{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 10, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.1, "grad_norm": 1.466568112373352, "learning_rate": 1e-05, "loss": 2.4115, "step": 1 }, { "epoch": 0.2, "grad_norm": 1.3858046531677246, "learning_rate": 9e-06, "loss": 2.34, "step": 2 }, { "epoch": 0.3, "grad_norm": 1.3575129508972168, "learning_rate": 8.000000000000001e-06, "loss": 2.3225, "step": 3 }, { "epoch": 0.4, "grad_norm": 1.363984227180481, "learning_rate": 7e-06, "loss": 2.3698, "step": 4 }, { "epoch": 0.5, "grad_norm": 1.3000918626785278, "learning_rate": 6e-06, "loss": 2.3159, "step": 5 }, { "epoch": 0.6, "grad_norm": 1.2665246725082397, "learning_rate": 5e-06, "loss": 2.329, "step": 6 }, { "epoch": 0.7, "grad_norm": 1.1995117664337158, "learning_rate": 4.000000000000001e-06, "loss": 2.2944, "step": 7 }, { "epoch": 0.8, "grad_norm": 1.1621100902557373, "learning_rate": 3e-06, "loss": 2.2407, "step": 8 }, { "epoch": 0.9, "grad_norm": 1.167473554611206, "learning_rate": 2.0000000000000003e-06, "loss": 2.2982, "step": 9 }, { "epoch": 1.0, "grad_norm": 1.0859638452529907, "learning_rate": 1.0000000000000002e-06, "loss": 2.1708, "step": 10 }, { "epoch": 1.0, "eval_loss": 2.2755022048950195, "eval_runtime": 1.1517, "eval_samples_per_second": 1.737, "eval_steps_per_second": 0.868, "step": 10 } ], "logging_steps": 1.0, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 0, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 7989451657576448.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }