Change the workload name to finewebedu everywhere to maintain uniformity.

Author: aahladc

.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     

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)
 

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" \

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 = {

scoring/utils/workload_metadata_external_tuning.json

@@ -33,6 +33,6 @@
   },
   "finewebedu_lm" : {
     "max_steps": 55000,
-    "dataset":"fineweb_edu_10B"
+    "dataset":"finewebedu"
   }
 }