diff --git a/configs/neox_arguments.md b/configs/neox_arguments.md index e83756ca..159a6e55 100644 --- a/configs/neox_arguments.md +++ b/configs/neox_arguments.md @@ -111,7 +111,7 @@ Logging Arguments - **git_hash**: str - Default = 3463ca4 + Default = 7ed7bc6 current git hash of repository @@ -1018,6 +1018,15 @@ Training Arguments +- **use_shared_fs**: bool + + Default = True + + Whether to use a shared filesystem for data loading. If False, local rank 0 on all nodes will preprocess the data, + otherwise only global rank 0 will preprocess the data. This is implemented in megatron/data/gpt2_dataset.py::_build_index_mappings. + + + - **train_data_paths**: list Default = None diff --git a/eval_tasks/eval_adapter.py b/eval_tasks/eval_adapter.py index 22280182..e0a32797 100644 --- a/eval_tasks/eval_adapter.py +++ b/eval_tasks/eval_adapter.py @@ -462,4 +462,5 @@ def run_eval_harness( eval_tasks=eval_tasks, num_fewshot=num_fewshot, bootstrap_iters=bootstrap_iters, + use_cache=False, )