Hugging Face's logo

galkinv42
/
nli-cross-encoder-roberta

Text Classification
Transformers
Safetensors
deberta-v2
Generated from Trainer
Model card Files Community
galkinv42 commited on
Commit
1191042
·
verified ·
1 Parent(s): cebac5a

Hinter-Models/deberta-sber-nli-v2

Browse files
Files changed (3) hide show
  1. README.md +10 -10
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7](https://huggingface.co/MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.4873
22
  - Accuracy: 0.9448
23
- - F1 Macro: 0.9468
24
 
25
  ## Model description
26
 
@@ -55,14 +55,14 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
57
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
58
- | 0.2507 | 1.0 | 197 | 0.2485 | 0.9282 | 0.9303 |
59
- | 0.0926 | 2.0 | 394 | 0.1878 | 0.9420 | 0.9436 |
60
- | 0.0339 | 3.0 | 591 | 0.3596 | 0.9448 | 0.9468 |
61
- | 0.0183 | 4.0 | 788 | 0.4495 | 0.9448 | 0.9463 |
62
- | 0.0185 | 5.0 | 985 | 0.4833 | 0.9392 | 0.9410 |
63
- | 0.0007 | 6.0 | 1182 | 0.5019 | 0.9365 | 0.9381 |
64
- | 0.0005 | 7.0 | 1379 | 0.4779 | 0.9475 | 0.9494 |
65
- | 0.0003 | 8.0 | 1576 | 0.4873 | 0.9448 | 0.9468 |
66
 
67
 
68
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7](https://huggingface.co/MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.4859
22
  - Accuracy: 0.9448
23
+ - F1 Macro: 0.9469
24
 
25
  ## Model description
26
 
 
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
57
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
58
+ | 0.1806 | 1.0 | 211 | 0.3069 | 0.9088 | 0.9134 |
59
+ | 0.1021 | 2.0 | 422 | 0.1795 | 0.9530 | 0.9544 |
60
+ | 0.0343 | 3.0 | 633 | 0.4396 | 0.9365 | 0.9389 |
61
+ | 0.0182 | 4.0 | 844 | 0.4025 | 0.9475 | 0.9496 |
62
+ | 0.0047 | 5.0 | 1055 | 0.4674 | 0.9420 | 0.9441 |
63
+ | 0.0014 | 6.0 | 1266 | 0.4457 | 0.9448 | 0.9469 |
64
+ | 0.0049 | 7.0 | 1477 | 0.4835 | 0.9448 | 0.9469 |
65
+ | 0.0004 | 8.0 | 1688 | 0.4859 | 0.9448 | 0.9469 |
66
 
67
 
68
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:711a94b17c5dee50bb196b1b806826548ed6f75ae5c755ad3f9570f2ba1e5eb8
3
  size 1115271284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd7bf47a8114bc514edd50629c3ceb099b5f8103eca296eb1b77bfb4d57c64b8
3
  size 1115271284
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8be86ed7ee6f7443f053f70914524c45f0513b8229ed903d5822ba9ca0b99ab
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:563e179d17f2f2b3df766f8408fc2f9b960775dc4f7da4b711848147e94ba540
3
  size 5368