diff --git a/.github/workflows/regression_tests.yml b/.github/workflows/regression_tests.yml
index ce60313d6..2594e6dad 100644
--- a/.github/workflows/regression_tests.yml
+++ b/.github/workflows/regression_tests.yml
@@ -116,7 +116,7 @@ jobs:
     - name: Run containerized workload
       run: |
         docker pull us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_jax_${{ github.head_ref || github.ref_name }}  
-        docker run  -v $HOME/data/:/data/ -v $HOME/experiment_runs/:/experiment_runs -v $HOME/experiment_runs/logs:/logs --gpus all --ipc=host us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_jax_${{ github.head_ref || github.ref_name }}  -d fineweb_edu_10B -f jax -s algorithms/archived_paper_baselines/adamw/jax/submission.py -w finewebedu_lm -t algorithms/archived_paper_baselines/adamw/tuning_search_space.json -e tests/regression_tests/adamw -m 10 -c False -o True -r false --data_bucket mlcommons-data --logs_bucket mlcommons-runs --data_bucket mlcommons-data --logs_bucket mlcommons-runs    
+        docker run  -v $HOME/data/:/data/ -v $HOME/experiment_runs/:/experiment_runs -v $HOME/experiment_runs/logs:/logs --gpus all --ipc=host us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_jax_${{ github.head_ref || github.ref_name }}  -d finewebedu -f jax -s algorithms/archived_paper_baselines/adamw/jax/submission.py -w finewebedu_lm -t algorithms/archived_paper_baselines/adamw/tuning_search_space.json -e tests/regression_tests/adamw -m 10 -c False -o True -r false --data_bucket mlcommons-data --logs_bucket mlcommons-runs --data_bucket mlcommons-data --logs_bucket mlcommons-runs    
   fastmri_pytorch:
     runs-on: self-hosted
     needs: build_and_push_pytorch_docker_image
@@ -198,4 +198,4 @@ jobs:
     - name: Run containerized workload
       run: |
         docker pull us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_pytorch_${{ github.head_ref || github.ref_name }}  
-        docker run  -v $HOME/data/:/data/ -v $HOME/experiment_runs/:/experiment_runs -v $HOME/experiment_runs/logs:/logs --gpus all --ipc=host us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_pytorch_${{ github.head_ref || github.ref_name }}  -d fineweb_edu_10B -f pytorch -s algorithms/archived_paper_baselines/adamw/pytorch/submission.py -w finewebedu_lm -t algorithms/archived_paper_baselines/adamw/tuning_search_space.json -e tests/regression_tests/adamw -m 10 -c False -o True -r false --data_bucket mlcommons-data --logs_bucket mlcommons-runs --data_bucket mlcommons-data --logs_bucket mlcommons-runs     
+        docker run  -v $HOME/data/:/data/ -v $HOME/experiment_runs/:/experiment_runs -v $HOME/experiment_runs/logs:/logs --gpus all --ipc=host us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_pytorch_${{ github.head_ref || github.ref_name }}  -d finewebedu -f pytorch -s algorithms/archived_paper_baselines/adamw/pytorch/submission.py -w finewebedu_lm -t algorithms/archived_paper_baselines/adamw/tuning_search_space.json -e tests/regression_tests/adamw -m 10 -c False -o True -r false --data_bucket mlcommons-data --logs_bucket mlcommons-runs --data_bucket mlcommons-data --logs_bucket mlcommons-runs     
diff --git a/algoperf/_version.py b/algoperf/_version.py
new file mode 100644
index 000000000..397ff039f
--- /dev/null
+++ b/algoperf/_version.py
@@ -0,0 +1,34 @@
+# file generated by setuptools-scm
+# don't change, don't track in version control
+
+__all__ = [
+    "__version__",
+    "__version_tuple__",
+    "version",
+    "version_tuple",
+    "__commit_id__",
+    "commit_id",
+]
+
+TYPE_CHECKING = False
+if TYPE_CHECKING:
+    from typing import Tuple
+    from typing import Union
+
+    VERSION_TUPLE = Tuple[Union[int, str], ...]
+    COMMIT_ID = Union[str, None]
+else:
+    VERSION_TUPLE = object
+    COMMIT_ID = object
+
+version: str
+__version__: str
+__version_tuple__: VERSION_TUPLE
+version_tuple: VERSION_TUPLE
+commit_id: COMMIT_ID
+__commit_id__: COMMIT_ID
+
+__version__ = version = '1.0.1'
+__version_tuple__ = version_tuple = (1, 0, 1)
+
+__commit_id__ = commit_id = 'ga673f5835'
diff --git a/algoperf/workloads/finewebedu_lm/input_pipeline.py b/algoperf/workloads/finewebedu_lm/input_pipeline.py
index 3007371fc..5798f6638 100644
--- a/algoperf/workloads/finewebedu_lm/input_pipeline.py
+++ b/algoperf/workloads/finewebedu_lm/input_pipeline.py
@@ -6,6 +6,7 @@
 
 import jax
 import tensorflow as tf
+import datasets as hf_datasets
 
 from algoperf import data_utils
 
@@ -83,7 +84,8 @@ def get_lm_dataset(
   shuffle_seed = jax.random.randint(data_rng, (), -(2**31), 2**31 - 1)
 
   data_dir = os.path.join(data_dir, TFDS_SPLIT_NAME[split])
-  tokens_ds = tf.data.Dataset.load(data_dir)
+  ds = hf_datasets.load_from_disk(data_dir)
+  tokens_ds = ds.to_tf_dataset()
 
   # tokens
   tokens_ds = tokens_ds.flat_map(tf.data.Dataset.from_tensor_slices)
diff --git a/dataset/dataset_setup.py b/dataset/dataset_setup.py
index 30bd9dec6..9374b11ea 100644
--- a/dataset/dataset_setup.py
+++ b/dataset/dataset_setup.py
@@ -782,7 +782,7 @@ def download_finewebedu(
 ):
   """Download FineWebEdu-10B."""
 
-  data_dir = os.path.join(data_dir, 'fineweb_edu_10B')
+  data_dir = os.path.join(data_dir, 'finewebedu')
   _maybe_mkdir(data_dir)
   _maybe_mkdir(tmp_dir)
 
diff --git a/docker/scripts/startup.sh b/docker/scripts/startup.sh
index 1cd676d2a..b4a7111f2 100644
--- a/docker/scripts/startup.sh
+++ b/docker/scripts/startup.sh
@@ -174,7 +174,7 @@ fi
 
 # Check if arguments are valid
 VALID_DATASETS=("criteo1tb" "imagenet"  "fastmri" "ogbg" "librispeech" \
-                "wmt" "mnist" "fineweb_edu_10B")
+                "wmt" "mnist" "finewebedu")
 VALID_WORKLOADS=("criteo1tb" "imagenet_resnet" "imagenet_resnet_silu" "imagenet_resnet_gelu" \
                  "imagenet_resnet_large_bn_init" "imagenet_vit" "imagenet_vit_glu" \
                  "imagenet_vit_post_ln" "imagenet_vit_map" "fastmri" "ogbg" \
diff --git a/scoring/utils/slurm/make_job_config.py b/scoring/utils/slurm/make_job_config.py
index f796c6caf..787d9a152 100644
--- a/scoring/utils/slurm/make_job_config.py
+++ b/scoring/utils/slurm/make_job_config.py
@@ -67,7 +67,7 @@
   'librispeech_deepspeech': {'dataset': 'librispeech'},
   'criteo1tb': {'dataset': 'criteo1tb'},
   'librispeech_conformer': {'dataset': 'librispeech'},
-  'finewebedu_lm': {'dataset': 'fineweb_edu_10B'},
+  'finewebedu_lm': {'dataset': 'finewebedu'},
 }
 
 RULESET_CONFIGS = {
diff --git a/scoring/utils/slurm/run_jobs.sh b/scoring/utils/slurm/run_jobs.sh
index 1047b31c0..85272cc23 100644
--- a/scoring/utils/slurm/run_jobs.sh
+++ b/scoring/utils/slurm/run_jobs.sh
@@ -91,6 +91,7 @@ DOCKER_CMD=(
   docker run
   -v /opt/data/:/data/
   -v "$HOME/experiment_runs:/experiment_runs"
+  -v "$HOME/algorithmic-efficiency/:/algorithmic-efficiency/"
   -v "$HOME/submissions_algorithms/:/algorithmic-efficiency/submissions_algorithms"
   -v "$HOME/algorithmic-efficiency/docker/scripts/startup.sh:/algorithmic-efficiency/docker/scripts/startup.sh"
   --gpus all
diff --git a/scoring/utils/workload_metadata_external_tuning.json b/scoring/utils/workload_metadata_external_tuning.json
index 0ba0d99ee..f4d268683 100644
--- a/scoring/utils/workload_metadata_external_tuning.json
+++ b/scoring/utils/workload_metadata_external_tuning.json
@@ -33,6 +33,6 @@
   },
   "finewebedu_lm" : {
     "max_steps": 55000,
-    "dataset":"fineweb_edu_10B"
+    "dataset":"finewebedu"
   }
 }