoch": 6.55, |
| "learning_rate": 0.00020172413793103448, |
| "loss": 0.002, |
| "step": 380 |
| }, |
| { |
| "epoch": 6.72, |
| "learning_rate": 0.00019913793103448275, |
| "loss": 0.0062, |
| "step": 390 |
| }, |
| { |
| "epoch": 6.9, |
| "learning_rate": 0.000196551724137931, |
| "loss": 0.0099, |
| "step": 400 |
| }, |
| { |
| "epoch": 6.9, |
| "eval_accuracy": 0.0, |
| "eval_average_metrics": 0.0, |
| "eval_f1": 0.0, |
| "eval_loss": 0.24928051233291626, |
| "eval_runtime": 1.0803, |
| "eval_samples_per_second": 188.836, |
| "step": 400 |
| }, |
| { |
| "epoch": 7.07, |
| "learning_rate": 0.0001939655172413793, |
| "loss": 0.0138, |
| "step": 410 |
| }, |
| { |
| "epoch": 7.24, |
| "learning_rate": 0.0001913793103448276, |
| "loss": 0.0016, |
| "step": 420 |
| }, |
| { |
| "epoch": 7.41, |
| "learning_rate": 0.00018879310344827583, |
| "loss": 0.0044, |
| "step": 430 |
| }, |
| { |
| "epoch": 7.59, |
| "learning_rate": 0.00018620689655172412, |
| "loss": 0.0039, |
| "step": 440 |
| }, |
| { |
| "epoch": 7.76, |
| "learning_rate": 0.0001836206896551724, |
| "loss": 0.0063, |
| "step": 450 |
| }, |
| { |
| "epoch": 7.93, |
| "learning_rate": 0.00018103448275862068, |
| "loss": 0.0076, |
| "step": 460 |
| }, |
| { |
| "epoch": 8.1, |
| "learning_rate": 0.00017844827586206897, |
| "loss": 0.005, |
| "step": 470 |
| }, |
| { |
| "epoch": 8.28, |
| "learning_rate": 0.0001758620689655172, |
| "loss": 0.0018, |
| "step": 480 |
| }, |
| { |
| "epoch": 8.45, |
| "learning_rate": 0.0001732758620689655, |
| "loss": 0.0033, |
| "step": 490 |
| }, |
| { |
| "epoch": 8.62, |
| "learning_rate": 0.0001706896551724138, |
| "loss": 0.0049, |
| "step": 500 |
| }, |
| { |
| "epoch": 8.62, |
| "eval_accuracy": 0.0, |
| "eval_average_metrics": 0.0, |
| "eval_f1": 0.0, |
| "eval_loss": 0.26071295142173767, |
| "eval_runtime": 1.6002, |
| "eval_samples_per_second": 127.481, |
| "step": 500 |
| }, |
| { |
| "epoch": 8.79, |
| "learning_rate": 0.00016810344827586203, |
| "loss": 0.0027, |
| "step": 510 |
| }, |
| { |
| "epoch": 8.97, |
| "learning_rate": 0.00016551724137931032, |
| "loss": 0.0052, |
| "step": 520 |
| }, |
| { |
| "epoch": 9.14, |
| "learning_rate": 0.0001629310344827586, |
| "loss": 0.0003, |
| "step": 530 |
| }, |
| { |
| "epoch": 9.31, |
| "learning_rate": 0.00016034482758620688, |
| "loss": 0.0017, |
| "step": 540 |
| }, |
| { |
| "epoch": 9.48, |
| "learning_rate": 0.00015775862068965517, |
| "loss": 0.0016, |
| "step": 550 |
| }, |
| { |
| "epoch": 9.66, |
| "learning_rate": 0.00015517241379310346, |
| "loss": 0.0037, |
| "step": 560 |
| }, |
| { |
| "epoch": 9.83, |
| "learning_rate": 0.0001525862068965517, |
| "loss": 0.0008, |
| "step": 570 |
| }, |
| { |
| "epoch": 10.0, |
| "learning_rate": 0.00015, |
| "loss": 0.0065, |
| "step": 580 |
| }, |
| { |
| "epoch": 10.17, |
| "learning_rate": 0.00014741379310344825, |
| "loss": 0.0005, |
| "step": 590 |
| }, |
| { |
| "epoch": 10.34, |
| "learning_rate": 0.00014482758620689654, |
| "loss": 0.0012, |
| "step": 600 |
| }, |
| { |
| "epoch": 10.34, |
| "eval_accuracy": 0.0, |
| "eval_average_metrics": 0.0, |
| "eval_f1": 0.0, |
| "eval_loss": 0.3229135274887085, |
| "eval_runtime": 1.6354, |
| "eval_samples_per_second": 124.74, |
| "step": 600 |
| }, |
| { |
| "epoch": 10.52, |
| "learning_rate": 0.0001422413793103448, |
| "loss": 0.0015, |
| "step": 610 |
| }, |
| { |
| "epoch": 10.69, |
| "learning_rate": 0.0001396551724137931, |
| "loss": 0.0031, |
| "step": 620 |
| }, |
| { |
| "epoch": 10.86, |
| "learning_rate": 0.00013706896551724136, |
| "loss": 0.009, |
| "step": 630 |
| }, |
| { |
| "epoch": 11.03, |
| "learning_rate": 0.00013448275862068965, |
| "loss": 0.0008, |
| "step": 640 |
| }, |
| { |
| "epoch": 11.21, |
| "learning_rate": 0.00013189655172413792, |
| "loss": 0.0002, |
| "step": 650 |
| }, |
| { |
| "epoch": 11.38, |
| "learning_rate": 0.00012931034482758618, |
| "loss": 0.0002, |
| "step": 660 |
| }, |
| { |
| "epoch": 11.55, |
| "learning_rate": 0.00012672413793103447, |
| "loss": 0.004, |
| "step": 670 |
| }, |
| { |
| "epoch": 11.72, |
| "learning_rate": 0.00012413793103448274, |
| "loss": 0.004, |
| "step": 680 |
| }, |
| { |
| "epoch": 11.9, |
| "learning_rate": 0.00012155172413793102, |
| "loss": 0.0005, |
| "step": 690 |
| }, |
| { |
| "epoch": 12.07, |
| "learning_rate": 0.00011896551724137931, |
| "loss": 0.003, |
| "step": 700 |
| }, |
| { |
| "epoch": 12.07, |
| "eval_accuracy": 0.0, |
| "eval_average_metrics": 0.0, |
| "eval_f1": 0.0, |
| "eval_loss": 0.3359452784061432, |
| "eval_runtime": 1.9034, |
| "eval_samples_per_second": 107.177, |
| "step": 700 |
| }, |
| { |
| "epoch": 12.24, |
| "learning_rate": 0.00011637931034482757, |
| "loss": 0.0005, |
| "step": 710 |
| }, |
| { |
| "epoch": 12.41, |
| "learning_rate": 0.00011379310344827585, |
| "loss": 0.0002, |
| "step": 720 |
| }, |
| { |
| "epoch": 12.59, |
| "learning_rate": 0.00011120689655172413, |
| "loss": 0.0001, |
| "step": 730 |
| }, |
| { |
| "epoch": 12.76, |
| "learning_rate": 0.00010862068965517241, |
| "loss": 0.0024, |
| "step": 740 |
| }, |
| { |
| "epoch": 12.93, |
| "learning_rate": 0.00010603448275862067, |
| "loss": 0.0002, |
| "step": 750 |
| }, |
| { |
| "epoch": 13.1, |
| "learning_rate": 0.00010344827586206896, |
| "loss": 0.0003, |
| "step": 760 |
| }, |
| { |
| "epoch": 13.28, |
| "learning_rate": 0.00010086206896551724, |
| "loss": 0.0007, |
| "step": 770 |
| }, |
| { |
| "epoch": 13.45, |
| "learning_rate": 9.82758620689655e-05, |
| "loss": 0.0, |
| "step": 780 |
| }, |
| { |
| "epoch": 13.62, |
| "learning_rate": 9.56896551724138e-05, |
| "loss": 0.0001, |
| "step": 790 |
| }, |
| { |
| "epoch": 13.79, |
| "learning_rate": 9.310344827586206e-05, |
| "loss": 0.0003, |
| "step": 800 |
| }, |
| { |
| "epoch": 13.79, |
| "eval_accuracy": 0.0, |
| "eval_average_metrics": 0.0, |
| "eval_f1": 0.0, |
| "eval_loss": 0.40144264698028564, |
| "eval_runtime": 1.2399, |
| "eval_samples_per_second": 164.525, |
| "step": 800 |
| }, |
| { |
| "epoch": 13.97, |
| "learning_rate": 9.051724137931034e-05, |
| "loss": 0.003, |
| "step": 810 |
| }, |
| { |
| "epoch": 14.14, |
| "learning_rate": 8.79310344827586e-05, |
| "loss": 0.0, |
| "step": 820 |
| }, |
| { |
| "epoch": 14.31, |
| "learning_rate": 8.53448275862069e-05, |
| "loss": 0.0004, |
| "step": 830 |
| }, |
| { |
| "epoch": 14.48, |
| "learning_rate": 8.275862068965516e-05, |
| "loss": 0.0001, |
| "step": 840 |
| }, |
| { |
| "epoch": 14.66, |
| "learning_rate": 8.017241379310344e-05, |
| "loss": 0.0001, |
| "step": 850 |
| }, |
| { |
| "epoch": 14.83, |
| "learning_rate": 7.758620689655173e-05, |
| "loss": 0.0008, |
| "step": 860 |
| }, |
| { |
| "epoch": 15.0, |
| "learning_rate": 7.5e-05, |
| "loss": 0.0001, |
| "step": 870 |
| }, |
| { |
| "epoch": 15.17, |
| "learning_rate": 7.241379310344827e-05, |
| "loss": 0.0001, |
| "step": 880 |
| }, |
| { |
| "epoch": 15.34, |
| "learning_rate": 6.982758620689655e-05, |
| "loss": 0.0018, |
| "step": 890 |
| }, |
| { |
| "epoch": 15.52, |
| "learning_rate": 6.724137931034483e-05, |
| "loss": 0.0001, |
| "step": 900 |
| }, |
| { |
| "epoch": 15.52, |
| "eval_accuracy": 0.0, |
| "eval_average_metrics": 0.0, |
| "eval_f1": 0.0, |
| "eval_loss": 0.37248921394348145, |
| "eval_runtime": 1.2617, |
| "eval_samples_per_second": 161.691, |
| "step": 900 |
| }, |
| { |
| "epoch": 15.69, |
| "learning_rate": 6.465517241379309e-05, |
| "loss": 0.0, |
| "step": 910 |
| }, |
| { |
| "epoch": 15.86, |
| "learning_rate": 6.206896551724137e-05, |
| "loss": 0.0, |
| "step": 920 |
| }, |
| { |
| "epoch": 16.03, |
| "learning_rate": 5.9482758620689654e-05, |
| "loss": 0.0001, |
| "step": 930 |
| }, |
| { |
| "epoch": 16.21, |
| "learning_rate": 5.6896551724137926e-05, |
| "loss": 0.0007, |
| "step": 940 |
| }, |
| { |
| "epoch": 16.38, |
| "learning_rate": 5.4310344827586204e-05, |
| "loss": 0.0, |
| "step": 950 |
| }, |
| { |
| "epoch": 16.55, |
| "learning_rate": 5.172413793103448e-05, |
| "loss": 0.0, |
| "step": 960 |
| }, |
| { |
| "epoch": 16.72, |
| "learning_rate": 4.913793103448275e-05, |
| "loss": 0.0, |
| "step": 970 |
| }, |
| { |
| "epoch": 16.9, |
| "learning_rate": 4.655172413793103e-05, |
| "loss": 0.0001, |
| "step": 980 |
| }, |
| { |
| "epoch": 17.07, |
| "learning_rate": 4.39655172413793e-05, |
| "loss": 0.0, |
| "step": 990 |
| }, |
| { |
| "epoch": 17.24, |
| "learning_rate": 4.137931034482758e-05, |
| "loss": 0.0001, |
| "step": 1000 |
| }, |
| { |
| "epoch": 17.24, |
| "eval_accuracy": 0.0, |
| "eval_average_metrics": 0.0, |
| "eval_f1": 0.0, |
| "eval_loss": 0.38377830386161804, |
| "eval_runtime": 1.3412, |
| "eval_samples_per_second": 152.099, |
| "step": 1000 |
| }, |
| { |
| "epoch": 17.41, |
| "learning_rate": 3.8793103448275865e-05, |
| "loss": 0.0, |
| "step": 1010 |
| }, |
| { |
| "epoch": 17.59, |
| "learning_rate": 3.6206896551724136e-05, |
| "loss": 0.0, |
| "step": 1020 |
| }, |
| { |
| "epoch": 17.76, |
| "learning_rate": 3.3620689655172414e-05, |
| "loss": 0.0001, |
| "step": 1030 |
| }, |
| { |
| "epoch": 17.93, |
| "learning_rate": 3.1034482758620685e-05, |
| "loss": 0.0004, |
| "step": 1040 |
| }, |
| { |
| "epoch": 18.1, |
| "learning_rate": 2.8448275862068963e-05, |
| "loss": 0.0, |
| "step": 1050 |
| }, |
| { |
| "epoch": 18.28, |
| "learning_rate": 2.586206896551724e-05, |
| "loss": 0.0001, |
| "step": 1060 |
| }, |
| { |
| "epoch": 18.45, |
| "learning_rate": 2.3275862068965515e-05, |
| "loss": 0.0002, |
| "step": 1070 |
| }, |
| { |
| "epoch": 18.62, |
| "learning_rate": 2.068965517241379e-05, |
| "loss": 0.0, |
| "step": 1080 |
| }, |
| { |
| "epoch": 18.79, |
| "learning_rate": 1.8103448275862068e-05, |
| "loss": 0.0, |
| "step": 1090 |
| }, |
| { |
| "epoch": 18.97, |
| "learning_rate": 1.5517241379310342e-05, |
| "loss": 0.0, |
| "step": 1100 |
| }, |
| { |
| "epoch": 18.97, |
| "eval_accuracy": 0.0, |
| "eval_average_metrics": 0.0, |
| "eval_f1": 0.0, |
| "eval_loss": 0.4036322236061096, |
| "eval_runtime": 1.3625, |
| "eval_samples_per_second": 149.728, |
| "step": 1100 |
| }, |
| { |
| "epoch": 19.14, |
| "learning_rate": 1.293103448275862e-05, |
| "loss": 0.0, |
| "step": 1110 |
| }, |
| { |
| "epoch": 19.31, |
| "learning_rate": 1.0344827586206895e-05, |
| "loss": 0.0, |
| "step": 1120 |
| }, |
| { |
| "epoch": 19.48, |
| "learning_rate": 7.758620689655171e-06, |
| "loss": 0.0, |
| "step": 1130 |
| }, |
| { |
| "epoch": 19.66, |
| "learning_rate": 5.1724137931034475e-06, |
| "loss": 0.0, |
| "step": 1140 |
| }, |
| { |
| "epoch": 19.83, |
| "learning_rate": 2.5862068965517237e-06, |
| "loss": 0.0001, |
| "step": 1150 |
| }, |
| { |
| "epoch": 20.0, |
| "learning_rate": 0.0, |
| "loss": 0.0001, |
| "step": 1160 |
| }, |
| { |
| "epoch": 20.0, |
| "step": 1160, |
| "total_flos": 9652606012532736.0, |
| "train_loss": 0.03386630766055595, |
| "train_runtime": 583.9583, |
| "train_samples_per_second": 125.625, |
| "train_steps_per_second": 1.986 |
| } |
| ], |
| "max_steps": 1160, |
| "num_train_epochs": 20, |
| "total_flos": 9652606012532736.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
