| { | |
| "best_metric": 46.55123943708554, | |
| "best_model_checkpoint": "/media/makhataei/Backups/Whisper-Small-Common-Voice/checkpoint-500", | |
| "epoch": 3.861003861003861, | |
| "eval_steps": 100, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.600000000000001e-06, | |
| "loss": 3.1025, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.600000000000001e-06, | |
| "loss": 1.3525, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 9.976884422110554e-06, | |
| "loss": 0.9564, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.95175879396985e-06, | |
| "loss": 0.7495, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 0.860159158706665, | |
| "eval_runtime": 1426.2695, | |
| "eval_samples_per_second": 6.062, | |
| "eval_steps_per_second": 0.606, | |
| "eval_wer": 58.07742554282218, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 9.926633165829147e-06, | |
| "loss": 0.5073, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 9.901507537688444e-06, | |
| "loss": 0.3749, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 9.87638190954774e-06, | |
| "loss": 0.3247, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 9.851256281407035e-06, | |
| "loss": 0.3059, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 0.5538379549980164, | |
| "eval_runtime": 1589.2333, | |
| "eval_samples_per_second": 5.44, | |
| "eval_steps_per_second": 0.544, | |
| "eval_wer": 55.22481850804518, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 9.826130653266333e-06, | |
| "loss": 0.2963, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 9.80100502512563e-06, | |
| "loss": 0.2882, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 9.775879396984925e-06, | |
| "loss": 0.2327, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 9.750753768844222e-06, | |
| "loss": 0.2002, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_loss": 0.5136818885803223, | |
| "eval_runtime": 1646.1357, | |
| "eval_samples_per_second": 5.252, | |
| "eval_steps_per_second": 0.525, | |
| "eval_wer": 52.46151047609599, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 9.725628140703518e-06, | |
| "loss": 0.1893, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 9.700502512562815e-06, | |
| "loss": 0.185, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 9.675376884422111e-06, | |
| "loss": 0.1847, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 9.650251256281408e-06, | |
| "loss": 0.1798, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "eval_loss": 0.5102902054786682, | |
| "eval_runtime": 1650.3734, | |
| "eval_samples_per_second": 5.239, | |
| "eval_steps_per_second": 0.524, | |
| "eval_wer": 51.65781945064576, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 9.625125628140705e-06, | |
| "loss": 0.1804, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 9.600000000000001e-06, | |
| "loss": 0.1807, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 9.574874371859298e-06, | |
| "loss": 0.1714, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 9.549748743718595e-06, | |
| "loss": 0.1678, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "eval_loss": 0.48063144087791443, | |
| "eval_runtime": 1482.5018, | |
| "eval_samples_per_second": 5.832, | |
| "eval_steps_per_second": 0.583, | |
| "eval_wer": 46.55123943708554, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 9.52462311557789e-06, | |
| "loss": 0.1542, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 9.499497487437188e-06, | |
| "loss": 0.0929, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 9.474371859296483e-06, | |
| "loss": 0.0936, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 9.44924623115578e-06, | |
| "loss": 0.0932, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_loss": 0.49363330006599426, | |
| "eval_runtime": 1993.4903, | |
| "eval_samples_per_second": 4.337, | |
| "eval_steps_per_second": 0.434, | |
| "eval_wer": 47.49549370772767, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 9.424120603015076e-06, | |
| "loss": 0.0936, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 9.398994974874373e-06, | |
| "loss": 0.0955, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 9.373869346733669e-06, | |
| "loss": 0.0871, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 9.348743718592966e-06, | |
| "loss": 0.0944, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "eval_loss": 0.5119881629943848, | |
| "eval_runtime": 1791.3192, | |
| "eval_samples_per_second": 4.827, | |
| "eval_steps_per_second": 0.483, | |
| "eval_wer": 48.91600932678474, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 9.323618090452262e-06, | |
| "loss": 0.0927, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 9.298492462311557e-06, | |
| "loss": 0.0964, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 9.273366834170856e-06, | |
| "loss": 0.1038, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 9.248241206030152e-06, | |
| "loss": 0.0493, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "eval_loss": 0.5198288559913635, | |
| "eval_runtime": 1878.4077, | |
| "eval_samples_per_second": 4.603, | |
| "eval_steps_per_second": 0.46, | |
| "eval_wer": 48.26114997271419, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 9.223115577889447e-06, | |
| "loss": 0.0501, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 9.197989949748744e-06, | |
| "loss": 0.0458, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 9.17286432160804e-06, | |
| "loss": 0.0492, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 9.147738693467337e-06, | |
| "loss": 0.0506, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "eval_loss": 0.5227376222610474, | |
| "eval_runtime": 1759.968, | |
| "eval_samples_per_second": 4.913, | |
| "eval_steps_per_second": 0.491, | |
| "eval_wer": 47.41280944585008, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 9.122613065326634e-06, | |
| "loss": 0.0494, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 9.09748743718593e-06, | |
| "loss": 0.051, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 9.072361809045227e-06, | |
| "loss": 0.0466, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 9.047236180904524e-06, | |
| "loss": 0.0482, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "eval_loss": 0.5255833268165588, | |
| "eval_runtime": 1701.3645, | |
| "eval_samples_per_second": 5.082, | |
| "eval_steps_per_second": 0.508, | |
| "eval_wer": 46.94977757933555, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 10000, | |
| "num_train_epochs": 39, | |
| "save_steps": 100, | |
| "total_flos": 1.61564536369152e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |