{ "best_global_step": 10, "best_metric": 3.068567991256714, "best_model_checkpoint": "/tmp/checkpoints_/job_fa60d36f-e0b6-414f-8ec4-8d27b9463040/checkpoint-10", "epoch": 1.0, "eval_steps": 50, "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": 4.2067131996154785, "learning_rate": 0.0, "loss": 3.324939250946045, "step": 1 }, { "epoch": 0.2, "grad_norm": 4.331752777099609, "learning_rate": 6e-06, "loss": 3.4889280796051025, "step": 2 }, { "epoch": 0.3, "grad_norm": 3.86865496635437, "learning_rate": 1.2e-05, "loss": 3.312532901763916, "step": 3 }, { "epoch": 0.4, "grad_norm": 4.405333995819092, "learning_rate": 1.8e-05, "loss": 3.5451769828796387, "step": 4 }, { "epoch": 0.5, "grad_norm": 4.006685256958008, "learning_rate": 2.4e-05, "loss": 3.31204891204834, "step": 5 }, { "epoch": 0.6, "grad_norm": 4.052533149719238, "learning_rate": 3e-05, "loss": 3.3880691528320312, "step": 6 }, { "epoch": 0.7, "grad_norm": 3.28196382522583, "learning_rate": 2.4e-05, "loss": 3.151078224182129, "step": 7 }, { "epoch": 0.8, "grad_norm": 3.2284908294677734, "learning_rate": 1.8e-05, "loss": 3.2133283615112305, "step": 8 }, { "epoch": 0.9, "grad_norm": 2.721409797668457, "learning_rate": 1.2e-05, "loss": 3.000295400619507, "step": 9 }, { "epoch": 1.0, "grad_norm": 2.67348051071167, "learning_rate": 6e-06, "loss": 3.0001535415649414, "step": 10 }, { "epoch": 1.0, "eval_loss": 3.068567991256714, "eval_runtime": 0.3622, "eval_samples_per_second": 13.803, "eval_steps_per_second": 5.521, "step": 10 } ], "logging_steps": 1, "max_steps": 10, "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": 15401254652160.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }