Merge pull request mlcommons#903 from mlcommons/clean_up

clean up

Author: priyakasimbeg

.github/workflows/regression_tests.yml

@@ -107,7 +107,16 @@ 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 wmt -f jax -s algorithms/archived_paper_baselines/adamw/jax/submission.py -w wmt -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 wmt -f jax -s algorithms/archived_paper_baselines/adamw/jax/submission.py -w wmt -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
+  finewebedu_lm_jax:
+    runs-on: self-hosted
+    needs: build_and_push_jax_docker_image
+    steps:
+    - uses: actions/checkout@v2
+    - 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    
   fastmri_pytorch:
     runs-on: self-hosted
     needs: build_and_push_pytorch_docker_image
@@ -181,3 +190,12 @@ jobs:
       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 wmt -f pytorch -s algorithms/archived_paper_baselines/adamw/pytorch/submission.py -w wmt -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     
+  finewebedu_lm_pytorch:
+    runs-on: self-hosted
+    needs: build_and_push_pytorch_docker_image
+    steps:
+    - uses: actions/checkout@v2
+    - 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     

algoperf/workloads/workloads.py

@@ -117,10 +117,6 @@
     'workload_path': 'finewebedu_lm/finewebedu_lm',
     'workload_class_name': 'LmWorkload',
   },
-  'lm': {
-    'workload_path': 'finewebedu_lm/finewebedu_lm',
-    'workload_class_name': 'LmWorkload',
-  },
   'mnist': {
     'workload_path': 'mnist/mnist',
     'workload_class_name': 'MnistWorkload',

dataset/README.md

@@ -16,6 +16,7 @@
   - [LibriSpeech](#librispeech)
     - [Training SPM Tokenizer](#training-spm-tokenizer)
     - [Preprocessing Script](#preprocessing-script)
+  - [Fineweb-edu 10B](#fineweb-edu-10b)
 
 ## General Setup