| { | |
| "best_metric": 0.29899266362190247, | |
| "best_model_checkpoint": "nrshoudi/wav2vec_arabic_mdd/checkpoint-19404", | |
| "epoch": 20.0, | |
| "eval_steps": 500, | |
| "global_step": 32340, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5e-05, | |
| "loss": 8.2138, | |
| "step": 1617 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.1148788928985596, | |
| "eval_per": 1.0, | |
| "eval_runtime": 115.2576, | |
| "eval_samples_per_second": 7.054, | |
| "eval_steps_per_second": 3.531, | |
| "eval_wer": 1.0, | |
| "step": 1617 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1507, | |
| "step": 3234 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.37626245617866516, | |
| "eval_per": 0.0569820032036182, | |
| "eval_runtime": 116.2275, | |
| "eval_samples_per_second": 6.995, | |
| "eval_steps_per_second": 3.502, | |
| "eval_wer": 0.0732583640520741, | |
| "step": 3234 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 9.444444444444444e-05, | |
| "loss": 0.2, | |
| "step": 4851 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.319857656955719, | |
| "eval_per": 0.04925562988787336, | |
| "eval_runtime": 115.4027, | |
| "eval_samples_per_second": 7.045, | |
| "eval_steps_per_second": 3.527, | |
| "eval_wer": 0.06341281321450236, | |
| "step": 4851 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 8.888888888888889e-05, | |
| "loss": 0.1328, | |
| "step": 6468 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.34467777609825134, | |
| "eval_per": 0.03985677942146424, | |
| "eval_runtime": 115.3838, | |
| "eval_samples_per_second": 7.046, | |
| "eval_steps_per_second": 3.527, | |
| "eval_wer": 0.05296066445802809, | |
| "step": 6468 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 0.1045, | |
| "step": 8085 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.30046939849853516, | |
| "eval_per": 0.04013945161594271, | |
| "eval_runtime": 116.1796, | |
| "eval_samples_per_second": 6.998, | |
| "eval_steps_per_second": 3.503, | |
| "eval_wer": 0.05142083897158322, | |
| "step": 8085 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 7.777777777777778e-05, | |
| "loss": 0.088, | |
| "step": 9702 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.32756975293159485, | |
| "eval_per": 0.03907943088664845, | |
| "eval_runtime": 116.0861, | |
| "eval_samples_per_second": 7.003, | |
| "eval_steps_per_second": 3.506, | |
| "eval_wer": 0.05165414586346881, | |
| "step": 9702 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 7.222222222222222e-05, | |
| "loss": 0.0756, | |
| "step": 11319 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.33674493432044983, | |
| "eval_per": 0.03879675869216998, | |
| "eval_runtime": 115.7009, | |
| "eval_samples_per_second": 7.027, | |
| "eval_steps_per_second": 3.518, | |
| "eval_wer": 0.05118753207969763, | |
| "step": 11319 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.062, | |
| "step": 12936 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.3933280110359192, | |
| "eval_per": 0.042165269009705075, | |
| "eval_runtime": 115.0602, | |
| "eval_samples_per_second": 7.066, | |
| "eval_steps_per_second": 3.537, | |
| "eval_wer": 0.05720684989034576, | |
| "step": 12936 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 6.111111111111112e-05, | |
| "loss": 0.0603, | |
| "step": 14553 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.3331439197063446, | |
| "eval_per": 0.03587581268255913, | |
| "eval_runtime": 115.3081, | |
| "eval_samples_per_second": 7.051, | |
| "eval_steps_per_second": 3.53, | |
| "eval_wer": 0.04754794456628249, | |
| "step": 14553 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 5.555555555555556e-05, | |
| "loss": 0.0517, | |
| "step": 16170 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.301434725522995, | |
| "eval_per": 0.03717139357391878, | |
| "eval_runtime": 115.3305, | |
| "eval_samples_per_second": 7.049, | |
| "eval_steps_per_second": 3.529, | |
| "eval_wer": 0.049974336241892583, | |
| "step": 16170 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.046, | |
| "step": 17787 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.30668768286705017, | |
| "eval_per": 0.036017148779798364, | |
| "eval_runtime": 115.2426, | |
| "eval_samples_per_second": 7.055, | |
| "eval_steps_per_second": 3.532, | |
| "eval_wer": 0.04768792870141384, | |
| "step": 17787 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.0398, | |
| "step": 19404 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.29899266362190247, | |
| "eval_per": 0.03481579195326486, | |
| "eval_runtime": 115.6042, | |
| "eval_samples_per_second": 7.033, | |
| "eval_steps_per_second": 3.521, | |
| "eval_wer": 0.04558816667444356, | |
| "step": 19404 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.0329, | |
| "step": 21021 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.3064207434654236, | |
| "eval_per": 0.034226891548101386, | |
| "eval_runtime": 116.0675, | |
| "eval_samples_per_second": 7.005, | |
| "eval_steps_per_second": 3.507, | |
| "eval_wer": 0.04498156875554104, | |
| "step": 21021 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0319, | |
| "step": 22638 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.3336479663848877, | |
| "eval_per": 0.03825497031941958, | |
| "eval_runtime": 115.1932, | |
| "eval_samples_per_second": 7.058, | |
| "eval_steps_per_second": 3.533, | |
| "eval_wer": 0.04988101348513835, | |
| "step": 22638 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.0288, | |
| "step": 24255 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.32215777039527893, | |
| "eval_per": 0.03575803260152643, | |
| "eval_runtime": 115.0522, | |
| "eval_samples_per_second": 7.066, | |
| "eval_steps_per_second": 3.538, | |
| "eval_wer": 0.04512155289067239, | |
| "step": 24255 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.0258, | |
| "step": 25872 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 0.33019357919692993, | |
| "eval_per": 0.03241307830019787, | |
| "eval_runtime": 115.355, | |
| "eval_samples_per_second": 7.048, | |
| "eval_steps_per_second": 3.528, | |
| "eval_wer": 0.042788483971816525, | |
| "step": 25872 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0181, | |
| "step": 27489 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 0.3408127427101135, | |
| "eval_per": 0.03335531894845944, | |
| "eval_runtime": 115.3097, | |
| "eval_samples_per_second": 7.051, | |
| "eval_steps_per_second": 3.53, | |
| "eval_wer": 0.0432550977555877, | |
| "step": 27489 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0172, | |
| "step": 29106 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 0.3215967118740082, | |
| "eval_per": 0.033119758786394046, | |
| "eval_runtime": 115.4137, | |
| "eval_samples_per_second": 7.044, | |
| "eval_steps_per_second": 3.526, | |
| "eval_wer": 0.043021790863702114, | |
| "step": 29106 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.0145, | |
| "step": 30723 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 0.3254193663597107, | |
| "eval_per": 0.03293131065674173, | |
| "eval_runtime": 115.2743, | |
| "eval_samples_per_second": 7.053, | |
| "eval_steps_per_second": 3.531, | |
| "eval_wer": 0.042975129485324996, | |
| "step": 30723 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0127, | |
| "step": 32340 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.32637345790863037, | |
| "eval_per": 0.0321304061057194, | |
| "eval_runtime": 115.2538, | |
| "eval_samples_per_second": 7.054, | |
| "eval_steps_per_second": 3.531, | |
| "eval_wer": 0.04166861089076571, | |
| "step": 32340 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 32340, | |
| "total_flos": 1.0355998175044045e+19, | |
| "train_loss": 0.520349072083029, | |
| "train_runtime": 19017.9936, | |
| "train_samples_per_second": 3.401, | |
| "train_steps_per_second": 1.7 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 32340, | |
| "num_train_epochs": 20, | |
| "save_steps": 500, | |
| "total_flos": 1.0355998175044045e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |