| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.018214936247723135, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0036429872495446266, | |
| "grad_norm": 2.274423122406006, | |
| "learning_rate": 1e-05, | |
| "loss": 2.0596, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0036429872495446266, | |
| "eval_loss": 2.859105110168457, | |
| "eval_runtime": 159.8665, | |
| "eval_samples_per_second": 2.896, | |
| "eval_steps_per_second": 1.451, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007285974499089253, | |
| "grad_norm": 2.203864336013794, | |
| "learning_rate": 2e-05, | |
| "loss": 2.1696, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007285974499089253, | |
| "eval_loss": 2.82100248336792, | |
| "eval_runtime": 16.3027, | |
| "eval_samples_per_second": 28.4, | |
| "eval_steps_per_second": 14.231, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01092896174863388, | |
| "grad_norm": 2.344345808029175, | |
| "learning_rate": 3e-05, | |
| "loss": 2.2768, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.014571948998178506, | |
| "grad_norm": 2.500903844833374, | |
| "learning_rate": 4e-05, | |
| "loss": 2.3183, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.014571948998178506, | |
| "eval_loss": 2.722424268722534, | |
| "eval_runtime": 16.3267, | |
| "eval_samples_per_second": 28.359, | |
| "eval_steps_per_second": 14.21, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.018214936247723135, | |
| "grad_norm": 2.416565418243408, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9803, | |
| "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": 5828828819619840.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |