| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.997824510514866, |
| "global_step": 688, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.29, |
| "learning_rate": 6.613023952095809e-05, |
| "loss": 5.1206, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 5.490269461077844e-05, |
| "loss": 3.0901, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.87, |
| "learning_rate": 4.36751497005988e-05, |
| "loss": 3.0224, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.16, |
| "learning_rate": 3.244760479041916e-05, |
| "loss": 2.9922, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.45, |
| "learning_rate": 2.1220059880239517e-05, |
| "loss": 2.9357, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.45, |
| "eval_loss": 2.9458744525909424, |
| "eval_runtime": 138.8724, |
| "eval_samples_per_second": 33.268, |
| "eval_steps_per_second": 4.162, |
| "eval_wer": 1.0, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.74, |
| "learning_rate": 9.99251497005988e-06, |
| "loss": 2.9153, |
| "step": 600 |
| }, |
| { |
| "epoch": 2.0, |
| "step": 688, |
| "total_flos": 2.0290377210557414e+18, |
| "train_loss": 3.289040254992108, |
| "train_runtime": 1292.4856, |
| "train_samples_per_second": 17.068, |
| "train_steps_per_second": 0.532 |
| } |
| ], |
| "max_steps": 688, |
| "num_train_epochs": 2, |
| "total_flos": 2.0290377210557414e+18, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
