JinbiaoZhu commited on
Commit
598547e
1 Parent(s): a14100b

End of training

Browse files
Files changed (1) hide show
  1. README.md +14 -1
README.md CHANGED
@@ -3,6 +3,8 @@ license: mit
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: []
@@ -13,7 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
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
 
@@ -40,6 +44,15 @@ The following hyperparameters were used during training:
40
  - lr_scheduler_type: linear
41
  - num_epochs: 3
42
 
 
 
 
 
 
 
 
 
 
43
  ### Framework versions
44
 
45
  - Transformers 4.38.2
 
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
 
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: 3.9098
21
 
22
  ## Model description
23
 
 
44
  - lr_scheduler_type: linear
45
  - num_epochs: 3
46
 
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:----:|:---------------:|
51
+ | 4.2858 | 1.0 | 1198 | 4.5540 |
52
+ | 4.5096 | 2.0 | 2396 | 4.0584 |
53
+ | 5.3879 | 3.0 | 3594 | 3.8995 |
54
+
55
+
56
  ### Framework versions
57
 
58
  - Transformers 4.38.2