Commit
•
951cf46
1
Parent(s):
a27a884
End of training
Browse files
README.md
CHANGED
@@ -3,9 +3,26 @@ license: mit
|
|
3 |
base_model: w11wo/indo-roberta-small
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
6 |
model-index:
|
7 |
- name: indo-roberta-small-finetuned-indonlu-smsa
|
8 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
---
|
10 |
|
11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -13,7 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# indo-roberta-small-finetuned-indonlu-smsa
|
15 |
|
16 |
-
This model is a fine-tuned version of [w11wo/indo-roberta-small](https://huggingface.co/w11wo/indo-roberta-small) on
|
|
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
@@ -41,6 +61,22 @@ The following hyperparameters were used during training:
|
|
41 |
- lr_scheduler_warmup_steps: 2000
|
42 |
- num_epochs: 10
|
43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
44 |
### Framework versions
|
45 |
|
46 |
- Transformers 4.38.2
|
|
|
3 |
base_model: w11wo/indo-roberta-small
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- indonlu
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
model-index:
|
11 |
- name: indo-roberta-small-finetuned-indonlu-smsa
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Text Classification
|
15 |
+
type: text-classification
|
16 |
+
dataset:
|
17 |
+
name: indonlu
|
18 |
+
type: indonlu
|
19 |
+
config: smsa
|
20 |
+
split: validation
|
21 |
+
args: smsa
|
22 |
+
metrics:
|
23 |
+
- name: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 0.8809523809523809
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
30 |
|
31 |
# indo-roberta-small-finetuned-indonlu-smsa
|
32 |
|
33 |
+
This model is a fine-tuned version of [w11wo/indo-roberta-small](https://huggingface.co/w11wo/indo-roberta-small) on the indonlu dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.4075
|
36 |
+
- Accuracy: 0.8810
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
61 |
- lr_scheduler_warmup_steps: 2000
|
62 |
- num_epochs: 10
|
63 |
|
64 |
+
### Training results
|
65 |
+
|
66 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
67 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
68 |
+
| No log | 1.0 | 344 | 0.6672 | 0.7103 |
|
69 |
+
| 0.7802 | 2.0 | 688 | 0.4828 | 0.8111 |
|
70 |
+
| 0.4817 | 3.0 | 1032 | 0.4378 | 0.8278 |
|
71 |
+
| 0.4817 | 4.0 | 1376 | 0.3920 | 0.8540 |
|
72 |
+
| 0.3703 | 5.0 | 1720 | 0.4251 | 0.8524 |
|
73 |
+
| 0.2826 | 6.0 | 2064 | 0.3883 | 0.8659 |
|
74 |
+
| 0.2826 | 7.0 | 2408 | 0.3782 | 0.8698 |
|
75 |
+
| 0.2024 | 8.0 | 2752 | 0.3932 | 0.8698 |
|
76 |
+
| 0.1429 | 9.0 | 3096 | 0.4075 | 0.8810 |
|
77 |
+
| 0.1429 | 10.0 | 3440 | 0.4257 | 0.8738 |
|
78 |
+
|
79 |
+
|
80 |
### Framework versions
|
81 |
|
82 |
- Transformers 4.38.2
|