CesarLeblanc commited on
Commit
13f6fc2
·
verified ·
1 Parent(s): 2a0ecb7

Model save

Browse files
Files changed (1) hide show
  1. README.md +6 -6
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 2.6842
19
 
20
  ## Model description
21
 
@@ -47,11 +47,11 @@ The following hyperparameters were used during training:
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:------:|:---------------:|
50
- | 4.2492 | 1.0 | 22164 | 3.4632 |
51
- | 3.3388 | 2.0 | 44328 | 3.0353 |
52
- | 3.0538 | 3.0 | 66492 | 2.8427 |
53
- | 2.9078 | 4.0 | 88656 | 2.7292 |
54
- | 2.8305 | 5.0 | 110820 | 2.6842 |
55
 
56
 
57
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.4940
19
 
20
  ## Model description
21
 
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:------:|:---------------:|
50
+ | 1.0374 | 1.0 | 33077 | 0.7095 |
51
+ | 0.6842 | 2.0 | 66154 | 0.5977 |
52
+ | 0.6043 | 3.0 | 99231 | 0.5408 |
53
+ | 0.5622 | 4.0 | 132308 | 0.5119 |
54
+ | 0.5368 | 5.0 | 165385 | 0.4940 |
55
 
56
 
57
  ### Framework versions