Hugging Face's logo

ezipe
/
reward_learning

Model card Files
xet
Community
ezipe commited on
Commit
2aa458a
·
verified ·
1 Parent(s): c7f1c78

Upload folder using huggingface_hub

Browse files
Files changed (36) hide show
  1. reward_1707748948.8494434_config.reward_from=llm_task_index=10_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=10_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  2. reward_1707748948.8494434_config.reward_from=llm_task_index=10_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=10_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  3. reward_1707748948.8494434_config.reward_from=llm_task_index=10_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=10_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  4. reward_1707748948.8494434_config.reward_from=llm_task_index=10_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=10_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  5. reward_1707748948.8494434_config.reward_from=llm_task_index=10_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=10_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  6. reward_1707748948.8494434_config.reward_from=llm_task_index=10_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=10_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  7. reward_1707748948.8494434_config.reward_from=llm_task_index=10_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=10_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  8. reward_1707748948.8494434_config.reward_from=llm_task_index=10_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=10_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  9. reward_1707748948.8494434_config.reward_from=llm_task_index=10_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=10_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  10. reward_1707748948.8494434_config.reward_from=llm_task_index=10_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=10_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  11. reward_1707748948.8494434_config.reward_from=llm_task_index=10_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=10_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  12. reward_1707748948.8494434_config.reward_from=llm_task_index=10_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=10_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  13. reward_1707748948.8494434_config.reward_from=llm_task_index=11_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=11_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  14. reward_1707748948.8494434_config.reward_from=llm_task_index=11_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=11_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  15. reward_1707748948.8494434_config.reward_from=llm_task_index=11_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=11_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  16. reward_1707748948.8494434_config.reward_from=llm_task_index=11_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=11_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  17. reward_1707748948.8494434_config.reward_from=llm_task_index=11_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=11_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  18. reward_1707748948.8494434_config.reward_from=llm_task_index=11_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=11_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  19. reward_1707748948.8494434_config.reward_from=llm_task_index=11_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=11_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  20. reward_1707748948.8494434_config.reward_from=llm_task_index=11_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=11_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  21. reward_1707748948.8494434_config.reward_from=llm_task_index=11_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=11_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  22. reward_1707748948.8494434_config.reward_from=llm_task_index=11_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=11_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  23. reward_1707748948.8494434_config.reward_from=llm_task_index=11_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=11_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  24. reward_1707748948.8494434_config.reward_from=llm_task_index=11_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=11_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  25. reward_1707748948.8494434_config.reward_from=llm_task_index=9_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=9_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  26. reward_1707748948.8494434_config.reward_from=llm_task_index=9_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=9_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  27. reward_1707748948.8494434_config.reward_from=llm_task_index=9_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=9_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  28. reward_1707748948.8494434_config.reward_from=llm_task_index=9_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=9_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  29. reward_1707748948.8494434_config.reward_from=llm_task_index=9_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=9_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  30. reward_1707748948.8494434_config.reward_from=llm_task_index=9_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=9_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  31. reward_1707748948.8494434_config.reward_from=llm_task_index=9_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=9_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  32. reward_1707748948.8494434_config.reward_from=llm_task_index=9_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=9_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  33. reward_1707748948.8494434_config.reward_from=llm_task_index=9_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=9_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  34. reward_1707748948.8494434_config.reward_from=llm_task_index=9_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=9_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  35. reward_1707748948.8494434_config.reward_from=llm_task_index=9_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=9_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  36. reward_1707748948.8494434_config.reward_from=llm_task_index=9_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=9_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
reward_1707748948.8494434_config.reward_from=llm_task_index=10_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=10_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
+ 0 625.0 0.0 625.0 625.0 316.38385 0.0 316.38385 316.38385 -0.004587063 0.043720983 0.060041465 -0.07400994 0.32971808 1.3237676620483398
reward_1707748948.8494434_config.reward_from=llm_task_index=10_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=10_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 sha256:61e14a0e9723f73cec88bb5ef337a98a60bbb723880487b5b575144dbdb6fd8e
3
+ size 26198
reward_1707748948.8494434_config.reward_from=llm_task_index=10_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=10_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_1707748948.8494434_config.reward_from=llm_task_index=10_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=10_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 2354.0 0.0 2354.0 2354.0 2074.7317 0.0 2074.7317 2074.7317 0.0023907605 0.045787644 0.060506456 -0.07357042 0.3224806 1.6612930297851562
reward_1707748948.8494434_config.reward_from=llm_task_index=10_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=10_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 sha256:36cd6cadb59c3468beed7390835ae2024233b656ecce44fd453a0d1b8aa7fd48
3
+ size 26198
reward_1707748948.8494434_config.reward_from=llm_task_index=10_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=10_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_1707748948.8494434_config.reward_from=llm_task_index=10_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=10_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
+ 0 647.0 0.0 647.0 647.0 360.89197 0.0 360.89197 360.89197 0.0006176396 0.04604034 0.059649844 -0.07437968 0.3358074 1.7680466175079346
reward_1707748948.8494434_config.reward_from=llm_task_index=10_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=10_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:ea9c9e8af794871c71f9a116c4f52b296dd23f617baae062b4ef4e6cc43a2f95
3
+ size 26198
reward_1707748948.8494434_config.reward_from=llm_task_index=10_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=10_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_1707748948.8494434_config.reward_from=llm_task_index=10_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=10_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 2238.75 0.0 2238.75 2238.75 1906.6228 0.0 1906.6228 1906.6228 -0.0059993602 0.043736286 0.05904211 -0.07495253 0.34524554 1.430422067642212
reward_1707748948.8494434_config.reward_from=llm_task_index=10_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=10_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:f8895de78cfcad7769af7a11aeefc58a4be330abbc7636234e8ca11ddd0e9a3b
3
+ size 26198
reward_1707748948.8494434_config.reward_from=llm_task_index=10_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=10_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_1707748948.8494434_config.reward_from=llm_task_index=11_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=11_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 3026.2642 0.0 3026.2642 3026.2642 2751.3645 0.0 2751.3645 2751.3645 0.0015116996 0.046019 0.060323816 -0.07374313 0.32532418 1.2384414672851562
reward_1707748948.8494434_config.reward_from=llm_task_index=11_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=11_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 sha256:7fc0be133025e7f5daee42cc02792ad4040d2c99a15384215e696522a3f45960
3
+ size 26198
reward_1707748948.8494434_config.reward_from=llm_task_index=11_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=11_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_1707748948.8494434_config.reward_from=llm_task_index=11_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=11_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
+ 0 398.66666 0.0 398.66666 398.66666 136.61026 0.0 136.61026 136.61026 0.005419462 0.04637427 0.060047086 -0.06914543 0.3296307 1.6691844463348389
reward_1707748948.8494434_config.reward_from=llm_task_index=11_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=11_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:cbb7e9c88f6145627d92b5d595eba267df2721841fef6f03fcbcbcc3f292d935
3
+ size 26198
reward_1707748948.8494434_config.reward_from=llm_task_index=11_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=11_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_1707748948.8494434_config.reward_from=llm_task_index=11_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=11_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
+ 0 841.6667 0.0 841.6667 841.6667 554.28986 0.0 554.28986 554.28986 0.0023876857 0.046881538 0.05842687 -0.07553137 0.35478613 1.1732330322265625
reward_1707748948.8494434_config.reward_from=llm_task_index=11_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=11_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 sha256:336a714926955f85b749379f0bfac1cde34a9c6c12631221ea3f2a4b26851158
3
+ size 26198
reward_1707748948.8494434_config.reward_from=llm_task_index=11_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=11_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_1707748948.8494434_config.reward_from=llm_task_index=11_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=11_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 50334884.0 0.0 50334884.0 50334884.0 50334600.0 0.0 50334600.0 50334600.0 0.0016184432 0.045863442 0.06027094 -0.07379311 0.3261472 1.1296970844268799
reward_1707748948.8494434_config.reward_from=llm_task_index=11_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=11_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 sha256:119e15483b321ba36d9b04a7c450fd32670df4b30025a85ab58c1a1ebbd80c0c
3
+ size 26198
reward_1707748948.8494434_config.reward_from=llm_task_index=11_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=11_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_1707748948.8494434_config.reward_from=llm_task_index=9_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=9_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 0.0 0.0 0.0 0.0 -289.91953 0.0 -289.91953 -289.91953 -0.0022616072 0.045124255 0.0604596 -0.07361474 0.32321012 1.5675554275512695
reward_1707748948.8494434_config.reward_from=llm_task_index=9_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=9_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 sha256:72e2dae0aab49486156b0658922a1692e280df2ad22eb5943e0d8d7866f84f70
3
+ size 26198
reward_1707748948.8494434_config.reward_from=llm_task_index=9_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=9_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_1707748948.8494434_config.reward_from=llm_task_index=9_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=9_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
+ 0 105.0 0.0 105.0 105.0 -221.14183 0.0 -221.14183 -221.14183 -0.007816804 0.04234601 0.04392085 -0.07385238 0.32712317 1.2745072841644287
reward_1707748948.8494434_config.reward_from=llm_task_index=9_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=9_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 sha256:33f7a738b691745f19400632c7ab1d27610964c362a54c5c0df0a75d62b88bc1
3
+ size 26198
reward_1707748948.8494434_config.reward_from=llm_task_index=9_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=9_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_1707748948.8494434_config.reward_from=llm_task_index=9_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=9_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 0.0 0.0 0.0 0.0 -333.8578 0.0 -333.8578 -333.8578 -0.0066482634 0.04380754 0.058571637 -0.075395264 0.35254255 1.3192360401153564
reward_1707748948.8494434_config.reward_from=llm_task_index=9_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=9_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:e63447a6a467f83a9818680ce55d669e8781fcb38dda915999ab46d44e0270c3
3
+ size 26198
reward_1707748948.8494434_config.reward_from=llm_task_index=9_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=9_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_1707748948.8494434_config.reward_from=llm_task_index=9_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=9_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
+ 0 914.0 0.0 914.0 914.0 587.8582 0.0 587.8582 587.8582 -0.007816804 0.04234601 0.04392085 -0.07385238 0.32712317 1.3053889274597168
reward_1707748948.8494434_config.reward_from=llm_task_index=9_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=9_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:bbd1d293ae8b804849546a19f414c18034d0c48ef84b6b300d449969596fa705
3
+ size 26198
reward_1707748948.8494434_config.reward_from=llm_task_index=9_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748948.8494434_config.reward_from=llm_task_index=9_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