Hugging Face's logo

amritpuhan
/
fine-tuned-MoritzLaurer-deberta-v3-large-zeroshot-v2.0-arceasy

Multiple Choice
Transformers
Safetensors
deberta-v2
Generated from Trainer
Inference Endpoints
Model card Files Community
amritpuhan commited on
Commit
81e3949
•
1 Parent(s): 726eedc

End of training

Browse files
Files changed (2) hide show
  1. README.md +14 -12
  2. adapter_model.safetensors +1 -1
README.md CHANGED
@@ -1,10 +1,11 @@
1
  ---
2
- license: mit
3
  base_model: MoritzLaurer/deberta-v3-large-zeroshot-v2.0
4
- tags:
5
- - generated_from_trainer
6
  metrics:
7
  - accuracy
 
 
8
  model-index:
9
  - name: fine-tuned-MoritzLaurer-deberta-v3-large-zeroshot-v2.0-arceasy
10
  results: []
@@ -17,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [MoritzLaurer/deberta-v3-large-zeroshot-v2.0](https://huggingface.co/MoritzLaurer/deberta-v3-large-zeroshot-v2.0) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.8204
21
- - Accuracy: 0.8175
22
 
23
  ## Model description
24
 
@@ -50,17 +51,18 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
- | No log | 1.0 | 141 | 0.4636 | 0.8333 |
54
- | No log | 2.0 | 282 | 0.5887 | 0.8175 |
55
- | No log | 3.0 | 423 | 0.5583 | 0.8316 |
56
- | 0.3291 | 4.0 | 564 | 0.7024 | 0.8246 |
57
- | 0.3291 | 5.0 | 705 | 0.7975 | 0.8246 |
58
- | 0.3291 | 6.0 | 846 | 0.8204 | 0.8175 |
59
 
60
 
61
  ### Framework versions
62
 
 
63
  - Transformers 4.41.2
64
  - Pytorch 2.3.0+cu121
65
  - Datasets 2.20.0
66
- - Tokenizers 0.19.1
 
1
  ---
 
2
  base_model: MoritzLaurer/deberta-v3-large-zeroshot-v2.0
3
+ library_name: peft
4
+ license: mit
5
  metrics:
6
  - accuracy
7
+ tags:
8
+ - generated_from_trainer
9
  model-index:
10
  - name: fine-tuned-MoritzLaurer-deberta-v3-large-zeroshot-v2.0-arceasy
11
  results: []
 
18
 
19
  This model is a fine-tuned version of [MoritzLaurer/deberta-v3-large-zeroshot-v2.0](https://huggingface.co/MoritzLaurer/deberta-v3-large-zeroshot-v2.0) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.7638
22
+ - Accuracy: 0.8368
23
 
24
  ## Model description
25
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
+ | No log | 1.0 | 141 | 0.4862 | 0.8281 |
55
+ | No log | 2.0 | 282 | 0.4829 | 0.8439 |
56
+ | No log | 3.0 | 423 | 0.6579 | 0.8456 |
57
+ | 0.3419 | 4.0 | 564 | 0.6815 | 0.8404 |
58
+ | 0.3419 | 5.0 | 705 | 0.7499 | 0.8404 |
59
+ | 0.3419 | 6.0 | 846 | 0.7638 | 0.8368 |
60
 
61
 
62
  ### Framework versions
63
 
64
+ - PEFT 0.11.1
65
  - Transformers 4.41.2
66
  - Pytorch 2.3.0+cu121
67
  - Datasets 2.20.0
68
+ - Tokenizers 0.19.1
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1086fdefb0739d6f7c505158bfa6eca9537557b51c8ee61ff7fc38f4ec699205
3
  size 3164340
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:686997c04b434b7f1925310c96b20c5fa21325ad395ff648f01249f09caed8df
3
  size 3164340