Hugging Face's logo

konradhugging
/
fine-tuned-Qwen2-0.5B-Instruct-NER

Safetensors
qwen2
Generated from Trainer
Model card Files
xet
Community
konradhugging commited on
Commit
801ab74
·
verified ·
1 Parent(s): c43e78e

End of training

Browse files
Files changed (3) hide show
  1. README.md +17 -22
  2. generation_config.json +1 -1
  3. model.safetensors +1 -1
README.md CHANGED
@@ -15,15 +15,15 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.3619
19
  - Exact Match: 0.0
20
- - F1 Score: 48.5865
21
  - Format Score: 0.0
22
- - Content Score: 66.6667
23
- - Pred Items: 1
24
- - True Items: 61
25
  - Common Items: 0
26
- - Levenshtein Distance: 151.5
27
 
28
  ## Model description
29
 
@@ -48,27 +48,22 @@ The following hyperparameters were used during training:
48
  - seed: 42
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: linear
51
- - num_epochs: 10
52
 
53
  ### Training results
54
 
55
- | Training Loss | Epoch | Step | Validation Loss | Exact Match | F1 Score | Format Score | Content Score | Pred Items | True Items | Common Items | Levenshtein Distance |
56
- |:-------------:|:-----:|:----:|:---------------:|:-----------:|:--------:|:------------:|:-------------:|:----------:|:----------:|:------------:|:--------------------:|
57
- | 0.5075 | 1.0 | 527 | 0.4887 | 0.0 | 52.3308 | 0.0 | 66.6667 | 0 | 83 | 0 | 205.9167 |
58
- | 0.3014 | 2.0 | 1054 | 0.1629 | 0.0 | 64.1598 | 0.0 | 83.3333 | 0 | 26 | 0 | 72.4167 |
59
- | 0.2859 | 3.0 | 1581 | 0.9125 | 0.0 | 33.4787 | 0.0 | 41.6667 | 0 | 134 | 0 | 357.0 |
60
- | 0.2702 | 4.0 | 2108 | 0.3270 | 0.0 | 56.7024 | 0.0 | 66.6667 | 0 | 60 | 0 | 143.3333 |
61
- | 0.2462 | 5.0 | 2635 | 0.2629 | 0.0 | 62.3809 | 0.0 | 83.3333 | 0 | 50 | 0 | 110.25 |
62
- | 0.2312 | 6.0 | 3162 | 0.4293 | 0.0 | 45.5724 | 0.0 | 58.3333 | 1 | 69 | 0 | 170.75 |
63
- | 0.2322 | 7.0 | 3689 | 0.1284 | 0.0 | 67.2158 | 0.0 | 83.3333 | 0 | 17 | 0 | 46.5833 |
64
- | 0.2067 | 8.0 | 4216 | 0.5583 | 0.0 | 47.1238 | 0.0 | 58.3333 | 0 | 88 | 0 | 219.25 |
65
- | 0.1953 | 9.0 | 4743 | 0.1389 | 0.0 | 56.6947 | 0.0 | 91.6667 | 0 | 12 | 0 | 52.9167 |
66
- | 0.2192 | 10.0 | 5270 | 0.3619 | 0.0 | 48.5865 | 0.0 | 66.6667 | 1 | 61 | 0 | 151.5 |
67
 
68
 
69
  ### Framework versions
70
 
71
- - Transformers 4.42.4
72
- - Pytorch 2.3.1+cu121
73
- - Datasets 2.20.0
74
  - Tokenizers 0.19.1
 
15
 
16
  This model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.7071
19
  - Exact Match: 0.0
20
+ - F1 Score: 47.2556
21
  - Format Score: 0.0
22
+ - Content Score: 83.3333
23
+ - Pred Items: 0
24
+ - True Items: 23
25
  - Common Items: 0
26
+ - Levenshtein Distance: 196.1667
27
 
28
  ## Model description
29
 
 
48
  - seed: 42
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: linear
51
+ - num_epochs: 50
52
 
53
  ### Training results
54
 
55
+ | Training Loss | Epoch | Step | Validation Loss | Exact Match | F1 Score | Format Score | Content Score | Pred Items | True Items | Common Items | Levenshtein Distance |
56
+ |:-------------:|:-------:|:-----:|:---------------:|:-----------:|:--------:|:------------:|:-------------:|:----------:|:----------:|:------------:|:--------------------:|
57
+ | 0.2192 | 9.4877 | 5000 | 0.3631 | 0.0 | 50.5576 | 0.0 | 50.0 | 0 | 37 | 0 | 164.3333 |
58
+ | 0.154 | 18.9753 | 10000 | 0.3042 | 0.0 | 34.6132 | 0.0 | 83.3333 | 0 | 19 | 0 | 133.8333 |
59
+ | 0.1439 | 28.4630 | 15000 | 0.2594 | 0.0 | 38.6508 | 0.0 | 66.6667 | 1 | 11 | 0 | 102.0 |
60
+ | 0.1315 | 37.9507 | 20000 | 0.2014 | 0.0 | 43.9169 | 0.0 | 66.6667 | 2 | 10 | 0 | 79.0 |
61
+ | 0.1204 | 47.4383 | 25000 | 0.7071 | 0.0 | 47.2556 | 0.0 | 83.3333 | 0 | 23 | 0 | 196.1667 |
 
 
 
 
 
62
 
63
 
64
  ### Framework versions
65
 
66
+ - Transformers 4.44.0
67
+ - Pytorch 2.4.0
68
+ - Datasets 2.21.0
69
  - Tokenizers 0.19.1
generation_config.json CHANGED
@@ -10,5 +10,5 @@
10
  "temperature": 0.7,
11
  "top_k": 20,
12
  "top_p": 0.8,
13
- "transformers_version": "4.42.4"
14
  }
 
10
  "temperature": 0.7,
11
  "top_k": 20,
12
  "top_p": 0.8,
13
+ "transformers_version": "4.44.0"
14
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:762989b4398c5492b9ed9b3005e7b388754e6fdc5c165c344b54f8b19d87fd9c
3
  size 1976163472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c2135c877e08399e75e2e509ec805f28e3711d0c70a0b0832f707415937119d
3
  size 1976163472