| { |
| "best_global_step": 20, |
| "best_metric": 2.1710100173950195, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 10, |
| "global_step": 21, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.48, |
| "grad_norm": 0.9073830246925354, |
| "learning_rate": 0.00013333333333333334, |
| "loss": 3.9875, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.48, |
| "eval_loss": 2.841432809829712, |
| "eval_runtime": 18.1998, |
| "eval_samples_per_second": 5.495, |
| "eval_steps_per_second": 1.374, |
| "step": 10 |
| }, |
| { |
| "epoch": 2.96, |
| "grad_norm": 0.7091864347457886, |
| "learning_rate": 2.2222222222222223e-05, |
| "loss": 2.4419, |
| "step": 20 |
| }, |
| { |
| "epoch": 2.96, |
| "eval_loss": 2.1710100173950195, |
| "eval_runtime": 16.3023, |
| "eval_samples_per_second": 6.134, |
| "eval_steps_per_second": 1.534, |
| "step": 20 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 21, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.6742946708504576e+16, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
