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-4
|
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-4
|
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: 0.7179
|
24 |
+
- Accuracy: 0.9223
|
25 |
+
- Precision: 0.9170
|
26 |
+
- Recall: 0.8925
|
27 |
+
- F1: 0.9035
|
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 |
+
| 0.3833 | 1.0 | 122 | 0.3131 | 0.8697 | 0.8474 | 0.8328 | 0.8395 |
|
59 |
+
| 0.2232 | 2.0 | 244 | 0.2697 | 0.8872 | 0.8658 | 0.8602 | 0.8629 |
|
60 |
+
| 0.1574 | 3.0 | 366 | 0.5306 | 0.8596 | 0.8777 | 0.7782 | 0.8080 |
|
61 |
+
| 0.0861 | 4.0 | 488 | 0.3975 | 0.9148 | 0.8923 | 0.9072 | 0.8992 |
|
62 |
+
| 0.0444 | 5.0 | 610 | 0.4916 | 0.8972 | 0.8767 | 0.8748 | 0.8757 |
|
63 |
+
| 0.0323 | 6.0 | 732 | 0.4763 | 0.9048 | 0.8851 | 0.8851 | 0.8851 |
|
64 |
+
| 0.0343 | 7.0 | 854 | 0.8505 | 0.8747 | 0.8784 | 0.8113 | 0.8354 |
|
65 |
+
| 0.021 | 8.0 | 976 | 0.5843 | 0.9073 | 0.8888 | 0.8869 | 0.8879 |
|
66 |
+
| 0.0171 | 9.0 | 1098 | 0.7052 | 0.8972 | 0.8940 | 0.8523 | 0.8695 |
|
67 |
+
| 0.0125 | 10.0 | 1220 | 0.7268 | 0.9048 | 0.8935 | 0.8726 | 0.8821 |
|
68 |
+
| 0.0106 | 11.0 | 1342 | 0.7198 | 0.9123 | 0.9064 | 0.8779 | 0.8905 |
|
69 |
+
| 0.0153 | 12.0 | 1464 | 0.6023 | 0.9098 | 0.8898 | 0.8937 | 0.8917 |
|
70 |
+
| 0.0047 | 13.0 | 1586 | 0.7099 | 0.9148 | 0.9135 | 0.8772 | 0.8927 |
|
71 |
+
| 0.0109 | 14.0 | 1708 | 0.6722 | 0.9098 | 0.8999 | 0.8787 | 0.8883 |
|
72 |
+
| 0.0044 | 15.0 | 1830 | 0.7060 | 0.9198 | 0.9175 | 0.8858 | 0.8996 |
|
73 |
+
| 0.0053 | 16.0 | 1952 | 0.7098 | 0.9223 | 0.9194 | 0.8900 | 0.9030 |
|
74 |
+
| 0.005 | 17.0 | 2074 | 0.7069 | 0.9198 | 0.9105 | 0.8933 | 0.9012 |
|
75 |
+
| 0.0005 | 18.0 | 2196 | 0.7586 | 0.9173 | 0.9155 | 0.8815 | 0.8962 |
|
76 |
+
| 0.0017 | 19.0 | 2318 | 0.7198 | 0.9223 | 0.9170 | 0.8925 | 0.9035 |
|
77 |
+
| 0.0009 | 20.0 | 2440 | 0.7179 | 0.9223 | 0.9170 | 0.8925 | 0.9035 |
|
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 |
+
}
|