| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.6, | |
| "eval_steps": 500, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5333333333333333, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.6602, | |
| "eval_samples_per_second": 60.835, | |
| "eval_steps_per_second": 2.409, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.5765, | |
| "eval_samples_per_second": 39.201, | |
| "eval_steps_per_second": 1.552, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "step": 3, | |
| "total_flos": 2.833014287331492e+17, | |
| "train_loss": 2741718698.6666665, | |
| "train_runtime": 750.1141, | |
| "train_samples_per_second": 7.675, | |
| "train_steps_per_second": 0.004 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 3, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.833014287331492e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |