nejox commited on
Commit
5229ef2
1 Parent(s): 73dec53

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +18 -18
README.md CHANGED
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [distilbert-base-cased-distilled-squad](https://huggingface.co/distilbert-base-cased-distilled-squad) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 2.1937
18
 
19
  ## Model description
20
 
@@ -34,8 +34,8 @@ More information needed
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 5e-05
37
- - train_batch_size: 16
38
- - eval_batch_size: 16
39
  - seed: 42
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
@@ -46,21 +46,21 @@ The following hyperparameters were used during training:
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | No log | 1.0 | 2 | 2.5987 |
50
- | No log | 2.0 | 4 | 2.5874 |
51
- | No log | 3.0 | 6 | 2.5674 |
52
- | No log | 4.0 | 8 | 2.5434 |
53
- | No log | 5.0 | 10 | 2.5217 |
54
- | No log | 6.0 | 12 | 2.4956 |
55
- | No log | 7.0 | 14 | 2.4719 |
56
- | No log | 8.0 | 16 | 2.4341 |
57
- | No log | 9.0 | 18 | 2.3780 |
58
- | No log | 10.0 | 20 | 2.3192 |
59
- | No log | 11.0 | 22 | 2.2701 |
60
- | No log | 12.0 | 24 | 2.2405 |
61
- | No log | 13.0 | 26 | 2.2175 |
62
- | No log | 14.0 | 28 | 2.2044 |
63
- | No log | 15.0 | 30 | 2.1937 |
64
 
65
 
66
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [distilbert-base-cased-distilled-squad](https://huggingface.co/distilbert-base-cased-distilled-squad) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 1.7601
18
 
19
  ## Model description
20
 
 
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 5e-05
37
+ - train_batch_size: 8
38
+ - eval_batch_size: 8
39
  - seed: 42
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
 
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | No log | 1.0 | 3 | 2.3917 |
50
+ | No log | 2.0 | 6 | 2.3782 |
51
+ | No log | 3.0 | 9 | 2.3533 |
52
+ | No log | 4.0 | 12 | 2.3143 |
53
+ | No log | 5.0 | 15 | 2.2670 |
54
+ | No log | 6.0 | 18 | 2.2112 |
55
+ | No log | 7.0 | 21 | 2.1549 |
56
+ | No log | 8.0 | 24 | 2.0915 |
57
+ | No log | 9.0 | 27 | 2.0377 |
58
+ | No log | 10.0 | 30 | 1.9545 |
59
+ | No log | 11.0 | 33 | 1.8787 |
60
+ | No log | 12.0 | 36 | 1.8299 |
61
+ | No log | 13.0 | 39 | 1.7897 |
62
+ | No log | 14.0 | 42 | 1.7662 |
63
+ | No log | 15.0 | 45 | 1.7601 |
64
 
65
 
66
  ### Framework versions