| { | |
| "best_metric": 33.43170709213317, | |
| "best_model_checkpoint": "./whisper-tiny-id/checkpoint-2000", | |
| "epoch": 9.0364, | |
| "eval_steps": 1000, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.4e-07, | |
| "loss": 2.0646, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.400000000000001e-07, | |
| "loss": 1.9267, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.44e-06, | |
| "loss": 1.6098, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.94e-06, | |
| "loss": 1.5123, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.4400000000000004e-06, | |
| "loss": 1.3693, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.9400000000000002e-06, | |
| "loss": 1.1379, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 3.44e-06, | |
| "loss": 1.0054, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 3.94e-06, | |
| "loss": 0.9672, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.440000000000001e-06, | |
| "loss": 0.9067, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 4.94e-06, | |
| "loss": 0.8923, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 5.4400000000000004e-06, | |
| "loss": 0.8273, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 5.94e-06, | |
| "loss": 0.8439, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 6.440000000000001e-06, | |
| "loss": 0.9079, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 6.9400000000000005e-06, | |
| "loss": 0.806, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 7.440000000000001e-06, | |
| "loss": 0.7395, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 7.94e-06, | |
| "loss": 0.7039, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8.44e-06, | |
| "loss": 0.6698, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 8.94e-06, | |
| "loss": 0.6674, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 9.440000000000001e-06, | |
| "loss": 0.6174, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 9.940000000000001e-06, | |
| "loss": 0.6379, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 9.951111111111111e-06, | |
| "loss": 0.6653, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 9.895555555555557e-06, | |
| "loss": 0.6247, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 9.84e-06, | |
| "loss": 0.5467, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 9.784444444444445e-06, | |
| "loss": 0.542, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 9.72888888888889e-06, | |
| "loss": 0.4957, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 9.673333333333334e-06, | |
| "loss": 0.4905, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 9.617777777777778e-06, | |
| "loss": 0.4642, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 9.562222222222223e-06, | |
| "loss": 0.4582, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 9.506666666666667e-06, | |
| "loss": 0.4847, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 9.451111111111112e-06, | |
| "loss": 0.472, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 9.395555555555556e-06, | |
| "loss": 0.4146, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 9.340000000000002e-06, | |
| "loss": 0.4009, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 9.284444444444444e-06, | |
| "loss": 0.376, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 9.22888888888889e-06, | |
| "loss": 0.362, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 9.173333333333334e-06, | |
| "loss": 0.3366, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 9.117777777777778e-06, | |
| "loss": 0.3615, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 9.062222222222224e-06, | |
| "loss": 0.3715, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 9.006666666666666e-06, | |
| "loss": 0.3495, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 8.951111111111112e-06, | |
| "loss": 0.3111, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 8.895555555555556e-06, | |
| "loss": 0.313, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "eval_loss": 0.5312389135360718, | |
| "eval_runtime": 582.6315, | |
| "eval_samples_per_second": 6.21, | |
| "eval_steps_per_second": 0.778, | |
| "eval_wer": 34.496910449137694, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 8.84e-06, | |
| "loss": 0.2908, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 8.784444444444446e-06, | |
| "loss": 0.274, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 8.72888888888889e-06, | |
| "loss": 0.2577, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 8.673333333333334e-06, | |
| "loss": 0.2692, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 8.617777777777778e-06, | |
| "loss": 0.2812, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 8.562222222222224e-06, | |
| "loss": 0.2723, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 8.506666666666668e-06, | |
| "loss": 0.247, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 8.451111111111112e-06, | |
| "loss": 0.2334, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 8.395555555555557e-06, | |
| "loss": 0.2206, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 8.34e-06, | |
| "loss": 0.2065, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 8.284444444444446e-06, | |
| "loss": 0.1984, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 8.22888888888889e-06, | |
| "loss": 0.1983, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 8.173333333333334e-06, | |
| "loss": 0.2097, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "learning_rate": 8.11777777777778e-06, | |
| "loss": 0.2196, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "learning_rate": 8.062222222222222e-06, | |
| "loss": 0.1885, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 8.006666666666667e-06, | |
| "loss": 0.1769, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 7.951111111111111e-06, | |
| "loss": 0.1682, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 7.895555555555557e-06, | |
| "loss": 0.1514, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 7.840000000000001e-06, | |
| "loss": 0.1455, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 7.784444444444445e-06, | |
| "loss": 0.1488, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 7.72888888888889e-06, | |
| "loss": 0.1563, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 7.673333333333333e-06, | |
| "loss": 0.1576, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 7.617777777777778e-06, | |
| "loss": 0.1515, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 7.562222222222223e-06, | |
| "loss": 0.1321, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 7.506666666666668e-06, | |
| "loss": 0.1301, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 7.451111111111111e-06, | |
| "loss": 0.1087, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 7.395555555555556e-06, | |
| "loss": 0.1093, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 7.340000000000001e-06, | |
| "loss": 0.1069, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 7.284444444444445e-06, | |
| "loss": 0.12, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "learning_rate": 7.22888888888889e-06, | |
| "loss": 0.122, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "learning_rate": 7.173333333333335e-06, | |
| "loss": 0.1116, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "learning_rate": 7.117777777777778e-06, | |
| "loss": 0.1051, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 7.062222222222223e-06, | |
| "loss": 0.0983, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 7.006666666666667e-06, | |
| "loss": 0.0806, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 6.951111111111112e-06, | |
| "loss": 0.0801, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 6.8955555555555565e-06, | |
| "loss": 0.0788, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 6.8400000000000014e-06, | |
| "loss": 0.0918, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 6.784444444444445e-06, | |
| "loss": 0.0906, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 6.7288888888888895e-06, | |
| "loss": 0.0814, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 6.6733333333333335e-06, | |
| "loss": 0.0745, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "eval_loss": 0.5521692633628845, | |
| "eval_runtime": 494.0388, | |
| "eval_samples_per_second": 7.323, | |
| "eval_steps_per_second": 0.917, | |
| "eval_wer": 33.43170709213317, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 5000, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 1000, | |
| "total_flos": 1.57294980808704e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |