| { | |
| "best_metric": 34.55136995509666, | |
| "best_model_checkpoint": "drive/MyDrive/whisper-base-sv/checkpoint-2000", | |
| "epoch": 2.5873221216041395, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.400000000000001e-07, | |
| "loss": 2.5457, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.9200000000000003e-06, | |
| "loss": 1.8539, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 2.92e-06, | |
| "loss": 0.9435, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.920000000000001e-06, | |
| "loss": 0.6976, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.92e-06, | |
| "loss": 0.6091, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 0.6114889979362488, | |
| "eval_runtime": 1063.3892, | |
| "eval_samples_per_second": 4.767, | |
| "eval_steps_per_second": 0.596, | |
| "eval_wer": 42.31668952165847, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 5.92e-06, | |
| "loss": 0.5908, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 6.92e-06, | |
| "loss": 0.5695, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 7.92e-06, | |
| "loss": 0.5481, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 8.920000000000001e-06, | |
| "loss": 0.536, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 9.920000000000002e-06, | |
| "loss": 0.5032, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 0.5396197438240051, | |
| "eval_runtime": 1082.4366, | |
| "eval_samples_per_second": 4.683, | |
| "eval_steps_per_second": 0.586, | |
| "eval_wer": 39.05245892823533, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 9.86857142857143e-06, | |
| "loss": 0.5107, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 9.725714285714287e-06, | |
| "loss": 0.5179, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 9.582857142857143e-06, | |
| "loss": 0.507, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 9.440000000000001e-06, | |
| "loss": 0.4837, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 9.297142857142857e-06, | |
| "loss": 0.4776, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 0.5054066181182861, | |
| "eval_runtime": 1083.7563, | |
| "eval_samples_per_second": 4.677, | |
| "eval_steps_per_second": 0.585, | |
| "eval_wer": 37.20254900379124, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 9.154285714285715e-06, | |
| "loss": 0.3998, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 9.011428571428572e-06, | |
| "loss": 0.3516, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 8.86857142857143e-06, | |
| "loss": 0.3336, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 8.725714285714286e-06, | |
| "loss": 0.3486, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 8.582857142857144e-06, | |
| "loss": 0.3391, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "eval_loss": 0.4857306182384491, | |
| "eval_runtime": 1083.0435, | |
| "eval_samples_per_second": 4.68, | |
| "eval_steps_per_second": 0.585, | |
| "eval_wer": 35.86620418918556, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 8.44e-06, | |
| "loss": 0.3365, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 8.297142857142859e-06, | |
| "loss": 0.3378, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 8.154285714285715e-06, | |
| "loss": 0.328, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 8.011428571428573e-06, | |
| "loss": 0.3432, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 7.86857142857143e-06, | |
| "loss": 0.335, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "eval_loss": 0.4708064794540405, | |
| "eval_runtime": 1085.5679, | |
| "eval_samples_per_second": 4.669, | |
| "eval_steps_per_second": 0.584, | |
| "eval_wer": 35.80705009276438, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 7.725714285714286e-06, | |
| "loss": 0.3286, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 7.5828571428571444e-06, | |
| "loss": 0.3185, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 7.440000000000001e-06, | |
| "loss": 0.3337, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 7.297142857142858e-06, | |
| "loss": 0.3045, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 7.154285714285715e-06, | |
| "loss": 0.3239, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_loss": 0.45699021220207214, | |
| "eval_runtime": 1186.6678, | |
| "eval_samples_per_second": 4.272, | |
| "eval_steps_per_second": 0.534, | |
| "eval_wer": 34.75303164744158, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 6.440000000000001e-06, | |
| "loss": 0.2205, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 5.725714285714287e-06, | |
| "loss": 0.1952, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "eval_loss": 0.4576089084148407, | |
| "eval_runtime": 1097.6955, | |
| "eval_samples_per_second": 4.618, | |
| "eval_steps_per_second": 0.578, | |
| "eval_wer": 34.55136995509666, | |
| "step": 2000 | |
| } | |
| ], | |
| "max_steps": 4000, | |
| "num_train_epochs": 6, | |
| "total_flos": 2.07448211718144e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |