| { | |
| "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 | |
| } | |