|
{ |
|
"best_metric": 0.9925, |
|
"best_model_checkpoint": "./BeiT/checkpoint-3058", |
|
"epoch": 22.0, |
|
"eval_steps": 500, |
|
"global_step": 3058, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 4.796163069544365e-07, |
|
"loss": 1.3973, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 9.59232613908873e-07, |
|
"loss": 1.3593, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 1.4388489208633094e-06, |
|
"loss": 1.2572, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 1.918465227817746e-06, |
|
"loss": 1.1821, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 2.3980815347721824e-06, |
|
"loss": 1.0659, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 2.877697841726619e-06, |
|
"loss": 0.926, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 3.3573141486810557e-06, |
|
"loss": 0.8208, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 3.836930455635492e-06, |
|
"loss": 0.7399, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 4.316546762589928e-06, |
|
"loss": 0.7633, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 4.796163069544365e-06, |
|
"loss": 0.7109, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 5.275779376498802e-06, |
|
"loss": 0.6965, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 5.755395683453238e-06, |
|
"loss": 0.6409, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 6.2350119904076745e-06, |
|
"loss": 0.6413, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.74, |
|
"eval_loss": 0.6694741249084473, |
|
"eval_runtime": 7.2563, |
|
"eval_samples_per_second": 55.124, |
|
"eval_steps_per_second": 3.445, |
|
"step": 139 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 6.714628297362111e-06, |
|
"loss": 0.6174, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 7.194244604316547e-06, |
|
"loss": 0.5881, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 7.673860911270984e-06, |
|
"loss": 0.5689, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"learning_rate": 8.153477218225421e-06, |
|
"loss": 0.5596, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 8.633093525179856e-06, |
|
"loss": 0.5571, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 1.37, |
|
"learning_rate": 9.112709832134293e-06, |
|
"loss": 0.4756, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 9.59232613908873e-06, |
|
"loss": 0.4701, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 1.51, |
|
"learning_rate": 1.0071942446043167e-05, |
|
"loss": 0.4945, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 1.58, |
|
"learning_rate": 1.0551558752997603e-05, |
|
"loss": 0.4683, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 1.65, |
|
"learning_rate": 1.103117505995204e-05, |
|
"loss": 0.4497, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 1.73, |
|
"learning_rate": 1.1510791366906475e-05, |
|
"loss": 0.4282, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 1.8, |
|
"learning_rate": 1.1990407673860914e-05, |
|
"loss": 0.3876, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 1.87, |
|
"learning_rate": 1.2470023980815349e-05, |
|
"loss": 0.3782, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 1.94, |
|
"learning_rate": 1.2949640287769784e-05, |
|
"loss": 0.391, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.8575, |
|
"eval_loss": 0.37282153964042664, |
|
"eval_runtime": 6.8753, |
|
"eval_samples_per_second": 58.18, |
|
"eval_steps_per_second": 3.636, |
|
"step": 278 |
|
}, |
|
{ |
|
"epoch": 2.01, |
|
"learning_rate": 1.3429256594724223e-05, |
|
"loss": 0.3699, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 2.09, |
|
"learning_rate": 1.3908872901678658e-05, |
|
"loss": 0.3421, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 2.16, |
|
"learning_rate": 1.4388489208633095e-05, |
|
"loss": 0.3257, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 2.23, |
|
"learning_rate": 1.4868105515587531e-05, |
|
"loss": 0.2969, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 2.3, |
|
"learning_rate": 1.534772182254197e-05, |
|
"loss": 0.2498, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 2.37, |
|
"learning_rate": 1.5827338129496403e-05, |
|
"loss": 0.2428, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 2.45, |
|
"learning_rate": 1.6306954436450842e-05, |
|
"loss": 0.2272, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 2.52, |
|
"learning_rate": 1.6786570743405277e-05, |
|
"loss": 0.267, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 2.59, |
|
"learning_rate": 1.7266187050359712e-05, |
|
"loss": 0.2261, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 2.66, |
|
"learning_rate": 1.774580335731415e-05, |
|
"loss": 0.2052, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 2.73, |
|
"learning_rate": 1.8225419664268586e-05, |
|
"loss": 0.236, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 2.81, |
|
"learning_rate": 1.870503597122302e-05, |
|
"loss": 0.2256, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 2.88, |
|
"learning_rate": 1.918465227817746e-05, |
|
"loss": 0.1794, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 2.95, |
|
"learning_rate": 1.9664268585131895e-05, |
|
"loss": 0.2041, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.9075, |
|
"eval_loss": 0.2558615207672119, |
|
"eval_runtime": 6.9006, |
|
"eval_samples_per_second": 57.966, |
|
"eval_steps_per_second": 3.623, |
|
"step": 417 |
|
}, |
|
{ |
|
"epoch": 3.02, |
|
"learning_rate": 1.9984012789768187e-05, |
|
"loss": 0.2144, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 3.09, |
|
"learning_rate": 1.993072208899547e-05, |
|
"loss": 0.2121, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 3.17, |
|
"learning_rate": 1.9877431388222757e-05, |
|
"loss": 0.1434, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 3.24, |
|
"learning_rate": 1.982414068745004e-05, |
|
"loss": 0.1592, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 3.31, |
|
"learning_rate": 1.9770849986677328e-05, |
|
"loss": 0.1343, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 3.38, |
|
"learning_rate": 1.971755928590461e-05, |
|
"loss": 0.1119, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 3.45, |
|
"learning_rate": 1.9664268585131895e-05, |
|
"loss": 0.0998, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 3.53, |
|
"learning_rate": 1.961097788435918e-05, |
|
"loss": 0.1291, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 3.6, |
|
"learning_rate": 1.955768718358647e-05, |
|
"loss": 0.105, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 3.67, |
|
"learning_rate": 1.950439648281375e-05, |
|
"loss": 0.0977, |
|
"step": 510 |
|
}, |
|
{ |
|
"epoch": 3.74, |
|
"learning_rate": 1.9451105782041035e-05, |
|
"loss": 0.0733, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 3.81, |
|
"learning_rate": 1.9397815081268322e-05, |
|
"loss": 0.0885, |
|
"step": 530 |
|
}, |
|
{ |
|
"epoch": 3.88, |
|
"learning_rate": 1.9344524380495602e-05, |
|
"loss": 0.1262, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 3.96, |
|
"learning_rate": 1.929123367972289e-05, |
|
"loss": 0.1423, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_accuracy": 0.94, |
|
"eval_loss": 0.18216529488563538, |
|
"eval_runtime": 7.2699, |
|
"eval_samples_per_second": 55.022, |
|
"eval_steps_per_second": 3.439, |
|
"step": 556 |
|
}, |
|
{ |
|
"epoch": 4.03, |
|
"learning_rate": 1.9237942978950176e-05, |
|
"loss": 0.1161, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 4.1, |
|
"learning_rate": 1.918465227817746e-05, |
|
"loss": 0.0915, |
|
"step": 570 |
|
}, |
|
{ |
|
"epoch": 4.17, |
|
"learning_rate": 1.9131361577404743e-05, |
|
"loss": 0.0604, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 4.24, |
|
"learning_rate": 1.907807087663203e-05, |
|
"loss": 0.0902, |
|
"step": 590 |
|
}, |
|
{ |
|
"epoch": 4.32, |
|
"learning_rate": 1.9024780175859313e-05, |
|
"loss": 0.0442, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 4.39, |
|
"learning_rate": 1.89714894750866e-05, |
|
"loss": 0.046, |
|
"step": 610 |
|
}, |
|
{ |
|
"epoch": 4.46, |
|
"learning_rate": 1.8918198774313884e-05, |
|
"loss": 0.0934, |
|
"step": 620 |
|
}, |
|
{ |
|
"epoch": 4.53, |
|
"learning_rate": 1.8864908073541167e-05, |
|
"loss": 0.0748, |
|
"step": 630 |
|
}, |
|
{ |
|
"epoch": 4.6, |
|
"learning_rate": 1.8811617372768454e-05, |
|
"loss": 0.0561, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 4.68, |
|
"learning_rate": 1.8758326671995738e-05, |
|
"loss": 0.0618, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 4.75, |
|
"learning_rate": 1.870503597122302e-05, |
|
"loss": 0.0415, |
|
"step": 660 |
|
}, |
|
{ |
|
"epoch": 4.82, |
|
"learning_rate": 1.8651745270450308e-05, |
|
"loss": 0.073, |
|
"step": 670 |
|
}, |
|
{ |
|
"epoch": 4.89, |
|
"learning_rate": 1.8598454569677595e-05, |
|
"loss": 0.0632, |
|
"step": 680 |
|
}, |
|
{ |
|
"epoch": 4.96, |
|
"learning_rate": 1.8545163868904878e-05, |
|
"loss": 0.0568, |
|
"step": 690 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_accuracy": 0.975, |
|
"eval_loss": 0.06315237283706665, |
|
"eval_runtime": 7.0385, |
|
"eval_samples_per_second": 56.83, |
|
"eval_steps_per_second": 3.552, |
|
"step": 695 |
|
}, |
|
{ |
|
"epoch": 5.04, |
|
"learning_rate": 1.8491873168132162e-05, |
|
"loss": 0.0407, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 5.11, |
|
"learning_rate": 1.843858246735945e-05, |
|
"loss": 0.0445, |
|
"step": 710 |
|
}, |
|
{ |
|
"epoch": 5.18, |
|
"learning_rate": 1.8385291766586732e-05, |
|
"loss": 0.029, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 5.25, |
|
"learning_rate": 1.833200106581402e-05, |
|
"loss": 0.031, |
|
"step": 730 |
|
}, |
|
{ |
|
"epoch": 5.32, |
|
"learning_rate": 1.8278710365041302e-05, |
|
"loss": 0.0548, |
|
"step": 740 |
|
}, |
|
{ |
|
"epoch": 5.4, |
|
"learning_rate": 1.8225419664268586e-05, |
|
"loss": 0.0242, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 5.47, |
|
"learning_rate": 1.8172128963495873e-05, |
|
"loss": 0.0266, |
|
"step": 760 |
|
}, |
|
{ |
|
"epoch": 5.54, |
|
"learning_rate": 1.8118838262723156e-05, |
|
"loss": 0.0263, |
|
"step": 770 |
|
}, |
|
{ |
|
"epoch": 5.61, |
|
"learning_rate": 1.806554756195044e-05, |
|
"loss": 0.0468, |
|
"step": 780 |
|
}, |
|
{ |
|
"epoch": 5.68, |
|
"learning_rate": 1.8012256861177727e-05, |
|
"loss": 0.0375, |
|
"step": 790 |
|
}, |
|
{ |
|
"epoch": 5.76, |
|
"learning_rate": 1.795896616040501e-05, |
|
"loss": 0.0203, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 5.83, |
|
"learning_rate": 1.7905675459632294e-05, |
|
"loss": 0.0131, |
|
"step": 810 |
|
}, |
|
{ |
|
"epoch": 5.9, |
|
"learning_rate": 1.785238475885958e-05, |
|
"loss": 0.0722, |
|
"step": 820 |
|
}, |
|
{ |
|
"epoch": 5.97, |
|
"learning_rate": 1.7799094058086864e-05, |
|
"loss": 0.059, |
|
"step": 830 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"eval_accuracy": 0.9625, |
|
"eval_loss": 0.1519964635372162, |
|
"eval_runtime": 7.1264, |
|
"eval_samples_per_second": 56.129, |
|
"eval_steps_per_second": 3.508, |
|
"step": 834 |
|
}, |
|
{ |
|
"epoch": 6.04, |
|
"learning_rate": 1.774580335731415e-05, |
|
"loss": 0.0351, |
|
"step": 840 |
|
}, |
|
{ |
|
"epoch": 6.12, |
|
"learning_rate": 1.7692512656541434e-05, |
|
"loss": 0.0197, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 6.19, |
|
"learning_rate": 1.763922195576872e-05, |
|
"loss": 0.0217, |
|
"step": 860 |
|
}, |
|
{ |
|
"epoch": 6.26, |
|
"learning_rate": 1.7585931254996005e-05, |
|
"loss": 0.0217, |
|
"step": 870 |
|
}, |
|
{ |
|
"epoch": 6.33, |
|
"learning_rate": 1.753264055422329e-05, |
|
"loss": 0.02, |
|
"step": 880 |
|
}, |
|
{ |
|
"epoch": 6.4, |
|
"learning_rate": 1.7479349853450575e-05, |
|
"loss": 0.0236, |
|
"step": 890 |
|
}, |
|
{ |
|
"epoch": 6.47, |
|
"learning_rate": 1.742605915267786e-05, |
|
"loss": 0.0118, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 6.55, |
|
"learning_rate": 1.7372768451905145e-05, |
|
"loss": 0.0266, |
|
"step": 910 |
|
}, |
|
{ |
|
"epoch": 6.62, |
|
"learning_rate": 1.731947775113243e-05, |
|
"loss": 0.0183, |
|
"step": 920 |
|
}, |
|
{ |
|
"epoch": 6.69, |
|
"learning_rate": 1.7266187050359712e-05, |
|
"loss": 0.0454, |
|
"step": 930 |
|
}, |
|
{ |
|
"epoch": 6.76, |
|
"learning_rate": 1.7212896349587e-05, |
|
"loss": 0.0166, |
|
"step": 940 |
|
}, |
|
{ |
|
"epoch": 6.83, |
|
"learning_rate": 1.7159605648814283e-05, |
|
"loss": 0.0099, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 6.91, |
|
"learning_rate": 1.710631494804157e-05, |
|
"loss": 0.0106, |
|
"step": 960 |
|
}, |
|
{ |
|
"epoch": 6.98, |
|
"learning_rate": 1.7053024247268853e-05, |
|
"loss": 0.0396, |
|
"step": 970 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"eval_accuracy": 0.98, |
|
"eval_loss": 0.09595155715942383, |
|
"eval_runtime": 6.9691, |
|
"eval_samples_per_second": 57.396, |
|
"eval_steps_per_second": 3.587, |
|
"step": 973 |
|
}, |
|
{ |
|
"epoch": 7.05, |
|
"learning_rate": 1.6999733546496136e-05, |
|
"loss": 0.0152, |
|
"step": 980 |
|
}, |
|
{ |
|
"epoch": 7.12, |
|
"learning_rate": 1.6946442845723423e-05, |
|
"loss": 0.0171, |
|
"step": 990 |
|
}, |
|
{ |
|
"epoch": 7.19, |
|
"learning_rate": 1.689315214495071e-05, |
|
"loss": 0.0058, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 7.27, |
|
"learning_rate": 1.683986144417799e-05, |
|
"loss": 0.0287, |
|
"step": 1010 |
|
}, |
|
{ |
|
"epoch": 7.34, |
|
"learning_rate": 1.6786570743405277e-05, |
|
"loss": 0.0342, |
|
"step": 1020 |
|
}, |
|
{ |
|
"epoch": 7.41, |
|
"learning_rate": 1.6733280042632564e-05, |
|
"loss": 0.0331, |
|
"step": 1030 |
|
}, |
|
{ |
|
"epoch": 7.48, |
|
"learning_rate": 1.6679989341859847e-05, |
|
"loss": 0.0153, |
|
"step": 1040 |
|
}, |
|
{ |
|
"epoch": 7.55, |
|
"learning_rate": 1.662669864108713e-05, |
|
"loss": 0.0444, |
|
"step": 1050 |
|
}, |
|
{ |
|
"epoch": 7.63, |
|
"learning_rate": 1.6573407940314418e-05, |
|
"loss": 0.009, |
|
"step": 1060 |
|
}, |
|
{ |
|
"epoch": 7.7, |
|
"learning_rate": 1.65201172395417e-05, |
|
"loss": 0.012, |
|
"step": 1070 |
|
}, |
|
{ |
|
"epoch": 7.77, |
|
"learning_rate": 1.6466826538768985e-05, |
|
"loss": 0.0158, |
|
"step": 1080 |
|
}, |
|
{ |
|
"epoch": 7.84, |
|
"learning_rate": 1.641353583799627e-05, |
|
"loss": 0.0328, |
|
"step": 1090 |
|
}, |
|
{ |
|
"epoch": 7.91, |
|
"learning_rate": 1.6360245137223555e-05, |
|
"loss": 0.0159, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 7.99, |
|
"learning_rate": 1.6306954436450842e-05, |
|
"loss": 0.0076, |
|
"step": 1110 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"eval_accuracy": 0.98, |
|
"eval_loss": 0.07062595337629318, |
|
"eval_runtime": 6.9534, |
|
"eval_samples_per_second": 57.526, |
|
"eval_steps_per_second": 3.595, |
|
"step": 1112 |
|
}, |
|
{ |
|
"epoch": 8.06, |
|
"learning_rate": 1.6253663735678125e-05, |
|
"loss": 0.0208, |
|
"step": 1120 |
|
}, |
|
{ |
|
"epoch": 8.13, |
|
"learning_rate": 1.620037303490541e-05, |
|
"loss": 0.0138, |
|
"step": 1130 |
|
}, |
|
{ |
|
"epoch": 8.2, |
|
"learning_rate": 1.6147082334132696e-05, |
|
"loss": 0.0404, |
|
"step": 1140 |
|
}, |
|
{ |
|
"epoch": 8.27, |
|
"learning_rate": 1.609379163335998e-05, |
|
"loss": 0.0395, |
|
"step": 1150 |
|
}, |
|
{ |
|
"epoch": 8.35, |
|
"learning_rate": 1.6040500932587263e-05, |
|
"loss": 0.0044, |
|
"step": 1160 |
|
}, |
|
{ |
|
"epoch": 8.42, |
|
"learning_rate": 1.598721023181455e-05, |
|
"loss": 0.0055, |
|
"step": 1170 |
|
}, |
|
{ |
|
"epoch": 8.49, |
|
"learning_rate": 1.5933919531041836e-05, |
|
"loss": 0.017, |
|
"step": 1180 |
|
}, |
|
{ |
|
"epoch": 8.56, |
|
"learning_rate": 1.588062883026912e-05, |
|
"loss": 0.0405, |
|
"step": 1190 |
|
}, |
|
{ |
|
"epoch": 8.63, |
|
"learning_rate": 1.5827338129496403e-05, |
|
"loss": 0.0405, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 8.71, |
|
"learning_rate": 1.577404742872369e-05, |
|
"loss": 0.0289, |
|
"step": 1210 |
|
}, |
|
{ |
|
"epoch": 8.78, |
|
"learning_rate": 1.5720756727950974e-05, |
|
"loss": 0.0217, |
|
"step": 1220 |
|
}, |
|
{ |
|
"epoch": 8.85, |
|
"learning_rate": 1.566746602717826e-05, |
|
"loss": 0.0319, |
|
"step": 1230 |
|
}, |
|
{ |
|
"epoch": 8.92, |
|
"learning_rate": 1.5614175326405544e-05, |
|
"loss": 0.0176, |
|
"step": 1240 |
|
}, |
|
{ |
|
"epoch": 8.99, |
|
"learning_rate": 1.5560884625632828e-05, |
|
"loss": 0.0316, |
|
"step": 1250 |
|
}, |
|
{ |
|
"epoch": 9.0, |
|
"eval_accuracy": 0.9775, |
|
"eval_loss": 0.1436285525560379, |
|
"eval_runtime": 6.9746, |
|
"eval_samples_per_second": 57.351, |
|
"eval_steps_per_second": 3.584, |
|
"step": 1251 |
|
}, |
|
{ |
|
"epoch": 9.06, |
|
"learning_rate": 1.5507593924860114e-05, |
|
"loss": 0.0269, |
|
"step": 1260 |
|
}, |
|
{ |
|
"epoch": 9.14, |
|
"learning_rate": 1.5454303224087398e-05, |
|
"loss": 0.016, |
|
"step": 1270 |
|
}, |
|
{ |
|
"epoch": 9.21, |
|
"learning_rate": 1.540101252331468e-05, |
|
"loss": 0.0046, |
|
"step": 1280 |
|
}, |
|
{ |
|
"epoch": 9.28, |
|
"learning_rate": 1.534772182254197e-05, |
|
"loss": 0.0437, |
|
"step": 1290 |
|
}, |
|
{ |
|
"epoch": 9.35, |
|
"learning_rate": 1.5294431121769252e-05, |
|
"loss": 0.0109, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 9.42, |
|
"learning_rate": 1.5241140420996537e-05, |
|
"loss": 0.011, |
|
"step": 1310 |
|
}, |
|
{ |
|
"epoch": 9.5, |
|
"learning_rate": 1.5187849720223822e-05, |
|
"loss": 0.0045, |
|
"step": 1320 |
|
}, |
|
{ |
|
"epoch": 9.57, |
|
"learning_rate": 1.5134559019451107e-05, |
|
"loss": 0.0157, |
|
"step": 1330 |
|
}, |
|
{ |
|
"epoch": 9.64, |
|
"learning_rate": 1.5081268318678392e-05, |
|
"loss": 0.0077, |
|
"step": 1340 |
|
}, |
|
{ |
|
"epoch": 9.71, |
|
"learning_rate": 1.5027977617905676e-05, |
|
"loss": 0.0638, |
|
"step": 1350 |
|
}, |
|
{ |
|
"epoch": 9.78, |
|
"learning_rate": 1.4974686917132961e-05, |
|
"loss": 0.0166, |
|
"step": 1360 |
|
}, |
|
{ |
|
"epoch": 9.86, |
|
"learning_rate": 1.4921396216360246e-05, |
|
"loss": 0.0189, |
|
"step": 1370 |
|
}, |
|
{ |
|
"epoch": 9.93, |
|
"learning_rate": 1.4868105515587531e-05, |
|
"loss": 0.0171, |
|
"step": 1380 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"learning_rate": 1.4814814814814815e-05, |
|
"loss": 0.0306, |
|
"step": 1390 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"eval_accuracy": 0.9075, |
|
"eval_loss": 0.604502260684967, |
|
"eval_runtime": 6.8184, |
|
"eval_samples_per_second": 58.664, |
|
"eval_steps_per_second": 3.667, |
|
"step": 1390 |
|
}, |
|
{ |
|
"epoch": 10.07, |
|
"learning_rate": 1.47615241140421e-05, |
|
"loss": 0.0172, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 10.14, |
|
"learning_rate": 1.4708233413269385e-05, |
|
"loss": 0.0334, |
|
"step": 1410 |
|
}, |
|
{ |
|
"epoch": 10.22, |
|
"learning_rate": 1.4654942712496672e-05, |
|
"loss": 0.0366, |
|
"step": 1420 |
|
}, |
|
{ |
|
"epoch": 10.29, |
|
"learning_rate": 1.4601652011723954e-05, |
|
"loss": 0.0109, |
|
"step": 1430 |
|
}, |
|
{ |
|
"epoch": 10.36, |
|
"learning_rate": 1.454836131095124e-05, |
|
"loss": 0.032, |
|
"step": 1440 |
|
}, |
|
{ |
|
"epoch": 10.43, |
|
"learning_rate": 1.4495070610178526e-05, |
|
"loss": 0.0078, |
|
"step": 1450 |
|
}, |
|
{ |
|
"epoch": 10.5, |
|
"learning_rate": 1.4441779909405811e-05, |
|
"loss": 0.024, |
|
"step": 1460 |
|
}, |
|
{ |
|
"epoch": 10.58, |
|
"learning_rate": 1.4388489208633095e-05, |
|
"loss": 0.0126, |
|
"step": 1470 |
|
}, |
|
{ |
|
"epoch": 10.65, |
|
"learning_rate": 1.433519850786038e-05, |
|
"loss": 0.0014, |
|
"step": 1480 |
|
}, |
|
{ |
|
"epoch": 10.72, |
|
"learning_rate": 1.4281907807087665e-05, |
|
"loss": 0.0308, |
|
"step": 1490 |
|
}, |
|
{ |
|
"epoch": 10.79, |
|
"learning_rate": 1.422861710631495e-05, |
|
"loss": 0.023, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 10.86, |
|
"learning_rate": 1.4175326405542234e-05, |
|
"loss": 0.0044, |
|
"step": 1510 |
|
}, |
|
{ |
|
"epoch": 10.94, |
|
"learning_rate": 1.4122035704769519e-05, |
|
"loss": 0.0093, |
|
"step": 1520 |
|
}, |
|
{ |
|
"epoch": 11.0, |
|
"eval_accuracy": 0.99, |
|
"eval_loss": 0.09465105831623077, |
|
"eval_runtime": 7.036, |
|
"eval_samples_per_second": 56.85, |
|
"eval_steps_per_second": 3.553, |
|
"step": 1529 |
|
}, |
|
{ |
|
"epoch": 11.01, |
|
"learning_rate": 1.4068745003996804e-05, |
|
"loss": 0.0059, |
|
"step": 1530 |
|
}, |
|
{ |
|
"epoch": 11.08, |
|
"learning_rate": 1.4015454303224087e-05, |
|
"loss": 0.0108, |
|
"step": 1540 |
|
}, |
|
{ |
|
"epoch": 11.15, |
|
"learning_rate": 1.3962163602451373e-05, |
|
"loss": 0.0021, |
|
"step": 1550 |
|
}, |
|
{ |
|
"epoch": 11.22, |
|
"learning_rate": 1.3908872901678658e-05, |
|
"loss": 0.0233, |
|
"step": 1560 |
|
}, |
|
{ |
|
"epoch": 11.29, |
|
"learning_rate": 1.3855582200905943e-05, |
|
"loss": 0.0138, |
|
"step": 1570 |
|
}, |
|
{ |
|
"epoch": 11.37, |
|
"learning_rate": 1.3802291500133226e-05, |
|
"loss": 0.0021, |
|
"step": 1580 |
|
}, |
|
{ |
|
"epoch": 11.44, |
|
"learning_rate": 1.3749000799360512e-05, |
|
"loss": 0.0431, |
|
"step": 1590 |
|
}, |
|
{ |
|
"epoch": 11.51, |
|
"learning_rate": 1.3695710098587799e-05, |
|
"loss": 0.0433, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 11.58, |
|
"learning_rate": 1.3642419397815084e-05, |
|
"loss": 0.0074, |
|
"step": 1610 |
|
}, |
|
{ |
|
"epoch": 11.65, |
|
"learning_rate": 1.3589128697042367e-05, |
|
"loss": 0.0163, |
|
"step": 1620 |
|
}, |
|
{ |
|
"epoch": 11.73, |
|
"learning_rate": 1.3535837996269652e-05, |
|
"loss": 0.0118, |
|
"step": 1630 |
|
}, |
|
{ |
|
"epoch": 11.8, |
|
"learning_rate": 1.3482547295496938e-05, |
|
"loss": 0.0139, |
|
"step": 1640 |
|
}, |
|
{ |
|
"epoch": 11.87, |
|
"learning_rate": 1.3429256594724223e-05, |
|
"loss": 0.0021, |
|
"step": 1650 |
|
}, |
|
{ |
|
"epoch": 11.94, |
|
"learning_rate": 1.3375965893951506e-05, |
|
"loss": 0.0268, |
|
"step": 1660 |
|
}, |
|
{ |
|
"epoch": 12.0, |
|
"eval_accuracy": 0.98, |
|
"eval_loss": 0.18784460425376892, |
|
"eval_runtime": 6.9369, |
|
"eval_samples_per_second": 57.662, |
|
"eval_steps_per_second": 3.604, |
|
"step": 1668 |
|
}, |
|
{ |
|
"epoch": 12.01, |
|
"learning_rate": 1.3322675193178791e-05, |
|
"loss": 0.0057, |
|
"step": 1670 |
|
}, |
|
{ |
|
"epoch": 12.09, |
|
"learning_rate": 1.3269384492406077e-05, |
|
"loss": 0.0175, |
|
"step": 1680 |
|
}, |
|
{ |
|
"epoch": 12.16, |
|
"learning_rate": 1.3216093791633362e-05, |
|
"loss": 0.0159, |
|
"step": 1690 |
|
}, |
|
{ |
|
"epoch": 12.23, |
|
"learning_rate": 1.3162803090860645e-05, |
|
"loss": 0.0209, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 12.3, |
|
"learning_rate": 1.310951239008793e-05, |
|
"loss": 0.0383, |
|
"step": 1710 |
|
}, |
|
{ |
|
"epoch": 12.37, |
|
"learning_rate": 1.3056221689315216e-05, |
|
"loss": 0.0291, |
|
"step": 1720 |
|
}, |
|
{ |
|
"epoch": 12.45, |
|
"learning_rate": 1.30029309885425e-05, |
|
"loss": 0.0002, |
|
"step": 1730 |
|
}, |
|
{ |
|
"epoch": 12.52, |
|
"learning_rate": 1.2949640287769784e-05, |
|
"loss": 0.0009, |
|
"step": 1740 |
|
}, |
|
{ |
|
"epoch": 12.59, |
|
"learning_rate": 1.289634958699707e-05, |
|
"loss": 0.004, |
|
"step": 1750 |
|
}, |
|
{ |
|
"epoch": 12.66, |
|
"learning_rate": 1.2843058886224356e-05, |
|
"loss": 0.003, |
|
"step": 1760 |
|
}, |
|
{ |
|
"epoch": 12.73, |
|
"learning_rate": 1.2789768185451638e-05, |
|
"loss": 0.0116, |
|
"step": 1770 |
|
}, |
|
{ |
|
"epoch": 12.81, |
|
"learning_rate": 1.2736477484678925e-05, |
|
"loss": 0.04, |
|
"step": 1780 |
|
}, |
|
{ |
|
"epoch": 12.88, |
|
"learning_rate": 1.268318678390621e-05, |
|
"loss": 0.0225, |
|
"step": 1790 |
|
}, |
|
{ |
|
"epoch": 12.95, |
|
"learning_rate": 1.2629896083133495e-05, |
|
"loss": 0.0037, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 13.0, |
|
"eval_accuracy": 0.9825, |
|
"eval_loss": 0.11539778858423233, |
|
"eval_runtime": 6.9266, |
|
"eval_samples_per_second": 57.749, |
|
"eval_steps_per_second": 3.609, |
|
"step": 1807 |
|
}, |
|
{ |
|
"epoch": 13.02, |
|
"learning_rate": 1.2576605382360779e-05, |
|
"loss": 0.0465, |
|
"step": 1810 |
|
}, |
|
{ |
|
"epoch": 13.09, |
|
"learning_rate": 1.2523314681588064e-05, |
|
"loss": 0.0189, |
|
"step": 1820 |
|
}, |
|
{ |
|
"epoch": 13.17, |
|
"learning_rate": 1.2470023980815349e-05, |
|
"loss": 0.0393, |
|
"step": 1830 |
|
}, |
|
{ |
|
"epoch": 13.24, |
|
"learning_rate": 1.2416733280042634e-05, |
|
"loss": 0.0043, |
|
"step": 1840 |
|
}, |
|
{ |
|
"epoch": 13.31, |
|
"learning_rate": 1.2363442579269918e-05, |
|
"loss": 0.0283, |
|
"step": 1850 |
|
}, |
|
{ |
|
"epoch": 13.38, |
|
"learning_rate": 1.2310151878497203e-05, |
|
"loss": 0.0546, |
|
"step": 1860 |
|
}, |
|
{ |
|
"epoch": 13.45, |
|
"learning_rate": 1.2256861177724488e-05, |
|
"loss": 0.0078, |
|
"step": 1870 |
|
}, |
|
{ |
|
"epoch": 13.53, |
|
"learning_rate": 1.2203570476951773e-05, |
|
"loss": 0.0057, |
|
"step": 1880 |
|
}, |
|
{ |
|
"epoch": 13.6, |
|
"learning_rate": 1.2150279776179057e-05, |
|
"loss": 0.002, |
|
"step": 1890 |
|
}, |
|
{ |
|
"epoch": 13.67, |
|
"learning_rate": 1.2096989075406342e-05, |
|
"loss": 0.0221, |
|
"step": 1900 |
|
}, |
|
{ |
|
"epoch": 13.74, |
|
"learning_rate": 1.2043698374633627e-05, |
|
"loss": 0.0107, |
|
"step": 1910 |
|
}, |
|
{ |
|
"epoch": 13.81, |
|
"learning_rate": 1.1990407673860914e-05, |
|
"loss": 0.0088, |
|
"step": 1920 |
|
}, |
|
{ |
|
"epoch": 13.88, |
|
"learning_rate": 1.1937116973088196e-05, |
|
"loss": 0.0363, |
|
"step": 1930 |
|
}, |
|
{ |
|
"epoch": 13.96, |
|
"learning_rate": 1.1883826272315483e-05, |
|
"loss": 0.0005, |
|
"step": 1940 |
|
}, |
|
{ |
|
"epoch": 14.0, |
|
"eval_accuracy": 0.9875, |
|
"eval_loss": 0.13052797317504883, |
|
"eval_runtime": 7.0568, |
|
"eval_samples_per_second": 56.683, |
|
"eval_steps_per_second": 3.543, |
|
"step": 1946 |
|
}, |
|
{ |
|
"epoch": 14.03, |
|
"learning_rate": 1.1830535571542768e-05, |
|
"loss": 0.0045, |
|
"step": 1950 |
|
}, |
|
{ |
|
"epoch": 14.1, |
|
"learning_rate": 1.1777244870770053e-05, |
|
"loss": 0.0345, |
|
"step": 1960 |
|
}, |
|
{ |
|
"epoch": 14.17, |
|
"learning_rate": 1.1723954169997336e-05, |
|
"loss": 0.0001, |
|
"step": 1970 |
|
}, |
|
{ |
|
"epoch": 14.24, |
|
"learning_rate": 1.1670663469224622e-05, |
|
"loss": 0.0215, |
|
"step": 1980 |
|
}, |
|
{ |
|
"epoch": 14.32, |
|
"learning_rate": 1.1617372768451907e-05, |
|
"loss": 0.0264, |
|
"step": 1990 |
|
}, |
|
{ |
|
"epoch": 14.39, |
|
"learning_rate": 1.156408206767919e-05, |
|
"loss": 0.0002, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 14.46, |
|
"learning_rate": 1.1510791366906475e-05, |
|
"loss": 0.0017, |
|
"step": 2010 |
|
}, |
|
{ |
|
"epoch": 14.53, |
|
"learning_rate": 1.145750066613376e-05, |
|
"loss": 0.01, |
|
"step": 2020 |
|
}, |
|
{ |
|
"epoch": 14.6, |
|
"learning_rate": 1.1404209965361046e-05, |
|
"loss": 0.0, |
|
"step": 2030 |
|
}, |
|
{ |
|
"epoch": 14.68, |
|
"learning_rate": 1.135091926458833e-05, |
|
"loss": 0.0333, |
|
"step": 2040 |
|
}, |
|
{ |
|
"epoch": 14.75, |
|
"learning_rate": 1.1297628563815614e-05, |
|
"loss": 0.0002, |
|
"step": 2050 |
|
}, |
|
{ |
|
"epoch": 14.82, |
|
"learning_rate": 1.12443378630429e-05, |
|
"loss": 0.0147, |
|
"step": 2060 |
|
}, |
|
{ |
|
"epoch": 14.89, |
|
"learning_rate": 1.1191047162270185e-05, |
|
"loss": 0.0652, |
|
"step": 2070 |
|
}, |
|
{ |
|
"epoch": 14.96, |
|
"learning_rate": 1.1137756461497468e-05, |
|
"loss": 0.0232, |
|
"step": 2080 |
|
}, |
|
{ |
|
"epoch": 15.0, |
|
"eval_accuracy": 0.9825, |
|
"eval_loss": 0.1760598123073578, |
|
"eval_runtime": 6.7923, |
|
"eval_samples_per_second": 58.89, |
|
"eval_steps_per_second": 3.681, |
|
"step": 2085 |
|
}, |
|
{ |
|
"epoch": 15.04, |
|
"learning_rate": 1.1084465760724753e-05, |
|
"loss": 0.0012, |
|
"step": 2090 |
|
}, |
|
{ |
|
"epoch": 15.11, |
|
"learning_rate": 1.103117505995204e-05, |
|
"loss": 0.0, |
|
"step": 2100 |
|
}, |
|
{ |
|
"epoch": 15.18, |
|
"learning_rate": 1.0977884359179325e-05, |
|
"loss": 0.0399, |
|
"step": 2110 |
|
}, |
|
{ |
|
"epoch": 15.25, |
|
"learning_rate": 1.0924593658406609e-05, |
|
"loss": 0.0176, |
|
"step": 2120 |
|
}, |
|
{ |
|
"epoch": 15.32, |
|
"learning_rate": 1.0871302957633894e-05, |
|
"loss": 0.0102, |
|
"step": 2130 |
|
}, |
|
{ |
|
"epoch": 15.4, |
|
"learning_rate": 1.081801225686118e-05, |
|
"loss": 0.0043, |
|
"step": 2140 |
|
}, |
|
{ |
|
"epoch": 15.47, |
|
"learning_rate": 1.0764721556088464e-05, |
|
"loss": 0.0036, |
|
"step": 2150 |
|
}, |
|
{ |
|
"epoch": 15.54, |
|
"learning_rate": 1.0711430855315748e-05, |
|
"loss": 0.0034, |
|
"step": 2160 |
|
}, |
|
{ |
|
"epoch": 15.61, |
|
"learning_rate": 1.0658140154543033e-05, |
|
"loss": 0.0045, |
|
"step": 2170 |
|
}, |
|
{ |
|
"epoch": 15.68, |
|
"learning_rate": 1.0604849453770318e-05, |
|
"loss": 0.0002, |
|
"step": 2180 |
|
}, |
|
{ |
|
"epoch": 15.76, |
|
"learning_rate": 1.0551558752997603e-05, |
|
"loss": 0.0264, |
|
"step": 2190 |
|
}, |
|
{ |
|
"epoch": 15.83, |
|
"learning_rate": 1.0498268052224887e-05, |
|
"loss": 0.0149, |
|
"step": 2200 |
|
}, |
|
{ |
|
"epoch": 15.9, |
|
"learning_rate": 1.0444977351452172e-05, |
|
"loss": 0.0015, |
|
"step": 2210 |
|
}, |
|
{ |
|
"epoch": 15.97, |
|
"learning_rate": 1.0391686650679457e-05, |
|
"loss": 0.0048, |
|
"step": 2220 |
|
}, |
|
{ |
|
"epoch": 16.0, |
|
"eval_accuracy": 0.98, |
|
"eval_loss": 0.28786617517471313, |
|
"eval_runtime": 7.1065, |
|
"eval_samples_per_second": 56.287, |
|
"eval_steps_per_second": 3.518, |
|
"step": 2224 |
|
}, |
|
{ |
|
"epoch": 16.04, |
|
"learning_rate": 1.0338395949906742e-05, |
|
"loss": 0.0, |
|
"step": 2230 |
|
}, |
|
{ |
|
"epoch": 16.12, |
|
"learning_rate": 1.0285105249134026e-05, |
|
"loss": 0.0135, |
|
"step": 2240 |
|
}, |
|
{ |
|
"epoch": 16.19, |
|
"learning_rate": 1.0231814548361311e-05, |
|
"loss": 0.0054, |
|
"step": 2250 |
|
}, |
|
{ |
|
"epoch": 16.26, |
|
"learning_rate": 1.0178523847588598e-05, |
|
"loss": 0.0005, |
|
"step": 2260 |
|
}, |
|
{ |
|
"epoch": 16.33, |
|
"learning_rate": 1.012523314681588e-05, |
|
"loss": 0.0045, |
|
"step": 2270 |
|
}, |
|
{ |
|
"epoch": 16.4, |
|
"learning_rate": 1.0071942446043167e-05, |
|
"loss": 0.0101, |
|
"step": 2280 |
|
}, |
|
{ |
|
"epoch": 16.47, |
|
"learning_rate": 1.0018651745270452e-05, |
|
"loss": 0.0241, |
|
"step": 2290 |
|
}, |
|
{ |
|
"epoch": 16.55, |
|
"learning_rate": 9.965361044497735e-06, |
|
"loss": 0.0035, |
|
"step": 2300 |
|
}, |
|
{ |
|
"epoch": 16.62, |
|
"learning_rate": 9.91207034372502e-06, |
|
"loss": 0.0315, |
|
"step": 2310 |
|
}, |
|
{ |
|
"epoch": 16.69, |
|
"learning_rate": 9.858779642952306e-06, |
|
"loss": 0.0049, |
|
"step": 2320 |
|
}, |
|
{ |
|
"epoch": 16.76, |
|
"learning_rate": 9.80548894217959e-06, |
|
"loss": 0.0, |
|
"step": 2330 |
|
}, |
|
{ |
|
"epoch": 16.83, |
|
"learning_rate": 9.752198241406874e-06, |
|
"loss": 0.0378, |
|
"step": 2340 |
|
}, |
|
{ |
|
"epoch": 16.91, |
|
"learning_rate": 9.698907540634161e-06, |
|
"loss": 0.0, |
|
"step": 2350 |
|
}, |
|
{ |
|
"epoch": 16.98, |
|
"learning_rate": 9.645616839861445e-06, |
|
"loss": 0.0, |
|
"step": 2360 |
|
}, |
|
{ |
|
"epoch": 17.0, |
|
"eval_accuracy": 0.985, |
|
"eval_loss": 0.20865210890769958, |
|
"eval_runtime": 6.9281, |
|
"eval_samples_per_second": 57.736, |
|
"eval_steps_per_second": 3.608, |
|
"step": 2363 |
|
}, |
|
{ |
|
"epoch": 17.05, |
|
"learning_rate": 9.59232613908873e-06, |
|
"loss": 0.0168, |
|
"step": 2370 |
|
}, |
|
{ |
|
"epoch": 17.12, |
|
"learning_rate": 9.539035438316015e-06, |
|
"loss": 0.0048, |
|
"step": 2380 |
|
}, |
|
{ |
|
"epoch": 17.19, |
|
"learning_rate": 9.4857447375433e-06, |
|
"loss": 0.0071, |
|
"step": 2390 |
|
}, |
|
{ |
|
"epoch": 17.27, |
|
"learning_rate": 9.432454036770584e-06, |
|
"loss": 0.0, |
|
"step": 2400 |
|
}, |
|
{ |
|
"epoch": 17.34, |
|
"learning_rate": 9.379163335997869e-06, |
|
"loss": 0.0, |
|
"step": 2410 |
|
}, |
|
{ |
|
"epoch": 17.41, |
|
"learning_rate": 9.325872635225154e-06, |
|
"loss": 0.0, |
|
"step": 2420 |
|
}, |
|
{ |
|
"epoch": 17.48, |
|
"learning_rate": 9.272581934452439e-06, |
|
"loss": 0.0, |
|
"step": 2430 |
|
}, |
|
{ |
|
"epoch": 17.55, |
|
"learning_rate": 9.219291233679724e-06, |
|
"loss": 0.0061, |
|
"step": 2440 |
|
}, |
|
{ |
|
"epoch": 17.63, |
|
"learning_rate": 9.16600053290701e-06, |
|
"loss": 0.0108, |
|
"step": 2450 |
|
}, |
|
{ |
|
"epoch": 17.7, |
|
"learning_rate": 9.112709832134293e-06, |
|
"loss": 0.014, |
|
"step": 2460 |
|
}, |
|
{ |
|
"epoch": 17.77, |
|
"learning_rate": 9.059419131361578e-06, |
|
"loss": 0.003, |
|
"step": 2470 |
|
}, |
|
{ |
|
"epoch": 17.84, |
|
"learning_rate": 9.006128430588863e-06, |
|
"loss": 0.0273, |
|
"step": 2480 |
|
}, |
|
{ |
|
"epoch": 17.91, |
|
"learning_rate": 8.952837729816147e-06, |
|
"loss": 0.0187, |
|
"step": 2490 |
|
}, |
|
{ |
|
"epoch": 17.99, |
|
"learning_rate": 8.899547029043432e-06, |
|
"loss": 0.0055, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 18.0, |
|
"eval_accuracy": 0.985, |
|
"eval_loss": 0.2575609087944031, |
|
"eval_runtime": 7.0331, |
|
"eval_samples_per_second": 56.874, |
|
"eval_steps_per_second": 3.555, |
|
"step": 2502 |
|
}, |
|
{ |
|
"epoch": 18.06, |
|
"learning_rate": 8.846256328270717e-06, |
|
"loss": 0.0108, |
|
"step": 2510 |
|
}, |
|
{ |
|
"epoch": 18.13, |
|
"learning_rate": 8.792965627498002e-06, |
|
"loss": 0.034, |
|
"step": 2520 |
|
}, |
|
{ |
|
"epoch": 18.2, |
|
"learning_rate": 8.739674926725287e-06, |
|
"loss": 0.0001, |
|
"step": 2530 |
|
}, |
|
{ |
|
"epoch": 18.27, |
|
"learning_rate": 8.686384225952573e-06, |
|
"loss": 0.0035, |
|
"step": 2540 |
|
}, |
|
{ |
|
"epoch": 18.35, |
|
"learning_rate": 8.633093525179856e-06, |
|
"loss": 0.0278, |
|
"step": 2550 |
|
}, |
|
{ |
|
"epoch": 18.42, |
|
"learning_rate": 8.579802824407141e-06, |
|
"loss": 0.0025, |
|
"step": 2560 |
|
}, |
|
{ |
|
"epoch": 18.49, |
|
"learning_rate": 8.526512123634426e-06, |
|
"loss": 0.0, |
|
"step": 2570 |
|
}, |
|
{ |
|
"epoch": 18.56, |
|
"learning_rate": 8.473221422861712e-06, |
|
"loss": 0.0199, |
|
"step": 2580 |
|
}, |
|
{ |
|
"epoch": 18.63, |
|
"learning_rate": 8.419930722088995e-06, |
|
"loss": 0.0, |
|
"step": 2590 |
|
}, |
|
{ |
|
"epoch": 18.71, |
|
"learning_rate": 8.366640021316282e-06, |
|
"loss": 0.0171, |
|
"step": 2600 |
|
}, |
|
{ |
|
"epoch": 18.78, |
|
"learning_rate": 8.313349320543565e-06, |
|
"loss": 0.0, |
|
"step": 2610 |
|
}, |
|
{ |
|
"epoch": 18.85, |
|
"learning_rate": 8.26005861977085e-06, |
|
"loss": 0.0189, |
|
"step": 2620 |
|
}, |
|
{ |
|
"epoch": 18.92, |
|
"learning_rate": 8.206767918998136e-06, |
|
"loss": 0.0, |
|
"step": 2630 |
|
}, |
|
{ |
|
"epoch": 18.99, |
|
"learning_rate": 8.153477218225421e-06, |
|
"loss": 0.0, |
|
"step": 2640 |
|
}, |
|
{ |
|
"epoch": 19.0, |
|
"eval_accuracy": 0.985, |
|
"eval_loss": 0.23741036653518677, |
|
"eval_runtime": 6.8944, |
|
"eval_samples_per_second": 58.019, |
|
"eval_steps_per_second": 3.626, |
|
"step": 2641 |
|
}, |
|
{ |
|
"epoch": 19.06, |
|
"learning_rate": 8.100186517452704e-06, |
|
"loss": 0.0, |
|
"step": 2650 |
|
}, |
|
{ |
|
"epoch": 19.14, |
|
"learning_rate": 8.04689581667999e-06, |
|
"loss": 0.0, |
|
"step": 2660 |
|
}, |
|
{ |
|
"epoch": 19.21, |
|
"learning_rate": 7.993605115907275e-06, |
|
"loss": 0.0, |
|
"step": 2670 |
|
}, |
|
{ |
|
"epoch": 19.28, |
|
"learning_rate": 7.94031441513456e-06, |
|
"loss": 0.0126, |
|
"step": 2680 |
|
}, |
|
{ |
|
"epoch": 19.35, |
|
"learning_rate": 7.887023714361845e-06, |
|
"loss": 0.0208, |
|
"step": 2690 |
|
}, |
|
{ |
|
"epoch": 19.42, |
|
"learning_rate": 7.83373301358913e-06, |
|
"loss": 0.0007, |
|
"step": 2700 |
|
}, |
|
{ |
|
"epoch": 19.5, |
|
"learning_rate": 7.780442312816414e-06, |
|
"loss": 0.035, |
|
"step": 2710 |
|
}, |
|
{ |
|
"epoch": 19.57, |
|
"learning_rate": 7.727151612043699e-06, |
|
"loss": 0.0, |
|
"step": 2720 |
|
}, |
|
{ |
|
"epoch": 19.64, |
|
"learning_rate": 7.673860911270984e-06, |
|
"loss": 0.0, |
|
"step": 2730 |
|
}, |
|
{ |
|
"epoch": 19.71, |
|
"learning_rate": 7.6205702104982685e-06, |
|
"loss": 0.0, |
|
"step": 2740 |
|
}, |
|
{ |
|
"epoch": 19.78, |
|
"learning_rate": 7.567279509725554e-06, |
|
"loss": 0.0225, |
|
"step": 2750 |
|
}, |
|
{ |
|
"epoch": 19.86, |
|
"learning_rate": 7.513988808952838e-06, |
|
"loss": 0.0, |
|
"step": 2760 |
|
}, |
|
{ |
|
"epoch": 19.93, |
|
"learning_rate": 7.460698108180123e-06, |
|
"loss": 0.0157, |
|
"step": 2770 |
|
}, |
|
{ |
|
"epoch": 20.0, |
|
"learning_rate": 7.4074074074074075e-06, |
|
"loss": 0.0034, |
|
"step": 2780 |
|
}, |
|
{ |
|
"epoch": 20.0, |
|
"eval_accuracy": 0.99, |
|
"eval_loss": 0.16036586463451385, |
|
"eval_runtime": 6.9057, |
|
"eval_samples_per_second": 57.923, |
|
"eval_steps_per_second": 3.62, |
|
"step": 2780 |
|
}, |
|
{ |
|
"epoch": 20.07, |
|
"learning_rate": 7.354116706634693e-06, |
|
"loss": 0.0, |
|
"step": 2790 |
|
}, |
|
{ |
|
"epoch": 20.14, |
|
"learning_rate": 7.300826005861977e-06, |
|
"loss": 0.0061, |
|
"step": 2800 |
|
}, |
|
{ |
|
"epoch": 20.22, |
|
"learning_rate": 7.247535305089263e-06, |
|
"loss": 0.0, |
|
"step": 2810 |
|
}, |
|
{ |
|
"epoch": 20.29, |
|
"learning_rate": 7.194244604316547e-06, |
|
"loss": 0.0, |
|
"step": 2820 |
|
}, |
|
{ |
|
"epoch": 20.36, |
|
"learning_rate": 7.1409539035438325e-06, |
|
"loss": 0.0303, |
|
"step": 2830 |
|
}, |
|
{ |
|
"epoch": 20.43, |
|
"learning_rate": 7.087663202771117e-06, |
|
"loss": 0.0, |
|
"step": 2840 |
|
}, |
|
{ |
|
"epoch": 20.5, |
|
"learning_rate": 7.034372501998402e-06, |
|
"loss": 0.0, |
|
"step": 2850 |
|
}, |
|
{ |
|
"epoch": 20.58, |
|
"learning_rate": 6.981081801225686e-06, |
|
"loss": 0.0126, |
|
"step": 2860 |
|
}, |
|
{ |
|
"epoch": 20.65, |
|
"learning_rate": 6.9277911004529715e-06, |
|
"loss": 0.0299, |
|
"step": 2870 |
|
}, |
|
{ |
|
"epoch": 20.72, |
|
"learning_rate": 6.874500399680256e-06, |
|
"loss": 0.01, |
|
"step": 2880 |
|
}, |
|
{ |
|
"epoch": 20.79, |
|
"learning_rate": 6.821209698907542e-06, |
|
"loss": 0.0, |
|
"step": 2890 |
|
}, |
|
{ |
|
"epoch": 20.86, |
|
"learning_rate": 6.767918998134826e-06, |
|
"loss": 0.0025, |
|
"step": 2900 |
|
}, |
|
{ |
|
"epoch": 20.94, |
|
"learning_rate": 6.714628297362111e-06, |
|
"loss": 0.0303, |
|
"step": 2910 |
|
}, |
|
{ |
|
"epoch": 21.0, |
|
"eval_accuracy": 0.9875, |
|
"eval_loss": 0.14314711093902588, |
|
"eval_runtime": 7.0921, |
|
"eval_samples_per_second": 56.401, |
|
"eval_steps_per_second": 3.525, |
|
"step": 2919 |
|
}, |
|
{ |
|
"epoch": 21.01, |
|
"learning_rate": 6.661337596589396e-06, |
|
"loss": 0.0203, |
|
"step": 2920 |
|
}, |
|
{ |
|
"epoch": 21.08, |
|
"learning_rate": 6.608046895816681e-06, |
|
"loss": 0.0, |
|
"step": 2930 |
|
}, |
|
{ |
|
"epoch": 21.15, |
|
"learning_rate": 6.554756195043965e-06, |
|
"loss": 0.0, |
|
"step": 2940 |
|
}, |
|
{ |
|
"epoch": 21.22, |
|
"learning_rate": 6.50146549427125e-06, |
|
"loss": 0.0186, |
|
"step": 2950 |
|
}, |
|
{ |
|
"epoch": 21.29, |
|
"learning_rate": 6.448174793498535e-06, |
|
"loss": 0.0071, |
|
"step": 2960 |
|
}, |
|
{ |
|
"epoch": 21.37, |
|
"learning_rate": 6.394884092725819e-06, |
|
"loss": 0.0005, |
|
"step": 2970 |
|
}, |
|
{ |
|
"epoch": 21.44, |
|
"learning_rate": 6.341593391953105e-06, |
|
"loss": 0.0055, |
|
"step": 2980 |
|
}, |
|
{ |
|
"epoch": 21.51, |
|
"learning_rate": 6.288302691180389e-06, |
|
"loss": 0.0, |
|
"step": 2990 |
|
}, |
|
{ |
|
"epoch": 21.58, |
|
"learning_rate": 6.2350119904076745e-06, |
|
"loss": 0.0331, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 21.65, |
|
"learning_rate": 6.181721289634959e-06, |
|
"loss": 0.0, |
|
"step": 3010 |
|
}, |
|
{ |
|
"epoch": 21.73, |
|
"learning_rate": 6.128430588862244e-06, |
|
"loss": 0.002, |
|
"step": 3020 |
|
}, |
|
{ |
|
"epoch": 21.8, |
|
"learning_rate": 6.075139888089528e-06, |
|
"loss": 0.0132, |
|
"step": 3030 |
|
}, |
|
{ |
|
"epoch": 21.87, |
|
"learning_rate": 6.0218491873168135e-06, |
|
"loss": 0.0, |
|
"step": 3040 |
|
}, |
|
{ |
|
"epoch": 21.94, |
|
"learning_rate": 5.968558486544098e-06, |
|
"loss": 0.0, |
|
"step": 3050 |
|
}, |
|
{ |
|
"epoch": 22.0, |
|
"eval_accuracy": 0.9925, |
|
"eval_loss": 0.14593777060508728, |
|
"eval_runtime": 6.9363, |
|
"eval_samples_per_second": 57.668, |
|
"eval_steps_per_second": 3.604, |
|
"step": 3058 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 4170, |
|
"num_train_epochs": 30, |
|
"save_steps": 500, |
|
"total_flos": 1.7055354463120835e+19, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|