| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 6, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2e-05, | |
| "loss": 2.0792, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.8090169943749477e-05, | |
| "loss": 2.0873, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.3090169943749475e-05, | |
| "loss": 1.5322, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 0.0, | |
| "learning_rate": 6.909830056250527e-06, | |
| "loss": 1.4408, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.9098300562505266e-06, | |
| "loss": 1.5425, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.4849, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 6, | |
| "total_flos": 0.0, | |
| "train_loss": 1.694474995136261, | |
| "train_runtime": 211.4693, | |
| "train_samples_per_second": 58.108, | |
| "train_steps_per_second": 0.028 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 6, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |