Model save
Browse files
README.md
CHANGED
@@ -1,10 +1,13 @@
|
|
1 |
---
|
2 |
-
language:
|
3 |
-
- id
|
4 |
license: mit
|
5 |
base_model: indolem/indobert-base-uncased
|
6 |
tags:
|
7 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
8 |
model-index:
|
9 |
- name: nerugm-base-0
|
10 |
results: []
|
@@ -16,6 +19,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
# nerugm-base-0
|
17 |
|
18 |
This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -36,12 +45,38 @@ More information needed
|
|
36 |
The following hyperparameters were used during training:
|
37 |
- learning_rate: 5e-05
|
38 |
- train_batch_size: 16
|
39 |
-
- eval_batch_size:
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
- num_epochs: 20.0
|
44 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
45 |
### Framework versions
|
46 |
|
47 |
- Transformers 4.39.3
|
|
|
1 |
---
|
|
|
|
|
2 |
license: mit
|
3 |
base_model: indolem/indobert-base-uncased
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
model-index:
|
12 |
- name: nerugm-base-0
|
13 |
results: []
|
|
|
19 |
# nerugm-base-0
|
20 |
|
21 |
This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on an unknown dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.2749
|
24 |
+
- Precision: 0.8234
|
25 |
+
- Recall: 0.8964
|
26 |
+
- F1: 0.8584
|
27 |
+
- Accuracy: 0.9631
|
28 |
|
29 |
## Model description
|
30 |
|
|
|
45 |
The following hyperparameters were used during training:
|
46 |
- learning_rate: 5e-05
|
47 |
- train_batch_size: 16
|
48 |
+
- eval_batch_size: 64
|
49 |
- seed: 42
|
50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
- lr_scheduler_type: linear
|
52 |
- num_epochs: 20.0
|
53 |
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
+
| 0.3551 | 1.0 | 106 | 0.1873 | 0.6789 | 0.8757 | 0.7649 | 0.9414 |
|
59 |
+
| 0.1199 | 2.0 | 212 | 0.1308 | 0.7602 | 0.8817 | 0.8164 | 0.9611 |
|
60 |
+
| 0.0746 | 3.0 | 318 | 0.1383 | 0.7755 | 0.8787 | 0.8239 | 0.9618 |
|
61 |
+
| 0.0497 | 4.0 | 424 | 0.1717 | 0.7922 | 0.8462 | 0.8183 | 0.9554 |
|
62 |
+
| 0.0289 | 5.0 | 530 | 0.1706 | 0.8027 | 0.8787 | 0.8390 | 0.9621 |
|
63 |
+
| 0.023 | 6.0 | 636 | 0.1929 | 0.7688 | 0.8757 | 0.8188 | 0.9585 |
|
64 |
+
| 0.0161 | 7.0 | 742 | 0.2457 | 0.7769 | 0.8757 | 0.8234 | 0.9539 |
|
65 |
+
| 0.0106 | 8.0 | 848 | 0.2450 | 0.7926 | 0.8817 | 0.8347 | 0.9572 |
|
66 |
+
| 0.0065 | 9.0 | 954 | 0.2315 | 0.8150 | 0.8994 | 0.8551 | 0.9629 |
|
67 |
+
| 0.0053 | 10.0 | 1060 | 0.2373 | 0.8147 | 0.8846 | 0.8482 | 0.9626 |
|
68 |
+
| 0.004 | 11.0 | 1166 | 0.2421 | 0.8283 | 0.8846 | 0.8555 | 0.9639 |
|
69 |
+
| 0.003 | 12.0 | 1272 | 0.2572 | 0.808 | 0.8964 | 0.8499 | 0.9621 |
|
70 |
+
| 0.0027 | 13.0 | 1378 | 0.2516 | 0.8135 | 0.8905 | 0.8503 | 0.9616 |
|
71 |
+
| 0.0012 | 14.0 | 1484 | 0.2636 | 0.8123 | 0.8964 | 0.8523 | 0.9649 |
|
72 |
+
| 0.002 | 15.0 | 1590 | 0.2672 | 0.8091 | 0.8905 | 0.8479 | 0.9626 |
|
73 |
+
| 0.0012 | 16.0 | 1696 | 0.2610 | 0.8130 | 0.8876 | 0.8487 | 0.9634 |
|
74 |
+
| 0.001 | 17.0 | 1802 | 0.2694 | 0.8251 | 0.8935 | 0.8580 | 0.9631 |
|
75 |
+
| 0.0012 | 18.0 | 1908 | 0.2815 | 0.8177 | 0.9024 | 0.8579 | 0.9626 |
|
76 |
+
| 0.0012 | 19.0 | 2014 | 0.2723 | 0.8229 | 0.8935 | 0.8567 | 0.9629 |
|
77 |
+
| 0.0008 | 20.0 | 2120 | 0.2749 | 0.8234 | 0.8964 | 0.8584 | 0.9631 |
|
78 |
+
|
79 |
+
|
80 |
### Framework versions
|
81 |
|
82 |
- Transformers 4.39.3
|