| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.7451236844062805, | |
| "eval_runtime": 1.2183, | |
| "eval_samples_per_second": 82.081, | |
| "eval_steps_per_second": 10.67, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.8544089794158936, | |
| "eval_runtime": 1.1946, | |
| "eval_samples_per_second": 83.713, | |
| "eval_steps_per_second": 10.883, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.0189313888549805, | |
| "eval_runtime": 1.2024, | |
| "eval_samples_per_second": 83.167, | |
| "eval_steps_per_second": 10.812, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 39, | |
| "total_flos": 2667373869924352.0, | |
| "train_loss": 0.4380333729279347, | |
| "train_runtime": 62.4476, | |
| "train_samples_per_second": 4.804, | |
| "train_steps_per_second": 0.625 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 39, | |
| "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": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2667373869924352.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |