| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 57, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.17777777777777778, | |
| "grad_norm": 0.5156543850898743, | |
| "learning_rate": 0.00018823529411764707, | |
| "loss": 1.9626, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 0.9887303709983826, | |
| "learning_rate": 0.00014901960784313728, | |
| "loss": 1.7144, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 0.8708482980728149, | |
| "learning_rate": 0.00010980392156862746, | |
| "loss": 1.3437, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.5636587142944336, | |
| "learning_rate": 7.058823529411765e-05, | |
| "loss": 1.3288, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.5663055181503296, | |
| "learning_rate": 3.137254901960784e-05, | |
| "loss": 1.2226, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.2128527164459229, | |
| "eval_runtime": 16.499, | |
| "eval_samples_per_second": 1.515, | |
| "eval_steps_per_second": 1.515, | |
| "step": 57 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 57, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1226078506598400.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |