Hugging Face's logo

ayameRushia
/
roberta-base-indonesian-1.5G-sentiment-analysis-smsa

Text Classification Transformers PyTorch
Indonesian roberta generated_from_trainer Eval Results Inference Endpoints
Model card Files Community
4
ayameRushia commited on
Commit
5e6ce61
•
1 Parent(s): c001bc7

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +17 -19
README.md CHANGED
@@ -6,7 +6,7 @@ datasets:
6
  metrics:
7
  - accuracy
8
  model-index:
9
- - name: roberta-base-indonesian-1.5G-finetuned-wnli
10
  results:
11
  - task:
12
  name: Text Classification
@@ -18,21 +18,18 @@ model-index:
18
  metrics:
19
  - name: Accuracy
20
  type: accuracy
21
- value: 0.9246031746031746
22
- language: id
23
- widget:
24
- - text: "Saya mengapresiasi usaha anda"
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
  should probably proofread and complete it, then remove this comment. -->
29
 
30
- # roberta-base-indonesian-1.5G-finetuned-wnli
31
 
32
  This model is a fine-tuned version of [cahya/roberta-base-indonesian-1.5G](https://huggingface.co/cahya/roberta-base-indonesian-1.5G) on the indonlu dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 0.5420
35
- - Accuracy: 0.9246
36
 
37
  ## Model description
38
 
@@ -51,28 +48,29 @@ More information needed
51
  ### Training hyperparameters
52
 
53
  The following hyperparameters were used during training:
54
- - learning_rate: 2e-05
55
  - train_batch_size: 16
56
  - eval_batch_size: 16
57
  - seed: 42
58
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
  - lr_scheduler_type: linear
 
60
  - num_epochs: 10
61
 
62
  ### Training results
63
 
64
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
65
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
66
- | 0.3123 | 1.0 | 688 | 0.3496 | 0.8944 |
67
- | 0.1888 | 2.0 | 1376 | 0.2877 | 0.9103 |
68
- | 0.0981 | 3.0 | 2064 | 0.3936 | 0.9143 |
69
- | 0.0529 | 4.0 | 2752 | 0.4431 | 0.9183 |
70
- | 0.0419 | 5.0 | 3440 | 0.5350 | 0.9167 |
71
- | 0.0121 | 6.0 | 4128 | 0.5420 | 0.9246 |
72
- | 0.0116 | 7.0 | 4816 | 0.5920 | 0.9175 |
73
- | 0.0042 | 8.0 | 5504 | 0.6440 | 0.9190 |
74
- | 0.0013 | 9.0 | 6192 | 0.6460 | 0.9222 |
75
- | 0.001 | 10.0 | 6880 | 0.6575 | 0.9230 |
76
 
77
 
78
  ### Framework versions
6
  metrics:
7
  - accuracy
8
  model-index:
9
+ - name: roberta-base-indonesian-1.5G-sentiment-analysis-smsa
10
  results:
11
  - task:
12
  name: Text Classification
18
  metrics:
19
  - name: Accuracy
20
  type: accuracy
21
+ value: 0.9261904761904762
 
 
 
22
  ---
23
 
24
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
25
  should probably proofread and complete it, then remove this comment. -->
26
 
27
+ # roberta-base-indonesian-1.5G-sentiment-analysis-smsa
28
 
29
  This model is a fine-tuned version of [cahya/roberta-base-indonesian-1.5G](https://huggingface.co/cahya/roberta-base-indonesian-1.5G) on the indonlu dataset.
30
  It achieves the following results on the evaluation set:
31
+ - Loss: 0.4294
32
+ - Accuracy: 0.9262
33
 
34
  ## Model description
35
 
48
  ### Training hyperparameters
49
 
50
  The following hyperparameters were used during training:
51
+ - learning_rate: 1e-05
52
  - train_batch_size: 16
53
  - eval_batch_size: 16
54
  - seed: 42
55
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
56
  - lr_scheduler_type: linear
57
+ - lr_scheduler_warmup_steps: 1500
58
  - num_epochs: 10
59
 
60
  ### Training results
61
 
62
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
63
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
64
+ | 0.6461 | 1.0 | 688 | 0.2620 | 0.9087 |
65
+ | 0.2627 | 2.0 | 1376 | 0.2291 | 0.9151 |
66
+ | 0.1784 | 3.0 | 2064 | 0.2891 | 0.9167 |
67
+ | 0.1099 | 4.0 | 2752 | 0.3317 | 0.9230 |
68
+ | 0.0857 | 5.0 | 3440 | 0.4294 | 0.9262 |
69
+ | 0.0346 | 6.0 | 4128 | 0.4759 | 0.9246 |
70
+ | 0.0221 | 7.0 | 4816 | 0.4946 | 0.9206 |
71
+ | 0.006 | 8.0 | 5504 | 0.5823 | 0.9175 |
72
+ | 0.0047 | 9.0 | 6192 | 0.5777 | 0.9159 |
73
+ | 0.004 | 10.0 | 6880 | 0.5800 | 0.9175 |
74
 
75
 
76
  ### Framework versions