Anurag0961 commited on
Commit
e98f781
·
1 Parent(s): f49cc3a

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -11
README.md CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.5252
20
- - F1: 0.8001
21
 
22
  ## Model description
23
 
@@ -49,18 +49,18 @@ The following hyperparameters were used during training:
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | F1 |
51
  |:-------------:|:-----:|:----:|:---------------:|:------:|
52
- | 1.8319 | 1.0 | 39 | 1.6539 | 0.4812 |
53
- | 1.3017 | 2.0 | 78 | 0.9994 | 0.7275 |
54
- | 0.7721 | 3.0 | 117 | 0.7172 | 0.7593 |
55
- | 0.52 | 4.0 | 156 | 0.5922 | 0.7714 |
56
- | 0.4092 | 5.0 | 195 | 0.5660 | 0.7714 |
57
- | 0.2953 | 6.0 | 234 | 0.5250 | 0.8111 |
58
- | 0.2544 | 7.0 | 273 | 0.5247 | 0.8001 |
59
- | 0.2206 | 8.0 | 312 | 0.5252 | 0.8001 |
60
 
61
 
62
  ### Framework versions
63
 
64
- - Transformers 4.21.3
65
  - Pytorch 1.12.1+cu113
66
  - Tokenizers 0.12.1
 
16
 
17
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.5290
20
+ - F1: 0.8211
21
 
22
  ## Model description
23
 
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | F1 |
51
  |:-------------:|:-----:|:----:|:---------------:|:------:|
52
+ | 1.813 | 1.0 | 40 | 1.5304 | 0.5227 |
53
+ | 1.2312 | 2.0 | 80 | 0.9138 | 0.7439 |
54
+ | 0.7428 | 3.0 | 120 | 0.6869 | 0.7518 |
55
+ | 0.5055 | 4.0 | 160 | 0.5766 | 0.8050 |
56
+ | 0.3581 | 5.0 | 200 | 0.5454 | 0.8052 |
57
+ | 0.2664 | 6.0 | 240 | 0.5208 | 0.8200 |
58
+ | 0.2145 | 7.0 | 280 | 0.5218 | 0.8241 |
59
+ | 0.1853 | 8.0 | 320 | 0.5290 | 0.8211 |
60
 
61
 
62
  ### Framework versions
63
 
64
+ - Transformers 4.22.1
65
  - Pytorch 1.12.1+cu113
66
  - Tokenizers 0.12.1