yiran-wang3/ds_chat_cosine_replace_sppo-GT_REPLACE-sppo_hard-0.005-cosine-rmsprop-1e-7-checkpoint-386
Updated
ds_chat_cosine_replace_sppo
sppo training with replaced coding block ground truth
-
-
yiran-wang3/ds_chat_cosine_replace_sppo-GT_REPLACE_MASKED-sppo_hard-0.01-cosine-rmsprop-1e-7-checkpoint-1158
Updated -
yiran-wang3/ds_chat_cosine_replace_sppo-GT_REPLACE_MASKED-sppo_hard-0.01-cosine-rmsprop-1e-7-checkpoint-772
Updated -
yiran-wang3/ds_chat_cosine_replace_sppo-GT_REPLACE_MASKED-sppo_hard-0.01-cosine-rmsprop-1e-7-checkpoint-386
Updated -
yiran-wang3/ds_chat_cosine_replace_sppo-GT_REPLACE-sppo_hard-0.01-cosine-rmsprop-1e-7-checkpoint-1158
Updated -
yiran-wang3/ds_chat_cosine_replace_sppo-GT_REPLACE-sppo_hard-0.01-cosine-rmsprop-1e-7-checkpoint-772
Updated -
yiran-wang3/ds_chat_cosine_replace_sppo-GT_REPLACE-sppo_hard-0.01-cosine-rmsprop-1e-7-checkpoint-386
Updated -
yiran-wang3/ds_chat_cosine_replace_sppo-GT_REPLACE-sppo_hard-0.1-cosine-rmsprop-1e-7-checkpoint-1158
Updated -
yiran-wang3/ds_chat_cosine_replace_sppo-GT_REPLACE-sppo_hard-0.1-cosine-rmsprop-1e-7-checkpoint-772
Updated -
yiran-wang3/ds_chat_cosine_replace_sppo-GT_REPLACE-sppo_hard-0.1-cosine-rmsprop-1e-7-checkpoint-386
Updated -
yiran-wang3/ds_chat_cosine_replace_sppo-GT_REPLACE-sppo-0.005-cos-rmsp-1e-7-checkpoint-1158
Text Generation • Updated • 6 -
yiran-wang3/ds_chat_cosine_replace_sppo-GT_REPLACE-sppo-0.005-cos-rmsp-1e-7-checkpoint-772
Text Generation • Updated • 6 -
yiran-wang3/ds_chat_cosine_replace_sppo-GT_REPLACE-sppo-0.005-cos-rmsp-1e-7-checkpoint-386
Text Generation • Updated • 5 -
yiran-wang3/ds_chat_cosine_replace_sppo-GT_REPLACE_MASKED-sppo-0.01-cos-rmsp-1e-7-checkpoint-1158
Text Generation • Updated • 6 -
yiran-wang3/ds_chat_cosine_replace_sppo-GT_REPLACE_MASKED-sppo-0.01-cos-rmsp-1e-7-checkpoint-772
Text Generation • Updated • 5 -
yiran-wang3/ds_chat_cosine_replace_sppo-GT_REPLACE_MASKED-sppo-0.01-cos-rmsp-1e-7-checkpoint-386
Text Generation • Updated • 4 -
yiran-wang3/ds_chat_cosine_replace_sppo-GT_REPLACE-sppo-0.01-cos-rmsp-1e-7-checkpoint-1158
Text Generation • Updated • 5 -
yiran-wang3/ds_chat_cosine_replace_sppo-GT_REPLACE-sppo-0.01-cos-rmsp-1e-7-checkpoint-772
Text Generation • Updated • 3 -
yiran-wang3/ds_chat_cosine_replace_sppo-GT_REPLACE-sppo-0.01-cos-rmsp-1e-7-checkpoint-386
Text Generation • Updated • 3 -
yiran-wang3/ds_chat_cosine_replace_sppo-GT_REPLACE-sppo-0.1-cos-rmsp-1e-7-checkpoint-1158
Text Generation • Updated • 4 -
yiran-wang3/ds_chat_cosine_replace_sppo-GT_REPLACE-sppo-0.1-cos-rmsp-1e-7-checkpoint-772
Text Generation • Updated • 6 -
yiran-wang3/ds_chat_cosine_replace_sppo-GT_REPLACE-sppo-0.1-cos-rmsp-1e-7-checkpoint-386
Text Generation • Updated • 6 -
yiran-wang3/ds_chat_cosine_replace_sppo-GT_REPLACE_MASKED-sppo-0.005-cos-rmsp-1e-7-checkpoint-1158
Text Generation • Updated • 9 -
yiran-wang3/ds_chat_cosine_replace_sppo-GT_REPLACE_MASKED-sppo-0.005-cos-rmsp-1e-7-checkpoint-772
Text Generation • Updated • 6 -
yiran-wang3/ds_chat_cosine_replace_sppo-GT_REPLACE_MASKED-sppo-0.005-cos-rmsp-1e-7-checkpoint-386
Text Generation • Updated • 6 -
yiran-wang3/ds_chat_cosine_replace_sppo-GT_REPLACE_MASKED-sppo-0.1-cos-rmsp-1e-7-checkpoint-1158
Text Generation • Updated • 6 -
yiran-wang3/ds_chat_cosine_replace_sppo-GT_REPLACE_MASKED-sppo-0.1-cos-rmsp-1e-7-checkpoint-772
Text Generation • Updated • 5 -
yiran-wang3/ds_chat_cosine_replace_sppo-GT_REPLACE_MASKED-sppo-0.1-cos-rmsp-1e-7-checkpoint-386
Text Generation • Updated • 10