Hugging Face's logo

ezipe
/
reward_learning

Model card Files
xet
Community
ezipe commited on
Commit
a908af8
·
verified ·
1 Parent(s): 57128ca

Upload folder using huggingface_hub

Browse files
Files changed (36) hide show
  1. reward_1707748949.1211529_config.reward_from=llm_task_index=6_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=6_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  2. reward_1707748949.1211529_config.reward_from=llm_task_index=6_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=6_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  3. reward_1707748949.1211529_config.reward_from=llm_task_index=6_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=6_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  4. reward_1707748949.1211529_config.reward_from=llm_task_index=6_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=6_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  5. reward_1707748949.1211529_config.reward_from=llm_task_index=6_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=6_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  6. reward_1707748949.1211529_config.reward_from=llm_task_index=6_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=6_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  7. reward_1707748949.1211529_config.reward_from=llm_task_index=6_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=6_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  8. reward_1707748949.1211529_config.reward_from=llm_task_index=6_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=6_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  9. reward_1707748949.1211529_config.reward_from=llm_task_index=6_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=6_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  10. reward_1707748949.1211529_config.reward_from=llm_task_index=6_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=6_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  11. reward_1707748949.1211529_config.reward_from=llm_task_index=6_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=6_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  12. reward_1707748949.1211529_config.reward_from=llm_task_index=6_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=6_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  13. reward_1707748949.1211529_config.reward_from=llm_task_index=7_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=7_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  14. reward_1707748949.1211529_config.reward_from=llm_task_index=7_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=7_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  15. reward_1707748949.1211529_config.reward_from=llm_task_index=7_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=7_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  16. reward_1707748949.1211529_config.reward_from=llm_task_index=7_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=7_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  17. reward_1707748949.1211529_config.reward_from=llm_task_index=7_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=7_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  18. reward_1707748949.1211529_config.reward_from=llm_task_index=7_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=7_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  19. reward_1707748949.1211529_config.reward_from=llm_task_index=7_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=7_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  20. reward_1707748949.1211529_config.reward_from=llm_task_index=7_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=7_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  21. reward_1707748949.1211529_config.reward_from=llm_task_index=7_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=7_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  22. reward_1707748949.1211529_config.reward_from=llm_task_index=7_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=7_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  23. reward_1707748949.1211529_config.reward_from=llm_task_index=7_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=7_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  24. reward_1707748949.1211529_config.reward_from=llm_task_index=7_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=7_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  25. reward_1707748949.1211529_config.reward_from=llm_task_index=8_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=8_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  26. reward_1707748949.1211529_config.reward_from=llm_task_index=8_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=8_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  27. reward_1707748949.1211529_config.reward_from=llm_task_index=8_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=8_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  28. reward_1707748949.1211529_config.reward_from=llm_task_index=8_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=8_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  29. reward_1707748949.1211529_config.reward_from=llm_task_index=8_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=8_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  30. reward_1707748949.1211529_config.reward_from=llm_task_index=8_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=8_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  31. reward_1707748949.1211529_config.reward_from=llm_task_index=8_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=8_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  32. reward_1707748949.1211529_config.reward_from=llm_task_index=8_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=8_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  33. reward_1707748949.1211529_config.reward_from=llm_task_index=8_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=8_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  34. reward_1707748949.1211529_config.reward_from=llm_task_index=8_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=8_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  35. reward_1707748949.1211529_config.reward_from=llm_task_index=8_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=8_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  36. reward_1707748949.1211529_config.reward_from=llm_task_index=8_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=8_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
reward_1707748949.1211529_config.reward_from=llm_task_index=6_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=6_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
+ 0 927.0 0.0 927.0 927.0 620.0024 0.0 620.0024 620.0024 -0.0020957217 0.044920806 0.059454046 -0.074564345 0.33884946 2.196476697921753
reward_1707748949.1211529_config.reward_from=llm_task_index=6_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=6_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 sha256:076efbb80884ed9680a0e52f64c566a7b7ac809225867f9120b669265387b79e
3
+ size 26198
reward_1707748949.1211529_config.reward_from=llm_task_index=6_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=6_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_1707748949.1211529_config.reward_from=llm_task_index=6_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=6_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 9672.0 0.0 9672.0 9672.0 9367.203 0.0 9367.203 9367.203 -0.001445221 0.044752646 0.059681807 -0.074349515 0.33531064 1.3819494247436523
reward_1707748949.1211529_config.reward_from=llm_task_index=6_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=6_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 sha256:7fa6d995695190d0a2bd77dffe0129f5d6213fc19eec8dfa277f627ffae7b49d
3
+ size 26198
reward_1707748949.1211529_config.reward_from=llm_task_index=6_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=6_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_1707748949.1211529_config.reward_from=llm_task_index=6_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=6_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
+ 0 622.25 0.0 622.25 622.25 367.36813 0.0 367.36813 367.36813 0.005734781 0.046514753 0.060982764 -0.07311949 0.3150578 1.2527499198913574
reward_1707748949.1211529_config.reward_from=llm_task_index=6_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=6_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 sha256:79b1d7012a7d6693531b8c7095cbdf00493b70d1e19c57e6b04c865c2dcd6f85
3
+ size 26198
reward_1707748949.1211529_config.reward_from=llm_task_index=6_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=6_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_1707748949.1211529_config.reward_from=llm_task_index=6_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=6_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
+ 0 587.0 0.0 587.0 587.0 253.35881 0.0 253.35881 253.35881 -0.0041090813 0.04488344 0.057918865 -0.07600847 0.36265343 1.235605239868164
reward_1707748949.1211529_config.reward_from=llm_task_index=6_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=6_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:be75b7d8688faf243a24918ae555ef7deefaba6aaf9dd75bc04f18a787a71916
3
+ size 26198
reward_1707748949.1211529_config.reward_from=llm_task_index=6_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=6_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
reward_1707748949.1211529_config.reward_from=llm_task_index=7_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=7_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 20983.0 0.0 20983.0 20983.0 20697.361 0.0 20697.361 20697.361 0.0059071355 0.046967104 0.057720218 -0.07133144 0.36572734 1.1839430332183838
reward_1707748949.1211529_config.reward_from=llm_task_index=7_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=7_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:fa58c55c609e04e1cff7c70047bbf43d27ea76492be148bfa4bb500d93139209
3
+ size 26198
reward_1707748949.1211529_config.reward_from=llm_task_index=7_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=7_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_1707748949.1211529_config.reward_from=llm_task_index=7_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=7_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 1.916 0.0 1.916 1.916 -302.98575 0.0 -302.98575 -302.98575 -0.0016318782 0.044795927 0.059674412 -0.07435648 0.3354254 1.2936453819274902
reward_1707748949.1211529_config.reward_from=llm_task_index=7_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=7_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:b2de33535e1f8436f4df5033efd2a2a329675072783ccee2d242509e354babd9
3
+ size 26198
reward_1707748949.1211529_config.reward_from=llm_task_index=7_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=7_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_1707748949.1211529_config.reward_from=llm_task_index=7_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=7_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 1032.0 0.0 1032.0 1032.0 737.4055 0.0 737.4055 737.4055 0.0035244965 0.0460242 0.057909336 -0.07601743 0.36280102 1.185551404953003
reward_1707748949.1211529_config.reward_from=llm_task_index=7_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=7_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:d6ace2d59c465adb9d56463dee33c1ca3cf7804c253203e725f7680e167f8d16
3
+ size 26198
reward_1707748949.1211529_config.reward_from=llm_task_index=7_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=7_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_1707748949.1211529_config.reward_from=llm_task_index=7_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=7_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 18660.0 0.0 18660.0 18660.0 18359.748 0.0 18359.748 18359.748 -0.0034931244 0.04369259 0.060790155 -0.07330192 0.31806055 1.469165325164795
reward_1707748949.1211529_config.reward_from=llm_task_index=7_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=7_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 sha256:0825183f6ea7e6bdbfb77a5978fa8d2e511dc1d29723b7120606c8fbef2c7c25
3
+ size 26198
reward_1707748949.1211529_config.reward_from=llm_task_index=7_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=7_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
reward_1707748949.1211529_config.reward_from=llm_task_index=8_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=8_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
+ 0 125.0 0.0 125.0 125.0 -171.34587 0.0 -171.34587 -171.34587 -0.004067607 0.043875653 0.061076667 -0.07303053 0.31359354 1.3226549625396729
reward_1707748949.1211529_config.reward_from=llm_task_index=8_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=8_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 sha256:77938696825743ac2a10cd5b3661b791a6a4edd805f15d2a4ff096f0fe592762
3
+ size 26198
reward_1707748949.1211529_config.reward_from=llm_task_index=8_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=8_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_1707748949.1211529_config.reward_from=llm_task_index=8_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=8_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 1513.0 0.0 1513.0 1513.0 1179.1422 0.0 1179.1422 1179.1422 -0.0066482634 0.04380754 0.058571637 -0.075395264 0.35254255 1.2770061492919922
reward_1707748949.1211529_config.reward_from=llm_task_index=8_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=8_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 sha256:99dea49a56662d85fe3c064913f299bd44cda94dc0dd3bb52bb7078854070830
3
+ size 26198
reward_1707748949.1211529_config.reward_from=llm_task_index=8_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=8_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_1707748949.1211529_config.reward_from=llm_task_index=8_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=8_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
+ 0 119.0 0.0 119.0 119.0 -170.21362 0.0 -170.21362 -170.21362 0.0012113387 0.045754064 0.059389543 -0.07462516 0.33985147 1.1838469505310059
reward_1707748949.1211529_config.reward_from=llm_task_index=8_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=8_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 sha256:04f941dce1e52216e944de1ad9d3c09678c4fdee19eaacdb20c247232e9b5933
3
+ size 26198
reward_1707748949.1211529_config.reward_from=llm_task_index=8_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=8_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_1707748949.1211529_config.reward_from=llm_task_index=8_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=8_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
+ 0 794.0 0.0 794.0 794.0 520.75775 0.0 520.75775 520.75775 0.005694325 0.04591599 0.059658155 -0.07437182 0.3356783 1.0851311683654785
reward_1707748949.1211529_config.reward_from=llm_task_index=8_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=8_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 sha256:048c0a927d5d2be22d0fb37b511b26c77c0770c5f9d041d989e30d4b4105be34
3
+ size 26198
reward_1707748949.1211529_config.reward_from=llm_task_index=8_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.1211529_config.reward_from=llm_task_index=8_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