Hugging Face's logo

ezipe
/
reward_learning

Model card Files Community
ezipe commited on
Commit
c0ecb8b
·
verified ·
1 Parent(s): c1b16a6

Upload folder using huggingface_hub

Browse files
Files changed (18) hide show
  1. reward_1707747690.8976614_config.reward_from=llm_task_index=5_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707747690.8976614_config.reward_from=llm_task_index=5_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  2. reward_1707747690.8976614_config.reward_from=llm_task_index=5_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707747690.8976614_config.reward_from=llm_task_index=5_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  3. reward_1707747690.8976614_config.reward_from=llm_task_index=5_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707747690.8976614_config.reward_from=llm_task_index=5_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  4. reward_1707747690.8976614_config.reward_from=llm_task_index=5_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707747690.8976614_config.reward_from=llm_task_index=5_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  5. reward_1707747690.8976614_config.reward_from=llm_task_index=5_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707747690.8976614_config.reward_from=llm_task_index=5_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  6. reward_1707747690.8976614_config.reward_from=llm_task_index=5_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707747690.8976614_config.reward_from=llm_task_index=5_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  7. reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  8. reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  9. reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  10. reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  11. reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  12. reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  13. reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  14. reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  15. reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  16. reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  17. reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  18. reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
reward_1707747690.8976614_config.reward_from=llm_task_index=5_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707747690.8976614_config.reward_from=llm_task_index=5_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 314.0 0.0 314.0 314.0 -14.019587 0.0 -14.019587 -14.019587 -0.0032624158 0.044910785 0.058338463 -0.07561443 0.3561559 2.0334150791168213
reward_1707747690.8976614_config.reward_from=llm_task_index=5_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707747690.8976614_config.reward_from=llm_task_index=5_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54c6053d42da06a9f9eea3c0eed3fd3cfda1099758d0c77a45a5a65e90d69384
3
+ size 26198
reward_1707747690.8976614_config.reward_from=llm_task_index=5_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707747690.8976614_config.reward_from=llm_task_index=5_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92ea2e1ec564527e3eda889a660916cf8391e187b0b03eca4b7d2467c96d0991
3
+ size 13916
reward_1707747690.8976614_config.reward_from=llm_task_index=5_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707747690.8976614_config.reward_from=llm_task_index=5_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 945.0 0.0 945.0 945.0 622.4866 0.0 622.4866 622.4866 -0.005310931 0.043766547 0.059458897 -0.074559785 0.33877438 1.9380953311920166
reward_1707747690.8976614_config.reward_from=llm_task_index=5_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707747690.8976614_config.reward_from=llm_task_index=5_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e615bf64acae2f38c7e89270b489a066e123c23818f94198570588b47ec776c
3
+ size 26198
reward_1707747690.8976614_config.reward_from=llm_task_index=5_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707747690.8976614_config.reward_from=llm_task_index=5_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92ea2e1ec564527e3eda889a660916cf8391e187b0b03eca4b7d2467c96d0991
3
+ size 13916
reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 53.0 0.0 53.0 53.0 -269.53296 0.0 -269.53296 -269.53296 -0.0050954274 0.04381009 0.05952607 -0.07449645 0.33773082 1.1982462406158447
reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2933c14926c12365f14f8a8cefa9ce9d061b3dff33e6226857e7fe50673eab0c
3
+ size 26198
reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92ea2e1ec564527e3eda889a660916cf8391e187b0b03eca4b7d2467c96d0991
3
+ size 13916
reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 1100.0 0.0 1100.0 1100.0 792.12036 0.0 792.12036 792.12036 -0.0021661364 0.044934925 0.059318684 -0.07469196 0.34095204 1.162524938583374
reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c27a903553105e16eab4b30de5343a0eb4b553890a02d94738dd3da5fe85c2d1
3
+ size 26198
reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92ea2e1ec564527e3eda889a660916cf8391e187b0b03eca4b7d2467c96d0991
3
+ size 13916
reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 53.0 0.0 53.0 53.0 -232.9786 0.0 -232.9786 -232.9786 0.00090725033 0.045979533 0.05978559 -0.07425156 0.33369732 1.1709768772125244
reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:827e99ec13bfde14ad98e01125b2930c66ebd638209fc692ac962d34f2f0523e
3
+ size 26198
reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92ea2e1ec564527e3eda889a660916cf8391e187b0b03eca4b7d2467c96d0991
3
+ size 13916
reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 146.6 0.0 146.6 146.6 -175.93298 0.0 -175.93298 -175.93298 -0.0050954274 0.04381009 0.05952607 -0.07449645 0.33773082 1.1978497505187988
reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fde38b5692dafe44fe3a6f54194f3dd600bae2138a646530f8077f842f87928d
3
+ size 26198
reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707747773.961969_config.reward_from=llm_task_index=0_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92ea2e1ec564527e3eda889a660916cf8391e187b0b03eca4b7d2467c96d0991
3
+ size 13916