| { | |
| "best_metric": 0.9085, | |
| "best_model_checkpoint": "dinov2-base-imagenet1k-1-layer-finetuned-galaxy10-decals-head-finetuned-30-galaxy_mnist/checkpoint-1625", | |
| "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": 5.376344086021506e-06, | |
| "loss": 1.4847, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.0752688172043012e-05, | |
| "loss": 1.4852, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.6129032258064517e-05, | |
| "loss": 1.4228, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 1.3215, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2.6881720430107527e-05, | |
| "loss": 1.2228, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 1.1345, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.602, | |
| "eval_f1": 0.5996525481777757, | |
| "eval_loss": 0.9672438502311707, | |
| "eval_precision": 0.6135035757974513, | |
| "eval_recall": 0.602, | |
| "eval_runtime": 20.2505, | |
| "eval_samples_per_second": 98.763, | |
| "eval_steps_per_second": 3.111, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.763440860215054e-05, | |
| "loss": 1.0154, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 0.894, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 4.8387096774193554e-05, | |
| "loss": 0.8051, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 5.3763440860215054e-05, | |
| "loss": 0.7095, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 5.913978494623657e-05, | |
| "loss": 0.5923, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 6.451612903225807e-05, | |
| "loss": 0.5365, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8585, | |
| "eval_f1": 0.8584727216941275, | |
| "eval_loss": 0.38548731803894043, | |
| "eval_precision": 0.8601677831034371, | |
| "eval_recall": 0.8585, | |
| "eval_runtime": 18.9905, | |
| "eval_samples_per_second": 105.316, | |
| "eval_steps_per_second": 3.317, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 6.989247311827958e-05, | |
| "loss": 0.4901, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 7.526881720430108e-05, | |
| "loss": 0.4544, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 8.064516129032258e-05, | |
| "loss": 0.429, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 8.60215053763441e-05, | |
| "loss": 0.3978, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 9.13978494623656e-05, | |
| "loss": 0.4114, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 9.677419354838711e-05, | |
| "loss": 0.3715, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.8875, | |
| "eval_f1": 0.8872470858675392, | |
| "eval_loss": 0.2805759310722351, | |
| "eval_precision": 0.887274322709706, | |
| "eval_recall": 0.8875, | |
| "eval_runtime": 18.9054, | |
| "eval_samples_per_second": 105.79, | |
| "eval_steps_per_second": 3.332, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 9.97610513739546e-05, | |
| "loss": 0.3743, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 9.916367980884111e-05, | |
| "loss": 0.3883, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 9.85663082437276e-05, | |
| "loss": 0.3772, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 9.79689366786141e-05, | |
| "loss": 0.3383, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 9.73715651135006e-05, | |
| "loss": 0.3247, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 9.677419354838711e-05, | |
| "loss": 0.3435, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 9.61768219832736e-05, | |
| "loss": 0.3509, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.895, | |
| "eval_f1": 0.894923597615375, | |
| "eval_loss": 0.25571316480636597, | |
| "eval_precision": 0.8948639219853853, | |
| "eval_recall": 0.895, | |
| "eval_runtime": 18.3327, | |
| "eval_samples_per_second": 109.095, | |
| "eval_steps_per_second": 3.436, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 9.55794504181601e-05, | |
| "loss": 0.3312, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 9.49820788530466e-05, | |
| "loss": 0.3133, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 9.438470728793309e-05, | |
| "loss": 0.3154, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 9.378733572281961e-05, | |
| "loss": 0.3345, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 9.31899641577061e-05, | |
| "loss": 0.3199, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 9.25925925925926e-05, | |
| "loss": 0.3333, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.898, | |
| "eval_f1": 0.8978858543835784, | |
| "eval_loss": 0.2504391074180603, | |
| "eval_precision": 0.8984821452036961, | |
| "eval_recall": 0.898, | |
| "eval_runtime": 18.9012, | |
| "eval_samples_per_second": 105.813, | |
| "eval_steps_per_second": 3.333, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 9.199522102747909e-05, | |
| "loss": 0.324, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 9.13978494623656e-05, | |
| "loss": 0.3337, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 9.080047789725208e-05, | |
| "loss": 0.3034, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 9.02031063321386e-05, | |
| "loss": 0.3125, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "learning_rate": 8.960573476702509e-05, | |
| "loss": 0.3379, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 5.92, | |
| "learning_rate": 8.900836320191159e-05, | |
| "loss": 0.3073, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8965, | |
| "eval_f1": 0.8963823706059946, | |
| "eval_loss": 0.2423676997423172, | |
| "eval_precision": 0.8978691592905659, | |
| "eval_recall": 0.8965, | |
| "eval_runtime": 18.3587, | |
| "eval_samples_per_second": 108.94, | |
| "eval_steps_per_second": 3.432, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 8.84109916367981e-05, | |
| "loss": 0.3171, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 8.781362007168459e-05, | |
| "loss": 0.2992, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 8.72162485065711e-05, | |
| "loss": 0.3137, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 8.661887694145759e-05, | |
| "loss": 0.3001, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 8.60215053763441e-05, | |
| "loss": 0.2973, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 8.542413381123058e-05, | |
| "loss": 0.3169, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "eval_accuracy": 0.898, | |
| "eval_f1": 0.8979351860376636, | |
| "eval_loss": 0.23515738546848297, | |
| "eval_precision": 0.8981763641021214, | |
| "eval_recall": 0.898, | |
| "eval_runtime": 18.3352, | |
| "eval_samples_per_second": 109.08, | |
| "eval_steps_per_second": 3.436, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 8.482676224611709e-05, | |
| "loss": 0.3304, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 8.422939068100359e-05, | |
| "loss": 0.3123, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 8.363201911589009e-05, | |
| "loss": 0.3158, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "learning_rate": 8.30346475507766e-05, | |
| "loss": 0.306, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 8.243727598566309e-05, | |
| "loss": 0.332, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 8.183990442054959e-05, | |
| "loss": 0.2854, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 8.124253285543608e-05, | |
| "loss": 0.2698, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.896, | |
| "eval_f1": 0.8959315867259724, | |
| "eval_loss": 0.2348407357931137, | |
| "eval_precision": 0.8970828903049132, | |
| "eval_recall": 0.896, | |
| "eval_runtime": 18.9718, | |
| "eval_samples_per_second": 105.419, | |
| "eval_steps_per_second": 3.321, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.16, | |
| "learning_rate": 8.064516129032258e-05, | |
| "loss": 0.2916, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 8.004778972520908e-05, | |
| "loss": 0.3167, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 8.48, | |
| "learning_rate": 7.945041816009559e-05, | |
| "loss": 0.3004, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 7.885304659498209e-05, | |
| "loss": 0.2871, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 7.825567502986858e-05, | |
| "loss": 0.3021, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 7.765830346475508e-05, | |
| "loss": 0.2681, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_accuracy": 0.903, | |
| "eval_f1": 0.9030294415458766, | |
| "eval_loss": 0.2299664318561554, | |
| "eval_precision": 0.9040191472829451, | |
| "eval_recall": 0.903, | |
| "eval_runtime": 18.9775, | |
| "eval_samples_per_second": 105.388, | |
| "eval_steps_per_second": 3.32, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "learning_rate": 7.706093189964157e-05, | |
| "loss": 0.2993, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 7.646356033452809e-05, | |
| "loss": 0.2923, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 9.44, | |
| "learning_rate": 7.586618876941458e-05, | |
| "loss": 0.2982, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 7.526881720430108e-05, | |
| "loss": 0.2982, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 9.76, | |
| "learning_rate": 7.467144563918757e-05, | |
| "loss": 0.2911, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 7.407407407407407e-05, | |
| "loss": 0.2533, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9045, | |
| "eval_f1": 0.9045277233870969, | |
| "eval_loss": 0.22740726172924042, | |
| "eval_precision": 0.9049334888453927, | |
| "eval_recall": 0.9045, | |
| "eval_runtime": 18.9014, | |
| "eval_samples_per_second": 105.812, | |
| "eval_steps_per_second": 3.333, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 10.08, | |
| "learning_rate": 7.347670250896058e-05, | |
| "loss": 0.2947, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 10.24, | |
| "learning_rate": 7.287933094384708e-05, | |
| "loss": 0.2948, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "learning_rate": 7.228195937873358e-05, | |
| "loss": 0.2977, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 7.168458781362007e-05, | |
| "loss": 0.2928, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 10.72, | |
| "learning_rate": 7.108721624850657e-05, | |
| "loss": 0.279, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 10.88, | |
| "learning_rate": 7.048984468339306e-05, | |
| "loss": 0.2816, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "eval_accuracy": 0.9035, | |
| "eval_f1": 0.9034374170529604, | |
| "eval_loss": 0.22473882138729095, | |
| "eval_precision": 0.9037339672384987, | |
| "eval_recall": 0.9035, | |
| "eval_runtime": 18.9107, | |
| "eval_samples_per_second": 105.76, | |
| "eval_steps_per_second": 3.331, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 11.04, | |
| "learning_rate": 6.989247311827958e-05, | |
| "loss": 0.2938, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 6.929510155316607e-05, | |
| "loss": 0.2668, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 11.36, | |
| "learning_rate": 6.869772998805257e-05, | |
| "loss": 0.2738, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "learning_rate": 6.810035842293908e-05, | |
| "loss": 0.2984, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 11.68, | |
| "learning_rate": 6.750298685782557e-05, | |
| "loss": 0.3222, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 11.84, | |
| "learning_rate": 6.690561529271207e-05, | |
| "loss": 0.3011, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 6.630824372759857e-05, | |
| "loss": 0.27, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9055, | |
| "eval_f1": 0.9055186113920457, | |
| "eval_loss": 0.22268515825271606, | |
| "eval_precision": 0.9056819816793115, | |
| "eval_recall": 0.9055, | |
| "eval_runtime": 18.3106, | |
| "eval_samples_per_second": 109.227, | |
| "eval_steps_per_second": 3.441, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 12.16, | |
| "learning_rate": 6.571087216248507e-05, | |
| "loss": 0.276, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 12.32, | |
| "learning_rate": 6.511350059737156e-05, | |
| "loss": 0.3129, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "learning_rate": 6.451612903225807e-05, | |
| "loss": 0.2917, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 12.64, | |
| "learning_rate": 6.391875746714456e-05, | |
| "loss": 0.2754, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 6.332138590203107e-05, | |
| "loss": 0.2613, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 12.96, | |
| "learning_rate": 6.272401433691756e-05, | |
| "loss": 0.2716, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "eval_accuracy": 0.903, | |
| "eval_f1": 0.9029885028927512, | |
| "eval_loss": 0.2239924967288971, | |
| "eval_precision": 0.9034879312167448, | |
| "eval_recall": 0.903, | |
| "eval_runtime": 18.897, | |
| "eval_samples_per_second": 105.837, | |
| "eval_steps_per_second": 3.334, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "learning_rate": 6.212664277180407e-05, | |
| "loss": 0.2982, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 13.28, | |
| "learning_rate": 6.152927120669057e-05, | |
| "loss": 0.2715, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "learning_rate": 6.093189964157706e-05, | |
| "loss": 0.2783, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "learning_rate": 6.033452807646356e-05, | |
| "loss": 0.2848, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 13.76, | |
| "learning_rate": 5.9737156511350064e-05, | |
| "loss": 0.2802, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 13.92, | |
| "learning_rate": 5.913978494623657e-05, | |
| "loss": 0.2638, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.904, | |
| "eval_f1": 0.903993732957165, | |
| "eval_loss": 0.2199670523405075, | |
| "eval_precision": 0.9041546755106024, | |
| "eval_recall": 0.904, | |
| "eval_runtime": 18.9152, | |
| "eval_samples_per_second": 105.735, | |
| "eval_steps_per_second": 3.331, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "learning_rate": 5.8542413381123063e-05, | |
| "loss": 0.2741, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 14.24, | |
| "learning_rate": 5.794504181600956e-05, | |
| "loss": 0.3091, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 5.7347670250896056e-05, | |
| "loss": 0.2751, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 14.56, | |
| "learning_rate": 5.675029868578255e-05, | |
| "loss": 0.2481, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 14.72, | |
| "learning_rate": 5.615292712066906e-05, | |
| "loss": 0.2832, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 14.88, | |
| "learning_rate": 5.555555555555556e-05, | |
| "loss": 0.3064, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 14.99, | |
| "eval_accuracy": 0.907, | |
| "eval_f1": 0.9069462959672662, | |
| "eval_loss": 0.22218729555606842, | |
| "eval_precision": 0.9083327409883352, | |
| "eval_recall": 0.907, | |
| "eval_runtime": 19.2711, | |
| "eval_samples_per_second": 103.782, | |
| "eval_steps_per_second": 3.269, | |
| "step": 937 | |
| }, | |
| { | |
| "epoch": 15.04, | |
| "learning_rate": 5.495818399044206e-05, | |
| "loss": 0.2906, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 15.2, | |
| "learning_rate": 5.436081242532856e-05, | |
| "loss": 0.292, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 15.36, | |
| "learning_rate": 5.3763440860215054e-05, | |
| "loss": 0.2618, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 15.52, | |
| "learning_rate": 5.316606929510155e-05, | |
| "loss": 0.2815, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 15.68, | |
| "learning_rate": 5.256869772998806e-05, | |
| "loss": 0.3114, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 15.84, | |
| "learning_rate": 5.1971326164874556e-05, | |
| "loss": 0.2861, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 5.137395459976105e-05, | |
| "loss": 0.268, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.9065, | |
| "eval_f1": 0.9063928167999953, | |
| "eval_loss": 0.22152148187160492, | |
| "eval_precision": 0.9082845248046524, | |
| "eval_recall": 0.9065, | |
| "eval_runtime": 18.8832, | |
| "eval_samples_per_second": 105.914, | |
| "eval_steps_per_second": 3.336, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 16.16, | |
| "learning_rate": 5.077658303464755e-05, | |
| "loss": 0.2379, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 16.32, | |
| "learning_rate": 5.017921146953405e-05, | |
| "loss": 0.2823, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 16.48, | |
| "learning_rate": 4.9581839904420555e-05, | |
| "loss": 0.2919, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 16.64, | |
| "learning_rate": 4.898446833930705e-05, | |
| "loss": 0.2843, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 16.8, | |
| "learning_rate": 4.8387096774193554e-05, | |
| "loss": 0.2796, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 16.96, | |
| "learning_rate": 4.778972520908005e-05, | |
| "loss": 0.2717, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "eval_accuracy": 0.907, | |
| "eval_f1": 0.9069572366368293, | |
| "eval_loss": 0.21916481852531433, | |
| "eval_precision": 0.907972609650692, | |
| "eval_recall": 0.907, | |
| "eval_runtime": 18.9283, | |
| "eval_samples_per_second": 105.662, | |
| "eval_steps_per_second": 3.328, | |
| "step": 1062 | |
| }, | |
| { | |
| "epoch": 17.12, | |
| "learning_rate": 4.7192353643966546e-05, | |
| "loss": 0.2706, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 17.28, | |
| "learning_rate": 4.659498207885305e-05, | |
| "loss": 0.2923, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 17.44, | |
| "learning_rate": 4.5997610513739546e-05, | |
| "loss": 0.2882, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 17.6, | |
| "learning_rate": 4.540023894862604e-05, | |
| "loss": 0.2956, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 17.76, | |
| "learning_rate": 4.4802867383512545e-05, | |
| "loss": 0.289, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 17.92, | |
| "learning_rate": 4.420549581839905e-05, | |
| "loss": 0.2706, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.907, | |
| "eval_f1": 0.9069565739130867, | |
| "eval_loss": 0.21854616701602936, | |
| "eval_precision": 0.9080263033747717, | |
| "eval_recall": 0.907, | |
| "eval_runtime": 18.3621, | |
| "eval_samples_per_second": 108.92, | |
| "eval_steps_per_second": 3.431, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 18.08, | |
| "learning_rate": 4.360812425328555e-05, | |
| "loss": 0.2743, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 18.24, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 0.2892, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 18.4, | |
| "learning_rate": 4.241338112305854e-05, | |
| "loss": 0.3034, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 18.56, | |
| "learning_rate": 4.1816009557945046e-05, | |
| "loss": 0.2713, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 18.72, | |
| "learning_rate": 4.121863799283154e-05, | |
| "loss": 0.2699, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 18.88, | |
| "learning_rate": 4.062126642771804e-05, | |
| "loss": 0.2697, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 18.99, | |
| "eval_accuracy": 0.907, | |
| "eval_f1": 0.9069581674905959, | |
| "eval_loss": 0.21837656199932098, | |
| "eval_precision": 0.90840630106049, | |
| "eval_recall": 0.907, | |
| "eval_runtime": 18.969, | |
| "eval_samples_per_second": 105.435, | |
| "eval_steps_per_second": 3.321, | |
| "step": 1187 | |
| }, | |
| { | |
| "epoch": 19.04, | |
| "learning_rate": 4.002389486260454e-05, | |
| "loss": 0.2889, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "learning_rate": 3.9426523297491045e-05, | |
| "loss": 0.2441, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 19.36, | |
| "learning_rate": 3.882915173237754e-05, | |
| "loss": 0.2823, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 19.52, | |
| "learning_rate": 3.8231780167264044e-05, | |
| "loss": 0.2606, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 19.68, | |
| "learning_rate": 3.763440860215054e-05, | |
| "loss": 0.2996, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 19.84, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.2746, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 3.643966547192354e-05, | |
| "loss": 0.2696, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.906, | |
| "eval_f1": 0.9059864486381697, | |
| "eval_loss": 0.21691195666790009, | |
| "eval_precision": 0.9070531266074939, | |
| "eval_recall": 0.906, | |
| "eval_runtime": 18.3046, | |
| "eval_samples_per_second": 109.262, | |
| "eval_steps_per_second": 3.442, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 20.16, | |
| "learning_rate": 3.5842293906810036e-05, | |
| "loss": 0.2717, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 20.32, | |
| "learning_rate": 3.524492234169653e-05, | |
| "loss": 0.2966, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 20.48, | |
| "learning_rate": 3.4647550776583035e-05, | |
| "loss": 0.2982, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 20.64, | |
| "learning_rate": 3.405017921146954e-05, | |
| "loss": 0.2789, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 20.8, | |
| "learning_rate": 3.3452807646356034e-05, | |
| "loss": 0.2793, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 20.96, | |
| "learning_rate": 3.285543608124254e-05, | |
| "loss": 0.2966, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 20.99, | |
| "eval_accuracy": 0.9055, | |
| "eval_f1": 0.9055014318837107, | |
| "eval_loss": 0.2157575637102127, | |
| "eval_precision": 0.9063500314516164, | |
| "eval_recall": 0.9055, | |
| "eval_runtime": 18.3823, | |
| "eval_samples_per_second": 108.8, | |
| "eval_steps_per_second": 3.427, | |
| "step": 1312 | |
| }, | |
| { | |
| "epoch": 21.12, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 0.2692, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 21.28, | |
| "learning_rate": 3.1660692951015537e-05, | |
| "loss": 0.2314, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 21.44, | |
| "learning_rate": 3.106332138590203e-05, | |
| "loss": 0.2936, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 21.6, | |
| "learning_rate": 3.046594982078853e-05, | |
| "loss": 0.2725, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 21.76, | |
| "learning_rate": 2.9868578255675032e-05, | |
| "loss": 0.2703, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 21.92, | |
| "learning_rate": 2.9271206690561532e-05, | |
| "loss": 0.273, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.9065, | |
| "eval_f1": 0.9064231860364218, | |
| "eval_loss": 0.21748855710029602, | |
| "eval_precision": 0.9079390386760382, | |
| "eval_recall": 0.9065, | |
| "eval_runtime": 18.4017, | |
| "eval_samples_per_second": 108.686, | |
| "eval_steps_per_second": 3.424, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 22.08, | |
| "learning_rate": 2.8673835125448028e-05, | |
| "loss": 0.2421, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 22.24, | |
| "learning_rate": 2.807646356033453e-05, | |
| "loss": 0.2628, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 22.4, | |
| "learning_rate": 2.747909199522103e-05, | |
| "loss": 0.2678, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 22.56, | |
| "learning_rate": 2.6881720430107527e-05, | |
| "loss": 0.2551, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 22.72, | |
| "learning_rate": 2.628434886499403e-05, | |
| "loss": 0.2921, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 22.88, | |
| "learning_rate": 2.5686977299880526e-05, | |
| "loss": 0.259, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 22.99, | |
| "eval_accuracy": 0.904, | |
| "eval_f1": 0.9039336951682637, | |
| "eval_loss": 0.21833094954490662, | |
| "eval_precision": 0.9058751252122637, | |
| "eval_recall": 0.904, | |
| "eval_runtime": 18.5157, | |
| "eval_samples_per_second": 108.017, | |
| "eval_steps_per_second": 3.403, | |
| "step": 1437 | |
| }, | |
| { | |
| "epoch": 23.04, | |
| "learning_rate": 2.5089605734767026e-05, | |
| "loss": 0.2823, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 23.2, | |
| "learning_rate": 2.4492234169653525e-05, | |
| "loss": 0.2376, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 23.36, | |
| "learning_rate": 2.3894862604540025e-05, | |
| "loss": 0.287, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 23.52, | |
| "learning_rate": 2.3297491039426525e-05, | |
| "loss": 0.2618, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 23.68, | |
| "learning_rate": 2.270011947431302e-05, | |
| "loss": 0.2689, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 23.84, | |
| "learning_rate": 2.2102747909199524e-05, | |
| "loss": 0.2627, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 0.2711, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.906, | |
| "eval_f1": 0.9059718122109574, | |
| "eval_loss": 0.21671248972415924, | |
| "eval_precision": 0.9074141081421832, | |
| "eval_recall": 0.906, | |
| "eval_runtime": 18.9604, | |
| "eval_samples_per_second": 105.483, | |
| "eval_steps_per_second": 3.323, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 24.16, | |
| "learning_rate": 2.0908004778972523e-05, | |
| "loss": 0.2748, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 24.32, | |
| "learning_rate": 2.031063321385902e-05, | |
| "loss": 0.2436, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 24.48, | |
| "learning_rate": 1.9713261648745522e-05, | |
| "loss": 0.2572, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 24.64, | |
| "learning_rate": 1.9115890083632022e-05, | |
| "loss": 0.2814, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 24.8, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.2722, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 24.96, | |
| "learning_rate": 1.7921146953405018e-05, | |
| "loss": 0.2704, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 24.99, | |
| "eval_accuracy": 0.9065, | |
| "eval_f1": 0.9064215569103755, | |
| "eval_loss": 0.2160024344921112, | |
| "eval_precision": 0.9080799318498731, | |
| "eval_recall": 0.9065, | |
| "eval_runtime": 18.2855, | |
| "eval_samples_per_second": 109.377, | |
| "eval_steps_per_second": 3.445, | |
| "step": 1562 | |
| }, | |
| { | |
| "epoch": 25.12, | |
| "learning_rate": 1.7323775388291518e-05, | |
| "loss": 0.2756, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 25.28, | |
| "learning_rate": 1.6726403823178017e-05, | |
| "loss": 0.2552, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 25.44, | |
| "learning_rate": 1.6129032258064517e-05, | |
| "loss": 0.2855, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 25.6, | |
| "learning_rate": 1.5531660692951016e-05, | |
| "loss": 0.2931, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 25.76, | |
| "learning_rate": 1.4934289127837516e-05, | |
| "loss": 0.2775, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 25.92, | |
| "learning_rate": 1.4336917562724014e-05, | |
| "loss": 0.2233, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.9085, | |
| "eval_f1": 0.9085090936756758, | |
| "eval_loss": 0.21386541426181793, | |
| "eval_precision": 0.9092156514932994, | |
| "eval_recall": 0.9085, | |
| "eval_runtime": 18.8701, | |
| "eval_samples_per_second": 105.988, | |
| "eval_steps_per_second": 3.339, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 26.08, | |
| "learning_rate": 1.3739545997610515e-05, | |
| "loss": 0.2662, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 26.24, | |
| "learning_rate": 1.3142174432497015e-05, | |
| "loss": 0.2616, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 26.4, | |
| "learning_rate": 1.2544802867383513e-05, | |
| "loss": 0.2634, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 26.56, | |
| "learning_rate": 1.1947431302270013e-05, | |
| "loss": 0.3007, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 26.72, | |
| "learning_rate": 1.135005973715651e-05, | |
| "loss": 0.2642, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 26.88, | |
| "learning_rate": 1.0752688172043012e-05, | |
| "loss": 0.2759, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 26.99, | |
| "eval_accuracy": 0.907, | |
| "eval_f1": 0.9070126266344571, | |
| "eval_loss": 0.21516349911689758, | |
| "eval_precision": 0.9083904204635809, | |
| "eval_recall": 0.907, | |
| "eval_runtime": 18.8999, | |
| "eval_samples_per_second": 105.821, | |
| "eval_steps_per_second": 3.333, | |
| "step": 1687 | |
| }, | |
| { | |
| "epoch": 27.04, | |
| "learning_rate": 1.015531660692951e-05, | |
| "loss": 0.2562, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 27.2, | |
| "learning_rate": 9.557945041816011e-06, | |
| "loss": 0.2692, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 27.36, | |
| "learning_rate": 8.960573476702509e-06, | |
| "loss": 0.2526, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 27.52, | |
| "learning_rate": 8.363201911589009e-06, | |
| "loss": 0.2431, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 27.68, | |
| "learning_rate": 7.765830346475508e-06, | |
| "loss": 0.2941, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 27.84, | |
| "learning_rate": 7.168458781362007e-06, | |
| "loss": 0.2849, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 6.5710872162485075e-06, | |
| "loss": 0.2667, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.907, | |
| "eval_f1": 0.9070053397639775, | |
| "eval_loss": 0.21557794511318207, | |
| "eval_precision": 0.9085165088141129, | |
| "eval_recall": 0.907, | |
| "eval_runtime": 18.4096, | |
| "eval_samples_per_second": 108.639, | |
| "eval_steps_per_second": 3.422, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 28.16, | |
| "learning_rate": 5.973715651135006e-06, | |
| "loss": 0.2594, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 28.32, | |
| "learning_rate": 5.376344086021506e-06, | |
| "loss": 0.2958, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 28.48, | |
| "learning_rate": 4.7789725209080055e-06, | |
| "loss": 0.2934, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 28.64, | |
| "learning_rate": 4.181600955794504e-06, | |
| "loss": 0.2724, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 28.8, | |
| "learning_rate": 3.5842293906810035e-06, | |
| "loss": 0.2569, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 28.96, | |
| "learning_rate": 2.986857825567503e-06, | |
| "loss": 0.2663, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 28.99, | |
| "eval_accuracy": 0.907, | |
| "eval_f1": 0.9070053397639775, | |
| "eval_loss": 0.21561561524868011, | |
| "eval_precision": 0.9085165088141129, | |
| "eval_recall": 0.907, | |
| "eval_runtime": 18.3181, | |
| "eval_samples_per_second": 109.182, | |
| "eval_steps_per_second": 3.439, | |
| "step": 1812 | |
| }, | |
| { | |
| "epoch": 29.12, | |
| "learning_rate": 2.3894862604540028e-06, | |
| "loss": 0.2891, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 29.28, | |
| "learning_rate": 1.7921146953405017e-06, | |
| "loss": 0.2629, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 29.44, | |
| "learning_rate": 1.1947431302270014e-06, | |
| "loss": 0.2745, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 29.6, | |
| "learning_rate": 5.973715651135007e-07, | |
| "loss": 0.274, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "learning_rate": 0.0, | |
| "loss": 0.2645, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "eval_accuracy": 0.907, | |
| "eval_f1": 0.9070053397639775, | |
| "eval_loss": 0.21537359058856964, | |
| "eval_precision": 0.9085165088141129, | |
| "eval_recall": 0.907, | |
| "eval_runtime": 18.2926, | |
| "eval_samples_per_second": 109.334, | |
| "eval_steps_per_second": 3.444, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "step": 1860, | |
| "total_flos": 2.4317906065576428e+19, | |
| "train_loss": 0.34036189715067544, | |
| "train_runtime": 3023.1847, | |
| "train_samples_per_second": 79.386, | |
| "train_steps_per_second": 0.615 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1860, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "total_flos": 2.4317906065576428e+19, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |