Hugging Face's logo

ThuyNT03
/
xlm-roberta-base-Final_Mixed-aug_replace_synonym-1

Text Classification
Transformers
PyTorch
xlm-roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
ThuyNT03 commited on
Commit
2d61643
•
1 Parent(s): ce76e69

Training completed!

Browse files
Files changed (2) hide show
  1. README.md +14 -14
  2. pytorch_model.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 [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.9852
22
- - Accuracy: 0.74
23
- - F1: 0.7369
24
 
25
  ## Model description
26
 
@@ -42,7 +42,7 @@ The following hyperparameters were used during training:
42
  - learning_rate: 2e-05
43
  - train_batch_size: 16
44
  - eval_batch_size: 16
45
- - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - num_epochs: 8
@@ -51,19 +51,19 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
54
- | 1.0471 | 1.0 | 87 | 0.9289 | 0.64 | 0.5512 |
55
- | 0.9553 | 2.0 | 174 | 0.7912 | 0.64 | 0.5672 |
56
- | 0.7049 | 3.0 | 261 | 0.6276 | 0.75 | 0.7341 |
57
- | 0.5556 | 4.0 | 348 | 0.7291 | 0.74 | 0.7291 |
58
- | 0.435 | 5.0 | 435 | 0.6930 | 0.72 | 0.7163 |
59
- | 0.3534 | 6.0 | 522 | 0.8526 | 0.74 | 0.7369 |
60
- | 0.2774 | 7.0 | 609 | 0.9620 | 0.73 | 0.7259 |
61
- | 0.2152 | 8.0 | 696 | 0.9852 | 0.74 | 0.7369 |
62
 
63
 
64
  ### Framework versions
65
 
66
- - Transformers 4.32.1
67
  - Pytorch 2.0.1+cu118
68
- - Datasets 2.14.4
69
  - Tokenizers 0.13.3
 
18
 
19
  This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.8727
22
+ - Accuracy: 0.76
23
+ - F1: 0.7592
24
 
25
  ## Model description
26
 
 
42
  - learning_rate: 2e-05
43
  - train_batch_size: 16
44
  - eval_batch_size: 16
45
+ - seed: 41
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - num_epochs: 8
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
54
+ | 1.0219 | 1.0 | 87 | 0.7346 | 0.68 | 0.6276 |
55
+ | 0.7518 | 2.0 | 174 | 0.5934 | 0.75 | 0.7425 |
56
+ | 0.6023 | 3.0 | 261 | 0.7553 | 0.7 | 0.6975 |
57
+ | 0.479 | 4.0 | 348 | 0.7275 | 0.72 | 0.7118 |
58
+ | 0.3515 | 5.0 | 435 | 0.9068 | 0.74 | 0.7306 |
59
+ | 0.2646 | 6.0 | 522 | 0.7953 | 0.77 | 0.7633 |
60
+ | 0.2123 | 7.0 | 609 | 0.8673 | 0.77 | 0.7652 |
61
+ | 0.1535 | 8.0 | 696 | 0.8727 | 0.76 | 0.7592 |
62
 
63
 
64
  ### Framework versions
65
 
66
+ - Transformers 4.33.1
67
  - Pytorch 2.0.1+cu118
68
+ - Datasets 2.14.5
69
  - Tokenizers 0.13.3
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:18bda0fac443145b9220137811b57842b246945ee601c84f83e50376a0e9c3b8
3
  size 1112252785
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c70ae81e454f80f073ba963ba2f7913dc0d60307551825303631799c11b0f3f9
3
  size 1112252785