lilt-xlm-roberta-1
Browse files- .gitattributes +1 -0
- README.md +87 -0
- config.json +39 -0
- model.safetensors +3 -0
- runs/May23_06-54-21_142600b4fecf/events.out.tfevents.1716447273.142600b4fecf.3462.0 +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +3 -0
- tokenizer_config.json +54 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: nielsr/lilt-xlm-roberta-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: test
|
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 |
+
# test
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [nielsr/lilt-xlm-roberta-base](https://huggingface.co/nielsr/lilt-xlm-roberta-base) on an unknown dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 1.6527
|
24 |
+
- Precision: 0.7393
|
25 |
+
- Recall: 0.7759
|
26 |
+
- F1: 0.7571
|
27 |
+
- Accuracy: 0.7614
|
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: 8
|
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: 30
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
+
|:-------------:|:-------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
+
| No log | 1.3333 | 100 | 0.9776 | 0.4894 | 0.6113 | 0.5436 | 0.6166 |
|
59 |
+
| No log | 2.6667 | 200 | 0.8649 | 0.6249 | 0.6296 | 0.6273 | 0.7231 |
|
60 |
+
| No log | 4.0 | 300 | 0.8745 | 0.6449 | 0.7392 | 0.6888 | 0.7326 |
|
61 |
+
| No log | 5.3333 | 400 | 0.9419 | 0.6292 | 0.7168 | 0.6702 | 0.7367 |
|
62 |
+
| 0.6362 | 6.6667 | 500 | 0.9902 | 0.7090 | 0.7458 | 0.7269 | 0.7700 |
|
63 |
+
| 0.6362 | 8.0 | 600 | 1.0048 | 0.7050 | 0.7315 | 0.7180 | 0.7614 |
|
64 |
+
| 0.6362 | 9.3333 | 700 | 1.1327 | 0.6918 | 0.7305 | 0.7106 | 0.7568 |
|
65 |
+
| 0.6362 | 10.6667 | 800 | 1.3954 | 0.6952 | 0.7366 | 0.7153 | 0.7333 |
|
66 |
+
| 0.6362 | 12.0 | 900 | 1.2721 | 0.7002 | 0.7509 | 0.7247 | 0.7491 |
|
67 |
+
| 0.1105 | 13.3333 | 1000 | 1.3422 | 0.7166 | 0.7356 | 0.7260 | 0.7521 |
|
68 |
+
| 0.1105 | 14.6667 | 1100 | 1.3957 | 0.72 | 0.7427 | 0.7312 | 0.7605 |
|
69 |
+
| 0.1105 | 16.0 | 1200 | 1.4581 | 0.7250 | 0.7519 | 0.7382 | 0.7608 |
|
70 |
+
| 0.1105 | 17.3333 | 1300 | 1.4598 | 0.7459 | 0.7371 | 0.7415 | 0.7577 |
|
71 |
+
| 0.1105 | 18.6667 | 1400 | 1.5542 | 0.7182 | 0.7504 | 0.7339 | 0.7497 |
|
72 |
+
| 0.0271 | 20.0 | 1500 | 1.5411 | 0.7176 | 0.7779 | 0.7465 | 0.7549 |
|
73 |
+
| 0.0271 | 21.3333 | 1600 | 1.6468 | 0.7251 | 0.7539 | 0.7393 | 0.7452 |
|
74 |
+
| 0.0271 | 22.6667 | 1700 | 1.6821 | 0.7311 | 0.7550 | 0.7429 | 0.7487 |
|
75 |
+
| 0.0271 | 24.0 | 1800 | 1.6220 | 0.7364 | 0.7499 | 0.7431 | 0.7585 |
|
76 |
+
| 0.0271 | 25.3333 | 1900 | 1.6220 | 0.7403 | 0.7667 | 0.7533 | 0.7599 |
|
77 |
+
| 0.0055 | 26.6667 | 2000 | 1.6161 | 0.7370 | 0.7682 | 0.7523 | 0.7687 |
|
78 |
+
| 0.0055 | 28.0 | 2100 | 1.6683 | 0.7396 | 0.7713 | 0.7551 | 0.7599 |
|
79 |
+
| 0.0055 | 29.3333 | 2200 | 1.6527 | 0.7393 | 0.7759 | 0.7571 | 0.7614 |
|
80 |
+
|
81 |
+
|
82 |
+
### Framework versions
|
83 |
+
|
84 |
+
- Transformers 4.41.0
|
85 |
+
- Pytorch 2.3.0+cu121
|
86 |
+
- Datasets 2.19.1
|
87 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "nielsr/lilt-xlm-roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"LiltForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"channel_shrink_ratio": 4,
|
9 |
+
"classifier_dropout": null,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "O",
|
16 |
+
"1": "B-HEADER",
|
17 |
+
"2": "I-HEADER",
|
18 |
+
"3": "B-QUESTION",
|
19 |
+
"4": "I-QUESTION",
|
20 |
+
"5": "B-ANSWER",
|
21 |
+
"6": "I-ANSWER"
|
22 |
+
},
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"intermediate_size": 3072,
|
25 |
+
"layer_norm_eps": 1e-05,
|
26 |
+
"max_2d_position_embeddings": 1024,
|
27 |
+
"max_position_embeddings": 514,
|
28 |
+
"model_type": "lilt",
|
29 |
+
"num_attention_heads": 12,
|
30 |
+
"num_hidden_layers": 12,
|
31 |
+
"output_past": true,
|
32 |
+
"pad_token_id": 1,
|
33 |
+
"position_embedding_type": "absolute",
|
34 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.41.0",
|
36 |
+
"type_vocab_size": 1,
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 250002
|
39 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7161fd1865270b3a1b2dcf48b3cfb6f144ad9f414985aefaa89518d3121f501e
|
3 |
+
size 1134319924
|
runs/May23_06-54-21_142600b4fecf/events.out.tfevents.1716447273.142600b4fecf.3462.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebbffe79183779cbce7199db05195de1c74c048e6a2d54108b74ca0276002ab2
|
3 |
+
size 16630
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
|
3 |
+
size 17082832
|
tokenizer_config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"250001": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "<s>",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "<s>",
|
47 |
+
"eos_token": "</s>",
|
48 |
+
"mask_token": "<mask>",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"pad_token": "<pad>",
|
51 |
+
"sep_token": "</s>",
|
52 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
53 |
+
"unk_token": "<unk>"
|
54 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49d408cbea66f4f4378b28ea2c4a270244367bc182e1bce2b998bf6f1bbe209e
|
3 |
+
size 5048
|