{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.8, "eval_steps": 500, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "entropy": 3.8219700306653976, "epoch": 0.16, "grad_norm": 0.7156862616539001, "learning_rate": 9e-05, "loss": 3.582442283630371, "mean_token_accuracy": 0.3453360106796026, "num_tokens": 1483.0, "step": 2 }, { "entropy": 3.5303100049495697, "epoch": 0.32, "grad_norm": 0.7453158497810364, "learning_rate": 7e-05, "loss": 3.2444372177124023, "mean_token_accuracy": 0.33470346685498953, "num_tokens": 2837.0, "step": 4 }, { "entropy": 3.6205725222826004, "epoch": 0.48, "grad_norm": 0.8344905376434326, "learning_rate": 5e-05, "loss": 3.3127710819244385, "mean_token_accuracy": 0.3520954065024853, "num_tokens": 4496.0, "step": 6 }, { "entropy": 3.540287271142006, "epoch": 0.64, "grad_norm": 0.6347673535346985, "learning_rate": 3e-05, "loss": 3.3623509407043457, "mean_token_accuracy": 0.35118098463863134, "num_tokens": 6172.0, "step": 8 }, { "entropy": 3.6203979402780533, "epoch": 0.8, "grad_norm": 0.5857006907463074, "learning_rate": 1e-05, "loss": 3.3508670330047607, "mean_token_accuracy": 0.35943709686398506, "num_tokens": 7494.0, "step": 10 } ], "logging_steps": 2, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 10, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 3930541369344.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }