Model save
Browse files- README.md +85 -0
- generation_config.json +6 -0
README.md
ADDED
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: indolem/indobert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- precision
|
9 |
+
- recall
|
10 |
+
- f1
|
11 |
+
model-index:
|
12 |
+
- name: sentiment-base-3
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# sentiment-base-3
|
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: 0.7050
|
24 |
+
- Accuracy: 0.9023
|
25 |
+
- Precision: 0.8893
|
26 |
+
- Recall: 0.8708
|
27 |
+
- F1: 0.8793
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 5e-05
|
47 |
+
- train_batch_size: 30
|
48 |
+
- eval_batch_size: 8
|
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 | Accuracy | Precision | Recall | F1 |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
|
58 |
+
| 0.3971 | 1.0 | 122 | 0.2704 | 0.8822 | 0.8715 | 0.8367 | 0.8513 |
|
59 |
+
| 0.214 | 2.0 | 244 | 0.2381 | 0.9198 | 0.9033 | 0.9033 | 0.9033 |
|
60 |
+
| 0.1301 | 3.0 | 366 | 0.3832 | 0.8797 | 0.8795 | 0.8224 | 0.8439 |
|
61 |
+
| 0.0904 | 4.0 | 488 | 0.3873 | 0.8947 | 0.8662 | 0.8955 | 0.8782 |
|
62 |
+
| 0.0587 | 5.0 | 610 | 0.4034 | 0.9148 | 0.9022 | 0.8897 | 0.8956 |
|
63 |
+
| 0.0496 | 6.0 | 732 | 0.5249 | 0.8922 | 0.8632 | 0.8938 | 0.8756 |
|
64 |
+
| 0.0362 | 7.0 | 854 | 0.5330 | 0.9073 | 0.8999 | 0.8719 | 0.8842 |
|
65 |
+
| 0.0223 | 8.0 | 976 | 0.6168 | 0.8972 | 0.8743 | 0.8798 | 0.8770 |
|
66 |
+
| 0.0191 | 9.0 | 1098 | 0.7104 | 0.8947 | 0.8870 | 0.8530 | 0.8675 |
|
67 |
+
| 0.0147 | 10.0 | 1220 | 0.6125 | 0.8972 | 0.8732 | 0.8823 | 0.8776 |
|
68 |
+
| 0.0121 | 11.0 | 1342 | 0.6883 | 0.9048 | 0.8790 | 0.9001 | 0.8883 |
|
69 |
+
| 0.0118 | 12.0 | 1464 | 0.6760 | 0.8972 | 0.8723 | 0.8848 | 0.8781 |
|
70 |
+
| 0.0034 | 13.0 | 1586 | 0.7163 | 0.9048 | 0.8851 | 0.8851 | 0.8851 |
|
71 |
+
| 0.0064 | 14.0 | 1708 | 0.7180 | 0.9073 | 0.8875 | 0.8894 | 0.8884 |
|
72 |
+
| 0.008 | 15.0 | 1830 | 0.6915 | 0.9048 | 0.8978 | 0.8676 | 0.8808 |
|
73 |
+
| 0.0052 | 16.0 | 1952 | 0.6778 | 0.9073 | 0.8875 | 0.8894 | 0.8884 |
|
74 |
+
| 0.0066 | 17.0 | 2074 | 0.6993 | 0.9073 | 0.8875 | 0.8894 | 0.8884 |
|
75 |
+
| 0.0053 | 18.0 | 2196 | 0.6966 | 0.9048 | 0.8956 | 0.8701 | 0.8814 |
|
76 |
+
| 0.0022 | 19.0 | 2318 | 0.7112 | 0.8997 | 0.8852 | 0.8691 | 0.8765 |
|
77 |
+
| 0.0042 | 20.0 | 2440 | 0.7050 | 0.9023 | 0.8893 | 0.8708 | 0.8793 |
|
78 |
+
|
79 |
+
|
80 |
+
### Framework versions
|
81 |
+
|
82 |
+
- Transformers 4.39.3
|
83 |
+
- Pytorch 2.3.0+cu121
|
84 |
+
- Datasets 2.19.1
|
85 |
+
- Tokenizers 0.15.2
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"pad_token_id": 0,
|
5 |
+
"transformers_version": "4.39.3"
|
6 |
+
}
|