e5_group_difficulties.json 2.7 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132
  1. [
  2. {
  3. "group_name": "group_0_(最短)",
  4. "text_ids": [
  5. 3,
  6. 1,
  7. 23,
  8. 32,
  9. 40,
  10. 33,
  11. 24,
  12. 26,
  13. 21,
  14. 22
  15. ],
  16. "num_texts": 10,
  17. "r_effs": {
  18. "llama3.2-3b-instruct": 2.226330041885376,
  19. "Mistral-7B-v0.3": 2.4710209369659424,
  20. "llama3-8b": 2.1663646697998047,
  21. "Qwen2.5-7B-Instruct": 3.8829245567321777,
  22. "gemma-2-9b-it": 2.18928599357605
  23. },
  24. "rs_cross": 0.4316129517679338,
  25. "avg_text_length": 329.6,
  26. "estimated_difficulty": 2.58718523979187
  27. },
  28. {
  29. "group_name": "group_1_(较短)",
  30. "text_ids": [
  31. 18,
  32. 35,
  33. 34,
  34. 38,
  35. 48,
  36. 28,
  37. 0,
  38. 30,
  39. 36,
  40. 6
  41. ],
  42. "num_texts": 10,
  43. "r_effs": {
  44. "llama3.2-3b-instruct": 2.1320927143096924,
  45. "Mistral-7B-v0.3": 2.282879590988159,
  46. "llama3-8b": 1.977645993232727,
  47. "Qwen2.5-7B-Instruct": 3.2836060523986816,
  48. "gemma-2-9b-it": 2.0314362049102783
  49. },
  50. "rs_cross": 0.23267617354590583,
  51. "avg_text_length": 446.0,
  52. "estimated_difficulty": 2.3415321111679077
  53. },
  54. {
  55. "group_name": "group_2_(中等)",
  56. "text_ids": [
  57. 27,
  58. 37,
  59. 47,
  60. 49,
  61. 2,
  62. 29,
  63. 31,
  64. 42,
  65. 25,
  66. 11
  67. ],
  68. "num_texts": 10,
  69. "r_effs": {
  70. "llama3.2-3b-instruct": 2.0396993160247803,
  71. "Mistral-7B-v0.3": 2.237123727798462,
  72. "llama3-8b": 1.899621844291687,
  73. "Qwen2.5-7B-Instruct": 2.7096762657165527,
  74. "gemma-2-9b-it": 1.9543957710266113
  75. },
  76. "rs_cross": 0.08646117594966882,
  77. "avg_text_length": 555.8,
  78. "estimated_difficulty": 2.1681033849716185
  79. },
  80. {
  81. "group_name": "group_3_(较长)",
  82. "text_ids": [
  83. 12,
  84. 9,
  85. 20,
  86. 14,
  87. 5,
  88. 16,
  89. 13,
  90. 17,
  91. 43,
  92. 46
  93. ],
  94. "num_texts": 10,
  95. "r_effs": {
  96. "llama3.2-3b-instruct": 2.1218972206115723,
  97. "Mistral-7B-v0.3": 2.568671703338623,
  98. "llama3-8b": 2.1244308948516846,
  99. "Qwen2.5-7B-Instruct": 2.597262144088745,
  100. "gemma-2-9b-it": 2.120511054992676
  101. },
  102. "rs_cross": 0.05101916888623692,
  103. "avg_text_length": 684.8,
  104. "estimated_difficulty": 2.30655460357666
  105. },
  106. {
  107. "group_name": "group_4_(最长)",
  108. "text_ids": [
  109. 44,
  110. 10,
  111. 15,
  112. 4,
  113. 41,
  114. 8,
  115. 7,
  116. 19,
  117. 39,
  118. 45
  119. ],
  120. "num_texts": 10,
  121. "r_effs": {
  122. "llama3.2-3b-instruct": 2.1292803287506104,
  123. "Mistral-7B-v0.3": 2.7304728031158447,
  124. "llama3-8b": 2.1836905479431152,
  125. "Qwen2.5-7B-Instruct": 2.7516024112701416,
  126. "gemma-2-9b-it": 2.210625410079956
  127. },
  128. "rs_cross": 0.0777543501566106,
  129. "avg_text_length": 859.0,
  130. "estimated_difficulty": 2.4011343002319334
  131. }
  132. ]