Hugging Face's logo

ezipe
/
reward_learning

Model card Files
xet
Community
ezipe commited on
Commit
c7f1c78
·
verified ·
1 Parent(s): a908af8

Upload folder using huggingface_hub

Browse files
Files changed (36) hide show
  1. reward_1707748949.81621_config.reward_from=llm_task_index=3_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=3_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  2. reward_1707748949.81621_config.reward_from=llm_task_index=3_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=3_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  3. reward_1707748949.81621_config.reward_from=llm_task_index=3_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=3_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  4. reward_1707748949.81621_config.reward_from=llm_task_index=3_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=3_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  5. reward_1707748949.81621_config.reward_from=llm_task_index=3_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=3_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  6. reward_1707748949.81621_config.reward_from=llm_task_index=3_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=3_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  7. reward_1707748949.81621_config.reward_from=llm_task_index=3_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=3_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  8. reward_1707748949.81621_config.reward_from=llm_task_index=3_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=3_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  9. reward_1707748949.81621_config.reward_from=llm_task_index=3_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=3_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  10. reward_1707748949.81621_config.reward_from=llm_task_index=3_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=3_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  11. reward_1707748949.81621_config.reward_from=llm_task_index=3_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=3_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  12. reward_1707748949.81621_config.reward_from=llm_task_index=3_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=3_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  13. reward_1707748949.81621_config.reward_from=llm_task_index=4_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=4_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  14. reward_1707748949.81621_config.reward_from=llm_task_index=4_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=4_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  15. reward_1707748949.81621_config.reward_from=llm_task_index=4_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=4_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  16. reward_1707748949.81621_config.reward_from=llm_task_index=4_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=4_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  17. reward_1707748949.81621_config.reward_from=llm_task_index=4_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=4_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  18. reward_1707748949.81621_config.reward_from=llm_task_index=4_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=4_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  19. reward_1707748949.81621_config.reward_from=llm_task_index=4_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=4_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  20. reward_1707748949.81621_config.reward_from=llm_task_index=4_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=4_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  21. reward_1707748949.81621_config.reward_from=llm_task_index=4_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=4_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  22. reward_1707748949.81621_config.reward_from=llm_task_index=4_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=4_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  23. reward_1707748949.81621_config.reward_from=llm_task_index=4_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=4_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  24. reward_1707748949.81621_config.reward_from=llm_task_index=4_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=4_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  25. reward_1707748949.81621_config.reward_from=llm_task_index=5_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=5_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  26. reward_1707748949.81621_config.reward_from=llm_task_index=5_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=5_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  27. reward_1707748949.81621_config.reward_from=llm_task_index=5_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=5_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  28. reward_1707748949.81621_config.reward_from=llm_task_index=5_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=5_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  29. reward_1707748949.81621_config.reward_from=llm_task_index=5_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=5_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  30. reward_1707748949.81621_config.reward_from=llm_task_index=5_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=5_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  31. reward_1707748949.81621_config.reward_from=llm_task_index=5_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=5_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  32. reward_1707748949.81621_config.reward_from=llm_task_index=5_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=5_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  33. reward_1707748949.81621_config.reward_from=llm_task_index=5_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=5_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  34. reward_1707748949.81621_config.reward_from=llm_task_index=5_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=5_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  35. reward_1707748949.81621_config.reward_from=llm_task_index=5_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=5_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  36. reward_1707748949.81621_config.reward_from=llm_task_index=5_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=5_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
reward_1707748949.81621_config.reward_from=llm_task_index=3_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=3_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 915700.0 0.0 915700.0 915700.0 915373.8 0.0 915373.8 915373.8 -0.007816804 0.04234601 0.04392085 -0.07385238 0.32712317 2.23047137260437
reward_1707748949.81621_config.reward_from=llm_task_index=3_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=3_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 sha256:8f943d3ff8b444b6266145b65f49c8c22f0f9787de0a66926c899d53fe4782a4
3
+ size 26198
reward_1707748949.81621_config.reward_from=llm_task_index=3_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=3_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_1707748949.81621_config.reward_from=llm_task_index=3_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=3_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 5828.0 0.0 5828.0 5828.0 5545.189 0.0 5545.189 5545.189 -0.00026749764 0.044946436 0.061300676 -0.072818175 0.3100988 1.2785882949829102
reward_1707748949.81621_config.reward_from=llm_task_index=3_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=3_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 sha256:434212df6d7ea5e8b0fcf6ddd3b4c6ed6c464ebdb2aecfb72cfc2ecf72fac25b
3
+ size 26198
reward_1707748949.81621_config.reward_from=llm_task_index=3_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=3_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_1707748949.81621_config.reward_from=llm_task_index=3_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=3_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
+ 0 650.0 0.0 650.0 650.0 333.37833 0.0 333.37833 333.37833 -0.0046685985 0.04370932 0.059789453 -0.07424792 0.33363718 1.2192771434783936
reward_1707748949.81621_config.reward_from=llm_task_index=3_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=3_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 sha256:1c92ab4bb85220b51b81e9d652260e1060c010b5194b3e66299016e95b6dbf97
3
+ size 26198
reward_1707748949.81621_config.reward_from=llm_task_index=3_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=3_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_1707748949.81621_config.reward_from=llm_task_index=3_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=3_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 29300.0 0.0 29300.0 29300.0 28991.383 0.0 28991.383 28991.383 -0.004587063 0.043720983 0.060041465 -0.07400994 0.32971808 1.2852070331573486
reward_1707748949.81621_config.reward_from=llm_task_index=3_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=3_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 sha256:9f561355ecbdd4f5ee23e60a870eb6e5d3673d77660161a0678d52e6fb20568c
3
+ size 26198
reward_1707748949.81621_config.reward_from=llm_task_index=3_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=3_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_1707748949.81621_config.reward_from=llm_task_index=4_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=4_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
+ 0 989.0 0.0 989.0 989.0 662.8583 0.0 662.8583 662.8583 -0.007816804 0.04234601 0.04392085 -0.07385238 0.32712317 1.3432528972625732
reward_1707748949.81621_config.reward_from=llm_task_index=4_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=4_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 sha256:40962ccfa34a59bb81aee6ff5c462e571e2ea282dbfe7611a2b37a5ec9a7a3af
3
+ size 26198
reward_1707748949.81621_config.reward_from=llm_task_index=4_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=4_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_1707748949.81621_config.reward_from=llm_task_index=4_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=4_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 3036.0 0.0 3036.0 3036.0 2755.6565 0.0 2755.6565 2755.6565 0.0027563502 0.045634933 0.060281668 -0.07378297 0.3259803 1.1344637870788574
reward_1707748949.81621_config.reward_from=llm_task_index=4_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=4_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 sha256:5fc738f90f6438409a62a510bf029d5a1b91b2ebf867210acc07759fe8b8f72b
3
+ size 26198
reward_1707748949.81621_config.reward_from=llm_task_index=4_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=4_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_1707748949.81621_config.reward_from=llm_task_index=4_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=4_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 5484.0 0.0 5484.0 5484.0 5157.8574 0.0 5157.8574 5157.8574 -0.007816804 0.04234601 0.04392085 -0.07385238 0.32712317 1.2542459964752197
reward_1707748949.81621_config.reward_from=llm_task_index=4_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=4_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:f9ffe6a2eca2b95772030afbcecdd54ddb3cb1edfda205e16ebb6df02d23b157
3
+ size 26198
reward_1707748949.81621_config.reward_from=llm_task_index=4_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=4_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_1707748949.81621_config.reward_from=llm_task_index=4_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=4_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
+ 0 960.0 0.0 960.0 960.0 650.6313 0.0 650.6313 650.6313 -0.0017648827 0.044846732 0.05935812 -0.07465479 0.34033966 1.8772311210632324
reward_1707748949.81621_config.reward_from=llm_task_index=4_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=4_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 sha256:0cc6eea531e6d2b76bc685a674c7bb7f582f5073564c22949cb7fd32dd6312ae
3
+ size 26198
reward_1707748949.81621_config.reward_from=llm_task_index=4_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=4_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_1707748949.81621_config.reward_from=llm_task_index=5_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_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
+ 0 909.0 0.0 909.0 909.0 636.2229 0.0 636.2229 636.2229 -0.00027516263 0.04504237 0.061487578 -0.07264087 0.30718124 1.1947624683380127
reward_1707748949.81621_config.reward_from=llm_task_index=5_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_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 sha256:6eebeccf54bdff3ba546322e5e492c0d14d9f1a702548f9797abcb2175d92114
3
+ size 26198
reward_1707748949.81621_config.reward_from=llm_task_index=5_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_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_1707748949.81621_config.reward_from=llm_task_index=5_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_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
+ 0 291.0 0.0 291.0 291.0 35.541943 0.0 35.541943 35.541943 0.0048033874 0.046840604 0.060836416 -0.07325809 0.3173392 1.19264554977417
reward_1707748949.81621_config.reward_from=llm_task_index=5_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_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:b6f988a8c935d076205ccaf87b3d1f5acf785e8c8041f9f938c74b0ceba5d0d7
3
+ size 26198
reward_1707748949.81621_config.reward_from=llm_task_index=5_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_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_1707748949.81621_config.reward_from=llm_task_index=5_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=5_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
+ 0 291.0 0.0 291.0 291.0 -26.00079 0.0 -26.00079 -26.00079 -0.0052386457 0.0438325 0.059876367 -0.074165866 0.33228594 1.5589053630828857
reward_1707748949.81621_config.reward_from=llm_task_index=5_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=5_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 sha256:9d4fb83b7e6a5a8e8dec7547c047c9da1edfc5e92e7679360fda8a2f7662749b
3
+ size 26198
reward_1707748949.81621_config.reward_from=llm_task_index=5_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=5_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_1707748949.81621_config.reward_from=llm_task_index=5_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=5_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
+ 0 286.0 0.0 286.0 286.0 -51.13057 0.0 -51.13057 -51.13057 -0.005968874 0.043723438 0.05839706 -0.07555939 0.3552482 1.3142452239990234
reward_1707748949.81621_config.reward_from=llm_task_index=5_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=5_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 sha256:731a8c7b020d7fa3c2fbe9b2bd5b7e90c0a606fd1d9d23bfc5156c7ca3a56034
3
+ size 26198
reward_1707748949.81621_config.reward_from=llm_task_index=5_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748949.81621_config.reward_from=llm_task_index=5_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