Hugging Face's logo

apwic
/
sentiment-base-0

Transformers
TensorBoard
Safetensors
Indonesian
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
apwic commited on
Commit
e1f15de
•
1 Parent(s): e3e6285

Model save

Browse files
Files changed (7) hide show
  1. README.md +25 -27
  2. default/head_config.json +19 -0
  3. default/pytorch_model_head.bin +3 -0
  4. sentiment-lora/adapter_config.json +26 -0
  5. sentiment-lora/pytorch_adapter.bin +3 -0
  6. sentiment/head_config.json +21 -0
  7. sentiment/pytorch_model_head.bin +3 -0
README.md CHANGED
@@ -1,6 +1,4 @@
1
  ---
2
- language:
3
- - id
4
  license: mit
5
  base_model: indolem/indobert-base-uncased
6
  tags:
@@ -22,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
22
 
23
  This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on an unknown dataset.
24
  It achieves the following results on the evaluation set:
25
- - Loss: 0.7536
26
- - Accuracy: 0.9048
27
- - Precision: 0.8798
28
- - Recall: 0.8976
29
- - F1: 0.8878
30
 
31
  ## Model description
32
 
@@ -57,26 +55,26 @@ The following hyperparameters were used during training:
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
59
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
60
- | 0.4355 | 1.0 | 122 | 0.3243 | 0.8697 | 0.8538 | 0.8228 | 0.8359 |
61
- | 0.2295 | 2.0 | 244 | 0.3047 | 0.8897 | 0.8625 | 0.8795 | 0.8701 |
62
- | 0.1337 | 3.0 | 366 | 0.3747 | 0.8997 | 0.8778 | 0.8816 | 0.8797 |
63
- | 0.1038 | 4.0 | 488 | 0.4188 | 0.8822 | 0.8518 | 0.8867 | 0.8651 |
64
- | 0.072 | 5.0 | 610 | 0.6271 | 0.8872 | 0.8672 | 0.8577 | 0.8622 |
65
- | 0.0462 | 6.0 | 732 | 0.6129 | 0.8897 | 0.8632 | 0.8770 | 0.8695 |
66
- | 0.0459 | 7.0 | 854 | 0.5891 | 0.8897 | 0.8710 | 0.8595 | 0.8649 |
67
- | 0.0391 | 8.0 | 976 | 0.5973 | 0.8872 | 0.8587 | 0.8802 | 0.8681 |
68
- | 0.0307 | 9.0 | 1098 | 0.7087 | 0.8747 | 0.8441 | 0.8863 | 0.8585 |
69
- | 0.0199 | 10.0 | 1220 | 0.7264 | 0.8972 | 0.8869 | 0.8598 | 0.8717 |
70
- | 0.0105 | 11.0 | 1342 | 0.6738 | 0.8972 | 0.8767 | 0.8748 | 0.8757 |
71
- | 0.0131 | 12.0 | 1464 | 0.7488 | 0.8997 | 0.8733 | 0.8941 | 0.8825 |
72
- | 0.0102 | 13.0 | 1586 | 0.7155 | 0.8972 | 0.8708 | 0.8898 | 0.8793 |
73
- | 0.0061 | 14.0 | 1708 | 0.7196 | 0.9073 | 0.8851 | 0.8944 | 0.8895 |
74
- | 0.0138 | 15.0 | 1830 | 0.7618 | 0.9023 | 0.8773 | 0.8933 | 0.8846 |
75
- | 0.0075 | 16.0 | 1952 | 0.7253 | 0.9048 | 0.8806 | 0.8951 | 0.8873 |
76
- | 0.0063 | 17.0 | 2074 | 0.7560 | 0.9023 | 0.8782 | 0.8908 | 0.8841 |
77
- | 0.0066 | 18.0 | 2196 | 0.7483 | 0.9023 | 0.8758 | 0.8983 | 0.8857 |
78
- | 0.0023 | 19.0 | 2318 | 0.7535 | 0.9023 | 0.8773 | 0.8933 | 0.8846 |
79
- | 0.0021 | 20.0 | 2440 | 0.7536 | 0.9048 | 0.8798 | 0.8976 | 0.8878 |
80
 
81
 
82
  ### Framework versions
 
1
  ---
 
 
2
  license: mit
3
  base_model: indolem/indobert-base-uncased
4
  tags:
 
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: 0.3540
24
+ - Accuracy: 0.8546
25
+ - Precision: 0.8233
26
+ - Recall: 0.8297
27
+ - F1: 0.8264
28
 
29
  ## Model description
30
 
 
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
57
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
58
+ | 0.5623 | 1.0 | 122 | 0.5053 | 0.7168 | 0.6410 | 0.5796 | 0.5795 |
59
+ | 0.518 | 2.0 | 244 | 0.4861 | 0.7293 | 0.6674 | 0.5960 | 0.5998 |
60
+ | 0.4835 | 3.0 | 366 | 0.4552 | 0.7694 | 0.7211 | 0.7094 | 0.7145 |
61
+ | 0.4497 | 4.0 | 488 | 0.4223 | 0.7945 | 0.7521 | 0.7521 | 0.7521 |
62
+ | 0.4266 | 5.0 | 610 | 0.3996 | 0.8170 | 0.7814 | 0.7680 | 0.7741 |
63
+ | 0.3907 | 6.0 | 732 | 0.3830 | 0.8195 | 0.7818 | 0.7873 | 0.7845 |
64
+ | 0.3742 | 7.0 | 854 | 0.3684 | 0.8346 | 0.8016 | 0.7955 | 0.7984 |
65
+ | 0.3616 | 8.0 | 976 | 0.3720 | 0.8271 | 0.7902 | 0.8051 | 0.7968 |
66
+ | 0.3294 | 9.0 | 1098 | 0.3689 | 0.8371 | 0.8019 | 0.8147 | 0.8077 |
67
+ | 0.3207 | 10.0 | 1220 | 0.3632 | 0.8396 | 0.8047 | 0.8190 | 0.8111 |
68
+ | 0.3214 | 11.0 | 1342 | 0.3577 | 0.8371 | 0.8017 | 0.8172 | 0.8086 |
69
+ | 0.3167 | 12.0 | 1464 | 0.3607 | 0.8396 | 0.8046 | 0.8215 | 0.8119 |
70
+ | 0.289 | 13.0 | 1586 | 0.3684 | 0.8346 | 0.7988 | 0.8155 | 0.8061 |
71
+ | 0.2997 | 14.0 | 1708 | 0.3480 | 0.8496 | 0.8193 | 0.8161 | 0.8177 |
72
+ | 0.2986 | 15.0 | 1830 | 0.3576 | 0.8496 | 0.8169 | 0.8261 | 0.8212 |
73
+ | 0.2914 | 16.0 | 1952 | 0.3497 | 0.8496 | 0.8180 | 0.8211 | 0.8195 |
74
+ | 0.278 | 17.0 | 2074 | 0.3540 | 0.8521 | 0.8207 | 0.8254 | 0.8229 |
75
+ | 0.2887 | 18.0 | 2196 | 0.3516 | 0.8521 | 0.8207 | 0.8254 | 0.8229 |
76
+ | 0.2829 | 19.0 | 2318 | 0.3537 | 0.8521 | 0.8207 | 0.8254 | 0.8229 |
77
+ | 0.2771 | 20.0 | 2440 | 0.3540 | 0.8546 | 0.8233 | 0.8297 | 0.8264 |
78
 
79
 
80
  ### Framework versions
default/head_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": {
3
+ "activation_function": "gelu",
4
+ "bias": true,
5
+ "embedding_size": 768,
6
+ "head_type": "masked_lm",
7
+ "label2id": null,
8
+ "layer_norm": true,
9
+ "layers": 2,
10
+ "shift_labels": false,
11
+ "vocab_size": 31923
12
+ },
13
+ "hidden_size": 768,
14
+ "model_class": "BertAdapterModel",
15
+ "model_name": "indolem/indobert-base-uncased",
16
+ "model_type": "bert",
17
+ "name": "default",
18
+ "version": "0.2.0"
19
+ }
default/pytorch_model_head.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a181f0177f3154142b57d9cab72a7e6f72dea1fe172d1a480ff543e0c17b0f3f
3
+ size 100566390
sentiment-lora/adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": {
3
+ "alpha": 2,
4
+ "architecture": "lora",
5
+ "attn_matrices": [
6
+ "q",
7
+ "v"
8
+ ],
9
+ "composition_mode": "add",
10
+ "dropout": 0.05,
11
+ "init_weights": "lora",
12
+ "intermediate_lora": false,
13
+ "leave_out": [],
14
+ "output_lora": false,
15
+ "r": 4,
16
+ "selfattn_lora": true,
17
+ "use_gating": false
18
+ },
19
+ "config_id": "04392fe6378dd022",
20
+ "hidden_size": 768,
21
+ "model_class": "BertAdapterModel",
22
+ "model_name": "indolem/indobert-base-uncased",
23
+ "model_type": "bert",
24
+ "name": "sentiment-lora",
25
+ "version": "0.2.0"
26
+ }
sentiment-lora/pytorch_adapter.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6aa11b9fbf236ea6ab9936049123585e8de8521eb8940b84ac8fcd9dfaf39209
3
+ size 607654
sentiment/head_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": {
3
+ "activation_function": "tanh",
4
+ "bias": true,
5
+ "dropout_prob": null,
6
+ "head_type": "classification",
7
+ "label2id": {
8
+ "0": 0,
9
+ "1": 1
10
+ },
11
+ "layers": 2,
12
+ "num_labels": 2,
13
+ "use_pooler": false
14
+ },
15
+ "hidden_size": 768,
16
+ "model_class": "BertAdapterModel",
17
+ "model_name": "indolem/indobert-base-uncased",
18
+ "model_type": "bert",
19
+ "name": "sentiment",
20
+ "version": "0.2.0"
21
+ }
sentiment/pytorch_model_head.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e44e53749c74896e37cbd00dd8d8d7d464d1ba766920fe41b41ddc9b0e02716
3
+ size 2370664