Hugging Face's logo

apwic
/
nerugm-lora-r4a1d0.1

TensorBoard
Indonesian
Generated from Trainer
Model card Files Metrics Community
apwic commited on
Commit
3717846
•
1 Parent(s): 59c937b

Model save

Browse files
Files changed (6) hide show
  1. README.md +85 -0
  2. nerugm-lora/adapter_config.json +26 -0
  3. nerugm-lora/head_config.json +23 -0
  4. nerugm-lora/pytorch_adapter.bin +3 -0
  5. nerugm-lora/pytorch_model_head.bin +3 -0
  6. runs/May24_23-19-08_indolem-petl-vm/events.out.tfevents.1716592755.indolem-petl-vm.1782730.0 +2 -2
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
+ - precision
8
+ - recall
9
+ - f1
10
+ - accuracy
11
+ model-index:
12
+ - name: nerugm-lora-r4a1d0.1
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
+ # nerugm-lora-r4a1d0.1
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: 0.1302
24
+ - Precision: 0.7375
25
+ - Recall: 0.8605
26
+ - F1: 0.7943
27
+ - Accuracy: 0.9573
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: 16
48
+ - eval_batch_size: 64
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 | Precision | Recall | F1 | Accuracy |
57
+ |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
+ | 0.7665 | 1.0 | 528 | 0.4290 | 0.3803 | 0.1255 | 0.1887 | 0.8711 |
59
+ | 0.336 | 2.0 | 1056 | 0.2177 | 0.6187 | 0.7751 | 0.6882 | 0.9335 |
60
+ | 0.2067 | 3.0 | 1584 | 0.1743 | 0.6523 | 0.8187 | 0.7261 | 0.9410 |
61
+ | 0.1734 | 4.0 | 2112 | 0.1525 | 0.7026 | 0.8443 | 0.7670 | 0.9500 |
62
+ | 0.1557 | 5.0 | 2640 | 0.1442 | 0.7125 | 0.8512 | 0.7757 | 0.9524 |
63
+ | 0.146 | 6.0 | 3168 | 0.1445 | 0.7085 | 0.8629 | 0.7781 | 0.9520 |
64
+ | 0.1397 | 7.0 | 3696 | 0.1444 | 0.7145 | 0.8768 | 0.7874 | 0.9525 |
65
+ | 0.1338 | 8.0 | 4224 | 0.1386 | 0.7262 | 0.8675 | 0.7906 | 0.9545 |
66
+ | 0.1277 | 9.0 | 4752 | 0.1365 | 0.7395 | 0.8629 | 0.7965 | 0.9561 |
67
+ | 0.1255 | 10.0 | 5280 | 0.1332 | 0.7348 | 0.8629 | 0.7937 | 0.9563 |
68
+ | 0.1215 | 11.0 | 5808 | 0.1330 | 0.7242 | 0.8652 | 0.7885 | 0.9557 |
69
+ | 0.1189 | 12.0 | 6336 | 0.1340 | 0.7342 | 0.8652 | 0.7943 | 0.9561 |
70
+ | 0.1179 | 13.0 | 6864 | 0.1295 | 0.7445 | 0.8582 | 0.7973 | 0.9571 |
71
+ | 0.114 | 14.0 | 7392 | 0.1295 | 0.7446 | 0.8675 | 0.8014 | 0.9579 |
72
+ | 0.1128 | 15.0 | 7920 | 0.1317 | 0.7371 | 0.8652 | 0.7960 | 0.9571 |
73
+ | 0.1115 | 16.0 | 8448 | 0.1300 | 0.7376 | 0.8675 | 0.7973 | 0.9575 |
74
+ | 0.1109 | 17.0 | 8976 | 0.1307 | 0.7357 | 0.8652 | 0.7952 | 0.9577 |
75
+ | 0.1097 | 18.0 | 9504 | 0.1319 | 0.7386 | 0.8652 | 0.7969 | 0.9575 |
76
+ | 0.1086 | 19.0 | 10032 | 0.1296 | 0.7375 | 0.8605 | 0.7943 | 0.9573 |
77
+ | 0.1094 | 20.0 | 10560 | 0.1302 | 0.7375 | 0.8605 | 0.7943 | 0.9573 |
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
nerugm-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": "BertForTokenClassification",
22
+ "model_name": "indolem/indobert-base-uncased",
23
+ "model_type": "bert",
24
+ "name": "nerugm-lora",
25
+ "version": "0.2.0"
26
+ }
nerugm-lora/head_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": null,
3
+ "hidden_size": 768,
4
+ "label2id": {
5
+ "B-LOCATION": 0,
6
+ "B-ORGANIZATION": 1,
7
+ "B-PERSON": 2,
8
+ "B-QUANTITY": 3,
9
+ "B-TIME": 4,
10
+ "I-LOCATION": 5,
11
+ "I-ORGANIZATION": 6,
12
+ "I-PERSON": 7,
13
+ "I-QUANTITY": 8,
14
+ "I-TIME": 9,
15
+ "O": 10
16
+ },
17
+ "model_class": "BertForTokenClassification",
18
+ "model_name": "indolem/indobert-base-uncased",
19
+ "model_type": "bert",
20
+ "name": null,
21
+ "num_labels": 11,
22
+ "version": "0.2.0"
23
+ }
nerugm-lora/pytorch_adapter.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1537ed6a03bc7a6bf89d4c7810a1d053d53375a539ab40fec690b4d03c4669d9
3
+ size 607526
nerugm-lora/pytorch_model_head.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:293823b3258bbd9939262d046c51ecbd1573820021237073c9671443d998980c
3
+ size 35354
runs/May24_23-19-08_indolem-petl-vm/events.out.tfevents.1716592755.indolem-petl-vm.1782730.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b1c976bc3c1fc0114aac2306dcd3b5c61c5668005a425e4c01f3c1860bbd127
3
- size 18199
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca5623f303d8d1a2110893550fe8c6c40e7fe4f07fea0e0cea11c7cd3d874ece
3
+ size 19236