| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 750, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_loss": 2.2818427085876465, |
| "eval_runtime": 12.7386, |
| "eval_samples_per_second": 78.502, |
| "eval_steps_per_second": 4.946, |
| "step": 250 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 23.603839874267578, |
| "learning_rate": 6.693333333333334e-06, |
| "loss": 2.7491, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 1.6762902736663818, |
| "eval_runtime": 14.5739, |
| "eval_samples_per_second": 68.616, |
| "eval_steps_per_second": 4.323, |
| "step": 500 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 750, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1175877900288000.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
