| { |
| "best_metric": 0.2617954611778259, |
| "best_model_checkpoint": "./vit-base-binary-isic-patch-32/checkpoint-1400", |
| "epoch": 4.0, |
| "global_step": 4304, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.01, |
| "learning_rate": 0.0001995353159851301, |
| "loss": 0.5769, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 0.00019907063197026022, |
| "loss": 0.417, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 0.00019860594795539035, |
| "loss": 0.4311, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.04, |
| "learning_rate": 0.00019814126394052047, |
| "loss": 0.3758, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 0.00019767657992565056, |
| "loss": 0.3708, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 0.00019721189591078068, |
| "loss": 0.4628, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 0.00019674721189591078, |
| "loss": 0.3757, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 0.00019628252788104092, |
| "loss": 0.394, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 0.00019581784386617102, |
| "loss": 0.5184, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 0.0001953531598513011, |
| "loss": 0.4617, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.09, |
| "eval_accuracy": 0.8083034341363403, |
| "eval_f1": 0.8083034341363403, |
| "eval_loss": 0.4375462830066681, |
| "eval_precision": 0.8083034341363403, |
| "eval_recall": 0.8083034341363403, |
| "eval_runtime": 66.4138, |
| "eval_samples_per_second": 117.506, |
| "eval_steps_per_second": 14.696, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 0.00019488847583643123, |
| "loss": 0.436, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 0.00019442379182156135, |
| "loss": 0.4712, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 0.00019395910780669148, |
| "loss": 0.289, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 0.00019349442379182157, |
| "loss": 0.3924, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 0.0001930297397769517, |
| "loss": 0.3118, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 0.00019256505576208178, |
| "loss": 0.2839, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 0.0001921003717472119, |
| "loss": 0.3411, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 0.00019163568773234203, |
| "loss": 0.3355, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 0.00019117100371747212, |
| "loss": 0.2539, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.00019070631970260224, |
| "loss": 0.28, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.19, |
| "eval_accuracy": 0.8575089697590978, |
| "eval_f1": 0.8575089697590978, |
| "eval_loss": 0.33516696095466614, |
| "eval_precision": 0.8575089697590978, |
| "eval_recall": 0.8575089697590978, |
| "eval_runtime": 66.1826, |
| "eval_samples_per_second": 117.916, |
| "eval_steps_per_second": 14.747, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 0.00019024163568773234, |
| "loss": 0.2905, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 0.00018977695167286246, |
| "loss": 0.3076, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 0.00018931226765799258, |
| "loss": 0.2826, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 0.0001888475836431227, |
| "loss": 0.2298, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 0.0001883828996282528, |
| "loss": 0.366, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 0.00018791821561338291, |
| "loss": 0.3178, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 0.000187453531598513, |
| "loss": 0.3823, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 0.00018698884758364313, |
| "loss": 0.2731, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 0.00018652416356877325, |
| "loss": 0.3478, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 0.00018605947955390334, |
| "loss": 0.2684, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.28, |
| "eval_accuracy": 0.8521271143003588, |
| "eval_f1": 0.8521271143003588, |
| "eval_loss": 0.30809658765792847, |
| "eval_precision": 0.8521271143003588, |
| "eval_recall": 0.8521271143003588, |
| "eval_runtime": 66.3034, |
| "eval_samples_per_second": 117.701, |
| "eval_steps_per_second": 14.72, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 0.00018559479553903347, |
| "loss": 0.2913, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 0.00018513011152416359, |
| "loss": 0.2884, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 0.0001846654275092937, |
| "loss": 0.2848, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 0.0001842007434944238, |
| "loss": 0.286, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 0.0001837360594795539, |
| "loss": 0.3444, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 0.00018327137546468402, |
| "loss": 0.3759, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 0.00018280669144981414, |
| "loss": 0.2864, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 0.00018234200743494426, |
| "loss": 0.2414, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 0.00018187732342007435, |
| "loss": 0.2437, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 0.00018141263940520447, |
| "loss": 0.2755, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.37, |
| "eval_accuracy": 0.8432854946181445, |
| "eval_f1": 0.8432854946181444, |
| "eval_loss": 0.34891098737716675, |
| "eval_precision": 0.8432854946181445, |
| "eval_recall": 0.8432854946181445, |
| "eval_runtime": 66.5005, |
| "eval_samples_per_second": 117.352, |
| "eval_steps_per_second": 14.677, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 0.00018094795539033457, |
| "loss": 0.3481, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 0.0001804832713754647, |
| "loss": 0.3405, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 0.0001800185873605948, |
| "loss": 0.2727, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.41, |
| "learning_rate": 0.0001795539033457249, |
| "loss": 0.2082, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 0.00017908921933085502, |
| "loss": 0.2912, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 0.00017862453531598512, |
| "loss": 0.2474, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 0.00017815985130111527, |
| "loss": 0.288, |
| "step": 470 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 0.00017769516728624536, |
| "loss": 0.2555, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 0.00017723048327137548, |
| "loss": 0.3658, |
| "step": 490 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 0.00017676579925650558, |
| "loss": 0.2683, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.46, |
| "eval_accuracy": 0.8120194771911841, |
| "eval_f1": 0.8120194771911842, |
| "eval_loss": 0.3533369302749634, |
| "eval_precision": 0.8120194771911841, |
| "eval_recall": 0.8120194771911841, |
| "eval_runtime": 66.3905, |
| "eval_samples_per_second": 117.547, |
| "eval_steps_per_second": 14.701, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 0.0001763011152416357, |
| "loss": 0.2198, |
| "step": 510 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 0.00017583643122676582, |
| "loss": 0.2941, |
| "step": 520 |
| }, |
| { |
| "epoch": 0.49, |
| "learning_rate": 0.0001753717472118959, |
| "loss": 0.3111, |
| "step": 530 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 0.00017490706319702603, |
| "loss": 0.203, |
| "step": 540 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 0.00017444237918215613, |
| "loss": 0.231, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 0.00017397769516728625, |
| "loss": 0.2677, |
| "step": 560 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 0.00017351301115241637, |
| "loss": 0.2691, |
| "step": 570 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 0.0001730483271375465, |
| "loss": 0.2573, |
| "step": 580 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 0.00017258364312267658, |
| "loss": 0.2687, |
| "step": 590 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 0.0001721189591078067, |
| "loss": 0.2013, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.56, |
| "eval_accuracy": 0.8682726806765761, |
| "eval_f1": 0.8682726806765761, |
| "eval_loss": 0.3403525650501251, |
| "eval_precision": 0.8682726806765761, |
| "eval_recall": 0.8682726806765761, |
| "eval_runtime": 66.8888, |
| "eval_samples_per_second": 116.671, |
| "eval_steps_per_second": 14.591, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.57, |
| "learning_rate": 0.0001716542750929368, |
| "loss": 0.2562, |
| "step": 610 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 0.00017118959107806692, |
| "loss": 0.2518, |
| "step": 620 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 0.00017072490706319704, |
| "loss": 0.2, |
| "step": 630 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 0.00017026022304832714, |
| "loss": 0.2618, |
| "step": 640 |
| }, |
| { |
| "epoch": 0.6, |
| "learning_rate": 0.00016979553903345726, |
| "loss": 0.2193, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.61, |
| "learning_rate": 0.00016933085501858735, |
| "loss": 0.288, |
| "step": 660 |
| }, |
| { |
| "epoch": 0.62, |
| "learning_rate": 0.0001688661710037175, |
| "loss": 0.2052, |
| "step": 670 |
| }, |
| { |
| "epoch": 0.63, |
| "learning_rate": 0.0001684014869888476, |
| "loss": 0.2946, |
| "step": 680 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 0.00016793680297397771, |
| "loss": 0.2439, |
| "step": 690 |
| }, |
| { |
| "epoch": 0.65, |
| "learning_rate": 0.0001674721189591078, |
| "loss": 0.2892, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.65, |
| "eval_accuracy": 0.8687852383393132, |
| "eval_f1": 0.8687852383393132, |
| "eval_loss": 0.2949552834033966, |
| "eval_precision": 0.8687852383393132, |
| "eval_recall": 0.8687852383393132, |
| "eval_runtime": 66.6611, |
| "eval_samples_per_second": 117.07, |
| "eval_steps_per_second": 14.641, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.66, |
| "learning_rate": 0.00016700743494423793, |
| "loss": 0.2619, |
| "step": 710 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 0.00016654275092936805, |
| "loss": 0.2083, |
| "step": 720 |
| }, |
| { |
| "epoch": 0.68, |
| "learning_rate": 0.00016607806691449814, |
| "loss": 0.2823, |
| "step": 730 |
| }, |
| { |
| "epoch": 0.69, |
| "learning_rate": 0.00016561338289962827, |
| "loss": 0.3511, |
| "step": 740 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 0.00016514869888475836, |
| "loss": 0.1567, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.71, |
| "learning_rate": 0.00016468401486988848, |
| "loss": 0.1868, |
| "step": 760 |
| }, |
| { |
| "epoch": 0.72, |
| "learning_rate": 0.0001642193308550186, |
| "loss": 0.2821, |
| "step": 770 |
| }, |
| { |
| "epoch": 0.72, |
| "learning_rate": 0.00016375464684014872, |
| "loss": 0.4099, |
| "step": 780 |
| }, |
| { |
| "epoch": 0.73, |
| "learning_rate": 0.00016328996282527882, |
| "loss": 0.2207, |
| "step": 790 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 0.0001628252788104089, |
| "loss": 0.2326, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.74, |
| "eval_accuracy": 0.8874935930292158, |
| "eval_f1": 0.8874935930292158, |
| "eval_loss": 0.2857530117034912, |
| "eval_precision": 0.8874935930292158, |
| "eval_recall": 0.8874935930292158, |
| "eval_runtime": 66.3946, |
| "eval_samples_per_second": 117.54, |
| "eval_steps_per_second": 14.7, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 0.00016236059479553903, |
| "loss": 0.1598, |
| "step": 810 |
| }, |
| { |
| "epoch": 0.76, |
| "learning_rate": 0.00016189591078066915, |
| "loss": 0.3847, |
| "step": 820 |
| }, |
| { |
| "epoch": 0.77, |
| "learning_rate": 0.00016143122676579927, |
| "loss": 0.3366, |
| "step": 830 |
| }, |
| { |
| "epoch": 0.78, |
| "learning_rate": 0.00016096654275092937, |
| "loss": 0.2052, |
| "step": 840 |
| }, |
| { |
| "epoch": 0.79, |
| "learning_rate": 0.0001605018587360595, |
| "loss": 0.2194, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.8, |
| "learning_rate": 0.0001600371747211896, |
| "loss": 0.1395, |
| "step": 860 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 0.0001595724907063197, |
| "loss": 0.3277, |
| "step": 870 |
| }, |
| { |
| "epoch": 0.82, |
| "learning_rate": 0.00015910780669144982, |
| "loss": 0.1741, |
| "step": 880 |
| }, |
| { |
| "epoch": 0.83, |
| "learning_rate": 0.00015864312267657992, |
| "loss": 0.215, |
| "step": 890 |
| }, |
| { |
| "epoch": 0.84, |
| "learning_rate": 0.00015817843866171004, |
| "loss": 0.2642, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.84, |
| "eval_accuracy": 0.8666068682726806, |
| "eval_f1": 0.8666068682726806, |
| "eval_loss": 0.317574143409729, |
| "eval_precision": 0.8666068682726806, |
| "eval_recall": 0.8666068682726806, |
| "eval_runtime": 66.4647, |
| "eval_samples_per_second": 117.416, |
| "eval_steps_per_second": 14.684, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.85, |
| "learning_rate": 0.00015771375464684016, |
| "loss": 0.1681, |
| "step": 910 |
| }, |
| { |
| "epoch": 0.86, |
| "learning_rate": 0.00015724907063197028, |
| "loss": 0.2367, |
| "step": 920 |
| }, |
| { |
| "epoch": 0.86, |
| "learning_rate": 0.00015678438661710038, |
| "loss": 0.1929, |
| "step": 930 |
| }, |
| { |
| "epoch": 0.87, |
| "learning_rate": 0.0001563197026022305, |
| "loss": 0.3496, |
| "step": 940 |
| }, |
| { |
| "epoch": 0.88, |
| "learning_rate": 0.0001558550185873606, |
| "loss": 0.19, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.89, |
| "learning_rate": 0.0001553903345724907, |
| "loss": 0.2852, |
| "step": 960 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 0.00015492565055762083, |
| "loss": 0.1865, |
| "step": 970 |
| }, |
| { |
| "epoch": 0.91, |
| "learning_rate": 0.00015446096654275093, |
| "loss": 0.1807, |
| "step": 980 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 0.00015399628252788105, |
| "loss": 0.2201, |
| "step": 990 |
| }, |
| { |
| "epoch": 0.93, |
| "learning_rate": 0.00015353159851301114, |
| "loss": 0.1676, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.93, |
| "eval_accuracy": 0.8726294208098411, |
| "eval_f1": 0.8726294208098411, |
| "eval_loss": 0.30488839745521545, |
| "eval_precision": 0.8726294208098411, |
| "eval_recall": 0.8726294208098411, |
| "eval_runtime": 66.3608, |
| "eval_samples_per_second": 117.6, |
| "eval_steps_per_second": 14.707, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.94, |
| "learning_rate": 0.0001530669144981413, |
| "loss": 0.1966, |
| "step": 1010 |
| }, |
| { |
| "epoch": 0.95, |
| "learning_rate": 0.00015260223048327138, |
| "loss": 0.2201, |
| "step": 1020 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 0.0001521375464684015, |
| "loss": 0.2339, |
| "step": 1030 |
| }, |
| { |
| "epoch": 0.97, |
| "learning_rate": 0.0001516728624535316, |
| "loss": 0.2185, |
| "step": 1040 |
| }, |
| { |
| "epoch": 0.98, |
| "learning_rate": 0.00015120817843866172, |
| "loss": 0.3148, |
| "step": 1050 |
| }, |
| { |
| "epoch": 0.99, |
| "learning_rate": 0.00015074349442379184, |
| "loss": 0.2023, |
| "step": 1060 |
| }, |
| { |
| "epoch": 0.99, |
| "learning_rate": 0.00015027881040892194, |
| "loss": 0.233, |
| "step": 1070 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 0.00014981412639405206, |
| "loss": 0.1473, |
| "step": 1080 |
| }, |
| { |
| "epoch": 1.01, |
| "learning_rate": 0.00014934944237918215, |
| "loss": 0.163, |
| "step": 1090 |
| }, |
| { |
| "epoch": 1.02, |
| "learning_rate": 0.00014888475836431227, |
| "loss": 0.1002, |
| "step": 1100 |
| }, |
| { |
| "epoch": 1.02, |
| "eval_accuracy": 0.8796770886724756, |
| "eval_f1": 0.8796770886724756, |
| "eval_loss": 0.3511936068534851, |
| "eval_precision": 0.8796770886724756, |
| "eval_recall": 0.8796770886724756, |
| "eval_runtime": 66.5352, |
| "eval_samples_per_second": 117.291, |
| "eval_steps_per_second": 14.669, |
| "step": 1100 |
| }, |
| { |
| "epoch": 1.03, |
| "learning_rate": 0.0001484200743494424, |
| "loss": 0.1181, |
| "step": 1110 |
| }, |
| { |
| "epoch": 1.04, |
| "learning_rate": 0.00014795539033457251, |
| "loss": 0.1446, |
| "step": 1120 |
| }, |
| { |
| "epoch": 1.05, |
| "learning_rate": 0.0001474907063197026, |
| "loss": 0.0893, |
| "step": 1130 |
| }, |
| { |
| "epoch": 1.06, |
| "learning_rate": 0.0001470260223048327, |
| "loss": 0.2209, |
| "step": 1140 |
| }, |
| { |
| "epoch": 1.07, |
| "learning_rate": 0.00014656133828996282, |
| "loss": 0.1739, |
| "step": 1150 |
| }, |
| { |
| "epoch": 1.08, |
| "learning_rate": 0.00014609665427509294, |
| "loss": 0.2015, |
| "step": 1160 |
| }, |
| { |
| "epoch": 1.09, |
| "learning_rate": 0.00014563197026022307, |
| "loss": 0.1425, |
| "step": 1170 |
| }, |
| { |
| "epoch": 1.1, |
| "learning_rate": 0.00014516728624535316, |
| "loss": 0.2311, |
| "step": 1180 |
| }, |
| { |
| "epoch": 1.11, |
| "learning_rate": 0.00014470260223048328, |
| "loss": 0.1539, |
| "step": 1190 |
| }, |
| { |
| "epoch": 1.12, |
| "learning_rate": 0.00014423791821561337, |
| "loss": 0.1888, |
| "step": 1200 |
| }, |
| { |
| "epoch": 1.12, |
| "eval_accuracy": 0.8566119938493081, |
| "eval_f1": 0.8566119938493082, |
| "eval_loss": 0.3286292552947998, |
| "eval_precision": 0.8566119938493081, |
| "eval_recall": 0.8566119938493081, |
| "eval_runtime": 66.7548, |
| "eval_samples_per_second": 116.905, |
| "eval_steps_per_second": 14.621, |
| "step": 1200 |
| }, |
| { |
| "epoch": 1.12, |
| "learning_rate": 0.00014377323420074352, |
| "loss": 0.1954, |
| "step": 1210 |
| }, |
| { |
| "epoch": 1.13, |
| "learning_rate": 0.00014330855018587362, |
| "loss": 0.1734, |
| "step": 1220 |
| }, |
| { |
| "epoch": 1.14, |
| "learning_rate": 0.0001428438661710037, |
| "loss": 0.1415, |
| "step": 1230 |
| }, |
| { |
| "epoch": 1.15, |
| "learning_rate": 0.00014237918215613383, |
| "loss": 0.1757, |
| "step": 1240 |
| }, |
| { |
| "epoch": 1.16, |
| "learning_rate": 0.00014191449814126395, |
| "loss": 0.1581, |
| "step": 1250 |
| }, |
| { |
| "epoch": 1.17, |
| "learning_rate": 0.00014144981412639407, |
| "loss": 0.16, |
| "step": 1260 |
| }, |
| { |
| "epoch": 1.18, |
| "learning_rate": 0.00014098513011152417, |
| "loss": 0.1833, |
| "step": 1270 |
| }, |
| { |
| "epoch": 1.19, |
| "learning_rate": 0.0001405204460966543, |
| "loss": 0.1713, |
| "step": 1280 |
| }, |
| { |
| "epoch": 1.2, |
| "learning_rate": 0.00014005576208178438, |
| "loss": 0.1731, |
| "step": 1290 |
| }, |
| { |
| "epoch": 1.21, |
| "learning_rate": 0.0001395910780669145, |
| "loss": 0.134, |
| "step": 1300 |
| }, |
| { |
| "epoch": 1.21, |
| "eval_accuracy": 0.8660943106099436, |
| "eval_f1": 0.8660943106099436, |
| "eval_loss": 0.31784388422966003, |
| "eval_precision": 0.8660943106099436, |
| "eval_recall": 0.8660943106099436, |
| "eval_runtime": 66.3638, |
| "eval_samples_per_second": 117.594, |
| "eval_steps_per_second": 14.707, |
| "step": 1300 |
| }, |
| { |
| "epoch": 1.22, |
| "learning_rate": 0.00013912639405204463, |
| "loss": 0.1777, |
| "step": 1310 |
| }, |
| { |
| "epoch": 1.23, |
| "learning_rate": 0.00013866171003717472, |
| "loss": 0.1357, |
| "step": 1320 |
| }, |
| { |
| "epoch": 1.24, |
| "learning_rate": 0.00013819702602230484, |
| "loss": 0.2282, |
| "step": 1330 |
| }, |
| { |
| "epoch": 1.25, |
| "learning_rate": 0.00013773234200743493, |
| "loss": 0.1245, |
| "step": 1340 |
| }, |
| { |
| "epoch": 1.25, |
| "learning_rate": 0.00013726765799256506, |
| "loss": 0.1217, |
| "step": 1350 |
| }, |
| { |
| "epoch": 1.26, |
| "learning_rate": 0.00013680297397769518, |
| "loss": 0.128, |
| "step": 1360 |
| }, |
| { |
| "epoch": 1.27, |
| "learning_rate": 0.0001363382899628253, |
| "loss": 0.1342, |
| "step": 1370 |
| }, |
| { |
| "epoch": 1.28, |
| "learning_rate": 0.0001358736059479554, |
| "loss": 0.243, |
| "step": 1380 |
| }, |
| { |
| "epoch": 1.29, |
| "learning_rate": 0.00013540892193308549, |
| "loss": 0.1637, |
| "step": 1390 |
| }, |
| { |
| "epoch": 1.3, |
| "learning_rate": 0.00013494423791821563, |
| "loss": 0.1085, |
| "step": 1400 |
| }, |
| { |
| "epoch": 1.3, |
| "eval_accuracy": 0.8896719630958483, |
| "eval_f1": 0.8896719630958483, |
| "eval_loss": 0.2617954611778259, |
| "eval_precision": 0.8896719630958483, |
| "eval_recall": 0.8896719630958483, |
| "eval_runtime": 66.4194, |
| "eval_samples_per_second": 117.496, |
| "eval_steps_per_second": 14.695, |
| "step": 1400 |
| }, |
| { |
| "epoch": 1.31, |
| "learning_rate": 0.00013447955390334573, |
| "loss": 0.1107, |
| "step": 1410 |
| }, |
| { |
| "epoch": 1.32, |
| "learning_rate": 0.00013401486988847585, |
| "loss": 0.1039, |
| "step": 1420 |
| }, |
| { |
| "epoch": 1.33, |
| "learning_rate": 0.00013355018587360594, |
| "loss": 0.1017, |
| "step": 1430 |
| }, |
| { |
| "epoch": 1.34, |
| "learning_rate": 0.00013308550185873606, |
| "loss": 0.2075, |
| "step": 1440 |
| }, |
| { |
| "epoch": 1.35, |
| "learning_rate": 0.00013262081784386618, |
| "loss": 0.1884, |
| "step": 1450 |
| }, |
| { |
| "epoch": 1.36, |
| "learning_rate": 0.0001321561338289963, |
| "loss": 0.2002, |
| "step": 1460 |
| }, |
| { |
| "epoch": 1.37, |
| "learning_rate": 0.0001316914498141264, |
| "loss": 0.1235, |
| "step": 1470 |
| }, |
| { |
| "epoch": 1.38, |
| "learning_rate": 0.0001312267657992565, |
| "loss": 0.1129, |
| "step": 1480 |
| }, |
| { |
| "epoch": 1.38, |
| "learning_rate": 0.00013076208178438661, |
| "loss": 0.1135, |
| "step": 1490 |
| }, |
| { |
| "epoch": 1.39, |
| "learning_rate": 0.00013029739776951674, |
| "loss": 0.189, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.39, |
| "eval_accuracy": 0.8736545361353152, |
| "eval_f1": 0.8736545361353152, |
| "eval_loss": 0.3490007817745209, |
| "eval_precision": 0.8736545361353152, |
| "eval_recall": 0.8736545361353152, |
| "eval_runtime": 66.3918, |
| "eval_samples_per_second": 117.545, |
| "eval_steps_per_second": 14.701, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.4, |
| "learning_rate": 0.00012983271375464686, |
| "loss": 0.253, |
| "step": 1510 |
| }, |
| { |
| "epoch": 1.41, |
| "learning_rate": 0.00012936802973977695, |
| "loss": 0.1548, |
| "step": 1520 |
| }, |
| { |
| "epoch": 1.42, |
| "learning_rate": 0.00012890334572490707, |
| "loss": 0.1097, |
| "step": 1530 |
| }, |
| { |
| "epoch": 1.43, |
| "learning_rate": 0.00012843866171003717, |
| "loss": 0.1006, |
| "step": 1540 |
| }, |
| { |
| "epoch": 1.44, |
| "learning_rate": 0.00012797397769516731, |
| "loss": 0.2097, |
| "step": 1550 |
| }, |
| { |
| "epoch": 1.45, |
| "learning_rate": 0.0001275092936802974, |
| "loss": 0.1861, |
| "step": 1560 |
| }, |
| { |
| "epoch": 1.46, |
| "learning_rate": 0.0001270446096654275, |
| "loss": 0.1229, |
| "step": 1570 |
| }, |
| { |
| "epoch": 1.47, |
| "learning_rate": 0.00012657992565055762, |
| "loss": 0.102, |
| "step": 1580 |
| }, |
| { |
| "epoch": 1.48, |
| "learning_rate": 0.00012611524163568772, |
| "loss": 0.1499, |
| "step": 1590 |
| }, |
| { |
| "epoch": 1.49, |
| "learning_rate": 0.00012565055762081787, |
| "loss": 0.1781, |
| "step": 1600 |
| }, |
| { |
| "epoch": 1.49, |
| "eval_accuracy": 0.8727575602255254, |
| "eval_f1": 0.8727575602255254, |
| "eval_loss": 0.3032713830471039, |
| "eval_precision": 0.8727575602255254, |
| "eval_recall": 0.8727575602255254, |
| "eval_runtime": 66.5418, |
| "eval_samples_per_second": 117.28, |
| "eval_steps_per_second": 14.667, |
| "step": 1600 |
| }, |
| { |
| "epoch": 1.5, |
| "learning_rate": 0.00012518587360594796, |
| "loss": 0.1255, |
| "step": 1610 |
| }, |
| { |
| "epoch": 1.51, |
| "learning_rate": 0.00012472118959107808, |
| "loss": 0.1935, |
| "step": 1620 |
| }, |
| { |
| "epoch": 1.51, |
| "learning_rate": 0.00012425650557620817, |
| "loss": 0.2025, |
| "step": 1630 |
| }, |
| { |
| "epoch": 1.52, |
| "learning_rate": 0.0001237918215613383, |
| "loss": 0.1018, |
| "step": 1640 |
| }, |
| { |
| "epoch": 1.53, |
| "learning_rate": 0.00012332713754646842, |
| "loss": 0.1196, |
| "step": 1650 |
| }, |
| { |
| "epoch": 1.54, |
| "learning_rate": 0.0001228624535315985, |
| "loss": 0.151, |
| "step": 1660 |
| }, |
| { |
| "epoch": 1.55, |
| "learning_rate": 0.00012239776951672863, |
| "loss": 0.1108, |
| "step": 1670 |
| }, |
| { |
| "epoch": 1.56, |
| "learning_rate": 0.00012193308550185874, |
| "loss": 0.1645, |
| "step": 1680 |
| }, |
| { |
| "epoch": 1.57, |
| "learning_rate": 0.00012146840148698886, |
| "loss": 0.0958, |
| "step": 1690 |
| }, |
| { |
| "epoch": 1.58, |
| "learning_rate": 0.00012100371747211895, |
| "loss": 0.0788, |
| "step": 1700 |
| }, |
| { |
| "epoch": 1.58, |
| "eval_accuracy": 0.8773705791901589, |
| "eval_f1": 0.8773705791901589, |
| "eval_loss": 0.3623415231704712, |
| "eval_precision": 0.8773705791901589, |
| "eval_recall": 0.8773705791901589, |
| "eval_runtime": 66.0334, |
| "eval_samples_per_second": 118.183, |
| "eval_steps_per_second": 14.78, |
| "step": 1700 |
| }, |
| { |
| "epoch": 1.59, |
| "learning_rate": 0.00012053903345724909, |
| "loss": 0.0737, |
| "step": 1710 |
| }, |
| { |
| "epoch": 1.6, |
| "learning_rate": 0.00012007434944237918, |
| "loss": 0.1594, |
| "step": 1720 |
| }, |
| { |
| "epoch": 1.61, |
| "learning_rate": 0.0001196096654275093, |
| "loss": 0.0925, |
| "step": 1730 |
| }, |
| { |
| "epoch": 1.62, |
| "learning_rate": 0.00011914498141263941, |
| "loss": 0.0653, |
| "step": 1740 |
| }, |
| { |
| "epoch": 1.63, |
| "learning_rate": 0.00011868029739776952, |
| "loss": 0.1623, |
| "step": 1750 |
| }, |
| { |
| "epoch": 1.64, |
| "learning_rate": 0.00011821561338289964, |
| "loss": 0.1621, |
| "step": 1760 |
| }, |
| { |
| "epoch": 1.64, |
| "learning_rate": 0.00011775092936802973, |
| "loss": 0.1171, |
| "step": 1770 |
| }, |
| { |
| "epoch": 1.65, |
| "learning_rate": 0.00011728624535315987, |
| "loss": 0.1406, |
| "step": 1780 |
| }, |
| { |
| "epoch": 1.66, |
| "learning_rate": 0.00011682156133828996, |
| "loss": 0.1442, |
| "step": 1790 |
| }, |
| { |
| "epoch": 1.67, |
| "learning_rate": 0.00011635687732342008, |
| "loss": 0.1135, |
| "step": 1800 |
| }, |
| { |
| "epoch": 1.67, |
| "eval_accuracy": 0.8687852383393132, |
| "eval_f1": 0.8687852383393132, |
| "eval_loss": 0.33408355712890625, |
| "eval_precision": 0.8687852383393132, |
| "eval_recall": 0.8687852383393132, |
| "eval_runtime": 66.0554, |
| "eval_samples_per_second": 118.143, |
| "eval_steps_per_second": 14.775, |
| "step": 1800 |
| }, |
| { |
| "epoch": 1.68, |
| "learning_rate": 0.00011589219330855019, |
| "loss": 0.1214, |
| "step": 1810 |
| }, |
| { |
| "epoch": 1.69, |
| "learning_rate": 0.00011542750929368031, |
| "loss": 0.2146, |
| "step": 1820 |
| }, |
| { |
| "epoch": 1.7, |
| "learning_rate": 0.00011496282527881042, |
| "loss": 0.1605, |
| "step": 1830 |
| }, |
| { |
| "epoch": 1.71, |
| "learning_rate": 0.00011449814126394051, |
| "loss": 0.1619, |
| "step": 1840 |
| }, |
| { |
| "epoch": 1.72, |
| "learning_rate": 0.00011403345724907064, |
| "loss": 0.1122, |
| "step": 1850 |
| }, |
| { |
| "epoch": 1.73, |
| "learning_rate": 0.00011356877323420074, |
| "loss": 0.1836, |
| "step": 1860 |
| }, |
| { |
| "epoch": 1.74, |
| "learning_rate": 0.00011310408921933086, |
| "loss": 0.0742, |
| "step": 1870 |
| }, |
| { |
| "epoch": 1.75, |
| "learning_rate": 0.00011263940520446097, |
| "loss": 0.194, |
| "step": 1880 |
| }, |
| { |
| "epoch": 1.76, |
| "learning_rate": 0.00011217472118959109, |
| "loss": 0.1294, |
| "step": 1890 |
| }, |
| { |
| "epoch": 1.77, |
| "learning_rate": 0.0001117100371747212, |
| "loss": 0.0607, |
| "step": 1900 |
| }, |
| { |
| "epoch": 1.77, |
| "eval_accuracy": 0.8873654536135315, |
| "eval_f1": 0.8873654536135316, |
| "eval_loss": 0.295357882976532, |
| "eval_precision": 0.8873654536135315, |
| "eval_recall": 0.8873654536135315, |
| "eval_runtime": 65.8734, |
| "eval_samples_per_second": 118.47, |
| "eval_steps_per_second": 14.816, |
| "step": 1900 |
| }, |
| { |
| "epoch": 1.78, |
| "learning_rate": 0.0001112453531598513, |
| "loss": 0.1617, |
| "step": 1910 |
| }, |
| { |
| "epoch": 1.78, |
| "learning_rate": 0.00011078066914498142, |
| "loss": 0.1475, |
| "step": 1920 |
| }, |
| { |
| "epoch": 1.79, |
| "learning_rate": 0.00011031598513011152, |
| "loss": 0.1151, |
| "step": 1930 |
| }, |
| { |
| "epoch": 1.8, |
| "learning_rate": 0.00010985130111524164, |
| "loss": 0.0612, |
| "step": 1940 |
| }, |
| { |
| "epoch": 1.81, |
| "learning_rate": 0.00010938661710037175, |
| "loss": 0.0782, |
| "step": 1950 |
| }, |
| { |
| "epoch": 1.82, |
| "learning_rate": 0.00010892193308550187, |
| "loss": 0.1133, |
| "step": 1960 |
| }, |
| { |
| "epoch": 1.83, |
| "learning_rate": 0.00010845724907063197, |
| "loss": 0.1403, |
| "step": 1970 |
| }, |
| { |
| "epoch": 1.84, |
| "learning_rate": 0.0001079925650557621, |
| "loss": 0.0869, |
| "step": 1980 |
| }, |
| { |
| "epoch": 1.85, |
| "learning_rate": 0.0001075278810408922, |
| "loss": 0.1225, |
| "step": 1990 |
| }, |
| { |
| "epoch": 1.86, |
| "learning_rate": 0.0001070631970260223, |
| "loss": 0.058, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.86, |
| "eval_accuracy": 0.8780112762685802, |
| "eval_f1": 0.8780112762685802, |
| "eval_loss": 0.39207538962364197, |
| "eval_precision": 0.8780112762685802, |
| "eval_recall": 0.8780112762685802, |
| "eval_runtime": 66.3391, |
| "eval_samples_per_second": 117.638, |
| "eval_steps_per_second": 14.712, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.87, |
| "learning_rate": 0.00010659851301115242, |
| "loss": 0.1409, |
| "step": 2010 |
| }, |
| { |
| "epoch": 1.88, |
| "learning_rate": 0.00010613382899628253, |
| "loss": 0.0797, |
| "step": 2020 |
| }, |
| { |
| "epoch": 1.89, |
| "learning_rate": 0.00010566914498141265, |
| "loss": 0.1295, |
| "step": 2030 |
| }, |
| { |
| "epoch": 1.9, |
| "learning_rate": 0.00010520446096654275, |
| "loss": 0.1062, |
| "step": 2040 |
| }, |
| { |
| "epoch": 1.91, |
| "learning_rate": 0.00010473977695167288, |
| "loss": 0.0671, |
| "step": 2050 |
| }, |
| { |
| "epoch": 1.91, |
| "learning_rate": 0.00010427509293680297, |
| "loss": 0.0503, |
| "step": 2060 |
| }, |
| { |
| "epoch": 1.92, |
| "learning_rate": 0.0001038104089219331, |
| "loss": 0.1064, |
| "step": 2070 |
| }, |
| { |
| "epoch": 1.93, |
| "learning_rate": 0.0001033457249070632, |
| "loss": 0.1218, |
| "step": 2080 |
| }, |
| { |
| "epoch": 1.94, |
| "learning_rate": 0.0001028810408921933, |
| "loss": 0.1302, |
| "step": 2090 |
| }, |
| { |
| "epoch": 1.95, |
| "learning_rate": 0.00010241635687732343, |
| "loss": 0.0873, |
| "step": 2100 |
| }, |
| { |
| "epoch": 1.95, |
| "eval_accuracy": 0.8882624295233214, |
| "eval_f1": 0.8882624295233214, |
| "eval_loss": 0.30943068861961365, |
| "eval_precision": 0.8882624295233214, |
| "eval_recall": 0.8882624295233214, |
| "eval_runtime": 65.7152, |
| "eval_samples_per_second": 118.755, |
| "eval_steps_per_second": 14.852, |
| "step": 2100 |
| }, |
| { |
| "epoch": 1.96, |
| "learning_rate": 0.00010195167286245353, |
| "loss": 0.1149, |
| "step": 2110 |
| }, |
| { |
| "epoch": 1.97, |
| "learning_rate": 0.00010148698884758365, |
| "loss": 0.1039, |
| "step": 2120 |
| }, |
| { |
| "epoch": 1.98, |
| "learning_rate": 0.00010102230483271375, |
| "loss": 0.0973, |
| "step": 2130 |
| }, |
| { |
| "epoch": 1.99, |
| "learning_rate": 0.00010055762081784388, |
| "loss": 0.0828, |
| "step": 2140 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 0.00010013940520446097, |
| "loss": 0.1082, |
| "step": 2150 |
| }, |
| { |
| "epoch": 2.01, |
| "learning_rate": 9.967472118959109e-05, |
| "loss": 0.1088, |
| "step": 2160 |
| }, |
| { |
| "epoch": 2.02, |
| "learning_rate": 9.92100371747212e-05, |
| "loss": 0.0729, |
| "step": 2170 |
| }, |
| { |
| "epoch": 2.03, |
| "learning_rate": 9.87453531598513e-05, |
| "loss": 0.063, |
| "step": 2180 |
| }, |
| { |
| "epoch": 2.04, |
| "learning_rate": 9.828066914498142e-05, |
| "loss": 0.0381, |
| "step": 2190 |
| }, |
| { |
| "epoch": 2.04, |
| "learning_rate": 9.781598513011153e-05, |
| "loss": 0.0584, |
| "step": 2200 |
| }, |
| { |
| "epoch": 2.04, |
| "eval_accuracy": 0.8891594054331112, |
| "eval_f1": 0.8891594054331112, |
| "eval_loss": 0.36880868673324585, |
| "eval_precision": 0.8891594054331112, |
| "eval_recall": 0.8891594054331112, |
| "eval_runtime": 65.8807, |
| "eval_samples_per_second": 118.457, |
| "eval_steps_per_second": 14.815, |
| "step": 2200 |
| }, |
| { |
| "epoch": 2.05, |
| "learning_rate": 9.735130111524164e-05, |
| "loss": 0.0618, |
| "step": 2210 |
| }, |
| { |
| "epoch": 2.06, |
| "learning_rate": 9.688661710037176e-05, |
| "loss": 0.0258, |
| "step": 2220 |
| }, |
| { |
| "epoch": 2.07, |
| "learning_rate": 9.646840148698886e-05, |
| "loss": 0.1181, |
| "step": 2230 |
| }, |
| { |
| "epoch": 2.08, |
| "learning_rate": 9.600371747211896e-05, |
| "loss": 0.0247, |
| "step": 2240 |
| }, |
| { |
| "epoch": 2.09, |
| "learning_rate": 9.553903345724908e-05, |
| "loss": 0.0442, |
| "step": 2250 |
| }, |
| { |
| "epoch": 2.1, |
| "learning_rate": 9.507434944237919e-05, |
| "loss": 0.0416, |
| "step": 2260 |
| }, |
| { |
| "epoch": 2.11, |
| "learning_rate": 9.460966542750929e-05, |
| "loss": 0.1076, |
| "step": 2270 |
| }, |
| { |
| "epoch": 2.12, |
| "learning_rate": 9.414498141263941e-05, |
| "loss": 0.0183, |
| "step": 2280 |
| }, |
| { |
| "epoch": 2.13, |
| "learning_rate": 9.368029739776952e-05, |
| "loss": 0.0592, |
| "step": 2290 |
| }, |
| { |
| "epoch": 2.14, |
| "learning_rate": 9.321561338289964e-05, |
| "loss": 0.0978, |
| "step": 2300 |
| }, |
| { |
| "epoch": 2.14, |
| "eval_accuracy": 0.8915940543311123, |
| "eval_f1": 0.8915940543311123, |
| "eval_loss": 0.38737115263938904, |
| "eval_precision": 0.8915940543311123, |
| "eval_recall": 0.8915940543311123, |
| "eval_runtime": 65.8844, |
| "eval_samples_per_second": 118.45, |
| "eval_steps_per_second": 14.814, |
| "step": 2300 |
| }, |
| { |
| "epoch": 2.15, |
| "learning_rate": 9.275092936802975e-05, |
| "loss": 0.0345, |
| "step": 2310 |
| }, |
| { |
| "epoch": 2.16, |
| "learning_rate": 9.228624535315984e-05, |
| "loss": 0.0566, |
| "step": 2320 |
| }, |
| { |
| "epoch": 2.17, |
| "learning_rate": 9.182156133828997e-05, |
| "loss": 0.1458, |
| "step": 2330 |
| }, |
| { |
| "epoch": 2.17, |
| "learning_rate": 9.135687732342007e-05, |
| "loss": 0.0487, |
| "step": 2340 |
| }, |
| { |
| "epoch": 2.18, |
| "learning_rate": 9.08921933085502e-05, |
| "loss": 0.0737, |
| "step": 2350 |
| }, |
| { |
| "epoch": 2.19, |
| "learning_rate": 9.04275092936803e-05, |
| "loss": 0.14, |
| "step": 2360 |
| }, |
| { |
| "epoch": 2.2, |
| "learning_rate": 8.996282527881041e-05, |
| "loss": 0.0927, |
| "step": 2370 |
| }, |
| { |
| "epoch": 2.21, |
| "learning_rate": 8.949814126394053e-05, |
| "loss": 0.055, |
| "step": 2380 |
| }, |
| { |
| "epoch": 2.22, |
| "learning_rate": 8.903345724907064e-05, |
| "loss": 0.0317, |
| "step": 2390 |
| }, |
| { |
| "epoch": 2.23, |
| "learning_rate": 8.856877323420076e-05, |
| "loss": 0.0958, |
| "step": 2400 |
| }, |
| { |
| "epoch": 2.23, |
| "eval_accuracy": 0.8927473090722706, |
| "eval_f1": 0.8927473090722706, |
| "eval_loss": 0.3678542375564575, |
| "eval_precision": 0.8927473090722706, |
| "eval_recall": 0.8927473090722706, |
| "eval_runtime": 66.3916, |
| "eval_samples_per_second": 117.545, |
| "eval_steps_per_second": 14.701, |
| "step": 2400 |
| }, |
| { |
| "epoch": 2.24, |
| "learning_rate": 8.810408921933085e-05, |
| "loss": 0.0444, |
| "step": 2410 |
| }, |
| { |
| "epoch": 2.25, |
| "learning_rate": 8.763940520446097e-05, |
| "loss": 0.0118, |
| "step": 2420 |
| }, |
| { |
| "epoch": 2.26, |
| "learning_rate": 8.717472118959108e-05, |
| "loss": 0.0232, |
| "step": 2430 |
| }, |
| { |
| "epoch": 2.27, |
| "learning_rate": 8.671003717472119e-05, |
| "loss": 0.008, |
| "step": 2440 |
| }, |
| { |
| "epoch": 2.28, |
| "learning_rate": 8.624535315985131e-05, |
| "loss": 0.1033, |
| "step": 2450 |
| }, |
| { |
| "epoch": 2.29, |
| "learning_rate": 8.578066914498142e-05, |
| "loss": 0.0479, |
| "step": 2460 |
| }, |
| { |
| "epoch": 2.3, |
| "learning_rate": 8.531598513011152e-05, |
| "loss": 0.0115, |
| "step": 2470 |
| }, |
| { |
| "epoch": 2.3, |
| "learning_rate": 8.485130111524165e-05, |
| "loss": 0.0538, |
| "step": 2480 |
| }, |
| { |
| "epoch": 2.31, |
| "learning_rate": 8.438661710037175e-05, |
| "loss": 0.0458, |
| "step": 2490 |
| }, |
| { |
| "epoch": 2.32, |
| "learning_rate": 8.392193308550186e-05, |
| "loss": 0.0559, |
| "step": 2500 |
| }, |
| { |
| "epoch": 2.32, |
| "eval_accuracy": 0.8873654536135315, |
| "eval_f1": 0.8873654536135316, |
| "eval_loss": 0.4649113118648529, |
| "eval_precision": 0.8873654536135315, |
| "eval_recall": 0.8873654536135315, |
| "eval_runtime": 66.1513, |
| "eval_samples_per_second": 117.972, |
| "eval_steps_per_second": 14.754, |
| "step": 2500 |
| }, |
| { |
| "epoch": 2.33, |
| "learning_rate": 8.345724907063197e-05, |
| "loss": 0.1311, |
| "step": 2510 |
| }, |
| { |
| "epoch": 2.34, |
| "learning_rate": 8.299256505576209e-05, |
| "loss": 0.0464, |
| "step": 2520 |
| }, |
| { |
| "epoch": 2.35, |
| "learning_rate": 8.25278810408922e-05, |
| "loss": 0.1095, |
| "step": 2530 |
| }, |
| { |
| "epoch": 2.36, |
| "learning_rate": 8.20631970260223e-05, |
| "loss": 0.0329, |
| "step": 2540 |
| }, |
| { |
| "epoch": 2.37, |
| "learning_rate": 8.159851301115243e-05, |
| "loss": 0.0212, |
| "step": 2550 |
| }, |
| { |
| "epoch": 2.38, |
| "learning_rate": 8.113382899628253e-05, |
| "loss": 0.0273, |
| "step": 2560 |
| }, |
| { |
| "epoch": 2.39, |
| "learning_rate": 8.066914498141265e-05, |
| "loss": 0.0273, |
| "step": 2570 |
| }, |
| { |
| "epoch": 2.4, |
| "learning_rate": 8.020446096654275e-05, |
| "loss": 0.0772, |
| "step": 2580 |
| }, |
| { |
| "epoch": 2.41, |
| "learning_rate": 7.973977695167286e-05, |
| "loss": 0.0361, |
| "step": 2590 |
| }, |
| { |
| "epoch": 2.42, |
| "learning_rate": 7.927509293680298e-05, |
| "loss": 0.0125, |
| "step": 2600 |
| }, |
| { |
| "epoch": 2.42, |
| "eval_accuracy": 0.8942849820604818, |
| "eval_f1": 0.8942849820604818, |
| "eval_loss": 0.43495211005210876, |
| "eval_precision": 0.8942849820604818, |
| "eval_recall": 0.8942849820604818, |
| "eval_runtime": 67.0087, |
| "eval_samples_per_second": 116.462, |
| "eval_steps_per_second": 14.565, |
| "step": 2600 |
| }, |
| { |
| "epoch": 2.43, |
| "learning_rate": 7.881040892193308e-05, |
| "loss": 0.0493, |
| "step": 2610 |
| }, |
| { |
| "epoch": 2.43, |
| "learning_rate": 7.83457249070632e-05, |
| "loss": 0.0063, |
| "step": 2620 |
| }, |
| { |
| "epoch": 2.44, |
| "learning_rate": 7.788104089219331e-05, |
| "loss": 0.1419, |
| "step": 2630 |
| }, |
| { |
| "epoch": 2.45, |
| "learning_rate": 7.741635687732342e-05, |
| "loss": 0.0781, |
| "step": 2640 |
| }, |
| { |
| "epoch": 2.46, |
| "learning_rate": 7.695167286245354e-05, |
| "loss": 0.0436, |
| "step": 2650 |
| }, |
| { |
| "epoch": 2.47, |
| "learning_rate": 7.648698884758365e-05, |
| "loss": 0.0642, |
| "step": 2660 |
| }, |
| { |
| "epoch": 2.48, |
| "learning_rate": 7.602230483271376e-05, |
| "loss": 0.0676, |
| "step": 2670 |
| }, |
| { |
| "epoch": 2.49, |
| "learning_rate": 7.555762081784386e-05, |
| "loss": 0.0418, |
| "step": 2680 |
| }, |
| { |
| "epoch": 2.5, |
| "learning_rate": 7.509293680297399e-05, |
| "loss": 0.0337, |
| "step": 2690 |
| }, |
| { |
| "epoch": 2.51, |
| "learning_rate": 7.462825278810409e-05, |
| "loss": 0.0636, |
| "step": 2700 |
| }, |
| { |
| "epoch": 2.51, |
| "eval_accuracy": 0.8905689390056382, |
| "eval_f1": 0.890568939005638, |
| "eval_loss": 0.4195483326911926, |
| "eval_precision": 0.8905689390056382, |
| "eval_recall": 0.8905689390056382, |
| "eval_runtime": 66.3238, |
| "eval_samples_per_second": 117.665, |
| "eval_steps_per_second": 14.716, |
| "step": 2700 |
| }, |
| { |
| "epoch": 2.52, |
| "learning_rate": 7.41635687732342e-05, |
| "loss": 0.0316, |
| "step": 2710 |
| }, |
| { |
| "epoch": 2.53, |
| "learning_rate": 7.369888475836432e-05, |
| "loss": 0.0508, |
| "step": 2720 |
| }, |
| { |
| "epoch": 2.54, |
| "learning_rate": 7.323420074349443e-05, |
| "loss": 0.0156, |
| "step": 2730 |
| }, |
| { |
| "epoch": 2.55, |
| "learning_rate": 7.276951672862454e-05, |
| "loss": 0.0606, |
| "step": 2740 |
| }, |
| { |
| "epoch": 2.56, |
| "learning_rate": 7.230483271375466e-05, |
| "loss": 0.0253, |
| "step": 2750 |
| }, |
| { |
| "epoch": 2.57, |
| "learning_rate": 7.184014869888475e-05, |
| "loss": 0.0454, |
| "step": 2760 |
| }, |
| { |
| "epoch": 2.57, |
| "learning_rate": 7.137546468401487e-05, |
| "loss": 0.0491, |
| "step": 2770 |
| }, |
| { |
| "epoch": 2.58, |
| "learning_rate": 7.091078066914498e-05, |
| "loss": 0.0261, |
| "step": 2780 |
| }, |
| { |
| "epoch": 2.59, |
| "learning_rate": 7.04460966542751e-05, |
| "loss": 0.0776, |
| "step": 2790 |
| }, |
| { |
| "epoch": 2.6, |
| "learning_rate": 6.998141263940521e-05, |
| "loss": 0.0458, |
| "step": 2800 |
| }, |
| { |
| "epoch": 2.6, |
| "eval_accuracy": 0.8980010251153254, |
| "eval_f1": 0.8980010251153254, |
| "eval_loss": 0.41266024112701416, |
| "eval_precision": 0.8980010251153254, |
| "eval_recall": 0.8980010251153254, |
| "eval_runtime": 67.6849, |
| "eval_samples_per_second": 115.299, |
| "eval_steps_per_second": 14.42, |
| "step": 2800 |
| }, |
| { |
| "epoch": 2.61, |
| "learning_rate": 6.951672862453532e-05, |
| "loss": 0.0488, |
| "step": 2810 |
| }, |
| { |
| "epoch": 2.62, |
| "learning_rate": 6.905204460966544e-05, |
| "loss": 0.0265, |
| "step": 2820 |
| }, |
| { |
| "epoch": 2.63, |
| "learning_rate": 6.858736059479555e-05, |
| "loss": 0.0342, |
| "step": 2830 |
| }, |
| { |
| "epoch": 2.64, |
| "learning_rate": 6.812267657992565e-05, |
| "loss": 0.067, |
| "step": 2840 |
| }, |
| { |
| "epoch": 2.65, |
| "learning_rate": 6.765799256505576e-05, |
| "loss": 0.0239, |
| "step": 2850 |
| }, |
| { |
| "epoch": 2.66, |
| "learning_rate": 6.719330855018587e-05, |
| "loss": 0.0356, |
| "step": 2860 |
| }, |
| { |
| "epoch": 2.67, |
| "learning_rate": 6.672862453531599e-05, |
| "loss": 0.0485, |
| "step": 2870 |
| }, |
| { |
| "epoch": 2.68, |
| "learning_rate": 6.62639405204461e-05, |
| "loss": 0.06, |
| "step": 2880 |
| }, |
| { |
| "epoch": 2.69, |
| "learning_rate": 6.579925650557622e-05, |
| "loss": 0.0282, |
| "step": 2890 |
| }, |
| { |
| "epoch": 2.7, |
| "learning_rate": 6.533457249070633e-05, |
| "loss": 0.055, |
| "step": 2900 |
| }, |
| { |
| "epoch": 2.7, |
| "eval_accuracy": 0.8992824192721681, |
| "eval_f1": 0.8992824192721681, |
| "eval_loss": 0.40864527225494385, |
| "eval_precision": 0.8992824192721681, |
| "eval_recall": 0.8992824192721681, |
| "eval_runtime": 67.4771, |
| "eval_samples_per_second": 115.654, |
| "eval_steps_per_second": 14.464, |
| "step": 2900 |
| }, |
| { |
| "epoch": 2.7, |
| "learning_rate": 6.486988847583643e-05, |
| "loss": 0.0473, |
| "step": 2910 |
| }, |
| { |
| "epoch": 2.71, |
| "learning_rate": 6.440520446096655e-05, |
| "loss": 0.0589, |
| "step": 2920 |
| }, |
| { |
| "epoch": 2.72, |
| "learning_rate": 6.394052044609665e-05, |
| "loss": 0.1052, |
| "step": 2930 |
| }, |
| { |
| "epoch": 2.73, |
| "learning_rate": 6.347583643122677e-05, |
| "loss": 0.0352, |
| "step": 2940 |
| }, |
| { |
| "epoch": 2.74, |
| "learning_rate": 6.301115241635688e-05, |
| "loss": 0.0338, |
| "step": 2950 |
| }, |
| { |
| "epoch": 2.75, |
| "learning_rate": 6.2546468401487e-05, |
| "loss": 0.0848, |
| "step": 2960 |
| }, |
| { |
| "epoch": 2.76, |
| "learning_rate": 6.20817843866171e-05, |
| "loss": 0.1017, |
| "step": 2970 |
| }, |
| { |
| "epoch": 2.77, |
| "learning_rate": 6.161710037174721e-05, |
| "loss": 0.1063, |
| "step": 2980 |
| }, |
| { |
| "epoch": 2.78, |
| "learning_rate": 6.115241635687733e-05, |
| "loss": 0.0106, |
| "step": 2990 |
| }, |
| { |
| "epoch": 2.79, |
| "learning_rate": 6.068773234200744e-05, |
| "loss": 0.03, |
| "step": 3000 |
| }, |
| { |
| "epoch": 2.79, |
| "eval_accuracy": 0.9013326499231163, |
| "eval_f1": 0.9013326499231163, |
| "eval_loss": 0.3709835112094879, |
| "eval_precision": 0.9013326499231163, |
| "eval_recall": 0.9013326499231163, |
| "eval_runtime": 67.603, |
| "eval_samples_per_second": 115.439, |
| "eval_steps_per_second": 14.437, |
| "step": 3000 |
| }, |
| { |
| "epoch": 2.8, |
| "learning_rate": 6.0223048327137555e-05, |
| "loss": 0.0621, |
| "step": 3010 |
| }, |
| { |
| "epoch": 2.81, |
| "learning_rate": 5.9758364312267656e-05, |
| "loss": 0.081, |
| "step": 3020 |
| }, |
| { |
| "epoch": 2.82, |
| "learning_rate": 5.929368029739777e-05, |
| "loss": 0.0152, |
| "step": 3030 |
| }, |
| { |
| "epoch": 2.83, |
| "learning_rate": 5.8828996282527885e-05, |
| "loss": 0.0075, |
| "step": 3040 |
| }, |
| { |
| "epoch": 2.83, |
| "learning_rate": 5.836431226765799e-05, |
| "loss": 0.0309, |
| "step": 3050 |
| }, |
| { |
| "epoch": 2.84, |
| "learning_rate": 5.7899628252788107e-05, |
| "loss": 0.0172, |
| "step": 3060 |
| }, |
| { |
| "epoch": 2.85, |
| "learning_rate": 5.743494423791822e-05, |
| "loss": 0.0168, |
| "step": 3070 |
| }, |
| { |
| "epoch": 2.86, |
| "learning_rate": 5.6970260223048335e-05, |
| "loss": 0.006, |
| "step": 3080 |
| }, |
| { |
| "epoch": 2.87, |
| "learning_rate": 5.650557620817844e-05, |
| "loss": 0.0521, |
| "step": 3090 |
| }, |
| { |
| "epoch": 2.88, |
| "learning_rate": 5.604089219330855e-05, |
| "loss": 0.027, |
| "step": 3100 |
| }, |
| { |
| "epoch": 2.88, |
| "eval_accuracy": 0.8940287032291133, |
| "eval_f1": 0.8940287032291133, |
| "eval_loss": 0.4147852957248688, |
| "eval_precision": 0.8940287032291133, |
| "eval_recall": 0.8940287032291133, |
| "eval_runtime": 67.4544, |
| "eval_samples_per_second": 115.693, |
| "eval_steps_per_second": 14.469, |
| "step": 3100 |
| }, |
| { |
| "epoch": 2.89, |
| "learning_rate": 5.557620817843866e-05, |
| "loss": 0.0706, |
| "step": 3110 |
| }, |
| { |
| "epoch": 2.9, |
| "learning_rate": 5.511152416356877e-05, |
| "loss": 0.0134, |
| "step": 3120 |
| }, |
| { |
| "epoch": 2.91, |
| "learning_rate": 5.4646840148698886e-05, |
| "loss": 0.0217, |
| "step": 3130 |
| }, |
| { |
| "epoch": 2.92, |
| "learning_rate": 5.4182156133829e-05, |
| "loss": 0.0791, |
| "step": 3140 |
| }, |
| { |
| "epoch": 2.93, |
| "learning_rate": 5.371747211895911e-05, |
| "loss": 0.1216, |
| "step": 3150 |
| }, |
| { |
| "epoch": 2.94, |
| "learning_rate": 5.325278810408922e-05, |
| "loss": 0.0637, |
| "step": 3160 |
| }, |
| { |
| "epoch": 2.95, |
| "learning_rate": 5.278810408921934e-05, |
| "loss": 0.0223, |
| "step": 3170 |
| }, |
| { |
| "epoch": 2.96, |
| "learning_rate": 5.232342007434945e-05, |
| "loss": 0.0491, |
| "step": 3180 |
| }, |
| { |
| "epoch": 2.96, |
| "learning_rate": 5.185873605947955e-05, |
| "loss": 0.0075, |
| "step": 3190 |
| }, |
| { |
| "epoch": 2.97, |
| "learning_rate": 5.1394052044609666e-05, |
| "loss": 0.0384, |
| "step": 3200 |
| }, |
| { |
| "epoch": 2.97, |
| "eval_accuracy": 0.8937724243977447, |
| "eval_f1": 0.8937724243977447, |
| "eval_loss": 0.403576135635376, |
| "eval_precision": 0.8937724243977447, |
| "eval_recall": 0.8937724243977447, |
| "eval_runtime": 67.9485, |
| "eval_samples_per_second": 114.852, |
| "eval_steps_per_second": 14.364, |
| "step": 3200 |
| }, |
| { |
| "epoch": 2.98, |
| "learning_rate": 5.0929368029739774e-05, |
| "loss": 0.0812, |
| "step": 3210 |
| }, |
| { |
| "epoch": 2.99, |
| "learning_rate": 5.046468401486989e-05, |
| "loss": 0.0272, |
| "step": 3220 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 5e-05, |
| "loss": 0.0094, |
| "step": 3230 |
| }, |
| { |
| "epoch": 3.01, |
| "learning_rate": 4.953531598513012e-05, |
| "loss": 0.0106, |
| "step": 3240 |
| }, |
| { |
| "epoch": 3.02, |
| "learning_rate": 4.907063197026023e-05, |
| "loss": 0.0039, |
| "step": 3250 |
| }, |
| { |
| "epoch": 3.03, |
| "learning_rate": 4.860594795539034e-05, |
| "loss": 0.0028, |
| "step": 3260 |
| }, |
| { |
| "epoch": 3.04, |
| "learning_rate": 4.8141263940520446e-05, |
| "loss": 0.0031, |
| "step": 3270 |
| }, |
| { |
| "epoch": 3.05, |
| "learning_rate": 4.767657992565056e-05, |
| "loss": 0.0038, |
| "step": 3280 |
| }, |
| { |
| "epoch": 3.06, |
| "learning_rate": 4.7211895910780675e-05, |
| "loss": 0.0324, |
| "step": 3290 |
| }, |
| { |
| "epoch": 3.07, |
| "learning_rate": 4.674721189591078e-05, |
| "loss": 0.0095, |
| "step": 3300 |
| }, |
| { |
| "epoch": 3.07, |
| "eval_accuracy": 0.8891594054331112, |
| "eval_f1": 0.8891594054331112, |
| "eval_loss": 0.48301902413368225, |
| "eval_precision": 0.8891594054331112, |
| "eval_recall": 0.8891594054331112, |
| "eval_runtime": 68.0779, |
| "eval_samples_per_second": 114.633, |
| "eval_steps_per_second": 14.337, |
| "step": 3300 |
| }, |
| { |
| "epoch": 3.08, |
| "learning_rate": 4.6282527881040897e-05, |
| "loss": 0.0049, |
| "step": 3310 |
| }, |
| { |
| "epoch": 3.09, |
| "learning_rate": 4.5817843866171004e-05, |
| "loss": 0.003, |
| "step": 3320 |
| }, |
| { |
| "epoch": 3.09, |
| "learning_rate": 4.535315985130112e-05, |
| "loss": 0.0023, |
| "step": 3330 |
| }, |
| { |
| "epoch": 3.1, |
| "learning_rate": 4.4888475836431226e-05, |
| "loss": 0.0051, |
| "step": 3340 |
| }, |
| { |
| "epoch": 3.11, |
| "learning_rate": 4.442379182156134e-05, |
| "loss": 0.0014, |
| "step": 3350 |
| }, |
| { |
| "epoch": 3.12, |
| "learning_rate": 4.3959107806691455e-05, |
| "loss": 0.0024, |
| "step": 3360 |
| }, |
| { |
| "epoch": 3.13, |
| "learning_rate": 4.349442379182156e-05, |
| "loss": 0.0015, |
| "step": 3370 |
| }, |
| { |
| "epoch": 3.14, |
| "learning_rate": 4.3029739776951676e-05, |
| "loss": 0.0017, |
| "step": 3380 |
| }, |
| { |
| "epoch": 3.15, |
| "learning_rate": 4.2565055762081784e-05, |
| "loss": 0.0014, |
| "step": 3390 |
| }, |
| { |
| "epoch": 3.16, |
| "learning_rate": 4.21003717472119e-05, |
| "loss": 0.0489, |
| "step": 3400 |
| }, |
| { |
| "epoch": 3.16, |
| "eval_accuracy": 0.8945412608918504, |
| "eval_f1": 0.8945412608918504, |
| "eval_loss": 0.4590292274951935, |
| "eval_precision": 0.8945412608918504, |
| "eval_recall": 0.8945412608918504, |
| "eval_runtime": 67.7083, |
| "eval_samples_per_second": 115.259, |
| "eval_steps_per_second": 14.415, |
| "step": 3400 |
| }, |
| { |
| "epoch": 3.17, |
| "learning_rate": 4.163568773234201e-05, |
| "loss": 0.0012, |
| "step": 3410 |
| }, |
| { |
| "epoch": 3.18, |
| "learning_rate": 4.117100371747212e-05, |
| "loss": 0.0065, |
| "step": 3420 |
| }, |
| { |
| "epoch": 3.19, |
| "learning_rate": 4.070631970260223e-05, |
| "loss": 0.0276, |
| "step": 3430 |
| }, |
| { |
| "epoch": 3.2, |
| "learning_rate": 4.024163568773234e-05, |
| "loss": 0.0013, |
| "step": 3440 |
| }, |
| { |
| "epoch": 3.21, |
| "learning_rate": 3.9776951672862456e-05, |
| "loss": 0.0019, |
| "step": 3450 |
| }, |
| { |
| "epoch": 3.22, |
| "learning_rate": 3.931226765799257e-05, |
| "loss": 0.0017, |
| "step": 3460 |
| }, |
| { |
| "epoch": 3.22, |
| "learning_rate": 3.884758364312268e-05, |
| "loss": 0.0025, |
| "step": 3470 |
| }, |
| { |
| "epoch": 3.23, |
| "learning_rate": 3.8382899628252786e-05, |
| "loss": 0.0028, |
| "step": 3480 |
| }, |
| { |
| "epoch": 3.24, |
| "learning_rate": 3.79182156133829e-05, |
| "loss": 0.0398, |
| "step": 3490 |
| }, |
| { |
| "epoch": 3.25, |
| "learning_rate": 3.7453531598513014e-05, |
| "loss": 0.0198, |
| "step": 3500 |
| }, |
| { |
| "epoch": 3.25, |
| "eval_accuracy": 0.8972321886212199, |
| "eval_f1": 0.8972321886212199, |
| "eval_loss": 0.47322773933410645, |
| "eval_precision": 0.8972321886212199, |
| "eval_recall": 0.8972321886212199, |
| "eval_runtime": 67.7316, |
| "eval_samples_per_second": 115.22, |
| "eval_steps_per_second": 14.41, |
| "step": 3500 |
| }, |
| { |
| "epoch": 3.26, |
| "learning_rate": 3.698884758364313e-05, |
| "loss": 0.0019, |
| "step": 3510 |
| }, |
| { |
| "epoch": 3.27, |
| "learning_rate": 3.6524163568773236e-05, |
| "loss": 0.0019, |
| "step": 3520 |
| }, |
| { |
| "epoch": 3.28, |
| "learning_rate": 3.6059479553903344e-05, |
| "loss": 0.0014, |
| "step": 3530 |
| }, |
| { |
| "epoch": 3.29, |
| "learning_rate": 3.559479553903346e-05, |
| "loss": 0.0013, |
| "step": 3540 |
| }, |
| { |
| "epoch": 3.3, |
| "learning_rate": 3.513011152416357e-05, |
| "loss": 0.003, |
| "step": 3550 |
| }, |
| { |
| "epoch": 3.31, |
| "learning_rate": 3.466542750929368e-05, |
| "loss": 0.0404, |
| "step": 3560 |
| }, |
| { |
| "epoch": 3.32, |
| "learning_rate": 3.4200743494423794e-05, |
| "loss": 0.0012, |
| "step": 3570 |
| }, |
| { |
| "epoch": 3.33, |
| "learning_rate": 3.373605947955391e-05, |
| "loss": 0.0196, |
| "step": 3580 |
| }, |
| { |
| "epoch": 3.34, |
| "learning_rate": 3.3271375464684016e-05, |
| "loss": 0.0128, |
| "step": 3590 |
| }, |
| { |
| "epoch": 3.35, |
| "learning_rate": 3.2806691449814123e-05, |
| "loss": 0.0604, |
| "step": 3600 |
| }, |
| { |
| "epoch": 3.35, |
| "eval_accuracy": 0.8915940543311123, |
| "eval_f1": 0.8915940543311123, |
| "eval_loss": 0.5282955169677734, |
| "eval_precision": 0.8915940543311123, |
| "eval_recall": 0.8915940543311123, |
| "eval_runtime": 67.8247, |
| "eval_samples_per_second": 115.061, |
| "eval_steps_per_second": 14.39, |
| "step": 3600 |
| }, |
| { |
| "epoch": 3.36, |
| "learning_rate": 3.234200743494424e-05, |
| "loss": 0.0019, |
| "step": 3610 |
| }, |
| { |
| "epoch": 3.36, |
| "learning_rate": 3.187732342007435e-05, |
| "loss": 0.0386, |
| "step": 3620 |
| }, |
| { |
| "epoch": 3.37, |
| "learning_rate": 3.1412639405204466e-05, |
| "loss": 0.0584, |
| "step": 3630 |
| }, |
| { |
| "epoch": 3.38, |
| "learning_rate": 3.0947955390334574e-05, |
| "loss": 0.0013, |
| "step": 3640 |
| }, |
| { |
| "epoch": 3.39, |
| "learning_rate": 3.0483271375464685e-05, |
| "loss": 0.0031, |
| "step": 3650 |
| }, |
| { |
| "epoch": 3.4, |
| "learning_rate": 3.0018587360594796e-05, |
| "loss": 0.0017, |
| "step": 3660 |
| }, |
| { |
| "epoch": 3.41, |
| "learning_rate": 2.955390334572491e-05, |
| "loss": 0.011, |
| "step": 3670 |
| }, |
| { |
| "epoch": 3.42, |
| "learning_rate": 2.908921933085502e-05, |
| "loss": 0.0014, |
| "step": 3680 |
| }, |
| { |
| "epoch": 3.43, |
| "learning_rate": 2.862453531598513e-05, |
| "loss": 0.0037, |
| "step": 3690 |
| }, |
| { |
| "epoch": 3.44, |
| "learning_rate": 2.8159851301115243e-05, |
| "loss": 0.0028, |
| "step": 3700 |
| }, |
| { |
| "epoch": 3.44, |
| "eval_accuracy": 0.8931317273193234, |
| "eval_f1": 0.8931317273193234, |
| "eval_loss": 0.5159913897514343, |
| "eval_precision": 0.8931317273193234, |
| "eval_recall": 0.8931317273193234, |
| "eval_runtime": 67.8895, |
| "eval_samples_per_second": 114.952, |
| "eval_steps_per_second": 14.376, |
| "step": 3700 |
| }, |
| { |
| "epoch": 3.45, |
| "learning_rate": 2.7695167286245354e-05, |
| "loss": 0.0018, |
| "step": 3710 |
| }, |
| { |
| "epoch": 3.46, |
| "learning_rate": 2.7230483271375468e-05, |
| "loss": 0.0013, |
| "step": 3720 |
| }, |
| { |
| "epoch": 3.47, |
| "learning_rate": 2.6765799256505576e-05, |
| "loss": 0.0014, |
| "step": 3730 |
| }, |
| { |
| "epoch": 3.48, |
| "learning_rate": 2.6301115241635687e-05, |
| "loss": 0.0184, |
| "step": 3740 |
| }, |
| { |
| "epoch": 3.49, |
| "learning_rate": 2.58364312267658e-05, |
| "loss": 0.0161, |
| "step": 3750 |
| }, |
| { |
| "epoch": 3.49, |
| "learning_rate": 2.5371747211895912e-05, |
| "loss": 0.0011, |
| "step": 3760 |
| }, |
| { |
| "epoch": 3.5, |
| "learning_rate": 2.4907063197026023e-05, |
| "loss": 0.0138, |
| "step": 3770 |
| }, |
| { |
| "epoch": 3.51, |
| "learning_rate": 2.4442379182156137e-05, |
| "loss": 0.0011, |
| "step": 3780 |
| }, |
| { |
| "epoch": 3.52, |
| "learning_rate": 2.3977695167286245e-05, |
| "loss": 0.0012, |
| "step": 3790 |
| }, |
| { |
| "epoch": 3.53, |
| "learning_rate": 2.351301115241636e-05, |
| "loss": 0.0018, |
| "step": 3800 |
| }, |
| { |
| "epoch": 3.53, |
| "eval_accuracy": 0.8965914915427986, |
| "eval_f1": 0.8965914915427986, |
| "eval_loss": 0.503774106502533, |
| "eval_precision": 0.8965914915427986, |
| "eval_recall": 0.8965914915427986, |
| "eval_runtime": 67.4354, |
| "eval_samples_per_second": 115.726, |
| "eval_steps_per_second": 14.473, |
| "step": 3800 |
| }, |
| { |
| "epoch": 3.54, |
| "learning_rate": 2.304832713754647e-05, |
| "loss": 0.0015, |
| "step": 3810 |
| }, |
| { |
| "epoch": 3.55, |
| "learning_rate": 2.258364312267658e-05, |
| "loss": 0.0009, |
| "step": 3820 |
| }, |
| { |
| "epoch": 3.56, |
| "learning_rate": 2.211895910780669e-05, |
| "loss": 0.0011, |
| "step": 3830 |
| }, |
| { |
| "epoch": 3.57, |
| "learning_rate": 2.1654275092936806e-05, |
| "loss": 0.0011, |
| "step": 3840 |
| }, |
| { |
| "epoch": 3.58, |
| "learning_rate": 2.1189591078066913e-05, |
| "loss": 0.0044, |
| "step": 3850 |
| }, |
| { |
| "epoch": 3.59, |
| "learning_rate": 2.0724907063197028e-05, |
| "loss": 0.001, |
| "step": 3860 |
| }, |
| { |
| "epoch": 3.6, |
| "learning_rate": 2.026022304832714e-05, |
| "loss": 0.0213, |
| "step": 3870 |
| }, |
| { |
| "epoch": 3.61, |
| "learning_rate": 1.979553903345725e-05, |
| "loss": 0.0009, |
| "step": 3880 |
| }, |
| { |
| "epoch": 3.62, |
| "learning_rate": 1.9330855018587364e-05, |
| "loss": 0.0008, |
| "step": 3890 |
| }, |
| { |
| "epoch": 3.62, |
| "learning_rate": 1.886617100371747e-05, |
| "loss": 0.0192, |
| "step": 3900 |
| }, |
| { |
| "epoch": 3.62, |
| "eval_accuracy": 0.8974884674525884, |
| "eval_f1": 0.8974884674525884, |
| "eval_loss": 0.5111924409866333, |
| "eval_precision": 0.8974884674525884, |
| "eval_recall": 0.8974884674525884, |
| "eval_runtime": 67.9243, |
| "eval_samples_per_second": 114.893, |
| "eval_steps_per_second": 14.369, |
| "step": 3900 |
| }, |
| { |
| "epoch": 3.63, |
| "learning_rate": 1.8401486988847586e-05, |
| "loss": 0.001, |
| "step": 3910 |
| }, |
| { |
| "epoch": 3.64, |
| "learning_rate": 1.7936802973977697e-05, |
| "loss": 0.0016, |
| "step": 3920 |
| }, |
| { |
| "epoch": 3.65, |
| "learning_rate": 1.7472118959107808e-05, |
| "loss": 0.0711, |
| "step": 3930 |
| }, |
| { |
| "epoch": 3.66, |
| "learning_rate": 1.700743494423792e-05, |
| "loss": 0.0008, |
| "step": 3940 |
| }, |
| { |
| "epoch": 3.67, |
| "learning_rate": 1.654275092936803e-05, |
| "loss": 0.002, |
| "step": 3950 |
| }, |
| { |
| "epoch": 3.68, |
| "learning_rate": 1.607806691449814e-05, |
| "loss": 0.0082, |
| "step": 3960 |
| }, |
| { |
| "epoch": 3.69, |
| "learning_rate": 1.5613382899628255e-05, |
| "loss": 0.0257, |
| "step": 3970 |
| }, |
| { |
| "epoch": 3.7, |
| "learning_rate": 1.5148698884758364e-05, |
| "loss": 0.0013, |
| "step": 3980 |
| }, |
| { |
| "epoch": 3.71, |
| "learning_rate": 1.4684014869888477e-05, |
| "loss": 0.0168, |
| "step": 3990 |
| }, |
| { |
| "epoch": 3.72, |
| "learning_rate": 1.421933085501859e-05, |
| "loss": 0.0455, |
| "step": 4000 |
| }, |
| { |
| "epoch": 3.72, |
| "eval_accuracy": 0.8985135827780625, |
| "eval_f1": 0.8985135827780625, |
| "eval_loss": 0.49538707733154297, |
| "eval_precision": 0.8985135827780625, |
| "eval_recall": 0.8985135827780625, |
| "eval_runtime": 67.643, |
| "eval_samples_per_second": 115.37, |
| "eval_steps_per_second": 14.429, |
| "step": 4000 |
| }, |
| { |
| "epoch": 3.73, |
| "learning_rate": 1.37546468401487e-05, |
| "loss": 0.001, |
| "step": 4010 |
| }, |
| { |
| "epoch": 3.74, |
| "learning_rate": 1.3289962825278813e-05, |
| "loss": 0.001, |
| "step": 4020 |
| }, |
| { |
| "epoch": 3.75, |
| "learning_rate": 1.2825278810408922e-05, |
| "loss": 0.005, |
| "step": 4030 |
| }, |
| { |
| "epoch": 3.75, |
| "learning_rate": 1.2360594795539033e-05, |
| "loss": 0.0287, |
| "step": 4040 |
| }, |
| { |
| "epoch": 3.76, |
| "learning_rate": 1.1895910780669145e-05, |
| "loss": 0.0316, |
| "step": 4050 |
| }, |
| { |
| "epoch": 3.77, |
| "learning_rate": 1.1431226765799256e-05, |
| "loss": 0.001, |
| "step": 4060 |
| }, |
| { |
| "epoch": 3.78, |
| "learning_rate": 1.0966542750929369e-05, |
| "loss": 0.0225, |
| "step": 4070 |
| }, |
| { |
| "epoch": 3.79, |
| "learning_rate": 1.050185873605948e-05, |
| "loss": 0.0275, |
| "step": 4080 |
| }, |
| { |
| "epoch": 3.8, |
| "learning_rate": 1.0037174721189593e-05, |
| "loss": 0.0019, |
| "step": 4090 |
| }, |
| { |
| "epoch": 3.81, |
| "learning_rate": 9.572490706319703e-06, |
| "loss": 0.0014, |
| "step": 4100 |
| }, |
| { |
| "epoch": 3.81, |
| "eval_accuracy": 0.8994105586878524, |
| "eval_f1": 0.8994105586878524, |
| "eval_loss": 0.4983733594417572, |
| "eval_precision": 0.8994105586878524, |
| "eval_recall": 0.8994105586878524, |
| "eval_runtime": 67.6703, |
| "eval_samples_per_second": 115.324, |
| "eval_steps_per_second": 14.423, |
| "step": 4100 |
| }, |
| { |
| "epoch": 3.82, |
| "learning_rate": 9.107806691449814e-06, |
| "loss": 0.0017, |
| "step": 4110 |
| }, |
| { |
| "epoch": 3.83, |
| "learning_rate": 8.643122676579925e-06, |
| "loss": 0.0009, |
| "step": 4120 |
| }, |
| { |
| "epoch": 3.84, |
| "learning_rate": 8.178438661710038e-06, |
| "loss": 0.0018, |
| "step": 4130 |
| }, |
| { |
| "epoch": 3.85, |
| "learning_rate": 7.713754646840149e-06, |
| "loss": 0.0011, |
| "step": 4140 |
| }, |
| { |
| "epoch": 3.86, |
| "learning_rate": 7.249070631970261e-06, |
| "loss": 0.0203, |
| "step": 4150 |
| }, |
| { |
| "epoch": 3.87, |
| "learning_rate": 6.7843866171003716e-06, |
| "loss": 0.001, |
| "step": 4160 |
| }, |
| { |
| "epoch": 3.88, |
| "learning_rate": 6.319702602230483e-06, |
| "loss": 0.0248, |
| "step": 4170 |
| }, |
| { |
| "epoch": 3.88, |
| "learning_rate": 5.855018587360595e-06, |
| "loss": 0.0021, |
| "step": 4180 |
| }, |
| { |
| "epoch": 3.89, |
| "learning_rate": 5.390334572490707e-06, |
| "loss": 0.0017, |
| "step": 4190 |
| }, |
| { |
| "epoch": 3.9, |
| "learning_rate": 4.925650557620818e-06, |
| "loss": 0.0012, |
| "step": 4200 |
| }, |
| { |
| "epoch": 3.9, |
| "eval_accuracy": 0.900691952844695, |
| "eval_f1": 0.900691952844695, |
| "eval_loss": 0.4987325072288513, |
| "eval_precision": 0.900691952844695, |
| "eval_recall": 0.900691952844695, |
| "eval_runtime": 67.8282, |
| "eval_samples_per_second": 115.055, |
| "eval_steps_per_second": 14.389, |
| "step": 4200 |
| }, |
| { |
| "epoch": 3.91, |
| "learning_rate": 4.4609665427509296e-06, |
| "loss": 0.0013, |
| "step": 4210 |
| }, |
| { |
| "epoch": 3.92, |
| "learning_rate": 3.9962825278810405e-06, |
| "loss": 0.0009, |
| "step": 4220 |
| }, |
| { |
| "epoch": 3.93, |
| "learning_rate": 3.5315985130111527e-06, |
| "loss": 0.0175, |
| "step": 4230 |
| }, |
| { |
| "epoch": 3.94, |
| "learning_rate": 3.0669144981412644e-06, |
| "loss": 0.001, |
| "step": 4240 |
| }, |
| { |
| "epoch": 3.95, |
| "learning_rate": 2.6022304832713758e-06, |
| "loss": 0.0009, |
| "step": 4250 |
| }, |
| { |
| "epoch": 3.96, |
| "learning_rate": 2.137546468401487e-06, |
| "loss": 0.0011, |
| "step": 4260 |
| }, |
| { |
| "epoch": 3.97, |
| "learning_rate": 1.6728624535315985e-06, |
| "loss": 0.0009, |
| "step": 4270 |
| }, |
| { |
| "epoch": 3.98, |
| "learning_rate": 1.2081784386617102e-06, |
| "loss": 0.0008, |
| "step": 4280 |
| }, |
| { |
| "epoch": 3.99, |
| "learning_rate": 7.434944237918216e-07, |
| "loss": 0.0009, |
| "step": 4290 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 2.788104089219331e-07, |
| "loss": 0.0009, |
| "step": 4300 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8997949769349052, |
| "eval_f1": 0.8997949769349052, |
| "eval_loss": 0.5004200339317322, |
| "eval_precision": 0.8997949769349052, |
| "eval_recall": 0.8997949769349052, |
| "eval_runtime": 68.3143, |
| "eval_samples_per_second": 114.237, |
| "eval_steps_per_second": 14.287, |
| "step": 4300 |
| }, |
| { |
| "epoch": 4.0, |
| "step": 4304, |
| "total_flos": 5.43880847279702e+18, |
| "train_loss": 0.12091769810952506, |
| "train_runtime": 4325.0151, |
| "train_samples_per_second": 15.92, |
| "train_steps_per_second": 0.995 |
| } |
| ], |
| "max_steps": 4304, |
| "num_train_epochs": 4, |
| "total_flos": 5.43880847279702e+18, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
