| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.0202729044834308, |
| "eval_steps": 10, |
| "global_step": 13, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0015594541910331384, |
| "eval_loss": 10.152922630310059, |
| "eval_runtime": 3.2878, |
| "eval_samples_per_second": 82.122, |
| "eval_steps_per_second": 41.061, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.007797270955165692, |
| "grad_norm": 2.428389549255371, |
| "learning_rate": 5e-05, |
| "loss": 10.1068, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.015594541910331383, |
| "grad_norm": 1.9053232669830322, |
| "learning_rate": 0.0001, |
| "loss": 10.1142, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.015594541910331383, |
| "eval_loss": 10.097267150878906, |
| "eval_runtime": 3.2915, |
| "eval_samples_per_second": 82.03, |
| "eval_steps_per_second": 41.015, |
| "step": 10 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 50, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 13, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 852261076992.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
