| { | |
| "best_metric": 0.8235625704622322, | |
| "best_model_checkpoint": "vit-large-patch32-224-in21k-finetuned-galaxy10-decals/checkpoint-1746", | |
| "epoch": 29.819639278557116, | |
| "eval_steps": 500, | |
| "global_step": 3720, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 2.688172043010753e-06, | |
| "loss": 2.2922, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 5.376344086021506e-06, | |
| "loss": 2.2641, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 8.064516129032258e-06, | |
| "loss": 2.1892, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.0752688172043012e-05, | |
| "loss": 2.0773, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.3440860215053763e-05, | |
| "loss": 1.9892, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.6129032258064517e-05, | |
| "loss": 1.8382, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 1.881720430107527e-05, | |
| "loss": 1.7049, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 1.5763, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.4193548387096777e-05, | |
| "loss": 1.4746, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2.6881720430107527e-05, | |
| "loss": 1.3415, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 2.9569892473118284e-05, | |
| "loss": 1.2596, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 1.1583, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.7068771138669673, | |
| "eval_f1": 0.675810673269607, | |
| "eval_loss": 1.0550673007965088, | |
| "eval_precision": 0.6558614630795221, | |
| "eval_recall": 0.7068771138669673, | |
| "eval_runtime": 13.9158, | |
| "eval_samples_per_second": 127.481, | |
| "eval_steps_per_second": 4.024, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3.494623655913979e-05, | |
| "loss": 1.1563, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.763440860215054e-05, | |
| "loss": 1.0897, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 4.032258064516129e-05, | |
| "loss": 1.0546, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 1.0226, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 4.56989247311828e-05, | |
| "loss": 0.9752, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 4.8387096774193554e-05, | |
| "loss": 0.9802, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 5.1075268817204304e-05, | |
| "loss": 0.9326, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 5.3763440860215054e-05, | |
| "loss": 0.9747, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 5.645161290322582e-05, | |
| "loss": 0.9057, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 5.913978494623657e-05, | |
| "loss": 0.9051, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 6.182795698924732e-05, | |
| "loss": 0.9089, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 6.451612903225807e-05, | |
| "loss": 0.8599, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.762119503945885, | |
| "eval_f1": 0.7556580755827043, | |
| "eval_loss": 0.7913542985916138, | |
| "eval_precision": 0.7717184841610082, | |
| "eval_recall": 0.762119503945885, | |
| "eval_runtime": 13.9163, | |
| "eval_samples_per_second": 127.476, | |
| "eval_steps_per_second": 4.024, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.720430107526882e-05, | |
| "loss": 0.8928, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 6.989247311827958e-05, | |
| "loss": 0.8706, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 7.258064516129033e-05, | |
| "loss": 0.8337, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 7.526881720430108e-05, | |
| "loss": 0.841, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 7.795698924731183e-05, | |
| "loss": 0.8265, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 8.064516129032258e-05, | |
| "loss": 0.8324, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 0.843, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 8.60215053763441e-05, | |
| "loss": 0.8416, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 8.870967741935484e-05, | |
| "loss": 0.8022, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 9.13978494623656e-05, | |
| "loss": 0.8954, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 9.408602150537636e-05, | |
| "loss": 0.8137, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 9.677419354838711e-05, | |
| "loss": 0.793, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 9.946236559139786e-05, | |
| "loss": 0.854, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7671927846674182, | |
| "eval_f1": 0.7641877899984297, | |
| "eval_loss": 0.711500346660614, | |
| "eval_precision": 0.7849640754022337, | |
| "eval_recall": 0.7671927846674182, | |
| "eval_runtime": 13.9691, | |
| "eval_samples_per_second": 126.994, | |
| "eval_steps_per_second": 4.009, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 9.97610513739546e-05, | |
| "loss": 0.8143, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 9.946236559139786e-05, | |
| "loss": 0.7927, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 9.916367980884111e-05, | |
| "loss": 0.7554, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 9.886499402628435e-05, | |
| "loss": 0.7916, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 9.85663082437276e-05, | |
| "loss": 0.743, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 9.826762246117085e-05, | |
| "loss": 0.7777, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 9.79689366786141e-05, | |
| "loss": 0.7625, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 9.767025089605735e-05, | |
| "loss": 0.7553, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 9.73715651135006e-05, | |
| "loss": 0.7728, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 9.707287933094386e-05, | |
| "loss": 0.7744, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 9.677419354838711e-05, | |
| "loss": 0.746, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 9.647550776583036e-05, | |
| "loss": 0.7282, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7683201803833145, | |
| "eval_f1": 0.7603757540346687, | |
| "eval_loss": 0.6807467937469482, | |
| "eval_precision": 0.7746268567673005, | |
| "eval_recall": 0.7683201803833145, | |
| "eval_runtime": 13.8857, | |
| "eval_samples_per_second": 127.757, | |
| "eval_steps_per_second": 4.033, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 9.61768219832736e-05, | |
| "loss": 0.6907, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 9.587813620071685e-05, | |
| "loss": 0.7377, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 9.55794504181601e-05, | |
| "loss": 0.7166, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 9.528076463560335e-05, | |
| "loss": 0.6948, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 9.49820788530466e-05, | |
| "loss": 0.6907, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 9.468339307048984e-05, | |
| "loss": 0.7011, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 9.438470728793309e-05, | |
| "loss": 0.6377, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 9.408602150537636e-05, | |
| "loss": 0.6651, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 9.378733572281961e-05, | |
| "loss": 0.6564, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 9.348864994026285e-05, | |
| "loss": 0.6498, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 9.31899641577061e-05, | |
| "loss": 0.7252, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 9.289127837514935e-05, | |
| "loss": 0.6279, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "learning_rate": 9.25925925925926e-05, | |
| "loss": 0.6165, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.8015783540022547, | |
| "eval_f1": 0.8014834346227482, | |
| "eval_loss": 0.6207838654518127, | |
| "eval_precision": 0.808772544756013, | |
| "eval_recall": 0.8015783540022547, | |
| "eval_runtime": 13.9594, | |
| "eval_samples_per_second": 127.082, | |
| "eval_steps_per_second": 4.012, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 9.229390681003584e-05, | |
| "loss": 0.6385, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "learning_rate": 9.199522102747909e-05, | |
| "loss": 0.6732, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 5.21, | |
| "learning_rate": 9.169653524492234e-05, | |
| "loss": 0.6464, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "learning_rate": 9.13978494623656e-05, | |
| "loss": 0.6721, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "learning_rate": 9.109916367980885e-05, | |
| "loss": 0.6044, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 9.080047789725208e-05, | |
| "loss": 0.6356, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "learning_rate": 9.050179211469535e-05, | |
| "loss": 0.5974, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 9.02031063321386e-05, | |
| "loss": 0.6674, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "learning_rate": 8.990442054958185e-05, | |
| "loss": 0.6068, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "learning_rate": 8.960573476702509e-05, | |
| "loss": 0.5778, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 5.85, | |
| "learning_rate": 8.930704898446834e-05, | |
| "loss": 0.6623, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 8.900836320191159e-05, | |
| "loss": 0.5946, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8043968432919955, | |
| "eval_f1": 0.8009427414085736, | |
| "eval_loss": 0.5850139260292053, | |
| "eval_precision": 0.8083816060983575, | |
| "eval_recall": 0.8043968432919955, | |
| "eval_runtime": 13.968, | |
| "eval_samples_per_second": 127.005, | |
| "eval_steps_per_second": 4.009, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 8.870967741935484e-05, | |
| "loss": 0.637, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "learning_rate": 8.84109916367981e-05, | |
| "loss": 0.5925, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 6.17, | |
| "learning_rate": 8.811230585424133e-05, | |
| "loss": 0.6185, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 8.781362007168459e-05, | |
| "loss": 0.5654, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 8.751493428912784e-05, | |
| "loss": 0.5526, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 8.72162485065711e-05, | |
| "loss": 0.5886, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 6.49, | |
| "learning_rate": 8.691756272401434e-05, | |
| "loss": 0.6155, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "learning_rate": 8.661887694145759e-05, | |
| "loss": 0.5868, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 6.65, | |
| "learning_rate": 8.632019115890084e-05, | |
| "loss": 0.6124, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 6.73, | |
| "learning_rate": 8.60215053763441e-05, | |
| "loss": 0.5738, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "learning_rate": 8.572281959378735e-05, | |
| "loss": 0.6027, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 6.89, | |
| "learning_rate": 8.542413381123058e-05, | |
| "loss": 0.6024, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "learning_rate": 8.512544802867384e-05, | |
| "loss": 0.6243, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.7931228861330327, | |
| "eval_f1": 0.7934536670951715, | |
| "eval_loss": 0.6090168952941895, | |
| "eval_precision": 0.8036636158334073, | |
| "eval_recall": 0.7931228861330327, | |
| "eval_runtime": 13.9191, | |
| "eval_samples_per_second": 127.451, | |
| "eval_steps_per_second": 4.023, | |
| "step": 873 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 8.482676224611709e-05, | |
| "loss": 0.5911, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 7.13, | |
| "learning_rate": 8.452807646356034e-05, | |
| "loss": 0.575, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 8.422939068100359e-05, | |
| "loss": 0.5783, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 7.29, | |
| "learning_rate": 8.393070489844683e-05, | |
| "loss": 0.5047, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 8.363201911589009e-05, | |
| "loss": 0.5574, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 7.45, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 0.5489, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 7.54, | |
| "learning_rate": 8.30346475507766e-05, | |
| "loss": 0.5754, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 7.62, | |
| "learning_rate": 8.273596176821983e-05, | |
| "loss": 0.562, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 7.7, | |
| "learning_rate": 8.243727598566309e-05, | |
| "loss": 0.5474, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "learning_rate": 8.213859020310634e-05, | |
| "loss": 0.542, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "learning_rate": 8.183990442054959e-05, | |
| "loss": 0.5261, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 7.94, | |
| "learning_rate": 8.154121863799284e-05, | |
| "loss": 0.5429, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8021420518602029, | |
| "eval_f1": 0.800590565745525, | |
| "eval_loss": 0.5829988718032837, | |
| "eval_precision": 0.8086973403659105, | |
| "eval_recall": 0.8021420518602029, | |
| "eval_runtime": 13.8868, | |
| "eval_samples_per_second": 127.747, | |
| "eval_steps_per_second": 4.033, | |
| "step": 998 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 8.124253285543608e-05, | |
| "loss": 0.5494, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "learning_rate": 8.094384707287933e-05, | |
| "loss": 0.4858, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 8.18, | |
| "learning_rate": 8.064516129032258e-05, | |
| "loss": 0.4911, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 8.26, | |
| "learning_rate": 8.034647550776585e-05, | |
| "loss": 0.5308, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 8.34, | |
| "learning_rate": 8.004778972520908e-05, | |
| "loss": 0.4982, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 8.42, | |
| "learning_rate": 7.974910394265234e-05, | |
| "loss": 0.5323, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "learning_rate": 7.945041816009559e-05, | |
| "loss": 0.5513, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "learning_rate": 7.915173237753884e-05, | |
| "loss": 0.5434, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "learning_rate": 7.885304659498209e-05, | |
| "loss": 0.5127, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 8.74, | |
| "learning_rate": 7.855436081242533e-05, | |
| "loss": 0.5551, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "learning_rate": 7.825567502986858e-05, | |
| "loss": 0.4928, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "learning_rate": 7.795698924731183e-05, | |
| "loss": 0.5295, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 8.98, | |
| "learning_rate": 7.765830346475508e-05, | |
| "loss": 0.558, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_accuracy": 0.8094701240135288, | |
| "eval_f1": 0.8080741738843362, | |
| "eval_loss": 0.5725377202033997, | |
| "eval_precision": 0.8190738508467059, | |
| "eval_recall": 0.8094701240135288, | |
| "eval_runtime": 13.9705, | |
| "eval_samples_per_second": 126.982, | |
| "eval_steps_per_second": 4.008, | |
| "step": 1122 | |
| }, | |
| { | |
| "epoch": 9.06, | |
| "learning_rate": 7.735961768219832e-05, | |
| "loss": 0.5015, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 9.14, | |
| "learning_rate": 7.706093189964157e-05, | |
| "loss": 0.5086, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 9.22, | |
| "learning_rate": 7.676224611708484e-05, | |
| "loss": 0.503, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "learning_rate": 7.646356033452809e-05, | |
| "loss": 0.454, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "learning_rate": 7.616487455197133e-05, | |
| "loss": 0.4917, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 9.46, | |
| "learning_rate": 7.586618876941458e-05, | |
| "loss": 0.4835, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 9.54, | |
| "learning_rate": 7.556750298685783e-05, | |
| "loss": 0.5217, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 7.526881720430108e-05, | |
| "loss": 0.4515, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "learning_rate": 7.497013142174433e-05, | |
| "loss": 0.458, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "learning_rate": 7.467144563918757e-05, | |
| "loss": 0.4737, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 9.86, | |
| "learning_rate": 7.437275985663082e-05, | |
| "loss": 0.4771, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 9.94, | |
| "learning_rate": 7.407407407407407e-05, | |
| "loss": 0.457, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.8122886133032694, | |
| "eval_f1": 0.8085263361904211, | |
| "eval_loss": 0.570176899433136, | |
| "eval_precision": 0.8144151275813437, | |
| "eval_recall": 0.8122886133032694, | |
| "eval_runtime": 13.9223, | |
| "eval_samples_per_second": 127.421, | |
| "eval_steps_per_second": 4.022, | |
| "step": 1247 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "learning_rate": 7.377538829151732e-05, | |
| "loss": 0.5038, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 10.1, | |
| "learning_rate": 7.347670250896058e-05, | |
| "loss": 0.4696, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 10.18, | |
| "learning_rate": 7.317801672640383e-05, | |
| "loss": 0.4644, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 10.26, | |
| "learning_rate": 7.287933094384708e-05, | |
| "loss": 0.4382, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 10.34, | |
| "learning_rate": 7.258064516129033e-05, | |
| "loss": 0.5107, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 10.42, | |
| "learning_rate": 7.228195937873358e-05, | |
| "loss": 0.4672, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 10.5, | |
| "learning_rate": 7.198327359617682e-05, | |
| "loss": 0.4487, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 10.58, | |
| "learning_rate": 7.168458781362007e-05, | |
| "loss": 0.4769, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 10.66, | |
| "learning_rate": 7.138590203106332e-05, | |
| "loss": 0.467, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 10.74, | |
| "learning_rate": 7.108721624850657e-05, | |
| "loss": 0.4357, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 10.82, | |
| "learning_rate": 7.078853046594983e-05, | |
| "loss": 0.4554, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 10.9, | |
| "learning_rate": 7.048984468339306e-05, | |
| "loss": 0.4287, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 10.98, | |
| "learning_rate": 7.019115890083633e-05, | |
| "loss": 0.4399, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.8021420518602029, | |
| "eval_f1": 0.7994709899560392, | |
| "eval_loss": 0.5973069667816162, | |
| "eval_precision": 0.8012595725937439, | |
| "eval_recall": 0.8021420518602029, | |
| "eval_runtime": 13.9088, | |
| "eval_samples_per_second": 127.545, | |
| "eval_steps_per_second": 4.026, | |
| "step": 1372 | |
| }, | |
| { | |
| "epoch": 11.06, | |
| "learning_rate": 6.989247311827958e-05, | |
| "loss": 0.4462, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 11.14, | |
| "learning_rate": 6.959378733572283e-05, | |
| "loss": 0.4108, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 11.22, | |
| "learning_rate": 6.929510155316607e-05, | |
| "loss": 0.4281, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 11.3, | |
| "learning_rate": 6.899641577060932e-05, | |
| "loss": 0.4398, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 11.38, | |
| "learning_rate": 6.869772998805257e-05, | |
| "loss": 0.4099, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 11.46, | |
| "learning_rate": 6.839904420549582e-05, | |
| "loss": 0.416, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 11.54, | |
| "learning_rate": 6.810035842293908e-05, | |
| "loss": 0.4344, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 11.62, | |
| "learning_rate": 6.780167264038231e-05, | |
| "loss": 0.4743, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 11.7, | |
| "learning_rate": 6.750298685782557e-05, | |
| "loss": 0.4653, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 11.78, | |
| "learning_rate": 6.720430107526882e-05, | |
| "loss": 0.432, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 11.86, | |
| "learning_rate": 6.690561529271207e-05, | |
| "loss": 0.401, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 11.94, | |
| "learning_rate": 6.660692951015532e-05, | |
| "loss": 0.4055, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.8156708004509583, | |
| "eval_f1": 0.8121920876994667, | |
| "eval_loss": 0.5799275040626526, | |
| "eval_precision": 0.8186260895692437, | |
| "eval_recall": 0.8156708004509583, | |
| "eval_runtime": 13.8727, | |
| "eval_samples_per_second": 127.877, | |
| "eval_steps_per_second": 4.037, | |
| "step": 1497 | |
| }, | |
| { | |
| "epoch": 12.02, | |
| "learning_rate": 6.630824372759857e-05, | |
| "loss": 0.4159, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 12.1, | |
| "learning_rate": 6.600955794504182e-05, | |
| "loss": 0.4114, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 12.18, | |
| "learning_rate": 6.571087216248507e-05, | |
| "loss": 0.3556, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 12.26, | |
| "learning_rate": 6.541218637992833e-05, | |
| "loss": 0.3985, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 12.34, | |
| "learning_rate": 6.511350059737156e-05, | |
| "loss": 0.3881, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 12.42, | |
| "learning_rate": 6.481481481481482e-05, | |
| "loss": 0.4056, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 12.51, | |
| "learning_rate": 6.451612903225807e-05, | |
| "loss": 0.376, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 12.59, | |
| "learning_rate": 6.421744324970132e-05, | |
| "loss": 0.4252, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 12.67, | |
| "learning_rate": 6.391875746714456e-05, | |
| "loss": 0.4305, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 12.75, | |
| "learning_rate": 6.362007168458781e-05, | |
| "loss": 0.4046, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 12.83, | |
| "learning_rate": 6.332138590203107e-05, | |
| "loss": 0.4145, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 12.91, | |
| "learning_rate": 6.302270011947432e-05, | |
| "loss": 0.3957, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "learning_rate": 6.272401433691756e-05, | |
| "loss": 0.417, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "eval_accuracy": 0.8060879368658399, | |
| "eval_f1": 0.8065978971439847, | |
| "eval_loss": 0.6005584597587585, | |
| "eval_precision": 0.8174852930657591, | |
| "eval_recall": 0.8060879368658399, | |
| "eval_runtime": 13.8751, | |
| "eval_samples_per_second": 127.855, | |
| "eval_steps_per_second": 4.036, | |
| "step": 1621 | |
| }, | |
| { | |
| "epoch": 13.07, | |
| "learning_rate": 6.242532855436081e-05, | |
| "loss": 0.3922, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 13.15, | |
| "learning_rate": 6.212664277180407e-05, | |
| "loss": 0.3669, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 13.23, | |
| "learning_rate": 6.182795698924732e-05, | |
| "loss": 0.3481, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 13.31, | |
| "learning_rate": 6.152927120669057e-05, | |
| "loss": 0.4228, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 13.39, | |
| "learning_rate": 6.12305854241338e-05, | |
| "loss": 0.4005, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 13.47, | |
| "learning_rate": 6.093189964157706e-05, | |
| "loss": 0.3907, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 13.55, | |
| "learning_rate": 6.063321385902031e-05, | |
| "loss": 0.3794, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 13.63, | |
| "learning_rate": 6.033452807646356e-05, | |
| "loss": 0.3674, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 13.71, | |
| "learning_rate": 6.0035842293906806e-05, | |
| "loss": 0.3755, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 13.79, | |
| "learning_rate": 5.9737156511350064e-05, | |
| "loss": 0.3894, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 13.87, | |
| "learning_rate": 5.9438470728793316e-05, | |
| "loss": 0.3896, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 13.95, | |
| "learning_rate": 5.913978494623657e-05, | |
| "loss": 0.3843, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.8235625704622322, | |
| "eval_f1": 0.8211884981742252, | |
| "eval_loss": 0.5849118232727051, | |
| "eval_precision": 0.8257093320559268, | |
| "eval_recall": 0.8235625704622322, | |
| "eval_runtime": 13.9088, | |
| "eval_samples_per_second": 127.545, | |
| "eval_steps_per_second": 4.026, | |
| "step": 1746 | |
| }, | |
| { | |
| "epoch": 14.03, | |
| "learning_rate": 5.884109916367981e-05, | |
| "loss": 0.3812, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 14.11, | |
| "learning_rate": 5.8542413381123063e-05, | |
| "loss": 0.3649, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 14.19, | |
| "learning_rate": 5.824372759856631e-05, | |
| "loss": 0.3558, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 14.27, | |
| "learning_rate": 5.794504181600956e-05, | |
| "loss": 0.3546, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 14.35, | |
| "learning_rate": 5.764635603345281e-05, | |
| "loss": 0.3358, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 14.43, | |
| "learning_rate": 5.7347670250896056e-05, | |
| "loss": 0.3642, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 14.51, | |
| "learning_rate": 5.704898446833931e-05, | |
| "loss": 0.3864, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 14.59, | |
| "learning_rate": 5.675029868578255e-05, | |
| "loss": 0.3888, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 14.67, | |
| "learning_rate": 5.645161290322582e-05, | |
| "loss": 0.3685, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 14.75, | |
| "learning_rate": 5.615292712066906e-05, | |
| "loss": 0.3526, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 14.83, | |
| "learning_rate": 5.5854241338112313e-05, | |
| "loss": 0.3508, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 14.91, | |
| "learning_rate": 5.555555555555556e-05, | |
| "loss": 0.3899, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 14.99, | |
| "learning_rate": 5.525686977299881e-05, | |
| "loss": 0.371, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.8196166854565953, | |
| "eval_f1": 0.8160946296928634, | |
| "eval_loss": 0.5710554718971252, | |
| "eval_precision": 0.8157171716885654, | |
| "eval_recall": 0.8196166854565953, | |
| "eval_runtime": 13.9159, | |
| "eval_samples_per_second": 127.48, | |
| "eval_steps_per_second": 4.024, | |
| "step": 1871 | |
| }, | |
| { | |
| "epoch": 15.07, | |
| "learning_rate": 5.495818399044206e-05, | |
| "loss": 0.3403, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 15.15, | |
| "learning_rate": 5.4659498207885306e-05, | |
| "loss": 0.3424, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 15.23, | |
| "learning_rate": 5.436081242532856e-05, | |
| "loss": 0.3215, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 15.31, | |
| "learning_rate": 5.40621266427718e-05, | |
| "loss": 0.3331, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 15.39, | |
| "learning_rate": 5.3763440860215054e-05, | |
| "loss": 0.3256, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 15.47, | |
| "learning_rate": 5.34647550776583e-05, | |
| "loss": 0.3904, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 15.55, | |
| "learning_rate": 5.316606929510155e-05, | |
| "loss": 0.3341, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 15.63, | |
| "learning_rate": 5.286738351254481e-05, | |
| "loss": 0.3314, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 15.71, | |
| "learning_rate": 5.256869772998806e-05, | |
| "loss": 0.3456, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 15.79, | |
| "learning_rate": 5.2270011947431304e-05, | |
| "loss": 0.3519, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 15.87, | |
| "learning_rate": 5.1971326164874556e-05, | |
| "loss": 0.3828, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 15.95, | |
| "learning_rate": 5.167264038231781e-05, | |
| "loss": 0.3546, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.8139797068771139, | |
| "eval_f1": 0.8146871974463645, | |
| "eval_loss": 0.6050013899803162, | |
| "eval_precision": 0.8170888548475337, | |
| "eval_recall": 0.8139797068771139, | |
| "eval_runtime": 13.9647, | |
| "eval_samples_per_second": 127.034, | |
| "eval_steps_per_second": 4.01, | |
| "step": 1996 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 5.137395459976105e-05, | |
| "loss": 0.2979, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 16.11, | |
| "learning_rate": 5.1075268817204304e-05, | |
| "loss": 0.3127, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 16.19, | |
| "learning_rate": 5.077658303464755e-05, | |
| "loss": 0.3268, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 16.27, | |
| "learning_rate": 5.04778972520908e-05, | |
| "loss": 0.3028, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 16.35, | |
| "learning_rate": 5.017921146953405e-05, | |
| "loss": 0.3038, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 16.43, | |
| "learning_rate": 4.98805256869773e-05, | |
| "loss": 0.3026, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 16.51, | |
| "learning_rate": 4.9581839904420555e-05, | |
| "loss": 0.3286, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 16.59, | |
| "learning_rate": 4.92831541218638e-05, | |
| "loss": 0.3566, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 16.67, | |
| "learning_rate": 4.898446833930705e-05, | |
| "loss": 0.3359, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 16.75, | |
| "learning_rate": 4.86857825567503e-05, | |
| "loss": 0.3429, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 16.83, | |
| "learning_rate": 4.8387096774193554e-05, | |
| "loss": 0.3022, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 16.91, | |
| "learning_rate": 4.80884109916368e-05, | |
| "loss": 0.2499, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "learning_rate": 4.778972520908005e-05, | |
| "loss": 0.2935, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "eval_accuracy": 0.8105975197294251, | |
| "eval_f1": 0.8091270414673493, | |
| "eval_loss": 0.6425190567970276, | |
| "eval_precision": 0.8159338106488563, | |
| "eval_recall": 0.8105975197294251, | |
| "eval_runtime": 13.9131, | |
| "eval_samples_per_second": 127.506, | |
| "eval_steps_per_second": 4.025, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 17.07, | |
| "learning_rate": 4.74910394265233e-05, | |
| "loss": 0.3291, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 17.15, | |
| "learning_rate": 4.7192353643966546e-05, | |
| "loss": 0.2689, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 17.23, | |
| "learning_rate": 4.6893667861409805e-05, | |
| "loss": 0.3085, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 17.31, | |
| "learning_rate": 4.659498207885305e-05, | |
| "loss": 0.3301, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 17.39, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.3513, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 17.47, | |
| "learning_rate": 4.5997610513739546e-05, | |
| "loss": 0.3126, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 17.56, | |
| "learning_rate": 4.56989247311828e-05, | |
| "loss": 0.3097, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 17.64, | |
| "learning_rate": 4.540023894862604e-05, | |
| "loss": 0.2827, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 17.72, | |
| "learning_rate": 4.51015531660693e-05, | |
| "loss": 0.3009, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 17.8, | |
| "learning_rate": 4.4802867383512545e-05, | |
| "loss": 0.2964, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 17.88, | |
| "learning_rate": 4.4504181600955796e-05, | |
| "loss": 0.3333, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 17.96, | |
| "learning_rate": 4.420549581839905e-05, | |
| "loss": 0.2505, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.8111612175873731, | |
| "eval_f1": 0.8085505452503554, | |
| "eval_loss": 0.6569081544876099, | |
| "eval_precision": 0.8090615845706326, | |
| "eval_recall": 0.8111612175873731, | |
| "eval_runtime": 13.9528, | |
| "eval_samples_per_second": 127.143, | |
| "eval_steps_per_second": 4.014, | |
| "step": 2245 | |
| }, | |
| { | |
| "epoch": 18.04, | |
| "learning_rate": 4.390681003584229e-05, | |
| "loss": 0.3185, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 18.12, | |
| "learning_rate": 4.360812425328555e-05, | |
| "loss": 0.2652, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 18.2, | |
| "learning_rate": 4.3309438470728796e-05, | |
| "loss": 0.2574, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 18.28, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 0.2881, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 18.36, | |
| "learning_rate": 4.271206690561529e-05, | |
| "loss": 0.2817, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 18.44, | |
| "learning_rate": 4.241338112305854e-05, | |
| "loss": 0.2459, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 18.52, | |
| "learning_rate": 4.2114695340501795e-05, | |
| "loss": 0.2439, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 18.6, | |
| "learning_rate": 4.1816009557945046e-05, | |
| "loss": 0.3175, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 18.68, | |
| "learning_rate": 4.15173237753883e-05, | |
| "loss": 0.2769, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 18.76, | |
| "learning_rate": 4.121863799283154e-05, | |
| "loss": 0.2501, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 18.84, | |
| "learning_rate": 4.0919952210274794e-05, | |
| "loss": 0.2753, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 18.92, | |
| "learning_rate": 4.062126642771804e-05, | |
| "loss": 0.2596, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 4.032258064516129e-05, | |
| "loss": 0.3094, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.8162344983089064, | |
| "eval_f1": 0.8137230782611028, | |
| "eval_loss": 0.6557679176330566, | |
| "eval_precision": 0.8136560183765512, | |
| "eval_recall": 0.8162344983089064, | |
| "eval_runtime": 13.916, | |
| "eval_samples_per_second": 127.479, | |
| "eval_steps_per_second": 4.024, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 19.08, | |
| "learning_rate": 4.002389486260454e-05, | |
| "loss": 0.2808, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 19.16, | |
| "learning_rate": 3.972520908004779e-05, | |
| "loss": 0.2711, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 19.24, | |
| "learning_rate": 3.9426523297491045e-05, | |
| "loss": 0.2398, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 19.32, | |
| "learning_rate": 3.912783751493429e-05, | |
| "loss": 0.2486, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 19.4, | |
| "learning_rate": 3.882915173237754e-05, | |
| "loss": 0.298, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 19.48, | |
| "learning_rate": 3.8530465949820786e-05, | |
| "loss": 0.2912, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 19.56, | |
| "learning_rate": 3.8231780167264044e-05, | |
| "loss": 0.2639, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 19.64, | |
| "learning_rate": 3.793309438470729e-05, | |
| "loss": 0.2576, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 19.72, | |
| "learning_rate": 3.763440860215054e-05, | |
| "loss": 0.279, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 19.8, | |
| "learning_rate": 3.7335722819593785e-05, | |
| "loss": 0.2663, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 19.88, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.2825, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 19.96, | |
| "learning_rate": 3.673835125448029e-05, | |
| "loss": 0.2739, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.8066516347237881, | |
| "eval_f1": 0.802546589933035, | |
| "eval_loss": 0.7201483249664307, | |
| "eval_precision": 0.8094414374058572, | |
| "eval_recall": 0.8066516347237881, | |
| "eval_runtime": 13.9211, | |
| "eval_samples_per_second": 127.433, | |
| "eval_steps_per_second": 4.023, | |
| "step": 2495 | |
| }, | |
| { | |
| "epoch": 20.04, | |
| "learning_rate": 3.643966547192354e-05, | |
| "loss": 0.2703, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 20.12, | |
| "learning_rate": 3.614097968936679e-05, | |
| "loss": 0.2246, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 20.2, | |
| "learning_rate": 3.5842293906810036e-05, | |
| "loss": 0.2629, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 20.28, | |
| "learning_rate": 3.554360812425329e-05, | |
| "loss": 0.262, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 20.36, | |
| "learning_rate": 3.524492234169653e-05, | |
| "loss": 0.2514, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 20.44, | |
| "learning_rate": 3.494623655913979e-05, | |
| "loss": 0.2242, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 20.52, | |
| "learning_rate": 3.4647550776583035e-05, | |
| "loss": 0.2515, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 20.6, | |
| "learning_rate": 3.4348864994026287e-05, | |
| "loss": 0.2493, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 20.68, | |
| "learning_rate": 3.405017921146954e-05, | |
| "loss": 0.2214, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 20.76, | |
| "learning_rate": 3.375149342891278e-05, | |
| "loss": 0.2572, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 20.84, | |
| "learning_rate": 3.3452807646356034e-05, | |
| "loss": 0.284, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 20.92, | |
| "learning_rate": 3.3154121863799286e-05, | |
| "loss": 0.2224, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 20.99, | |
| "eval_accuracy": 0.8139797068771139, | |
| "eval_f1": 0.8113945895758867, | |
| "eval_loss": 0.7226550579071045, | |
| "eval_precision": 0.817507486502582, | |
| "eval_recall": 0.8139797068771139, | |
| "eval_runtime": 13.9528, | |
| "eval_samples_per_second": 127.143, | |
| "eval_steps_per_second": 4.014, | |
| "step": 2619 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 3.285543608124254e-05, | |
| "loss": 0.2487, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 21.08, | |
| "learning_rate": 3.255675029868578e-05, | |
| "loss": 0.2287, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 21.16, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 0.2602, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 21.24, | |
| "learning_rate": 3.195937873357228e-05, | |
| "loss": 0.2418, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 21.32, | |
| "learning_rate": 3.1660692951015537e-05, | |
| "loss": 0.2257, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 21.4, | |
| "learning_rate": 3.136200716845878e-05, | |
| "loss": 0.245, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 21.48, | |
| "learning_rate": 3.106332138590203e-05, | |
| "loss": 0.2372, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 21.56, | |
| "learning_rate": 3.0764635603345284e-05, | |
| "loss": 0.2423, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 21.64, | |
| "learning_rate": 3.046594982078853e-05, | |
| "loss": 0.2382, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 21.72, | |
| "learning_rate": 3.016726403823178e-05, | |
| "loss": 0.2612, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 21.8, | |
| "learning_rate": 2.9868578255675032e-05, | |
| "loss": 0.2672, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 21.88, | |
| "learning_rate": 2.9569892473118284e-05, | |
| "loss": 0.2709, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 21.96, | |
| "learning_rate": 2.9271206690561532e-05, | |
| "loss": 0.2359, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.8156708004509583, | |
| "eval_f1": 0.8136226295183577, | |
| "eval_loss": 0.6940749287605286, | |
| "eval_precision": 0.8141746574510457, | |
| "eval_recall": 0.8156708004509583, | |
| "eval_runtime": 13.9138, | |
| "eval_samples_per_second": 127.499, | |
| "eval_steps_per_second": 4.025, | |
| "step": 2744 | |
| }, | |
| { | |
| "epoch": 22.04, | |
| "learning_rate": 2.897252090800478e-05, | |
| "loss": 0.24, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 22.12, | |
| "learning_rate": 2.8673835125448028e-05, | |
| "loss": 0.2392, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 22.2, | |
| "learning_rate": 2.8375149342891276e-05, | |
| "loss": 0.2119, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 22.28, | |
| "learning_rate": 2.807646356033453e-05, | |
| "loss": 0.2302, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 22.36, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.2252, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 22.44, | |
| "learning_rate": 2.747909199522103e-05, | |
| "loss": 0.2462, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 22.53, | |
| "learning_rate": 2.718040621266428e-05, | |
| "loss": 0.2013, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 22.61, | |
| "learning_rate": 2.6881720430107527e-05, | |
| "loss": 0.2161, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 22.69, | |
| "learning_rate": 2.6583034647550775e-05, | |
| "loss": 0.234, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 22.77, | |
| "learning_rate": 2.628434886499403e-05, | |
| "loss": 0.2262, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 22.85, | |
| "learning_rate": 2.5985663082437278e-05, | |
| "loss": 0.2512, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 22.93, | |
| "learning_rate": 2.5686977299880526e-05, | |
| "loss": 0.2535, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.8156708004509583, | |
| "eval_f1": 0.81227251289756, | |
| "eval_loss": 0.7086111307144165, | |
| "eval_precision": 0.8160279268347481, | |
| "eval_recall": 0.8156708004509583, | |
| "eval_runtime": 13.9265, | |
| "eval_samples_per_second": 127.383, | |
| "eval_steps_per_second": 4.021, | |
| "step": 2869 | |
| }, | |
| { | |
| "epoch": 23.01, | |
| "learning_rate": 2.5388291517323774e-05, | |
| "loss": 0.2342, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 23.09, | |
| "learning_rate": 2.5089605734767026e-05, | |
| "loss": 0.2462, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 23.17, | |
| "learning_rate": 2.4790919952210277e-05, | |
| "loss": 0.2265, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 23.25, | |
| "learning_rate": 2.4492234169653525e-05, | |
| "loss": 0.2021, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 23.33, | |
| "learning_rate": 2.4193548387096777e-05, | |
| "loss": 0.2297, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 23.41, | |
| "learning_rate": 2.3894862604540025e-05, | |
| "loss": 0.2118, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 23.49, | |
| "learning_rate": 2.3596176821983273e-05, | |
| "loss": 0.2336, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 23.57, | |
| "learning_rate": 2.3297491039426525e-05, | |
| "loss": 0.2567, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 23.65, | |
| "learning_rate": 2.2998805256869773e-05, | |
| "loss": 0.2195, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 23.73, | |
| "learning_rate": 2.270011947431302e-05, | |
| "loss": 0.2118, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 23.81, | |
| "learning_rate": 2.2401433691756272e-05, | |
| "loss": 0.2059, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 23.89, | |
| "learning_rate": 2.2102747909199524e-05, | |
| "loss": 0.2296, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 23.97, | |
| "learning_rate": 2.1804062126642775e-05, | |
| "loss": 0.2047, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.8235625704622322, | |
| "eval_f1": 0.8207213990294976, | |
| "eval_loss": 0.718461275100708, | |
| "eval_precision": 0.8235593618387343, | |
| "eval_recall": 0.8235625704622322, | |
| "eval_runtime": 13.9231, | |
| "eval_samples_per_second": 127.414, | |
| "eval_steps_per_second": 4.022, | |
| "step": 2994 | |
| }, | |
| { | |
| "epoch": 24.05, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 0.2186, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 24.13, | |
| "learning_rate": 2.120669056152927e-05, | |
| "loss": 0.225, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 24.21, | |
| "learning_rate": 2.0908004778972523e-05, | |
| "loss": 0.2026, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 24.29, | |
| "learning_rate": 2.060931899641577e-05, | |
| "loss": 0.2395, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 24.37, | |
| "learning_rate": 2.031063321385902e-05, | |
| "loss": 0.2248, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 24.45, | |
| "learning_rate": 2.001194743130227e-05, | |
| "loss": 0.2428, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 24.53, | |
| "learning_rate": 1.9713261648745522e-05, | |
| "loss": 0.205, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 24.61, | |
| "learning_rate": 1.941457586618877e-05, | |
| "loss": 0.1945, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 24.69, | |
| "learning_rate": 1.9115890083632022e-05, | |
| "loss": 0.2383, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 24.77, | |
| "learning_rate": 1.881720430107527e-05, | |
| "loss": 0.2024, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 24.85, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.2566, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 24.93, | |
| "learning_rate": 1.821983273596177e-05, | |
| "loss": 0.2162, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 24.99, | |
| "eval_accuracy": 0.8218714768883878, | |
| "eval_f1": 0.819374560219833, | |
| "eval_loss": 0.7135424017906189, | |
| "eval_precision": 0.8200242274112762, | |
| "eval_recall": 0.8218714768883878, | |
| "eval_runtime": 13.9436, | |
| "eval_samples_per_second": 127.227, | |
| "eval_steps_per_second": 4.016, | |
| "step": 3118 | |
| }, | |
| { | |
| "epoch": 25.01, | |
| "learning_rate": 1.7921146953405018e-05, | |
| "loss": 0.1963, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 25.09, | |
| "learning_rate": 1.7622461170848266e-05, | |
| "loss": 0.2148, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 25.17, | |
| "learning_rate": 1.7323775388291518e-05, | |
| "loss": 0.1822, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 25.25, | |
| "learning_rate": 1.702508960573477e-05, | |
| "loss": 0.1892, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 25.33, | |
| "learning_rate": 1.6726403823178017e-05, | |
| "loss": 0.1957, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 25.41, | |
| "learning_rate": 1.642771804062127e-05, | |
| "loss": 0.1992, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 25.49, | |
| "learning_rate": 1.6129032258064517e-05, | |
| "loss": 0.2256, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 25.57, | |
| "learning_rate": 1.5830346475507768e-05, | |
| "loss": 0.2044, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 25.65, | |
| "learning_rate": 1.5531660692951016e-05, | |
| "loss": 0.1935, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 25.73, | |
| "learning_rate": 1.5232974910394265e-05, | |
| "loss": 0.204, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 25.81, | |
| "learning_rate": 1.4934289127837516e-05, | |
| "loss": 0.1704, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 25.89, | |
| "learning_rate": 1.4635603345280766e-05, | |
| "loss": 0.2058, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 25.97, | |
| "learning_rate": 1.4336917562724014e-05, | |
| "loss": 0.2297, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.8213077790304397, | |
| "eval_f1": 0.8179171868511029, | |
| "eval_loss": 0.7269182801246643, | |
| "eval_precision": 0.8171612109698507, | |
| "eval_recall": 0.8213077790304397, | |
| "eval_runtime": 13.9251, | |
| "eval_samples_per_second": 127.396, | |
| "eval_steps_per_second": 4.022, | |
| "step": 3243 | |
| }, | |
| { | |
| "epoch": 26.05, | |
| "learning_rate": 1.4038231780167265e-05, | |
| "loss": 0.204, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 26.13, | |
| "learning_rate": 1.3739545997610515e-05, | |
| "loss": 0.239, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 26.21, | |
| "learning_rate": 1.3440860215053763e-05, | |
| "loss": 0.194, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 26.29, | |
| "learning_rate": 1.3142174432497015e-05, | |
| "loss": 0.1982, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 26.37, | |
| "learning_rate": 1.2843488649940263e-05, | |
| "loss": 0.2319, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 26.45, | |
| "learning_rate": 1.2544802867383513e-05, | |
| "loss": 0.2058, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 26.53, | |
| "learning_rate": 1.2246117084826763e-05, | |
| "loss": 0.2072, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 26.61, | |
| "learning_rate": 1.1947431302270013e-05, | |
| "loss": 0.1955, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 26.69, | |
| "learning_rate": 1.1648745519713262e-05, | |
| "loss": 0.196, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 26.77, | |
| "learning_rate": 1.135005973715651e-05, | |
| "loss": 0.2042, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 26.85, | |
| "learning_rate": 1.1051373954599762e-05, | |
| "loss": 0.2072, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 26.93, | |
| "learning_rate": 1.0752688172043012e-05, | |
| "loss": 0.2048, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.814543404735062, | |
| "eval_f1": 0.8142732078615984, | |
| "eval_loss": 0.7392024993896484, | |
| "eval_precision": 0.8155644054213834, | |
| "eval_recall": 0.814543404735062, | |
| "eval_runtime": 13.9919, | |
| "eval_samples_per_second": 126.787, | |
| "eval_steps_per_second": 4.002, | |
| "step": 3368 | |
| }, | |
| { | |
| "epoch": 27.01, | |
| "learning_rate": 1.0454002389486262e-05, | |
| "loss": 0.2096, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 27.09, | |
| "learning_rate": 1.015531660692951e-05, | |
| "loss": 0.1959, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 27.17, | |
| "learning_rate": 9.856630824372761e-06, | |
| "loss": 0.192, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 27.25, | |
| "learning_rate": 9.557945041816011e-06, | |
| "loss": 0.2406, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 27.33, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.2225, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 27.41, | |
| "learning_rate": 8.960573476702509e-06, | |
| "loss": 0.206, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 27.49, | |
| "learning_rate": 8.661887694145759e-06, | |
| "loss": 0.1993, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 27.58, | |
| "learning_rate": 8.363201911589009e-06, | |
| "loss": 0.1926, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 27.66, | |
| "learning_rate": 8.064516129032258e-06, | |
| "loss": 0.1757, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 27.74, | |
| "learning_rate": 7.765830346475508e-06, | |
| "loss": 0.1913, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 27.82, | |
| "learning_rate": 7.467144563918758e-06, | |
| "loss": 0.196, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 27.9, | |
| "learning_rate": 7.168458781362007e-06, | |
| "loss": 0.1966, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 27.98, | |
| "learning_rate": 6.869772998805258e-06, | |
| "loss": 0.2156, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.8207440811724915, | |
| "eval_f1": 0.8173955936562302, | |
| "eval_loss": 0.7452513575553894, | |
| "eval_precision": 0.818232638453996, | |
| "eval_recall": 0.8207440811724915, | |
| "eval_runtime": 13.9402, | |
| "eval_samples_per_second": 127.258, | |
| "eval_steps_per_second": 4.017, | |
| "step": 3493 | |
| }, | |
| { | |
| "epoch": 28.06, | |
| "learning_rate": 6.5710872162485075e-06, | |
| "loss": 0.218, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 28.14, | |
| "learning_rate": 6.2724014336917564e-06, | |
| "loss": 0.1878, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 28.22, | |
| "learning_rate": 5.973715651135006e-06, | |
| "loss": 0.2132, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 28.3, | |
| "learning_rate": 5.675029868578255e-06, | |
| "loss": 0.1802, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 28.38, | |
| "learning_rate": 5.376344086021506e-06, | |
| "loss": 0.1857, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 28.46, | |
| "learning_rate": 5.077658303464755e-06, | |
| "loss": 0.189, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 28.54, | |
| "learning_rate": 4.7789725209080055e-06, | |
| "loss": 0.1699, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 28.62, | |
| "learning_rate": 4.4802867383512545e-06, | |
| "loss": 0.2193, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 28.7, | |
| "learning_rate": 4.181600955794504e-06, | |
| "loss": 0.1855, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 28.78, | |
| "learning_rate": 3.882915173237754e-06, | |
| "loss": 0.1957, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 28.86, | |
| "learning_rate": 3.5842293906810035e-06, | |
| "loss": 0.2059, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 28.94, | |
| "learning_rate": 3.2855436081242537e-06, | |
| "loss": 0.1785, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 28.99, | |
| "eval_accuracy": 0.8167981961668546, | |
| "eval_f1": 0.8144560702043755, | |
| "eval_loss": 0.749666690826416, | |
| "eval_precision": 0.8157480462760235, | |
| "eval_recall": 0.8167981961668546, | |
| "eval_runtime": 13.8966, | |
| "eval_samples_per_second": 127.657, | |
| "eval_steps_per_second": 4.03, | |
| "step": 3617 | |
| }, | |
| { | |
| "epoch": 29.02, | |
| "learning_rate": 2.986857825567503e-06, | |
| "loss": 0.2005, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 29.1, | |
| "learning_rate": 2.688172043010753e-06, | |
| "loss": 0.1767, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 29.18, | |
| "learning_rate": 2.3894862604540028e-06, | |
| "loss": 0.1836, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 29.26, | |
| "learning_rate": 2.090800477897252e-06, | |
| "loss": 0.1772, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 29.34, | |
| "learning_rate": 1.7921146953405017e-06, | |
| "loss": 0.1851, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 29.42, | |
| "learning_rate": 1.4934289127837516e-06, | |
| "loss": 0.1944, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 29.5, | |
| "learning_rate": 1.1947431302270014e-06, | |
| "loss": 0.1762, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 29.58, | |
| "learning_rate": 8.960573476702509e-07, | |
| "loss": 0.2001, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 29.66, | |
| "learning_rate": 5.973715651135007e-07, | |
| "loss": 0.1681, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 29.74, | |
| "learning_rate": 2.9868578255675034e-07, | |
| "loss": 0.1826, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 29.82, | |
| "learning_rate": 0.0, | |
| "loss": 0.1785, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 29.82, | |
| "eval_accuracy": 0.8201803833145435, | |
| "eval_f1": 0.8172820930459103, | |
| "eval_loss": 0.7429009079933167, | |
| "eval_precision": 0.8190214518875245, | |
| "eval_recall": 0.8201803833145435, | |
| "eval_runtime": 13.9063, | |
| "eval_samples_per_second": 127.568, | |
| "eval_steps_per_second": 4.027, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 29.82, | |
| "step": 3720, | |
| "total_flos": 1.3134189871289722e+20, | |
| "train_loss": 0.4506285851360649, | |
| "train_runtime": 7123.617, | |
| "train_samples_per_second": 67.221, | |
| "train_steps_per_second": 0.522 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 3720, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "total_flos": 1.3134189871289722e+20, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |