| { | |
| "best_global_step": 180, | |
| "best_metric": 50.112359550561806, | |
| "best_model_checkpoint": "./whisper-large-v3-is-raddromur-lora-wandb/checkpoint-180", | |
| "epoch": 2.9856262833675564, | |
| "eval_steps": 30, | |
| "global_step": 180, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.049281314168377825, | |
| "grad_norm": 0.22914348542690277, | |
| "learning_rate": 1.111111111111111e-06, | |
| "loss": 1.391, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.09856262833675565, | |
| "grad_norm": 0.24495559930801392, | |
| "learning_rate": 2.7777777777777783e-06, | |
| "loss": 1.417, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.14784394250513347, | |
| "grad_norm": 0.2494819313287735, | |
| "learning_rate": 4.444444444444444e-06, | |
| "loss": 1.4382, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1971252566735113, | |
| "grad_norm": 0.23504748940467834, | |
| "learning_rate": 6.111111111111112e-06, | |
| "loss": 1.3623, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2464065708418891, | |
| "grad_norm": 0.25508585572242737, | |
| "learning_rate": 7.77777777777778e-06, | |
| "loss": 1.4247, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.29568788501026694, | |
| "grad_norm": 0.24351638555526733, | |
| "learning_rate": 9.444444444444445e-06, | |
| "loss": 1.4221, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.34496919917864477, | |
| "grad_norm": 0.2543489933013916, | |
| "learning_rate": 9.876543209876543e-06, | |
| "loss": 1.4149, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3942505133470226, | |
| "grad_norm": 0.250897079706192, | |
| "learning_rate": 9.691358024691358e-06, | |
| "loss": 1.4158, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.44353182751540043, | |
| "grad_norm": 0.23567010462284088, | |
| "learning_rate": 9.506172839506174e-06, | |
| "loss": 1.3949, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.4928131416837782, | |
| "grad_norm": 0.24683956801891327, | |
| "learning_rate": 9.320987654320989e-06, | |
| "loss": 1.3688, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4928131416837782, | |
| "eval_runtime": 745.8583, | |
| "eval_samples_per_second": 1.735, | |
| "eval_steps_per_second": 0.036, | |
| "eval_wer": 53.24536190227332, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5420944558521561, | |
| "grad_norm": 0.22976352274417877, | |
| "learning_rate": 9.135802469135803e-06, | |
| "loss": 1.3591, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5913757700205339, | |
| "grad_norm": 0.24124480783939362, | |
| "learning_rate": 8.950617283950618e-06, | |
| "loss": 1.3709, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6406570841889117, | |
| "grad_norm": 0.22739216685295105, | |
| "learning_rate": 8.765432098765432e-06, | |
| "loss": 1.4126, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6899383983572895, | |
| "grad_norm": 0.2386259138584137, | |
| "learning_rate": 8.580246913580249e-06, | |
| "loss": 1.3458, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7392197125256673, | |
| "grad_norm": 0.23364992439746857, | |
| "learning_rate": 8.395061728395062e-06, | |
| "loss": 1.3779, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7885010266940452, | |
| "grad_norm": 0.23184379935264587, | |
| "learning_rate": 8.209876543209876e-06, | |
| "loss": 1.338, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.837782340862423, | |
| "grad_norm": 0.23423455655574799, | |
| "learning_rate": 8.024691358024692e-06, | |
| "loss": 1.3115, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.8870636550308009, | |
| "grad_norm": 0.23327411711215973, | |
| "learning_rate": 7.839506172839507e-06, | |
| "loss": 1.2838, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.9363449691991786, | |
| "grad_norm": 0.24564896523952484, | |
| "learning_rate": 7.654320987654322e-06, | |
| "loss": 1.3335, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.9856262833675564, | |
| "grad_norm": 0.21617886424064636, | |
| "learning_rate": 7.469135802469136e-06, | |
| "loss": 1.3044, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.9856262833675564, | |
| "eval_runtime": 755.2022, | |
| "eval_samples_per_second": 1.713, | |
| "eval_steps_per_second": 0.036, | |
| "eval_wer": 53.106872223673896, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.0492813141683779, | |
| "grad_norm": 0.2329856902360916, | |
| "learning_rate": 7.283950617283952e-06, | |
| "loss": 1.403, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.0985626283367556, | |
| "grad_norm": 0.2415734827518463, | |
| "learning_rate": 7.098765432098766e-06, | |
| "loss": 1.2926, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.1478439425051334, | |
| "grad_norm": 0.22719435393810272, | |
| "learning_rate": 6.913580246913581e-06, | |
| "loss": 1.3266, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.1971252566735113, | |
| "grad_norm": 0.22385141253471375, | |
| "learning_rate": 6.728395061728395e-06, | |
| "loss": 1.3099, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.2464065708418892, | |
| "grad_norm": 0.22575075924396515, | |
| "learning_rate": 6.543209876543211e-06, | |
| "loss": 1.2993, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.2956878850102669, | |
| "grad_norm": 0.2280450165271759, | |
| "learning_rate": 6.358024691358025e-06, | |
| "loss": 1.2516, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.3449691991786448, | |
| "grad_norm": 0.21805013716220856, | |
| "learning_rate": 6.17283950617284e-06, | |
| "loss": 1.2796, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.3942505133470227, | |
| "grad_norm": 0.2454097718000412, | |
| "learning_rate": 5.9876543209876546e-06, | |
| "loss": 1.2567, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.4435318275154003, | |
| "grad_norm": 0.23440390825271606, | |
| "learning_rate": 5.80246913580247e-06, | |
| "loss": 1.2578, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.4928131416837782, | |
| "grad_norm": 0.21233566105365753, | |
| "learning_rate": 5.617283950617285e-06, | |
| "loss": 1.226, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.4928131416837782, | |
| "eval_runtime": 757.9185, | |
| "eval_samples_per_second": 1.707, | |
| "eval_steps_per_second": 0.036, | |
| "eval_wer": 51.94408152599947, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.542094455852156, | |
| "grad_norm": 0.23111841082572937, | |
| "learning_rate": 5.432098765432099e-06, | |
| "loss": 1.2835, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.5913757700205338, | |
| "grad_norm": 0.22747503221035004, | |
| "learning_rate": 5.246913580246914e-06, | |
| "loss": 1.1713, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.6406570841889117, | |
| "grad_norm": 0.24629150331020355, | |
| "learning_rate": 5.061728395061729e-06, | |
| "loss": 1.2652, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.6899383983572895, | |
| "grad_norm": 0.20970605313777924, | |
| "learning_rate": 4.876543209876544e-06, | |
| "loss": 1.2063, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.7392197125256672, | |
| "grad_norm": 0.2347603589296341, | |
| "learning_rate": 4.691358024691358e-06, | |
| "loss": 1.1642, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.7885010266940453, | |
| "grad_norm": 0.22151677310466766, | |
| "learning_rate": 4.506172839506173e-06, | |
| "loss": 1.2559, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.837782340862423, | |
| "grad_norm": 0.21644067764282227, | |
| "learning_rate": 4.3209876543209875e-06, | |
| "loss": 1.2654, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.8870636550308009, | |
| "grad_norm": 0.2234969586133957, | |
| "learning_rate": 4.135802469135803e-06, | |
| "loss": 1.1653, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.9363449691991788, | |
| "grad_norm": 0.2156331092119217, | |
| "learning_rate": 3.9506172839506175e-06, | |
| "loss": 1.172, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.9856262833675564, | |
| "grad_norm": 0.21376466751098633, | |
| "learning_rate": 3.7654320987654325e-06, | |
| "loss": 1.2796, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.9856262833675564, | |
| "eval_runtime": 760.4652, | |
| "eval_samples_per_second": 1.702, | |
| "eval_steps_per_second": 0.036, | |
| "eval_wer": 51.795139796185, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.0492813141683777, | |
| "grad_norm": 0.2266222983598709, | |
| "learning_rate": 3.580246913580247e-06, | |
| "loss": 1.3315, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 2.0985626283367558, | |
| "grad_norm": 0.22814051806926727, | |
| "learning_rate": 3.395061728395062e-06, | |
| "loss": 1.1759, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 2.1478439425051334, | |
| "grad_norm": 0.22590585052967072, | |
| "learning_rate": 3.2098765432098767e-06, | |
| "loss": 1.2064, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 2.197125256673511, | |
| "grad_norm": 0.22349856793880463, | |
| "learning_rate": 3.0246913580246917e-06, | |
| "loss": 1.1868, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 2.246406570841889, | |
| "grad_norm": 0.21798408031463623, | |
| "learning_rate": 2.8395061728395062e-06, | |
| "loss": 1.1485, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.295687885010267, | |
| "grad_norm": 0.23827993869781494, | |
| "learning_rate": 2.6543209876543212e-06, | |
| "loss": 1.1347, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 2.344969199178645, | |
| "grad_norm": 0.21975603699684143, | |
| "learning_rate": 2.469135802469136e-06, | |
| "loss": 1.152, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 2.3942505133470227, | |
| "grad_norm": 0.2301456183195114, | |
| "learning_rate": 2.283950617283951e-06, | |
| "loss": 1.212, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 2.4435318275154003, | |
| "grad_norm": 0.2236107736825943, | |
| "learning_rate": 2.0987654320987654e-06, | |
| "loss": 1.2156, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 2.4928131416837784, | |
| "grad_norm": 0.22880277037620544, | |
| "learning_rate": 1.9135802469135804e-06, | |
| "loss": 1.1885, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.4928131416837784, | |
| "eval_runtime": 758.1625, | |
| "eval_samples_per_second": 1.707, | |
| "eval_steps_per_second": 0.036, | |
| "eval_wer": 50.802194930755164, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.542094455852156, | |
| "grad_norm": 0.23217734694480896, | |
| "learning_rate": 1.7283950617283952e-06, | |
| "loss": 1.2508, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 2.5913757700205338, | |
| "grad_norm": 0.21702837944030762, | |
| "learning_rate": 1.54320987654321e-06, | |
| "loss": 1.1574, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 2.640657084188912, | |
| "grad_norm": 0.22827443480491638, | |
| "learning_rate": 1.3580246913580248e-06, | |
| "loss": 1.1662, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 2.6899383983572895, | |
| "grad_norm": 0.22730480134487152, | |
| "learning_rate": 1.1728395061728396e-06, | |
| "loss": 1.1829, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 2.739219712525667, | |
| "grad_norm": 0.24221959710121155, | |
| "learning_rate": 9.876543209876544e-07, | |
| "loss": 1.2032, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 2.7885010266940453, | |
| "grad_norm": 0.22492796182632446, | |
| "learning_rate": 8.024691358024692e-07, | |
| "loss": 1.1646, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 2.837782340862423, | |
| "grad_norm": 0.23047611117362976, | |
| "learning_rate": 6.17283950617284e-07, | |
| "loss": 1.1689, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 2.8870636550308006, | |
| "grad_norm": 0.22853408753871918, | |
| "learning_rate": 4.320987654320988e-07, | |
| "loss": 1.1771, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 2.9363449691991788, | |
| "grad_norm": 0.21958370506763458, | |
| "learning_rate": 2.469135802469136e-07, | |
| "loss": 1.1692, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 2.9856262833675564, | |
| "grad_norm": 0.22913524508476257, | |
| "learning_rate": 6.17283950617284e-08, | |
| "loss": 1.1844, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.9856262833675564, | |
| "eval_runtime": 756.6055, | |
| "eval_samples_per_second": 1.71, | |
| "eval_steps_per_second": 0.036, | |
| "eval_wer": 50.112359550561806, | |
| "step": 180 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 180, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 30, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1899959344350469e+20, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |