{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.015888778550148957, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0031777557100297915, "grad_norm": 0.474895715713501, "learning_rate": 1e-05, "loss": 2.3103, "step": 1 }, { "epoch": 0.0031777557100297915, "eval_loss": 2.449401617050171, "eval_runtime": 49.9052, "eval_samples_per_second": 10.62, "eval_steps_per_second": 5.31, "step": 1 }, { "epoch": 0.006355511420059583, "grad_norm": 0.46380510926246643, "learning_rate": 2e-05, "loss": 2.4732, "step": 2 }, { "epoch": 0.006355511420059583, "eval_loss": 2.4418368339538574, "eval_runtime": 4.7085, "eval_samples_per_second": 112.562, "eval_steps_per_second": 56.281, "step": 2 }, { "epoch": 0.009533267130089375, "grad_norm": 0.5559589266777039, "learning_rate": 3e-05, "loss": 2.6117, "step": 3 }, { "epoch": 0.012711022840119166, "grad_norm": 0.5444060564041138, "learning_rate": 4e-05, "loss": 2.1045, "step": 4 }, { "epoch": 0.012711022840119166, "eval_loss": 2.43166184425354, "eval_runtime": 6.1581, "eval_samples_per_second": 86.066, "eval_steps_per_second": 43.033, "step": 4 }, { "epoch": 0.015888778550148957, "grad_norm": 0.4515919089317322, "learning_rate": 5e-05, "loss": 2.3747, "step": 5 } ], "logging_steps": 1, "max_steps": 5, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 2, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 667513805340672.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }