Commit
•
d2f9235
1
Parent(s):
58d9339
Model save
Browse files
README.md
CHANGED
@@ -3,26 +3,9 @@ license: mit
|
|
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
|
@@ -30,10 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
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
|
34 |
-
It achieves the following results on the evaluation set:
|
35 |
-
- Loss: 0.4075
|
36 |
-
- Accuracy: 0.8810
|
37 |
|
38 |
## Model description
|
39 |
|
@@ -52,31 +32,15 @@ More information needed
|
|
52 |
### Training hyperparameters
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
-
- learning_rate:
|
56 |
-
- train_batch_size:
|
57 |
-
- eval_batch_size:
|
58 |
- seed: 42
|
59 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
- lr_scheduler_type: linear
|
61 |
-
- lr_scheduler_warmup_steps:
|
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
|
|
|
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 |
|
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 an unknown dataset.
|
|
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
32 |
### Training hyperparameters
|
33 |
|
34 |
The following hyperparameters were used during training:
|
35 |
+
- learning_rate: 2e-05
|
36 |
+
- train_batch_size: 64
|
37 |
+
- eval_batch_size: 64
|
38 |
- seed: 42
|
39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
- lr_scheduler_type: linear
|
41 |
+
- lr_scheduler_warmup_steps: 1000
|
42 |
- num_epochs: 10
|
43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
44 |
### Framework versions
|
45 |
|
46 |
- Transformers 4.38.2
|