{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0008163098712271178, "eval_steps": 8, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 4.081549356135589e-05, "eval_loss": NaN, "eval_runtime": 258.5474, "eval_samples_per_second": 39.9, "eval_steps_per_second": 19.95, "step": 1 }, { "epoch": 0.00012244648068406768, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.00024489296136813535, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.0003265239484908471, "eval_loss": NaN, "eval_runtime": 258.4875, "eval_samples_per_second": 39.909, "eval_steps_per_second": 19.955, "step": 8 }, { "epoch": 0.000367339442052203, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.0004897859227362707, "grad_norm": NaN, "learning_rate": 0.00019510565162951537, "loss": 0.0, "step": 12 }, { "epoch": 0.0006122324034203384, "grad_norm": NaN, "learning_rate": 0.00017071067811865476, "loss": 0.0, "step": 15 }, { "epoch": 0.0006530478969816942, "eval_loss": NaN, "eval_runtime": 260.067, "eval_samples_per_second": 39.667, "eval_steps_per_second": 19.833, "step": 16 }, { "epoch": 0.000734678884104406, "grad_norm": NaN, "learning_rate": 0.00013090169943749476, "loss": 0.0, "step": 18 } ], "logging_steps": 3, "max_steps": 30, "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": false }, "attributes": {} } }, "total_flos": 1306268836823040.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }