| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0009377197780729859, | |
| "eval_steps": 3, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00031257325935766194, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 5.6661, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00031257325935766194, | |
| "eval_loss": 7.102509498596191, | |
| "eval_runtime": 153.2085, | |
| "eval_samples_per_second": 35.168, | |
| "eval_steps_per_second": 4.399, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006251465187153239, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 5.1426, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0009377197780729859, | |
| "grad_norm": 3.7997171878814697, | |
| "learning_rate": 2e-05, | |
| "loss": 5.1073, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009377197780729859, | |
| "eval_loss": 7.102509498596191, | |
| "eval_runtime": 147.6213, | |
| "eval_samples_per_second": 36.499, | |
| "eval_steps_per_second": 4.566, | |
| "step": 3 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.7805294805450752e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |