{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0005141828777101723, "eval_steps": 3, "global_step": 3, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0001713942925700574, "grad_norm": 0.6748816967010498, "learning_rate": 2e-05, "loss": 5.2217, "step": 1 }, { "epoch": 0.0001713942925700574, "eval_loss": 1.2500425577163696, "eval_runtime": 159.8786, "eval_samples_per_second": 15.368, "eval_steps_per_second": 7.687, "step": 1 }, { "epoch": 0.0003427885851401148, "grad_norm": 0.48369231820106506, "learning_rate": 4e-05, "loss": 5.07, "step": 2 }, { "epoch": 0.0005141828777101723, "grad_norm": 0.6595766544342041, "learning_rate": 6e-05, "loss": 4.7583, "step": 3 }, { "epoch": 0.0005141828777101723, "eval_loss": 1.249487042427063, "eval_runtime": 159.9385, "eval_samples_per_second": 15.362, "eval_steps_per_second": 7.684, "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": 1274012762112000.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }