apwic commited on
Commit
cf2b778
1 Parent(s): 4f82b38

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-r2a2d0.15-0
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-r2a2d0.15-0
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: 0.3672
24
+ - Accuracy: 0.8321
25
+ - Precision: 0.7961
26
+ - Recall: 0.8087
27
+ - F1: 0.8018
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
+ | 0.563 | 1.0 | 122 | 0.5138 | 0.7243 | 0.6636 | 0.6549 | 0.6586 |
59
+ | 0.509 | 2.0 | 244 | 0.5057 | 0.7168 | 0.6763 | 0.6996 | 0.6820 |
60
+ | 0.4924 | 3.0 | 366 | 0.4708 | 0.7393 | 0.6877 | 0.6931 | 0.6901 |
61
+ | 0.468 | 4.0 | 488 | 0.4379 | 0.7845 | 0.7412 | 0.7200 | 0.7286 |
62
+ | 0.4495 | 5.0 | 610 | 0.4466 | 0.7594 | 0.7233 | 0.7548 | 0.7313 |
63
+ | 0.4334 | 6.0 | 732 | 0.4041 | 0.8271 | 0.7927 | 0.7851 | 0.7887 |
64
+ | 0.415 | 7.0 | 854 | 0.4057 | 0.7995 | 0.7590 | 0.7756 | 0.7660 |
65
+ | 0.3974 | 8.0 | 976 | 0.3852 | 0.8321 | 0.7982 | 0.7937 | 0.7959 |
66
+ | 0.3849 | 9.0 | 1098 | 0.3829 | 0.8246 | 0.7880 | 0.7909 | 0.7894 |
67
+ | 0.3771 | 10.0 | 1220 | 0.3786 | 0.8396 | 0.8065 | 0.8065 | 0.8065 |
68
+ | 0.3633 | 11.0 | 1342 | 0.3843 | 0.8296 | 0.7931 | 0.8069 | 0.7993 |
69
+ | 0.3591 | 12.0 | 1464 | 0.3833 | 0.8296 | 0.7931 | 0.8069 | 0.7993 |
70
+ | 0.354 | 13.0 | 1586 | 0.3705 | 0.8396 | 0.8065 | 0.8065 | 0.8065 |
71
+ | 0.3451 | 14.0 | 1708 | 0.3709 | 0.8371 | 0.8028 | 0.8072 | 0.8049 |
72
+ | 0.3403 | 15.0 | 1830 | 0.3733 | 0.8321 | 0.7960 | 0.8112 | 0.8027 |
73
+ | 0.3282 | 16.0 | 1952 | 0.3715 | 0.8346 | 0.7988 | 0.8155 | 0.8061 |
74
+ | 0.3286 | 17.0 | 2074 | 0.3664 | 0.8321 | 0.7965 | 0.8037 | 0.7999 |
75
+ | 0.3348 | 18.0 | 2196 | 0.3670 | 0.8271 | 0.7904 | 0.8001 | 0.7949 |
76
+ | 0.325 | 19.0 | 2318 | 0.3669 | 0.8321 | 0.7961 | 0.8087 | 0.8018 |
77
+ | 0.3266 | 20.0 | 2440 | 0.3672 | 0.8321 | 0.7961 | 0.8087 | 0.8018 |
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/May17_17-03-01_indolem-petl-vm/events.out.tfevents.1715965386.indolem-petl-vm.1351291.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25def19ea61b6ad61b4bf78677beeb19ae1ec3338ec04f10782db192b5f66b93
3
- size 18293
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d3965184a4491da4ce8ab625dea9db94898477fd73f7a07d5ff4ac07630b98c
3
+ size 19330
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": 0.15,
11
+ "init_weights": "lora",
12
+ "intermediate_lora": false,
13
+ "leave_out": [],
14
+ "output_lora": false,
15
+ "r": 2,
16
+ "selfattn_lora": true,
17
+ "use_gating": false
18
+ },
19
+ "config_id": "8b182cf0e3f99d28",
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 sha256:9c2dd5425776d53e849cab686751fc67ef479a1e783cdba0694087c8deb0103a
3
+ size 312742
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 sha256:1209f310333ee8e23f7446289e6c5ed8fa7e5c8e9f1888f54f2d89149dd81a81
3
+ size 2370664