Hugging Face's logo

phoner45
/
wangchan-sentiment-thai-text-model

Text Classification
Transformers
TensorBoard
Safetensors
Thai
camembert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
phoner45 commited on
Commit
e6415dd
•
1 Parent(s): 340a006

wangchan-sentiment-thai-text-model

Browse files
Files changed (3) hide show
  1. README.md +15 -26
  2. model.safetensors +1 -1
  3. runs/Oct18_08-17-50_e532ffc414fd/events.out.tfevents.1729239478.e532ffc414fd.294.0 +2 -2
README.md CHANGED
@@ -1,16 +1,10 @@
1
  ---
2
- base_model: airesearch/wangchanberta-base-att-spm-uncased
3
- datasets:
4
- - pythainlp/wisesight_sentiment
5
- - Wongnai/wongnai_reviews
6
- language:
7
- - th
8
  library_name: transformers
9
- metrics:
10
- - accuracy
11
- pipeline_tag: text-classification
12
  tags:
13
  - generated_from_trainer
 
 
14
  model-index:
15
  - name: wangchan-sentiment-thai-text-model
16
  results: []
@@ -23,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
23
 
24
  This model is a fine-tuned version of [airesearch/wangchanberta-base-att-spm-uncased](https://huggingface.co/airesearch/wangchanberta-base-att-spm-uncased) on the None dataset.
25
  It achieves the following results on the evaluation set:
26
- - Loss: 1.1248
27
- - Accuracy: 0.7413
28
 
29
  ## Model description
30
 
@@ -43,29 +37,24 @@ More information needed
43
  ### Training hyperparameters
44
 
45
  The following hyperparameters were used during training:
46
- - learning_rate: 2e-05
47
- - train_batch_size: 32
48
- - eval_batch_size: 32
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
- - num_epochs: 10
53
  - mixed_precision_training: Native AMP
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
58
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
59
- | 0.6058 | 1.0 | 1911 | 0.5904 | 0.7442 |
60
- | 0.5355 | 2.0 | 3822 | 0.5625 | 0.7559 |
61
- | 0.4737 | 3.0 | 5733 | 0.5731 | 0.7493 |
62
- | 0.4039 | 4.0 | 7644 | 0.6235 | 0.7547 |
63
- | 0.3286 | 5.0 | 9555 | 0.7004 | 0.7524 |
64
- | 0.2704 | 6.0 | 11466 | 0.7713 | 0.7416 |
65
- | 0.21 | 7.0 | 13377 | 0.9502 | 0.7432 |
66
- | 0.1808 | 8.0 | 15288 | 0.9720 | 0.7407 |
67
- | 0.1494 | 9.0 | 17199 | 1.0570 | 0.7361 |
68
- | 0.1304 | 10.0 | 19110 | 1.1248 | 0.7413 |
69
 
70
 
71
  ### Framework versions
@@ -73,4 +62,4 @@ The following hyperparameters were used during training:
73
  - Transformers 4.44.2
74
  - Pytorch 2.4.1+cu121
75
  - Datasets 3.0.1
76
- - Tokenizers 0.19.1
 
1
  ---
 
 
 
 
 
 
2
  library_name: transformers
3
+ base_model: airesearch/wangchanberta-base-att-spm-uncased
 
 
4
  tags:
5
  - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
  model-index:
9
  - name: wangchan-sentiment-thai-text-model
10
  results: []
 
17
 
18
  This model is a fine-tuned version of [airesearch/wangchanberta-base-att-spm-uncased](https://huggingface.co/airesearch/wangchanberta-base-att-spm-uncased) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.5849
21
+ - Accuracy: 0.7535
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 1e-05
41
+ - train_batch_size: 16
42
+ - eval_batch_size: 16
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
+ - num_epochs: 5
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
53
+ | 0.6445 | 1.0 | 3822 | 0.6295 | 0.7309 |
54
+ | 0.5865 | 2.0 | 7644 | 0.5855 | 0.7430 |
55
+ | 0.5285 | 3.0 | 11466 | 0.5754 | 0.7455 |
56
+ | 0.5127 | 4.0 | 15288 | 0.5816 | 0.7492 |
57
+ | 0.4861 | 5.0 | 19110 | 0.5849 | 0.7535 |
 
 
 
 
 
58
 
59
 
60
  ### Framework versions
 
62
  - Transformers 4.44.2
63
  - Pytorch 2.4.1+cu121
64
  - Datasets 3.0.1
65
+ - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a84bcebade0726b71c072a3c23ddb4fcb1f20ca922870c29540f0965b737e1c
3
  size 421011004
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0a933bb4bcca5d8fb1a5054d45613992641516c0619e475d3ef1a19026c3fc9
3
  size 421011004
runs/Oct18_08-17-50_e532ffc414fd/events.out.tfevents.1729239478.e532ffc414fd.294.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62dd2f5fe77a6bbf013a66ad4735fd86592c11d6162e19e538df68ac2de49004
3
- size 14848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec5fab4364d2d2c22fa06561bdbff177e1a32228792171c086c3bb1ee9f98612
3
+ size 15208