{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.1363636363636362, "eval_steps": 50, "global_step": 500, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.11, "eval_loss": 1.453033447265625, "eval_runtime": 11.4227, "eval_samples_per_second": 9.63, "eval_steps_per_second": 1.226, "step": 50 }, { "epoch": 0.23, "eval_loss": 1.4157308340072632, "eval_runtime": 11.406, "eval_samples_per_second": 9.644, "eval_steps_per_second": 1.227, "step": 100 }, { "epoch": 0.34, "eval_loss": 1.3941584825515747, "eval_runtime": 11.4049, "eval_samples_per_second": 9.645, "eval_steps_per_second": 1.228, "step": 150 }, { "epoch": 0.45, "eval_loss": 1.3821239471435547, "eval_runtime": 11.4018, "eval_samples_per_second": 9.648, "eval_steps_per_second": 1.228, "step": 200 }, { "epoch": 0.57, "eval_loss": 1.3709255456924438, "eval_runtime": 11.3981, "eval_samples_per_second": 9.651, "eval_steps_per_second": 1.228, "step": 250 }, { "epoch": 0.68, "eval_loss": 1.3664299249649048, "eval_runtime": 11.3976, "eval_samples_per_second": 9.651, "eval_steps_per_second": 1.228, "step": 300 }, { "epoch": 0.8, "eval_loss": 1.3568395376205444, "eval_runtime": 11.4, "eval_samples_per_second": 9.649, "eval_steps_per_second": 1.228, "step": 350 }, { "epoch": 0.91, "eval_loss": 1.3490984439849854, "eval_runtime": 11.3989, "eval_samples_per_second": 9.65, "eval_steps_per_second": 1.228, "step": 400 }, { "epoch": 1.02, "eval_loss": 1.3464051485061646, "eval_runtime": 11.3981, "eval_samples_per_second": 9.651, "eval_steps_per_second": 1.228, "step": 450 }, { "epoch": 1.14, "learning_rate": 0.0, "loss": 1.3927, "step": 500 }, { "epoch": 1.14, "eval_loss": 1.343943476676941, "eval_runtime": 11.3987, "eval_samples_per_second": 9.65, "eval_steps_per_second": 1.228, "step": 500 } ], "logging_steps": 500, "max_steps": 500, "num_train_epochs": 2, "save_steps": 50, "total_flos": 2.6741709176832e+16, "trial_name": null, "trial_params": null }