| { | |
| "best_metric": 0.9564356435643564, | |
| "best_model_checkpoint": "/content/drive/MyDrive/wav2vec2-base2_temp/checkpoint-22702", | |
| "epoch": 44.9990089197225, | |
| "global_step": 22702, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 5.869047619047619e-07, | |
| "loss": 1.7909, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.22574257425742575, | |
| "eval_f1": 0.08821474321649003, | |
| "eval_loss": 1.7777053117752075, | |
| "eval_precision": 0.11965788905676666, | |
| "eval_recall": 0.17184714795008912, | |
| "eval_runtime": 11.4913, | |
| "eval_samples_per_second": 43.946, | |
| "eval_steps_per_second": 11.052, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 1.1797619047619049e-06, | |
| "loss": 1.7457, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.3485148514851485, | |
| "eval_f1": 0.08614782183064122, | |
| "eval_loss": 1.6808362007141113, | |
| "eval_precision": 0.05808580858085808, | |
| "eval_recall": 0.16666666666666666, | |
| "eval_runtime": 9.5448, | |
| "eval_samples_per_second": 52.908, | |
| "eval_steps_per_second": 13.306, | |
| "step": 1009 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 1.775e-06, | |
| "loss": 1.6522, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.4277227722772277, | |
| "eval_f1": 0.2012091077291391, | |
| "eval_loss": 1.5670676231384277, | |
| "eval_precision": 0.21909966172261253, | |
| "eval_recall": 0.25960391732450555, | |
| "eval_runtime": 11.3538, | |
| "eval_samples_per_second": 44.479, | |
| "eval_steps_per_second": 11.186, | |
| "step": 1513 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 2.3702380952380955e-06, | |
| "loss": 1.5185, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5881188118811881, | |
| "eval_f1": 0.3725029550190217, | |
| "eval_loss": 1.3283705711364746, | |
| "eval_precision": 0.44973544973544977, | |
| "eval_recall": 0.42331231676819914, | |
| "eval_runtime": 10.0287, | |
| "eval_samples_per_second": 50.356, | |
| "eval_steps_per_second": 12.664, | |
| "step": 2018 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 2.9654761904761905e-06, | |
| "loss": 1.2985, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.6772277227722773, | |
| "eval_f1": 0.4729958594455382, | |
| "eval_loss": 1.0731083154678345, | |
| "eval_precision": 0.43875160660457085, | |
| "eval_recall": 0.528141923436041, | |
| "eval_runtime": 12.9008, | |
| "eval_samples_per_second": 39.145, | |
| "eval_steps_per_second": 9.844, | |
| "step": 2522 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "learning_rate": 3.5595238095238097e-06, | |
| "loss": 1.0891, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.6871287128712872, | |
| "eval_f1": 0.5190569356664213, | |
| "eval_loss": 0.9219310879707336, | |
| "eval_precision": 0.5714776497659865, | |
| "eval_recall": 0.5614828961887786, | |
| "eval_runtime": 11.3089, | |
| "eval_samples_per_second": 44.655, | |
| "eval_steps_per_second": 11.23, | |
| "step": 3027 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "learning_rate": 4.152380952380952e-06, | |
| "loss": 0.898, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.7623762376237624, | |
| "eval_f1": 0.6067418025396825, | |
| "eval_loss": 0.7551212906837463, | |
| "eval_precision": 0.6263669695520484, | |
| "eval_recall": 0.6273902894491129, | |
| "eval_runtime": 10.502, | |
| "eval_samples_per_second": 48.086, | |
| "eval_steps_per_second": 12.093, | |
| "step": 3531 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "learning_rate": 4.7476190476190475e-06, | |
| "loss": 0.7131, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8237623762376237, | |
| "eval_f1": 0.6820230695773629, | |
| "eval_loss": 0.5713428258895874, | |
| "eval_precision": 0.6794105204506714, | |
| "eval_recall": 0.7097026992615229, | |
| "eval_runtime": 11.2886, | |
| "eval_samples_per_second": 44.736, | |
| "eval_steps_per_second": 11.25, | |
| "step": 4036 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "learning_rate": 5.342857142857143e-06, | |
| "loss": 0.5432, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.8613861386138614, | |
| "eval_f1": 0.7306731549704363, | |
| "eval_loss": 0.4402145743370056, | |
| "eval_precision": 0.7078735307061095, | |
| "eval_recall": 0.7635915881504117, | |
| "eval_runtime": 10.2752, | |
| "eval_samples_per_second": 49.147, | |
| "eval_steps_per_second": 12.36, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 9.91, | |
| "learning_rate": 5.9380952380952385e-06, | |
| "loss": 0.4296, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.8534653465346534, | |
| "eval_f1": 0.7203056745493539, | |
| "eval_loss": 0.42783123254776, | |
| "eval_precision": 0.7042866897841077, | |
| "eval_recall": 0.7496972880061116, | |
| "eval_runtime": 10.0025, | |
| "eval_samples_per_second": 50.488, | |
| "eval_steps_per_second": 12.697, | |
| "step": 5045 | |
| }, | |
| { | |
| "epoch": 10.9, | |
| "learning_rate": 6.532142857142857e-06, | |
| "loss": 0.3869, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.8772277227722772, | |
| "eval_f1": 0.7461735637601347, | |
| "eval_loss": 0.3639691174030304, | |
| "eval_precision": 0.7306143706983171, | |
| "eval_recall": 0.7771949537390714, | |
| "eval_runtime": 12.5987, | |
| "eval_samples_per_second": 40.083, | |
| "eval_steps_per_second": 10.08, | |
| "step": 5549 | |
| }, | |
| { | |
| "epoch": 11.89, | |
| "learning_rate": 7.127380952380952e-06, | |
| "loss": 0.3606, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.8673267326732673, | |
| "eval_f1": 0.7317576200752773, | |
| "eval_loss": 0.4499942660331726, | |
| "eval_precision": 0.7133735090373348, | |
| "eval_recall": 0.7651407987437399, | |
| "eval_runtime": 10.9939, | |
| "eval_samples_per_second": 45.934, | |
| "eval_steps_per_second": 11.552, | |
| "step": 6054 | |
| }, | |
| { | |
| "epoch": 12.88, | |
| "learning_rate": 7.722619047619049e-06, | |
| "loss": 0.3626, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.8653465346534653, | |
| "eval_f1": 0.7374268578667081, | |
| "eval_loss": 0.460127055644989, | |
| "eval_precision": 0.7374934142677786, | |
| "eval_recall": 0.7631706773618538, | |
| "eval_runtime": 10.5614, | |
| "eval_samples_per_second": 47.816, | |
| "eval_steps_per_second": 12.025, | |
| "step": 6558 | |
| }, | |
| { | |
| "epoch": 13.88, | |
| "learning_rate": 8.317857142857142e-06, | |
| "loss": 0.3276, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.8732673267326733, | |
| "eval_f1": 0.7421428470955433, | |
| "eval_loss": 0.41789284348487854, | |
| "eval_precision": 0.7395445813585981, | |
| "eval_recall": 0.7673902894491129, | |
| "eval_runtime": 10.505, | |
| "eval_samples_per_second": 48.072, | |
| "eval_steps_per_second": 12.09, | |
| "step": 7063 | |
| }, | |
| { | |
| "epoch": 14.87, | |
| "learning_rate": 8.913095238095238e-06, | |
| "loss": 0.3327, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.8910891089108911, | |
| "eval_f1": 0.7616771274725501, | |
| "eval_loss": 0.3447856605052948, | |
| "eval_precision": 0.7497788374032539, | |
| "eval_recall": 0.7904575163398694, | |
| "eval_runtime": 10.1528, | |
| "eval_samples_per_second": 49.74, | |
| "eval_steps_per_second": 12.509, | |
| "step": 7567 | |
| }, | |
| { | |
| "epoch": 15.86, | |
| "learning_rate": 9.508333333333333e-06, | |
| "loss": 0.3043, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.8851485148514852, | |
| "eval_f1": 0.7518326259740746, | |
| "eval_loss": 0.3687730133533478, | |
| "eval_precision": 0.7422745662572229, | |
| "eval_recall": 0.7788982259570495, | |
| "eval_runtime": 11.1359, | |
| "eval_samples_per_second": 45.349, | |
| "eval_steps_per_second": 11.405, | |
| "step": 8072 | |
| }, | |
| { | |
| "epoch": 16.85, | |
| "learning_rate": 1.0103571428571429e-05, | |
| "loss": 0.3127, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.8891089108910891, | |
| "eval_f1": 0.7565562985281078, | |
| "eval_loss": 0.3414187431335449, | |
| "eval_precision": 0.7434316232942377, | |
| "eval_recall": 0.7861912189118071, | |
| "eval_runtime": 10.7404, | |
| "eval_samples_per_second": 47.019, | |
| "eval_steps_per_second": 11.824, | |
| "step": 8576 | |
| }, | |
| { | |
| "epoch": 17.84, | |
| "learning_rate": 1.0698809523809525e-05, | |
| "loss": 0.306, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.8792079207920792, | |
| "eval_f1": 0.7478424649155898, | |
| "eval_loss": 0.4159949719905853, | |
| "eval_precision": 0.7357367052282306, | |
| "eval_recall": 0.7744677871148459, | |
| "eval_runtime": 10.479, | |
| "eval_samples_per_second": 48.192, | |
| "eval_steps_per_second": 12.119, | |
| "step": 9081 | |
| }, | |
| { | |
| "epoch": 18.83, | |
| "learning_rate": 1.1294047619047618e-05, | |
| "loss": 0.2756, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.8495049504950495, | |
| "eval_f1": 0.7182407626265085, | |
| "eval_loss": 0.7052268981933594, | |
| "eval_precision": 0.7064460784313725, | |
| "eval_recall": 0.7463492063492062, | |
| "eval_runtime": 11.111, | |
| "eval_samples_per_second": 45.45, | |
| "eval_steps_per_second": 11.43, | |
| "step": 9585 | |
| }, | |
| { | |
| "epoch": 19.82, | |
| "learning_rate": 1.1888095238095239e-05, | |
| "loss": 0.3233, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.904950495049505, | |
| "eval_f1": 0.7712251064475479, | |
| "eval_loss": 0.2911510169506073, | |
| "eval_precision": 0.7413165742555666, | |
| "eval_recall": 0.8109531236737119, | |
| "eval_runtime": 10.6787, | |
| "eval_samples_per_second": 47.29, | |
| "eval_steps_per_second": 11.893, | |
| "step": 10090 | |
| }, | |
| { | |
| "epoch": 20.81, | |
| "learning_rate": 1.2483333333333333e-05, | |
| "loss": 0.2932, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.904950495049505, | |
| "eval_f1": 0.8543450476033496, | |
| "eval_loss": 0.42383888363838196, | |
| "eval_precision": 0.8654226983060155, | |
| "eval_recall": 0.853277359895007, | |
| "eval_runtime": 9.6742, | |
| "eval_samples_per_second": 52.201, | |
| "eval_steps_per_second": 13.128, | |
| "step": 10594 | |
| }, | |
| { | |
| "epoch": 21.8, | |
| "learning_rate": 1.307857142857143e-05, | |
| "loss": 0.2698, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.9128712871287129, | |
| "eval_f1": 0.8604450377673127, | |
| "eval_loss": 0.386119544506073, | |
| "eval_precision": 0.9000550023499306, | |
| "eval_recall": 0.8544778424190188, | |
| "eval_runtime": 11.5253, | |
| "eval_samples_per_second": 43.817, | |
| "eval_steps_per_second": 11.019, | |
| "step": 11099 | |
| }, | |
| { | |
| "epoch": 22.79, | |
| "learning_rate": 1.3673809523809524e-05, | |
| "loss": 0.2658, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.9366336633663367, | |
| "eval_f1": 0.9043163728295133, | |
| "eval_loss": 0.336636483669281, | |
| "eval_precision": 0.9078665759004835, | |
| "eval_recall": 0.9021482439129498, | |
| "eval_runtime": 11.333, | |
| "eval_samples_per_second": 44.56, | |
| "eval_steps_per_second": 11.206, | |
| "step": 11603 | |
| }, | |
| { | |
| "epoch": 23.79, | |
| "learning_rate": 1.426904761904762e-05, | |
| "loss": 0.2393, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.9188118811881189, | |
| "eval_f1": 0.8657850889640667, | |
| "eval_loss": 0.4375390410423279, | |
| "eval_precision": 0.8887849766332739, | |
| "eval_recall": 0.8638055735114559, | |
| "eval_runtime": 11.0648, | |
| "eval_samples_per_second": 45.64, | |
| "eval_steps_per_second": 11.478, | |
| "step": 12108 | |
| }, | |
| { | |
| "epoch": 24.78, | |
| "learning_rate": 1.4864285714285713e-05, | |
| "loss": 0.2401, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.9207920792079208, | |
| "eval_f1": 0.8888781151825805, | |
| "eval_loss": 0.4757852256298065, | |
| "eval_precision": 0.8961036612926598, | |
| "eval_recall": 0.8866903929403929, | |
| "eval_runtime": 10.4698, | |
| "eval_samples_per_second": 48.234, | |
| "eval_steps_per_second": 12.13, | |
| "step": 12612 | |
| }, | |
| { | |
| "epoch": 25.77, | |
| "learning_rate": 1.545952380952381e-05, | |
| "loss": 0.2041, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.9425742574257425, | |
| "eval_f1": 0.9155025903592865, | |
| "eval_loss": 0.3074367940425873, | |
| "eval_precision": 0.9170299642442648, | |
| "eval_recall": 0.9228144078144078, | |
| "eval_runtime": 10.5628, | |
| "eval_samples_per_second": 47.809, | |
| "eval_steps_per_second": 12.023, | |
| "step": 13117 | |
| }, | |
| { | |
| "epoch": 26.76, | |
| "learning_rate": 1.605357142857143e-05, | |
| "loss": 0.1845, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.9108910891089109, | |
| "eval_f1": 0.8599750617887297, | |
| "eval_loss": 0.4771750867366791, | |
| "eval_precision": 0.864481386177137, | |
| "eval_recall": 0.8576941032823386, | |
| "eval_runtime": 11.1655, | |
| "eval_samples_per_second": 45.229, | |
| "eval_steps_per_second": 11.374, | |
| "step": 13621 | |
| }, | |
| { | |
| "epoch": 27.75, | |
| "learning_rate": 1.6648809523809525e-05, | |
| "loss": 0.1743, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.9386138613861386, | |
| "eval_f1": 0.9057775638831363, | |
| "eval_loss": 0.37529292702674866, | |
| "eval_precision": 0.9140135491407343, | |
| "eval_recall": 0.9027411722264663, | |
| "eval_runtime": 9.6192, | |
| "eval_samples_per_second": 52.499, | |
| "eval_steps_per_second": 13.203, | |
| "step": 14126 | |
| }, | |
| { | |
| "epoch": 28.74, | |
| "learning_rate": 1.7244047619047617e-05, | |
| "loss": 0.1539, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.9247524752475248, | |
| "eval_f1": 0.8866243367627531, | |
| "eval_loss": 0.5404527187347412, | |
| "eval_precision": 0.9116518987029846, | |
| "eval_recall": 0.8748301616683968, | |
| "eval_runtime": 10.8581, | |
| "eval_samples_per_second": 46.509, | |
| "eval_steps_per_second": 11.696, | |
| "step": 14630 | |
| }, | |
| { | |
| "epoch": 29.73, | |
| "learning_rate": 1.7839285714285716e-05, | |
| "loss": 0.1646, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.9346534653465347, | |
| "eval_f1": 0.9015438899526216, | |
| "eval_loss": 0.43599411845207214, | |
| "eval_precision": 0.9116436291187194, | |
| "eval_recall": 0.8942752998635353, | |
| "eval_runtime": 9.916, | |
| "eval_samples_per_second": 50.928, | |
| "eval_steps_per_second": 12.808, | |
| "step": 15135 | |
| }, | |
| { | |
| "epoch": 30.72, | |
| "learning_rate": 1.843452380952381e-05, | |
| "loss": 0.183, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.9346534653465347, | |
| "eval_f1": 0.9052713311328079, | |
| "eval_loss": 0.4353509545326233, | |
| "eval_precision": 0.9100534785215237, | |
| "eval_recall": 0.9015345357257122, | |
| "eval_runtime": 9.7228, | |
| "eval_samples_per_second": 51.94, | |
| "eval_steps_per_second": 13.062, | |
| "step": 15639 | |
| }, | |
| { | |
| "epoch": 31.71, | |
| "learning_rate": 1.9028571428571427e-05, | |
| "loss": 0.1547, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.9306930693069307, | |
| "eval_f1": 0.8978119183659733, | |
| "eval_loss": 0.49971604347229004, | |
| "eval_precision": 0.9138477382798044, | |
| "eval_recall": 0.888716153127918, | |
| "eval_runtime": 10.4672, | |
| "eval_samples_per_second": 48.246, | |
| "eval_steps_per_second": 12.133, | |
| "step": 16144 | |
| }, | |
| { | |
| "epoch": 32.71, | |
| "learning_rate": 1.9623809523809523e-05, | |
| "loss": 0.1658, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.9089108910891089, | |
| "eval_f1": 0.8687334612012699, | |
| "eval_loss": 0.5864279270172119, | |
| "eval_precision": 0.8899122777729049, | |
| "eval_recall": 0.8847601091718739, | |
| "eval_runtime": 10.5773, | |
| "eval_samples_per_second": 47.744, | |
| "eval_steps_per_second": 12.007, | |
| "step": 16648 | |
| }, | |
| { | |
| "epoch": 33.7, | |
| "learning_rate": 2.0219047619047622e-05, | |
| "loss": 0.1333, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.9089108910891089, | |
| "eval_f1": 0.8674149596498353, | |
| "eval_loss": 0.6616652607917786, | |
| "eval_precision": 0.8953076547670352, | |
| "eval_recall": 0.8615549809667457, | |
| "eval_runtime": 9.287, | |
| "eval_samples_per_second": 54.377, | |
| "eval_steps_per_second": 13.675, | |
| "step": 17153 | |
| }, | |
| { | |
| "epoch": 34.69, | |
| "learning_rate": 2.0814285714285714e-05, | |
| "loss": 0.1606, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.9346534653465347, | |
| "eval_f1": 0.9065032718742226, | |
| "eval_loss": 0.4562079906463623, | |
| "eval_precision": 0.9101611693862718, | |
| "eval_recall": 0.922783189033189, | |
| "eval_runtime": 10.427, | |
| "eval_samples_per_second": 48.432, | |
| "eval_steps_per_second": 12.18, | |
| "step": 17657 | |
| }, | |
| { | |
| "epoch": 35.68, | |
| "learning_rate": 2.140952380952381e-05, | |
| "loss": 0.1562, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.9346534653465347, | |
| "eval_f1": 0.9056285926854001, | |
| "eval_loss": 0.5119304060935974, | |
| "eval_precision": 0.9221614278132352, | |
| "eval_recall": 0.8947665732959851, | |
| "eval_runtime": 10.7345, | |
| "eval_samples_per_second": 47.045, | |
| "eval_steps_per_second": 11.831, | |
| "step": 18162 | |
| }, | |
| { | |
| "epoch": 36.67, | |
| "learning_rate": 2.200357142857143e-05, | |
| "loss": 0.1238, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.9465346534653465, | |
| "eval_f1": 0.9233277365446494, | |
| "eval_loss": 0.37833738327026367, | |
| "eval_precision": 0.9264774557165861, | |
| "eval_recall": 0.9206345615169145, | |
| "eval_runtime": 10.6894, | |
| "eval_samples_per_second": 47.243, | |
| "eval_steps_per_second": 11.881, | |
| "step": 18666 | |
| }, | |
| { | |
| "epoch": 37.66, | |
| "learning_rate": 2.2598809523809527e-05, | |
| "loss": 0.133, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.9207920792079208, | |
| "eval_f1": 0.88282026816653, | |
| "eval_loss": 0.44697701930999756, | |
| "eval_precision": 0.8940768234014104, | |
| "eval_recall": 0.9017844573726927, | |
| "eval_runtime": 9.8397, | |
| "eval_samples_per_second": 51.323, | |
| "eval_steps_per_second": 12.907, | |
| "step": 19171 | |
| }, | |
| { | |
| "epoch": 38.65, | |
| "learning_rate": 2.319404761904762e-05, | |
| "loss": 0.1817, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.9287128712871288, | |
| "eval_f1": 0.8884108101819078, | |
| "eval_loss": 0.4824526309967041, | |
| "eval_precision": 0.9067813929838341, | |
| "eval_recall": 0.8854446125769654, | |
| "eval_runtime": 10.5682, | |
| "eval_samples_per_second": 47.785, | |
| "eval_steps_per_second": 12.017, | |
| "step": 19675 | |
| }, | |
| { | |
| "epoch": 39.64, | |
| "learning_rate": 2.3789285714285715e-05, | |
| "loss": 0.1504, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.9346534653465347, | |
| "eval_f1": 0.9079267627717296, | |
| "eval_loss": 0.48847106099128723, | |
| "eval_precision": 0.9168877258505742, | |
| "eval_recall": 0.9021284924226101, | |
| "eval_runtime": 9.5244, | |
| "eval_samples_per_second": 53.021, | |
| "eval_steps_per_second": 13.334, | |
| "step": 20180 | |
| }, | |
| { | |
| "epoch": 40.63, | |
| "learning_rate": 2.4383333333333334e-05, | |
| "loss": 0.1367, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.902970297029703, | |
| "eval_f1": 0.8748563062275386, | |
| "eval_loss": 0.6201313734054565, | |
| "eval_precision": 0.8975989253974328, | |
| "eval_recall": 0.8675623151358445, | |
| "eval_runtime": 11.0171, | |
| "eval_samples_per_second": 45.838, | |
| "eval_steps_per_second": 11.528, | |
| "step": 20684 | |
| }, | |
| { | |
| "epoch": 41.63, | |
| "learning_rate": 2.497857142857143e-05, | |
| "loss": 0.1786, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.9089108910891089, | |
| "eval_f1": 0.8833714971261983, | |
| "eval_loss": 0.6504853963851929, | |
| "eval_precision": 0.9036762862738423, | |
| "eval_recall": 0.8743047475400418, | |
| "eval_runtime": 9.3899, | |
| "eval_samples_per_second": 53.781, | |
| "eval_steps_per_second": 13.525, | |
| "step": 21189 | |
| }, | |
| { | |
| "epoch": 42.62, | |
| "learning_rate": 2.5573809523809525e-05, | |
| "loss": 0.1589, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.9504950495049505, | |
| "eval_f1": 0.9268454843019528, | |
| "eval_loss": 0.35494372248649597, | |
| "eval_precision": 0.9327534998068862, | |
| "eval_recall": 0.9231311498958558, | |
| "eval_runtime": 10.3634, | |
| "eval_samples_per_second": 48.729, | |
| "eval_steps_per_second": 12.255, | |
| "step": 21693 | |
| }, | |
| { | |
| "epoch": 43.61, | |
| "learning_rate": 2.616904761904762e-05, | |
| "loss": 0.0857, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.9485148514851485, | |
| "eval_f1": 0.9224485798890482, | |
| "eval_loss": 0.41820821166038513, | |
| "eval_precision": 0.9441624977223921, | |
| "eval_recall": 0.9108187890540833, | |
| "eval_runtime": 9.3522, | |
| "eval_samples_per_second": 53.998, | |
| "eval_steps_per_second": 13.58, | |
| "step": 22198 | |
| }, | |
| { | |
| "epoch": 44.6, | |
| "learning_rate": 2.6763095238095236e-05, | |
| "loss": 0.102, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.9564356435643564, | |
| "eval_f1": 0.9306293793472796, | |
| "eval_loss": 0.29131555557250977, | |
| "eval_precision": 0.9291726584104362, | |
| "eval_recall": 0.9330733318968613, | |
| "eval_runtime": 9.5553, | |
| "eval_samples_per_second": 52.85, | |
| "eval_steps_per_second": 13.291, | |
| "step": 22702 | |
| } | |
| ], | |
| "max_steps": 252000, | |
| "num_train_epochs": 500, | |
| "total_flos": 1.9381803431060155e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |