| { | |
| "best_metric": 0.8647125140924464, | |
| "best_model_checkpoint": "swinv2-small-patch4-window8-256-finetuned-galaxy10-decals/checkpoint-875", | |
| "epoch": 29.76, | |
| "eval_steps": 500, | |
| "global_step": 1860, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.688172043010753e-06, | |
| "loss": 2.3705, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 5.376344086021506e-06, | |
| "loss": 2.303, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 8.064516129032258e-06, | |
| "loss": 2.2134, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.0752688172043012e-05, | |
| "loss": 2.0983, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.3440860215053763e-05, | |
| "loss": 1.9538, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.6129032258064517e-05, | |
| "loss": 1.6991, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.5011273957158963, | |
| "eval_f1": 0.46409627852618335, | |
| "eval_loss": 1.4105783700942993, | |
| "eval_precision": 0.46204909360959767, | |
| "eval_recall": 0.5011273957158963, | |
| "eval_runtime": 13.6927, | |
| "eval_samples_per_second": 129.558, | |
| "eval_steps_per_second": 2.045, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 1.881720430107527e-05, | |
| "loss": 1.5362, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 1.4012, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 2.4193548387096777e-05, | |
| "loss": 1.2326, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.6881720430107527e-05, | |
| "loss": 1.1378, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.9569892473118284e-05, | |
| "loss": 1.0244, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 0.9843, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7147688838782412, | |
| "eval_f1": 0.7097440442846092, | |
| "eval_loss": 0.8254368305206299, | |
| "eval_precision": 0.7389844061379163, | |
| "eval_recall": 0.7147688838782412, | |
| "eval_runtime": 13.3509, | |
| "eval_samples_per_second": 132.874, | |
| "eval_steps_per_second": 2.097, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 3.494623655913979e-05, | |
| "loss": 0.9378, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 3.763440860215054e-05, | |
| "loss": 0.8802, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 4.032258064516129e-05, | |
| "loss": 0.8868, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 0.8988, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 4.56989247311828e-05, | |
| "loss": 0.8653, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 4.8387096774193554e-05, | |
| "loss": 0.8115, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.7773393461104848, | |
| "eval_f1": 0.7671223871864332, | |
| "eval_loss": 0.6271385550498962, | |
| "eval_precision": 0.7700364597901287, | |
| "eval_recall": 0.7773393461104848, | |
| "eval_runtime": 13.1915, | |
| "eval_samples_per_second": 134.48, | |
| "eval_steps_per_second": 2.123, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 4.98805256869773e-05, | |
| "loss": 0.8503, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 4.9581839904420555e-05, | |
| "loss": 0.7757, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 4.92831541218638e-05, | |
| "loss": 0.7664, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 4.898446833930705e-05, | |
| "loss": 0.7837, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 4.86857825567503e-05, | |
| "loss": 0.712, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 4.8387096774193554e-05, | |
| "loss": 0.7336, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.80884109916368e-05, | |
| "loss": 0.6956, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8060879368658399, | |
| "eval_f1": 0.7966537537589246, | |
| "eval_loss": 0.5678830146789551, | |
| "eval_precision": 0.8029194318659799, | |
| "eval_recall": 0.8060879368658399, | |
| "eval_runtime": 13.5776, | |
| "eval_samples_per_second": 130.656, | |
| "eval_steps_per_second": 2.062, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 4.778972520908005e-05, | |
| "loss": 0.723, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 4.74910394265233e-05, | |
| "loss": 0.7006, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 4.7192353643966546e-05, | |
| "loss": 0.6869, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 4.6893667861409805e-05, | |
| "loss": 0.6641, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 4.659498207885305e-05, | |
| "loss": 0.7004, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.6167, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.8280721533258174, | |
| "eval_f1": 0.8247319496196939, | |
| "eval_loss": 0.5483558177947998, | |
| "eval_precision": 0.8270850188543143, | |
| "eval_recall": 0.8280721533258174, | |
| "eval_runtime": 14.0048, | |
| "eval_samples_per_second": 126.671, | |
| "eval_steps_per_second": 1.999, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 4.5997610513739546e-05, | |
| "loss": 0.6697, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 4.56989247311828e-05, | |
| "loss": 0.6862, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 4.540023894862604e-05, | |
| "loss": 0.6565, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 4.51015531660693e-05, | |
| "loss": 0.6431, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "learning_rate": 4.4802867383512545e-05, | |
| "loss": 0.6266, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 5.92, | |
| "learning_rate": 4.4504181600955796e-05, | |
| "loss": 0.6291, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8190529875986471, | |
| "eval_f1": 0.8123047671692809, | |
| "eval_loss": 0.518372118473053, | |
| "eval_precision": 0.8240742110809667, | |
| "eval_recall": 0.8190529875986471, | |
| "eval_runtime": 13.7531, | |
| "eval_samples_per_second": 128.989, | |
| "eval_steps_per_second": 2.036, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 4.420549581839905e-05, | |
| "loss": 0.6341, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 4.390681003584229e-05, | |
| "loss": 0.6138, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 4.360812425328555e-05, | |
| "loss": 0.6053, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 4.3309438470728796e-05, | |
| "loss": 0.6214, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 0.5813, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 4.271206690561529e-05, | |
| "loss": 0.6113, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "eval_accuracy": 0.8134160090191658, | |
| "eval_f1": 0.8097211330299542, | |
| "eval_loss": 0.517450213432312, | |
| "eval_precision": 0.8148503054250988, | |
| "eval_recall": 0.8134160090191658, | |
| "eval_runtime": 13.7536, | |
| "eval_samples_per_second": 128.984, | |
| "eval_steps_per_second": 2.036, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 4.241338112305854e-05, | |
| "loss": 0.6379, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 4.2114695340501795e-05, | |
| "loss": 0.6186, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 4.1816009557945046e-05, | |
| "loss": 0.5546, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "learning_rate": 4.15173237753883e-05, | |
| "loss": 0.6064, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 4.121863799283154e-05, | |
| "loss": 0.5838, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 4.0919952210274794e-05, | |
| "loss": 0.5869, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.062126642771804e-05, | |
| "loss": 0.5468, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.830890642615558, | |
| "eval_f1": 0.8283405562023753, | |
| "eval_loss": 0.48974525928497314, | |
| "eval_precision": 0.8362878221565939, | |
| "eval_recall": 0.830890642615558, | |
| "eval_runtime": 13.9451, | |
| "eval_samples_per_second": 127.213, | |
| "eval_steps_per_second": 2.008, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.16, | |
| "learning_rate": 4.032258064516129e-05, | |
| "loss": 0.5366, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 4.002389486260454e-05, | |
| "loss": 0.5855, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 8.48, | |
| "learning_rate": 3.972520908004779e-05, | |
| "loss": 0.614, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 3.9426523297491045e-05, | |
| "loss": 0.5627, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 3.912783751493429e-05, | |
| "loss": 0.5817, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 3.882915173237754e-05, | |
| "loss": 0.567, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_accuracy": 0.8568207440811725, | |
| "eval_f1": 0.8528984263652862, | |
| "eval_loss": 0.4458546042442322, | |
| "eval_precision": 0.8594188650488367, | |
| "eval_recall": 0.8568207440811725, | |
| "eval_runtime": 13.7168, | |
| "eval_samples_per_second": 129.331, | |
| "eval_steps_per_second": 2.041, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "learning_rate": 3.8530465949820786e-05, | |
| "loss": 0.5478, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 3.8231780167264044e-05, | |
| "loss": 0.545, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 9.44, | |
| "learning_rate": 3.793309438470729e-05, | |
| "loss": 0.5359, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 3.763440860215054e-05, | |
| "loss": 0.5629, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 9.76, | |
| "learning_rate": 3.7335722819593785e-05, | |
| "loss": 0.5235, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.5449, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.8393461104847801, | |
| "eval_f1": 0.8353113203285151, | |
| "eval_loss": 0.45436403155326843, | |
| "eval_precision": 0.8389857130866388, | |
| "eval_recall": 0.8393461104847801, | |
| "eval_runtime": 13.5281, | |
| "eval_samples_per_second": 131.134, | |
| "eval_steps_per_second": 2.07, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 10.08, | |
| "learning_rate": 3.673835125448029e-05, | |
| "loss": 0.5295, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 10.24, | |
| "learning_rate": 3.643966547192354e-05, | |
| "loss": 0.5449, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "learning_rate": 3.614097968936679e-05, | |
| "loss": 0.5487, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 3.5842293906810036e-05, | |
| "loss": 0.5373, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 10.72, | |
| "learning_rate": 3.554360812425329e-05, | |
| "loss": 0.5215, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 10.88, | |
| "learning_rate": 3.524492234169653e-05, | |
| "loss": 0.5437, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "eval_accuracy": 0.8387824126268321, | |
| "eval_f1": 0.837506113528873, | |
| "eval_loss": 0.4527810215950012, | |
| "eval_precision": 0.8410308621038163, | |
| "eval_recall": 0.8387824126268321, | |
| "eval_runtime": 13.9421, | |
| "eval_samples_per_second": 127.241, | |
| "eval_steps_per_second": 2.008, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 11.04, | |
| "learning_rate": 3.494623655913979e-05, | |
| "loss": 0.5171, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 3.4647550776583035e-05, | |
| "loss": 0.502, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 11.36, | |
| "learning_rate": 3.4348864994026287e-05, | |
| "loss": 0.4862, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "learning_rate": 3.405017921146954e-05, | |
| "loss": 0.4907, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 11.68, | |
| "learning_rate": 3.375149342891278e-05, | |
| "loss": 0.5338, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 11.84, | |
| "learning_rate": 3.3452807646356034e-05, | |
| "loss": 0.5086, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 3.3154121863799286e-05, | |
| "loss": 0.4754, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.8421645997745209, | |
| "eval_f1": 0.839619453099759, | |
| "eval_loss": 0.452364444732666, | |
| "eval_precision": 0.842050666156185, | |
| "eval_recall": 0.8421645997745209, | |
| "eval_runtime": 13.7371, | |
| "eval_samples_per_second": 129.139, | |
| "eval_steps_per_second": 2.038, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 12.16, | |
| "learning_rate": 3.285543608124254e-05, | |
| "loss": 0.5049, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 12.32, | |
| "learning_rate": 3.255675029868578e-05, | |
| "loss": 0.4785, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 0.4929, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 12.64, | |
| "learning_rate": 3.195937873357228e-05, | |
| "loss": 0.5231, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 3.1660692951015537e-05, | |
| "loss": 0.4916, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 12.96, | |
| "learning_rate": 3.136200716845878e-05, | |
| "loss": 0.5121, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "eval_accuracy": 0.8382187147688839, | |
| "eval_f1": 0.8349456841777169, | |
| "eval_loss": 0.48403945565223694, | |
| "eval_precision": 0.841504759452455, | |
| "eval_recall": 0.8382187147688839, | |
| "eval_runtime": 13.696, | |
| "eval_samples_per_second": 129.527, | |
| "eval_steps_per_second": 2.044, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "learning_rate": 3.106332138590203e-05, | |
| "loss": 0.4791, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 13.28, | |
| "learning_rate": 3.0764635603345284e-05, | |
| "loss": 0.4757, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "learning_rate": 3.046594982078853e-05, | |
| "loss": 0.5169, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "learning_rate": 3.016726403823178e-05, | |
| "loss": 0.4688, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 13.76, | |
| "learning_rate": 2.9868578255675032e-05, | |
| "loss": 0.4987, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 13.92, | |
| "learning_rate": 2.9569892473118284e-05, | |
| "loss": 0.5074, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.8647125140924464, | |
| "eval_f1": 0.8611504419681582, | |
| "eval_loss": 0.41382190585136414, | |
| "eval_precision": 0.8649618555829393, | |
| "eval_recall": 0.8647125140924464, | |
| "eval_runtime": 13.8401, | |
| "eval_samples_per_second": 128.178, | |
| "eval_steps_per_second": 2.023, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "learning_rate": 2.9271206690561532e-05, | |
| "loss": 0.4825, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 14.24, | |
| "learning_rate": 2.897252090800478e-05, | |
| "loss": 0.4469, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 2.8673835125448028e-05, | |
| "loss": 0.4806, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 14.56, | |
| "learning_rate": 2.8375149342891276e-05, | |
| "loss": 0.5046, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 14.72, | |
| "learning_rate": 2.807646356033453e-05, | |
| "loss": 0.4685, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 14.88, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.4567, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 14.99, | |
| "eval_accuracy": 0.8483652762119503, | |
| "eval_f1": 0.8473043652299705, | |
| "eval_loss": 0.43390360474586487, | |
| "eval_precision": 0.8478835574213358, | |
| "eval_recall": 0.8483652762119503, | |
| "eval_runtime": 13.4635, | |
| "eval_samples_per_second": 131.763, | |
| "eval_steps_per_second": 2.08, | |
| "step": 937 | |
| }, | |
| { | |
| "epoch": 15.04, | |
| "learning_rate": 2.747909199522103e-05, | |
| "loss": 0.4697, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 15.2, | |
| "learning_rate": 2.718040621266428e-05, | |
| "loss": 0.4448, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 15.36, | |
| "learning_rate": 2.6881720430107527e-05, | |
| "loss": 0.4779, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 15.52, | |
| "learning_rate": 2.6583034647550775e-05, | |
| "loss": 0.4728, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 15.68, | |
| "learning_rate": 2.628434886499403e-05, | |
| "loss": 0.449, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 15.84, | |
| "learning_rate": 2.5985663082437278e-05, | |
| "loss": 0.4647, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 2.5686977299880526e-05, | |
| "loss": 0.4686, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.8540022547914318, | |
| "eval_f1": 0.8503855717055063, | |
| "eval_loss": 0.4390581548213959, | |
| "eval_precision": 0.8521425478625434, | |
| "eval_recall": 0.8540022547914318, | |
| "eval_runtime": 13.6331, | |
| "eval_samples_per_second": 130.125, | |
| "eval_steps_per_second": 2.054, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 16.16, | |
| "learning_rate": 2.5388291517323774e-05, | |
| "loss": 0.4523, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 16.32, | |
| "learning_rate": 2.5089605734767026e-05, | |
| "loss": 0.425, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 16.48, | |
| "learning_rate": 2.4790919952210277e-05, | |
| "loss": 0.4576, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 16.64, | |
| "learning_rate": 2.4492234169653525e-05, | |
| "loss": 0.4716, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 16.8, | |
| "learning_rate": 2.4193548387096777e-05, | |
| "loss": 0.4653, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 16.96, | |
| "learning_rate": 2.3894862604540025e-05, | |
| "loss": 0.414, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "eval_accuracy": 0.8421645997745209, | |
| "eval_f1": 0.8387533980836047, | |
| "eval_loss": 0.4626242518424988, | |
| "eval_precision": 0.8443264937625163, | |
| "eval_recall": 0.8421645997745209, | |
| "eval_runtime": 13.5432, | |
| "eval_samples_per_second": 130.988, | |
| "eval_steps_per_second": 2.067, | |
| "step": 1062 | |
| }, | |
| { | |
| "epoch": 17.12, | |
| "learning_rate": 2.3596176821983273e-05, | |
| "loss": 0.4315, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 17.28, | |
| "learning_rate": 2.3297491039426525e-05, | |
| "loss": 0.4434, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 17.44, | |
| "learning_rate": 2.2998805256869773e-05, | |
| "loss": 0.471, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 17.6, | |
| "learning_rate": 2.270011947431302e-05, | |
| "loss": 0.4612, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 17.76, | |
| "learning_rate": 2.2401433691756272e-05, | |
| "loss": 0.4356, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 17.92, | |
| "learning_rate": 2.2102747909199524e-05, | |
| "loss": 0.4382, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.8568207440811725, | |
| "eval_f1": 0.8541399194911224, | |
| "eval_loss": 0.4116300642490387, | |
| "eval_precision": 0.85579386308307, | |
| "eval_recall": 0.8568207440811725, | |
| "eval_runtime": 13.7859, | |
| "eval_samples_per_second": 128.683, | |
| "eval_steps_per_second": 2.031, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 18.08, | |
| "learning_rate": 2.1804062126642775e-05, | |
| "loss": 0.4364, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 18.24, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 0.4274, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 18.4, | |
| "learning_rate": 2.120669056152927e-05, | |
| "loss": 0.4348, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 18.56, | |
| "learning_rate": 2.0908004778972523e-05, | |
| "loss": 0.4282, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 18.72, | |
| "learning_rate": 2.060931899641577e-05, | |
| "loss": 0.4276, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 18.88, | |
| "learning_rate": 2.031063321385902e-05, | |
| "loss": 0.4322, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 18.99, | |
| "eval_accuracy": 0.8511837655016911, | |
| "eval_f1": 0.8495623720056149, | |
| "eval_loss": 0.45063334703445435, | |
| "eval_precision": 0.852933422878775, | |
| "eval_recall": 0.8511837655016911, | |
| "eval_runtime": 13.8857, | |
| "eval_samples_per_second": 127.757, | |
| "eval_steps_per_second": 2.016, | |
| "step": 1187 | |
| }, | |
| { | |
| "epoch": 19.04, | |
| "learning_rate": 2.001194743130227e-05, | |
| "loss": 0.4436, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "learning_rate": 1.9713261648745522e-05, | |
| "loss": 0.4315, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 19.36, | |
| "learning_rate": 1.941457586618877e-05, | |
| "loss": 0.4345, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 19.52, | |
| "learning_rate": 1.9115890083632022e-05, | |
| "loss": 0.4184, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 19.68, | |
| "learning_rate": 1.881720430107527e-05, | |
| "loss": 0.3963, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 19.84, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.4429, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 1.821983273596177e-05, | |
| "loss": 0.4424, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.8568207440811725, | |
| "eval_f1": 0.853755880936842, | |
| "eval_loss": 0.4299766421318054, | |
| "eval_precision": 0.8542170522451458, | |
| "eval_recall": 0.8568207440811725, | |
| "eval_runtime": 13.9264, | |
| "eval_samples_per_second": 127.384, | |
| "eval_steps_per_second": 2.011, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 20.16, | |
| "learning_rate": 1.7921146953405018e-05, | |
| "loss": 0.4161, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 20.32, | |
| "learning_rate": 1.7622461170848266e-05, | |
| "loss": 0.4376, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 20.48, | |
| "learning_rate": 1.7323775388291518e-05, | |
| "loss": 0.4074, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 20.64, | |
| "learning_rate": 1.702508960573477e-05, | |
| "loss": 0.4086, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 20.8, | |
| "learning_rate": 1.6726403823178017e-05, | |
| "loss": 0.4241, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 20.96, | |
| "learning_rate": 1.642771804062127e-05, | |
| "loss": 0.4062, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 20.99, | |
| "eval_accuracy": 0.8607666290868095, | |
| "eval_f1": 0.8578192554406807, | |
| "eval_loss": 0.46094101667404175, | |
| "eval_precision": 0.8597134738328431, | |
| "eval_recall": 0.8607666290868095, | |
| "eval_runtime": 13.9346, | |
| "eval_samples_per_second": 127.309, | |
| "eval_steps_per_second": 2.009, | |
| "step": 1312 | |
| }, | |
| { | |
| "epoch": 21.12, | |
| "learning_rate": 1.6129032258064517e-05, | |
| "loss": 0.4001, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 21.28, | |
| "learning_rate": 1.5830346475507768e-05, | |
| "loss": 0.4104, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 21.44, | |
| "learning_rate": 1.5531660692951016e-05, | |
| "loss": 0.4122, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 21.6, | |
| "learning_rate": 1.5232974910394265e-05, | |
| "loss": 0.4104, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 21.76, | |
| "learning_rate": 1.4934289127837516e-05, | |
| "loss": 0.4147, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 21.92, | |
| "learning_rate": 1.4635603345280766e-05, | |
| "loss": 0.4459, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.8568207440811725, | |
| "eval_f1": 0.8550789116252512, | |
| "eval_loss": 0.4516655206680298, | |
| "eval_precision": 0.8580092586671261, | |
| "eval_recall": 0.8568207440811725, | |
| "eval_runtime": 14.066, | |
| "eval_samples_per_second": 126.119, | |
| "eval_steps_per_second": 1.991, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 22.08, | |
| "learning_rate": 1.4336917562724014e-05, | |
| "loss": 0.4001, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 22.24, | |
| "learning_rate": 1.4038231780167265e-05, | |
| "loss": 0.3857, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 22.4, | |
| "learning_rate": 1.3739545997610515e-05, | |
| "loss": 0.3974, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 22.56, | |
| "learning_rate": 1.3440860215053763e-05, | |
| "loss": 0.4053, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 22.72, | |
| "learning_rate": 1.3142174432497015e-05, | |
| "loss": 0.4245, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 22.88, | |
| "learning_rate": 1.2843488649940263e-05, | |
| "loss": 0.4109, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 22.99, | |
| "eval_accuracy": 0.8534385569334837, | |
| "eval_f1": 0.851281717070011, | |
| "eval_loss": 0.4489527940750122, | |
| "eval_precision": 0.8533797338459855, | |
| "eval_recall": 0.8534385569334837, | |
| "eval_runtime": 13.45, | |
| "eval_samples_per_second": 131.896, | |
| "eval_steps_per_second": 2.082, | |
| "step": 1437 | |
| }, | |
| { | |
| "epoch": 23.04, | |
| "learning_rate": 1.2544802867383513e-05, | |
| "loss": 0.3901, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 23.2, | |
| "learning_rate": 1.2246117084826763e-05, | |
| "loss": 0.3844, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 23.36, | |
| "learning_rate": 1.1947431302270013e-05, | |
| "loss": 0.4026, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 23.52, | |
| "learning_rate": 1.1648745519713262e-05, | |
| "loss": 0.3776, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 23.68, | |
| "learning_rate": 1.135005973715651e-05, | |
| "loss": 0.4339, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 23.84, | |
| "learning_rate": 1.1051373954599762e-05, | |
| "loss": 0.3664, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 1.0752688172043012e-05, | |
| "loss": 0.3984, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.8618940248027057, | |
| "eval_f1": 0.8600929614148337, | |
| "eval_loss": 0.4433577358722687, | |
| "eval_precision": 0.8606197563990508, | |
| "eval_recall": 0.8618940248027057, | |
| "eval_runtime": 13.7162, | |
| "eval_samples_per_second": 129.336, | |
| "eval_steps_per_second": 2.041, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 24.16, | |
| "learning_rate": 1.0454002389486262e-05, | |
| "loss": 0.4126, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 24.32, | |
| "learning_rate": 1.015531660692951e-05, | |
| "loss": 0.4055, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 24.48, | |
| "learning_rate": 9.856630824372761e-06, | |
| "loss": 0.3877, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 24.64, | |
| "learning_rate": 9.557945041816011e-06, | |
| "loss": 0.3729, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 24.8, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.3755, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 24.96, | |
| "learning_rate": 8.960573476702509e-06, | |
| "loss": 0.4034, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 24.99, | |
| "eval_accuracy": 0.8596392333709132, | |
| "eval_f1": 0.8570599752806491, | |
| "eval_loss": 0.4613305926322937, | |
| "eval_precision": 0.8576552533858167, | |
| "eval_recall": 0.8596392333709132, | |
| "eval_runtime": 13.9609, | |
| "eval_samples_per_second": 127.069, | |
| "eval_steps_per_second": 2.006, | |
| "step": 1562 | |
| }, | |
| { | |
| "epoch": 25.12, | |
| "learning_rate": 8.661887694145759e-06, | |
| "loss": 0.3659, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 25.28, | |
| "learning_rate": 8.363201911589009e-06, | |
| "loss": 0.3861, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 25.44, | |
| "learning_rate": 8.064516129032258e-06, | |
| "loss": 0.3785, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 25.6, | |
| "learning_rate": 7.765830346475508e-06, | |
| "loss": 0.3964, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 25.76, | |
| "learning_rate": 7.467144563918758e-06, | |
| "loss": 0.3637, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 25.92, | |
| "learning_rate": 7.168458781362007e-06, | |
| "loss": 0.3682, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.8596392333709132, | |
| "eval_f1": 0.8573210473344683, | |
| "eval_loss": 0.44932126998901367, | |
| "eval_precision": 0.8590653339754385, | |
| "eval_recall": 0.8596392333709132, | |
| "eval_runtime": 13.9659, | |
| "eval_samples_per_second": 127.023, | |
| "eval_steps_per_second": 2.005, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 26.08, | |
| "learning_rate": 6.869772998805258e-06, | |
| "loss": 0.3835, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 26.24, | |
| "learning_rate": 6.5710872162485075e-06, | |
| "loss": 0.3822, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 26.4, | |
| "learning_rate": 6.2724014336917564e-06, | |
| "loss": 0.3718, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 26.56, | |
| "learning_rate": 5.973715651135006e-06, | |
| "loss": 0.363, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 26.72, | |
| "learning_rate": 5.675029868578255e-06, | |
| "loss": 0.3806, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 26.88, | |
| "learning_rate": 5.376344086021506e-06, | |
| "loss": 0.3779, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 26.99, | |
| "eval_accuracy": 0.859075535512965, | |
| "eval_f1": 0.8574501446594237, | |
| "eval_loss": 0.43663036823272705, | |
| "eval_precision": 0.858097786045595, | |
| "eval_recall": 0.859075535512965, | |
| "eval_runtime": 13.9594, | |
| "eval_samples_per_second": 127.083, | |
| "eval_steps_per_second": 2.006, | |
| "step": 1687 | |
| }, | |
| { | |
| "epoch": 27.04, | |
| "learning_rate": 5.077658303464755e-06, | |
| "loss": 0.3703, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 27.2, | |
| "learning_rate": 4.7789725209080055e-06, | |
| "loss": 0.3861, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 27.36, | |
| "learning_rate": 4.4802867383512545e-06, | |
| "loss": 0.4055, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 27.52, | |
| "learning_rate": 4.181600955794504e-06, | |
| "loss": 0.367, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 27.68, | |
| "learning_rate": 3.882915173237754e-06, | |
| "loss": 0.3611, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 27.84, | |
| "learning_rate": 3.5842293906810035e-06, | |
| "loss": 0.3832, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 3.2855436081242537e-06, | |
| "loss": 0.3965, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.8635851183765502, | |
| "eval_f1": 0.860856890269207, | |
| "eval_loss": 0.4370027780532837, | |
| "eval_precision": 0.861555153490155, | |
| "eval_recall": 0.8635851183765502, | |
| "eval_runtime": 13.6783, | |
| "eval_samples_per_second": 129.695, | |
| "eval_steps_per_second": 2.047, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 28.16, | |
| "learning_rate": 2.986857825567503e-06, | |
| "loss": 0.3825, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 28.32, | |
| "learning_rate": 2.688172043010753e-06, | |
| "loss": 0.3915, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 28.48, | |
| "learning_rate": 2.3894862604540028e-06, | |
| "loss": 0.3672, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 28.64, | |
| "learning_rate": 2.090800477897252e-06, | |
| "loss": 0.3815, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 28.8, | |
| "learning_rate": 1.7921146953405017e-06, | |
| "loss": 0.3818, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 28.96, | |
| "learning_rate": 1.4934289127837516e-06, | |
| "loss": 0.3712, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 28.99, | |
| "eval_accuracy": 0.859075535512965, | |
| "eval_f1": 0.8568287375485683, | |
| "eval_loss": 0.43800774216651917, | |
| "eval_precision": 0.85758168827886, | |
| "eval_recall": 0.859075535512965, | |
| "eval_runtime": 13.5857, | |
| "eval_samples_per_second": 130.579, | |
| "eval_steps_per_second": 2.061, | |
| "step": 1812 | |
| }, | |
| { | |
| "epoch": 29.12, | |
| "learning_rate": 1.1947431302270014e-06, | |
| "loss": 0.3881, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 29.28, | |
| "learning_rate": 8.960573476702509e-07, | |
| "loss": 0.3663, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 29.44, | |
| "learning_rate": 5.973715651135007e-07, | |
| "loss": 0.367, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 29.6, | |
| "learning_rate": 2.9868578255675034e-07, | |
| "loss": 0.3605, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "learning_rate": 0.0, | |
| "loss": 0.3776, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "eval_accuracy": 0.863021420518602, | |
| "eval_f1": 0.861154414382136, | |
| "eval_loss": 0.4388639032840729, | |
| "eval_precision": 0.8623967061995776, | |
| "eval_recall": 0.863021420518602, | |
| "eval_runtime": 13.7313, | |
| "eval_samples_per_second": 129.194, | |
| "eval_steps_per_second": 2.039, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "step": 1860, | |
| "total_flos": 2.7441227042701443e+19, | |
| "train_loss": 0.5734176897233533, | |
| "train_runtime": 6732.6789, | |
| "train_samples_per_second": 71.125, | |
| "train_steps_per_second": 0.276 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1860, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "total_flos": 2.7441227042701443e+19, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |