| { | |
| "best_metric": 0.18050541516245489, | |
| "best_model_checkpoint": "/content/drive/MyDrive/Fine tune/wav2vec2_R/TestModel6/checkpoint-198", | |
| "epoch": 27.0, | |
| "eval_steps": 500, | |
| "global_step": 243, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 2.6207005977630615, | |
| "learning_rate": 2.0454545454545457e-05, | |
| "loss": 1.4468, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.9447698593139648, | |
| "eval_runtime": 7.468, | |
| "eval_samples_per_second": 1.339, | |
| "eval_steps_per_second": 0.268, | |
| "eval_wer": 0.3458483754512635, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.9180173873901367, | |
| "learning_rate": 4.0909090909090915e-05, | |
| "loss": 1.0187, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.7252597808837891, | |
| "eval_runtime": 7.0648, | |
| "eval_samples_per_second": 1.415, | |
| "eval_steps_per_second": 0.283, | |
| "eval_wer": 0.2772563176895307, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 1.0308139324188232, | |
| "learning_rate": 4.9978417404589105e-05, | |
| "loss": 0.7962, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.5624670386314392, | |
| "eval_runtime": 7.0549, | |
| "eval_samples_per_second": 1.417, | |
| "eval_steps_per_second": 0.283, | |
| "eval_wer": 0.30541516245487366, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 1.6524184942245483, | |
| "learning_rate": 4.983095894354858e-05, | |
| "loss": 0.6591, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.49896639585494995, | |
| "eval_runtime": 6.9528, | |
| "eval_samples_per_second": 1.438, | |
| "eval_steps_per_second": 0.288, | |
| "eval_wer": 0.24332129963898916, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 1.9104937314987183, | |
| "learning_rate": 4.954463568772415e-05, | |
| "loss": 0.5742, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.4727010130882263, | |
| "eval_runtime": 7.6581, | |
| "eval_samples_per_second": 1.306, | |
| "eval_steps_per_second": 0.261, | |
| "eval_wer": 0.23249097472924188, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.7306864261627197, | |
| "learning_rate": 4.912104887290587e-05, | |
| "loss": 0.5231, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.4486842155456543, | |
| "eval_runtime": 7.182, | |
| "eval_samples_per_second": 1.392, | |
| "eval_steps_per_second": 0.278, | |
| "eval_wer": 0.21444043321299638, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 0.8729464411735535, | |
| "learning_rate": 4.856256736838498e-05, | |
| "loss": 0.4567, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.45621854066848755, | |
| "eval_runtime": 7.0189, | |
| "eval_samples_per_second": 1.425, | |
| "eval_steps_per_second": 0.285, | |
| "eval_wer": 0.21516245487364621, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.9639649987220764, | |
| "learning_rate": 4.787231442927587e-05, | |
| "loss": 0.4934, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.4438972473144531, | |
| "eval_runtime": 7.0861, | |
| "eval_samples_per_second": 1.411, | |
| "eval_steps_per_second": 0.282, | |
| "eval_wer": 0.2108303249097473, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 1.3746402263641357, | |
| "learning_rate": 4.7054150230006604e-05, | |
| "loss": 0.4516, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.43273186683654785, | |
| "eval_runtime": 7.1786, | |
| "eval_samples_per_second": 1.393, | |
| "eval_steps_per_second": 0.279, | |
| "eval_wer": 0.2043321299638989, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.5043421387672424, | |
| "learning_rate": 4.61126502766577e-05, | |
| "loss": 0.4069, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.43151745200157166, | |
| "eval_runtime": 6.9477, | |
| "eval_samples_per_second": 1.439, | |
| "eval_steps_per_second": 0.288, | |
| "eval_wer": 0.1956678700361011, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "grad_norm": 1.8196316957473755, | |
| "learning_rate": 4.50530798188761e-05, | |
| "loss": 0.4235, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.4364844858646393, | |
| "eval_runtime": 7.1022, | |
| "eval_samples_per_second": 1.408, | |
| "eval_steps_per_second": 0.282, | |
| "eval_wer": 0.20144404332129964, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 0.22248859703540802, | |
| "learning_rate": 4.388136440446337e-05, | |
| "loss": 0.4004, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.43696457147598267, | |
| "eval_runtime": 7.1886, | |
| "eval_samples_per_second": 1.391, | |
| "eval_steps_per_second": 0.278, | |
| "eval_wer": 0.19855595667870035, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "grad_norm": 1.0341521501541138, | |
| "learning_rate": 4.2604056741308796e-05, | |
| "loss": 0.3652, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.4320377707481384, | |
| "eval_runtime": 7.073, | |
| "eval_samples_per_second": 1.414, | |
| "eval_steps_per_second": 0.283, | |
| "eval_wer": 0.19494584837545126, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "grad_norm": 0.6511925458908081, | |
| "learning_rate": 4.12283000519888e-05, | |
| "loss": 0.3597, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.4305523931980133, | |
| "eval_runtime": 7.0901, | |
| "eval_samples_per_second": 1.41, | |
| "eval_steps_per_second": 0.282, | |
| "eval_wer": 0.19133574007220217, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "grad_norm": 0.897441565990448, | |
| "learning_rate": 3.9761788125968744e-05, | |
| "loss": 0.3701, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.4407591223716736, | |
| "eval_runtime": 6.9823, | |
| "eval_samples_per_second": 1.432, | |
| "eval_steps_per_second": 0.286, | |
| "eval_wer": 0.1891696750902527, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "grad_norm": 1.0737636089324951, | |
| "learning_rate": 3.821272229281139e-05, | |
| "loss": 0.3348, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 0.4343787729740143, | |
| "eval_runtime": 7.07, | |
| "eval_samples_per_second": 1.414, | |
| "eval_steps_per_second": 0.283, | |
| "eval_wer": 0.18483754512635378, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "grad_norm": 0.5325424671173096, | |
| "learning_rate": 3.6589765557015145e-05, | |
| "loss": 0.3248, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 0.42944344878196716, | |
| "eval_runtime": 7.0553, | |
| "eval_samples_per_second": 1.417, | |
| "eval_steps_per_second": 0.283, | |
| "eval_wer": 0.1884476534296029, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "grad_norm": 0.6885235905647278, | |
| "learning_rate": 3.490199415097892e-05, | |
| "loss": 0.3212, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 0.4301183819770813, | |
| "eval_runtime": 6.9613, | |
| "eval_samples_per_second": 1.437, | |
| "eval_steps_per_second": 0.287, | |
| "eval_wer": 0.18483754512635378, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "grad_norm": 0.5315946340560913, | |
| "learning_rate": 3.31588467770289e-05, | |
| "loss": 0.3484, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 0.4417332112789154, | |
| "eval_runtime": 7.0935, | |
| "eval_samples_per_second": 1.41, | |
| "eval_steps_per_second": 0.282, | |
| "eval_wer": 0.1855595667870036, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 0.6952418684959412, | |
| "learning_rate": 3.137007182236637e-05, | |
| "loss": 0.3193, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.4366823732852936, | |
| "eval_runtime": 6.9514, | |
| "eval_samples_per_second": 1.439, | |
| "eval_steps_per_second": 0.288, | |
| "eval_wer": 0.19061371841155234, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "grad_norm": 0.3309876024723053, | |
| "learning_rate": 2.9545672842132273e-05, | |
| "loss": 0.3157, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 0.45008668303489685, | |
| "eval_runtime": 6.9279, | |
| "eval_samples_per_second": 1.443, | |
| "eval_steps_per_second": 0.289, | |
| "eval_wer": 0.18411552346570398, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "grad_norm": 0.49725911021232605, | |
| "learning_rate": 2.769585261546897e-05, | |
| "loss": 0.2985, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 0.4500831961631775, | |
| "eval_runtime": 6.8409, | |
| "eval_samples_per_second": 1.462, | |
| "eval_steps_per_second": 0.292, | |
| "eval_wer": 0.18050541516245489, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "grad_norm": 0.7141502499580383, | |
| "learning_rate": 2.5830956087440665e-05, | |
| "loss": 0.3284, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 0.4402785897254944, | |
| "eval_runtime": 6.9521, | |
| "eval_samples_per_second": 1.438, | |
| "eval_steps_per_second": 0.288, | |
| "eval_wer": 0.18483754512635378, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "grad_norm": 0.8570722341537476, | |
| "learning_rate": 2.3961412515904336e-05, | |
| "loss": 0.3057, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 0.4428979754447937, | |
| "eval_runtime": 6.9014, | |
| "eval_samples_per_second": 1.449, | |
| "eval_steps_per_second": 0.29, | |
| "eval_wer": 0.1884476534296029, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "grad_norm": 0.9306482076644897, | |
| "learning_rate": 2.2097677146869242e-05, | |
| "loss": 0.3062, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 0.4460487961769104, | |
| "eval_runtime": 6.8059, | |
| "eval_samples_per_second": 1.469, | |
| "eval_steps_per_second": 0.294, | |
| "eval_wer": 0.1855595667870036, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "grad_norm": 0.28782331943511963, | |
| "learning_rate": 2.0250172744520258e-05, | |
| "loss": 0.2985, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_loss": 0.4484630227088928, | |
| "eval_runtime": 6.8287, | |
| "eval_samples_per_second": 1.464, | |
| "eval_steps_per_second": 0.293, | |
| "eval_wer": 0.18411552346570398, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "grad_norm": 0.636001706123352, | |
| "learning_rate": 1.842923130289262e-05, | |
| "loss": 0.2732, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_loss": 0.449407160282135, | |
| "eval_runtime": 6.9231, | |
| "eval_samples_per_second": 1.444, | |
| "eval_steps_per_second": 0.289, | |
| "eval_wer": 0.18050541516245489, | |
| "step": 243 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 400, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 6, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 5 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.7013666477539267e+18, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |