| { |
| "best_metric": 2.747051954269409, |
| "best_model_checkpoint": "output/bill-wurtz/checkpoint-28", |
| "epoch": 1.0, |
| "global_step": 28, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.18, |
| "learning_rate": 0.00012668528006706036, |
| "loss": 2.3906, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 9.836442450346464e-05, |
| "loss": 2.3509, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 6.091923693931308e-05, |
| "loss": 2.3424, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.71, |
| "learning_rate": 2.582859959249092e-05, |
| "loss": 2.4842, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.89, |
| "learning_rate": 3.849603540845946e-06, |
| "loss": 2.52, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 2.747051954269409, |
| "eval_runtime": 0.9153, |
| "eval_samples_per_second": 21.851, |
| "eval_steps_per_second": 3.278, |
| "step": 28 |
| } |
| ], |
| "max_steps": 168, |
| "num_train_epochs": 6, |
| "total_flos": 29264707584000.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
