Hugging Face's logo

apwic
/
sentiment-seq_bn-4

TensorBoard
Indonesian
Generated from Trainer
Model card Files
xet
 Metrics Community
apwic commited on
Commit
9f78572
·
verified ·
1 Parent(s): b1e0e62

Model save

Browse files
Files changed (8) hide show
  1. README.md +85 -0
  2. adapter-sentiment/adapter_config.json +42 -0
  3. adapter-sentiment/pytorch_adapter.bin +3 -0
  4. default/head_config.json +19 -0
  5. default/pytorch_model_head.bin +3 -0
  6. runs/Jun09_12-56-15_a358b85c7679/events.out.tfevents.1717937782.a358b85c7679.22608.0 +2 -2
  7. sentiment/head_config.json +21 -0
  8. sentiment/pytorch_model_head.bin +3 -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-seq_bn-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-seq_bn-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: 0.2917
24
+ - Accuracy: 0.8847
25
+ - Precision: 0.8648
26
+ - Recall: 0.8534
27
+ - F1: 0.8588
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
+ | 0.5556 | 1.0 | 122 | 0.5148 | 0.7343 | 0.6852 | 0.6970 | 0.6899 |
59
+ | 0.476 | 2.0 | 244 | 0.4507 | 0.7870 | 0.7577 | 0.6918 | 0.7095 |
60
+ | 0.4238 | 3.0 | 366 | 0.4003 | 0.8195 | 0.7958 | 0.7473 | 0.7644 |
61
+ | 0.3735 | 4.0 | 488 | 0.3799 | 0.8371 | 0.8089 | 0.7872 | 0.7966 |
62
+ | 0.3548 | 5.0 | 610 | 0.3634 | 0.8471 | 0.8153 | 0.8168 | 0.8160 |
63
+ | 0.3213 | 6.0 | 732 | 0.3584 | 0.8421 | 0.8077 | 0.8208 | 0.8136 |
64
+ | 0.3085 | 7.0 | 854 | 0.3318 | 0.8622 | 0.8448 | 0.8125 | 0.8259 |
65
+ | 0.2981 | 8.0 | 976 | 0.3429 | 0.8672 | 0.8722 | 0.7985 | 0.8238 |
66
+ | 0.2788 | 9.0 | 1098 | 0.3304 | 0.8797 | 0.8795 | 0.8224 | 0.8439 |
67
+ | 0.259 | 10.0 | 1220 | 0.3076 | 0.8772 | 0.8535 | 0.8481 | 0.8507 |
68
+ | 0.2587 | 11.0 | 1342 | 0.3025 | 0.8747 | 0.8471 | 0.8538 | 0.8503 |
69
+ | 0.2391 | 12.0 | 1464 | 0.2990 | 0.8847 | 0.8697 | 0.8459 | 0.8565 |
70
+ | 0.2443 | 13.0 | 1586 | 0.2919 | 0.8797 | 0.8600 | 0.8449 | 0.8518 |
71
+ | 0.237 | 14.0 | 1708 | 0.3040 | 0.8772 | 0.8483 | 0.8631 | 0.8550 |
72
+ | 0.2176 | 15.0 | 1830 | 0.2937 | 0.8897 | 0.8649 | 0.8720 | 0.8683 |
73
+ | 0.2202 | 16.0 | 1952 | 0.2920 | 0.8822 | 0.8610 | 0.8517 | 0.8561 |
74
+ | 0.2203 | 17.0 | 2074 | 0.2923 | 0.8822 | 0.8585 | 0.8567 | 0.8575 |
75
+ | 0.2204 | 18.0 | 2196 | 0.2927 | 0.8847 | 0.8621 | 0.8584 | 0.8602 |
76
+ | 0.2124 | 19.0 | 2318 | 0.2920 | 0.8872 | 0.8672 | 0.8577 | 0.8622 |
77
+ | 0.2108 | 20.0 | 2440 | 0.2917 | 0.8847 | 0.8648 | 0.8534 | 0.8588 |
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
adapter-sentiment/adapter_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": {
3
+ "adapter_residual_before_ln": false,
4
+ "cross_adapter": false,
5
+ "dropout": 0.0,
6
+ "factorized_phm_W": true,
7
+ "factorized_phm_rule": false,
8
+ "hypercomplex_nonlinearity": "glorot-uniform",
9
+ "init_weights": "bert",
10
+ "inv_adapter": null,
11
+ "inv_adapter_reduction_factor": null,
12
+ "is_parallel": false,
13
+ "learn_phm": true,
14
+ "leave_out": [],
15
+ "ln_after": false,
16
+ "ln_before": false,
17
+ "mh_adapter": false,
18
+ "non_linearity": "relu",
19
+ "original_ln_after": true,
20
+ "original_ln_before": true,
21
+ "output_adapter": true,
22
+ "phm_bias": true,
23
+ "phm_c_init": "normal",
24
+ "phm_dim": 4,
25
+ "phm_init_range": 0.0001,
26
+ "phm_layer": false,
27
+ "phm_rank": 1,
28
+ "reduction_factor": 16,
29
+ "residual_before_ln": true,
30
+ "scaling": 1.0,
31
+ "shared_W_phm": false,
32
+ "shared_phm_rule": true,
33
+ "use_gating": false
34
+ },
35
+ "config_id": "9076f36a74755ac4",
36
+ "hidden_size": 768,
37
+ "model_class": "BertAdapterModel",
38
+ "model_name": "indolem/indobert-base-uncased",
39
+ "model_type": "bert",
40
+ "name": "adapter-sentiment",
41
+ "version": "0.2.0"
42
+ }
adapter-sentiment/pytorch_adapter.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94752c271f9c11674de1f8e8ea3ecfdf517f0392f4edd8007ed55e2c6061b5ff
3
+ size 3596006
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
runs/Jun09_12-56-15_a358b85c7679/events.out.tfevents.1717937782.a358b85c7679.22608.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:669bebfe139d3874d174c78a34bdd73b14bad304e6e008fec76c3a3e3ebae23c
3
- size 18266
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9cbbed3a635b89ba598954e9fab91aa2092446b387773f45e86ebcb7df35c75
3
+ size 19303
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 sha256:8dbc2d406b742d575801cf11f3d8f0e12eb9502f31e52c62fe30377c7e7a7e94
3
+ size 2370664