JinbiaoZhu commited on
Commit
a14100b
1 Parent(s): 847970b

Model save

Browse files
Files changed (1) hide show
  1. README.md +4 -16
README.md CHANGED
@@ -3,8 +3,6 @@ license: mit
3
  base_model: microsoft/deberta-v3-base
4
  tags:
5
  - generated_from_trainer
6
- datasets:
7
- - eli5_category
8
  model-index:
9
  - name: finetuned-DebertaV3-eli5-askscience-TextGeneration
10
  results: []
@@ -15,9 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # finetuned-DebertaV3-eli5-askscience-TextGeneration
17
 
18
- This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the eli5_category dataset.
19
- It achieves the following results on the evaluation set:
20
- - Loss: 0.2153
21
 
22
  ## Model description
23
 
@@ -37,20 +33,12 @@ More information needed
37
 
38
  The following hyperparameters were used during training:
39
  - learning_rate: 2e-05
40
- - train_batch_size: 12
41
- - eval_batch_size: 12
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
- - num_epochs: 2
46
-
47
- ### Training results
48
-
49
- | Training Loss | Epoch | Step | Validation Loss |
50
- |:-------------:|:-----:|:----:|:---------------:|
51
- | 0.4504 | 1.0 | 996 | 0.3881 |
52
- | 0.1694 | 2.0 | 1992 | 0.2153 |
53
-
54
 
55
  ### Framework versions
56
 
 
3
  base_model: microsoft/deberta-v3-base
4
  tags:
5
  - generated_from_trainer
 
 
6
  model-index:
7
  - name: finetuned-DebertaV3-eli5-askscience-TextGeneration
8
  results: []
 
13
 
14
  # finetuned-DebertaV3-eli5-askscience-TextGeneration
15
 
16
+ This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on an unknown dataset.
 
 
17
 
18
  ## Model description
19
 
 
33
 
34
  The following hyperparameters were used during training:
35
  - learning_rate: 2e-05
36
+ - train_batch_size: 16
37
+ - eval_batch_size: 16
38
  - seed: 42
39
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
  - lr_scheduler_type: linear
41
+ - num_epochs: 3
 
 
 
 
 
 
 
 
42
 
43
  ### Framework versions
44