| { |
| "best_metric": 1.8060141801834106, |
| "best_model_checkpoint": "output/mnogoznaal/checkpoint-42", |
| "epoch": 1.0, |
| "global_step": 42, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.12, |
| "learning_rate": 0.0001324579391569924, |
| "loss": 2.3988, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 0.00011888735840752609, |
| "loss": 2.1013, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 9.836442450346448e-05, |
| "loss": 2.0827, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 7.372648442002871e-05, |
| "loss": 1.9723, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.6, |
| "learning_rate": 4.837979503541197e-05, |
| "loss": 1.9794, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.71, |
| "learning_rate": 2.5828599592490882e-05, |
| "loss": 1.8512, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.83, |
| "learning_rate": 9.190657300387505e-06, |
| "loss": 1.971, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.95, |
| "learning_rate": 7.662053209561833e-07, |
| "loss": 1.8718, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.8060141801834106, |
| "eval_runtime": 4.3251, |
| "eval_samples_per_second": 21.04, |
| "eval_steps_per_second": 2.775, |
| "step": 42 |
| } |
| ], |
| "max_steps": 42, |
| "num_train_epochs": 1, |
| "total_flos": 43897061376000.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
