Hugging Face's logo

ezipe
/
reward_learning

Model card Files
xet
Community
ezipe commited on
Commit
57128ca
·
verified ·
1 Parent(s): c0ecb8b

Upload folder using huggingface_hub

Browse files
Files changed (34) hide show
  1. reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  2. reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  3. reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  4. reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  5. reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  6. reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  7. reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  8. reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  9. reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  10. reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  11. reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  12. reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  13. reward_1707748947.8148458_config.reward_from=llm_task_index=1_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=1_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  14. reward_1707748947.8148458_config.reward_from=llm_task_index=1_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=1_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  15. reward_1707748947.8148458_config.reward_from=llm_task_index=1_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=1_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  16. reward_1707748947.8148458_config.reward_from=llm_task_index=1_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=1_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +0 -0
  17. reward_1707748947.8148458_config.reward_from=llm_task_index=1_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=1_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  18. reward_1707748947.8148458_config.reward_from=llm_task_index=1_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=1_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  19. reward_1707748947.8148458_config.reward_from=llm_task_index=1_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=1_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  20. reward_1707748947.8148458_config.reward_from=llm_task_index=1_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=1_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  21. reward_1707748947.8148458_config.reward_from=llm_task_index=1_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=1_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  22. reward_1707748947.8148458_config.reward_from=llm_task_index=1_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=1_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  23. reward_1707748947.8148458_config.reward_from=llm_task_index=2_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=2_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  24. reward_1707748947.8148458_config.reward_from=llm_task_index=2_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=2_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  25. reward_1707748947.8148458_config.reward_from=llm_task_index=2_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=2_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  26. reward_1707748947.8148458_config.reward_from=llm_task_index=2_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=2_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  27. reward_1707748947.8148458_config.reward_from=llm_task_index=2_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=2_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  28. reward_1707748947.8148458_config.reward_from=llm_task_index=2_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=2_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  29. reward_1707748947.8148458_config.reward_from=llm_task_index=2_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=2_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  30. reward_1707748947.8148458_config.reward_from=llm_task_index=2_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=2_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  31. reward_1707748947.8148458_config.reward_from=llm_task_index=2_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=2_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  32. reward_1707748947.8148458_config.reward_from=llm_task_index=2_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=2_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  33. reward_1707748947.8148458_config.reward_from=llm_task_index=2_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=2_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  34. reward_1707748947.8148458_config.reward_from=llm_task_index=2_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=2_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 981.0 0.0 981.0 981.0 687.3424 0.0 687.3424 687.3424 0.00029671047 0.045972057 0.059208844 -0.07479544 0.34265745 1.94022798538208
reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf665e2020ee033a3c709c613819ccdc4bdcf015541680183368699f15a5e2fb
3
+ size 26198
reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92ea2e1ec564527e3eda889a660916cf8391e187b0b03eca4b7d2467c96d0991
3
+ size 13916
reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 144.4 0.0 144.4 144.4 -181.7418 0.0 -181.7418 -181.7418 -0.007816804 0.04234601 0.04392085 -0.07385238 0.32712317 1.2018802165985107
reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:489f0beda7f68781301d1426f00b56718b57cd71b7d80a6fd298a1d73ecfca2f
3
+ size 26198
reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92ea2e1ec564527e3eda889a660916cf8391e187b0b03eca4b7d2467c96d0991
3
+ size 13916
reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 931.6 0.0 931.6 931.6 668.88257 0.0 668.88257 668.88257 8.7622066e-05 0.045083374 0.062423024 -0.07175202 0.2925585 1.244737148284912
reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d47d45298bc283431f7f81c0b6dc86745fb7bb95628140f9135d84bb7e51407
3
+ size 26198
reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92ea2e1ec564527e3eda889a660916cf8391e187b0b03eca4b7d2467c96d0991
3
+ size 13916
reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 1.275 0.0 1.275 1.275 -324.86673 0.0 -324.86673 -324.86673 -0.007816804 0.04234601 0.04392085 -0.07385238 0.32712317 1.2792041301727295
reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0d3878d6472e9a8c335ca3b2ef26e8e72595b5ed3461835c35924b5f94f0e9a
3
+ size 26198
reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=0_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92ea2e1ec564527e3eda889a660916cf8391e187b0b03eca4b7d2467c96d0991
3
+ size 13916
reward_1707748947.8148458_config.reward_from=llm_task_index=1_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=1_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 -336.37268 0.0 -336.37268 -336.37268 -0.0018367671 0.045723826 0.056250878 -0.077569835 0.3884212 1.1619153022766113
reward_1707748947.8148458_config.reward_from=llm_task_index=1_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=1_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 sha256:893138a7f88889d0cbfaf2241dc26183a8a3c797bba8b4914d4e491833127039
3
+ size 26198
reward_1707748947.8148458_config.reward_from=llm_task_index=1_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=1_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_1707748947.8148458_config.reward_from=llm_task_index=1_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=1_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt ADDED
File without changes
reward_1707748947.8148458_config.reward_from=llm_task_index=1_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=1_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 -307.66922 0.0 -307.66922 -307.66922 0.00033607674 0.045715366 0.058235243 -0.07084871 0.35775492 1.3463826179504395
reward_1707748947.8148458_config.reward_from=llm_task_index=1_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=1_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:b078af9652a88ce81e7f0b6a3ec0f3558feb303ed76a019dbbf3a4854b2eb949
3
+ size 26198
reward_1707748947.8148458_config.reward_from=llm_task_index=1_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=1_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_1707748947.8148458_config.reward_from=llm_task_index=1_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=1_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 0.0 0.0 0.0 0.0 -263.7574 0.0 -263.7574 -263.7574 0.0005156792 0.04501936 0.06222274 -0.07194253 0.29569212 1.278496265411377
reward_1707748947.8148458_config.reward_from=llm_task_index=1_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=1_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:d1f532bb6d43a0c53c1e1a4bcea5e46001d9540e396fe19b826f4f0285815007
3
+ size 26198
reward_1707748947.8148458_config.reward_from=llm_task_index=1_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=1_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_1707748947.8148458_config.reward_from=llm_task_index=2_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=2_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
+ 0 390.0 0.0 390.0 390.0 47.270218 0.0 47.270218 47.270218 -0.0048859753 0.044931803 0.05671671 -0.07713459 0.38123447 1.2494497299194336
reward_1707748947.8148458_config.reward_from=llm_task_index=2_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=2_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:cc59108df7a1971dca18a334fabd62a0ad4cef71738436377ec8d2cf60b7fffa
3
+ size 26198
reward_1707748947.8148458_config.reward_from=llm_task_index=2_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=2_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_1707748947.8148458_config.reward_from=llm_task_index=2_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=2_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
+ 0 390.0 0.0 390.0 390.0 101.295364 0.0 101.295364 101.295364 0.0013034265 0.045714512 0.05927295 -0.07473506 0.34166226 1.249769687652588
reward_1707748947.8148458_config.reward_from=llm_task_index=2_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=2_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 sha256:4bd56f8beeb4672d463c4cbe4a9581e02d2b9974d418cb4f3fb11ee91d6a30a8
3
+ size 26198
reward_1707748947.8148458_config.reward_from=llm_task_index=2_stage=0_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=2_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_1707748947.8148458_config.reward_from=llm_task_index=2_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=2_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 9917.0 0.0 9917.0 9917.0 9656.23 0.0 9656.23 9656.23 0.0035738763 0.04564543 0.061350044 -0.072771356 0.3093281 1.2057149410247803
reward_1707748947.8148458_config.reward_from=llm_task_index=2_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=2_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 sha256:52661b2f086d4e56a6b78c24edda879817f16adaf7c00a3d1dda18a511551336
3
+ size 26198
reward_1707748947.8148458_config.reward_from=llm_task_index=2_stage=1_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=2_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_1707748947.8148458_config.reward_from=llm_task_index=2_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=2_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 2020.0 0.0 2020.0 2020.0 1731.0165 0.0 1731.0165 1731.0165 0.0015851272 0.045669205 0.05976066 -0.0742751 0.33408484 1.2185444831848145
reward_1707748947.8148458_config.reward_from=llm_task_index=2_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=2_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:a88d130ef2dbba6045f7930a87fbe258b48d65882f1a27bcf82a27b00c7c8a78
3
+ size 26198
reward_1707748947.8148458_config.reward_from=llm_task_index=2_stage=1_iteration=1_n21b7.0dcounterexamplersample_randomp0/reward_1707748947.8148458_config.reward_from=llm_task_index=2_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