| { | |
| "best_metric": 0.3490070093457944, | |
| "best_model_checkpoint": "/content/drive/MyDrive/wav2vec2-large-xlsr-persian-asr-shemo_partial/checkpoint-1900", | |
| "epoch": 12.5, | |
| "eval_steps": 100, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 2.3226, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 1.4547958374023438, | |
| "eval_runtime": 34.1762, | |
| "eval_samples_per_second": 8.31, | |
| "eval_steps_per_second": 1.053, | |
| "eval_wer": 0.48510514018691586, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.7166, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_loss": 1.2459642887115479, | |
| "eval_runtime": 33.6203, | |
| "eval_samples_per_second": 8.447, | |
| "eval_steps_per_second": 1.071, | |
| "eval_wer": 0.4278621495327103, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 6e-06, | |
| "loss": 1.4987, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "eval_loss": 1.0671327114105225, | |
| "eval_runtime": 34.2581, | |
| "eval_samples_per_second": 8.29, | |
| "eval_steps_per_second": 1.051, | |
| "eval_wer": 0.41939252336448596, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 7.980000000000002e-06, | |
| "loss": 1.3771, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_loss": 0.9783589243888855, | |
| "eval_runtime": 33.3818, | |
| "eval_samples_per_second": 8.508, | |
| "eval_steps_per_second": 1.078, | |
| "eval_wer": 0.4053738317757009, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 9.980000000000001e-06, | |
| "loss": 1.3217, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "eval_loss": 0.9450137615203857, | |
| "eval_runtime": 33.8716, | |
| "eval_samples_per_second": 8.385, | |
| "eval_steps_per_second": 1.063, | |
| "eval_wer": 0.3904789719626168, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 9.340000000000002e-06, | |
| "loss": 1.3272, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "eval_loss": 0.8850811719894409, | |
| "eval_runtime": 33.8154, | |
| "eval_samples_per_second": 8.399, | |
| "eval_steps_per_second": 1.065, | |
| "eval_wer": 0.384053738317757, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 8.673333333333334e-06, | |
| "loss": 1.3025, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "eval_loss": 0.8747560977935791, | |
| "eval_runtime": 33.4341, | |
| "eval_samples_per_second": 8.494, | |
| "eval_steps_per_second": 1.077, | |
| "eval_wer": 0.37792056074766356, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 8.006666666666667e-06, | |
| "loss": 1.2719, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.8673518300056458, | |
| "eval_runtime": 33.8685, | |
| "eval_samples_per_second": 8.385, | |
| "eval_steps_per_second": 1.063, | |
| "eval_wer": 0.3723714953271028, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "learning_rate": 7.340000000000001e-06, | |
| "loss": 1.2563, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "eval_loss": 0.846738338470459, | |
| "eval_runtime": 33.4615, | |
| "eval_samples_per_second": 8.487, | |
| "eval_steps_per_second": 1.076, | |
| "eval_wer": 0.3691588785046729, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 6.6733333333333335e-06, | |
| "loss": 1.2451, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "eval_loss": 0.8440045714378357, | |
| "eval_runtime": 33.5683, | |
| "eval_samples_per_second": 8.46, | |
| "eval_steps_per_second": 1.072, | |
| "eval_wer": 0.3644859813084112, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 6.006666666666667e-06, | |
| "loss": 1.2585, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "eval_loss": 0.8292242884635925, | |
| "eval_runtime": 33.7508, | |
| "eval_samples_per_second": 8.415, | |
| "eval_steps_per_second": 1.067, | |
| "eval_wer": 0.36098130841121495, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 5.3400000000000005e-06, | |
| "loss": 1.2633, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "eval_loss": 0.8137357234954834, | |
| "eval_runtime": 33.9332, | |
| "eval_samples_per_second": 8.369, | |
| "eval_steps_per_second": 1.061, | |
| "eval_wer": 0.36010514018691586, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 4.673333333333333e-06, | |
| "loss": 1.1923, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "eval_loss": 0.8262812495231628, | |
| "eval_runtime": 33.9528, | |
| "eval_samples_per_second": 8.365, | |
| "eval_steps_per_second": 1.06, | |
| "eval_wer": 0.3574766355140187, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 8.75, | |
| "learning_rate": 4.006666666666667e-06, | |
| "loss": 1.2349, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 8.75, | |
| "eval_loss": 0.8184483647346497, | |
| "eval_runtime": 33.8393, | |
| "eval_samples_per_second": 8.393, | |
| "eval_steps_per_second": 1.064, | |
| "eval_wer": 0.35514018691588783, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "learning_rate": 3.3400000000000006e-06, | |
| "loss": 1.2511, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "eval_loss": 0.8078120350837708, | |
| "eval_runtime": 34.5077, | |
| "eval_samples_per_second": 8.23, | |
| "eval_steps_per_second": 1.043, | |
| "eval_wer": 0.3516355140186916, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 2.6733333333333333e-06, | |
| "loss": 1.1779, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.8102284669876099, | |
| "eval_runtime": 33.4526, | |
| "eval_samples_per_second": 8.49, | |
| "eval_steps_per_second": 1.076, | |
| "eval_wer": 0.35046728971962615, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 10.62, | |
| "learning_rate": 2.006666666666667e-06, | |
| "loss": 1.2161, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 10.62, | |
| "eval_loss": 0.8123233318328857, | |
| "eval_runtime": 33.6692, | |
| "eval_samples_per_second": 8.435, | |
| "eval_steps_per_second": 1.069, | |
| "eval_wer": 0.34988317757009346, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 11.25, | |
| "learning_rate": 1.34e-06, | |
| "loss": 1.1967, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 11.25, | |
| "eval_loss": 0.8086321353912354, | |
| "eval_runtime": 33.5258, | |
| "eval_samples_per_second": 8.471, | |
| "eval_steps_per_second": 1.074, | |
| "eval_wer": 0.3501752336448598, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 11.88, | |
| "learning_rate": 6.733333333333334e-07, | |
| "loss": 1.2454, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 11.88, | |
| "eval_loss": 0.806648850440979, | |
| "eval_runtime": 33.3738, | |
| "eval_samples_per_second": 8.51, | |
| "eval_steps_per_second": 1.079, | |
| "eval_wer": 0.3490070093457944, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 6.666666666666667e-09, | |
| "loss": 1.1928, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "eval_loss": 0.8069162368774414, | |
| "eval_runtime": 33.1842, | |
| "eval_samples_per_second": 8.558, | |
| "eval_steps_per_second": 1.085, | |
| "eval_wer": 0.3490070093457944, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "step": 2000, | |
| "total_flos": 9.605345431463184e+18, | |
| "train_loss": 1.3434337348937988, | |
| "train_runtime": 8414.919, | |
| "train_samples_per_second": 3.803, | |
| "train_steps_per_second": 0.238 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 2000, | |
| "num_train_epochs": 13, | |
| "save_steps": 100, | |
| "total_flos": 9.605345431463184e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |