| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.42874062799783486, |
| "global_step": 10000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.21, |
| "learning_rate": 0.00046142663609645895, |
| "loss": 1.5427, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.21, |
| "eval_loss": 1.038360357284546, |
| "eval_runtime": 3085.6496, |
| "eval_samples_per_second": 242.166, |
| "eval_steps_per_second": 15.136, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 0.0003248949212697779, |
| "loss": 1.0429, |
| "step": 10000 |
| }, |
| { |
| "epoch": 0.43, |
| "eval_loss": 0.9611759781837463, |
| "eval_runtime": 16191.2875, |
| "eval_samples_per_second": 46.151, |
| "eval_steps_per_second": 2.884, |
| "step": 10000 |
| } |
| ], |
| "max_steps": 23324, |
| "num_train_epochs": 1, |
| "total_flos": 4.186787807232e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
