apwic commited on
Commit
fef2f75
1 Parent(s): a9b764c

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-r8a2d0.15-0
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-r8a2d0.15-0
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: 0.3217
24
+ - Accuracy: 0.8622
25
+ - Precision: 0.8326
26
+ - Recall: 0.8375
27
+ - F1: 0.8349
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
+ | 0.5593 | 1.0 | 122 | 0.5026 | 0.7268 | 0.6658 | 0.6542 | 0.6589 |
59
+ | 0.4995 | 2.0 | 244 | 0.4797 | 0.7544 | 0.7149 | 0.7412 | 0.7226 |
60
+ | 0.4612 | 3.0 | 366 | 0.4282 | 0.7644 | 0.7199 | 0.7358 | 0.7262 |
61
+ | 0.4019 | 4.0 | 488 | 0.3934 | 0.8296 | 0.7949 | 0.7919 | 0.7934 |
62
+ | 0.3665 | 5.0 | 610 | 0.4234 | 0.7970 | 0.7618 | 0.7964 | 0.7720 |
63
+ | 0.334 | 6.0 | 732 | 0.3723 | 0.8195 | 0.7817 | 0.7973 | 0.7884 |
64
+ | 0.3263 | 7.0 | 854 | 0.3704 | 0.8346 | 0.7990 | 0.8230 | 0.8086 |
65
+ | 0.3076 | 8.0 | 976 | 0.3521 | 0.8471 | 0.8153 | 0.8168 | 0.8160 |
66
+ | 0.298 | 9.0 | 1098 | 0.3522 | 0.8471 | 0.8138 | 0.8243 | 0.8187 |
67
+ | 0.2923 | 10.0 | 1220 | 0.3375 | 0.8571 | 0.8289 | 0.8239 | 0.8264 |
68
+ | 0.2689 | 11.0 | 1342 | 0.3392 | 0.8622 | 0.8319 | 0.8400 | 0.8357 |
69
+ | 0.2686 | 12.0 | 1464 | 0.3484 | 0.8622 | 0.8309 | 0.8450 | 0.8373 |
70
+ | 0.2726 | 13.0 | 1586 | 0.3258 | 0.8596 | 0.8316 | 0.8282 | 0.8298 |
71
+ | 0.2713 | 14.0 | 1708 | 0.3246 | 0.8622 | 0.8333 | 0.8350 | 0.8341 |
72
+ | 0.2577 | 15.0 | 1830 | 0.3307 | 0.8596 | 0.8293 | 0.8357 | 0.8324 |
73
+ | 0.2519 | 16.0 | 1952 | 0.3305 | 0.8622 | 0.8314 | 0.8425 | 0.8365 |
74
+ | 0.2488 | 17.0 | 2074 | 0.3234 | 0.8546 | 0.8246 | 0.8246 | 0.8246 |
75
+ | 0.2546 | 18.0 | 2196 | 0.3247 | 0.8647 | 0.8346 | 0.8442 | 0.8391 |
76
+ | 0.2463 | 19.0 | 2318 | 0.3204 | 0.8596 | 0.8307 | 0.8307 | 0.8307 |
77
+ | 0.2458 | 20.0 | 2440 | 0.3217 | 0.8622 | 0.8326 | 0.8375 | 0.8349 |
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_03-07-54_indolem-petl-vm/events.out.tfevents.1716001678.indolem-petl-vm.1551694.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2e722609833633d2cbae3c87f2cd8ae08f5a58ff04934615ee8b47527989400
3
- size 18293
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a6d99742d747bcf76ab4fb2b79b12d32ec663988d5cb04dd3c1f87e978e8b6a
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": 8,
16
+ "selfattn_lora": true,
17
+ "use_gating": false
18
+ },
19
+ "config_id": "889de044c8fec1ad",
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 sha256:51dfc88b76e260139533781f96438a370c6c543fc7cc707cd2648565b7751969
3
+ size 1197478
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 sha256:7a7fbdd7ccbb98f604487d19fd56c63bd06ace2c01edf9ef1e48be343390ac25
3
+ size 2370664