| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0029668088262562583, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005933617652512516, | |
| "grad_norm": 2.288240432739258, | |
| "learning_rate": 1e-05, | |
| "loss": 4.9986, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005933617652512516, | |
| "eval_loss": 5.55634880065918, | |
| "eval_runtime": 225.5584, | |
| "eval_samples_per_second": 12.587, | |
| "eval_steps_per_second": 6.295, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011867235305025032, | |
| "grad_norm": 2.224644899368286, | |
| "learning_rate": 2e-05, | |
| "loss": 5.2257, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011867235305025032, | |
| "eval_loss": 5.459936618804932, | |
| "eval_runtime": 108.099, | |
| "eval_samples_per_second": 26.263, | |
| "eval_steps_per_second": 13.136, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0017800852957537549, | |
| "grad_norm": 2.041822910308838, | |
| "learning_rate": 3e-05, | |
| "loss": 5.1087, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0023734470610050065, | |
| "grad_norm": 1.9054675102233887, | |
| "learning_rate": 4e-05, | |
| "loss": 4.8574, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0023734470610050065, | |
| "eval_loss": 5.3499555587768555, | |
| "eval_runtime": 109.9787, | |
| "eval_samples_per_second": 25.814, | |
| "eval_steps_per_second": 12.912, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0029668088262562583, | |
| "grad_norm": 2.086639881134033, | |
| "learning_rate": 5e-05, | |
| "loss": 5.2496, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1371213272186880.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |