nam-2pir

Untitled

Apr 3rd, 2025
57
0
Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 3.08 KB | None | 0 0
  1. ===== Gamma 1 =====
  2. ic| statistics.mean(summarization_ds_preserve_good["label_deepseek_10points"]): 0.898
  3. ic| statistics.mean(summarization_ds_preserve_meh["label_deepseek_10points"]): 0.875
  4. ic| statistics.mean(summarization_ds_preserve_bad["label_deepseek_10points"]): 0.8333333333333334
  5.  
  6. ic| statistics.mean(summarization_ds_preserve_good["4o_rating"]): 0.885
  7. ic| statistics.mean(summarization_ds_preserve_meh["4o_rating"]): 0.885
  8. ic| statistics.mean(summarization_ds_preserve_bad["4o_rating"]): 0.8535353535353536
  9.  
  10. ic| statistics.mean(summarization_ds_preserve_good["blueberry_piscorer"]): 0.6732421875
  11. ic| statistics.mean(summarization_ds_preserve_meh["blueberry_piscorer"]): 0.654638671875
  12. ic| statistics.mean(summarization_ds_preserve_bad["blueberry_piscorer"]): 0.65200836489899
  13.  
  14.  
  15. ===== Gamma 2 =====
  16. ic| statistics.mean(preserve_ds_preserve_good["label_deepseek_10points"]): 0.8530612244897959
  17. ic| statistics.mean(preserve_ds_preserve_meh["label_deepseek_10points"]): 0.8170000000000001
  18. ic| statistics.mean(preserve_ds_preserve_bad["label_deepseek_10points"]): 0.7555555555555555
  19.  
  20. ic| statistics.mean(preserve_ds_preserve_good["4o_rating"]): 0.8122448979591838
  21. ic| statistics.mean(preserve_ds_preserve_meh["4o_rating"]): 0.811
  22. ic| statistics.mean(preserve_ds_preserve_bad["4o_rating"]): 0.788888888888889
  23.  
  24. ic| statistics.mean(preserve_ds_preserve_good["blueberry_piscorer"]): 0.7357501594387755
  25. ic| statistics.mean(preserve_ds_preserve_meh["blueberry_piscorer"]): 0.7054833984375
  26. ic| statistics.mean(preserve_ds_preserve_bad["blueberry_piscorer"]): 0.7187598642676768
  27.  
  28.  
  29. ===== Gamma 3 =====
  30. ic| statistics.mean(summarization_ds_condense_good["label_deepseek_10points"]): 0.886
  31. ic| statistics.mean(summarization_ds_condense_meh["label_deepseek_10points"]): 0.875
  32. ic| statistics.mean(summarization_ds_condense_bad["label_deepseek_10points"]): 0.8515463917525773
  33.  
  34. ic| statistics.mean(summarization_ds_condense_good["4o_rating"]): 0.877
  35. ic| statistics.mean(summarization_ds_condense_meh["4o_rating"]): 0.88
  36. ic| statistics.mean(summarization_ds_condense_bad["4o_rating"]): 0.8649484536082475
  37.  
  38. ic| statistics.mean(summarization_ds_condense_good["blueberry_piscorer"]): 0.67046875
  39. ic| statistics.mean(summarization_ds_condense_meh["blueberry_piscorer"]): 0.66505859375
  40. ic| statistics.mean(summarization_ds_condense_bad["blueberry_piscorer"]): 0.6604784149484536
  41.  
  42.  
  43. ===== Gamma 4 =====
  44. ic| statistics.mean(preserve_ds_condense_good["label_deepseek_10points"]): 0.834
  45. ic| statistics.mean(preserve_ds_condense_meh["label_deepseek_10points"]): 0.799
  46. ic| statistics.mean(preserve_ds_condense_bad["label_deepseek_10points"]): 0.7443298969072165
  47.  
  48. ic| statistics.mean(preserve_ds_condense_good["4o_rating"]): 0.801
  49. ic| statistics.mean(preserve_ds_condense_meh["4o_rating"]): 0.806
  50. ic| statistics.mean(preserve_ds_condense_bad["4o_rating"]): 0.7783505154639175
  51.  
  52. ic| statistics.mean(preserve_ds_condense_good["blueberry_piscorer"]): 0.69740234375
  53. ic| statistics.mean(preserve_ds_condense_meh["blueberry_piscorer"]): 0.6843359375
  54. ic| statistics.mean(preserve_ds_condense_bad["blueberry_piscorer"]): 0.6792042525773195
Advertisement
Add Comment
Please, Sign In to add comment