| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.23684210526315788, | |
| "eval_steps": 9, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02631578947368421, | |
| "eval_loss": 1.6184024810791016, | |
| "eval_runtime": 4.4294, | |
| "eval_samples_per_second": 14.449, | |
| "eval_steps_per_second": 1.806, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07894736842105263, | |
| "grad_norm": 26.1455020904541, | |
| "learning_rate": 3e-05, | |
| "loss": 6.2533, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.15789473684210525, | |
| "grad_norm": 20.71628761291504, | |
| "learning_rate": 6e-05, | |
| "loss": 6.0813, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.23684210526315788, | |
| "grad_norm": 17.294282913208008, | |
| "learning_rate": 9e-05, | |
| "loss": 4.9981, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.23684210526315788, | |
| "eval_loss": 1.035604476928711, | |
| "eval_runtime": 4.5385, | |
| "eval_samples_per_second": 14.102, | |
| "eval_steps_per_second": 1.763, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.2656345471778816e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |