| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.444043321299639, |
| "eval_steps": 200, |
| "global_step": 800, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.36, |
| "grad_norm": 1.2521377801895142, |
| "learning_rate": 1.8867924528301888e-05, |
| "loss": 0.3063, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.36, |
| "eval_loss": 0.15049202740192413, |
| "eval_runtime": 17.5933, |
| "eval_samples_per_second": 7.048, |
| "eval_steps_per_second": 0.455, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 1.2193596363067627, |
| "learning_rate": 1.2578616352201259e-05, |
| "loss": 0.1466, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.72, |
| "eval_loss": 0.13752172887325287, |
| "eval_runtime": 19.0508, |
| "eval_samples_per_second": 6.509, |
| "eval_steps_per_second": 0.42, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.08, |
| "grad_norm": 1.3789132833480835, |
| "learning_rate": 6.289308176100629e-06, |
| "loss": 0.1385, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.08, |
| "eval_loss": 0.13329480588436127, |
| "eval_runtime": 20.1425, |
| "eval_samples_per_second": 6.156, |
| "eval_steps_per_second": 0.397, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.44, |
| "grad_norm": 1.421270728111267, |
| "learning_rate": 0.0, |
| "loss": 0.1257, |
| "step": 800 |
| }, |
| { |
| "epoch": 1.44, |
| "eval_loss": 0.13202674686908722, |
| "eval_runtime": 20.6481, |
| "eval_samples_per_second": 6.005, |
| "eval_steps_per_second": 0.387, |
| "step": 800 |
| } |
| ], |
| "logging_steps": 200, |
| "max_steps": 800, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 200, |
| "total_flos": 8758226453004288.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
