apwic commited on
Commit
951656a
1 Parent(s): 86fb3ac

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-r4a1d0.1-0
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-r4a1d0.1-0
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: 0.3483
24
+ - Accuracy: 0.8446
25
+ - Precision: 0.8111
26
+ - Recall: 0.8201
27
+ - F1: 0.8153
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
+ | 0.5617 | 1.0 | 122 | 0.5117 | 0.7193 | 0.6580 | 0.6514 | 0.6543 |
59
+ | 0.5046 | 2.0 | 244 | 0.4917 | 0.7419 | 0.7042 | 0.7324 | 0.7112 |
60
+ | 0.4798 | 3.0 | 366 | 0.4466 | 0.7594 | 0.7129 | 0.7248 | 0.7179 |
61
+ | 0.4374 | 4.0 | 488 | 0.3994 | 0.8195 | 0.7866 | 0.7648 | 0.7741 |
62
+ | 0.4037 | 5.0 | 610 | 0.4150 | 0.7845 | 0.7480 | 0.7800 | 0.7575 |
63
+ | 0.3741 | 6.0 | 732 | 0.3737 | 0.8371 | 0.8028 | 0.8072 | 0.8049 |
64
+ | 0.3574 | 7.0 | 854 | 0.3776 | 0.8221 | 0.7845 | 0.7991 | 0.7909 |
65
+ | 0.3387 | 8.0 | 976 | 0.3654 | 0.8446 | 0.8120 | 0.8151 | 0.8135 |
66
+ | 0.3293 | 9.0 | 1098 | 0.3627 | 0.8371 | 0.8021 | 0.8122 | 0.8068 |
67
+ | 0.3209 | 10.0 | 1220 | 0.3553 | 0.8371 | 0.8032 | 0.8047 | 0.8040 |
68
+ | 0.2967 | 11.0 | 1342 | 0.3674 | 0.8346 | 0.7989 | 0.8130 | 0.8052 |
69
+ | 0.2928 | 12.0 | 1464 | 0.3707 | 0.8321 | 0.7960 | 0.8112 | 0.8027 |
70
+ | 0.2967 | 13.0 | 1586 | 0.3514 | 0.8471 | 0.8153 | 0.8168 | 0.8160 |
71
+ | 0.2934 | 14.0 | 1708 | 0.3507 | 0.8421 | 0.8083 | 0.8158 | 0.8119 |
72
+ | 0.2811 | 15.0 | 1830 | 0.3553 | 0.8346 | 0.7991 | 0.8105 | 0.8043 |
73
+ | 0.2738 | 16.0 | 1952 | 0.3555 | 0.8421 | 0.8077 | 0.8208 | 0.8136 |
74
+ | 0.2717 | 17.0 | 2074 | 0.3468 | 0.8496 | 0.8174 | 0.8236 | 0.8204 |
75
+ | 0.278 | 18.0 | 2196 | 0.3510 | 0.8421 | 0.8080 | 0.8183 | 0.8127 |
76
+ | 0.2701 | 19.0 | 2318 | 0.3471 | 0.8471 | 0.8142 | 0.8218 | 0.8178 |
77
+ | 0.2722 | 20.0 | 2440 | 0.3483 | 0.8446 | 0.8111 | 0.8201 | 0.8153 |
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_19-52-58_indolem-petl-vm/events.out.tfevents.1715975583.indolem-petl-vm.1408004.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7a09980742b0902396f5cea970c88e91decf705ca7378fe5d6db312f6b3a9f7
3
- size 18290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bf10b228a8b60f9622c497e083ee0c00eebc4ead301c2ea6227ced522ce75c3
3
+ size 19327
sentiment-lora/adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": {
3
+ "alpha": 1,
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": "10bd443306cd2e68",
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 sha256:3b5cb5d127dff5eb7f21c2df739bc8509769d69ba4dc48804054d1ab01616710
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 sha256:6f09d41418e6370a7a24b63088d4e3b62ec9bdabe61e682b936e339402ff5a89
3
+ size 2370664