Hugging Face's logo

tyzhu
/
lmind_hotpot_train8000_eval7405_v1_doc_qa_Qwen_Qwen1.5-4B_lora2

PEFT
Safetensors
Generated from Trainer
Eval Results
Model card Files Community
tyzhu commited on
Commit
daf0df1
·
verified ·
1 Parent(s): bfa0dae

Model save

Browse files
Files changed (1) hide show
  1. README.md +14 -26
README.md CHANGED
@@ -3,23 +3,11 @@ license: other
3
  base_model: Qwen/Qwen1.5-4B
4
  tags:
5
  - generated_from_trainer
6
- datasets:
7
- - tyzhu/lmind_hotpot_train8000_eval7405_v1_doc_qa
8
  metrics:
9
  - accuracy
10
  model-index:
11
  - name: lmind_hotpot_train8000_eval7405_v1_doc_qa_Qwen_Qwen1.5-4B_lora2
12
- results:
13
- - task:
14
- name: Causal Language Modeling
15
- type: text-generation
16
- dataset:
17
- name: tyzhu/lmind_hotpot_train8000_eval7405_v1_doc_qa
18
- type: tyzhu/lmind_hotpot_train8000_eval7405_v1_doc_qa
19
- metrics:
20
- - name: Accuracy
21
- type: accuracy
22
- value: 0.5088571428571429
23
  library_name: peft
24
  ---
25
 
@@ -28,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
28
 
29
  # lmind_hotpot_train8000_eval7405_v1_doc_qa_Qwen_Qwen1.5-4B_lora2
30
 
31
- This model is a fine-tuned version of [Qwen/Qwen1.5-4B](https://huggingface.co/Qwen/Qwen1.5-4B) on the tyzhu/lmind_hotpot_train8000_eval7405_v1_doc_qa dataset.
32
  It achieves the following results on the evaluation set:
33
- - Loss: 3.6292
34
- - Accuracy: 0.5089
35
 
36
  ## Model description
37
 
@@ -78,16 +66,16 @@ The following hyperparameters were used during training:
78
  | 0.919 | 8.0 | 8714 | 0.5077 | 3.1141 |
79
  | 0.833 | 8.9998 | 9803 | 0.5084 | 3.1755 |
80
  | 0.7635 | 9.9977 | 10890 | 0.5085 | 3.3117 |
81
- | 0.6899 | 10.9998 | 11979 | 3.3183 | 0.5075 |
82
- | 0.6435 | 11.9995 | 13068 | 3.3756 | 0.5103 |
83
- | 0.6043 | 12.9993 | 14157 | 3.3887 | 0.5099 |
84
- | 0.5504 | 14.0 | 15247 | 3.4403 | 0.5091 |
85
- | 0.5091 | 14.9998 | 16336 | 3.4731 | 0.5091 |
86
- | 0.4794 | 15.9995 | 17425 | 3.5180 | 0.5089 |
87
- | 0.4553 | 16.9993 | 18514 | 3.5552 | 0.5088 |
88
- | 0.4275 | 18.0 | 19604 | 3.6266 | 0.5086 |
89
- | 0.4086 | 18.9998 | 20693 | 3.6208 | 0.5073 |
90
- | 0.3824 | 19.9977 | 21780 | 3.6292 | 0.5089 |
91
 
92
 
93
  ### Framework versions
 
3
  base_model: Qwen/Qwen1.5-4B
4
  tags:
5
  - generated_from_trainer
 
 
6
  metrics:
7
  - accuracy
8
  model-index:
9
  - name: lmind_hotpot_train8000_eval7405_v1_doc_qa_Qwen_Qwen1.5-4B_lora2
10
+ results: []
 
 
 
 
 
 
 
 
 
 
11
  library_name: peft
12
  ---
13
 
 
16
 
17
  # lmind_hotpot_train8000_eval7405_v1_doc_qa_Qwen_Qwen1.5-4B_lora2
18
 
19
+ This model is a fine-tuned version of [Qwen/Qwen1.5-4B](https://huggingface.co/Qwen/Qwen1.5-4B) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 3.6298
22
+ - Accuracy: 0.5108
23
 
24
  ## Model description
25
 
 
66
  | 0.919 | 8.0 | 8714 | 0.5077 | 3.1141 |
67
  | 0.833 | 8.9998 | 9803 | 0.5084 | 3.1755 |
68
  | 0.7635 | 9.9977 | 10890 | 0.5085 | 3.3117 |
69
+ | 0.6899 | 10.9998 | 11979 | 3.3147 | 0.5072 |
70
+ | 0.6427 | 11.9995 | 13068 | 3.4025 | 0.5101 |
71
+ | 0.604 | 12.9993 | 14157 | 3.3905 | 0.5103 |
72
+ | 0.5507 | 14.0 | 15247 | 3.4740 | 0.5088 |
73
+ | 0.5099 | 14.9998 | 16336 | 3.4772 | 0.5085 |
74
+ | 0.478 | 15.9995 | 17425 | 3.5259 | 0.5088 |
75
+ | 0.4545 | 16.9993 | 18514 | 3.5391 | 0.5094 |
76
+ | 0.427 | 18.0 | 19604 | 3.5887 | 0.5095 |
77
+ | 0.4083 | 18.9998 | 20693 | 3.5945 | 0.5097 |
78
+ | 0.3818 | 19.9977 | 21780 | 3.6298 | 0.5108 |
79
 
80
 
81
  ### Framework versions