| { | |
| "best_metric": 0.8985507246376812, | |
| "best_model_checkpoint": "vit-cxr4/checkpoint-1500", | |
| "epoch": 6.0, | |
| "eval_steps": 100, | |
| "global_step": 1914, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.9843260188087776e-05, | |
| "loss": 0.6092, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 2.9686520376175547e-05, | |
| "loss": 0.4743, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 2.9529780564263326e-05, | |
| "loss": 0.4443, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 2.9373040752351097e-05, | |
| "loss": 0.4, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.9216300940438872e-05, | |
| "loss": 0.3793, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 2.9059561128526644e-05, | |
| "loss": 0.368, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 2.8902821316614422e-05, | |
| "loss": 0.3486, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 2.8746081504702197e-05, | |
| "loss": 0.3741, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 2.858934169278997e-05, | |
| "loss": 0.3101, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 2.8432601880877743e-05, | |
| "loss": 0.3151, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_accuracy": 0.8552390906715442, | |
| "eval_f1": 0.8619142572283149, | |
| "eval_loss": 0.3317149877548218, | |
| "eval_precision": 0.8151815181518152, | |
| "eval_recall": 0.9143310417768377, | |
| "eval_runtime": 111.0975, | |
| "eval_samples_per_second": 34.447, | |
| "eval_steps_per_second": 0.54, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 2.8275862068965518e-05, | |
| "loss": 0.3398, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 2.8119122257053293e-05, | |
| "loss": 0.3507, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.7962382445141068e-05, | |
| "loss": 0.3321, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 2.780564263322884e-05, | |
| "loss": 0.3672, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.7648902821316615e-05, | |
| "loss": 0.374, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.749216300940439e-05, | |
| "loss": 0.3301, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.7335423197492164e-05, | |
| "loss": 0.2942, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.7178683385579936e-05, | |
| "loss": 0.2841, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2.702194357366771e-05, | |
| "loss": 0.2873, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 2.686520376175549e-05, | |
| "loss": 0.319, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_accuracy": 0.8620329239613274, | |
| "eval_f1": 0.8591248665955177, | |
| "eval_loss": 0.3048080801963806, | |
| "eval_precision": 0.8669897684437264, | |
| "eval_recall": 0.8514013749338974, | |
| "eval_runtime": 111.0562, | |
| "eval_samples_per_second": 34.46, | |
| "eval_steps_per_second": 0.54, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 2.670846394984326e-05, | |
| "loss": 0.3004, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.6551724137931036e-05, | |
| "loss": 0.2666, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.6394984326018807e-05, | |
| "loss": 0.3005, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 2.6238244514106586e-05, | |
| "loss": 0.2986, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.6081504702194357e-05, | |
| "loss": 0.2848, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 2.5924764890282132e-05, | |
| "loss": 0.2733, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 2.5768025078369907e-05, | |
| "loss": 0.3, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 2.561128526645768e-05, | |
| "loss": 0.2949, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.5454545454545457e-05, | |
| "loss": 0.2754, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 2.529780564263323e-05, | |
| "loss": 0.2926, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_accuracy": 0.8630781290828325, | |
| "eval_f1": 0.8621052631578947, | |
| "eval_loss": 0.28672918677330017, | |
| "eval_precision": 0.858040859088528, | |
| "eval_recall": 0.8662083553675304, | |
| "eval_runtime": 110.1753, | |
| "eval_samples_per_second": 34.736, | |
| "eval_steps_per_second": 0.545, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 2.5141065830721003e-05, | |
| "loss": 0.2624, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2.498432601880878e-05, | |
| "loss": 0.289, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 2.4827586206896553e-05, | |
| "loss": 0.2474, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 2.4670846394984328e-05, | |
| "loss": 0.2608, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 2.45141065830721e-05, | |
| "loss": 0.2675, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 2.4357366771159875e-05, | |
| "loss": 0.2019, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 2.420062695924765e-05, | |
| "loss": 0.249, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 2.4043887147335425e-05, | |
| "loss": 0.2448, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 2.38871473354232e-05, | |
| "loss": 0.2159, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 2.373040752351097e-05, | |
| "loss": 0.1884, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_accuracy": 0.885550039195192, | |
| "eval_f1": 0.890115403913698, | |
| "eval_loss": 0.26350638270378113, | |
| "eval_precision": 0.8467780429594272, | |
| "eval_recall": 0.938127974616605, | |
| "eval_runtime": 109.3869, | |
| "eval_samples_per_second": 34.986, | |
| "eval_steps_per_second": 0.549, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 2.3573667711598746e-05, | |
| "loss": 0.234, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.341692789968652e-05, | |
| "loss": 0.2151, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.3260188087774296e-05, | |
| "loss": 0.2391, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.3103448275862067e-05, | |
| "loss": 0.2644, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 2.2946708463949842e-05, | |
| "loss": 0.2211, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 2.278996865203762e-05, | |
| "loss": 0.2327, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2.2633228840125392e-05, | |
| "loss": 0.2315, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.2476489028213167e-05, | |
| "loss": 0.2386, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.231974921630094e-05, | |
| "loss": 0.2363, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2.2163009404388717e-05, | |
| "loss": 0.234, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "eval_accuracy": 0.8813692187091716, | |
| "eval_f1": 0.8896451142440447, | |
| "eval_loss": 0.2639271020889282, | |
| "eval_precision": 0.8232118758434548, | |
| "eval_recall": 0.967741935483871, | |
| "eval_runtime": 110.312, | |
| "eval_samples_per_second": 34.692, | |
| "eval_steps_per_second": 0.544, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.2006269592476492e-05, | |
| "loss": 0.1994, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 2.1849529780564264e-05, | |
| "loss": 0.2286, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 2.169278996865204e-05, | |
| "loss": 0.219, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 2.153605015673981e-05, | |
| "loss": 0.2267, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2.137931034482759e-05, | |
| "loss": 0.2032, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.122257053291536e-05, | |
| "loss": 0.2334, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 2.1065830721003135e-05, | |
| "loss": 0.2013, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 2.090909090909091e-05, | |
| "loss": 0.2145, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 2.0752351097178685e-05, | |
| "loss": 0.2113, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 2.059561128526646e-05, | |
| "loss": 0.2349, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "eval_accuracy": 0.8873791481578259, | |
| "eval_f1": 0.8911341247789846, | |
| "eval_loss": 0.24775628745555878, | |
| "eval_precision": 0.8529980657640233, | |
| "eval_recall": 0.9328397673188789, | |
| "eval_runtime": 108.727, | |
| "eval_samples_per_second": 35.198, | |
| "eval_steps_per_second": 0.552, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 2.043887147335423e-05, | |
| "loss": 0.2177, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 2.0282131661442006e-05, | |
| "loss": 0.2257, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 2.012539184952978e-05, | |
| "loss": 0.2283, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.9968652037617556e-05, | |
| "loss": 0.1925, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.981191222570533e-05, | |
| "loss": 0.1603, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.9655172413793102e-05, | |
| "loss": 0.1712, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 1.9498432601880877e-05, | |
| "loss": 0.1476, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 1.9341692789968652e-05, | |
| "loss": 0.1266, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.9184952978056427e-05, | |
| "loss": 0.142, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.9028213166144202e-05, | |
| "loss": 0.1476, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "eval_accuracy": 0.8894695584008362, | |
| "eval_f1": 0.8926123381568927, | |
| "eval_loss": 0.25599205493927, | |
| "eval_precision": 0.8583984375, | |
| "eval_recall": 0.9296668429402433, | |
| "eval_runtime": 112.4052, | |
| "eval_samples_per_second": 34.046, | |
| "eval_steps_per_second": 0.534, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.8871473354231974e-05, | |
| "loss": 0.172, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 1.8714733542319752e-05, | |
| "loss": 0.1384, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 1.8557993730407524e-05, | |
| "loss": 0.1401, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.84012539184953e-05, | |
| "loss": 0.1554, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 1.824451410658307e-05, | |
| "loss": 0.1591, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 1.808777429467085e-05, | |
| "loss": 0.163, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 1.7931034482758623e-05, | |
| "loss": 0.1565, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 1.7774294670846395e-05, | |
| "loss": 0.1528, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 1.761755485893417e-05, | |
| "loss": 0.148, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 1.746081504702194e-05, | |
| "loss": 0.1289, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "eval_accuracy": 0.8868565455970734, | |
| "eval_f1": 0.8862023653088041, | |
| "eval_loss": 0.26980680227279663, | |
| "eval_precision": 0.8808777429467085, | |
| "eval_recall": 0.8915917503966155, | |
| "eval_runtime": 109.5776, | |
| "eval_samples_per_second": 34.925, | |
| "eval_steps_per_second": 0.548, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 1.730407523510972e-05, | |
| "loss": 0.137, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 1.714733542319749e-05, | |
| "loss": 0.1528, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 1.6990595611285266e-05, | |
| "loss": 0.1457, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 1.683385579937304e-05, | |
| "loss": 0.1398, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 1.6677115987460816e-05, | |
| "loss": 0.1447, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 1.652037617554859e-05, | |
| "loss": 0.1407, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 1.6363636363636363e-05, | |
| "loss": 0.1421, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 1.6206896551724137e-05, | |
| "loss": 0.1766, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 1.6065830721003135e-05, | |
| "loss": 0.1507, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 1.590909090909091e-05, | |
| "loss": 0.1579, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "eval_accuracy": 0.8821531225503005, | |
| "eval_f1": 0.8796370429677075, | |
| "eval_loss": 0.2614140808582306, | |
| "eval_precision": 0.8879310344827587, | |
| "eval_recall": 0.8714965626652564, | |
| "eval_runtime": 109.0275, | |
| "eval_samples_per_second": 35.101, | |
| "eval_steps_per_second": 0.55, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 1.5752351097178685e-05, | |
| "loss": 0.1416, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 1.5595611285266457e-05, | |
| "loss": 0.1502, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 1.543887147335423e-05, | |
| "loss": 0.1447, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 1.5282131661442007e-05, | |
| "loss": 0.1688, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 1.512539184952978e-05, | |
| "loss": 0.1594, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 1.4968652037617555e-05, | |
| "loss": 0.1427, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 1.481191222570533e-05, | |
| "loss": 0.0816, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 1.4655172413793105e-05, | |
| "loss": 0.0904, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 1.4498432601880878e-05, | |
| "loss": 0.079, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 1.4341692789968653e-05, | |
| "loss": 0.0745, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "eval_accuracy": 0.8889469558400837, | |
| "eval_f1": 0.8879514895860795, | |
| "eval_loss": 0.2783428430557251, | |
| "eval_precision": 0.8853838065194533, | |
| "eval_recall": 0.8905341089370703, | |
| "eval_runtime": 108.1962, | |
| "eval_samples_per_second": 35.371, | |
| "eval_steps_per_second": 0.555, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 1.4184952978056426e-05, | |
| "loss": 0.082, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 1.4028213166144201e-05, | |
| "loss": 0.0818, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 1.3871473354231976e-05, | |
| "loss": 0.0689, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 1.371473354231975e-05, | |
| "loss": 0.0733, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 1.3557993730407524e-05, | |
| "loss": 0.0725, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 1.3401253918495299e-05, | |
| "loss": 0.0693, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 1.3244514106583072e-05, | |
| "loss": 0.0844, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 1.3087774294670845e-05, | |
| "loss": 0.08, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 1.293103448275862e-05, | |
| "loss": 0.0726, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 1.2774294670846395e-05, | |
| "loss": 0.0697, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "eval_accuracy": 0.8899921609615887, | |
| "eval_f1": 0.8885948663667637, | |
| "eval_loss": 0.28440213203430176, | |
| "eval_precision": 0.8893008474576272, | |
| "eval_recall": 0.8878900052882073, | |
| "eval_runtime": 113.241, | |
| "eval_samples_per_second": 33.795, | |
| "eval_steps_per_second": 0.53, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 1.261755485893417e-05, | |
| "loss": 0.0637, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 1.2460815047021943e-05, | |
| "loss": 0.0866, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 1.2304075235109718e-05, | |
| "loss": 0.0798, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 1.2147335423197492e-05, | |
| "loss": 0.0826, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 1.1990595611285267e-05, | |
| "loss": 0.0695, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 1.1833855799373042e-05, | |
| "loss": 0.0508, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 1.1677115987460816e-05, | |
| "loss": 0.0728, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 1.152037617554859e-05, | |
| "loss": 0.0627, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 1.1363636363636365e-05, | |
| "loss": 0.0598, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 1.1206896551724138e-05, | |
| "loss": 0.0602, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "eval_accuracy": 0.8868565455970734, | |
| "eval_f1": 0.8863815271582262, | |
| "eval_loss": 0.3213111460208893, | |
| "eval_precision": 0.8796875, | |
| "eval_recall": 0.8931782125859333, | |
| "eval_runtime": 109.9441, | |
| "eval_samples_per_second": 34.809, | |
| "eval_steps_per_second": 0.546, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 1.1050156739811911e-05, | |
| "loss": 0.0743, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 1.0893416927899688e-05, | |
| "loss": 0.091, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 1.0736677115987461e-05, | |
| "loss": 0.0711, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 1.0595611285266457e-05, | |
| "loss": 0.0779, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 1.0438871473354232e-05, | |
| "loss": 0.0638, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 1.0282131661442005e-05, | |
| "loss": 0.0589, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 1.0125391849529782e-05, | |
| "loss": 0.076, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 9.968652037617555e-06, | |
| "loss": 0.0667, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 9.81191222570533e-06, | |
| "loss": 0.0327, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 9.655172413793103e-06, | |
| "loss": 0.0246, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "eval_accuracy": 0.8912986673634701, | |
| "eval_f1": 0.892116182572614, | |
| "eval_loss": 0.3393436670303345, | |
| "eval_precision": 0.8753180661577609, | |
| "eval_recall": 0.9095716552088842, | |
| "eval_runtime": 109.0634, | |
| "eval_samples_per_second": 35.09, | |
| "eval_steps_per_second": 0.55, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 9.498432601880878e-06, | |
| "loss": 0.0254, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 9.341692789968651e-06, | |
| "loss": 0.0187, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 9.184952978056428e-06, | |
| "loss": 0.0288, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 9.028213166144201e-06, | |
| "loss": 0.0204, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 8.871473354231975e-06, | |
| "loss": 0.0372, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 8.71473354231975e-06, | |
| "loss": 0.0286, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 8.557993730407523e-06, | |
| "loss": 0.0217, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 8.401253918495298e-06, | |
| "loss": 0.0223, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 8.244514106583073e-06, | |
| "loss": 0.0184, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 8.087774294670848e-06, | |
| "loss": 0.0301, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "eval_accuracy": 0.8936503788868565, | |
| "eval_f1": 0.896358543417367, | |
| "eval_loss": 0.3592565953731537, | |
| "eval_precision": 0.8644400785854617, | |
| "eval_recall": 0.9307244843997885, | |
| "eval_runtime": 109.1725, | |
| "eval_samples_per_second": 35.055, | |
| "eval_steps_per_second": 0.55, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 7.93103448275862e-06, | |
| "loss": 0.028, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 7.774294670846396e-06, | |
| "loss": 0.0221, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 7.617554858934169e-06, | |
| "loss": 0.0256, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 7.460815047021944e-06, | |
| "loss": 0.0266, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 7.304075235109718e-06, | |
| "loss": 0.0173, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 7.147335423197492e-06, | |
| "loss": 0.0228, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "learning_rate": 6.990595611285267e-06, | |
| "loss": 0.0189, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 6.833855799373041e-06, | |
| "loss": 0.0163, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 6.677115987460815e-06, | |
| "loss": 0.0195, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 6.520376175548589e-06, | |
| "loss": 0.0348, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "eval_accuracy": 0.8957407891298668, | |
| "eval_f1": 0.8985507246376812, | |
| "eval_loss": 0.38041359186172485, | |
| "eval_precision": 0.8653281096963761, | |
| "eval_recall": 0.9344262295081968, | |
| "eval_runtime": 109.9449, | |
| "eval_samples_per_second": 34.808, | |
| "eval_steps_per_second": 0.546, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 6.363636363636364e-06, | |
| "loss": 0.0193, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 6.206896551724138e-06, | |
| "loss": 0.0175, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 6.050156739811912e-06, | |
| "loss": 0.0244, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 5.8934169278996865e-06, | |
| "loss": 0.0395, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 5.736677115987461e-06, | |
| "loss": 0.0198, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 5.579937304075235e-06, | |
| "loss": 0.0178, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 5.42319749216301e-06, | |
| "loss": 0.0149, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 5.266457680250784e-06, | |
| "loss": 0.0261, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "learning_rate": 5.109717868338558e-06, | |
| "loss": 0.0178, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 4.952978056426333e-06, | |
| "loss": 0.011, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "eval_accuracy": 0.8946955840083617, | |
| "eval_f1": 0.8978453738910013, | |
| "eval_loss": 0.38965746760368347, | |
| "eval_precision": 0.8622200584225901, | |
| "eval_recall": 0.9365415124272871, | |
| "eval_runtime": 109.9915, | |
| "eval_samples_per_second": 34.794, | |
| "eval_steps_per_second": 0.545, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 4.796238244514107e-06, | |
| "loss": 0.0109, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "learning_rate": 4.639498432601881e-06, | |
| "loss": 0.0092, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 4.482758620689656e-06, | |
| "loss": 0.0092, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 4.32601880877743e-06, | |
| "loss": 0.0084, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 4.169278996865204e-06, | |
| "loss": 0.0076, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 4.012539184952979e-06, | |
| "loss": 0.0056, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 3.855799373040752e-06, | |
| "loss": 0.0057, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 3.6990595611285267e-06, | |
| "loss": 0.0055, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 3.542319749216301e-06, | |
| "loss": 0.0045, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "learning_rate": 3.3855799373040753e-06, | |
| "loss": 0.0077, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "eval_accuracy": 0.894956885288738, | |
| "eval_f1": 0.8962312854930304, | |
| "eval_loss": 0.408812940120697, | |
| "eval_precision": 0.875441250630358, | |
| "eval_recall": 0.9180327868852459, | |
| "eval_runtime": 109.202, | |
| "eval_samples_per_second": 35.045, | |
| "eval_steps_per_second": 0.549, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 5.36, | |
| "learning_rate": 3.2288401253918494e-06, | |
| "loss": 0.0091, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 5.39, | |
| "learning_rate": 3.072100313479624e-06, | |
| "loss": 0.0032, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "learning_rate": 2.915360501567398e-06, | |
| "loss": 0.0044, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 2.7586206896551725e-06, | |
| "loss": 0.0052, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "learning_rate": 2.601880877742947e-06, | |
| "loss": 0.0049, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "learning_rate": 2.445141065830721e-06, | |
| "loss": 0.006, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 5.55, | |
| "learning_rate": 2.288401253918495e-06, | |
| "loss": 0.0035, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 5.58, | |
| "learning_rate": 2.1316614420062697e-06, | |
| "loss": 0.0041, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 1.9749216300940438e-06, | |
| "loss": 0.0076, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "learning_rate": 1.8181818181818183e-06, | |
| "loss": 0.0064, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "eval_accuracy": 0.896002090410243, | |
| "eval_f1": 0.8970512157268494, | |
| "eval_loss": 0.4281201958656311, | |
| "eval_precision": 0.8779746835443037, | |
| "eval_recall": 0.9169751454257007, | |
| "eval_runtime": 109.7966, | |
| "eval_samples_per_second": 34.855, | |
| "eval_steps_per_second": 0.546, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 1.6614420062695926e-06, | |
| "loss": 0.004, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 1.5047021943573667e-06, | |
| "loss": 0.0041, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 5.74, | |
| "learning_rate": 1.3479623824451412e-06, | |
| "loss": 0.0038, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "learning_rate": 1.1912225705329155e-06, | |
| "loss": 0.0044, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 1.0344827586206896e-06, | |
| "loss": 0.0024, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 5.83, | |
| "learning_rate": 8.77742946708464e-07, | |
| "loss": 0.0045, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 7.210031347962383e-07, | |
| "loss": 0.0047, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "learning_rate": 5.642633228840126e-07, | |
| "loss": 0.0038, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 5.92, | |
| "learning_rate": 4.0752351097178683e-07, | |
| "loss": 0.0038, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "learning_rate": 2.507836990595612e-07, | |
| "loss": 0.0031, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "eval_accuracy": 0.894956885288738, | |
| "eval_f1": 0.8964984552008239, | |
| "eval_loss": 0.42887693643569946, | |
| "eval_precision": 0.8735574510787757, | |
| "eval_recall": 0.920676890534109, | |
| "eval_runtime": 113.2911, | |
| "eval_samples_per_second": 33.78, | |
| "eval_steps_per_second": 0.53, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "learning_rate": 9.404388714733542e-08, | |
| "loss": 0.0047, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "step": 1914, | |
| "total_flos": 1.4238223187805905e+19, | |
| "train_loss": 0.13623220103334482, | |
| "train_runtime": 9420.2145, | |
| "train_samples_per_second": 19.505, | |
| "train_steps_per_second": 0.203 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8923719958202717, | |
| "eval_f1": 0.8937048503611971, | |
| "eval_loss": 0.37740620970726013, | |
| "eval_precision": 0.858701041150223, | |
| "eval_recall": 0.9316837009144702, | |
| "eval_runtime": 109.2986, | |
| "eval_samples_per_second": 35.023, | |
| "eval_steps_per_second": 0.549, | |
| "step": 1914 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1914, | |
| "num_train_epochs": 6, | |
| "save_steps": 100, | |
| "total_flos": 1.4238223187805905e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |