| { | |
| "best_metric": 0.2654845714569092, | |
| "best_model_checkpoint": "model\\checkpoint-20", | |
| "epoch": 1.1764705882352942, | |
| "eval_steps": 10, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5882352941176471, | |
| "grad_norm": 1.0573405027389526, | |
| "learning_rate": 0.00015, | |
| "loss": 1.3107, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5882352941176471, | |
| "eval_loss": 0.38725197315216064, | |
| "eval_runtime": 0.248, | |
| "eval_samples_per_second": 4.032, | |
| "eval_steps_per_second": 4.032, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.1764705882352942, | |
| "grad_norm": 0.7292496562004089, | |
| "learning_rate": 0.0, | |
| "loss": 0.4623, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.1764705882352942, | |
| "eval_loss": 0.2654845714569092, | |
| "eval_runtime": 0.276, | |
| "eval_samples_per_second": 3.623, | |
| "eval_steps_per_second": 3.623, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 291950319697920.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |