{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.034278180619644036, "eval_steps": 10, "global_step": 13, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0026367831245880024, "eval_loss": 9.952766418457031, "eval_runtime": 19.7234, "eval_samples_per_second": 8.112, "eval_steps_per_second": 4.056, "step": 1 }, { "epoch": 0.013183915622940013, "grad_norm": 7.932442665100098, "learning_rate": 5e-05, "loss": 9.1812, "step": 5 }, { "epoch": 0.026367831245880026, "grad_norm": 8.679454803466797, "learning_rate": 0.0001, "loss": 8.8656, "step": 10 }, { "epoch": 0.026367831245880026, "eval_loss": 7.980339050292969, "eval_runtime": 19.8797, "eval_samples_per_second": 8.048, "eval_steps_per_second": 4.024, "step": 10 } ], "logging_steps": 5, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 13, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 4210375092338688.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }