{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0016886899987334826, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00016886899987334826, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.00016886899987334826, "eval_loss": NaN, "eval_runtime": 163.5075, "eval_samples_per_second": 15.253, "eval_steps_per_second": 7.627, "step": 1 }, { "epoch": 0.0003377379997466965, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0005066069996200448, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0005066069996200448, "eval_loss": NaN, "eval_runtime": 162.5826, "eval_samples_per_second": 15.34, "eval_steps_per_second": 7.67, "step": 3 }, { "epoch": 0.000675475999493393, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.0008443449993667413, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.0010132139992400895, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.0010132139992400895, "eval_loss": NaN, "eval_runtime": 162.564, "eval_samples_per_second": 15.342, "eval_steps_per_second": 7.671, "step": 6 }, { "epoch": 0.0011820829991134377, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.001350951998986786, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.0015198209988601342, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.0015198209988601342, "eval_loss": NaN, "eval_runtime": 162.5352, "eval_samples_per_second": 15.344, "eval_steps_per_second": 7.672, "step": 9 }, { "epoch": 0.0016886899987334826, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 10 } ], "logging_steps": 1, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 3, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1849564248145920.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }