| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.75, | |
| "eval_steps": 1, | |
| "global_step": 4, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 1.7126013040542603, | |
| "eval_runtime": 37.4254, | |
| "eval_samples_per_second": 1.122, | |
| "eval_steps_per_second": 0.561, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.6999328136444092, | |
| "eval_runtime": 37.8712, | |
| "eval_samples_per_second": 1.109, | |
| "eval_steps_per_second": 0.555, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_loss": 1.6408756971359253, | |
| "eval_runtime": 37.9556, | |
| "eval_samples_per_second": 1.107, | |
| "eval_steps_per_second": 0.553, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_loss": 1.4504196643829346, | |
| "eval_runtime": 37.9832, | |
| "eval_samples_per_second": 1.106, | |
| "eval_steps_per_second": 0.553, | |
| "step": 4 | |
| } | |
| ], | |
| "logging_steps": 6, | |
| "max_steps": 4, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 1, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.349932924318515e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |