| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "entropy": 1.0464510180801154, | |
| "epoch": 0.16666666666666666, | |
| "grad_norm": 0.1865234375, | |
| "learning_rate": 0.00019305858028153186, | |
| "loss": 1.4016, | |
| "mean_token_accuracy": 0.724494147747755, | |
| "num_tokens": 249190.0, | |
| "step": 50 | |
| }, | |
| { | |
| "entropy": 0.8066404972411693, | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 0.15625, | |
| "learning_rate": 0.00016010811472830252, | |
| "loss": 0.9492, | |
| "mean_token_accuracy": 0.8130347758531571, | |
| "num_tokens": 483598.0, | |
| "step": 100 | |
| }, | |
| { | |
| "entropy": 0.733450262453407, | |
| "epoch": 0.5, | |
| "grad_norm": 0.1875, | |
| "learning_rate": 0.00010935595884991178, | |
| "loss": 0.8847, | |
| "mean_token_accuracy": 0.8233503015711904, | |
| "num_tokens": 730834.0, | |
| "step": 150 | |
| }, | |
| { | |
| "entropy": 0.7603415619581938, | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.1728515625, | |
| "learning_rate": 5.58329311367626e-05, | |
| "loss": 0.9069, | |
| "mean_token_accuracy": 0.8193877371773124, | |
| "num_tokens": 969912.0, | |
| "step": 200 | |
| }, | |
| { | |
| "entropy": 0.7501469237729907, | |
| "epoch": 0.8333333333333334, | |
| "grad_norm": 0.1484375, | |
| "learning_rate": 1.5390474757906446e-05, | |
| "loss": 0.8798, | |
| "mean_token_accuracy": 0.8209915024042129, | |
| "num_tokens": 1221026.0, | |
| "step": 250 | |
| }, | |
| { | |
| "entropy": 0.7552332373522223, | |
| "epoch": 1.0, | |
| "grad_norm": 0.166015625, | |
| "learning_rate": 6.075410565697937e-09, | |
| "loss": 0.9257, | |
| "mean_token_accuracy": 0.8195931713283062, | |
| "num_tokens": 1473279.0, | |
| "step": 300 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 300, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1328849257877504e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |