Hugging Face's logo

ezipe
/
reward_learning

Model card Files
xet
Community
ezipe commited on
Commit
6d37644
·
verified ·
1 Parent(s): 2aa458a

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. reward_1707748949.611114_config.reward_from=llm_task_index=12_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=12_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  2. reward_1707748949.611114_config.reward_from=llm_task_index=12_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=12_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  3. reward_1707748949.611114_config.reward_from=llm_task_index=12_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=12_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  4. reward_1707748949.611114_config.reward_from=llm_task_index=12_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=12_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  5. reward_1707748949.611114_config.reward_from=llm_task_index=12_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=12_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  6. reward_1707748949.611114_config.reward_from=llm_task_index=12_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=12_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  7. reward_1707748949.611114_config.reward_from=llm_task_index=12_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=12_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  8. reward_1707748949.611114_config.reward_from=llm_task_index=12_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=12_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  9. reward_1707748949.611114_config.reward_from=llm_task_index=12_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=12_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  10. reward_1707748949.611114_config.reward_from=llm_task_index=12_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=12_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  11. reward_1707748949.611114_config.reward_from=llm_task_index=12_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=12_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  12. reward_1707748949.611114_config.reward_from=llm_task_index=12_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=12_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  13. reward_1707748949.611114_config.reward_from=llm_task_index=13_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=13_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  14. reward_1707748949.611114_config.reward_from=llm_task_index=13_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=13_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  15. reward_1707748949.611114_config.reward_from=llm_task_index=13_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=13_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  16. reward_1707748949.611114_config.reward_from=llm_task_index=13_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=13_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  17. reward_1707748949.611114_config.reward_from=llm_task_index=13_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=13_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  18. reward_1707748949.611114_config.reward_from=llm_task_index=13_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=13_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  19. reward_1707748949.611114_config.reward_from=llm_task_index=13_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=13_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  20. reward_1707748949.611114_config.reward_from=llm_task_index=13_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=13_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  21. reward_1707748949.611114_config.reward_from=llm_task_index=13_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=13_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  22. reward_1707748949.611114_config.reward_from=llm_task_index=13_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=13_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  23. reward_1707748949.611114_config.reward_from=llm_task_index=13_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=13_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  24. reward_1707748949.611114_config.reward_from=llm_task_index=13_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=13_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  25. reward_1707748949.611114_config.reward_from=llm_task_index=14_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=14_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  26. reward_1707748949.611114_config.reward_from=llm_task_index=14_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=14_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  27. reward_1707748949.611114_config.reward_from=llm_task_index=14_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=14_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  28. reward_1707748949.611114_config.reward_from=llm_task_index=14_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=14_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  29. reward_1707748949.611114_config.reward_from=llm_task_index=14_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=14_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  30. reward_1707748949.611114_config.reward_from=llm_task_index=14_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=14_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  31. reward_1707748949.611114_config.reward_from=llm_task_index=14_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=14_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  32. reward_1707748949.611114_config.reward_from=llm_task_index=14_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=14_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  33. reward_1707748949.611114_config.reward_from=llm_task_index=14_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=14_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  34. reward_1707748949.611114_config.reward_from=llm_task_index=14_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=14_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  35. reward_1707748949.611114_config.reward_from=llm_task_index=14_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=14_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  36. reward_1707748949.611114_config.reward_from=llm_task_index=14_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=14_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  37. reward_1707748949.611114_config.reward_from=llm_task_index=15_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=15_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  38. reward_1707748949.611114_config.reward_from=llm_task_index=15_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=15_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  39. reward_1707748949.611114_config.reward_from=llm_task_index=15_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=15_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  40. reward_1707748949.611114_config.reward_from=llm_task_index=15_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=15_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  41. reward_1707748949.611114_config.reward_from=llm_task_index=15_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=15_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  42. reward_1707748949.611114_config.reward_from=llm_task_index=15_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=15_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  43. reward_1707748949.611114_config.reward_from=llm_task_index=15_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=15_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  44. reward_1707748949.611114_config.reward_from=llm_task_index=15_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=15_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  45. reward_1707748949.611114_config.reward_from=llm_task_index=15_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=15_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  46. reward_1707748949.611114_config.reward_from=llm_task_index=15_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=15_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  47. reward_1707748949.611114_config.reward_from=llm_task_index=15_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=15_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  48. reward_1707748949.611114_config.reward_from=llm_task_index=15_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=15_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  49. reward_1707748949.611114_config.reward_from=llm_task_index=16_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=16_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  50. reward_1707748949.611114_config.reward_from=llm_task_index=16_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=16_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
reward_1707748949.611114_config.reward_from=llm_task_index=12_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=12_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
+ 0 953.0 0.0 953.0 953.0 652.83594 0.0 652.83594 652.83594 -0.002168625 0.045007654 0.059986245 -0.07406212 0.33057702 2.4347472190856934
reward_1707748949.611114_config.reward_from=llm_task_index=12_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=12_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 sha256:078ce9e6cec48a03210cd96bbdfafdfaaf9a911c7a156af1ec376a4a0850b3ce
3
+ size 26198
reward_1707748949.611114_config.reward_from=llm_task_index=12_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=12_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_1707748949.611114_config.reward_from=llm_task_index=12_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=12_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 1376.0 0.0 1376.0 1376.0 1095.3876 0.0 1095.3876 1095.3876 0.0021131376 0.045713313 0.05986391 -0.074177615 0.3324795 1.2189209461212158
reward_1707748949.611114_config.reward_from=llm_task_index=12_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=12_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:ccd69b46ea9ea2ae5a0f3f070e9cac631c78b2a3fae1a3be584a211a4f729b4f
3
+ size 26198
reward_1707748949.611114_config.reward_from=llm_task_index=12_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=12_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_1707748949.611114_config.reward_from=llm_task_index=12_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=12_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 1604.0 0.0 1604.0 1604.0 1277.858 0.0 1277.858 1277.858 -0.007816804 0.04234601 0.04392085 -0.07385238 0.32712317 1.3374824523925781
reward_1707748949.611114_config.reward_from=llm_task_index=12_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=12_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:cc4e78f36d34a76e929ff642de1a30e4cabf43ad7db5584b3f7fe370fac5626c
3
+ size 26198
reward_1707748949.611114_config.reward_from=llm_task_index=12_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=12_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_1707748949.611114_config.reward_from=llm_task_index=12_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=12_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 2580.0 0.0 2580.0 2580.0 2303.1753 0.0 2303.1753 2303.1753 0.00021175982 0.044766117 0.06119552 -0.07291788 0.31173953 1.2636334896087646
reward_1707748949.611114_config.reward_from=llm_task_index=12_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=12_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 sha256:496d97394e097575b6e037199f6cfb8ba91408a063dff727be0ec56775229ed4
3
+ size 26198
reward_1707748949.611114_config.reward_from=llm_task_index=12_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=12_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_1707748949.611114_config.reward_from=llm_task_index=13_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=13_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 -19.5 0.0 -19.5 -19.5 -295.18323 0.0 -295.18323 -295.18323 0.004156622 0.04656521 0.05951858 -0.074503504 0.3378471 1.1905972957611084
reward_1707748949.611114_config.reward_from=llm_task_index=13_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=13_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 sha256:5ebd032ec441a06f6968ca2b16b51682cd6e79833aa1efdec1cf38c19e364842
3
+ size 26198
reward_1707748949.611114_config.reward_from=llm_task_index=13_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=13_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_1707748949.611114_config.reward_from=llm_task_index=13_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=13_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 39.0 0.0 39.0 39.0 -238.53288 0.0 -238.53288 -238.53288 0.0017500948 0.04590834 0.060370363 -0.07369913 0.32459962 1.2593295574188232
reward_1707748949.611114_config.reward_from=llm_task_index=13_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=13_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:c6aa19c4f4bad0ed96e8b7e614406ca263a6b40917c0fd32209306f0def6c65b
3
+ size 26198
reward_1707748949.611114_config.reward_from=llm_task_index=13_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=13_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_1707748949.611114_config.reward_from=llm_task_index=13_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=13_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 19.5 0.0 19.5 19.5 -201.3899 0.0 -201.3899 -201.3899 0.009826353 0.047053043 0.06222207 -0.07194317 0.29570273 1.1741359233856201
reward_1707748949.611114_config.reward_from=llm_task_index=13_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=13_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 sha256:67e38b43dbb2bf642fbf4d4f3f5280e8090d7c33344afa5885fce20fb44f6578
3
+ size 26198
reward_1707748949.611114_config.reward_from=llm_task_index=13_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=13_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_1707748949.611114_config.reward_from=llm_task_index=13_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=13_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 39.0 0.0 39.0 39.0 -227.24684 0.0 -227.24684 -227.24684 -0.00016120703 0.044984415 0.061915003 -0.07223507 0.3005043 1.2381904125213623
reward_1707748949.611114_config.reward_from=llm_task_index=13_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=13_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 sha256:0276f41badc0b9693f26de5f14bd31136ea2dd23cd6bf316eb7af475477c5ace
3
+ size 26198
reward_1707748949.611114_config.reward_from=llm_task_index=13_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=13_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_1707748949.611114_config.reward_from=llm_task_index=14_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=14_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
+ 0 214.0 0.0 214.0 214.0 -55.185673 0.0 -55.185673 -55.185673 0.0041629653 0.04669452 0.060185533 -0.073873825 0.32747644 1.1202867031097412
reward_1707748949.611114_config.reward_from=llm_task_index=14_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=14_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:f504428ffdfb0cf9d1594a1b55a3e11b894b42949703ac99e2bce2f8b7c3b881
3
+ size 26198
reward_1707748949.611114_config.reward_from=llm_task_index=14_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=14_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_1707748949.611114_config.reward_from=llm_task_index=14_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=14_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
+ 0 942.0 0.0 942.0 942.0 609.8738 0.0 609.8738 609.8738 -0.0059993602 0.043736286 0.05904211 -0.07495253 0.34524554 1.22102689743042
reward_1707748949.611114_config.reward_from=llm_task_index=14_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=14_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:fe9eb815636f624c749b5538b6dec2e1a57cb9e3f6f1f66056932ca973e41db3
3
+ size 26198
reward_1707748949.611114_config.reward_from=llm_task_index=14_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=14_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_1707748949.611114_config.reward_from=llm_task_index=14_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=14_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
+ 0 214.0 0.0 214.0 214.0 -69.954895 0.0 -69.954895 -69.954895 0.00080094236 0.046026777 0.05988761 -0.07415526 0.332111 1.2477691173553467
reward_1707748949.611114_config.reward_from=llm_task_index=14_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=14_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:b6d2ade6820a3cede6670c9a268475e3000e5b7fb0d97e86727b3e05447c99d0
3
+ size 26198
reward_1707748949.611114_config.reward_from=llm_task_index=14_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=14_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_1707748949.611114_config.reward_from=llm_task_index=14_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=14_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
+ 0 923.0 0.0 923.0 923.0 590.87384 0.0 590.87384 590.87384 -0.0059993602 0.043736286 0.05904211 -0.07495253 0.34524554 1.3280327320098877
reward_1707748949.611114_config.reward_from=llm_task_index=14_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=14_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:a406086c664bee26218c78a53b7223c30506c5165b93c4b401142da600c681b5
3
+ size 26198
reward_1707748949.611114_config.reward_from=llm_task_index=14_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=14_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_1707748949.611114_config.reward_from=llm_task_index=15_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=15_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 1848.2 0.0 1848.2 1848.2 1559.9917 0.0 1559.9917 1559.9917 -0.0035963813 0.043860883 0.06137715 -0.07274568 0.30890533 1.2274601459503174
reward_1707748949.611114_config.reward_from=llm_task_index=15_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=15_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:c638df4a59acb30559366536fcc6285741c7b2dc3646efdc4cd87ea036fccb0c
3
+ size 26198
reward_1707748949.611114_config.reward_from=llm_task_index=15_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=15_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_1707748949.611114_config.reward_from=llm_task_index=15_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=15_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 25202.5 0.0 25202.5 25202.5 24892.254 0.0 24892.254 24892.254 -0.004313882 0.043747842 0.060352977 -0.073715575 0.3248704 1.2146625518798828
reward_1707748949.611114_config.reward_from=llm_task_index=15_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=15_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 sha256:0bc2f0486657dfe33ac12a426e29cde5f716a457eea69ca9dc4b3829f3c48b3c
3
+ size 26198
reward_1707748949.611114_config.reward_from=llm_task_index=15_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=15_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_1707748949.611114_config.reward_from=llm_task_index=15_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=15_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 2973.0 0.0 2973.0 2973.0 2637.7659 0.0 2637.7659 2637.7659 -0.0023830372 0.045824938 0.055983238 -0.07781964 0.39254695 1.1980488300323486
reward_1707748949.611114_config.reward_from=llm_task_index=15_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=15_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:c88e2db2f193ae4b3dabd26e8def3434d2c688170c461954b5c36a073a53a222
3
+ size 26198
reward_1707748949.611114_config.reward_from=llm_task_index=15_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=15_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_1707748949.611114_config.reward_from=llm_task_index=15_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=15_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 69257.15 0.0 69257.15 69257.15 68971.67 0.0 68971.67 68971.67 -2.2340218e-05 0.044770774 0.060896598 -0.07320111 0.31640127 1.1387743949890137
reward_1707748949.611114_config.reward_from=llm_task_index=15_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=15_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:cdf0d9ab6f67c21b98303a249852b8e82c9160dc8324058929a8d149921b862d
3
+ size 26198
reward_1707748949.611114_config.reward_from=llm_task_index=15_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=15_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_1707748949.611114_config.reward_from=llm_task_index=16_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=16_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
+ 0 469.5 0.0 469.5 469.5 171.60954 0.0 171.60954 171.60954 -0.0040375427 0.043836556 0.06109938 -0.07300901 0.3132392 1.1946899890899658
reward_1707748949.611114_config.reward_from=llm_task_index=16_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.611114_config.reward_from=llm_task_index=16_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 sha256:26770c178b59d57b421b86be066216e9012d6524a7a5adc38ee5c6a6ca495c55
3
+ size 26198