dwlee/ds_base_alpha

1{2  "best_metric": null,3  "best_model_checkpoint": null,4  "epoch": 1.991249392318911,5  "global_step": 448,6  "is_hyper_param_search": false,7  "is_local_process_zero": true,8  "is_world_process_zero": true,9  "log_history": [10    {11      "epoch": 0.0,12      "learning_rate": 0,13      "loss": 2.4259,14      "step": 115    },16    {17      "epoch": 1.99,18      "step": 448,19      "total_flos": 1883191577149440.0,20      "train_loss": 0.7372576573065349,21      "train_runtime": 28706.0932,22      "train_samples_per_second": 4.013,23      "train_steps_per_second": 0.01624    }25  ],26  "max_steps": 448,27  "num_train_epochs": 2,28  "total_flos": 1883191577149440.0,29  "trial_name": null,30  "trial_params": null31}32