| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0326197757390418, | |
| "eval_steps": 1, | |
| "global_step": 4, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00815494393476045, | |
| "eval_loss": 1.6387360095977783, | |
| "eval_runtime": 6.2634, | |
| "eval_samples_per_second": 17.562, | |
| "eval_steps_per_second": 17.562, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0163098878695209, | |
| "eval_loss": 1.6256860494613647, | |
| "eval_runtime": 6.5091, | |
| "eval_samples_per_second": 16.9, | |
| "eval_steps_per_second": 16.9, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.024464831804281346, | |
| "eval_loss": 1.5953294038772583, | |
| "eval_runtime": 6.3157, | |
| "eval_samples_per_second": 17.417, | |
| "eval_steps_per_second": 17.417, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0326197757390418, | |
| "eval_loss": 1.5588785409927368, | |
| "eval_runtime": 6.1453, | |
| "eval_samples_per_second": 17.9, | |
| "eval_steps_per_second": 17.9, | |
| "step": 4 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 1, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 196877444382720.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |