VoCuc commited on
Commit
560e008
·
verified ·
1 Parent(s): 630e8c9

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. .gitattributes +218 -0
  2. qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/305/added_tokens.json +24 -0
  3. qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/305/chat_template.jinja +54 -0
  4. qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/305/config.json +56 -0
  5. qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/305/generation_config.json +6 -0
  6. qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/305/merges.txt +0 -0
  7. qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/305/pytorch_model.bin +3 -0
  8. qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/305/special_tokens_map.json +19 -0
  9. qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/305/tokenizer.json +3 -0
  10. qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/305/tokenizer_config.json +208 -0
  11. qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/305/vocab.json +0 -0
  12. qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/args.json +1 -0
  13. qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/eval/0/answers.jsonl +0 -0
  14. qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/eval/1/answers.jsonl +0 -0
  15. qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/eval/2/answers.jsonl +0 -0
  16. qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/eval/3/answers.jsonl +0 -0
  17. qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/eval/4/answers.jsonl +0 -0
  18. qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/log.txt +126 -0
  19. qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/1642/README.md +207 -0
  20. qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/1642/adapter_config.json +46 -0
  21. qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/1642/adapter_model.bin +3 -0
  22. qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/1642/added_tokens.json +24 -0
  23. qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/1642/chat_template.jinja +54 -0
  24. qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/1642/merges.txt +0 -0
  25. qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/1642/special_tokens_map.json +19 -0
  26. qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/1642/tokenizer.json +3 -0
  27. qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/1642/tokenizer_config.json +208 -0
  28. qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/1642/vocab.json +0 -0
  29. qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/2463/README.md +207 -0
  30. qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/2463/adapter_config.json +46 -0
  31. qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/2463/adapter_model.bin +3 -0
  32. qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/2463/added_tokens.json +24 -0
  33. qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/2463/chat_template.jinja +54 -0
  34. qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/2463/merges.txt +0 -0
  35. qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/2463/special_tokens_map.json +19 -0
  36. qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/2463/tokenizer.json +3 -0
  37. qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/2463/tokenizer_config.json +208 -0
  38. qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/2463/vocab.json +0 -0
  39. qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/3284/README.md +207 -0
  40. qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/3284/adapter_config.json +46 -0
  41. qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/3284/adapter_model.bin +3 -0
  42. qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/3284/added_tokens.json +24 -0
  43. qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/3284/chat_template.jinja +54 -0
  44. qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/3284/merges.txt +0 -0
  45. qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/3284/special_tokens_map.json +19 -0
  46. qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/3284/tokenizer.json +3 -0
  47. qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/3284/tokenizer_config.json +208 -0
  48. qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/3284/vocab.json +0 -0
  49. qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/4105/README.md +207 -0
  50. qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/4105/adapter_config.json +46 -0
.gitattributes CHANGED
@@ -39,3 +39,221 @@ qwen3/sft_0.6B/e10-bs8-lr5e-05-G2-N2-NN1/980/tokenizer.json filter=lfs diff=lfs
39
  qwen3/sft_4B/e5-bs2-lr0.0001-G8-N2-NN1-lora-16-64-0.1/428/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
  qwen3/sft_4B/e5-bs2-lr0.0001-G8-N2-NN1-lora-16-64-0.1/490/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
  qwen3/sft_8B/e5-bs1-lr0.0001-G16-N2-NN1-lora-16-64-0.1/98/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39
  qwen3/sft_4B/e5-bs2-lr0.0001-G8-N2-NN1-lora-16-64-0.1/428/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
  qwen3/sft_4B/e5-bs2-lr0.0001-G8-N2-NN1-lora-16-64-0.1/490/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
  qwen3/sft_8B/e5-bs1-lr0.0001-G16-N2-NN1-lora-16-64-0.1/98/tokenizer.json filter=lfs diff=lfs merge=lfs -text
42
+ qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/305/tokenizer.json filter=lfs diff=lfs merge=lfs -text
43
+ qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/1642/tokenizer.json filter=lfs diff=lfs merge=lfs -text
44
+ qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/2463/tokenizer.json filter=lfs diff=lfs merge=lfs -text
45
+ qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/3284/tokenizer.json filter=lfs diff=lfs merge=lfs -text
46
+ qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/4105/tokenizer.json filter=lfs diff=lfs merge=lfs -text
47
+ qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/821/tokenizer.json filter=lfs diff=lfs merge=lfs -text
48
+ qwen2.5/sft_0.5B_maven/e5-bs8-lr5e-05-G2-N2-NN1/4105/tokenizer.json filter=lfs diff=lfs merge=lfs -text
49
+ qwen2.5_no_CL_ace/distillm_0.5B_4B_on_srkl/392/tokenizer.json filter=lfs diff=lfs merge=lfs -text
50
+ qwen2.5_no_CL_ace/distillm_0.5B_4B_on_srkl/490/tokenizer.json filter=lfs diff=lfs merge=lfs -text
51
+ qwen2.5_no_CL_ace/sft_0.5B_ed/e5-bs8-lr5e-05-G2-N2-NN1/392/tokenizer.json filter=lfs diff=lfs merge=lfs -text
52
+ qwen2.5_no_CL_ace/sft_0.5B_ed/e5-bs8-lr5e-05-G2-N2-NN1/490-all/tokenizer.json filter=lfs diff=lfs merge=lfs -text
53
+ qwen2.5_no_CL_ace/sft_0.5B_lora/e5-bs8-lr5e-05-G2-N2-NN1/98/tokenizer.json filter=lfs diff=lfs merge=lfs -text
54
+ qwen2.5_no_CL_ace/sft_0.5B_lora/e5-bs8-lr5e-05-G2-N2-NN1-lora-32-64-0.1/196/tokenizer.json filter=lfs diff=lfs merge=lfs -text
55
+ qwen2.5_no_CL_ace/sft_0.5B_lora/e5-bs8-lr5e-05-G2-N2-NN1-lora-32-64-0.1/294/tokenizer.json filter=lfs diff=lfs merge=lfs -text
56
+ qwen2.5_no_CL_ace/sft_0.5B_lora/e5-bs8-lr5e-05-G2-N2-NN1-lora-32-64-0.1/392/tokenizer.json filter=lfs diff=lfs merge=lfs -text
57
+ qwen2.5_no_CL_ace/sft_0.5B_lora/e5-bs8-lr5e-05-G2-N2-NN1-lora-32-64-0.1/490/tokenizer.json filter=lfs diff=lfs merge=lfs -text
58
+ qwen2.5_no_CL_ace/sft_0.5B_lora/e5-bs8-lr5e-05-G2-N2-NN1-lora-32-64-0.1/98/tokenizer.json filter=lfs diff=lfs merge=lfs -text
59
+ qwen3/distillm_0.6B_4B_ace_kd/196/tokenizer.json filter=lfs diff=lfs merge=lfs -text
60
+ qwen3/distillm_0.6B_4B_ace_kd/294/tokenizer.json filter=lfs diff=lfs merge=lfs -text
61
+ qwen3/distillm_0.6B_4B_ace_kd/392/tokenizer.json filter=lfs diff=lfs merge=lfs -text
62
+ qwen3/distillm_0.6B_4B_ace_kd/490/tokenizer.json filter=lfs diff=lfs merge=lfs -text
63
+ qwen3/distillm_0.6B_4B_ace_kd/98/tokenizer.json filter=lfs diff=lfs merge=lfs -text
64
+ qwen3/distillm_0.6B_4B_ace_rkl/196/tokenizer.json filter=lfs diff=lfs merge=lfs -text
65
+ qwen3/distillm_0.6B_4B_ace_rkl/294/tokenizer.json filter=lfs diff=lfs merge=lfs -text
66
+ qwen3/distillm_0.6B_4B_ace_rkl/392/tokenizer.json filter=lfs diff=lfs merge=lfs -text
67
+ qwen3/distillm_0.6B_4B_ace_rkl/490/tokenizer.json filter=lfs diff=lfs merge=lfs -text
68
+ qwen3/distillm_0.6B_4B_ace_rkl/98/tokenizer.json filter=lfs diff=lfs merge=lfs -text
69
+ qwen3/distillm_0.6B_4B_ace_srkl/196/tokenizer.json filter=lfs diff=lfs merge=lfs -text
70
+ qwen3/distillm_0.6B_4B_ace_srkl/294/tokenizer.json filter=lfs diff=lfs merge=lfs -text
71
+ qwen3/distillm_0.6B_4B_ace_srkl/392/tokenizer.json filter=lfs diff=lfs merge=lfs -text
72
+ qwen3/distillm_0.6B_4B_ace_srkl/490/tokenizer.json filter=lfs diff=lfs merge=lfs -text
73
+ qwen3/distillm_0.6B_4B_ace_srkl/98/tokenizer.json filter=lfs diff=lfs merge=lfs -text
74
+ qwen3/distillm_0.6B_4B_ace_srkl_2/196/tokenizer.json filter=lfs diff=lfs merge=lfs -text
75
+ qwen3/distillm_0.6B_4B_ace_srkl_2/294/tokenizer.json filter=lfs diff=lfs merge=lfs -text
76
+ qwen3/distillm_0.6B_4B_ace_srkl_2/392/tokenizer.json filter=lfs diff=lfs merge=lfs -text
77
+ qwen3/distillm_0.6B_4B_ace_srkl_2/490/tokenizer.json filter=lfs diff=lfs merge=lfs -text
78
+ qwen3/distillm_0.6B_4B_ace_srkl_2/98/tokenizer.json filter=lfs diff=lfs merge=lfs -text
79
+ qwen3/distillm_0.6B_4B_ace_srkl_on/196/tokenizer.json filter=lfs diff=lfs merge=lfs -text
80
+ qwen3/distillm_0.6B_4B_ace_srkl_on/294/tokenizer.json filter=lfs diff=lfs merge=lfs -text
81
+ qwen3/distillm_0.6B_4B_ace_srkl_on/392/tokenizer.json filter=lfs diff=lfs merge=lfs -text
82
+ qwen3/distillm_0.6B_4B_ace_srkl_on/490/tokenizer.json filter=lfs diff=lfs merge=lfs -text
83
+ qwen3/distillm_0.6B_4B_ace_srkl_on/98/tokenizer.json filter=lfs diff=lfs merge=lfs -text
84
+ qwen3/distillm_0.6B_4B_geneva_kd/122/tokenizer.json filter=lfs diff=lfs merge=lfs -text
85
+ qwen3/distillm_0.6B_4B_geneva_kd/183/tokenizer.json filter=lfs diff=lfs merge=lfs -text
86
+ qwen3/distillm_0.6B_4B_geneva_kd/244/tokenizer.json filter=lfs diff=lfs merge=lfs -text
87
+ qwen3/distillm_0.6B_4B_geneva_kd/305/tokenizer.json filter=lfs diff=lfs merge=lfs -text
88
+ qwen3/distillm_0.6B_4B_geneva_kd/61/tokenizer.json filter=lfs diff=lfs merge=lfs -text
89
+ qwen3/distillm_0.6B_4B_geneva_rkl/122/tokenizer.json filter=lfs diff=lfs merge=lfs -text
90
+ qwen3/distillm_0.6B_4B_geneva_rkl/183/tokenizer.json filter=lfs diff=lfs merge=lfs -text
91
+ qwen3/distillm_0.6B_4B_geneva_rkl/244/tokenizer.json filter=lfs diff=lfs merge=lfs -text
92
+ qwen3/distillm_0.6B_4B_geneva_rkl/305/tokenizer.json filter=lfs diff=lfs merge=lfs -text
93
+ qwen3/distillm_0.6B_4B_geneva_rkl/61/tokenizer.json filter=lfs diff=lfs merge=lfs -text
94
+ qwen3/distillm_0.6B_4B_geneva_srkl/122/tokenizer.json filter=lfs diff=lfs merge=lfs -text
95
+ qwen3/distillm_0.6B_4B_geneva_srkl/183/tokenizer.json filter=lfs diff=lfs merge=lfs -text
96
+ qwen3/distillm_0.6B_4B_geneva_srkl/244/tokenizer.json filter=lfs diff=lfs merge=lfs -text
97
+ qwen3/distillm_0.6B_4B_geneva_srkl/305/tokenizer.json filter=lfs diff=lfs merge=lfs -text
98
+ qwen3/distillm_0.6B_4B_geneva_srkl/61/tokenizer.json filter=lfs diff=lfs merge=lfs -text
99
+ qwen3/distillm_0.6B_4B_geneva_srkl_2/122/tokenizer.json filter=lfs diff=lfs merge=lfs -text
100
+ qwen3/distillm_0.6B_4B_geneva_srkl_2/183/tokenizer.json filter=lfs diff=lfs merge=lfs -text
101
+ qwen3/distillm_0.6B_4B_geneva_srkl_2/244/tokenizer.json filter=lfs diff=lfs merge=lfs -text
102
+ qwen3/distillm_0.6B_4B_geneva_srkl_2/305/tokenizer.json filter=lfs diff=lfs merge=lfs -text
103
+ qwen3/distillm_0.6B_4B_geneva_srkl_2/61/tokenizer.json filter=lfs diff=lfs merge=lfs -text
104
+ qwen3/distillm_0.6B_4B_geneva_srkl_on/122/tokenizer.json filter=lfs diff=lfs merge=lfs -text
105
+ qwen3/distillm_0.6B_4B_geneva_srkl_on/183/tokenizer.json filter=lfs diff=lfs merge=lfs -text
106
+ qwen3/distillm_0.6B_4B_geneva_srkl_on/244/tokenizer.json filter=lfs diff=lfs merge=lfs -text
107
+ qwen3/distillm_0.6B_4B_geneva_srkl_on/305/tokenizer.json filter=lfs diff=lfs merge=lfs -text
108
+ qwen3/distillm_0.6B_4B_geneva_srkl_on/61/tokenizer.json filter=lfs diff=lfs merge=lfs -text
109
+ qwen3/distillm_0.6B_4B_maven_kd/1642/tokenizer.json filter=lfs diff=lfs merge=lfs -text
110
+ qwen3/distillm_0.6B_4B_maven_kd/2463/tokenizer.json filter=lfs diff=lfs merge=lfs -text
111
+ qwen3/distillm_0.6B_4B_maven_kd/3284/tokenizer.json filter=lfs diff=lfs merge=lfs -text
112
+ qwen3/distillm_0.6B_4B_maven_kd/4105/tokenizer.json filter=lfs diff=lfs merge=lfs -text
113
+ qwen3/distillm_0.6B_4B_maven_kd/821/tokenizer.json filter=lfs diff=lfs merge=lfs -text
114
+ qwen3/distillm_0.6B_4B_maven_rkl/1642/tokenizer.json filter=lfs diff=lfs merge=lfs -text
115
+ qwen3/distillm_0.6B_4B_maven_rkl/2463/tokenizer.json filter=lfs diff=lfs merge=lfs -text
116
+ qwen3/distillm_0.6B_4B_maven_rkl/3284/tokenizer.json filter=lfs diff=lfs merge=lfs -text
117
+ qwen3/distillm_0.6B_4B_maven_rkl/4105/tokenizer.json filter=lfs diff=lfs merge=lfs -text
118
+ qwen3/distillm_0.6B_4B_maven_rkl/821/tokenizer.json filter=lfs diff=lfs merge=lfs -text
119
+ qwen3/distillm_0.6B_4B_maven_srkl/1642/tokenizer.json filter=lfs diff=lfs merge=lfs -text
120
+ qwen3/distillm_0.6B_4B_maven_srkl/2463/tokenizer.json filter=lfs diff=lfs merge=lfs -text
121
+ qwen3/distillm_0.6B_4B_maven_srkl/3284/tokenizer.json filter=lfs diff=lfs merge=lfs -text
122
+ qwen3/distillm_0.6B_4B_maven_srkl/4105/tokenizer.json filter=lfs diff=lfs merge=lfs -text
123
+ qwen3/distillm_0.6B_4B_maven_srkl/821/tokenizer.json filter=lfs diff=lfs merge=lfs -text
124
+ qwen3/distillm_0.6B_4B_maven_srkl_2/1642/tokenizer.json filter=lfs diff=lfs merge=lfs -text
125
+ qwen3/distillm_0.6B_4B_maven_srkl_2/2463/tokenizer.json filter=lfs diff=lfs merge=lfs -text
126
+ qwen3/distillm_0.6B_4B_maven_srkl_2/3284/tokenizer.json filter=lfs diff=lfs merge=lfs -text
127
+ qwen3/distillm_0.6B_4B_maven_srkl_2/4105/tokenizer.json filter=lfs diff=lfs merge=lfs -text
128
+ qwen3/distillm_0.6B_4B_maven_srkl_2/821/tokenizer.json filter=lfs diff=lfs merge=lfs -text
129
+ qwen3/distillm_0.6B_4B_maven_srkl_on/1642/tokenizer.json filter=lfs diff=lfs merge=lfs -text
130
+ qwen3/distillm_0.6B_4B_maven_srkl_on/2463/tokenizer.json filter=lfs diff=lfs merge=lfs -text
131
+ qwen3/distillm_0.6B_4B_maven_srkl_on/3284/tokenizer.json filter=lfs diff=lfs merge=lfs -text
132
+ qwen3/distillm_0.6B_4B_maven_srkl_on/4105/tokenizer.json filter=lfs diff=lfs merge=lfs -text
133
+ qwen3/distillm_0.6B_4B_maven_srkl_on/821/tokenizer.json filter=lfs diff=lfs merge=lfs -text
134
+ qwen3/distillm_0.6B_4B_rams_kd/1155/tokenizer.json filter=lfs diff=lfs merge=lfs -text
135
+ qwen3/distillm_0.6B_4B_rams_kd/231/tokenizer.json filter=lfs diff=lfs merge=lfs -text
136
+ qwen3/distillm_0.6B_4B_rams_kd/462/tokenizer.json filter=lfs diff=lfs merge=lfs -text
137
+ qwen3/distillm_0.6B_4B_rams_kd/693/tokenizer.json filter=lfs diff=lfs merge=lfs -text
138
+ qwen3/distillm_0.6B_4B_rams_kd/924/tokenizer.json filter=lfs diff=lfs merge=lfs -text
139
+ qwen3/distillm_0.6B_4B_rams_rkl/1155/tokenizer.json filter=lfs diff=lfs merge=lfs -text
140
+ qwen3/distillm_0.6B_4B_rams_rkl/231/tokenizer.json filter=lfs diff=lfs merge=lfs -text
141
+ qwen3/distillm_0.6B_4B_rams_rkl/462/tokenizer.json filter=lfs diff=lfs merge=lfs -text
142
+ qwen3/distillm_0.6B_4B_rams_rkl/693/tokenizer.json filter=lfs diff=lfs merge=lfs -text
143
+ qwen3/distillm_0.6B_4B_rams_rkl/924/tokenizer.json filter=lfs diff=lfs merge=lfs -text
144
+ qwen3/distillm_0.6B_4B_rams_srkl/1155/tokenizer.json filter=lfs diff=lfs merge=lfs -text
145
+ qwen3/distillm_0.6B_4B_rams_srkl/231/tokenizer.json filter=lfs diff=lfs merge=lfs -text
146
+ qwen3/distillm_0.6B_4B_rams_srkl/462/tokenizer.json filter=lfs diff=lfs merge=lfs -text
147
+ qwen3/distillm_0.6B_4B_rams_srkl/693/tokenizer.json filter=lfs diff=lfs merge=lfs -text
148
+ qwen3/distillm_0.6B_4B_rams_srkl/924/tokenizer.json filter=lfs diff=lfs merge=lfs -text
149
+ qwen3/distillm_0.6B_4B_rams_srkl_2/1155/tokenizer.json filter=lfs diff=lfs merge=lfs -text
150
+ qwen3/distillm_0.6B_4B_rams_srkl_2/231/tokenizer.json filter=lfs diff=lfs merge=lfs -text
151
+ qwen3/distillm_0.6B_4B_rams_srkl_2/462/tokenizer.json filter=lfs diff=lfs merge=lfs -text
152
+ qwen3/distillm_0.6B_4B_rams_srkl_2/693/tokenizer.json filter=lfs diff=lfs merge=lfs -text
153
+ qwen3/distillm_0.6B_4B_rams_srkl_2/924/tokenizer.json filter=lfs diff=lfs merge=lfs -text
154
+ qwen3/distillm_0.6B_4B_rams_srkl_on/1155/tokenizer.json filter=lfs diff=lfs merge=lfs -text
155
+ qwen3/distillm_0.6B_4B_rams_srkl_on/231/tokenizer.json filter=lfs diff=lfs merge=lfs -text
156
+ qwen3/distillm_0.6B_4B_rams_srkl_on/462/tokenizer.json filter=lfs diff=lfs merge=lfs -text
157
+ qwen3/distillm_0.6B_4B_rams_srkl_on/693/tokenizer.json filter=lfs diff=lfs merge=lfs -text
158
+ qwen3/distillm_0.6B_4B_rams_srkl_on/924/tokenizer.json filter=lfs diff=lfs merge=lfs -text
159
+ qwen3/fdd/0.6B_4B_ace/196/tokenizer.json filter=lfs diff=lfs merge=lfs -text
160
+ qwen3/fdd/0.6B_4B_ace/294/tokenizer.json filter=lfs diff=lfs merge=lfs -text
161
+ qwen3/fdd/0.6B_4B_ace/392/tokenizer.json filter=lfs diff=lfs merge=lfs -text
162
+ qwen3/fdd/0.6B_4B_ace/490/tokenizer.json filter=lfs diff=lfs merge=lfs -text
163
+ qwen3/fdd/0.6B_4B_ace/98/tokenizer.json filter=lfs diff=lfs merge=lfs -text
164
+ qwen3/fdd/0.6B_4B_geneva/122/tokenizer.json filter=lfs diff=lfs merge=lfs -text
165
+ qwen3/fdd/0.6B_4B_geneva/183/tokenizer.json filter=lfs diff=lfs merge=lfs -text
166
+ qwen3/fdd/0.6B_4B_geneva/244/tokenizer.json filter=lfs diff=lfs merge=lfs -text
167
+ qwen3/fdd/0.6B_4B_geneva/305/tokenizer.json filter=lfs diff=lfs merge=lfs -text
168
+ qwen3/fdd/0.6B_4B_geneva/61/tokenizer.json filter=lfs diff=lfs merge=lfs -text
169
+ qwen3/fdd/0.6B_4B_maven/1642/tokenizer.json filter=lfs diff=lfs merge=lfs -text
170
+ qwen3/fdd/0.6B_4B_maven/2463/tokenizer.json filter=lfs diff=lfs merge=lfs -text
171
+ qwen3/fdd/0.6B_4B_maven/3284/tokenizer.json filter=lfs diff=lfs merge=lfs -text
172
+ qwen3/fdd/0.6B_4B_maven/4105/tokenizer.json filter=lfs diff=lfs merge=lfs -text
173
+ qwen3/fdd/0.6B_4B_maven/821/tokenizer.json filter=lfs diff=lfs merge=lfs -text
174
+ qwen3/fdd/0.6B_4B_rams/1155/tokenizer.json filter=lfs diff=lfs merge=lfs -text
175
+ qwen3/fdd/0.6B_4B_rams/231/tokenizer.json filter=lfs diff=lfs merge=lfs -text
176
+ qwen3/fdd/0.6B_4B_rams/462/tokenizer.json filter=lfs diff=lfs merge=lfs -text
177
+ qwen3/fdd/0.6B_4B_rams/693/tokenizer.json filter=lfs diff=lfs merge=lfs -text
178
+ qwen3/fdd/0.6B_4B_rams/924/tokenizer.json filter=lfs diff=lfs merge=lfs -text
179
+ qwen3/sft_0.6B_ace_lora/e5-bs8-lr5e-05-G2-N2-NN1-lora-8-64-0.1/196/tokenizer.json filter=lfs diff=lfs merge=lfs -text
180
+ qwen3/sft_0.6B_ace_lora/e5-bs8-lr5e-05-G2-N2-NN1-lora-8-64-0.1/294/tokenizer.json filter=lfs diff=lfs merge=lfs -text
181
+ qwen3/sft_0.6B_ace_lora/e5-bs8-lr5e-05-G2-N2-NN1-lora-8-64-0.1/392/tokenizer.json filter=lfs diff=lfs merge=lfs -text
182
+ qwen3/sft_0.6B_ace_lora/e5-bs8-lr5e-05-G2-N2-NN1-lora-8-64-0.1/490/tokenizer.json filter=lfs diff=lfs merge=lfs -text
183
+ qwen3/sft_0.6B_ace_lora/e5-bs8-lr5e-05-G2-N2-NN1-lora-8-64-0.1/98/tokenizer.json filter=lfs diff=lfs merge=lfs -text
184
+ qwen3/sft_0.6B_geneva_lora/e5-bs8-lr5e-05-G2-N2-NN1-lora-8-64-0.1/122/tokenizer.json filter=lfs diff=lfs merge=lfs -text
185
+ qwen3/sft_0.6B_geneva_lora/e5-bs8-lr5e-05-G2-N2-NN1-lora-8-64-0.1/183/tokenizer.json filter=lfs diff=lfs merge=lfs -text
186
+ qwen3/sft_0.6B_geneva_lora/e5-bs8-lr5e-05-G2-N2-NN1-lora-8-64-0.1/244/tokenizer.json filter=lfs diff=lfs merge=lfs -text
187
+ qwen3/sft_0.6B_geneva_lora/e5-bs8-lr5e-05-G2-N2-NN1-lora-8-64-0.1/305/tokenizer.json filter=lfs diff=lfs merge=lfs -text
188
+ qwen3/sft_0.6B_geneva_lora/e5-bs8-lr5e-05-G2-N2-NN1-lora-8-64-0.1/61/tokenizer.json filter=lfs diff=lfs merge=lfs -text
189
+ qwen3/sft_0.6B_maven_lora/e5-bs8-lr5e-05-G2-N2-NN1-lora-8-64-0.1/1642/tokenizer.json filter=lfs diff=lfs merge=lfs -text
190
+ qwen3/sft_0.6B_maven_lora/e5-bs8-lr5e-05-G2-N2-NN1-lora-8-64-0.1/2463/tokenizer.json filter=lfs diff=lfs merge=lfs -text
191
+ qwen3/sft_0.6B_maven_lora/e5-bs8-lr5e-05-G2-N2-NN1-lora-8-64-0.1/3284/tokenizer.json filter=lfs diff=lfs merge=lfs -text
192
+ qwen3/sft_0.6B_maven_lora/e5-bs8-lr5e-05-G2-N2-NN1-lora-8-64-0.1/4105/tokenizer.json filter=lfs diff=lfs merge=lfs -text
193
+ qwen3/sft_0.6B_maven_lora/e5-bs8-lr5e-05-G2-N2-NN1-lora-8-64-0.1/821/tokenizer.json filter=lfs diff=lfs merge=lfs -text
194
+ qwen3/sft_0.6B_rams_lora/e5-bs8-lr5e-05-G2-N2-NN1-lora-8-64-0.1/1155/tokenizer.json filter=lfs diff=lfs merge=lfs -text
195
+ qwen3/sft_0.6B_rams_lora/e5-bs8-lr5e-05-G2-N2-NN1-lora-8-64-0.1/231/tokenizer.json filter=lfs diff=lfs merge=lfs -text
196
+ qwen3/sft_0.6B_rams_lora/e5-bs8-lr5e-05-G2-N2-NN1-lora-8-64-0.1/462/tokenizer.json filter=lfs diff=lfs merge=lfs -text
197
+ qwen3/sft_0.6B_rams_lora/e5-bs8-lr5e-05-G2-N2-NN1-lora-8-64-0.1/693/tokenizer.json filter=lfs diff=lfs merge=lfs -text
198
+ qwen3/sft_0.6B_rams_lora/e5-bs8-lr5e-05-G2-N2-NN1-lora-8-64-0.1/924/tokenizer.json filter=lfs diff=lfs merge=lfs -text
199
+ qwen3/sft_4B_ace/e5-bs2-lr0.0001-G8-N2-NN1-lora-32-64-0.05/196/tokenizer.json filter=lfs diff=lfs merge=lfs -text
200
+ qwen3/sft_4B_ace/e5-bs2-lr0.0001-G8-N2-NN1-lora-32-64-0.05/294/tokenizer.json filter=lfs diff=lfs merge=lfs -text
201
+ qwen3/sft_4B_ace/e5-bs2-lr0.0001-G8-N2-NN1-lora-32-64-0.05/392/tokenizer.json filter=lfs diff=lfs merge=lfs -text
202
+ qwen3/sft_4B_ace/e5-bs2-lr0.0001-G8-N2-NN1-lora-32-64-0.05/490/tokenizer.json filter=lfs diff=lfs merge=lfs -text
203
+ qwen3/sft_4B_ace/e5-bs2-lr0.0001-G8-N2-NN1-lora-32-64-0.05/98/tokenizer.json filter=lfs diff=lfs merge=lfs -text
204
+ qwen3/sft_4B_geneva/e5-bs2-lr0.0003-G8-N2-NN1-lora-64-128-0.05/122/tokenizer.json filter=lfs diff=lfs merge=lfs -text
205
+ qwen3/sft_4B_geneva/e5-bs2-lr0.0003-G8-N2-NN1-lora-64-128-0.05/183/tokenizer.json filter=lfs diff=lfs merge=lfs -text
206
+ qwen3/sft_4B_geneva/e5-bs2-lr0.0003-G8-N2-NN1-lora-64-128-0.05/244/tokenizer.json filter=lfs diff=lfs merge=lfs -text
207
+ qwen3/sft_4B_geneva/e5-bs2-lr0.0003-G8-N2-NN1-lora-64-128-0.05/305/tokenizer.json filter=lfs diff=lfs merge=lfs -text
208
+ qwen3/sft_4B_geneva/e5-bs2-lr0.0003-G8-N2-NN1-lora-64-128-0.05/61/tokenizer.json filter=lfs diff=lfs merge=lfs -text
209
+ qwen3/sft_4B_maven/e6-bs2-lr0.0005-G8-N2-NN1-lora-64-128-0.1/1642/tokenizer.json filter=lfs diff=lfs merge=lfs -text
210
+ qwen3/sft_4B_maven/e6-bs2-lr0.0005-G8-N2-NN1-lora-64-128-0.1/2463/tokenizer.json filter=lfs diff=lfs merge=lfs -text
211
+ qwen3/sft_4B_maven/e6-bs2-lr0.0005-G8-N2-NN1-lora-64-128-0.1/3284/tokenizer.json filter=lfs diff=lfs merge=lfs -text
212
+ qwen3/sft_4B_maven/e6-bs2-lr0.0005-G8-N2-NN1-lora-64-128-0.1/4105/tokenizer.json filter=lfs diff=lfs merge=lfs -text
213
+ qwen3/sft_4B_maven/e6-bs2-lr0.0005-G8-N2-NN1-lora-64-128-0.1/4926/tokenizer.json filter=lfs diff=lfs merge=lfs -text
214
+ qwen3/sft_4B_maven/e6-bs2-lr0.0005-G8-N2-NN1-lora-64-128-0.1/821/tokenizer.json filter=lfs diff=lfs merge=lfs -text
215
+ qwen3/sft_4B_rams/e5-bs2-lr0.0001-G8-N2-NN1-lora-32-64-0.05/1155/tokenizer.json filter=lfs diff=lfs merge=lfs -text
216
+ qwen3/sft_4B_rams/e5-bs2-lr0.0001-G8-N2-NN1-lora-32-64-0.05/231/tokenizer.json filter=lfs diff=lfs merge=lfs -text
217
+ qwen3/sft_4B_rams/e5-bs2-lr0.0001-G8-N2-NN1-lora-32-64-0.05/462/tokenizer.json filter=lfs diff=lfs merge=lfs -text
218
+ qwen3/sft_4B_rams/e5-bs2-lr0.0001-G8-N2-NN1-lora-32-64-0.05/693/tokenizer.json filter=lfs diff=lfs merge=lfs -text
219
+ qwen3/sft_4B_rams/e5-bs2-lr0.0001-G8-N2-NN1-lora-32-64-0.05/924/tokenizer.json filter=lfs diff=lfs merge=lfs -text
220
+ qwen3/span_distillm/0.6B_4B_ace_srkl/196/tokenizer.json filter=lfs diff=lfs merge=lfs -text
221
+ qwen3/span_distillm/0.6B_4B_ace_srkl/294/tokenizer.json filter=lfs diff=lfs merge=lfs -text
222
+ qwen3/span_distillm/0.6B_4B_ace_srkl/392/tokenizer.json filter=lfs diff=lfs merge=lfs -text
223
+ qwen3/span_distillm/0.6B_4B_ace_srkl/490/tokenizer.json filter=lfs diff=lfs merge=lfs -text
224
+ qwen3/span_distillm/0.6B_4B_ace_srkl/98/tokenizer.json filter=lfs diff=lfs merge=lfs -text
225
+ qwen3/span_distillm/0.6B_4B_ace_srkl_2/196/tokenizer.json filter=lfs diff=lfs merge=lfs -text
226
+ qwen3/span_distillm/0.6B_4B_ace_srkl_2/294/tokenizer.json filter=lfs diff=lfs merge=lfs -text
227
+ qwen3/span_distillm/0.6B_4B_ace_srkl_2/392/tokenizer.json filter=lfs diff=lfs merge=lfs -text
228
+ qwen3/span_distillm/0.6B_4B_ace_srkl_2/490/tokenizer.json filter=lfs diff=lfs merge=lfs -text
229
+ qwen3/span_distillm/0.6B_4B_ace_srkl_2/98/tokenizer.json filter=lfs diff=lfs merge=lfs -text
230
+ qwen3/span_distillm/0.6B_4B_geneva_srkl/122/tokenizer.json filter=lfs diff=lfs merge=lfs -text
231
+ qwen3/span_distillm/0.6B_4B_geneva_srkl/183/tokenizer.json filter=lfs diff=lfs merge=lfs -text
232
+ qwen3/span_distillm/0.6B_4B_geneva_srkl/244/tokenizer.json filter=lfs diff=lfs merge=lfs -text
233
+ qwen3/span_distillm/0.6B_4B_geneva_srkl/305/tokenizer.json filter=lfs diff=lfs merge=lfs -text
234
+ qwen3/span_distillm/0.6B_4B_geneva_srkl/61/tokenizer.json filter=lfs diff=lfs merge=lfs -text
235
+ qwen3/span_distillm/0.6B_4B_geneva_srkl_2/122/tokenizer.json filter=lfs diff=lfs merge=lfs -text
236
+ qwen3/span_distillm/0.6B_4B_geneva_srkl_2/183/tokenizer.json filter=lfs diff=lfs merge=lfs -text
237
+ qwen3/span_distillm/0.6B_4B_geneva_srkl_2/244/tokenizer.json filter=lfs diff=lfs merge=lfs -text
238
+ qwen3/span_distillm/0.6B_4B_geneva_srkl_2/305/tokenizer.json filter=lfs diff=lfs merge=lfs -text
239
+ qwen3/span_distillm/0.6B_4B_geneva_srkl_2/61/tokenizer.json filter=lfs diff=lfs merge=lfs -text
240
+ qwen3/span_distillm/0.6B_4B_maven_srkl/1642/tokenizer.json filter=lfs diff=lfs merge=lfs -text
241
+ qwen3/span_distillm/0.6B_4B_maven_srkl/2463/tokenizer.json filter=lfs diff=lfs merge=lfs -text
242
+ qwen3/span_distillm/0.6B_4B_maven_srkl/3284/tokenizer.json filter=lfs diff=lfs merge=lfs -text
243
+ qwen3/span_distillm/0.6B_4B_maven_srkl/4105/tokenizer.json filter=lfs diff=lfs merge=lfs -text
244
+ qwen3/span_distillm/0.6B_4B_maven_srkl/821/tokenizer.json filter=lfs diff=lfs merge=lfs -text
245
+ qwen3/span_distillm/0.6B_4B_maven_srkl_2/1642/tokenizer.json filter=lfs diff=lfs merge=lfs -text
246
+ qwen3/span_distillm/0.6B_4B_maven_srkl_2/2463/tokenizer.json filter=lfs diff=lfs merge=lfs -text
247
+ qwen3/span_distillm/0.6B_4B_maven_srkl_2/3284/tokenizer.json filter=lfs diff=lfs merge=lfs -text
248
+ qwen3/span_distillm/0.6B_4B_maven_srkl_2/4105/tokenizer.json filter=lfs diff=lfs merge=lfs -text
249
+ qwen3/span_distillm/0.6B_4B_maven_srkl_2/821/tokenizer.json filter=lfs diff=lfs merge=lfs -text
250
+ qwen3/span_distillm/0.6B_4B_rams_srkl/1155/tokenizer.json filter=lfs diff=lfs merge=lfs -text
251
+ qwen3/span_distillm/0.6B_4B_rams_srkl/231/tokenizer.json filter=lfs diff=lfs merge=lfs -text
252
+ qwen3/span_distillm/0.6B_4B_rams_srkl/462/tokenizer.json filter=lfs diff=lfs merge=lfs -text
253
+ qwen3/span_distillm/0.6B_4B_rams_srkl/693/tokenizer.json filter=lfs diff=lfs merge=lfs -text
254
+ qwen3/span_distillm/0.6B_4B_rams_srkl/924/tokenizer.json filter=lfs diff=lfs merge=lfs -text
255
+ qwen3/span_distillm/0.6B_4B_rams_srkl_2/1155/tokenizer.json filter=lfs diff=lfs merge=lfs -text
256
+ qwen3/span_distillm/0.6B_4B_rams_srkl_2/231/tokenizer.json filter=lfs diff=lfs merge=lfs -text
257
+ qwen3/span_distillm/0.6B_4B_rams_srkl_2/462/tokenizer.json filter=lfs diff=lfs merge=lfs -text
258
+ qwen3/span_distillm/0.6B_4B_rams_srkl_2/693/tokenizer.json filter=lfs diff=lfs merge=lfs -text
259
+ qwen3/span_distillm/0.6B_4B_rams_srkl_2/924/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/305/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/305/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/305/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 896,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4864,
13
+ "is_model_parallel": false,
14
+ "layer_types": [
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention"
39
+ ],
40
+ "max_position_embeddings": 32768,
41
+ "max_window_layers": 24,
42
+ "model_type": "qwen2",
43
+ "num_attention_heads": 14,
44
+ "num_hidden_layers": 24,
45
+ "num_key_value_heads": 2,
46
+ "rms_norm_eps": 1e-06,
47
+ "rope_scaling": null,
48
+ "rope_theta": 1000000.0,
49
+ "sliding_window": null,
50
+ "tie_word_embeddings": true,
51
+ "transformers_version": "4.57.3",
52
+ "use_cache": true,
53
+ "use_mrope": false,
54
+ "use_sliding_window": false,
55
+ "vocab_size": 151936
56
+ }
qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/305/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
5
+ "transformers_version": "4.57.3"
6
+ }
qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/305/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/305/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b648f5a48d396f26f0ef5d4570dda7caab7ea304760862de83ea8b2ddb1e13fc
3
+ size 988104508
qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/305/special_tokens_map.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": "<|im_end|>",
18
+ "pad_token": "<|im_end|>"
19
+ }
qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/305/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/305/tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|im_end|>",
204
+ "padding_side": "right",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/305/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/args.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model_path": "Qwen/Qwen2.5-0.5B", "ckpt_name": "qwen2.5-0.5B", "model_type": "qwen", "teacher_model_type": null, "n_gpu": 2, "n_nodes": 1, "teacher_model_path": null, "teacher_ckpt_name": null, "teacher_model_fp16": false, "model_parallel": false, "model_parallel_size": null, "no_value": false, "dropout_path_rate": null, "fp32": false, "bf16": false, "type": "lm", "do_train": true, "do_valid": true, "do_eval": false, "base_path": ".", "load": null, "save": "./results/qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1", "log_interval": 20, "mid_log_num": -1, "save_interval": -1, "eval_interval": -1, "local_rank": 0, "save_additional_suffix": "", "save_rollout": false, "eb_sample_times": 3, "data_dir": "./processed_data/geneva/qwen/", "processed_data_dir": null, "force_process": false, "force_process_demo": false, "data_process_workers": -1, "train_num": -1, "train_ratio": 1, "dev_num": -1, "dev_ratio": 1, "gen_num": -1, "data_names": null, "prompt_type": null, "num_workers": 0, "max_prompt_length": 460, "t_max_prompt_length": 640, "min_prompt_length": 128, "json_data": false, "bin_data": false, "txt_data": false, "prompt_data_dir": null, "lm_data_dir": null, "eval_ppl": false, "eval_rw": false, "eval_gen": true, "only_prompt": false, "batch_size": 8, "eval_batch_size": 32, "clip_grad": 1.0, "total_iters": null, "train_iters_per_epoch": -1, "max_length": 768, "t_max_length": 1024, "seed": 42, "seed_order": 42, "seed_data": 42, "seed_ppo": 42, "seed_lm": 7, "epochs": 5, "training_epochs": 10000, "gradient_accumulation_steps": 2, "gradient_checkpointing": false, "attn_dtype": null, "lr": 5e-05, "lr_min": 1e-07, "weight_decay": 0.01, "loss_scale": 65536, "kd_ratio": null, "warmup_iters": 0, "warmup_ratio": 0.1, "lr_decay_iters": null, "lr_decay_style": "wrmup_cosine", "scheduler_name": "constant_trm", "w_span_loss": 1.0, "reward_scaling": null, "cliprange_reward": 1, "ppo_epochs": null, "num_rollouts": 256, "num_rollouts_per_device": null, "cliprange": 0.2, "chunk_size": null, "gamma": 0.95, "length_norm": false, "single_step_reg": false, "teacher_mixed_alpha": null, "lm_coef": 1, "skew_alpha": 0.1, "student_gen": false, "gen_top_p": 1.0, "gen_num_beams": 2, "mixed_alpha": 0.5, "loss_eps": 0.1, "init_threshold": 0.0, "capacity": 1000, "replay_ratio": "decreasing", "student_layer_mapping": [-1], "teacher_layer_mapping": [-1], "split_layer_mapping": [0, 0, 0, 0], "use_dsa": false, "use_hs": false, "top_k": 0, "top_p": 0.95, "do_sample": true, "no_repeat_ngram_size": 6, "repetition_penalty": null, "num_beams": 1, "temperature": 0.5, "peft": null, "peft_lora_r": 16, "peft_lora_alpha": 64, "peft_lora_dropout": 0.1, "peft_name": null, "peft_path": null, "teacher_peft_name": null, "teacher_peft_path": null, "deepspeed": true, "deepspeed_config": "./configs/deepspeed/ds_config_bf16.json", "deepscale": false, "deepscale_config": null, "rank": 0, "world_size": 2}
qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/eval/0/answers.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/eval/1/answers.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/eval/2/answers.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/eval/3/answers.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/eval/4/answers.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5/sft_0.5B_geneva/e5-bs8-lr5e-05-G2-N2-NN1/log.txt ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+
3
+ ============================== EXP at 2026-02-25 09:24:56 ==============================
4
+ dev | avg_loss: 2.519230769230769 | {'exact_match': 0.0, 'rougeL': 0.7516, 'trigger_counts': {'tp': 0, 'fp': 0, 'fn': 1440}, 'argument_counts': {'tp': 0, 'fp': 0, 'fn': 2383}, 'trigger_text': {'precision': 0, 'recall': 0.0, 'f1': 0}, 'trigger': {'precision': 0, 'recall': 0.0, 'f1': 0}, 'argument': {'precision': 0, 'recall': 0.0, 'f1': 0}}
5
+ train | epoch 0 | Iter: 38/ 610 | global iter: 20/ 305 | loss: 1.3396 | ds_loss: 0.0000 | lr: 3.1148e-05 | scale: 1.0000 | micro time: 0.275 | step time: 0.482
6
+ train | epoch 0 | Iter: 78/ 610 | global iter: 40/ 305 | loss: 0.4584 | ds_loss: 0.0000 | lr: 4.9882e-05 | scale: 1.0000 | micro time: 0.274 | step time: 0.502
7
+ train | epoch 0 | Iter: 118/ 610 | global iter: 60/ 305 | loss: 0.2991 | ds_loss: 0.0000 | lr: 4.8682e-05 | scale: 1.0000 | micro time: 0.276 | step time: 0.504
8
+ dev | avg_loss: 0.27576622596153844 | {'exact_match': 9.5785, 'rougeL': 58.6178, 'trigger_counts': {'tp': 578, 'fp': 330, 'fn': 862}, 'argument_counts': {'tp': 555, 'fp': 946, 'fn': 1828}, 'trigger_text': {'precision': 0.7059471365638766, 'recall': 0.44513888888888886, 'f1': 0.5459965928449744}, 'trigger': {'precision': 0.6365638766519823, 'recall': 0.4013888888888889, 'f1': 0.4923339011925042}, 'argument': {'precision': 0.3697534976682212, 'recall': 0.23289970625262274, 'f1': 0.2857878475798146}}
9
+ train | epoch 1 | Iter: 158/ 610 | global iter: 80/ 305 | loss: 0.1892 | ds_loss: 0.0000 | lr: 4.6247e-05 | scale: 1.0000 | micro time: 0.276 | step time: 0.504
10
+ train | epoch 1 | Iter: 198/ 610 | global iter: 100/ 305 | loss: 0.1732 | ds_loss: 0.0000 | lr: 4.2703e-05 | scale: 1.0000 | micro time: 0.277 | step time: 0.506
11
+ train | epoch 1 | Iter: 238/ 610 | global iter: 120/ 305 | loss: 0.1625 | ds_loss: 0.0000 | lr: 3.8236e-05 | scale: 1.0000 | micro time: 0.278 | step time: 0.506
12
+ dev | avg_loss: 0.23317307692307693 | {'exact_match': 10.2171, 'rougeL': 62.3835, 'trigger_counts': {'tp': 900, 'fp': 787, 'fn': 540}, 'argument_counts': {'tp': 983, 'fp': 1728, 'fn': 1400}, 'trigger_text': {'precision': 0.580166270783848, 'recall': 0.6784722222222223, 'f1': 0.6254801536491678}, 'trigger': {'precision': 0.5334914048606995, 'recall': 0.625, 'f1': 0.5756315957787017}, 'argument': {'precision': 0.3625968277388418, 'recall': 0.41250524548887957, 'f1': 0.38594424813506084}}
13
+ train | epoch 2 | Iter: 278/ 610 | global iter: 140/ 305 | loss: 0.1023 | ds_loss: 0.0000 | lr: 3.3078e-05 | scale: 1.0000 | micro time: 0.277 | step time: 0.506
14
+ train | epoch 2 | Iter: 318/ 610 | global iter: 160/ 305 | loss: 0.0910 | ds_loss: 0.0000 | lr: 2.7499e-05 | scale: 1.0000 | micro time: 0.277 | step time: 0.506
15
+ train | epoch 2 | Iter: 358/ 610 | global iter: 180/ 305 | loss: 0.0906 | ds_loss: 0.0000 | lr: 2.1790e-05 | scale: 1.0000 | micro time: 0.277 | step time: 0.508
16
+ dev | avg_loss: 0.22318209134615385 | {'exact_match': 13.7931, 'rougeL': 65.6264, 'trigger_counts': {'tp': 969, 'fp': 655, 'fn': 471}, 'argument_counts': {'tp': 1107, 'fp': 1594, 'fn': 1276}, 'trigger_text': {'precision': 0.6311576354679803, 'recall': 0.7118055555555556, 'f1': 0.6690600522193212}, 'trigger': {'precision': 0.5966748768472906, 'recall': 0.6729166666666667, 'f1': 0.6325065274151436}, 'argument': {'precision': 0.4098482043687523, 'recall': 0.46454049517415025, 'f1': 0.43548387096774194}}
17
+ train | epoch 3 | Iter: 398/ 610 | global iter: 200/ 305 | loss: 0.0543 | ds_loss: 0.0000 | lr: 1.6248e-05 | scale: 1.0000 | micro time: 0.276 | step time: 0.505
18
+ train | epoch 3 | Iter: 438/ 610 | global iter: 220/ 305 | loss: 0.0352 | ds_loss: 0.0000 | lr: 1.1163e-05 | scale: 1.0000 | micro time: 0.277 | step time: 0.506
19
+ train | epoch 3 | Iter: 478/ 610 | global iter: 240/ 305 | loss: 0.0378 | ds_loss: 0.0000 | lr: 6.7993e-06 | scale: 1.0000 | micro time: 0.279 | step time: 0.507
20
+ dev | avg_loss: 0.23985877403846154 | {'exact_match': 14.8148, 'rougeL': 66.674, 'trigger_counts': {'tp': 1017, 'fp': 606, 'fn': 423}, 'argument_counts': {'tp': 1191, 'fp': 1448, 'fn': 1192}, 'trigger_text': {'precision': 0.6592729513247073, 'recall': 0.7430555555555556, 'f1': 0.6986614430297095}, 'trigger': {'precision': 0.6266173752310537, 'recall': 0.70625, 'f1': 0.664054848188051}, 'argument': {'precision': 0.4513073133762789, 'recall': 0.49979018044481743, 'f1': 0.47431302270011944}}
21
+ train | epoch 4 | Iter: 518/ 610 | global iter: 260/ 305 | loss: 0.0174 | ds_loss: 0.0000 | lr: 3.3852e-06 | scale: 1.0000 | micro time: 0.277 | step time: 0.505
22
+ train | epoch 4 | Iter: 558/ 610 | global iter: 280/ 305 | loss: 0.0089 | ds_loss: 0.0000 | lr: 1.0987e-06 | scale: 1.0000 | micro time: 0.276 | step time: 0.506
23
+ train | epoch 4 | Iter: 598/ 610 | global iter: 300/ 305 | loss: 0.0095 | ds_loss: 0.0000 | lr: 5.8919e-08 | scale: 1.0000 | micro time: 0.278 | step time: 0.507
24
+ dev | avg_loss: 0.2682542067307692 | {'exact_match': 14.1762, 'rougeL': 67.0534, 'trigger_counts': {'tp': 1035, 'fp': 644, 'fn': 405}, 'argument_counts': {'tp': 1208, 'fp': 1572, 'fn': 1175}, 'trigger_text': {'precision': 0.6480047647409172, 'recall': 0.7555555555555555, 'f1': 0.6976595062520039}, 'trigger': {'precision': 0.6164383561643836, 'recall': 0.71875, 'f1': 0.663674254568772}, 'argument': {'precision': 0.43453237410071943, 'recall': 0.5069240453210239, 'f1': 0.46794499322099553}}
25
+
26
+
27
+ ============================== EXP at 2026-02-25 09:44:52 ==============================
28
+ dev | avg_loss: 1.3149038461538463 | {'exact_match': 0.0, 'rougeL': 1.1856, 'trigger_counts': {'tp': 0, 'fp': 0, 'fn': 1440}, 'argument_counts': {'tp': 0, 'fp': 0, 'fn': 2383}, 'trigger_text': {'precision': 0, 'recall': 0.0, 'f1': 0}, 'trigger': {'precision': 0, 'recall': 0.0, 'f1': 0}, 'argument': {'precision': 0, 'recall': 0.0, 'f1': 0}}
29
+ train | epoch 0 | Iter: 38/ 610 | global iter: 20/ 305 | loss: 0.7379 | ds_loss: 0.0000 | lr: 3.1148e-05 | scale: 1.0000 | micro time: 0.275 | step time: 0.485
30
+ train | epoch 0 | Iter: 78/ 610 | global iter: 40/ 305 | loss: 0.2913 | ds_loss: 0.0000 | lr: 4.9882e-05 | scale: 1.0000 | micro time: 0.276 | step time: 0.505
31
+ train | epoch 0 | Iter: 118/ 610 | global iter: 60/ 305 | loss: 0.1854 | ds_loss: 0.0000 | lr: 4.8682e-05 | scale: 1.0000 | micro time: 0.277 | step time: 0.506
32
+ dev | avg_loss: 0.16579026442307693 | {'exact_match': 8.94, 'rougeL': 64.8151, 'trigger_counts': {'tp': 656, 'fp': 455, 'fn': 784}, 'argument_counts': {'tp': 644, 'fp': 1177, 'fn': 1739}, 'trigger_text': {'precision': 0.6507650765076508, 'recall': 0.5020833333333333, 'f1': 0.5668365346922775}, 'trigger': {'precision': 0.5904590459045904, 'recall': 0.45555555555555555, 'f1': 0.5143081144649158}, 'argument': {'precision': 0.35365183964854474, 'recall': 0.2702475870751154, 'f1': 0.3063748810656518}}
33
+ train | epoch 1 | Iter: 158/ 610 | global iter: 80/ 305 | loss: 0.1243 | ds_loss: 0.0000 | lr: 4.6247e-05 | scale: 1.0000 | micro time: 0.279 | step time: 0.506
34
+ train | epoch 1 | Iter: 198/ 610 | global iter: 100/ 305 | loss: 0.1087 | ds_loss: 0.0000 | lr: 4.2703e-05 | scale: 1.0000 | micro time: 0.279 | step time: 0.508
35
+ train | epoch 1 | Iter: 238/ 610 | global iter: 120/ 305 | loss: 0.0995 | ds_loss: 0.0000 | lr: 3.8236e-05 | scale: 1.0000 | micro time: 0.283 | step time: 0.509
36
+ dev | avg_loss: 0.14528245192307693 | {'exact_match': 13.6654, 'rougeL': 69.3845, 'trigger_counts': {'tp': 812, 'fp': 538, 'fn': 628}, 'argument_counts': {'tp': 873, 'fp': 1240, 'fn': 1510}, 'trigger_text': {'precision': 0.6518518518518519, 'recall': 0.6111111111111112, 'f1': 0.6308243727598567}, 'trigger': {'precision': 0.6014814814814815, 'recall': 0.5638888888888889, 'f1': 0.582078853046595}, 'argument': {'precision': 0.4131566493137719, 'recall': 0.3663449433487201, 'f1': 0.38834519572953735}}
37
+ train | epoch 2 | Iter: 278/ 610 | global iter: 140/ 305 | loss: 0.0651 | ds_loss: 0.0000 | lr: 3.3078e-05 | scale: 1.0000 | micro time: 0.278 | step time: 0.507
38
+ train | epoch 2 | Iter: 318/ 610 | global iter: 160/ 305 | loss: 0.0541 | ds_loss: 0.0000 | lr: 2.7499e-05 | scale: 1.0000 | micro time: 0.280 | step time: 0.509
39
+ train | epoch 2 | Iter: 358/ 610 | global iter: 180/ 305 | loss: 0.0541 | ds_loss: 0.0000 | lr: 2.1790e-05 | scale: 1.0000 | micro time: 0.281 | step time: 0.510
40
+ dev | avg_loss: 0.13649338942307693 | {'exact_match': 15.3257, 'rougeL': 70.17, 'trigger_counts': {'tp': 842, 'fp': 406, 'fn': 598}, 'argument_counts': {'tp': 1009, 'fp': 1088, 'fn': 1374}, 'trigger_text': {'precision': 0.7035256410256411, 'recall': 0.6097222222222223, 'f1': 0.6532738095238095}, 'trigger': {'precision': 0.6746794871794872, 'recall': 0.5847222222222223, 'f1': 0.6264880952380953}, 'argument': {'precision': 0.48116356700047686, 'recall': 0.4234158623583718, 'f1': 0.4504464285714286}}
41
+ train | epoch 3 | Iter: 398/ 610 | global iter: 200/ 305 | loss: 0.0329 | ds_loss: 0.0000 | lr: 1.6248e-05 | scale: 1.0000 | micro time: 0.278 | step time: 0.508
42
+ train | epoch 3 | Iter: 438/ 610 | global iter: 220/ 305 | loss: 0.0224 | ds_loss: 0.0000 | lr: 1.1163e-05 | scale: 1.0000 | micro time: 0.280 | step time: 0.509
43
+ train | epoch 3 | Iter: 478/ 610 | global iter: 240/ 305 | loss: 0.0215 | ds_loss: 0.0000 | lr: 6.7993e-06 | scale: 1.0000 | micro time: 0.281 | step time: 0.510
44
+ dev | avg_loss: 0.14832481971153846 | {'exact_match': 13.7931, 'rougeL': 69.6037, 'trigger_counts': {'tp': 959, 'fp': 594, 'fn': 481}, 'argument_counts': {'tp': 1124, 'fp': 1404, 'fn': 1259}, 'trigger_text': {'precision': 0.6458467482292337, 'recall': 0.6965277777777777, 'f1': 0.6702305379218175}, 'trigger': {'precision': 0.6175144880875725, 'recall': 0.6659722222222222, 'f1': 0.6408286000668226}, 'argument': {'precision': 0.44462025316455694, 'recall': 0.4716743600503567, 'f1': 0.4577479128487069}}
45
+ train | epoch 4 | Iter: 518/ 610 | global iter: 260/ 305 | loss: 0.0122 | ds_loss: 0.0000 | lr: 3.3852e-06 | scale: 1.0000 | micro time: 0.278 | step time: 0.508
46
+ train | epoch 4 | Iter: 558/ 610 | global iter: 280/ 305 | loss: 0.0066 | ds_loss: 0.0000 | lr: 1.0987e-06 | scale: 1.0000 | micro time: 0.279 | step time: 0.509
47
+ train | epoch 4 | Iter: 598/ 610 | global iter: 300/ 305 | loss: 0.0074 | ds_loss: 0.0000 | lr: 5.8919e-08 | scale: 1.0000 | micro time: 0.279 | step time: 0.510
48
+ dev | avg_loss: 0.16278545673076922 | {'exact_match': 14.4317, 'rougeL': 69.7236, 'trigger_counts': {'tp': 989, 'fp': 623, 'fn': 451}, 'argument_counts': {'tp': 1201, 'fp': 1514, 'fn': 1182}, 'trigger_text': {'precision': 0.6433002481389578, 'recall': 0.7201388888888889, 'f1': 0.6795543905635649}, 'trigger': {'precision': 0.6135235732009926, 'recall': 0.6868055555555556, 'f1': 0.6480996068152032}, 'argument': {'precision': 0.4423572744014733, 'recall': 0.5039865715484683, 'f1': 0.47116516280894466}}
49
+
50
+
51
+ ============================== EXP at 2026-02-25 09:59:35 ==============================
52
+
53
+
54
+ ============================== EXP at 2026-02-25 10:00:16 ==============================
55
+ dev | avg_loss: 1.2199519230769231 | {'exact_match': 0.0, 'rougeL': 0.897, 'trigger_counts': {'tp': 0, 'fp': 0, 'fn': 1440}, 'argument_counts': {'tp': 0, 'fp': 0, 'fn': 2383}, 'trigger_text': {'precision': 0, 'recall': 0.0, 'f1': 0}, 'trigger': {'precision': 0, 'recall': 0.0, 'f1': 0}, 'argument': {'precision': 0, 'recall': 0.0, 'f1': 0}}
56
+ train | epoch 0 | Iter: 38/ 610 | global iter: 20/ 305 | loss: 0.6820 | ds_loss: 0.0000 | lr: 3.1148e-05 | scale: 1.0000 | micro time: 0.278 | step time: 0.488
57
+ train | epoch 0 | Iter: 78/ 610 | global iter: 40/ 305 | loss: 0.2544 | ds_loss: 0.0000 | lr: 4.9882e-05 | scale: 1.0000 | micro time: 0.278 | step time: 0.507
58
+ train | epoch 0 | Iter: 118/ 610 | global iter: 60/ 305 | loss: 0.1641 | ds_loss: 0.0000 | lr: 4.8682e-05 | scale: 1.0000 | micro time: 0.278 | step time: 0.508
59
+ dev | avg_loss: 0.14723557692307693 | {'exact_match': 6.1303, 'rougeL': 64.9987, 'trigger_counts': {'tp': 776, 'fp': 674, 'fn': 664}, 'argument_counts': {'tp': 672, 'fp': 1465, 'fn': 1711}, 'trigger_text': {'precision': 0.5979310344827586, 'recall': 0.6020833333333333, 'f1': 0.6000000000000001}, 'trigger': {'precision': 0.5351724137931034, 'recall': 0.5388888888888889, 'f1': 0.5370242214532872}, 'argument': {'precision': 0.3144595226953673, 'recall': 0.2819974821653378, 'f1': 0.29734513274336277}}
60
+ train | epoch 1 | Iter: 158/ 610 | global iter: 80/ 305 | loss: 0.1035 | ds_loss: 0.0000 | lr: 4.6247e-05 | scale: 1.0000 | micro time: 0.280 | step time: 0.507
61
+ train | epoch 1 | Iter: 198/ 610 | global iter: 100/ 305 | loss: 0.0933 | ds_loss: 0.0000 | lr: 4.2703e-05 | scale: 1.0000 | micro time: 0.279 | step time: 0.509
62
+ train | epoch 1 | Iter: 238/ 610 | global iter: 120/ 305 | loss: 0.0916 | ds_loss: 0.0000 | lr: 3.8236e-05 | scale: 1.0000 | micro time: 0.279 | step time: 0.510
63
+ dev | avg_loss: 0.12898137019230768 | {'exact_match': 9.9617, 'rougeL': 68.917, 'trigger_counts': {'tp': 893, 'fp': 606, 'fn': 547}, 'argument_counts': {'tp': 987, 'fp': 1568, 'fn': 1396}, 'trigger_text': {'precision': 0.6450967311541027, 'recall': 0.6715277777777777, 'f1': 0.6580469547465124}, 'trigger': {'precision': 0.5957304869913276, 'recall': 0.6201388888888889, 'f1': 0.6076896903708745}, 'argument': {'precision': 0.3863013698630137, 'recall': 0.41418380193033993, 'f1': 0.3997569866342649}}
64
+ train | epoch 2 | Iter: 278/ 610 | global iter: 140/ 305 | loss: 0.0554 | ds_loss: 0.0000 | lr: 3.3078e-05 | scale: 1.0000 | micro time: 0.278 | step time: 0.508
65
+ train | epoch 2 | Iter: 318/ 610 | global iter: 160/ 305 | loss: 0.0452 | ds_loss: 0.0000 | lr: 2.7499e-05 | scale: 1.0000 | micro time: 0.280 | step time: 0.510
66
+ train | epoch 2 | Iter: 358/ 610 | global iter: 180/ 305 | loss: 0.0446 | ds_loss: 0.0000 | lr: 2.1790e-05 | scale: 1.0000 | micro time: 0.279 | step time: 0.511
67
+ dev | avg_loss: 0.12901893028846154 | {'exact_match': 13.1545, 'rougeL': 69.6698, 'trigger_counts': {'tp': 972, 'fp': 697, 'fn': 468}, 'argument_counts': {'tp': 1126, 'fp': 1691, 'fn': 1257}, 'trigger_text': {'precision': 0.6195326542840024, 'recall': 0.7180555555555556, 'f1': 0.6651656481183661}, 'trigger': {'precision': 0.5823846614739365, 'recall': 0.675, 'f1': 0.6252814409778065}, 'argument': {'precision': 0.3997160099396521, 'recall': 0.4725136382710869, 'f1': 0.4330769230769231}}
68
+ train | epoch 3 | Iter: 398/ 610 | global iter: 200/ 305 | loss: 0.0244 | ds_loss: 0.0000 | lr: 1.6248e-05 | scale: 1.0000 | micro time: 0.277 | step time: 0.509
69
+ train | epoch 3 | Iter: 438/ 610 | global iter: 220/ 305 | loss: 0.0173 | ds_loss: 0.0000 | lr: 1.1163e-05 | scale: 1.0000 | micro time: 0.279 | step time: 0.510
70
+ train | epoch 3 | Iter: 478/ 610 | global iter: 240/ 305 | loss: 0.0182 | ds_loss: 0.0000 | lr: 6.7993e-06 | scale: 1.0000 | micro time: 0.281 | step time: 0.511
71
+ dev | avg_loss: 0.13322566105769232 | {'exact_match': 17.4968, 'rougeL': 73.8592, 'trigger_counts': {'tp': 976, 'fp': 481, 'fn': 464}, 'argument_counts': {'tp': 1202, 'fp': 1208, 'fn': 1181}, 'trigger_text': {'precision': 0.7028140013726836, 'recall': 0.7111111111111111, 'f1': 0.7069382119433898}, 'trigger': {'precision': 0.6698695950583391, 'recall': 0.6777777777777778, 'f1': 0.6738004832585434}, 'argument': {'precision': 0.4987551867219917, 'recall': 0.5044062106588334, 'f1': 0.5015647819737116}}
72
+ train | epoch 4 | Iter: 518/ 610 | global iter: 260/ 305 | loss: 0.0088 | ds_loss: 0.0000 | lr: 3.3852e-06 | scale: 1.0000 | micro time: 0.279 | step time: 0.508
73
+ train | epoch 4 | Iter: 558/ 610 | global iter: 280/ 305 | loss: 0.0044 | ds_loss: 0.0000 | lr: 1.0987e-06 | scale: 1.0000 | micro time: 0.280 | step time: 0.510
74
+ train | epoch 4 | Iter: 598/ 610 | global iter: 300/ 305 | loss: 0.0047 | ds_loss: 0.0000 | lr: 5.8919e-08 | scale: 1.0000 | micro time: 0.281 | step time: 0.511
75
+ dev | avg_loss: 0.1448692908653846 | {'exact_match': 17.1137, 'rougeL': 72.7217, 'trigger_counts': {'tp': 1002, 'fp': 570, 'fn': 438}, 'argument_counts': {'tp': 1236, 'fp': 1429, 'fn': 1147}, 'trigger_text': {'precision': 0.6692111959287532, 'recall': 0.7305555555555555, 'f1': 0.6985391766268261}, 'trigger': {'precision': 0.6374045801526718, 'recall': 0.6958333333333333, 'f1': 0.6653386454183267}, 'argument': {'precision': 0.46378986866791744, 'recall': 0.5186739404112464, 'f1': 0.4896988906497623}}
76
+
77
+
78
+ ============================== EXP at 2026-02-25 12:56:01 ==============================
79
+ dev | avg_loss: 1.4771634615384615 | {'exact_match': 0.0, 'rougeL': 1.0805, 'trigger_counts': {'tp': 0, 'fp': 0, 'fn': 1440}, 'argument_counts': {'tp': 0, 'fp': 0, 'fn': 2383}, 'trigger_text': {'precision': 0, 'recall': 0.0, 'f1': 0}, 'trigger': {'precision': 0, 'recall': 0.0, 'f1': 0}, 'argument': {'precision': 0, 'recall': 0.0, 'f1': 0}}
80
+ train | epoch 0 | Iter: 38/ 610 | global iter: 20/ 305 | loss: 0.8543 | ds_loss: 0.0000 | lr: 3.1148e-05 | scale: 1.0000 | micro time: 0.277 | step time: 0.486
81
+ train | epoch 0 | Iter: 78/ 610 | global iter: 40/ 305 | loss: 0.3717 | ds_loss: 0.0000 | lr: 4.9882e-05 | scale: 1.0000 | micro time: 0.278 | step time: 0.507
82
+ train | epoch 0 | Iter: 118/ 610 | global iter: 60/ 305 | loss: 0.2736 | ds_loss: 0.0000 | lr: 4.8682e-05 | scale: 1.0000 | micro time: 0.279 | step time: 0.508
83
+ dev | avg_loss: 0.2276893028846154 | {'exact_match': 0.7663, 'rougeL': 53.4699, 'trigger_counts': {'tp': 572, 'fp': 746, 'fn': 868}, 'argument_counts': {'tp': 524, 'fp': 1572, 'fn': 1859}, 'trigger_text': {'precision': 0.5703185703185704, 'recall': 0.5097222222222222, 'f1': 0.5383204987165384}, 'trigger': {'precision': 0.4339908952959029, 'recall': 0.3972222222222222, 'f1': 0.41479332849891226}, 'argument': {'precision': 0.25, 'recall': 0.21989089383130508, 'f1': 0.2339807992855548}}
84
+ train | epoch 1 | Iter: 158/ 610 | global iter: 80/ 305 | loss: 0.1862 | ds_loss: 0.0000 | lr: 4.6247e-05 | scale: 1.0000 | micro time: 0.278 | step time: 0.507
85
+ train | epoch 1 | Iter: 198/ 610 | global iter: 100/ 305 | loss: 0.1680 | ds_loss: 0.0000 | lr: 4.2703e-05 | scale: 1.0000 | micro time: 0.278 | step time: 0.508
86
+ train | epoch 1 | Iter: 238/ 610 | global iter: 120/ 305 | loss: 0.1610 | ds_loss: 0.0000 | lr: 3.8236e-05 | scale: 1.0000 | micro time: 0.280 | step time: 0.509
87
+ dev | avg_loss: 0.20808293269230768 | {'exact_match': 1.1494, 'rougeL': 56.7094, 'trigger_counts': {'tp': 763, 'fp': 661, 'fn': 677}, 'argument_counts': {'tp': 703, 'fp': 1497, 'fn': 1680}, 'trigger_text': {'precision': 0.6099290780141844, 'recall': 0.5972222222222222, 'f1': 0.6035087719298247}, 'trigger': {'precision': 0.535814606741573, 'recall': 0.5298611111111111, 'f1': 0.5328212290502793}, 'argument': {'precision': 0.3195454545454545, 'recall': 0.29500629458665545, 'f1': 0.30678594806895043}}
88
+ train | epoch 2 | Iter: 278/ 610 | global iter: 140/ 305 | loss: 0.1174 | ds_loss: 0.0000 | lr: 3.3078e-05 | scale: 1.0000 | micro time: 0.277 | step time: 0.507
89
+ train | epoch 2 | Iter: 318/ 610 | global iter: 160/ 305 | loss: 0.1013 | ds_loss: 0.0000 | lr: 2.7499e-05 | scale: 1.0000 | micro time: 0.280 | step time: 0.508
90
+ train | epoch 2 | Iter: 358/ 610 | global iter: 180/ 305 | loss: 0.0977 | ds_loss: 0.0000 | lr: 2.1790e-05 | scale: 1.0000 | micro time: 0.281 | step time: 0.509
91
+ dev | avg_loss: 0.20094651442307693 | {'exact_match': 1.0217, 'rougeL': 58.4867, 'trigger_counts': {'tp': 879, 'fp': 745, 'fn': 561}, 'argument_counts': {'tp': 924, 'fp': 1700, 'fn': 1459}, 'trigger_text': {'precision': 0.6217391304347826, 'recall': 0.6951388888888889, 'f1': 0.6563934426229507}, 'trigger': {'precision': 0.541256157635468, 'recall': 0.6104166666666667, 'f1': 0.5737597911227155}, 'argument': {'precision': 0.3521341463414634, 'recall': 0.3877465379773395, 'f1': 0.36908328340323543}}
92
+ train | epoch 3 | Iter: 398/ 610 | global iter: 200/ 305 | loss: 0.0761 | ds_loss: 0.0000 | lr: 1.6248e-05 | scale: 1.0000 | micro time: 0.278 | step time: 0.507
93
+ train | epoch 3 | Iter: 438/ 610 | global iter: 220/ 305 | loss: 0.0644 | ds_loss: 0.0000 | lr: 1.1163e-05 | scale: 1.0000 | micro time: 0.278 | step time: 0.507
94
+ train | epoch 3 | Iter: 478/ 610 | global iter: 240/ 305 | loss: 0.0633 | ds_loss: 0.0000 | lr: 6.7993e-06 | scale: 1.0000 | micro time: 0.279 | step time: 0.509
95
+ dev | avg_loss: 0.21138822115384615 | {'exact_match': 2.2989, 'rougeL': 61.1661, 'trigger_counts': {'tp': 916, 'fp': 549, 'fn': 524}, 'argument_counts': {'tp': 1070, 'fp': 1410, 'fn': 1313}, 'trigger_text': {'precision': 0.6814764183185236, 'recall': 0.6923611111111111, 'f1': 0.6868756458835686}, 'trigger': {'precision': 0.6252559726962458, 'recall': 0.6361111111111111, 'f1': 0.6306368330464716}, 'argument': {'precision': 0.4314516129032258, 'recall': 0.44901384809064204, 'f1': 0.4400575776269792}}
96
+ train | epoch 4 | Iter: 518/ 610 | global iter: 260/ 305 | loss: 0.0491 | ds_loss: 0.0000 | lr: 3.3852e-06 | scale: 1.0000 | micro time: 0.277 | step time: 0.507
97
+ train | epoch 4 | Iter: 558/ 610 | global iter: 280/ 305 | loss: 0.0444 | ds_loss: 0.0000 | lr: 1.0987e-06 | scale: 1.0000 | micro time: 0.277 | step time: 0.507
98
+ train | epoch 4 | Iter: 598/ 610 | global iter: 300/ 305 | loss: 0.0445 | ds_loss: 0.0000 | lr: 5.8919e-08 | scale: 1.0000 | micro time: 0.279 | step time: 0.508
99
+ dev | avg_loss: 0.22513521634615385 | {'exact_match': 2.682, 'rougeL': 60.7811, 'trigger_counts': {'tp': 935, 'fp': 636, 'fn': 505}, 'argument_counts': {'tp': 1062, 'fp': 1636, 'fn': 1321}, 'trigger_text': {'precision': 0.6539196940726577, 'recall': 0.7125, 'f1': 0.6819541375872383}, 'trigger': {'precision': 0.5951623169955442, 'recall': 0.6493055555555556, 'f1': 0.6210561275323813}, 'argument': {'precision': 0.3936249073387695, 'recall': 0.44565673520772137, 'f1': 0.4180279472544775}}
100
+
101
+
102
+ ============================== EXP at 2026-02-26 05:56:52 ==============================
103
+
104
+
105
+ ============================== EXP at 2026-02-26 07:50:27 ==============================
106
+ dev | avg_loss: 1.1484375 | {'exact_match': 0.0, 'rougeL': 1.001, 'trigger_counts': {'tp': 0, 'fp': 0, 'fn': 1440}, 'argument_counts': {'tp': 0, 'fp': 0, 'fn': 2433}, 'trigger_text': {'precision': 0, 'recall': 0.0, 'f1': 0}, 'trigger': {'precision': 0, 'recall': 0.0, 'f1': 0}, 'argument': {'precision': 0, 'recall': 0.0, 'f1': 0}}
107
+ train | epoch 0 | Iter: 38/ 610 | global iter: 20/ 305 | loss: 0.6251 | ds_loss: 0.0000 | lr: 3.1148e-05 | scale: 1.0000 | micro time: 0.279 | step time: 0.486
108
+ train | epoch 0 | Iter: 78/ 610 | global iter: 40/ 305 | loss: 0.2767 | ds_loss: 0.0000 | lr: 4.9882e-05 | scale: 1.0000 | micro time: 0.280 | step time: 0.509
109
+ train | epoch 0 | Iter: 118/ 610 | global iter: 60/ 305 | loss: 0.2195 | ds_loss: 0.0000 | lr: 4.8682e-05 | scale: 1.0000 | micro time: 0.279 | step time: 0.509
110
+ dev | avg_loss: 0.21033653846153846 | {'exact_match': 5.1086, 'rougeL': 62.8964, 'trigger_counts': {'tp': 678, 'fp': 483, 'fn': 762}, 'argument_counts': {'tp': 331, 'fp': 1047, 'fn': 2102}, 'trigger_text': {'precision': 0.6416881998277347, 'recall': 0.5173611111111112, 'f1': 0.5728565936178394}, 'trigger': {'precision': 0.5839793281653747, 'recall': 0.4708333333333333, 'f1': 0.5213379469434833}, 'argument': {'precision': 0.24020319303338172, 'recall': 0.13604603370324703, 'f1': 0.17370768827079508}}
111
+ train | epoch 1 | Iter: 158/ 610 | global iter: 80/ 305 | loss: 0.1419 | ds_loss: 0.0000 | lr: 4.6247e-05 | scale: 1.0000 | micro time: 0.278 | step time: 0.510
112
+ train | epoch 1 | Iter: 198/ 610 | global iter: 100/ 305 | loss: 0.1252 | ds_loss: 0.0000 | lr: 4.2703e-05 | scale: 1.0000 | micro time: 0.279 | step time: 0.509
113
+ train | epoch 1 | Iter: 238/ 610 | global iter: 120/ 305 | loss: 0.1247 | ds_loss: 0.0000 | lr: 3.8236e-05 | scale: 1.0000 | micro time: 0.279 | step time: 0.510
114
+ dev | avg_loss: 0.19230769230769232 | {'exact_match': 6.3857, 'rougeL': 66.8909, 'trigger_counts': {'tp': 808, 'fp': 513, 'fn': 632}, 'argument_counts': {'tp': 462, 'fp': 1706, 'fn': 1971}, 'trigger_text': {'precision': 0.6563209689629069, 'recall': 0.6020833333333333, 'f1': 0.628033321260413}, 'trigger': {'precision': 0.6116578349735049, 'recall': 0.5611111111111111, 'f1': 0.5852951829047446}, 'argument': {'precision': 0.21309963099630996, 'recall': 0.18988902589395806, 'f1': 0.2008259074114323}}
115
+ train | epoch 2 | Iter: 278/ 610 | global iter: 140/ 305 | loss: 0.0787 | ds_loss: 0.0000 | lr: 3.3078e-05 | scale: 1.0000 | micro time: 0.278 | step time: 0.508
116
+ train | epoch 2 | Iter: 318/ 610 | global iter: 160/ 305 | loss: 0.0642 | ds_loss: 0.0000 | lr: 2.7499e-05 | scale: 1.0000 | micro time: 0.279 | step time: 0.508
117
+ train | epoch 2 | Iter: 358/ 610 | global iter: 180/ 305 | loss: 0.0650 | ds_loss: 0.0000 | lr: 2.1790e-05 | scale: 1.0000 | micro time: 0.279 | step time: 0.510
118
+ dev | avg_loss: 0.19974459134615385 | {'exact_match': 6.3857, 'rougeL': 68.7581, 'trigger_counts': {'tp': 939, 'fp': 626, 'fn': 501}, 'argument_counts': {'tp': 557, 'fp': 2018, 'fn': 1876}, 'trigger_text': {'precision': 0.6345047923322684, 'recall': 0.6895833333333333, 'f1': 0.6608985024958404}, 'trigger': {'precision': 0.6, 'recall': 0.6520833333333333, 'f1': 0.6249584026622297}, 'argument': {'precision': 0.21631067961165049, 'recall': 0.22893547061241265, 'f1': 0.22244408945686903}}
119
+ train | epoch 3 | Iter: 398/ 610 | global iter: 200/ 305 | loss: 0.0387 | ds_loss: 0.0000 | lr: 1.6248e-05 | scale: 1.0000 | micro time: 0.279 | step time: 0.508
120
+ train | epoch 3 | Iter: 438/ 610 | global iter: 220/ 305 | loss: 0.0247 | ds_loss: 0.0000 | lr: 1.1163e-05 | scale: 1.0000 | micro time: 0.279 | step time: 0.509
121
+ train | epoch 3 | Iter: 478/ 610 | global iter: 240/ 305 | loss: 0.0244 | ds_loss: 0.0000 | lr: 6.7993e-06 | scale: 1.0000 | micro time: 0.280 | step time: 0.510
122
+ dev | avg_loss: 0.2215294471153846 | {'exact_match': 7.152, 'rougeL': 69.1322, 'trigger_counts': {'tp': 1007, 'fp': 613, 'fn': 433}, 'argument_counts': {'tp': 624, 'fp': 1991, 'fn': 1809}, 'trigger_text': {'precision': 0.6555555555555556, 'recall': 0.7375, 'f1': 0.6941176470588235}, 'trigger': {'precision': 0.6216049382716049, 'recall': 0.6993055555555555, 'f1': 0.6581699346405228}, 'argument': {'precision': 0.23862332695984703, 'recall': 0.2564734895191122, 'f1': 0.24722662440570523}}
123
+ train | epoch 4 | Iter: 518/ 610 | global iter: 260/ 305 | loss: 0.0120 | ds_loss: 0.0000 | lr: 3.3852e-06 | scale: 1.0000 | micro time: 0.277 | step time: 0.513
124
+ train | epoch 4 | Iter: 558/ 610 | global iter: 280/ 305 | loss: 0.0065 | ds_loss: 0.0000 | lr: 1.0987e-06 | scale: 1.0000 | micro time: 0.280 | step time: 0.509
125
+ train | epoch 4 | Iter: 598/ 610 | global iter: 300/ 305 | loss: 0.0060 | ds_loss: 0.0000 | lr: 5.8919e-08 | scale: 1.0000 | micro time: 0.279 | step time: 0.510
126
+ dev | avg_loss: 0.24406550480769232 | {'exact_match': 8.1737, 'rougeL': 69.4812, 'trigger_counts': {'tp': 1004, 'fp': 635, 'fn': 436}, 'argument_counts': {'tp': 644, 'fp': 2093, 'fn': 1789}, 'trigger_text': {'precision': 0.6516168395363027, 'recall': 0.7416666666666667, 'f1': 0.6937317310815201}, 'trigger': {'precision': 0.612568639414277, 'recall': 0.6972222222222222, 'f1': 0.6521597921403053}, 'argument': {'precision': 0.23529411764705882, 'recall': 0.26469379367036583, 'f1': 0.2491295938104449}}
qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/1642/README.md ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-0.5B
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:Qwen/Qwen2.5-0.5B
7
+ - lora
8
+ - transformers
9
+ ---
10
+
11
+ # Model Card for Model ID
12
+
13
+ <!-- Provide a quick summary of what the model is/does. -->
14
+
15
+
16
+
17
+ ## Model Details
18
+
19
+ ### Model Description
20
+
21
+ <!-- Provide a longer summary of what this model is. -->
22
+
23
+
24
+
25
+ - **Developed by:** [More Information Needed]
26
+ - **Funded by [optional]:** [More Information Needed]
27
+ - **Shared by [optional]:** [More Information Needed]
28
+ - **Model type:** [More Information Needed]
29
+ - **Language(s) (NLP):** [More Information Needed]
30
+ - **License:** [More Information Needed]
31
+ - **Finetuned from model [optional]:** [More Information Needed]
32
+
33
+ ### Model Sources [optional]
34
+
35
+ <!-- Provide the basic links for the model. -->
36
+
37
+ - **Repository:** [More Information Needed]
38
+ - **Paper [optional]:** [More Information Needed]
39
+ - **Demo [optional]:** [More Information Needed]
40
+
41
+ ## Uses
42
+
43
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
44
+
45
+ ### Direct Use
46
+
47
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
48
+
49
+ [More Information Needed]
50
+
51
+ ### Downstream Use [optional]
52
+
53
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
54
+
55
+ [More Information Needed]
56
+
57
+ ### Out-of-Scope Use
58
+
59
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
60
+
61
+ [More Information Needed]
62
+
63
+ ## Bias, Risks, and Limitations
64
+
65
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
66
+
67
+ [More Information Needed]
68
+
69
+ ### Recommendations
70
+
71
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
72
+
73
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
74
+
75
+ ## How to Get Started with the Model
76
+
77
+ Use the code below to get started with the model.
78
+
79
+ [More Information Needed]
80
+
81
+ ## Training Details
82
+
83
+ ### Training Data
84
+
85
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
86
+
87
+ [More Information Needed]
88
+
89
+ ### Training Procedure
90
+
91
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
92
+
93
+ #### Preprocessing [optional]
94
+
95
+ [More Information Needed]
96
+
97
+
98
+ #### Training Hyperparameters
99
+
100
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
101
+
102
+ #### Speeds, Sizes, Times [optional]
103
+
104
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
105
+
106
+ [More Information Needed]
107
+
108
+ ## Evaluation
109
+
110
+ <!-- This section describes the evaluation protocols and provides the results. -->
111
+
112
+ ### Testing Data, Factors & Metrics
113
+
114
+ #### Testing Data
115
+
116
+ <!-- This should link to a Dataset Card if possible. -->
117
+
118
+ [More Information Needed]
119
+
120
+ #### Factors
121
+
122
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
123
+
124
+ [More Information Needed]
125
+
126
+ #### Metrics
127
+
128
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
129
+
130
+ [More Information Needed]
131
+
132
+ ### Results
133
+
134
+ [More Information Needed]
135
+
136
+ #### Summary
137
+
138
+
139
+
140
+ ## Model Examination [optional]
141
+
142
+ <!-- Relevant interpretability work for the model goes here -->
143
+
144
+ [More Information Needed]
145
+
146
+ ## Environmental Impact
147
+
148
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
149
+
150
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
151
+
152
+ - **Hardware Type:** [More Information Needed]
153
+ - **Hours used:** [More Information Needed]
154
+ - **Cloud Provider:** [More Information Needed]
155
+ - **Compute Region:** [More Information Needed]
156
+ - **Carbon Emitted:** [More Information Needed]
157
+
158
+ ## Technical Specifications [optional]
159
+
160
+ ### Model Architecture and Objective
161
+
162
+ [More Information Needed]
163
+
164
+ ### Compute Infrastructure
165
+
166
+ [More Information Needed]
167
+
168
+ #### Hardware
169
+
170
+ [More Information Needed]
171
+
172
+ #### Software
173
+
174
+ [More Information Needed]
175
+
176
+ ## Citation [optional]
177
+
178
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
179
+
180
+ **BibTeX:**
181
+
182
+ [More Information Needed]
183
+
184
+ **APA:**
185
+
186
+ [More Information Needed]
187
+
188
+ ## Glossary [optional]
189
+
190
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
191
+
192
+ [More Information Needed]
193
+
194
+ ## More Information [optional]
195
+
196
+ [More Information Needed]
197
+
198
+ ## Model Card Authors [optional]
199
+
200
+ [More Information Needed]
201
+
202
+ ## Model Card Contact
203
+
204
+ [More Information Needed]
205
+ ### Framework versions
206
+
207
+ - PEFT 0.18.1
qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/1642/adapter_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen2.5-0.5B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 128,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.05,
22
+ "megatron_config": null,
23
+ "megatron_core": "megatron.core",
24
+ "modules_to_save": null,
25
+ "peft_type": "LORA",
26
+ "peft_version": "0.18.1",
27
+ "qalora_group_size": 16,
28
+ "r": 128,
29
+ "rank_pattern": {},
30
+ "revision": null,
31
+ "target_modules": [
32
+ "v_proj",
33
+ "down_proj",
34
+ "up_proj",
35
+ "gate_proj",
36
+ "q_proj",
37
+ "k_proj",
38
+ "o_proj"
39
+ ],
40
+ "target_parameters": null,
41
+ "task_type": "CAUSAL_LM",
42
+ "trainable_token_indices": null,
43
+ "use_dora": false,
44
+ "use_qalora": false,
45
+ "use_rslora": false
46
+ }
qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/1642/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ee488bda285b71c96302b7f7da1d638bf1f69f2bcab72ba1b46e41e7b90dbf1
3
+ size 140824634
qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/1642/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/1642/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/1642/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/1642/special_tokens_map.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": "<|im_end|>",
18
+ "pad_token": "<|im_end|>"
19
+ }
qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/1642/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/1642/tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|im_end|>",
204
+ "padding_side": "right",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/1642/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/2463/README.md ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-0.5B
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:Qwen/Qwen2.5-0.5B
7
+ - lora
8
+ - transformers
9
+ ---
10
+
11
+ # Model Card for Model ID
12
+
13
+ <!-- Provide a quick summary of what the model is/does. -->
14
+
15
+
16
+
17
+ ## Model Details
18
+
19
+ ### Model Description
20
+
21
+ <!-- Provide a longer summary of what this model is. -->
22
+
23
+
24
+
25
+ - **Developed by:** [More Information Needed]
26
+ - **Funded by [optional]:** [More Information Needed]
27
+ - **Shared by [optional]:** [More Information Needed]
28
+ - **Model type:** [More Information Needed]
29
+ - **Language(s) (NLP):** [More Information Needed]
30
+ - **License:** [More Information Needed]
31
+ - **Finetuned from model [optional]:** [More Information Needed]
32
+
33
+ ### Model Sources [optional]
34
+
35
+ <!-- Provide the basic links for the model. -->
36
+
37
+ - **Repository:** [More Information Needed]
38
+ - **Paper [optional]:** [More Information Needed]
39
+ - **Demo [optional]:** [More Information Needed]
40
+
41
+ ## Uses
42
+
43
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
44
+
45
+ ### Direct Use
46
+
47
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
48
+
49
+ [More Information Needed]
50
+
51
+ ### Downstream Use [optional]
52
+
53
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
54
+
55
+ [More Information Needed]
56
+
57
+ ### Out-of-Scope Use
58
+
59
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
60
+
61
+ [More Information Needed]
62
+
63
+ ## Bias, Risks, and Limitations
64
+
65
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
66
+
67
+ [More Information Needed]
68
+
69
+ ### Recommendations
70
+
71
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
72
+
73
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
74
+
75
+ ## How to Get Started with the Model
76
+
77
+ Use the code below to get started with the model.
78
+
79
+ [More Information Needed]
80
+
81
+ ## Training Details
82
+
83
+ ### Training Data
84
+
85
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
86
+
87
+ [More Information Needed]
88
+
89
+ ### Training Procedure
90
+
91
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
92
+
93
+ #### Preprocessing [optional]
94
+
95
+ [More Information Needed]
96
+
97
+
98
+ #### Training Hyperparameters
99
+
100
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
101
+
102
+ #### Speeds, Sizes, Times [optional]
103
+
104
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
105
+
106
+ [More Information Needed]
107
+
108
+ ## Evaluation
109
+
110
+ <!-- This section describes the evaluation protocols and provides the results. -->
111
+
112
+ ### Testing Data, Factors & Metrics
113
+
114
+ #### Testing Data
115
+
116
+ <!-- This should link to a Dataset Card if possible. -->
117
+
118
+ [More Information Needed]
119
+
120
+ #### Factors
121
+
122
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
123
+
124
+ [More Information Needed]
125
+
126
+ #### Metrics
127
+
128
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
129
+
130
+ [More Information Needed]
131
+
132
+ ### Results
133
+
134
+ [More Information Needed]
135
+
136
+ #### Summary
137
+
138
+
139
+
140
+ ## Model Examination [optional]
141
+
142
+ <!-- Relevant interpretability work for the model goes here -->
143
+
144
+ [More Information Needed]
145
+
146
+ ## Environmental Impact
147
+
148
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
149
+
150
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
151
+
152
+ - **Hardware Type:** [More Information Needed]
153
+ - **Hours used:** [More Information Needed]
154
+ - **Cloud Provider:** [More Information Needed]
155
+ - **Compute Region:** [More Information Needed]
156
+ - **Carbon Emitted:** [More Information Needed]
157
+
158
+ ## Technical Specifications [optional]
159
+
160
+ ### Model Architecture and Objective
161
+
162
+ [More Information Needed]
163
+
164
+ ### Compute Infrastructure
165
+
166
+ [More Information Needed]
167
+
168
+ #### Hardware
169
+
170
+ [More Information Needed]
171
+
172
+ #### Software
173
+
174
+ [More Information Needed]
175
+
176
+ ## Citation [optional]
177
+
178
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
179
+
180
+ **BibTeX:**
181
+
182
+ [More Information Needed]
183
+
184
+ **APA:**
185
+
186
+ [More Information Needed]
187
+
188
+ ## Glossary [optional]
189
+
190
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
191
+
192
+ [More Information Needed]
193
+
194
+ ## More Information [optional]
195
+
196
+ [More Information Needed]
197
+
198
+ ## Model Card Authors [optional]
199
+
200
+ [More Information Needed]
201
+
202
+ ## Model Card Contact
203
+
204
+ [More Information Needed]
205
+ ### Framework versions
206
+
207
+ - PEFT 0.18.1
qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/2463/adapter_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen2.5-0.5B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 128,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.05,
22
+ "megatron_config": null,
23
+ "megatron_core": "megatron.core",
24
+ "modules_to_save": null,
25
+ "peft_type": "LORA",
26
+ "peft_version": "0.18.1",
27
+ "qalora_group_size": 16,
28
+ "r": 128,
29
+ "rank_pattern": {},
30
+ "revision": null,
31
+ "target_modules": [
32
+ "up_proj",
33
+ "down_proj",
34
+ "v_proj",
35
+ "gate_proj",
36
+ "k_proj",
37
+ "o_proj",
38
+ "q_proj"
39
+ ],
40
+ "target_parameters": null,
41
+ "task_type": "CAUSAL_LM",
42
+ "trainable_token_indices": null,
43
+ "use_dora": false,
44
+ "use_qalora": false,
45
+ "use_rslora": false
46
+ }
qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/2463/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dce45959c4ed8f30ba5c4499045b54a27672ba15461ac28411711b8a2e37c26
3
+ size 140824634
qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/2463/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/2463/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/2463/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/2463/special_tokens_map.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": "<|im_end|>",
18
+ "pad_token": "<|im_end|>"
19
+ }
qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/2463/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/2463/tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|im_end|>",
204
+ "padding_side": "right",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/2463/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/3284/README.md ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-0.5B
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:Qwen/Qwen2.5-0.5B
7
+ - lora
8
+ - transformers
9
+ ---
10
+
11
+ # Model Card for Model ID
12
+
13
+ <!-- Provide a quick summary of what the model is/does. -->
14
+
15
+
16
+
17
+ ## Model Details
18
+
19
+ ### Model Description
20
+
21
+ <!-- Provide a longer summary of what this model is. -->
22
+
23
+
24
+
25
+ - **Developed by:** [More Information Needed]
26
+ - **Funded by [optional]:** [More Information Needed]
27
+ - **Shared by [optional]:** [More Information Needed]
28
+ - **Model type:** [More Information Needed]
29
+ - **Language(s) (NLP):** [More Information Needed]
30
+ - **License:** [More Information Needed]
31
+ - **Finetuned from model [optional]:** [More Information Needed]
32
+
33
+ ### Model Sources [optional]
34
+
35
+ <!-- Provide the basic links for the model. -->
36
+
37
+ - **Repository:** [More Information Needed]
38
+ - **Paper [optional]:** [More Information Needed]
39
+ - **Demo [optional]:** [More Information Needed]
40
+
41
+ ## Uses
42
+
43
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
44
+
45
+ ### Direct Use
46
+
47
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
48
+
49
+ [More Information Needed]
50
+
51
+ ### Downstream Use [optional]
52
+
53
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
54
+
55
+ [More Information Needed]
56
+
57
+ ### Out-of-Scope Use
58
+
59
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
60
+
61
+ [More Information Needed]
62
+
63
+ ## Bias, Risks, and Limitations
64
+
65
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
66
+
67
+ [More Information Needed]
68
+
69
+ ### Recommendations
70
+
71
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
72
+
73
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
74
+
75
+ ## How to Get Started with the Model
76
+
77
+ Use the code below to get started with the model.
78
+
79
+ [More Information Needed]
80
+
81
+ ## Training Details
82
+
83
+ ### Training Data
84
+
85
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
86
+
87
+ [More Information Needed]
88
+
89
+ ### Training Procedure
90
+
91
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
92
+
93
+ #### Preprocessing [optional]
94
+
95
+ [More Information Needed]
96
+
97
+
98
+ #### Training Hyperparameters
99
+
100
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
101
+
102
+ #### Speeds, Sizes, Times [optional]
103
+
104
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
105
+
106
+ [More Information Needed]
107
+
108
+ ## Evaluation
109
+
110
+ <!-- This section describes the evaluation protocols and provides the results. -->
111
+
112
+ ### Testing Data, Factors & Metrics
113
+
114
+ #### Testing Data
115
+
116
+ <!-- This should link to a Dataset Card if possible. -->
117
+
118
+ [More Information Needed]
119
+
120
+ #### Factors
121
+
122
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
123
+
124
+ [More Information Needed]
125
+
126
+ #### Metrics
127
+
128
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
129
+
130
+ [More Information Needed]
131
+
132
+ ### Results
133
+
134
+ [More Information Needed]
135
+
136
+ #### Summary
137
+
138
+
139
+
140
+ ## Model Examination [optional]
141
+
142
+ <!-- Relevant interpretability work for the model goes here -->
143
+
144
+ [More Information Needed]
145
+
146
+ ## Environmental Impact
147
+
148
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
149
+
150
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
151
+
152
+ - **Hardware Type:** [More Information Needed]
153
+ - **Hours used:** [More Information Needed]
154
+ - **Cloud Provider:** [More Information Needed]
155
+ - **Compute Region:** [More Information Needed]
156
+ - **Carbon Emitted:** [More Information Needed]
157
+
158
+ ## Technical Specifications [optional]
159
+
160
+ ### Model Architecture and Objective
161
+
162
+ [More Information Needed]
163
+
164
+ ### Compute Infrastructure
165
+
166
+ [More Information Needed]
167
+
168
+ #### Hardware
169
+
170
+ [More Information Needed]
171
+
172
+ #### Software
173
+
174
+ [More Information Needed]
175
+
176
+ ## Citation [optional]
177
+
178
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
179
+
180
+ **BibTeX:**
181
+
182
+ [More Information Needed]
183
+
184
+ **APA:**
185
+
186
+ [More Information Needed]
187
+
188
+ ## Glossary [optional]
189
+
190
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
191
+
192
+ [More Information Needed]
193
+
194
+ ## More Information [optional]
195
+
196
+ [More Information Needed]
197
+
198
+ ## Model Card Authors [optional]
199
+
200
+ [More Information Needed]
201
+
202
+ ## Model Card Contact
203
+
204
+ [More Information Needed]
205
+ ### Framework versions
206
+
207
+ - PEFT 0.18.1
qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/3284/adapter_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen2.5-0.5B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 128,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.05,
22
+ "megatron_config": null,
23
+ "megatron_core": "megatron.core",
24
+ "modules_to_save": null,
25
+ "peft_type": "LORA",
26
+ "peft_version": "0.18.1",
27
+ "qalora_group_size": 16,
28
+ "r": 128,
29
+ "rank_pattern": {},
30
+ "revision": null,
31
+ "target_modules": [
32
+ "up_proj",
33
+ "down_proj",
34
+ "v_proj",
35
+ "gate_proj",
36
+ "k_proj",
37
+ "o_proj",
38
+ "q_proj"
39
+ ],
40
+ "target_parameters": null,
41
+ "task_type": "CAUSAL_LM",
42
+ "trainable_token_indices": null,
43
+ "use_dora": false,
44
+ "use_qalora": false,
45
+ "use_rslora": false
46
+ }
qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/3284/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1bc06d3e9bb434db5f294e77c1defdc582437a38c100734f58007375a252af5
3
+ size 140824634
qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/3284/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/3284/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/3284/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/3284/special_tokens_map.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": "<|im_end|>",
18
+ "pad_token": "<|im_end|>"
19
+ }
qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/3284/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/3284/tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|im_end|>",
204
+ "padding_side": "right",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/3284/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/4105/README.md ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-0.5B
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:Qwen/Qwen2.5-0.5B
7
+ - lora
8
+ - transformers
9
+ ---
10
+
11
+ # Model Card for Model ID
12
+
13
+ <!-- Provide a quick summary of what the model is/does. -->
14
+
15
+
16
+
17
+ ## Model Details
18
+
19
+ ### Model Description
20
+
21
+ <!-- Provide a longer summary of what this model is. -->
22
+
23
+
24
+
25
+ - **Developed by:** [More Information Needed]
26
+ - **Funded by [optional]:** [More Information Needed]
27
+ - **Shared by [optional]:** [More Information Needed]
28
+ - **Model type:** [More Information Needed]
29
+ - **Language(s) (NLP):** [More Information Needed]
30
+ - **License:** [More Information Needed]
31
+ - **Finetuned from model [optional]:** [More Information Needed]
32
+
33
+ ### Model Sources [optional]
34
+
35
+ <!-- Provide the basic links for the model. -->
36
+
37
+ - **Repository:** [More Information Needed]
38
+ - **Paper [optional]:** [More Information Needed]
39
+ - **Demo [optional]:** [More Information Needed]
40
+
41
+ ## Uses
42
+
43
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
44
+
45
+ ### Direct Use
46
+
47
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
48
+
49
+ [More Information Needed]
50
+
51
+ ### Downstream Use [optional]
52
+
53
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
54
+
55
+ [More Information Needed]
56
+
57
+ ### Out-of-Scope Use
58
+
59
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
60
+
61
+ [More Information Needed]
62
+
63
+ ## Bias, Risks, and Limitations
64
+
65
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
66
+
67
+ [More Information Needed]
68
+
69
+ ### Recommendations
70
+
71
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
72
+
73
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
74
+
75
+ ## How to Get Started with the Model
76
+
77
+ Use the code below to get started with the model.
78
+
79
+ [More Information Needed]
80
+
81
+ ## Training Details
82
+
83
+ ### Training Data
84
+
85
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
86
+
87
+ [More Information Needed]
88
+
89
+ ### Training Procedure
90
+
91
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
92
+
93
+ #### Preprocessing [optional]
94
+
95
+ [More Information Needed]
96
+
97
+
98
+ #### Training Hyperparameters
99
+
100
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
101
+
102
+ #### Speeds, Sizes, Times [optional]
103
+
104
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
105
+
106
+ [More Information Needed]
107
+
108
+ ## Evaluation
109
+
110
+ <!-- This section describes the evaluation protocols and provides the results. -->
111
+
112
+ ### Testing Data, Factors & Metrics
113
+
114
+ #### Testing Data
115
+
116
+ <!-- This should link to a Dataset Card if possible. -->
117
+
118
+ [More Information Needed]
119
+
120
+ #### Factors
121
+
122
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
123
+
124
+ [More Information Needed]
125
+
126
+ #### Metrics
127
+
128
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
129
+
130
+ [More Information Needed]
131
+
132
+ ### Results
133
+
134
+ [More Information Needed]
135
+
136
+ #### Summary
137
+
138
+
139
+
140
+ ## Model Examination [optional]
141
+
142
+ <!-- Relevant interpretability work for the model goes here -->
143
+
144
+ [More Information Needed]
145
+
146
+ ## Environmental Impact
147
+
148
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
149
+
150
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
151
+
152
+ - **Hardware Type:** [More Information Needed]
153
+ - **Hours used:** [More Information Needed]
154
+ - **Cloud Provider:** [More Information Needed]
155
+ - **Compute Region:** [More Information Needed]
156
+ - **Carbon Emitted:** [More Information Needed]
157
+
158
+ ## Technical Specifications [optional]
159
+
160
+ ### Model Architecture and Objective
161
+
162
+ [More Information Needed]
163
+
164
+ ### Compute Infrastructure
165
+
166
+ [More Information Needed]
167
+
168
+ #### Hardware
169
+
170
+ [More Information Needed]
171
+
172
+ #### Software
173
+
174
+ [More Information Needed]
175
+
176
+ ## Citation [optional]
177
+
178
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
179
+
180
+ **BibTeX:**
181
+
182
+ [More Information Needed]
183
+
184
+ **APA:**
185
+
186
+ [More Information Needed]
187
+
188
+ ## Glossary [optional]
189
+
190
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
191
+
192
+ [More Information Needed]
193
+
194
+ ## More Information [optional]
195
+
196
+ [More Information Needed]
197
+
198
+ ## Model Card Authors [optional]
199
+
200
+ [More Information Needed]
201
+
202
+ ## Model Card Contact
203
+
204
+ [More Information Needed]
205
+ ### Framework versions
206
+
207
+ - PEFT 0.18.1
qwen2.5/sft_0.5B_maven/e5-bs8-lr0.0002-G2-N2-NN1-lora-128-128-0.05/4105/adapter_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen2.5-0.5B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 128,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.05,
22
+ "megatron_config": null,
23
+ "megatron_core": "megatron.core",
24
+ "modules_to_save": null,
25
+ "peft_type": "LORA",
26
+ "peft_version": "0.18.1",
27
+ "qalora_group_size": 16,
28
+ "r": 128,
29
+ "rank_pattern": {},
30
+ "revision": null,
31
+ "target_modules": [
32
+ "up_proj",
33
+ "down_proj",
34
+ "v_proj",
35
+ "gate_proj",
36
+ "k_proj",
37
+ "o_proj",
38
+ "q_proj"
39
+ ],
40
+ "target_parameters": null,
41
+ "task_type": "CAUSAL_LM",
42
+ "trainable_token_indices": null,
43
+ "use_dora": false,
44
+ "use_qalora": false,
45
+ "use_rslora": false
46
+ }