diff --git "a/.gitattributes" "b/.gitattributes" --- "a/.gitattributes" +++ "b/.gitattributes" @@ -33,3 +33,789 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +.venv/bin/python filter=lfs diff=lfs merge=lfs -text +.venv/bin/python3 filter=lfs diff=lfs merge=lfs -text +.venv/bin/python3.10 filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/Pillow.libs/libfreetype-82733d78.so.6.20.1 filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/Pillow.libs/libharfbuzz-e3b74c67.so.0.60821.0 filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/aiohttp/_http_parser.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/debugpy/_vendored/pydevd/_pydevd_bundle/pydevd_cython.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/debugpy/_vendored/pydevd/_pydevd_frame_eval/pydevd_frame_evaluator.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/fontTools/feaLib/lexer.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/fontTools/misc/bezierTools.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/fontTools/pens/momentsPen.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/fontTools/qu2cu/qu2cu.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/fontTools/varLib/iup.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/grpc/_cython/cygrpc.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/hf_transfer/hf_transfer.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/kiwisolver/_cext.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/matplotlib/_image.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/matplotlib/_path.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/matplotlib/_qhull.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/matplotlib/backends/_backend_agg.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/matplotlib/ft2font.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/numpy/core/_multiarray_umath.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/numpy/core/_simd.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/numpy.libs/libgfortran-040039e1.so.5.0.0 filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/numpy.libs/libopenblas64_p-r0-0cf96a72.3.23.dev.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/nvfuser/_C.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/nvidia/cublas/lib/libcublas.so.12 filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/nvidia/cublas/lib/libcublasLt.so.12 filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/nvidia/cuda_cupti/lib/libcheckpoint.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/nvidia/cuda_cupti/lib/libcupti.so.12 filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/nvidia/cuda_cupti/lib/libnvperf_host.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/nvidia/cuda_cupti/lib/libnvperf_target.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/nvidia/cuda_nvrtc/lib/libnvrtc-builtins.so.12.1 filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/nvidia/cuda_nvrtc/lib/libnvrtc.so.12 filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/nvidia/cudnn/lib/libcudnn_adv_infer.so.8 filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/nvidia/cudnn/lib/libcudnn_adv_train.so.8 filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/nvidia/cudnn/lib/libcudnn_cnn_infer.so.8 filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/nvidia/cudnn/lib/libcudnn_cnn_train.so.8 filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/nvidia/cudnn/lib/libcudnn_ops_infer.so.8 filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/nvidia/cudnn/lib/libcudnn_ops_train.so.8 filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/nvidia/cufft/lib/libcufft.so.11 filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/nvidia/cufft/lib/libcufftw.so.11 filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/nvidia/curand/lib/libcurand.so.10 filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/nvidia/cusolver/lib/libcusolver.so.11 filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/nvidia/cusolver/lib/libcusolverMg.so.11 filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/nvidia/cusparse/lib/libcusparse.so.12 filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/nvidia/nccl/lib/libnccl.so.2 filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/nvidia/nvjitlink/lib/libnvJitLink.so.12 filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/pandas/_libs/algos.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/pandas/_libs/groupby.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/pandas/_libs/hashtable.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/pandas/_libs/interval.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/pandas/_libs/join.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/pyarrow/_compute.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/pyarrow/_flight.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/pyarrow/lib.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/pyarrow/libarrow.so.1200 filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/pyarrow/libarrow_acero.so.1200 filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/pyarrow/libarrow_dataset.so.1200 filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/pyarrow/libarrow_flight.so.1200 filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/pyarrow/libarrow_python.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/pyarrow/libarrow_substrait.so.1200 filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/pyarrow/libparquet.so.1200 filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/pydantic_core/_pydantic_core.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/pyzmq.libs/libsodium-cb25555f.so.23.3.0 filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/pyzmq.libs/libzmq-f468291a.so.5.2.4 filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/regex/_regex.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/safetensors/_safetensors_rust.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/tensorboard_data_server/bin/server filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/tokenizers/tokenizers.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/tokenizers.libs/libcrypto-d3570994.so.1.0.2k filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/tokenizers.libs/libkrb5-fcafa220.so.3.3 filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/torch/bin/nvfuser_tests filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/torch/bin/protoc filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/torch/bin/protoc-3.13.0.0 filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/torch/lib/libc10.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/torch/lib/libnvfuser_codegen.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/torch/lib/libtorch_cpu.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/torch/lib/libtorch_cuda.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/torch/lib/libtorch_cuda_linalg.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/torch/lib/libtorch_python.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/triton/_C/libtriton.so filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/triton/third_party/cuda/bin/ptxas filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/virtualenv/seed/wheels/embed/pip-23.1.2-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/virtualenv/seed/wheels/embed/setuptools-67.7.2-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.10/site-packages/yaml/_yaml.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +dataset_visuals/policy_comparisons_improved.png filter=lfs diff=lfs merge=lfs -text +eval/oai_final.csv filter=lfs diff=lfs merge=lfs -text +eval/oai_final2.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/openai_ppo_original_1.3b/test.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/openai_ppo_original_1.3b/test.jsonl filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/openai_ppo_original_1.3b/validation.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/openai_ppo_original_1.3b/validation.csv_judged.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/openai_ppo_original_1.3b/validation.jsonl filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/openai_ppo_original_1.3b/validation_gpt-4-0125-preview.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-1b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-1b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-1b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-1b-deduped/44413/query_responses_gpt-3.5-turbo-0125_vs_sft11.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-1b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-1b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-1b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-1b-deduped/55513/query_responses_gpt-3.5-turbo-0125_vs_sft11.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-1b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-1b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-1b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-1b-deduped/66613/query_responses_gpt-3.5-turbo-0125_vs_sft11.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-1b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-1b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-1b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-1b-deduped/77713/query_responses_gpt-3.5-turbo-0125_vs_sft11.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-2.8b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-2.8b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-2.8b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-2.8b-deduped/44413/query_responses_gpt-3.5-turbo-0125_vs_sft11.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-2.8b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-2.8b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-2.8b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-2.8b-deduped/55513/query_responses_gpt-3.5-turbo-0125_vs_sft11.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-2.8b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-2.8b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-2.8b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-2.8b-deduped/66613/query_responses_gpt-3.5-turbo-0125_vs_sft11.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-2.8b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-2.8b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-2.8b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-2.8b-deduped/77713/query_responses_gpt-3.5-turbo-0125_vs_sft11.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-6.9b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-6.9b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-6.9b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-6.9b-deduped/44413/query_responses_gpt-3.5-turbo-0125_vs_sft11.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-6.9b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-6.9b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-6.9b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-6.9b-deduped/55513/query_responses_gpt-3.5-turbo-0125_vs_sft11.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-6.9b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-6.9b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-6.9b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-6.9b-deduped/66613/query_responses_gpt-3.5-turbo-0125_vs_sft11.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-6.9b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-6.9b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-6.9b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/dpo/EleutherAI/pythia-6.9b-deduped/77713/query_responses_gpt-3.5-turbo-0125_vs_sft11.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-1b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-1b-deduped/44413/query_responses.csv_judged.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-1b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-1b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-1b-deduped/44413/query_responses_gpt-3.5-turbo-0125_vs_sft11.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-1b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-1b-deduped/55513/query_responses.csv_judged.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-1b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-1b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-1b-deduped/55513/query_responses_gpt-3.5-turbo-0125_vs_sft11.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-1b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-1b-deduped/66613/query_responses.csv_judged.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-1b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-1b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-1b-deduped/66613/query_responses_gpt-3.5-turbo-0125_vs_sft11.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-1b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-1b-deduped/77713/query_responses.csv_judged.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-1b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-1b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-1b-deduped/77713/query_responses_gpt-3.5-turbo-0125_vs_sft11.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-2.8b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-2.8b-deduped/44413/query_responses.csv_judged.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-2.8b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-2.8b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-2.8b-deduped/44413/query_responses_gpt-3.5-turbo-0125_vs_sft11.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-2.8b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-2.8b-deduped/55513/query_responses.csv_judged.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-2.8b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-2.8b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-2.8b-deduped/55513/query_responses_gpt-3.5-turbo-0125_vs_sft11.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-2.8b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-2.8b-deduped/66613/query_responses.csv_judged.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-2.8b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-2.8b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-2.8b-deduped/66613/query_responses_gpt-3.5-turbo-0125_vs_sft11.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-2.8b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-2.8b-deduped/77713/query_responses.csv_judged.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-2.8b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-2.8b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-2.8b-deduped/77713/query_responses_gpt-3.5-turbo-0125_vs_sft11.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-6.9b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-6.9b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-6.9b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-6.9b-deduped/44413/query_responses_gpt-3.5-turbo-0125_vs_sft11.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-6.9b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-6.9b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-6.9b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-6.9b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-6.9b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-6.9b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-6.9b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-6.9b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding/EleutherAI/pythia-6.9b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding_128/EleutherAI/pythia-1b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding_128/EleutherAI/pythia-1b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding_128/EleutherAI/pythia-1b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding_128/EleutherAI/pythia-1b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding_128/EleutherAI/pythia-1b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding_128/EleutherAI/pythia-1b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding_128/EleutherAI/pythia-1b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding_128/EleutherAI/pythia-1b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding_128/EleutherAI/pythia-1b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding_128/EleutherAI/pythia-1b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding_128/EleutherAI/pythia-1b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding_128/EleutherAI/pythia-1b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding_128/EleutherAI/pythia-2.8b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding_128/EleutherAI/pythia-2.8b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding_128/EleutherAI/pythia-2.8b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding_128/EleutherAI/pythia-2.8b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding_128/EleutherAI/pythia-2.8b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding_128/EleutherAI/pythia-2.8b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding_128/EleutherAI/pythia-2.8b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding_128/EleutherAI/pythia-2.8b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding_128/EleutherAI/pythia-2.8b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding_128/EleutherAI/pythia-2.8b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding_128/EleutherAI/pythia-2.8b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding_128/EleutherAI/pythia-2.8b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding_128/EleutherAI/pythia-6.9b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding_128/EleutherAI/pythia-6.9b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding_128/EleutherAI/pythia-6.9b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding_128/EleutherAI/pythia-6.9b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding_128/EleutherAI/pythia-6.9b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/ppo_left_padding_128/EleutherAI/pythia-6.9b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/sft/EleutherAI/pythia-1b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/sft/EleutherAI/pythia-1b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/sft/EleutherAI/pythia-1b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/sft/EleutherAI/pythia-1b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/sft/EleutherAI/pythia-1b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/sft/EleutherAI/pythia-1b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/sft/EleutherAI/pythia-1b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/sft/EleutherAI/pythia-1b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/sft/EleutherAI/pythia-2.8b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/sft/EleutherAI/pythia-2.8b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/sft/EleutherAI/pythia-2.8b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/sft/EleutherAI/pythia-2.8b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/sft/EleutherAI/pythia-2.8b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/sft/EleutherAI/pythia-2.8b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/sft/EleutherAI/pythia-2.8b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/sft/EleutherAI/pythia-2.8b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/sft/EleutherAI/pythia-6.9b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/sft/EleutherAI/pythia-6.9b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/sft/EleutherAI/pythia-6.9b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/sft/EleutherAI/pythia-6.9b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/sft/EleutherAI/pythia-6.9b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/sft/EleutherAI/pythia-6.9b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/sft/EleutherAI/pythia-6.9b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected2/sft/EleutherAI/pythia-6.9b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-1b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-1b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-1b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-1b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-1b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-1b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-1b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-1b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-1b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-1b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-1b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-1b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-2.8b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-2.8b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-2.8b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-2.8b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-2.8b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-2.8b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-2.8b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-2.8b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-2.8b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-2.8b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-2.8b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-2.8b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-6.9b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-6.9b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-6.9b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-6.9b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-6.9b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-6.9b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-6.9b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-6.9b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-6.9b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-6.9b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-6.9b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo/EleutherAI/pythia-6.9b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-1b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-1b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-1b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-1b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-1b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-1b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-1b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-1b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-1b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-1b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-1b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-1b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-2.8b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-2.8b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-2.8b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-2.8b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-2.8b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-2.8b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-2.8b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-2.8b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-2.8b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-2.8b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-2.8b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-2.8b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-6.9b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-6.9b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-6.9b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-6.9b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-6.9b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-6.9b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-6.9b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-6.9b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-6.9b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-6.9b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-6.9b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/dpo_0.5/EleutherAI/pythia-6.9b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo/EleutherAI/pythia-1.4b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo/EleutherAI/pythia-1.4b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo/EleutherAI/pythia-1.4b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo/EleutherAI/pythia-1.4b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo/EleutherAI/pythia-1.4b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo/EleutherAI/pythia-1.4b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo/EleutherAI/pythia-1.4b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo/EleutherAI/pythia-1.4b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo/EleutherAI/pythia-1.4b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo/EleutherAI/pythia-1.4b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo/EleutherAI/pythia-1.4b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo/EleutherAI/pythia-1.4b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo/EleutherAI/pythia-1.4b-deduped/77713/query_responses_gpt-4-0125-preview.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-1b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-1b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-1b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-1b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-1b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-1b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-1b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-1b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-1b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-1b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-1b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-1b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-1b-deduped/77713/query_responses_gpt-4-0125-preview.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-2.8b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-2.8b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-2.8b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-2.8b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-2.8b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-2.8b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-2.8b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-2.8b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-2.8b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-2.8b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-2.8b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-2.8b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-2.8b-deduped/77713/query_responses_gpt-4-0125-preview.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-6.9b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-6.9b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-6.9b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-6.9b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-6.9b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-6.9b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-6.9b-deduped/55513/query_responses_gpt-4-0125-preview.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-6.9b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-6.9b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-6.9b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-6.9b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-6.9b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding/EleutherAI/pythia-6.9b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_kl_0.07/EleutherAI/pythia-1b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_kl_0.07/EleutherAI/pythia-1b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_kl_0.07/EleutherAI/pythia-1b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_kl_0.07/EleutherAI/pythia-1b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_kl_0.07/EleutherAI/pythia-1b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_kl_0.07/EleutherAI/pythia-1b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_kl_0.07/EleutherAI/pythia-1b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_kl_0.07/EleutherAI/pythia-1b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_kl_0.07/EleutherAI/pythia-1b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_kl_0.07/EleutherAI/pythia-1b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_kl_0.07/EleutherAI/pythia-1b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_kl_0.07/EleutherAI/pythia-1b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_kl_0.07/EleutherAI/pythia-2.8b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_kl_0.07/EleutherAI/pythia-2.8b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_kl_0.07/EleutherAI/pythia-2.8b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_kl_0.07/EleutherAI/pythia-2.8b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_kl_0.07/EleutherAI/pythia-2.8b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_kl_0.07/EleutherAI/pythia-2.8b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_kl_0.07/EleutherAI/pythia-6.9b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_kl_0.07/EleutherAI/pythia-6.9b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_kl_0.07/EleutherAI/pythia-6.9b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-1b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-1b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-1b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-1b-deduped/44413/query_responses_gpt-4-0125-preview.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-1b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-1b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-1b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-1b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-1b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-1b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-1b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-1b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-1b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-2.8b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-2.8b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-2.8b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-2.8b-deduped/44413/query_responses_gpt-4-0125-preview.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-2.8b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-2.8b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-2.8b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-2.8b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-2.8b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-2.8b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-2.8b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-2.8b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-2.8b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-6.9b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-6.9b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-6.9b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-6.9b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-6.9b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-6.9b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-6.9b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-6.9b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-6.9b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-6.9b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-6.9b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-6.9b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new/EleutherAI/pythia-6.9b-deduped/77713/query_responses_gpt-4-0125-preview.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new1/EleutherAI/pythia-1b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new1/EleutherAI/pythia-1b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new1/EleutherAI/pythia-1b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new1/EleutherAI/pythia-1b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new1/EleutherAI/pythia-1b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new1/EleutherAI/pythia-1b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new1/EleutherAI/pythia-1b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new1/EleutherAI/pythia-1b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new1/EleutherAI/pythia-1b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new1/EleutherAI/pythia-1b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new1/EleutherAI/pythia-1b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new1/EleutherAI/pythia-1b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new1_kl_0.07/EleutherAI/pythia-1b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new1_kl_0.07/EleutherAI/pythia-1b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new1_kl_0.07/EleutherAI/pythia-1b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new1_kl_0.07/EleutherAI/pythia-1b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new1_kl_0.07/EleutherAI/pythia-1b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new1_kl_0.07/EleutherAI/pythia-1b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new1_kl_0.07/EleutherAI/pythia-1b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new1_kl_0.07/EleutherAI/pythia-1b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new1_kl_0.07/EleutherAI/pythia-1b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new1_kl_0.07/EleutherAI/pythia-1b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new1_kl_0.07/EleutherAI/pythia-1b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new1_kl_0.07/EleutherAI/pythia-1b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-1b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-1b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-1b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-1b-deduped/44413/query_responses_gpt-4-0125-preview.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-1b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-1b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-1b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-1b-deduped/55513/query_responses_gpt-4-0125-preview.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-1b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-1b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-1b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-1b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-1b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-1b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-2.8b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-2.8b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-2.8b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-2.8b-deduped/44413/query_responses_gpt-4-0125-preview.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-2.8b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-2.8b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-2.8b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-2.8b-deduped/55513/query_responses_gpt-4-0125-preview.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-2.8b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-2.8b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-2.8b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-2.8b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-2.8b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-2.8b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-6.9b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-6.9b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-6.9b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-6.9b-deduped/44413/query_responses_gpt-4-0125-preview.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-6.9b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-6.9b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-6.9b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.07/EleutherAI/pythia-6.9b-deduped/55513/query_responses_gpt-4-0125-preview.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.1/EleutherAI/pythia-1b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.1/EleutherAI/pythia-1b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.1/EleutherAI/pythia-1b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.1/EleutherAI/pythia-1b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.1/EleutherAI/pythia-1b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.1/EleutherAI/pythia-1b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.1/EleutherAI/pythia-1b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.1/EleutherAI/pythia-1b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.1/EleutherAI/pythia-1b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.1/EleutherAI/pythia-1b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.1/EleutherAI/pythia-1b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_kl_0.1/EleutherAI/pythia-1b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-1b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-1b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-1b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-1b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-1b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-1b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-1b-deduped/55513/query_responses_gpt-4-0125-preview.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-1b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-1b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-1b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-1b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-1b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-1b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-2.8b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-2.8b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-2.8b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-2.8b-deduped/44413/query_responses_gpt-4-0125-preview.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-2.8b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-2.8b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-2.8b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-2.8b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-2.8b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-2.8b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-2.8b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-2.8b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-2.8b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-2.8b-deduped/77713/query_responses_gpt-4-0125-preview.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-6.9b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-6.9b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-6.9b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-6.9b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-6.9b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-6.9b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-6.9b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-6.9b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-6.9b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-6.9b-deduped/66613/query_responses_gpt-4-0125-preview.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-6.9b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-6.9b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-6.9b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_new_nowhiten_reward/EleutherAI/pythia-6.9b-deduped/77713/query_responses_gpt-4-0125-preview.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_nowhiten_reward/EleutherAI/pythia-1b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_nowhiten_reward/EleutherAI/pythia-1b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_nowhiten_reward/EleutherAI/pythia-1b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_nowhiten_reward/EleutherAI/pythia-1b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_nowhiten_reward/EleutherAI/pythia-1b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_nowhiten_reward/EleutherAI/pythia-1b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_nowhiten_reward/EleutherAI/pythia-1b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_nowhiten_reward/EleutherAI/pythia-1b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_nowhiten_reward/EleutherAI/pythia-1b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_nowhiten_reward/EleutherAI/pythia-1b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_nowhiten_reward/EleutherAI/pythia-1b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_left_padding_nowhiten_reward/EleutherAI/pythia-1b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_lora/EleutherAI/pythia-1b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_lora/EleutherAI/pythia-1b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_lora/EleutherAI/pythia-1b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_lora/EleutherAI/pythia-1b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_lora/EleutherAI/pythia-1b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_lora/EleutherAI/pythia-1b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_lora/EleutherAI/pythia-1b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_lora/EleutherAI/pythia-1b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_lora/EleutherAI/pythia-1b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_lora/EleutherAI/pythia-1b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_lora/EleutherAI/pythia-1b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_lora/EleutherAI/pythia-1b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_lora/EleutherAI/pythia-2.8b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_lora/EleutherAI/pythia-2.8b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_lora/EleutherAI/pythia-2.8b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_lora/EleutherAI/pythia-2.8b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_lora/EleutherAI/pythia-2.8b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_lora/EleutherAI/pythia-2.8b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_lora/EleutherAI/pythia-2.8b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_lora/EleutherAI/pythia-2.8b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/ppo_lora/EleutherAI/pythia-2.8b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/reward_eval/EleutherAI/pythia-1b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/reward_eval/EleutherAI/pythia-1b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/reward_eval/EleutherAI/pythia-1b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/reward_eval/EleutherAI/pythia-1b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/reward_eval/EleutherAI/pythia-1b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/reward_eval/EleutherAI/pythia-1b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/reward_eval/EleutherAI/pythia-1b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/reward_eval/EleutherAI/pythia-1b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/reward_eval/EleutherAI/pythia-2.8b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/reward_eval/EleutherAI/pythia-2.8b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/reward_eval/EleutherAI/pythia-2.8b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/reward_eval/EleutherAI/pythia-2.8b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/reward_eval/EleutherAI/pythia-2.8b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/reward_eval/EleutherAI/pythia-2.8b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/reward_eval/EleutherAI/pythia-6.9b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/reward_eval/EleutherAI/pythia-6.9b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/reward_eval/EleutherAI/pythia-6.9b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/reward_eval/EleutherAI/pythia-6.9b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/reward_eval/EleutherAI/pythia-6.9b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/reward_eval/EleutherAI/pythia-6.9b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/reward_eval/EleutherAI/pythia-6.9b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/reward_eval/EleutherAI/pythia-6.9b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-1.4b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-1.4b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-1.4b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-1.4b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-1.4b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-1.4b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-1.4b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-1.4b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-1.4b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-1.4b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-1.4b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-1.4b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-1b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-1b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-1b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-1b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-1b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-1b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-1b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-1b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-1b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-1b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-1b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-1b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-2.8b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-2.8b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-2.8b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-2.8b-deduped/44413/query_responses_gpt-4-0125-preview.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-2.8b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-2.8b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-2.8b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-2.8b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-2.8b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-2.8b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-2.8b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-2.8b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-2.8b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-6.9b-deduped/44413/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-6.9b-deduped/44413/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-6.9b-deduped/44413/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-6.9b-deduped/55513/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-6.9b-deduped/55513/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-6.9b-deduped/55513/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-6.9b-deduped/66613/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-6.9b-deduped/66613/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-6.9b-deduped/66613/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-6.9b-deduped/77713/query_responses.csv filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-6.9b-deduped/77713/query_responses.json filter=lfs diff=lfs merge=lfs -text +eval/sampled_data/refactor-chosen-rejected3/sft/EleutherAI/pythia-6.9b-deduped/77713/query_responses_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval/title_against_reference.csv_gpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo_0.5__44413__1711045325/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo_0.5__44413__1711045325/eval_validation_cnndm_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo_0.5__44413__1711045326/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo_0.5__44413__1711045326/eval_validation_cnndm_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo_0.5__55513__1711045325/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo_0.5__55513__1711045325/eval_validation_cnndm_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo_0.5__55513__1711045326/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo_0.5__55513__1711045326/eval_validation_cnndm_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo_0.5__66613__1711045325/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo_0.5__66613__1711045325/eval_validation_cnndm_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo_0.5__77713__1711045325/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo_0.5__77713__1711045325/eval_validation_cnndm_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo_0.5__77713__1711045326/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo_0.5__77713__1711045326/eval_validation_cnndm_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__44413__1707268320/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__44413__1707313795/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__44413__1707367217/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__44413__1707379466/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__44413__1707405254/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__44413__1711045929/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__44413__1711045929/eval_validation_cnndm_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__44413__1711045930/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__44413__1711045930/eval_validation_cnndm_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__44413__1711045935/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__44413__1711045935/eval_validation_cnndm_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__55513__1707268320/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__55513__1707313794/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__55513__1707367250/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__55513__1707379566/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__55513__1707405254/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__55513__1711045929/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__55513__1711045929/eval_validation_cnndm_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__55513__1711045931/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__55513__1711045931/eval_validation_cnndm_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__55513__1711045932/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__55513__1711045932/eval_validation_cnndm_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__66613__1707268319/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__66613__1707268320/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__66613__1707313794/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__66613__1707367742/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__66613__1707379613/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__66613__1707405253/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__66613__1711045929/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__66613__1711045929/eval_validation_cnndm_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__66613__1711045930/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__66613__1711045930/eval_validation_cnndm_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__77713__1707268320/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__77713__1707313794/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__77713__1707368092/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__77713__1707380008/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__77713__1707405254/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__77713__1711045930/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__77713__1711045930/eval_validation_cnndm_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__77713__1711045934/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__77713__1711045934/eval_validation_cnndm_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__77713__1711045936/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/dpo__77713__1711045936/eval_validation_cnndm_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__44413__1706392663/eval_11604_normalized.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__44413__1706392663/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__44413__1706392664/eval_11604_normalized.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__44413__1706392664/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__44413__1706651113/eval_11604_normalized.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__44413__1706651113/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__44413__1708616371/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__44413__1708628552/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__44413__1711148741/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__44413__1711148741/eval_validation_cnndm_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__55513__1706392664/eval_11604_normalized.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__55513__1706392664/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__55513__1706392668/eval_11604_normalized.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__55513__1706392668/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__55513__1706651113/eval_11604_normalized.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__55513__1706651113/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__55513__1708616371/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__55513__1708628552/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__55513__1711148742/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__55513__1711148742/eval_validation_cnndm_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__66613__1706392663/eval_11604_normalized.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__66613__1706392663/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__66613__1706651113/eval_11604_normalized.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__66613__1706651113/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__66613__1706651114/eval_11604_normalized.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__66613__1706651114/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__66613__1708616371/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__66613__1708628551/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__66613__1708628552/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__66613__1711148756/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__66613__1711148756/eval_validation_cnndm_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__77713__1706392663/eval_11604_normalized.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__77713__1706392663/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__77713__1706392664/eval_11604_normalized.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__77713__1706392664/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__77713__1706651114/eval_11604_normalized.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__77713__1706651114/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__77713__1708616371/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__77713__1708616372/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__77713__1708628551/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__77713__1708628552/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__77713__1708628553/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__77713__1711148771/eval_validation_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward__77713__1711148771/eval_validation_cnndm_11604.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward_eval__1__1710877435/eval_validation_0.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward_eval__44413__1710877750/eval_validation_0.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward_eval__44413__1710877887/eval_validation_0.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward_eval__44413__1711030600/eval_validation_0.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward_eval__44413__1711030600/eval_validation_cnndm_0.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward_eval__44413__1711030601/eval_validation_0.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward_eval__44413__1711030601/eval_validation_cnndm_0.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward_eval__55513__1710877750/eval_validation_0.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward_eval__55513__1710878145/eval_validation_0.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward_eval__55513__1711030600/eval_validation_0.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward_eval__55513__1711030600/eval_validation_cnndm_0.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward_eval__55513__1711030601/eval_validation_0.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward_eval__55513__1711030601/eval_validation_cnndm_0.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward_eval__66613__1710877750/eval_validation_0.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward_eval__66613__1710877769/eval_validation_0.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward_eval__66613__1710878146/eval_validation_0.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward_eval__66613__1711030600/eval_validation_0.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward_eval__66613__1711030600/eval_validation_cnndm_0.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward_eval__77713__1710877750/eval_validation_0.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward_eval__77713__1710877791/eval_validation_0.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward_eval__77713__1710878146/eval_validation_0.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward_eval__77713__1711030600/eval_validation_0.csv filter=lfs diff=lfs merge=lfs -text +eval_tables/reward_eval__77713__1711030600/eval_validation_cnndm_0.csv filter=lfs diff=lfs merge=lfs -text +tmp/dpo.csv filter=lfs diff=lfs merge=lfs -text +tmp/dpo_on_policy.csv filter=lfs diff=lfs merge=lfs -text +tmp/dpo_on_policygpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +tmp/dpo_onp.csv filter=lfs diff=lfs merge=lfs -text +tmp/dpo_onp_high_beta.csv filter=lfs diff=lfs merge=lfs -text +tmp/dpo_onp_high_betagpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +tmp/dpo_onpgpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +tmp/dpogpt-3.5-turbo-0125.csv filter=lfs diff=lfs merge=lfs -text +tmp/our1b.csv filter=lfs diff=lfs merge=lfs -text +tmp/our1b_judged.csv filter=lfs diff=lfs merge=lfs -text