apwic commited on
Commit
9aa1f02
1 Parent(s): 6080c33

Model save

Browse files
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-lora-r4a0d0.1-1
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-lora-r4a0d0.1-1
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: 0.3239
24
+ - Accuracy: 0.8622
25
+ - Precision: 0.8373
26
+ - Recall: 0.8250
27
+ - F1: 0.8307
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
+ | 0.5658 | 1.0 | 122 | 0.5195 | 0.7268 | 0.6646 | 0.6492 | 0.6550 |
59
+ | 0.5125 | 2.0 | 244 | 0.5060 | 0.7293 | 0.6805 | 0.6935 | 0.6855 |
60
+ | 0.4809 | 3.0 | 366 | 0.4686 | 0.7669 | 0.7184 | 0.7151 | 0.7167 |
61
+ | 0.4353 | 4.0 | 488 | 0.4295 | 0.7920 | 0.7500 | 0.7353 | 0.7417 |
62
+ | 0.4116 | 5.0 | 610 | 0.4171 | 0.8020 | 0.7628 | 0.7849 | 0.7714 |
63
+ | 0.3809 | 6.0 | 732 | 0.3865 | 0.8446 | 0.8148 | 0.8051 | 0.8096 |
64
+ | 0.3681 | 7.0 | 854 | 0.3697 | 0.8496 | 0.8193 | 0.8161 | 0.8177 |
65
+ | 0.3469 | 8.0 | 976 | 0.3554 | 0.8471 | 0.8206 | 0.8018 | 0.8102 |
66
+ | 0.3455 | 9.0 | 1098 | 0.3494 | 0.8496 | 0.8211 | 0.8111 | 0.8158 |
67
+ | 0.3284 | 10.0 | 1220 | 0.3437 | 0.8496 | 0.8289 | 0.7961 | 0.8096 |
68
+ | 0.3132 | 11.0 | 1342 | 0.3371 | 0.8596 | 0.8389 | 0.8132 | 0.8243 |
69
+ | 0.3042 | 12.0 | 1464 | 0.3371 | 0.8546 | 0.8254 | 0.8221 | 0.8238 |
70
+ | 0.3063 | 13.0 | 1586 | 0.3317 | 0.8596 | 0.8406 | 0.8107 | 0.8233 |
71
+ | 0.3013 | 14.0 | 1708 | 0.3304 | 0.8622 | 0.8373 | 0.8250 | 0.8307 |
72
+ | 0.2928 | 15.0 | 1830 | 0.3295 | 0.8596 | 0.8325 | 0.8257 | 0.8290 |
73
+ | 0.2864 | 16.0 | 1952 | 0.3284 | 0.8622 | 0.8351 | 0.8300 | 0.8325 |
74
+ | 0.2819 | 17.0 | 2074 | 0.3254 | 0.8596 | 0.8347 | 0.8207 | 0.8272 |
75
+ | 0.2877 | 18.0 | 2196 | 0.3249 | 0.8596 | 0.8336 | 0.8232 | 0.8281 |
76
+ | 0.2819 | 19.0 | 2318 | 0.3241 | 0.8647 | 0.8410 | 0.8267 | 0.8333 |
77
+ | 0.2803 | 20.0 | 2440 | 0.3239 | 0.8622 | 0.8373 | 0.8250 | 0.8307 |
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
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/May18_23-51-56_indolem-petl-vm/events.out.tfevents.1716076320.indolem-petl-vm.2003960.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56893fa53bf9514602de9f75bf591164892fa921d81d8ef3a664f393936fa708
3
- size 18290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fab21d0d1a7dd5a82f0c941923fd75120ad9c052f701cbd9e1f70fd326d03f8
3
+ size 19327
sentiment-lora/adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": {
3
+ "alpha": 0,
4
+ "architecture": "lora",
5
+ "attn_matrices": [
6
+ "q",
7
+ "v"
8
+ ],
9
+ "composition_mode": "add",
10
+ "dropout": 0.1,
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": "e496874b2522628a",
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:bc712bb2644baeadf15c032925949cf50d667b59af3be9bec0b9a2c8085fe8c2
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:c7f0d32a44d94603a8629f53a6d705f300230e313bfd330549ff14570281b4ba
3
+ size 2370664