| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.1, |
| "eval_steps": 500, |
| "global_step": 500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.02, |
| "learning_rate": 1.9600000000000002e-05, |
| "loss": 1.5719, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.04, |
| "learning_rate": 3.960000000000001e-05, |
| "loss": 0.3718, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 5.96e-05, |
| "loss": 0.3261, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 7.960000000000001e-05, |
| "loss": 0.3219, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 9.960000000000001e-05, |
| "loss": 0.3252, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.1, |
| "eval_combined_wer": 0.19175330812854444, |
| "eval_f1_score": 0.6148314606741573, |
| "eval_label_f1": 0.7577528089887641, |
| "eval_loss": 0.3395695686340332, |
| "eval_runtime": 98.1651, |
| "eval_samples_per_second": 10.187, |
| "eval_steps_per_second": 0.163, |
| "eval_wer": 0.11928060336491975, |
| "step": 500 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 5000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9223372036854775807, |
| "save_steps": 500, |
| "total_flos": 1.846946562048e+19, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
