{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.00020479213598197828, "eval_steps": 3, "global_step": 3, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 6.82640453273261e-05, "grad_norm": 1.0312207450624555e-05, "learning_rate": 2e-05, "loss": 46.0, "step": 1 }, { "epoch": 6.82640453273261e-05, "eval_loss": 11.5, "eval_runtime": 219.9365, "eval_samples_per_second": 28.044, "eval_steps_per_second": 14.022, "step": 1 }, { "epoch": 0.0001365280906546522, "grad_norm": 1.0248472790408414e-05, "learning_rate": 4e-05, "loss": 46.0, "step": 2 }, { "epoch": 0.00020479213598197828, "grad_norm": 1.0351810487918556e-05, "learning_rate": 6e-05, "loss": 46.0, "step": 3 }, { "epoch": 0.00020479213598197828, "eval_loss": 11.5, "eval_runtime": 234.4844, "eval_samples_per_second": 26.305, "eval_steps_per_second": 13.152, "step": 3 } ], "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": false }, "attributes": {} } }, "total_flos": 74710794240.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }