| { | |
| "best_metric": 0.855129650507328, | |
| "best_model_checkpoint": "vit-large-patch16-224-finetuned-galaxy10-decals/checkpoint-906", | |
| "epoch": 29.76, | |
| "eval_steps": 500, | |
| "global_step": 930, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.0752688172043012e-05, | |
| "loss": 2.2239, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 1.609, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 1.0358, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.7361894024802705, | |
| "eval_f1": 0.7266397888949025, | |
| "eval_loss": 0.7598127126693726, | |
| "eval_precision": 0.7424926838922145, | |
| "eval_recall": 0.7361894024802705, | |
| "eval_runtime": 17.3826, | |
| "eval_samples_per_second": 102.056, | |
| "eval_steps_per_second": 0.805, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 0.8138, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 5.3763440860215054e-05, | |
| "loss": 0.7072, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 6.451612903225807e-05, | |
| "loss": 0.6822, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "eval_accuracy": 0.7919954904171365, | |
| "eval_f1": 0.7898931758849426, | |
| "eval_loss": 0.6136134266853333, | |
| "eval_precision": 0.7971665728434488, | |
| "eval_recall": 0.7919954904171365, | |
| "eval_runtime": 17.1163, | |
| "eval_samples_per_second": 103.644, | |
| "eval_steps_per_second": 0.818, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 7.526881720430108e-05, | |
| "loss": 0.6682, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 8.60215053763441e-05, | |
| "loss": 0.6424, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 9.677419354838711e-05, | |
| "loss": 0.6535, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_accuracy": 0.8105975197294251, | |
| "eval_f1": 0.8061910960708782, | |
| "eval_loss": 0.5416004061698914, | |
| "eval_precision": 0.8140360122948396, | |
| "eval_recall": 0.8105975197294251, | |
| "eval_runtime": 17.566, | |
| "eval_samples_per_second": 100.99, | |
| "eval_steps_per_second": 0.797, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 9.916367980884111e-05, | |
| "loss": 0.6169, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 9.79689366786141e-05, | |
| "loss": 0.6022, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 9.677419354838711e-05, | |
| "loss": 0.5696, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8162344983089064, | |
| "eval_f1": 0.8139861710754493, | |
| "eval_loss": 0.5304952263832092, | |
| "eval_precision": 0.8195322178917354, | |
| "eval_recall": 0.8162344983089064, | |
| "eval_runtime": 17.3334, | |
| "eval_samples_per_second": 102.346, | |
| "eval_steps_per_second": 0.808, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 9.55794504181601e-05, | |
| "loss": 0.5455, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 9.438470728793309e-05, | |
| "loss": 0.5421, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 9.31899641577061e-05, | |
| "loss": 0.5435, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.814543404735062, | |
| "eval_f1": 0.8161156144737257, | |
| "eval_loss": 0.5555492043495178, | |
| "eval_precision": 0.8241810477987659, | |
| "eval_recall": 0.814543404735062, | |
| "eval_runtime": 17.1642, | |
| "eval_samples_per_second": 103.354, | |
| "eval_steps_per_second": 0.816, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 9.199522102747909e-05, | |
| "loss": 0.5186, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 9.080047789725208e-05, | |
| "loss": 0.5074, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "learning_rate": 8.960573476702509e-05, | |
| "loss": 0.4621, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 5.98, | |
| "eval_accuracy": 0.8297632468996617, | |
| "eval_f1": 0.8254361806374156, | |
| "eval_loss": 0.5074881315231323, | |
| "eval_precision": 0.8343689618318259, | |
| "eval_recall": 0.8297632468996617, | |
| "eval_runtime": 17.1936, | |
| "eval_samples_per_second": 103.178, | |
| "eval_steps_per_second": 0.814, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 8.84109916367981e-05, | |
| "loss": 0.4713, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 8.72162485065711e-05, | |
| "loss": 0.4516, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 8.60215053763441e-05, | |
| "loss": 0.4479, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 6.98, | |
| "eval_accuracy": 0.8280721533258174, | |
| "eval_f1": 0.8268976469809478, | |
| "eval_loss": 0.5117892622947693, | |
| "eval_precision": 0.8290711099056762, | |
| "eval_recall": 0.8280721533258174, | |
| "eval_runtime": 17.1887, | |
| "eval_samples_per_second": 103.207, | |
| "eval_steps_per_second": 0.814, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 8.482676224611709e-05, | |
| "loss": 0.4864, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 8.363201911589009e-05, | |
| "loss": 0.4469, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 8.243727598566309e-05, | |
| "loss": 0.4427, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 8.124253285543608e-05, | |
| "loss": 0.4318, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8196166854565953, | |
| "eval_f1": 0.8165810295817906, | |
| "eval_loss": 0.5163812041282654, | |
| "eval_precision": 0.8254762320844335, | |
| "eval_recall": 0.8196166854565953, | |
| "eval_runtime": 17.2603, | |
| "eval_samples_per_second": 102.779, | |
| "eval_steps_per_second": 0.811, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 8.004778972520908e-05, | |
| "loss": 0.3936, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 7.885304659498209e-05, | |
| "loss": 0.4184, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 7.765830346475508e-05, | |
| "loss": 0.4011, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_accuracy": 0.8410372040586246, | |
| "eval_f1": 0.8361869699508147, | |
| "eval_loss": 0.5086681246757507, | |
| "eval_precision": 0.8369303660828149, | |
| "eval_recall": 0.8410372040586246, | |
| "eval_runtime": 17.2372, | |
| "eval_samples_per_second": 102.917, | |
| "eval_steps_per_second": 0.812, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 7.646356033452809e-05, | |
| "loss": 0.3623, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 7.526881720430108e-05, | |
| "loss": 0.3859, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 7.407407407407407e-05, | |
| "loss": 0.355, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 9.98, | |
| "eval_accuracy": 0.8410372040586246, | |
| "eval_f1": 0.8405397327667177, | |
| "eval_loss": 0.5063195824623108, | |
| "eval_precision": 0.8432750192889569, | |
| "eval_recall": 0.8410372040586246, | |
| "eval_runtime": 16.9471, | |
| "eval_samples_per_second": 104.678, | |
| "eval_steps_per_second": 0.826, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 10.24, | |
| "learning_rate": 7.287933094384708e-05, | |
| "loss": 0.3546, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 7.168458781362007e-05, | |
| "loss": 0.3651, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 10.88, | |
| "learning_rate": 7.048984468339306e-05, | |
| "loss": 0.3655, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 10.98, | |
| "eval_accuracy": 0.8325817361894025, | |
| "eval_f1": 0.8304645126548728, | |
| "eval_loss": 0.5418781042098999, | |
| "eval_precision": 0.8342869154143101, | |
| "eval_recall": 0.8325817361894025, | |
| "eval_runtime": 17.1542, | |
| "eval_samples_per_second": 103.415, | |
| "eval_steps_per_second": 0.816, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 6.929510155316607e-05, | |
| "loss": 0.321, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "learning_rate": 6.810035842293908e-05, | |
| "loss": 0.3149, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 11.84, | |
| "learning_rate": 6.690561529271207e-05, | |
| "loss": 0.3292, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.8438556933483653, | |
| "eval_f1": 0.8414694905603178, | |
| "eval_loss": 0.5134132504463196, | |
| "eval_precision": 0.8441999477281247, | |
| "eval_recall": 0.8438556933483653, | |
| "eval_runtime": 17.5078, | |
| "eval_samples_per_second": 101.326, | |
| "eval_steps_per_second": 0.8, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 12.16, | |
| "learning_rate": 6.571087216248507e-05, | |
| "loss": 0.307, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "learning_rate": 6.451612903225807e-05, | |
| "loss": 0.2954, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 6.332138590203107e-05, | |
| "loss": 0.3207, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "eval_accuracy": 0.818489289740699, | |
| "eval_f1": 0.8178062229123537, | |
| "eval_loss": 0.6284513473510742, | |
| "eval_precision": 0.8292555687045076, | |
| "eval_recall": 0.818489289740699, | |
| "eval_runtime": 17.3492, | |
| "eval_samples_per_second": 102.253, | |
| "eval_steps_per_second": 0.807, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "learning_rate": 6.212664277180407e-05, | |
| "loss": 0.3036, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "learning_rate": 6.093189964157706e-05, | |
| "loss": 0.2996, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 13.76, | |
| "learning_rate": 5.9737156511350064e-05, | |
| "loss": 0.2931, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 13.98, | |
| "eval_accuracy": 0.8382187147688839, | |
| "eval_f1": 0.8370541465865403, | |
| "eval_loss": 0.5627130270004272, | |
| "eval_precision": 0.839486824110364, | |
| "eval_recall": 0.8382187147688839, | |
| "eval_runtime": 17.3615, | |
| "eval_samples_per_second": 102.18, | |
| "eval_steps_per_second": 0.806, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "learning_rate": 5.8542413381123063e-05, | |
| "loss": 0.285, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 5.7347670250896056e-05, | |
| "loss": 0.2668, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 14.72, | |
| "learning_rate": 5.615292712066906e-05, | |
| "loss": 0.2817, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 14.98, | |
| "eval_accuracy": 0.8207440811724915, | |
| "eval_f1": 0.8215045979425666, | |
| "eval_loss": 0.6059415936470032, | |
| "eval_precision": 0.8277800413747494, | |
| "eval_recall": 0.8207440811724915, | |
| "eval_runtime": 17.4368, | |
| "eval_samples_per_second": 101.739, | |
| "eval_steps_per_second": 0.803, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 15.04, | |
| "learning_rate": 5.495818399044206e-05, | |
| "loss": 0.2788, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 15.36, | |
| "learning_rate": 5.3763440860215054e-05, | |
| "loss": 0.2477, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 15.68, | |
| "learning_rate": 5.256869772998806e-05, | |
| "loss": 0.2632, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 5.137395459976105e-05, | |
| "loss": 0.2713, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.8382187147688839, | |
| "eval_f1": 0.833707206410208, | |
| "eval_loss": 0.6140456795692444, | |
| "eval_precision": 0.8367410596472065, | |
| "eval_recall": 0.8382187147688839, | |
| "eval_runtime": 16.853, | |
| "eval_samples_per_second": 105.263, | |
| "eval_steps_per_second": 0.831, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 16.32, | |
| "learning_rate": 5.017921146953405e-05, | |
| "loss": 0.2436, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 16.64, | |
| "learning_rate": 4.898446833930705e-05, | |
| "loss": 0.2609, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 16.96, | |
| "learning_rate": 4.778972520908005e-05, | |
| "loss": 0.233, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "eval_accuracy": 0.8382187147688839, | |
| "eval_f1": 0.8374417130087097, | |
| "eval_loss": 0.5992226004600525, | |
| "eval_precision": 0.8384211210396012, | |
| "eval_recall": 0.8382187147688839, | |
| "eval_runtime": 17.2766, | |
| "eval_samples_per_second": 102.682, | |
| "eval_steps_per_second": 0.81, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 17.28, | |
| "learning_rate": 4.659498207885305e-05, | |
| "loss": 0.2495, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 17.6, | |
| "learning_rate": 4.540023894862604e-05, | |
| "loss": 0.2439, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 17.92, | |
| "learning_rate": 4.420549581839905e-05, | |
| "loss": 0.2313, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 17.98, | |
| "eval_accuracy": 0.8291995490417137, | |
| "eval_f1": 0.8277700567784572, | |
| "eval_loss": 0.6679310202598572, | |
| "eval_precision": 0.8343220081023114, | |
| "eval_recall": 0.8291995490417137, | |
| "eval_runtime": 17.1635, | |
| "eval_samples_per_second": 103.359, | |
| "eval_steps_per_second": 0.816, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 18.24, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 0.2372, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 18.56, | |
| "learning_rate": 4.1816009557945046e-05, | |
| "loss": 0.2221, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 18.88, | |
| "learning_rate": 4.062126642771804e-05, | |
| "loss": 0.223, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 18.98, | |
| "eval_accuracy": 0.8342728297632469, | |
| "eval_f1": 0.8347284925921231, | |
| "eval_loss": 0.650068461894989, | |
| "eval_precision": 0.83863912442667, | |
| "eval_recall": 0.8342728297632469, | |
| "eval_runtime": 17.3595, | |
| "eval_samples_per_second": 102.192, | |
| "eval_steps_per_second": 0.806, | |
| "step": 593 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "learning_rate": 3.9426523297491045e-05, | |
| "loss": 0.2233, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 19.52, | |
| "learning_rate": 3.8231780167264044e-05, | |
| "loss": 0.2252, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 19.84, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.2126, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.8342728297632469, | |
| "eval_f1": 0.8296208996152092, | |
| "eval_loss": 0.6730501651763916, | |
| "eval_precision": 0.8304365724870174, | |
| "eval_recall": 0.8342728297632469, | |
| "eval_runtime": 17.1049, | |
| "eval_samples_per_second": 103.713, | |
| "eval_steps_per_second": 0.818, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 20.16, | |
| "learning_rate": 3.5842293906810036e-05, | |
| "loss": 0.2106, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 20.48, | |
| "learning_rate": 3.4647550776583035e-05, | |
| "loss": 0.2086, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 20.8, | |
| "learning_rate": 3.3452807646356034e-05, | |
| "loss": 0.2078, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 20.99, | |
| "eval_accuracy": 0.8387824126268321, | |
| "eval_f1": 0.8383399204498011, | |
| "eval_loss": 0.6334655284881592, | |
| "eval_precision": 0.8409778004650714, | |
| "eval_recall": 0.8387824126268321, | |
| "eval_runtime": 16.9486, | |
| "eval_samples_per_second": 104.669, | |
| "eval_steps_per_second": 0.826, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 21.12, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 0.2071, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 21.44, | |
| "learning_rate": 3.106332138590203e-05, | |
| "loss": 0.2069, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 21.76, | |
| "learning_rate": 2.9868578255675032e-05, | |
| "loss": 0.201, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 21.98, | |
| "eval_accuracy": 0.850620067643743, | |
| "eval_f1": 0.8485040018671677, | |
| "eval_loss": 0.6119940876960754, | |
| "eval_precision": 0.84779749511018, | |
| "eval_recall": 0.850620067643743, | |
| "eval_runtime": 17.2379, | |
| "eval_samples_per_second": 102.913, | |
| "eval_steps_per_second": 0.812, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 22.08, | |
| "learning_rate": 2.8673835125448028e-05, | |
| "loss": 0.2058, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 22.4, | |
| "learning_rate": 2.747909199522103e-05, | |
| "loss": 0.1894, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 22.72, | |
| "learning_rate": 2.628434886499403e-05, | |
| "loss": 0.2045, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 22.98, | |
| "eval_accuracy": 0.8410372040586246, | |
| "eval_f1": 0.8370636059789568, | |
| "eval_loss": 0.6590279340744019, | |
| "eval_precision": 0.8389140338894852, | |
| "eval_recall": 0.8410372040586246, | |
| "eval_runtime": 17.4487, | |
| "eval_samples_per_second": 101.669, | |
| "eval_steps_per_second": 0.802, | |
| "step": 718 | |
| }, | |
| { | |
| "epoch": 23.04, | |
| "learning_rate": 2.5089605734767026e-05, | |
| "loss": 0.2042, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 23.36, | |
| "learning_rate": 2.3894862604540025e-05, | |
| "loss": 0.2018, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 23.68, | |
| "learning_rate": 2.270011947431302e-05, | |
| "loss": 0.201, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 0.1759, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.8489289740698985, | |
| "eval_f1": 0.8457283475787394, | |
| "eval_loss": 0.6477726697921753, | |
| "eval_precision": 0.8463914374344644, | |
| "eval_recall": 0.8489289740698985, | |
| "eval_runtime": 17.1928, | |
| "eval_samples_per_second": 103.183, | |
| "eval_steps_per_second": 0.814, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 24.32, | |
| "learning_rate": 2.031063321385902e-05, | |
| "loss": 0.2004, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 24.64, | |
| "learning_rate": 1.9115890083632022e-05, | |
| "loss": 0.1828, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 24.96, | |
| "learning_rate": 1.7921146953405018e-05, | |
| "loss": 0.1856, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 24.99, | |
| "eval_accuracy": 0.8444193912063134, | |
| "eval_f1": 0.8420114736469138, | |
| "eval_loss": 0.6604239344596863, | |
| "eval_precision": 0.8413499043245124, | |
| "eval_recall": 0.8444193912063134, | |
| "eval_runtime": 17.0578, | |
| "eval_samples_per_second": 103.999, | |
| "eval_steps_per_second": 0.821, | |
| "step": 781 | |
| }, | |
| { | |
| "epoch": 25.28, | |
| "learning_rate": 1.6726403823178017e-05, | |
| "loss": 0.1685, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 25.6, | |
| "learning_rate": 1.5531660692951016e-05, | |
| "loss": 0.1717, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 25.92, | |
| "learning_rate": 1.4336917562724014e-05, | |
| "loss": 0.1766, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 25.98, | |
| "eval_accuracy": 0.8500563697857948, | |
| "eval_f1": 0.8484278487289038, | |
| "eval_loss": 0.6922361850738525, | |
| "eval_precision": 0.8491261339823137, | |
| "eval_recall": 0.8500563697857948, | |
| "eval_runtime": 17.4796, | |
| "eval_samples_per_second": 101.49, | |
| "eval_steps_per_second": 0.801, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 26.24, | |
| "learning_rate": 1.3142174432497015e-05, | |
| "loss": 0.1839, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 26.56, | |
| "learning_rate": 1.1947431302270013e-05, | |
| "loss": 0.1758, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 26.88, | |
| "learning_rate": 1.0752688172043012e-05, | |
| "loss": 0.1841, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 26.98, | |
| "eval_accuracy": 0.8500563697857948, | |
| "eval_f1": 0.8485537434372422, | |
| "eval_loss": 0.6484794616699219, | |
| "eval_precision": 0.8493151913843657, | |
| "eval_recall": 0.8500563697857948, | |
| "eval_runtime": 17.1293, | |
| "eval_samples_per_second": 103.565, | |
| "eval_steps_per_second": 0.817, | |
| "step": 843 | |
| }, | |
| { | |
| "epoch": 27.2, | |
| "learning_rate": 9.557945041816011e-06, | |
| "loss": 0.1818, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 27.52, | |
| "learning_rate": 8.363201911589009e-06, | |
| "loss": 0.1798, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 27.84, | |
| "learning_rate": 7.168458781362007e-06, | |
| "loss": 0.1707, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.846674182638106, | |
| "eval_f1": 0.844633535513836, | |
| "eval_loss": 0.6392838954925537, | |
| "eval_precision": 0.8439910314731612, | |
| "eval_recall": 0.846674182638106, | |
| "eval_runtime": 17.3476, | |
| "eval_samples_per_second": 102.262, | |
| "eval_steps_per_second": 0.807, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 28.16, | |
| "learning_rate": 5.973715651135006e-06, | |
| "loss": 0.1883, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 28.48, | |
| "learning_rate": 4.7789725209080055e-06, | |
| "loss": 0.1712, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 28.8, | |
| "learning_rate": 3.5842293906810035e-06, | |
| "loss": 0.1792, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 28.99, | |
| "eval_accuracy": 0.855129650507328, | |
| "eval_f1": 0.8525596225280389, | |
| "eval_loss": 0.6403793692588806, | |
| "eval_precision": 0.8525018926508404, | |
| "eval_recall": 0.855129650507328, | |
| "eval_runtime": 17.1962, | |
| "eval_samples_per_second": 103.162, | |
| "eval_steps_per_second": 0.814, | |
| "step": 906 | |
| }, | |
| { | |
| "epoch": 29.12, | |
| "learning_rate": 2.3894862604540028e-06, | |
| "loss": 0.1795, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 29.44, | |
| "learning_rate": 1.1947431302270014e-06, | |
| "loss": 0.1619, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "learning_rate": 0.0, | |
| "loss": 0.1713, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "eval_accuracy": 0.8534385569334837, | |
| "eval_f1": 0.851097208124706, | |
| "eval_loss": 0.6397678256034851, | |
| "eval_precision": 0.8513110036968645, | |
| "eval_recall": 0.8534385569334837, | |
| "eval_runtime": 17.1103, | |
| "eval_samples_per_second": 103.68, | |
| "eval_steps_per_second": 0.818, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "step": 930, | |
| "total_flos": 1.3013814188701234e+20, | |
| "train_loss": 0.3639387649874533, | |
| "train_runtime": 9909.908, | |
| "train_samples_per_second": 48.321, | |
| "train_steps_per_second": 0.094 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 930, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "total_flos": 1.3013814188701234e+20, | |
| "train_batch_size": 128, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |