| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 100, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.5258620381355286, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 1.8946, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.42345377802848816, | |
| "learning_rate": 3.6e-05, | |
| "loss": 1.8109, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.4051591157913208, | |
| "learning_rate": 5.6000000000000006e-05, | |
| "loss": 1.5842, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.5201464295387268, | |
| "learning_rate": 7.6e-05, | |
| "loss": 1.4923, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 0.2786524295806885, | |
| "learning_rate": 9.6e-05, | |
| "loss": 1.2476, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.36792418360710144, | |
| "learning_rate": 0.000116, | |
| "loss": 1.1255, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7149165616300032.0, | |
| "train_batch_size": 6, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |