| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.3980000000000001, | |
| "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": 4.4e-06, | |
| "loss": 0.6563, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.4e-06, | |
| "loss": 0.303, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2222, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2058, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2137, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1e-05, | |
| "loss": 0.209, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1859, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1716, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1746, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1996, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1e-05, | |
| "loss": 0.192, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1707, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1824, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1671, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1401, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1568, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1499, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1665, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1882, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1995, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1972, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1e-05, | |
| "loss": 0.187, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1756, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1761, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1401, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 1e-05, | |
| "loss": 0.117, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0835, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0784, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0861, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0844, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0691, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0685, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0676, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0788, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 1e-05, | |
| "loss": 0.076, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0715, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0762, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0644, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0605, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0637, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_loss": 0.21794496476650238, | |
| "eval_runtime": 2944.9179, | |
| "eval_samples_per_second": 3.27, | |
| "eval_steps_per_second": 0.204, | |
| "eval_wer": 12.883608587437623, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "step": 1000, | |
| "total_flos": 9.23300129783808e+18, | |
| "train_loss": 0.15691602289676665, | |
| "train_runtime": 6554.2706, | |
| "train_samples_per_second": 4.882, | |
| "train_steps_per_second": 0.153 | |
| } | |
| ], | |
| "max_steps": 1000, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 9.23300129783808e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |