{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0034812880765883376, "eval_steps": 3, "global_step": 3, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0011604293588627793, "grad_norm": 0.7944301962852478, "learning_rate": 2e-05, "loss": 0.7467, "step": 1 }, { "epoch": 0.0011604293588627793, "eval_loss": 0.8326185941696167, "eval_runtime": 71.8908, "eval_samples_per_second": 5.049, "eval_steps_per_second": 2.532, "step": 1 }, { "epoch": 0.0023208587177255585, "grad_norm": 0.3806622624397278, "learning_rate": 4e-05, "loss": 0.5817, "step": 2 }, { "epoch": 0.0034812880765883376, "grad_norm": 0.49611735343933105, "learning_rate": 6e-05, "loss": 0.7386, "step": 3 }, { "epoch": 0.0034812880765883376, "eval_loss": 0.8255924582481384, "eval_runtime": 72.0457, "eval_samples_per_second": 5.038, "eval_steps_per_second": 2.526, "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": 763750546145280.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }