Hugging Face's logo

ezipe
/
reward_learning

Model card Files
xet
 Community
ezipe commited on
Commit
780e46e
·
verified ·
1 Parent(s): 5ec774a

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_1707780024.5255785_rfbase_cotTrue_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/progress.txt +11 -0
  2. reward_1707780024.5255785_rfbase_cotTrue_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/pyt_save/model.pt +3 -0
  3. reward_1707780024.5255785_rfbase_cotTrue_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/vars.pkl +3 -0
  4. reward_1707780024.5255785_rfbase_cotTrue_task_index=10_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=10_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/progress.txt +11 -0
  5. reward_1707780024.5255785_rfbase_cotTrue_task_index=10_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=10_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/pyt_save/model.pt +3 -0
  6. reward_1707780024.5255785_rfbase_cotTrue_task_index=10_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=10_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/vars.pkl +3 -0
  7. reward_1707780024.5255785_rfbase_cotTrue_task_index=10_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=10_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/progress.txt +11 -0
  8. reward_1707780024.5255785_rfbase_cotTrue_task_index=10_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=10_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/pyt_save/model.pt +3 -0
  9. reward_1707780024.5255785_rfbase_cotTrue_task_index=10_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=10_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/vars.pkl +3 -0
  10. reward_1707780024.5255785_rfbase_cotTrue_task_index=11_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=11_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/progress.txt +11 -0
  11. reward_1707780024.5255785_rfbase_cotTrue_task_index=11_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=11_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/pyt_save/model.pt +3 -0
  12. reward_1707780024.5255785_rfbase_cotTrue_task_index=11_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=11_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/vars.pkl +3 -0
  13. reward_1707780024.5255785_rfbase_cotTrue_task_index=11_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=11_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/progress.txt +11 -0
  14. reward_1707780024.5255785_rfbase_cotTrue_task_index=11_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=11_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/pyt_save/model.pt +3 -0
  15. reward_1707780024.5255785_rfbase_cotTrue_task_index=11_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=11_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/vars.pkl +3 -0
  16. reward_1707780024.5255785_rfbase_cotTrue_task_index=12_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=12_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/progress.txt +11 -0
  17. reward_1707780024.5255785_rfbase_cotTrue_task_index=12_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=12_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/pyt_save/model.pt +3 -0
  18. reward_1707780024.5255785_rfbase_cotTrue_task_index=12_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=12_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/vars.pkl +3 -0
  19. reward_1707780024.5255785_rfbase_cotTrue_task_index=12_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=12_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/progress.txt +11 -0
  20. reward_1707780024.5255785_rfbase_cotTrue_task_index=12_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=12_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/pyt_save/model.pt +3 -0
  21. reward_1707780024.5255785_rfbase_cotTrue_task_index=12_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=12_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/vars.pkl +3 -0
  22. reward_1707780024.5255785_rfbase_cotTrue_task_index=13_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=13_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/progress.txt +11 -0
  23. reward_1707780024.5255785_rfbase_cotTrue_task_index=13_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=13_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/pyt_save/model.pt +3 -0
  24. reward_1707780024.5255785_rfbase_cotTrue_task_index=13_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=13_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/vars.pkl +3 -0
  25. reward_1707780024.5255785_rfbase_cotTrue_task_index=13_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=13_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/progress.txt +11 -0
  26. reward_1707780024.5255785_rfbase_cotTrue_task_index=13_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=13_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/pyt_save/model.pt +3 -0
  27. reward_1707780024.5255785_rfbase_cotTrue_task_index=13_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=13_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/vars.pkl +3 -0
  28. reward_1707780024.5255785_rfbase_cotTrue_task_index=14_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=14_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/progress.txt +11 -0
  29. reward_1707780024.5255785_rfbase_cotTrue_task_index=14_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=14_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/pyt_save/model.pt +3 -0
  30. reward_1707780024.5255785_rfbase_cotTrue_task_index=14_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=14_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/vars.pkl +3 -0
  31. reward_1707780024.5255785_rfbase_cotTrue_task_index=14_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=14_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/progress.txt +11 -0
  32. reward_1707780024.5255785_rfbase_cotTrue_task_index=14_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=14_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/pyt_save/model.pt +3 -0
  33. reward_1707780024.5255785_rfbase_cotTrue_task_index=14_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=14_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/vars.pkl +3 -0
  34. reward_1707780024.5255785_rfbase_cotTrue_task_index=15_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=15_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/progress.txt +11 -0
  35. reward_1707780024.5255785_rfbase_cotTrue_task_index=15_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=15_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/pyt_save/model.pt +3 -0
  36. reward_1707780024.5255785_rfbase_cotTrue_task_index=15_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=15_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/vars.pkl +3 -0
  37. reward_1707780024.5255785_rfbase_cotTrue_task_index=15_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=15_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/progress.txt +11 -0
  38. reward_1707780024.5255785_rfbase_cotTrue_task_index=15_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=15_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/pyt_save/model.pt +3 -0
  39. reward_1707780024.5255785_rfbase_cotTrue_task_index=15_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=15_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/vars.pkl +3 -0
  40. reward_1707780024.5255785_rfbase_cotTrue_task_index=1_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=1_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/progress.txt +11 -0
  41. reward_1707780024.5255785_rfbase_cotTrue_task_index=1_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=1_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/pyt_save/model.pt +3 -0
  42. reward_1707780024.5255785_rfbase_cotTrue_task_index=1_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=1_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/vars.pkl +3 -0
  43. reward_1707780024.5255785_rfbase_cotTrue_task_index=2_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=2_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/progress.txt +11 -0
  44. reward_1707780024.5255785_rfbase_cotTrue_task_index=2_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=2_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/pyt_save/model.pt +3 -0
  45. reward_1707780024.5255785_rfbase_cotTrue_task_index=2_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=2_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/vars.pkl +3 -0
  46. reward_1707780024.5255785_rfbase_cotTrue_task_index=3_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=3_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/progress.txt +11 -0
  47. reward_1707780024.5255785_rfbase_cotTrue_task_index=3_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=3_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/pyt_save/model.pt +3 -0
  48. reward_1707780024.5255785_rfbase_cotTrue_task_index=3_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=3_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/vars.pkl +3 -0
  49. reward_1707780024.5255785_rfbase_cotTrue_task_index=4_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=4_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/progress.txt +11 -0
  50. reward_1707780024.5255785_rfbase_cotTrue_task_index=4_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=4_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/pyt_save/model.pt +3 -0
reward_1707780024.5255785_rfbase_cotTrue_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/progress.txt ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 954.0 0.0 954.0 954.0 676.30365 0.0 676.30365 676.30365 0.14188744 0.029580075 0.18554002 0.099726446 0.23613659 1.685011386871338
3
+ 1 1088.0 0.0 1088.0 1088.0 875.66016 0.0 875.66016 875.66016 2.7156632 0.26439393 3.124498 1.9588704 0.2846375 3.354931354522705
4
+ 2 1067.0 0.0 1067.0 1067.0 933.66156 0.0 933.66156 933.66156 3.7461822 0.7800167 4.7676888 2.1093745 0.20866704 5.025254249572754
5
+ 3 1118.0 0.0 1118.0 1118.0 947.54987 0.0 947.54987 947.54987 4.13867 0.97118366 5.501315 2.3923388 0.22726646 6.718552827835083
6
+ 4 1146.0 0.0 1146.0 1146.0 875.4446 0.0 875.4446 875.4446 4.1683536 0.95543545 5.538224 2.405601 0.35046008 8.415615320205688
7
+ 5 794.0 0.0 794.0 794.0 794.0 0.0 794.0 794.0 3.7854521 0.7186139 4.9333296 2.130577 0.2753125 10.088018417358398
8
+ 6 1138.0 0.0 1138.0 1138.0 918.3662 0.0 918.3662 918.3662 3.632194 0.25992176 4.0443754 2.6205857 0.2599218 11.742835283279419
9
+ 7 1138.0 0.0 1138.0 1138.0 934.5082 0.0 934.5082 934.5082 4.052964 0.7706236 5.1679006 2.463 0.25029743 13.396860122680664
10
+ 8 816.0 0.0 816.0 816.0 804.1616 0.0 804.1616 804.1616 4.123271 0.911171 5.480109 2.1358142 0.2818742 15.051286458969116
11
+ 9 1110.0 0.0 1110.0 1110.0 914.8971 0.0 914.8971 914.8971 3.742129 0.3038148 4.1755457 2.754515 0.2608328 16.70838165283203
reward_1707780024.5255785_rfbase_cotTrue_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee031b8ea45491362e43c7ce674d39ecb36e746010f6b95e465253ff86c21ef9
3
+ size 26198
reward_1707780024.5255785_rfbase_cotTrue_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=0_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c3c0e5ddaa6502219c5a3b188956e89c1de4d56482f37e86b0bd5ee366b89ae
3
+ size 13916
reward_1707780024.5255785_rfbase_cotTrue_task_index=10_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=10_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/progress.txt ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 997.0 0.0 997.0 997.0 1058.7911 0.0 1058.7911 1058.7911 0.21737418 0.042151038 0.28000772 0.15522087 -0.052144095 1.51759934425354
3
+ 1 1136.0 0.0 1136.0 1136.0 1197.8588 0.0 1197.8588 1197.8588 4.1114125 0.24794304 4.4734383 3.6201067 -0.034405142 3.0470921993255615
4
+ 2 1102.0 0.0 1102.0 1102.0 1221.4424 0.0 1221.4424 1221.4424 5.045687 1.1366005 6.9132295 3.5108063 -0.06643066 4.5611960887908936
5
+ 3 1096.0 0.0 1096.0 1096.0 1184.7007 0.0 1184.7007 1184.7007 5.3385153 1.1670407 7.4819694 3.6490781 -0.049916 6.074115991592407
6
+ 4 1109.0 0.0 1109.0 1109.0 1199.6577 0.0 1199.6577 1199.6577 5.2527514 1.1154491 7.4085336 3.6039195 -0.050365567 7.692310333251953
7
+ 5 1115.0 0.0 1115.0 1115.0 1207.973 0.0 1207.973 1207.973 5.2693186 1.3570057 8.087105 3.36601 -0.05167994 9.33620572090149
8
+ 6 1162.0 0.0 1162.0 1162.0 1264.7056 0.0 1264.7056 1264.7056 5.2789917 1.4095856 8.628875 3.575611 -0.057090417 10.972888946533203
9
+ 7 1114.0 0.0 1114.0 1114.0 1283.9711 0.0 1283.9711 1283.9711 5.4764786 1.4388483 8.887676 3.9530437 -0.09442891 12.60637092590332
10
+ 8 1122.0 0.0 1122.0 1122.0 1244.4823 0.0 1244.4823 1244.4823 5.741321 1.2205355 8.815638 4.464262 -0.06808375 14.243744611740112
11
+ 9 1144.0 0.0 1144.0 1144.0 1196.1349 0.0 1196.1349 1196.1349 5.5388002 1.3731841 8.808408 4.0520897 -0.028963044 15.886062622070312
reward_1707780024.5255785_rfbase_cotTrue_task_index=10_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=10_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d47a7445193fafa260f96a14587ab71d6260743127df121e945093162a55331
3
+ size 26198
reward_1707780024.5255785_rfbase_cotTrue_task_index=10_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=10_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:770168b3aaef05c84af851d3036d265dcee4f037db63d5c1823616342f1a4a47
3
+ size 13916
reward_1707780024.5255785_rfbase_cotTrue_task_index=10_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=10_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/progress.txt ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 969.0 0.0 969.0 969.0 672.0358 0.0 672.0358 672.0358 0.13857247 0.028742015 0.18557829 0.0976936 0.23910148 1.7235760688781738
3
+ 1 1129.0 0.0 1129.0 1129.0 892.93854 0.0 892.93854 892.93854 2.7903426 0.26809582 3.1833777 2.220827 0.28893682 3.436563491821289
4
+ 2 1108.0 0.0 1108.0 1108.0 950.0444 0.0 950.0444 950.0444 3.851257 0.8142764 4.8837566 1.9756792 0.212878 5.146819591522217
5
+ 3 1140.0 0.0 1140.0 1140.0 950.0861 0.0 950.0861 950.0861 4.295231 0.9214783 5.551752 2.4944773 0.23075852 6.881531238555908
6
+ 4 1161.0 0.0 1161.0 1161.0 863.2509 0.0 863.2509 863.2509 4.3084717 0.9155701 5.5986896 2.2193334 0.35488576 8.564943075180054
7
+ 5 777.0 0.0 777.0 777.0 777.0 0.0 777.0 777.0 3.9260473 0.62447685 4.9239335 2.5548265 0.27851456 10.14668321609497
8
+ 6 1156.0 0.0 1156.0 1156.0 915.9216 0.0 915.9216 915.9216 3.6206124 0.2194028 3.9964087 2.7010636 0.26411274 11.727385520935059
9
+ 7 1157.0 0.0 1157.0 1157.0 944.37555 0.0 944.37555 944.37555 4.159795 0.72802097 5.235955 2.2842658 0.25494617 13.318596839904785
10
+ 8 815.0 0.0 815.0 815.0 801.8212 0.0 801.8212 801.8212 4.259533 0.8243809 5.52667 2.2840571 0.28649062 14.910341024398804
11
+ 9 1140.0 0.0 1140.0 1140.0 923.73157 0.0 923.73157 923.73157 3.7145355 0.22608782 4.069248 2.8610425 0.26535982 16.709343433380127
reward_1707780024.5255785_rfbase_cotTrue_task_index=10_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=10_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcbb21a53a76ab81a8916d88fa3128417631d9f9330c82f2352d414e6ac97e7f
3
+ size 26198
reward_1707780024.5255785_rfbase_cotTrue_task_index=10_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=10_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c3c0e5ddaa6502219c5a3b188956e89c1de4d56482f37e86b0bd5ee366b89ae
3
+ size 13916
reward_1707780024.5255785_rfbase_cotTrue_task_index=11_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=11_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/progress.txt ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 1026.0 0.0 1026.0 1026.0 1044.981 0.0 1044.981 1044.981 0.21341561 0.04293082 0.2790111 0.15456104 -0.016195491 1.649519443511963
3
+ 1 1196.0 0.0 1196.0 1196.0 1193.6396 0.0 1193.6396 1193.6396 4.2593827 0.41461113 4.723946 3.4081898 0.0013123602 3.3138091564178467
4
+ 2 1146.0 0.0 1146.0 1146.0 1203.194 0.0 1203.194 1203.194 5.139553 1.3488352 6.81776 2.957762 -0.031880304 4.954023122787476
5
+ 3 1124.0 0.0 1124.0 1124.0 1151.5206 0.0 1151.5206 1151.5206 5.3119226 1.6662182 7.496709 2.5901408 -0.01538305 6.505433797836304
6
+ 4 1176.0 0.0 1176.0 1176.0 1200.1287 0.0 1200.1287 1200.1287 5.2056518 1.5982985 7.3847084 2.3569124 -0.013717562 8.029346942901611
7
+ 5 1158.0 0.0 1158.0 1158.0 1188.6652 0.0 1188.6652 1188.6652 5.3105674 1.782296 7.800515 2.0591264 -0.017036721 9.547352075576782
8
+ 6 1187.0 0.0 1187.0 1187.0 1227.7499 0.0 1227.7499 1227.7499 5.2800403 1.8861856 8.190782 1.8425303 -0.02265191 11.06665301322937
9
+ 7 1157.0 0.0 1157.0 1157.0 1268.9706 0.0 1268.9706 1268.9706 5.4762006 1.8380868 8.36121 2.0251794 -0.062205777 12.584624767303467
10
+ 8 1174.0 0.0 1174.0 1174.0 1242.0238 0.0 1242.0238 1242.0238 5.776742 1.6408564 8.433153 2.505 -0.03781183 14.096492290496826
11
+ 9 1184.0 0.0 1184.0 1184.0 1174.2599 0.0 1174.2599 1174.2599 5.616263 1.8906851 8.666612 1.8428457 0.005410582 15.658498525619507
reward_1707780024.5255785_rfbase_cotTrue_task_index=11_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=11_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbc160d55365e856595a2f2d13738797d85fa62ce83f5579768bc7e1aa434201
3
+ size 26198
reward_1707780024.5255785_rfbase_cotTrue_task_index=11_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=11_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:770168b3aaef05c84af851d3036d265dcee4f037db63d5c1823616342f1a4a47
3
+ size 13916
reward_1707780024.5255785_rfbase_cotTrue_task_index=11_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=11_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/progress.txt ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 969.0 0.0 969.0 969.0 652.86145 0.0 652.86145 652.86145 0.14414199 0.031151053 0.18614006 0.09822309 0.28277177 1.6294469833374023
3
+ 1 1103.0 0.0 1103.0 1103.0 882.0578 0.0 882.0578 882.0578 2.451144 0.35985994 2.9899967 1.7108487 0.33526963 3.2637274265289307
4
+ 2 1135.0 0.0 1135.0 1135.0 960.75586 0.0 960.75586 960.75586 3.6939754 0.73008066 4.6222386 2.3335814 0.25737727 4.864926338195801
5
+ 3 1138.0 0.0 1138.0 1138.0 954.2068 0.0 954.2068 954.2068 4.070017 0.94288146 5.3400016 2.5666225 0.2743185 6.495613098144531
6
+ 4 1135.0 0.0 1135.0 1135.0 841.90515 0.0 841.90515 841.90515 4.1153016 0.90182793 5.342021 2.5547903 0.3960741 8.126822471618652
7
+ 5 812.0 0.0 812.0 812.0 812.0 0.0 812.0 812.0 3.6437478 0.4509163 4.3484116 2.5868795 0.32354915 9.755660057067871
8
+ 6 1144.0 0.0 1144.0 1144.0 933.24384 0.0 933.24384 933.24384 3.6029906 0.23639365 4.059921 2.741676 0.30993444 11.380826950073242
9
+ 7 1144.0 0.0 1144.0 1144.0 938.77954 0.0 938.77954 938.77954 4.1037803 0.57644045 4.8851786 2.8273032 0.30047005 13.012800931930542
10
+ 8 817.0 0.0 817.0 817.0 817.0 0.0 817.0 817.0 4.09069 0.78461653 5.227884 2.5871317 0.3324399 14.543687582015991
11
+ 9 816.0 0.0 816.0 816.0 816.0 0.0 816.0 816.0 3.6571302 0.2472473 4.1313453 2.8621936 0.31087673 16.17698884010315
reward_1707780024.5255785_rfbase_cotTrue_task_index=11_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=11_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:276f415b593d9585472db5629736fe862372ca3b3326c1ab5f03d31e042ee11c
3
+ size 26198
reward_1707780024.5255785_rfbase_cotTrue_task_index=11_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=11_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c3c0e5ddaa6502219c5a3b188956e89c1de4d56482f37e86b0bd5ee366b89ae
3
+ size 13916
reward_1707780024.5255785_rfbase_cotTrue_task_index=12_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=12_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/progress.txt ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 1009.0 0.0 1009.0 1009.0 1022.16797 0.0 1022.16797 1022.16797 0.2132047 0.042787187 0.27887252 0.15446824 -0.011216506 1.5374846458435059
3
+ 1 1158.0 0.0 1158.0 1158.0 1146.3192 0.0 1146.3192 1146.3192 4.287194 0.3480199 4.6768413 3.5652573 0.00649295 3.1237385272979736
4
+ 2 1136.0 0.0 1136.0 1136.0 1183.0306 0.0 1183.0306 1183.0306 5.070743 1.3248519 6.7394876 2.9550483 -0.026142046 4.7451255321502686
5
+ 3 1154.0 0.0 1154.0 1154.0 1172.1407 0.0 1172.1407 1172.1407 5.27241 1.6528273 7.426351 2.589364 -0.010078713 6.40146017074585
6
+ 4 1128.0 0.0 1128.0 1128.0 1143.442 0.0 1143.442 1143.442 5.263782 1.6090158 7.3939953 2.4137821 -0.008579209 8.014779806137085
7
+ 5 1171.0 0.0 1171.0 1171.0 1192.0204 0.0 1192.0204 1192.0204 5.1072497 1.8183484 7.648181 1.964186 -0.01167798 9.631031513214111
8
+ 6 1189.0 0.0 1189.0 1189.0 1220.4288 0.0 1220.4288 1220.4288 5.245264 1.9371377 8.151563 1.7184973 -0.017470613 11.250556945800781
9
+ 7 1159.0 0.0 1159.0 1159.0 1263.9722 0.0 1263.9722 1263.9722 5.4867663 1.8630611 8.297822 2.0054038 -0.058318004 12.860278844833374
10
+ 8 1161.0 0.0 1161.0 1161.0 1219.4999 0.0 1219.4999 1219.4999 5.7067165 1.6905651 8.332491 2.4044118 -0.0325177 14.476622104644775
11
+ 9 1200.0 0.0 1200.0 1200.0 1180.4674 0.0 1180.4674 1180.4674 5.5160165 1.9323374 8.593139 1.734514 0.010852054 16.08645796775818
reward_1707780024.5255785_rfbase_cotTrue_task_index=12_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=12_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4e20cf11982939a62c82a77802a678650ee8f8eb9545ff91a3c40a586ff8804
3
+ size 26198
reward_1707780024.5255785_rfbase_cotTrue_task_index=12_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=12_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:770168b3aaef05c84af851d3036d265dcee4f037db63d5c1823616342f1a4a47
3
+ size 13916
reward_1707780024.5255785_rfbase_cotTrue_task_index=12_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=12_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/progress.txt ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 954.0 0.0 954.0 954.0 668.0948 0.0 668.0948 668.0948 0.14391032 0.030783739 0.18578668 0.097890265 0.25527233 1.7034809589385986
3
+ 1 1059.0 0.0 1059.0 1059.0 880.30005 0.0 880.30005 880.30005 2.6123362 0.26732633 3.019003 1.8907772 0.3054697 3.3405532836914062
4
+ 2 1099.0 0.0 1099.0 1099.0 944.048 0.0 944.048 944.048 3.5920753 0.74030995 4.5635943 2.1490664 0.22787021 4.905843019485474
5
+ 3 1116.0 0.0 1116.0 1116.0 927.9279 0.0 927.9279 927.9279 4.026224 0.9658623 5.3856153 2.3828697 0.24681357 6.419819593429565
6
+ 4 1102.0 0.0 1102.0 1102.0 832.1054 0.0 832.1054 832.1054 3.9524424 0.9923887 5.4511447 2.1054041 0.36770397 7.9319517612457275
7
+ 5 808.0 0.0 808.0 808.0 808.0 0.0 808.0 808.0 3.6329916 0.5241222 4.4886074 2.2946682 0.29519513 9.443203449249268
8
+ 6 1140.0 0.0 1140.0 1140.0 912.6025 0.0 912.6025 912.6025 3.5414517 0.28236043 4.003264 2.5154777 0.28073776 10.959861755371094
9
+ 7 1139.0 0.0 1139.0 1139.0 933.8369 0.0 933.8369 933.8369 3.949693 0.88118356 5.2524185 2.1059723 0.27137956 12.471558094024658
10
+ 8 842.0 0.0 842.0 842.0 828.6844 0.0 828.6844 828.6844 3.9791253 0.941225 5.4319673 2.109551 0.30262908 14.01619577407837
11
+ 9 1111.0 0.0 1111.0 1111.0 914.0822 0.0 914.0822 914.0822 3.6446168 0.32956383 4.1361604 2.7111197 0.2813115 15.666466236114502
reward_1707780024.5255785_rfbase_cotTrue_task_index=12_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=12_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6ac088e50ab9a0aa60513e1098c44ddc85dc9f6953a69e27738670a10fded3f
3
+ size 26198
reward_1707780024.5255785_rfbase_cotTrue_task_index=12_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=12_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c3c0e5ddaa6502219c5a3b188956e89c1de4d56482f37e86b0bd5ee366b89ae
3
+ size 13916
reward_1707780024.5255785_rfbase_cotTrue_task_index=13_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=13_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/progress.txt ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 972.0 0.0 972.0 972.0 984.6938 0.0 984.6938 984.6938 0.211579 0.04046322 0.27884093 0.1544471 -0.010082543 1.7365944385528564
3
+ 1 1127.0 0.0 1127.0 1127.0 1113.5631 0.0 1113.5631 1113.5631 4.159586 0.27912626 4.5003414 3.480257 0.00707902 3.4840445518493652
4
+ 2 1089.0 0.0 1089.0 1089.0 1137.8744 0.0 1137.8744 1137.8744 4.9767046 1.1194432 6.4365654 2.9823587 -0.025791213 5.0699238777160645
5
+ 3 1109.0 0.0 1109.0 1109.0 1126.9594 0.0 1126.9594 1126.9594 5.1694717 1.4040157 7.0854287 2.5595465 -0.009457365 6.654399871826172
6
+ 4 1105.0 0.0 1105.0 1105.0 1118.8917 0.0 1118.8917 1118.8917 5.1303077 1.4057866 7.1245637 2.3683422 -0.007311538 8.233429431915283
7
+ 5 1115.0 0.0 1115.0 1115.0 1135.9646 0.0 1135.9646 1135.9646 5.002605 1.5961031 7.3556356 2.4214263 -0.011033729 9.815142631530762
8
+ 6 1140.0 0.0 1140.0 1140.0 1170.7115 0.0 1170.7115 1170.7115 5.112533 1.5856723 7.6747427 1.8765056 -0.016163468 11.389655351638794
9
+ 7 1098.0 0.0 1098.0 1098.0 1205.5194 0.0 1205.5194 1205.5194 5.3550334 1.5047942 7.8033247 3.0084562 -0.056589186 12.96997880935669
10
+ 8 1127.0 0.0 1127.0 1127.0 1189.6857 0.0 1189.6857 1189.6857 5.56936 1.5296624 8.209306 2.3203254 -0.033009395 14.545027256011963
11
+ 9 1159.0 0.0 1159.0 1159.0 1137.631 0.0 1137.631 1137.631 5.387512 1.7438824 8.512893 1.7574779 0.011246681 16.142975091934204
reward_1707780024.5255785_rfbase_cotTrue_task_index=13_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=13_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1f4b1e857f88b9a5aff3340d84094d6435150d93ceba03e1d41ff780b684706
3
+ size 26198
reward_1707780024.5255785_rfbase_cotTrue_task_index=13_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=13_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:770168b3aaef05c84af851d3036d265dcee4f037db63d5c1823616342f1a4a47
3
+ size 13916
reward_1707780024.5255785_rfbase_cotTrue_task_index=13_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=13_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/progress.txt ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 973.0 0.0 973.0 973.0 694.662 0.0 694.662 694.662 0.14365676 0.0307239 0.18567976 0.09778939 0.24697244 1.558793306350708
3
+ 1 1078.0 0.0 1078.0 1078.0 882.59326 0.0 882.59326 882.59326 2.6239333 0.31518146 3.0829072 1.8954208 0.2983309 3.0810515880584717
4
+ 2 1106.0 0.0 1106.0 1106.0 966.9103 0.0 966.9103 966.9103 3.759089 0.7501848 4.6976714 2.3135533 0.2204276 4.57916784286499
5
+ 3 1130.0 0.0 1130.0 1130.0 968.87177 0.0 968.87177 968.87177 4.1473646 1.0389292 5.550422 2.4351237 0.23870844 6.222944021224976
6
+ 4 1146.0 0.0 1146.0 1146.0 883.5273 0.0 883.5273 883.5273 4.1733065 1.047617 5.5759683 2.2192788 0.36103547 7.8501503467559814
7
+ 5 813.0 0.0 813.0 813.0 813.0 0.0 813.0 813.0 3.8126295 0.8231941 4.9781203 2.0010927 0.28780985 9.477843999862671
8
+ 6 1153.0 0.0 1153.0 1153.0 939.56793 0.0 939.56793 939.56793 3.5396867 0.2822938 3.9829445 2.458968 0.27328056 11.106434106826782
9
+ 7 1143.0 0.0 1143.0 1143.0 952.993 0.0 952.993 952.993 4.109153 0.8529048 5.189638 2.2652974 0.26389876 12.731141567230225
10
+ 8 839.0 0.0 839.0 839.0 826.59515 0.0 826.59515 826.59515 4.0551176 1.0523028 5.4699583 1.8837241 0.29536194 14.35535717010498
11
+ 9 1130.0 0.0 1130.0 1130.0 939.2314 0.0 939.2314 939.2314 3.6228032 0.3550596 4.07415 2.5550227 0.27409273 15.982172012329102
reward_1707780024.5255785_rfbase_cotTrue_task_index=13_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=13_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f27323761f43d78e37be93432af6308a6536a92c7796b5f53158774d6bf0d4c2
3
+ size 26198
reward_1707780024.5255785_rfbase_cotTrue_task_index=13_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=13_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c3c0e5ddaa6502219c5a3b188956e89c1de4d56482f37e86b0bd5ee366b89ae
3
+ size 13916
reward_1707780024.5255785_rfbase_cotTrue_task_index=14_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=14_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/progress.txt ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 1005.0 0.0 1005.0 1005.0 1050.3073 0.0 1050.3073 1050.3073 0.2083331 0.038922932 0.27951896 0.15489888 -0.034480557 1.6062653064727783
3
+ 1 1132.0 0.0 1132.0 1132.0 1167.6956 0.0 1167.6956 1167.6956 4.417243 0.30045772 4.809263 3.5751004 -0.01786621 3.31565260887146
4
+ 2 1109.0 0.0 1109.0 1109.0 1210.0961 0.0 1210.0961 1210.0961 5.286 1.2887203 7.020565 2.9970827 -0.050751507 5.019345283508301
5
+ 3 1140.0 0.0 1140.0 1140.0 1205.8854 0.0 1205.8854 1205.8854 5.5683193 1.4816289 7.6672544 2.7909489 -0.032942563 6.717926263809204
6
+ 4 1121.0 0.0 1121.0 1121.0 1185.4083 0.0 1185.4083 1185.4083 5.550827 1.4996761 7.7361946 3.0177293 -0.032203898 8.419236421585083
7
+ 5 1136.0 0.0 1136.0 1136.0 1205.4613 0.0 1205.4613 1205.4613 5.4719586 1.6848688 8.039 2.107475 -0.034764916 10.121132850646973
8
+ 6 1156.0 0.0 1156.0 1156.0 1236.1248 0.0 1236.1248 1236.1248 5.559444 1.7833451 8.552049 2.8100243 -0.040083125 11.819284439086914
9
+ 7 1129.0 0.0 1129.0 1129.0 1289.9814 0.0 1289.9814 1289.9814 5.7034388 1.7226404 8.609366 3.206553 -0.0804901 13.520227432250977
10
+ 8 1145.0 0.0 1145.0 1145.0 1250.1304 0.0 1250.1304 1250.1304 6.012895 1.5530797 8.673737 2.972351 -0.05259113 15.213274955749512
11
+ 9 1161.0 0.0 1161.0 1161.0 1186.224 0.0 1186.224 1186.224 5.8791814 1.8160787 8.90383 3.2829866 -0.012612 16.91295027732849
reward_1707780024.5255785_rfbase_cotTrue_task_index=14_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=14_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb67346217210b13452f837c729700c9ae7eb5ed25e144c36579a09311c518ab
3
+ size 26198
reward_1707780024.5255785_rfbase_cotTrue_task_index=14_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=14_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:770168b3aaef05c84af851d3036d265dcee4f037db63d5c1823616342f1a4a47
3
+ size 13916
reward_1707780024.5255785_rfbase_cotTrue_task_index=14_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=14_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/progress.txt ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 967.0 0.0 967.0 967.0 650.47815 0.0 650.47815 650.47815 0.14131632 0.030033182 0.18593313 0.09802827 0.2666568 1.6628952026367188
3
+ 1 1091.0 0.0 1091.0 1091.0 876.4549 0.0 876.4549 876.4549 2.5565624 0.32225707 3.0280733 1.7767868 0.31831637 3.3128859996795654
4
+ 2 1104.0 0.0 1104.0 1104.0 939.44507 0.0 939.44507 939.44507 3.850918 0.59140176 4.597783 2.7538157 0.24057762 4.967300176620483
5
+ 3 1132.0 0.0 1132.0 1132.0 943.1971 0.0 943.1971 943.1971 4.152701 0.9084487 5.3756094 2.494341 0.25828075 6.525930643081665
6
+ 4 1134.0 0.0 1134.0 1134.0 821.749 0.0 821.749 821.749 4.3288636 0.74346656 5.3766456 2.7144861 0.38079417 8.047613859176636
7
+ 5 796.0 0.0 796.0 796.0 796.0 0.0 796.0 796.0 3.7517662 0.4084951 4.4196243 2.5840096 0.30703163 9.564523458480835
8
+ 6 1162.0 0.0 1162.0 1162.0 905.5834 0.0 905.5834 905.5834 3.5776546 0.23350081 4.0045986 2.6295357 0.29304737 11.076406478881836
9
+ 7 1163.0 0.0 1163.0 1163.0 927.96704 0.0 927.96704 927.96704 4.136982 0.6175513 5.0085883 2.5484107 0.2838559 12.595866680145264
10
+ 8 794.0 0.0 794.0 794.0 793.68445 0.0 793.68445 793.68445 4.147046 0.7952608 5.3124604 2.2684364 0.31556553 14.116122245788574
11
+ 9 1135.0 0.0 1135.0 1135.0 911.79504 0.0 911.79504 911.79504 3.6932654 0.24959518 4.196717 2.832329 0.29407793 15.635130643844604
reward_1707780024.5255785_rfbase_cotTrue_task_index=14_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=14_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc5de8d6527fdf635d9b770f2fa05e9dd9bb33def4e5e8e92c8df308b0cb854f
3
+ size 26198
reward_1707780024.5255785_rfbase_cotTrue_task_index=14_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=14_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c3c0e5ddaa6502219c5a3b188956e89c1de4d56482f37e86b0bd5ee366b89ae
3
+ size 13916
reward_1707780024.5255785_rfbase_cotTrue_task_index=15_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=15_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/progress.txt ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 994.0 0.0 994.0 994.0 1021.0768 0.0 1021.0768 1021.0768 0.21250007 0.04066559 0.27916646 0.15466475 -0.021783084 1.668320894241333
3
+ 1 1109.0 0.0 1109.0 1109.0 1117.7433 0.0 1117.7433 1117.7433 4.2616544 0.31179178 4.665305 3.5361261 -0.0046065897 3.335503578186035
4
+ 2 1108.0 0.0 1108.0 1108.0 1176.506 0.0 1176.506 1176.506 4.9562883 1.2602054 6.7487607 2.8961759 -0.03611198 4.906333923339844
5
+ 3 1123.0 0.0 1123.0 1123.0 1161.7898 0.0 1161.7898 1161.7898 5.270969 1.5578464 7.5988173 2.6020186 -0.020426288 6.446594476699829
6
+ 4 1123.0 0.0 1123.0 1123.0 1158.9955 0.0 1158.9955 1158.9955 5.23163 1.5479801 7.62154 2.4043288 -0.0190451 7.98651647567749
7
+ 5 1119.0 0.0 1119.0 1119.0 1158.3104 0.0 1158.3104 1158.3104 5.1757507 1.7599212 8.004074 1.9698908 -0.022010192 9.531043529510498
8
+ 6 1128.0 0.0 1128.0 1128.0 1174.9309 0.0 1174.9309 1174.9309 5.2521195 1.8197953 8.52076 1.9909644 -0.027720481 11.089900732040405
9
+ 7 1122.0 0.0 1122.0 1122.0 1233.4878 0.0 1233.4878 1233.4878 5.360936 1.6240821 8.3361025 2.3635793 -0.06869224 12.642500877380371
10
+ 8 1141.0 0.0 1141.0 1141.0 1213.4513 0.0 1213.4513 1213.4513 5.664172 1.639796 8.690855 2.6192145 -0.040611833 14.194446086883545
11
+ 9 1136.0 0.0 1136.0 1136.0 1135.4099 0.0 1135.4099 1135.4099 5.582672 1.9019033 8.972779 2.0850525 0.00032451004 15.862299680709839
reward_1707780024.5255785_rfbase_cotTrue_task_index=15_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=15_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c545b3f2162f5bfd9d95e91d7aed169e0bd5f7b22bcd0ea4e9181c001501806a
3
+ size 26198
reward_1707780024.5255785_rfbase_cotTrue_task_index=15_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=15_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s13/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:770168b3aaef05c84af851d3036d265dcee4f037db63d5c1823616342f1a4a47
3
+ size 13916
reward_1707780024.5255785_rfbase_cotTrue_task_index=15_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=15_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/progress.txt ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 960.0 0.0 960.0 960.0 696.962 0.0 696.962 696.962 0.14461029 0.030458668 0.18551809 0.09763673 0.23443723 1.4871890544891357
3
+ 1 1067.0 0.0 1067.0 1067.0 876.4156 0.0 876.4156 876.4156 2.6846 0.26483467 3.0909948 1.9939945 0.28403038 2.9716782569885254
4
+ 2 1063.0 0.0 1063.0 1063.0 943.0397 0.0 943.0397 943.0397 3.7068694 0.7814084 4.7681146 2.210012 0.2071846 4.4772045612335205
5
+ 3 1096.0 0.0 1096.0 1096.0 940.43274 0.0 940.43274 940.43274 4.0503674 0.9625744 5.473732 2.595045 0.2261152 5.95758581161499
6
+ 4 1122.0 0.0 1122.0 1122.0 876.138 0.0 876.138 876.138 4.124876 0.95054567 5.554649 2.518483 0.34923637 7.440656900405884
7
+ 5 810.0 0.0 810.0 810.0 810.0 0.0 810.0 810.0 3.7733152 0.71175516 4.9754953 2.42703 0.27406585 8.979296445846558
8
+ 6 1143.0 0.0 1143.0 1143.0 943.0028 0.0 943.0028 943.0028 3.5873153 0.21049257 3.976318 2.8371928 0.25940034 10.609726667404175
9
+ 7 1124.0 0.0 1124.0 1124.0 940.73334 0.0 940.73334 940.73334 4.059508 0.76205575 5.230571 2.6240344 0.2500227 12.174387693405151
10
+ 8 832.0 0.0 832.0 832.0 820.45306 0.0 820.45306 820.45306 4.0821867 0.92500216 5.5930085 2.4797463 0.28163868 13.762090682983398
11
+ 9 1107.0 0.0 1107.0 1107.0 927.1604 0.0 927.1604 927.1604 3.6596467 0.27138594 4.0661035 3.148018 0.26025942 15.34944224357605
reward_1707780024.5255785_rfbase_cotTrue_task_index=15_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=15_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e566593534bcc07af3a3c019cece2285a71715bba92eb4a81edd25c0c848479
3
+ size 26198
reward_1707780024.5255785_rfbase_cotTrue_task_index=15_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=15_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c3c0e5ddaa6502219c5a3b188956e89c1de4d56482f37e86b0bd5ee366b89ae
3
+ size 13916
reward_1707780024.5255785_rfbase_cotTrue_task_index=1_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=1_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/progress.txt ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 961.0 0.0 961.0 961.0 658.6351 0.0 658.6351 658.6351 0.13925515 0.028934551 0.18562427 0.09773703 0.24266842 1.7062528133392334
3
+ 1 1115.0 0.0 1115.0 1115.0 882.6471 0.0 882.6471 882.6471 2.7469413 0.30195028 3.1831293 1.9095322 0.2922673 3.428800106048584
4
+ 2 1103.0 0.0 1103.0 1103.0 950.87756 0.0 950.87756 950.87756 3.941822 0.7039695 4.8088365 2.424278 0.21577637 4.998257398605347
5
+ 3 1138.0 0.0 1138.0 1138.0 947.5591 0.0 947.5591 947.5591 4.3396482 0.880968 5.4976707 2.4547722 0.23395738 6.566149711608887
6
+ 4 1151.0 0.0 1151.0 1151.0 851.09656 0.0 851.09656 851.09656 4.399286 0.82830334 5.5150275 2.2771075 0.35745353 8.141887426376343
7
+ 5 783.0 0.0 783.0 783.0 783.0 0.0 783.0 783.0 3.9612834 0.5851283 4.832699 2.4762652 0.28221935 9.71167802810669
8
+ 6 1158.0 0.0 1158.0 1158.0 925.7624 0.0 925.7624 925.7624 3.6690085 0.22637503 4.0836244 3.107776 0.2675549 11.303403377532959
9
+ 7 1158.0 0.0 1158.0 1158.0 941.23206 0.0 941.23206 941.23206 4.2673216 0.62286407 5.1033444 2.5053515 0.25805783 12.89110279083252
10
+ 8 808.0 0.0 808.0 808.0 795.8295 0.0 795.8295 795.8295 4.275804 0.81354845 5.431799 2.1283097 0.28976882 14.46428370475769
11
+ 9 1141.0 0.0 1141.0 1141.0 922.4609 0.0 922.4609 922.4609 3.73936 0.25211564 4.0857506 2.9073336 0.26814616 16.137130975723267
reward_1707780024.5255785_rfbase_cotTrue_task_index=1_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=1_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0df1af3e041777cfb0384b23866782c277c9e4ad6afb414cd24f84470374495
3
+ size 26198
reward_1707780024.5255785_rfbase_cotTrue_task_index=1_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=1_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c3c0e5ddaa6502219c5a3b188956e89c1de4d56482f37e86b0bd5ee366b89ae
3
+ size 13916
reward_1707780024.5255785_rfbase_cotTrue_task_index=2_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=2_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/progress.txt ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 980.0 0.0 980.0 980.0 718.56384 0.0 718.56384 718.56384 0.14357658 0.030604603 0.18548897 0.09760922 0.2321811 1.6380438804626465
3
+ 1 1089.0 0.0 1089.0 1089.0 891.0919 0.0 891.0919 891.0919 2.8142233 0.22972487 3.1516528 2.1108203 0.2803231 3.2650067806243896
4
+ 2 1075.0 0.0 1075.0 1075.0 952.34393 0.0 952.34393 952.34393 3.6632435 0.7975244 4.717457 2.075314 0.20476793 4.8938682079315186
5
+ 3 1099.0 0.0 1099.0 1099.0 943.2908 0.0 943.2908 943.2908 4.1468287 0.94457436 5.4132915 2.502675 0.22339925 6.521366357803345
6
+ 4 1141.0 0.0 1141.0 1141.0 853.15894 0.0 853.15894 853.15894 4.149177 0.97772545 5.471329 2.2829554 0.34596258 8.145384073257446
7
+ 5 808.0 0.0 808.0 808.0 808.0 0.0 808.0 808.0 3.7084212 0.7831058 4.877923 1.9607472 0.27125865 9.769689559936523
8
+ 6 1142.0 0.0 1142.0 1142.0 936.8659 0.0 936.8659 936.8659 3.569337 0.26803124 4.0268626 2.5658014 0.25577822 11.398471355438232
9
+ 7 1145.0 0.0 1145.0 1145.0 956.43195 0.0 956.43195 956.43195 4.0238905 0.82438606 5.1553283 2.225504 0.24617216 13.037954568862915
10
+ 8 842.0 0.0 842.0 842.0 830.6262 0.0 830.6262 830.6262 4.0586476 1.010051 5.524897 2.057889 0.27741665 14.670298337936401
11
+ 9 1123.0 0.0 1123.0 1123.0 932.80743 0.0 932.80743 932.80743 3.6569283 0.32923123 4.0800157 2.7342982 0.2566702 16.301510334014893
reward_1707780024.5255785_rfbase_cotTrue_task_index=2_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=2_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee182722fb4ba177d9bd74986bf940318019cb0d36a83afb50d12ab7b17d09ac
3
+ size 26198
reward_1707780024.5255785_rfbase_cotTrue_task_index=2_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=2_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c3c0e5ddaa6502219c5a3b188956e89c1de4d56482f37e86b0bd5ee366b89ae
3
+ size 13916
reward_1707780024.5255785_rfbase_cotTrue_task_index=3_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=3_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/progress.txt ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 969.0 0.0 969.0 969.0 672.0358 0.0 672.0358 672.0358 0.13857247 0.028742015 0.18557829 0.0976936 0.23910148 1.7088229656219482
3
+ 1 1129.0 0.0 1129.0 1129.0 892.93854 0.0 892.93854 892.93854 2.7903426 0.26809582 3.1833777 2.220827 0.28893682 3.2944161891937256
4
+ 2 1108.0 0.0 1108.0 1108.0 950.0444 0.0 950.0444 950.0444 3.851257 0.8142764 4.8837566 1.9756792 0.212878 4.854521751403809
5
+ 3 1140.0 0.0 1140.0 1140.0 950.0861 0.0 950.0861 950.0861 4.295231 0.9214783 5.551752 2.4944773 0.23075852 6.406561613082886
6
+ 4 1161.0 0.0 1161.0 1161.0 863.2509 0.0 863.2509 863.2509 4.3084717 0.9155701 5.5986896 2.2193334 0.35488576 7.961761951446533
7
+ 5 777.0 0.0 777.0 777.0 777.0 0.0 777.0 777.0 3.9260473 0.62447685 4.9239335 2.5548265 0.27851456 9.513084650039673
8
+ 6 1156.0 0.0 1156.0 1156.0 915.9216 0.0 915.9216 915.9216 3.6206124 0.2194028 3.9964087 2.7010636 0.26411274 11.063723087310791
9
+ 7 1157.0 0.0 1157.0 1157.0 944.37555 0.0 944.37555 944.37555 4.159795 0.72802097 5.235955 2.2842658 0.25494617 12.639371395111084
10
+ 8 815.0 0.0 815.0 815.0 801.8212 0.0 801.8212 801.8212 4.259533 0.8243809 5.52667 2.2840571 0.28649062 14.626024007797241
11
+ 9 1140.0 0.0 1140.0 1140.0 923.73157 0.0 923.73157 923.73157 3.7145355 0.22608782 4.069248 2.8610425 0.26535982 16.209736824035645
reward_1707780024.5255785_rfbase_cotTrue_task_index=3_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=3_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcbb21a53a76ab81a8916d88fa3128417631d9f9330c82f2352d414e6ac97e7f
3
+ size 26198
reward_1707780024.5255785_rfbase_cotTrue_task_index=3_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=3_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c3c0e5ddaa6502219c5a3b188956e89c1de4d56482f37e86b0bd5ee366b89ae
3
+ size 13916
reward_1707780024.5255785_rfbase_cotTrue_task_index=4_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=4_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/progress.txt ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 981.0 0.0 981.0 981.0 729.52344 0.0 729.52344 729.52344 0.14621699 0.03135319 0.18559822 0.09771243 0.24064764 1.5561282634735107
3
+ 1 1088.0 0.0 1088.0 1088.0 886.0866 0.0 886.0866 886.0866 2.7020202 0.25672847 3.0952837 2.0296285 0.2913613 3.012709379196167
4
+ 2 1079.0 0.0 1079.0 1079.0 961.9102 0.0 961.9102 961.9102 3.5723522 0.8149151 4.6430964 2.1418855 0.21484354 4.471331357955933
5
+ 3 1157.0 0.0 1157.0 1157.0 982.6906 0.0 982.6906 982.6906 3.9439235 1.0480071 5.469137 2.4121728 0.23241222 5.962704181671143
6
+ 4 1146.0 0.0 1146.0 1146.0 898.5622 0.0 898.5622 898.5622 3.9444327 1.1628145 5.648532 2.0789957 0.3570521 7.541250944137573
7
+ 5 1151.0 0.0 1151.0 1151.0 953.1763 0.0 953.1763 953.1763 3.631081 0.8536078 4.9947143 2.1580963 0.28060052 9.022983312606812
8
+ 6 1159.0 0.0 1159.0 1159.0 976.00684 0.0 976.00684 976.00684 3.9881725 0.8392917 5.407794 2.6539266 0.26636583 10.534041166305542
9
+ 7 866.0 0.0 866.0 866.0 850.5669 0.0 850.5669 850.5669 4.0766387 0.7861288 5.3801 2.8064446 0.25722128 12.10569953918457
10
+ 8 1173.0 0.0 1173.0 1173.0 932.3998 0.0 932.3998 932.3998 3.7177083 0.37252915 4.268213 2.9544246 0.288836 13.681437015533447
11
+ 9 1133.0 0.0 1133.0 1133.0 922.1462 0.0 922.1462 922.1462 3.8427944 0.96484137 5.5094194 2.4508233 0.26758152 15.255890130996704
reward_1707780024.5255785_rfbase_cotTrue_task_index=4_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0/reward_1707780024.5255785_rfbase_cotTrue_task_index=4_stage=0_iteration=0_n21b7.0dcounterexamplersample_randomp0_s42/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e46393eb8368dce9768fa12ea544185077b5312ab57cd04f2c48f759befa2bf
3
+ size 26198