Hugging Face's logo

duynhatran
/
deberta_textclassification

Text Classification
Transformers
TensorBoard
Safetensors
deberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
duynhatran commited on
Commit
7dec7e9
•
1 Parent(s): e6673b3

End of training

Browse files
Files changed (2) hide show
  1. README.md +23 -13
  2. model.safetensors +1 -1
README.md CHANGED
@@ -6,7 +6,6 @@ tags:
6
  - generated_from_trainer
7
  metrics:
8
  - accuracy
9
- - f1
10
  model-index:
11
  - name: deberta_textclassification
12
  results: []
@@ -19,9 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [microsoft/deberta-base](https://huggingface.co/microsoft/deberta-base) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.5291
23
- - Accuracy: 0.9043
24
- - F1: 0.9320
25
 
26
  ## Model description
27
 
@@ -41,8 +39,8 @@ More information needed
41
 
42
  The following hyperparameters were used during training:
43
  - learning_rate: 2e-05
44
- - train_batch_size: 16
45
- - eval_batch_size: 16
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
@@ -50,13 +48,25 @@ The following hyperparameters were used during training:
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
54
- |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
55
- | 0.4082 | 1.0 | 760 | 0.3256 | 0.8720 | 0.9050 |
56
- | 0.2193 | 2.0 | 1520 | 0.2805 | 0.8967 | 0.9259 |
57
- | 0.1571 | 3.0 | 2280 | 0.3280 | 0.9089 | 0.9357 |
58
- | 0.0947 | 4.0 | 3040 | 0.4283 | 0.9112 | 0.9368 |
59
- | 0.0489 | 5.0 | 3800 | 0.5291 | 0.9043 | 0.9320 |
 
 
 
 
 
 
 
 
 
 
 
 
60
 
61
 
62
  ### Framework versions
 
6
  - generated_from_trainer
7
  metrics:
8
  - accuracy
 
9
  model-index:
10
  - name: deberta_textclassification
11
  results: []
 
18
 
19
  This model is a fine-tuned version of [microsoft/deberta-base](https://huggingface.co/microsoft/deberta-base) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.3436
22
+ - Accuracy: 0.9520
 
23
 
24
  ## Model description
25
 
 
39
 
40
  The following hyperparameters were used during training:
41
  - learning_rate: 2e-05
42
+ - train_batch_size: 8
43
+ - eval_batch_size: 8
44
  - seed: 42
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
 
48
 
49
  ### Training results
50
 
51
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
+ |:-------------:|:------:|:----:|:---------------:|:--------:|
53
+ | 0.3919 | 0.2924 | 500 | 0.2821 | 0.9184 |
54
+ | 0.274 | 0.5848 | 1000 | 0.2795 | 0.9362 |
55
+ | 0.2552 | 0.8772 | 1500 | 0.2469 | 0.9355 |
56
+ | 0.2148 | 1.1696 | 2000 | 0.3214 | 0.9421 |
57
+ | 0.1876 | 1.4620 | 2500 | 0.2636 | 0.9382 |
58
+ | 0.1505 | 1.7544 | 3000 | 0.2323 | 0.9467 |
59
+ | 0.1411 | 2.0468 | 3500 | 0.3445 | 0.9395 |
60
+ | 0.0676 | 2.3392 | 4000 | 0.3280 | 0.9414 |
61
+ | 0.1089 | 2.6316 | 4500 | 0.4225 | 0.9270 |
62
+ | 0.0888 | 2.9240 | 5000 | 0.2458 | 0.9520 |
63
+ | 0.0544 | 3.2164 | 5500 | 0.2877 | 0.9539 |
64
+ | 0.0366 | 3.5088 | 6000 | 0.3010 | 0.9553 |
65
+ | 0.0322 | 3.8012 | 6500 | 0.3508 | 0.9474 |
66
+ | 0.0313 | 4.0936 | 7000 | 0.3302 | 0.9520 |
67
+ | 0.0191 | 4.3860 | 7500 | 0.3527 | 0.9493 |
68
+ | 0.0118 | 4.6784 | 8000 | 0.3378 | 0.9513 |
69
+ | 0.0189 | 4.9708 | 8500 | 0.3436 | 0.9520 |
70
 
71
 
72
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7b91f32916a9986ce63f829193cdc506c5e804db066a9442b855c89280bfd48
3
  size 556799560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b807f8a112e9cb02e20847219de4cea1702922830258ef4ecbb36b8acd0c9338
3
  size 556799560