{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.003920287487749101, "eval_steps": 3, "global_step": 3, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0013067624959163672, "grad_norm": 1.7657692432403564, "learning_rate": 2e-05, "loss": 6.7344, "step": 1 }, { "epoch": 0.0013067624959163672, "eval_loss": 6.717371940612793, "eval_runtime": 16.7474, "eval_samples_per_second": 19.287, "eval_steps_per_second": 9.673, "step": 1 }, { "epoch": 0.0026135249918327343, "grad_norm": 1.6176117658615112, "learning_rate": 4e-05, "loss": 6.7046, "step": 2 }, { "epoch": 0.003920287487749101, "grad_norm": 1.6528016328811646, "learning_rate": 6e-05, "loss": 5.8803, "step": 3 }, { "epoch": 0.003920287487749101, "eval_loss": 6.710137844085693, "eval_runtime": 14.7271, "eval_samples_per_second": 21.932, "eval_steps_per_second": 11.0, "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": 958449825349632.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }