| { | |
| "best_metric": 0.3106290400028229, | |
| "best_model_checkpoint": "nrshoudi/wav2vec-arabic-V2-50/checkpoint-8180", | |
| "epoch": 20.0, | |
| "eval_steps": 500, | |
| "global_step": 16360, | |
| "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": 10.1558, | |
| "step": 818 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.2108113765716553, | |
| "eval_per": 1.0, | |
| "eval_runtime": 121.3546, | |
| "eval_samples_per_second": 6.699, | |
| "eval_steps_per_second": 3.354, | |
| "eval_wer": 1.0, | |
| "step": 818 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0001, | |
| "loss": 3.0783, | |
| "step": 1636 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.077756881713867, | |
| "eval_per": 0.9395552624140205, | |
| "eval_runtime": 121.8972, | |
| "eval_samples_per_second": 6.67, | |
| "eval_steps_per_second": 3.339, | |
| "eval_wer": 0.9260417152722692, | |
| "step": 1636 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 9.444444444444444e-05, | |
| "loss": 0.7602, | |
| "step": 2454 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.38355985283851624, | |
| "eval_per": 0.08696881183454254, | |
| "eval_runtime": 123.229, | |
| "eval_samples_per_second": 6.597, | |
| "eval_steps_per_second": 3.303, | |
| "eval_wer": 0.10232840278101815, | |
| "step": 2454 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 8.888888888888889e-05, | |
| "loss": 0.2361, | |
| "step": 3272 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.325092613697052, | |
| "eval_per": 0.05165834354094036, | |
| "eval_runtime": 122.9982, | |
| "eval_samples_per_second": 6.61, | |
| "eval_steps_per_second": 3.309, | |
| "eval_wer": 0.0667724324576548, | |
| "step": 3272 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 0.1602, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.3239767551422119, | |
| "eval_per": 0.05151700744370112, | |
| "eval_runtime": 122.92, | |
| "eval_samples_per_second": 6.614, | |
| "eval_steps_per_second": 3.311, | |
| "eval_wer": 0.06639914143063787, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 7.777777777777778e-05, | |
| "loss": 0.1216, | |
| "step": 4908 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.32677653431892395, | |
| "eval_per": 0.05311881654574578, | |
| "eval_runtime": 123.0237, | |
| "eval_samples_per_second": 6.608, | |
| "eval_steps_per_second": 3.308, | |
| "eval_wer": 0.06733236899818021, | |
| "step": 4908 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 7.222222222222222e-05, | |
| "loss": 0.1078, | |
| "step": 5726 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.35006746649742126, | |
| "eval_per": 0.04649957599170828, | |
| "eval_runtime": 123.221, | |
| "eval_samples_per_second": 6.598, | |
| "eval_steps_per_second": 3.303, | |
| "eval_wer": 0.06079977602538379, | |
| "step": 5726 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.0933, | |
| "step": 6544 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.34512361884117126, | |
| "eval_per": 0.04021011966456233, | |
| "eval_runtime": 123.1692, | |
| "eval_samples_per_second": 6.601, | |
| "eval_steps_per_second": 3.304, | |
| "eval_wer": 0.053847230647193316, | |
| "step": 6544 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 6.111111111111112e-05, | |
| "loss": 0.0713, | |
| "step": 7362 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.36584600806236267, | |
| "eval_per": 0.04072835202110619, | |
| "eval_runtime": 123.1989, | |
| "eval_samples_per_second": 6.599, | |
| "eval_steps_per_second": 3.304, | |
| "eval_wer": 0.05389389202557043, | |
| "step": 7362 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 5.555555555555556e-05, | |
| "loss": 0.0687, | |
| "step": 8180 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.3106290400028229, | |
| "eval_per": 0.03856119853010459, | |
| "eval_runtime": 123.4148, | |
| "eval_samples_per_second": 6.588, | |
| "eval_steps_per_second": 3.298, | |
| "eval_wer": 0.05188745275535439, | |
| "step": 8180 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0561, | |
| "step": 8998 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.3322308361530304, | |
| "eval_per": 0.03959766324319231, | |
| "eval_runtime": 124.0615, | |
| "eval_samples_per_second": 6.553, | |
| "eval_steps_per_second": 3.281, | |
| "eval_wer": 0.052914003079650974, | |
| "step": 8998 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.0516, | |
| "step": 9816 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.32428082823753357, | |
| "eval_per": 0.036087816828417975, | |
| "eval_runtime": 123.5702, | |
| "eval_samples_per_second": 6.579, | |
| "eval_steps_per_second": 3.294, | |
| "eval_wer": 0.04843451075544772, | |
| "step": 9816 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.0392, | |
| "step": 10634 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.3411938548088074, | |
| "eval_per": 0.035404692358428344, | |
| "eval_runtime": 123.9404, | |
| "eval_samples_per_second": 6.56, | |
| "eval_steps_per_second": 3.284, | |
| "eval_wer": 0.04745462180952825, | |
| "step": 10634 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.037, | |
| "step": 11452 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.3370288014411926, | |
| "eval_per": 0.035899368698765664, | |
| "eval_runtime": 123.6678, | |
| "eval_samples_per_second": 6.574, | |
| "eval_steps_per_second": 3.291, | |
| "eval_wer": 0.04768792870141384, | |
| "step": 11452 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.0318, | |
| "step": 12270 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.32496118545532227, | |
| "eval_per": 0.03580514463393951, | |
| "eval_runtime": 123.6467, | |
| "eval_samples_per_second": 6.575, | |
| "eval_steps_per_second": 3.292, | |
| "eval_wer": 0.04656805562036303, | |
| "step": 12270 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.0291, | |
| "step": 13088 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 0.34510985016822815, | |
| "eval_per": 0.035946480731178745, | |
| "eval_runtime": 123.7608, | |
| "eval_samples_per_second": 6.569, | |
| "eval_steps_per_second": 3.289, | |
| "eval_wer": 0.04773459007979096, | |
| "step": 13088 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.025, | |
| "step": 13906 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 0.3712596893310547, | |
| "eval_per": 0.03679449731461415, | |
| "eval_runtime": 123.927, | |
| "eval_samples_per_second": 6.56, | |
| "eval_steps_per_second": 3.284, | |
| "eval_wer": 0.04862115626895618, | |
| "step": 13906 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0274, | |
| "step": 14724 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 0.32992804050445557, | |
| "eval_per": 0.03458023179119947, | |
| "eval_runtime": 123.4837, | |
| "eval_samples_per_second": 6.584, | |
| "eval_steps_per_second": 3.296, | |
| "eval_wer": 0.04591479632308339, | |
| "step": 14724 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.0208, | |
| "step": 15542 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 0.34512093663215637, | |
| "eval_per": 0.03488646000188448, | |
| "eval_runtime": 122.6539, | |
| "eval_samples_per_second": 6.628, | |
| "eval_steps_per_second": 3.318, | |
| "eval_wer": 0.04628808735010032, | |
| "step": 15542 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0187, | |
| "step": 16360 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.3407500386238098, | |
| "eval_per": 0.03474512390464524, | |
| "eval_runtime": 122.6729, | |
| "eval_samples_per_second": 6.627, | |
| "eval_steps_per_second": 3.318, | |
| "eval_wer": 0.0459614577014605, | |
| "step": 16360 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 16360, | |
| "total_flos": 5.249198170404504e+18, | |
| "train_loss": 0.7594956291916901, | |
| "train_runtime": 11598.3794, | |
| "train_samples_per_second": 2.821, | |
| "train_steps_per_second": 1.411 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 16360, | |
| "num_train_epochs": 20, | |
| "save_steps": 500, | |
| "total_flos": 5.249198170404504e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |