| { | |
| "best_metric": 20.488827942244093, | |
| "best_model_checkpoint": "./swedish_asr_model_training/checkpoint-1000", | |
| "epoch": 1.2936610608020698, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.800000000000001e-07, | |
| "loss": 0.2028, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.800000000000001e-07, | |
| "loss": 0.1848, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.48e-06, | |
| "loss": 0.1794, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.9600000000000003e-06, | |
| "loss": 0.1622, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.46e-06, | |
| "loss": 0.1571, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 2.96e-06, | |
| "loss": 0.1529, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.46e-06, | |
| "loss": 0.1411, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.96e-06, | |
| "loss": 0.1357, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.4600000000000005e-06, | |
| "loss": 0.1233, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.960000000000001e-06, | |
| "loss": 0.1235, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 5.460000000000001e-06, | |
| "loss": 0.1263, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 5.9600000000000005e-06, | |
| "loss": 0.09, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 6.460000000000001e-06, | |
| "loss": 0.1032, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 6.96e-06, | |
| "loss": 0.0935, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 7.4600000000000006e-06, | |
| "loss": 0.0901, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 7.960000000000002e-06, | |
| "loss": 0.1006, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 8.46e-06, | |
| "loss": 0.0912, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 8.96e-06, | |
| "loss": 0.0861, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 9.460000000000001e-06, | |
| "loss": 0.0748, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 9.960000000000001e-06, | |
| "loss": 0.0894, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 9.54e-06, | |
| "loss": 0.073, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 9.040000000000002e-06, | |
| "loss": 0.0749, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 8.540000000000001e-06, | |
| "loss": 0.0762, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 8.040000000000001e-06, | |
| "loss": 0.0844, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 7.540000000000001e-06, | |
| "loss": 0.0872, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 7.04e-06, | |
| "loss": 0.0944, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 6.540000000000001e-06, | |
| "loss": 0.0773, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 6.040000000000001e-06, | |
| "loss": 0.0832, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 5.540000000000001e-06, | |
| "loss": 0.0872, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 5.04e-06, | |
| "loss": 0.0801, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.540000000000001e-06, | |
| "loss": 0.0821, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 4.04e-06, | |
| "loss": 0.0284, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.54e-06, | |
| "loss": 0.0351, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.04e-06, | |
| "loss": 0.0291, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 2.5400000000000002e-06, | |
| "loss": 0.0284, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 2.04e-06, | |
| "loss": 0.0335, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 1.54e-06, | |
| "loss": 0.0287, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 1.04e-06, | |
| "loss": 0.0333, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 5.4e-07, | |
| "loss": 0.0334, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 4e-08, | |
| "loss": 0.0342, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "eval_loss": 0.29397502541542053, | |
| "eval_runtime": 1052.6737, | |
| "eval_samples_per_second": 4.815, | |
| "eval_steps_per_second": 0.602, | |
| "eval_wer": 20.488827942244093, | |
| "step": 1000 | |
| } | |
| ], | |
| "max_steps": 1000, | |
| "num_train_epochs": 2, | |
| "total_flos": 4.61505772191744e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |