| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01, | |
| "eval_steps": 500, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0026666666666666666, | |
| "grad_norm": 35.846343994140625, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 1.0788, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005333333333333333, | |
| "grad_norm": 37.91228103637695, | |
| "learning_rate": 1.0666666666666667e-05, | |
| "loss": 0.9709, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008, | |
| "grad_norm": 33.33842468261719, | |
| "learning_rate": 5.333333333333334e-06, | |
| "loss": 0.9643, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "step": 75, | |
| "total_flos": 7693271040.0, | |
| "train_loss": 0.985154406229655, | |
| "train_runtime": 287.5291, | |
| "train_samples_per_second": 0.261, | |
| "train_steps_per_second": 0.261 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7693271040.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |