| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 13.693877551020408, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 4.999657487327031e-06, | |
| "loss": 0.0321, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 4.998629949308124e-06, | |
| "loss": 0.0265, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "learning_rate": 4.997602411289218e-06, | |
| "loss": 0.0244, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 6.84, | |
| "eval_loss": 0.19918830692768097, | |
| "eval_runtime": 422.7179, | |
| "eval_samples_per_second": 9.924, | |
| "eval_steps_per_second": 1.242, | |
| "eval_wer": 0.16014906363507714, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "learning_rate": 4.9965748732703115e-06, | |
| "loss": 0.0242, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 10.27, | |
| "learning_rate": 4.995547335251405e-06, | |
| "loss": 0.0228, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 12.33, | |
| "learning_rate": 4.994519797232499e-06, | |
| "loss": 0.0228, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 13.69, | |
| "eval_loss": 0.2058412730693817, | |
| "eval_runtime": 245.0508, | |
| "eval_samples_per_second": 17.119, | |
| "eval_steps_per_second": 2.142, | |
| "eval_wer": 0.15878107457898957, | |
| "step": 1000 | |
| } | |
| ], | |
| "max_steps": 730000, | |
| "num_train_epochs": 10000, | |
| "total_flos": 4.5875321808669204e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |