| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1787409931296431, | |
| "eval_steps": 200, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08937049656482154, | |
| "grad_norm": 1.7896469831466675, | |
| "learning_rate": 5.9523809523809524e-05, | |
| "loss": 0.5113, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.08937049656482154, | |
| "eval_loss": 0.2866540253162384, | |
| "eval_runtime": 106.9805, | |
| "eval_samples_per_second": 1.692, | |
| "eval_steps_per_second": 1.692, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.1787409931296431, | |
| "grad_norm": 1.647935390472412, | |
| "learning_rate": 9.999141366451437e-05, | |
| "loss": 0.198, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.1787409931296431, | |
| "eval_loss": 0.181967094540596, | |
| "eval_runtime": 106.8254, | |
| "eval_samples_per_second": 1.694, | |
| "eval_steps_per_second": 1.694, | |
| "step": 400 | |
| } | |
| ], | |
| "logging_steps": 200, | |
| "max_steps": 11185, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.107646385924608e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |