| { | |
| "best_metric": 0.6166583378418276, | |
| "best_model_checkpoint": "13E-affecthq-fer-balanced/checkpoint-1729", | |
| "epoch": 12.99625468164794, | |
| "global_step": 1729, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 5.780346820809249e-07, | |
| "loss": 1.9634, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.1560693641618499e-06, | |
| "loss": 1.9552, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.7341040462427746e-06, | |
| "loss": 1.96, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 2.3121387283236997e-06, | |
| "loss": 1.9515, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 2.890173410404625e-06, | |
| "loss": 1.9503, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 3.468208092485549e-06, | |
| "loss": 1.9404, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.046242774566474e-06, | |
| "loss": 1.9321, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.6242774566473994e-06, | |
| "loss": 1.92, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 5.202312138728324e-06, | |
| "loss": 1.9068, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 5.78034682080925e-06, | |
| "loss": 1.8931, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 6.358381502890174e-06, | |
| "loss": 1.8641, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 6.936416184971098e-06, | |
| "loss": 1.8289, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 7.5144508670520235e-06, | |
| "loss": 1.7863, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.40046838407494145, | |
| "eval_f1": 0.3058443007386033, | |
| "eval_loss": 1.7632062435150146, | |
| "eval_precision": 0.36173402622129774, | |
| "eval_recall": 0.40046838407494145, | |
| "eval_runtime": 67.8192, | |
| "eval_samples_per_second": 31.481, | |
| "eval_steps_per_second": 0.988, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 8.092485549132949e-06, | |
| "loss": 1.8586, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 8.670520231213873e-06, | |
| "loss": 1.7136, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 9.248554913294799e-06, | |
| "loss": 1.6728, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 9.826589595375723e-06, | |
| "loss": 1.6475, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 9.955012853470438e-06, | |
| "loss": 1.5912, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 9.890745501285348e-06, | |
| "loss": 1.545, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 9.826478149100258e-06, | |
| "loss": 1.5187, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 9.762210796915168e-06, | |
| "loss": 1.5123, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 9.697943444730078e-06, | |
| "loss": 1.4574, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 9.633676092544988e-06, | |
| "loss": 1.4483, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 9.569408740359899e-06, | |
| "loss": 1.4114, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 9.505141388174809e-06, | |
| "loss": 1.3853, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 9.440874035989717e-06, | |
| "loss": 1.3653, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5049180327868853, | |
| "eval_f1": 0.44452526643283874, | |
| "eval_loss": 1.3629579544067383, | |
| "eval_precision": 0.48383855087708, | |
| "eval_recall": 0.5049180327868853, | |
| "eval_runtime": 67.0004, | |
| "eval_samples_per_second": 31.865, | |
| "eval_steps_per_second": 1.0, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 9.376606683804627e-06, | |
| "loss": 1.44, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 9.312339331619537e-06, | |
| "loss": 1.3714, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 9.248071979434447e-06, | |
| "loss": 1.3243, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 9.183804627249359e-06, | |
| "loss": 1.3214, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 9.119537275064269e-06, | |
| "loss": 1.2917, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 9.055269922879179e-06, | |
| "loss": 1.3092, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 8.991002570694089e-06, | |
| "loss": 1.2699, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 8.926735218508999e-06, | |
| "loss": 1.2668, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 8.862467866323907e-06, | |
| "loss": 1.2747, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 8.798200514138818e-06, | |
| "loss": 1.2415, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 8.733933161953728e-06, | |
| "loss": 1.2671, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 8.669665809768638e-06, | |
| "loss": 1.2717, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 8.605398457583548e-06, | |
| "loss": 1.2468, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.5466042154566745, | |
| "eval_f1": 0.5114853306120848, | |
| "eval_loss": 1.2475332021713257, | |
| "eval_precision": 0.5451199399022204, | |
| "eval_recall": 0.5466042154566745, | |
| "eval_runtime": 66.2985, | |
| "eval_samples_per_second": 32.203, | |
| "eval_steps_per_second": 1.011, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 8.541131105398458e-06, | |
| "loss": 1.2806, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 8.476863753213368e-06, | |
| "loss": 1.2417, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 8.412596401028278e-06, | |
| "loss": 1.2221, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 8.348329048843188e-06, | |
| "loss": 1.1889, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 8.2840616966581e-06, | |
| "loss": 1.1994, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 8.219794344473008e-06, | |
| "loss": 1.196, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 8.155526992287918e-06, | |
| "loss": 1.1762, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 8.091259640102828e-06, | |
| "loss": 1.1714, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 8.026992287917738e-06, | |
| "loss": 1.1773, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 7.962724935732648e-06, | |
| "loss": 1.1672, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 7.898457583547558e-06, | |
| "loss": 1.1577, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 7.834190231362468e-06, | |
| "loss": 1.1438, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 7.769922879177378e-06, | |
| "loss": 1.1594, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 7.705655526992289e-06, | |
| "loss": 1.1527, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5761124121779859, | |
| "eval_f1": 0.5579541032814586, | |
| "eval_loss": 1.1865291595458984, | |
| "eval_precision": 0.561218961307198, | |
| "eval_recall": 0.5761124121779859, | |
| "eval_runtime": 65.9861, | |
| "eval_samples_per_second": 32.355, | |
| "eval_steps_per_second": 1.015, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 7.641388174807199e-06, | |
| "loss": 1.2137, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 7.577120822622109e-06, | |
| "loss": 1.1637, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 7.512853470437018e-06, | |
| "loss": 1.108, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 7.448586118251928e-06, | |
| "loss": 1.0764, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 7.384318766066839e-06, | |
| "loss": 1.1141, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 7.320051413881749e-06, | |
| "loss": 1.1119, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 7.255784061696659e-06, | |
| "loss": 1.0904, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 7.191516709511569e-06, | |
| "loss": 1.1055, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 7.127249357326479e-06, | |
| "loss": 1.1115, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 7.062982005141389e-06, | |
| "loss": 1.1029, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 6.998714652956299e-06, | |
| "loss": 1.1017, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 6.934447300771208e-06, | |
| "loss": 1.0723, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 6.870179948586118e-06, | |
| "loss": 1.0862, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.5784543325526932, | |
| "eval_f1": 0.5658700696765325, | |
| "eval_loss": 1.1448348760604858, | |
| "eval_precision": 0.5686897608132185, | |
| "eval_recall": 0.5784543325526932, | |
| "eval_runtime": 66.3078, | |
| "eval_samples_per_second": 32.198, | |
| "eval_steps_per_second": 1.01, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 6.8059125964010285e-06, | |
| "loss": 1.1261, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 6.7416452442159385e-06, | |
| "loss": 1.0695, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 5.19, | |
| "learning_rate": 6.677377892030849e-06, | |
| "loss": 1.0273, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "learning_rate": 6.613110539845759e-06, | |
| "loss": 1.0905, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "learning_rate": 6.548843187660669e-06, | |
| "loss": 1.0512, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "learning_rate": 6.48457583547558e-06, | |
| "loss": 1.0329, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "learning_rate": 6.42030848329049e-06, | |
| "loss": 1.0337, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "learning_rate": 6.3560411311054e-06, | |
| "loss": 1.0676, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "learning_rate": 6.291773778920309e-06, | |
| "loss": 1.0171, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 6.227506426735219e-06, | |
| "loss": 1.0644, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 6.163239074550129e-06, | |
| "loss": 1.048, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 6.098971722365039e-06, | |
| "loss": 1.0129, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 5.94, | |
| "learning_rate": 6.034704370179949e-06, | |
| "loss": 1.064, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5971896955503513, | |
| "eval_f1": 0.5853025369018718, | |
| "eval_loss": 1.1107723712921143, | |
| "eval_precision": 0.5866546554640366, | |
| "eval_recall": 0.5971896955503513, | |
| "eval_runtime": 66.5889, | |
| "eval_samples_per_second": 32.062, | |
| "eval_steps_per_second": 1.006, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 5.970437017994859e-06, | |
| "loss": 1.0766, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "learning_rate": 5.906169665809769e-06, | |
| "loss": 1.0108, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "learning_rate": 5.8419023136246785e-06, | |
| "loss": 1.0335, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 5.7776349614395885e-06, | |
| "loss": 1.007, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 6.31, | |
| "learning_rate": 5.713367609254499e-06, | |
| "loss": 1.0071, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "learning_rate": 5.649100257069409e-06, | |
| "loss": 1.0096, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "learning_rate": 5.5848329048843196e-06, | |
| "loss": 0.9766, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 6.54, | |
| "learning_rate": 5.52056555269923e-06, | |
| "loss": 0.9753, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 6.61, | |
| "learning_rate": 5.45629820051414e-06, | |
| "loss": 0.9808, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 6.69, | |
| "learning_rate": 5.39203084832905e-06, | |
| "loss": 1.0024, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 5.32776349614396e-06, | |
| "loss": 0.9615, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 6.84, | |
| "learning_rate": 5.26349614395887e-06, | |
| "loss": 0.9698, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "learning_rate": 5.199228791773779e-06, | |
| "loss": 1.0006, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 5.134961439588689e-06, | |
| "loss": 1.0037, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.6018735362997658, | |
| "eval_f1": 0.5945820873638747, | |
| "eval_loss": 1.0968866348266602, | |
| "eval_precision": 0.5968403329145666, | |
| "eval_recall": 0.6018735362997658, | |
| "eval_runtime": 65.51, | |
| "eval_samples_per_second": 32.59, | |
| "eval_steps_per_second": 1.023, | |
| "step": 931 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "learning_rate": 5.070694087403599e-06, | |
| "loss": 0.9839, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 5.006426735218509e-06, | |
| "loss": 0.9645, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "learning_rate": 4.942159383033419e-06, | |
| "loss": 0.9692, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 7.29, | |
| "learning_rate": 4.877892030848329e-06, | |
| "loss": 0.9593, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 4.813624678663239e-06, | |
| "loss": 1.0119, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "learning_rate": 4.7493573264781495e-06, | |
| "loss": 0.9453, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "learning_rate": 4.6850899742930595e-06, | |
| "loss": 0.933, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 7.59, | |
| "learning_rate": 4.62082262210797e-06, | |
| "loss": 0.9249, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "learning_rate": 4.55655526992288e-06, | |
| "loss": 0.9538, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 4.49228791773779e-06, | |
| "loss": 0.9535, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 7.82, | |
| "learning_rate": 4.4280205655527e-06, | |
| "loss": 0.9383, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 7.89, | |
| "learning_rate": 4.36375321336761e-06, | |
| "loss": 0.9449, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 7.97, | |
| "learning_rate": 4.29948586118252e-06, | |
| "loss": 0.9533, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.6126463700234192, | |
| "eval_f1": 0.6046320973113557, | |
| "eval_loss": 1.0763905048370361, | |
| "eval_precision": 0.6033502517484726, | |
| "eval_recall": 0.6126463700234192, | |
| "eval_runtime": 66.8256, | |
| "eval_samples_per_second": 31.949, | |
| "eval_steps_per_second": 1.003, | |
| "step": 1064 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "learning_rate": 4.23521850899743e-06, | |
| "loss": 0.9792, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 4.170951156812339e-06, | |
| "loss": 0.9325, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "learning_rate": 4.106683804627249e-06, | |
| "loss": 0.9394, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 8.27, | |
| "learning_rate": 4.04241645244216e-06, | |
| "loss": 0.8888, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 8.34, | |
| "learning_rate": 3.97814910025707e-06, | |
| "loss": 0.9058, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 8.42, | |
| "learning_rate": 3.91388174807198e-06, | |
| "loss": 0.9316, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "learning_rate": 3.849614395886889e-06, | |
| "loss": 0.9179, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 3.7853470437018e-06, | |
| "loss": 0.885, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 3.7210796915167095e-06, | |
| "loss": 0.933, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 8.72, | |
| "learning_rate": 3.6568123393316196e-06, | |
| "loss": 0.9388, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "learning_rate": 3.59254498714653e-06, | |
| "loss": 0.9112, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 8.87, | |
| "learning_rate": 3.52827763496144e-06, | |
| "loss": 0.9207, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 8.94, | |
| "learning_rate": 3.46401028277635e-06, | |
| "loss": 0.9063, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.615456674473068, | |
| "eval_f1": 0.6046961104183071, | |
| "eval_loss": 1.071085810661316, | |
| "eval_precision": 0.6035147338471722, | |
| "eval_recall": 0.615456674473068, | |
| "eval_runtime": 66.7376, | |
| "eval_samples_per_second": 31.991, | |
| "eval_steps_per_second": 1.004, | |
| "step": 1197 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 3.39974293059126e-06, | |
| "loss": 0.9774, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "learning_rate": 3.33547557840617e-06, | |
| "loss": 0.8738, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 9.17, | |
| "learning_rate": 3.27120822622108e-06, | |
| "loss": 0.8628, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 3.2069408740359896e-06, | |
| "loss": 0.8989, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "learning_rate": 3.1426735218509e-06, | |
| "loss": 0.8994, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "learning_rate": 3.07840616966581e-06, | |
| "loss": 0.8749, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 3.01413881748072e-06, | |
| "loss": 0.8741, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 9.55, | |
| "learning_rate": 2.9498714652956302e-06, | |
| "loss": 0.8934, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 2.88560411311054e-06, | |
| "loss": 0.8906, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "learning_rate": 2.82133676092545e-06, | |
| "loss": 0.9228, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 9.77, | |
| "learning_rate": 2.75706940874036e-06, | |
| "loss": 0.867, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 9.85, | |
| "learning_rate": 2.6928020565552705e-06, | |
| "loss": 0.9146, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 2.6285347043701805e-06, | |
| "loss": 0.9205, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 2.56426735218509e-06, | |
| "loss": 0.8666, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.6173302107728337, | |
| "eval_f1": 0.61075488056197, | |
| "eval_loss": 1.0589306354522705, | |
| "eval_precision": 0.6106645901461774, | |
| "eval_recall": 0.6173302107728337, | |
| "eval_runtime": 66.4667, | |
| "eval_samples_per_second": 32.121, | |
| "eval_steps_per_second": 1.008, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 10.07, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.8981, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 10.15, | |
| "learning_rate": 2.4357326478149103e-06, | |
| "loss": 0.8835, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 10.22, | |
| "learning_rate": 2.3714652956298203e-06, | |
| "loss": 0.8641, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 10.3, | |
| "learning_rate": 2.3071979434447304e-06, | |
| "loss": 0.8887, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 10.37, | |
| "learning_rate": 2.2429305912596404e-06, | |
| "loss": 0.878, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 10.45, | |
| "learning_rate": 2.17866323907455e-06, | |
| "loss": 0.8524, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 10.52, | |
| "learning_rate": 2.1143958868894605e-06, | |
| "loss": 0.8656, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 10.6, | |
| "learning_rate": 2.05012853470437e-06, | |
| "loss": 0.8966, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 10.67, | |
| "learning_rate": 1.9858611825192802e-06, | |
| "loss": 0.8858, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 10.75, | |
| "learning_rate": 1.9215938303341903e-06, | |
| "loss": 0.8647, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 10.82, | |
| "learning_rate": 1.8573264781491004e-06, | |
| "loss": 0.8278, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 10.9, | |
| "learning_rate": 1.7930591259640104e-06, | |
| "loss": 0.8571, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 10.97, | |
| "learning_rate": 1.7287917737789203e-06, | |
| "loss": 0.8364, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.6177985948477752, | |
| "eval_f1": 0.6108344054636982, | |
| "eval_loss": 1.0555986166000366, | |
| "eval_precision": 0.6110212240412639, | |
| "eval_recall": 0.6177985948477752, | |
| "eval_runtime": 66.1391, | |
| "eval_samples_per_second": 32.28, | |
| "eval_steps_per_second": 1.013, | |
| "step": 1463 | |
| }, | |
| { | |
| "epoch": 11.05, | |
| "learning_rate": 1.6645244215938305e-06, | |
| "loss": 0.8808, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 11.13, | |
| "learning_rate": 1.6002570694087406e-06, | |
| "loss": 0.8383, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 1.5359897172236504e-06, | |
| "loss": 0.863, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 11.28, | |
| "learning_rate": 1.4717223650385607e-06, | |
| "loss": 0.8312, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 11.35, | |
| "learning_rate": 1.4074550128534705e-06, | |
| "loss": 0.8933, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 11.43, | |
| "learning_rate": 1.3431876606683806e-06, | |
| "loss": 0.8563, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 11.5, | |
| "learning_rate": 1.2789203084832904e-06, | |
| "loss": 0.8588, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 11.58, | |
| "learning_rate": 1.2146529562982007e-06, | |
| "loss": 0.8611, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 11.65, | |
| "learning_rate": 1.1503856041131106e-06, | |
| "loss": 0.8356, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 11.73, | |
| "learning_rate": 1.0861182519280206e-06, | |
| "loss": 0.8371, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 11.8, | |
| "learning_rate": 1.0218508997429307e-06, | |
| "loss": 0.8177, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 11.88, | |
| "learning_rate": 9.575835475578407e-07, | |
| "loss": 0.8477, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 11.95, | |
| "learning_rate": 8.933161953727507e-07, | |
| "loss": 0.8659, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.6196721311475409, | |
| "eval_f1": 0.6150725729241909, | |
| "eval_loss": 1.0520738363265991, | |
| "eval_precision": 0.6140597586468644, | |
| "eval_recall": 0.6196721311475409, | |
| "eval_runtime": 66.4481, | |
| "eval_samples_per_second": 32.13, | |
| "eval_steps_per_second": 1.008, | |
| "step": 1596 | |
| }, | |
| { | |
| "epoch": 12.03, | |
| "learning_rate": 8.290488431876607e-07, | |
| "loss": 0.9068, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 12.1, | |
| "learning_rate": 7.647814910025708e-07, | |
| "loss": 0.8314, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 12.18, | |
| "learning_rate": 7.005141388174808e-07, | |
| "loss": 0.8761, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 12.25, | |
| "learning_rate": 6.362467866323908e-07, | |
| "loss": 0.8346, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 12.33, | |
| "learning_rate": 5.719794344473009e-07, | |
| "loss": 0.8345, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 12.4, | |
| "learning_rate": 5.077120822622108e-07, | |
| "loss": 0.8641, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "learning_rate": 4.434447300771209e-07, | |
| "loss": 0.8213, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 12.55, | |
| "learning_rate": 3.791773778920309e-07, | |
| "loss": 0.8584, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 12.63, | |
| "learning_rate": 3.149100257069409e-07, | |
| "loss": 0.8402, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 12.7, | |
| "learning_rate": 2.5064267352185095e-07, | |
| "loss": 0.8239, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 12.78, | |
| "learning_rate": 1.8637532133676095e-07, | |
| "loss": 0.7957, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 12.85, | |
| "learning_rate": 1.2210796915167095e-07, | |
| "loss": 0.8504, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 12.93, | |
| "learning_rate": 5.784061696658098e-08, | |
| "loss": 0.8383, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.6224824355971897, | |
| "eval_f1": 0.6166583378418276, | |
| "eval_loss": 1.0525678396224976, | |
| "eval_precision": 0.6161446612041342, | |
| "eval_recall": 0.6224824355971897, | |
| "eval_runtime": 65.747, | |
| "eval_samples_per_second": 32.473, | |
| "eval_steps_per_second": 1.019, | |
| "step": 1729 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "step": 1729, | |
| "total_flos": 1.7197173028930535e+19, | |
| "train_loss": 1.109088444861461, | |
| "train_runtime": 12754.1331, | |
| "train_samples_per_second": 17.403, | |
| "train_steps_per_second": 0.136 | |
| } | |
| ], | |
| "max_steps": 1729, | |
| "num_train_epochs": 13, | |
| "total_flos": 1.7197173028930535e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |