kavg commited on
Commit
f60d847
1 Parent(s): aff6379

LiLT-RE-SIN

Browse files
.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 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: nielsr/lilt-xlm-roberta-base
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - xfun
8
+ metrics:
9
+ - precision
10
+ - recall
11
+ - f1
12
+ model-index:
13
+ - name: checkpoints
14
+ results: []
15
+ ---
16
+
17
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
+ should probably proofread and complete it, then remove this comment. -->
19
+
20
+ # checkpoints
21
+
22
+ This model is a fine-tuned version of [nielsr/lilt-xlm-roberta-base](https://huggingface.co/nielsr/lilt-xlm-roberta-base) on the xfun dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Precision: 0.2809
25
+ - Recall: 0.5051
26
+ - F1: 0.3610
27
+ - Loss: 1.6168
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: 1e-05
47
+ - train_batch_size: 8
48
+ - eval_batch_size: 2
49
+ - seed: 42
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - lr_scheduler_warmup_ratio: 0.1
53
+ - training_steps: 8000
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | F1 | Validation Loss | Precision | Recall |
58
+ |:-------------:|:------:|:----:|:------:|:---------------:|:---------:|:------:|
59
+ | 0.1546 | 41.67 | 500 | 0 | 0.2482 | 0 | 0 |
60
+ | 0.1674 | 83.33 | 1000 | 0 | 0.2477 | 0 | 0 |
61
+ | 0.1368 | 125.0 | 1500 | 0.1502 | 0.2256 | 0.1975 | 0.1212 |
62
+ | 0.0727 | 166.67 | 2000 | 0.2732 | 0.3218 | 0.2091 | 0.3939 |
63
+ | 0.0718 | 208.33 | 2500 | 0.3385 | 0.3518 | 0.2579 | 0.4924 |
64
+ | 0.0612 | 250.0 | 3000 | 0.3371 | 0.5235 | 0.2555 | 0.4949 |
65
+ | 0.0504 | 291.67 | 3500 | 0.3353 | 0.5280 | 0.2536 | 0.4949 |
66
+ | 0.0418 | 333.33 | 4000 | 0.3476 | 0.6919 | 0.2657 | 0.5025 |
67
+ | 0.0308 | 375.0 | 4500 | 0.3490 | 0.7819 | 0.2613 | 0.5253 |
68
+ | 0.039 | 416.67 | 5000 | 0.3463 | 1.0291 | 0.2627 | 0.5076 |
69
+ | 0.0301 | 458.33 | 5500 | 0.3443 | 1.1661 | 0.2626 | 0.5 |
70
+ | 0.0245 | 500.0 | 6000 | 0.3414 | 1.2341 | 0.2642 | 0.4823 |
71
+ | 0.0347 | 541.67 | 6500 | 0.3389 | 1.4114 | 0.2605 | 0.4848 |
72
+ | 0.0327 | 583.33 | 7000 | 0.3422 | 1.4326 | 0.2683 | 0.4722 |
73
+ | 0.0117 | 625.0 | 7500 | 0.3670 | 1.6092 | 0.2899 | 0.5 |
74
+ | 0.0255 | 666.67 | 8000 | 0.3607 | 1.6141 | 0.2805 | 0.5051 |
75
+
76
+
77
+ ### Framework versions
78
+
79
+ - Transformers 4.38.2
80
+ - Pytorch 2.1.0+cu121
81
+ - Datasets 2.18.0
82
+ - Tokenizers 0.15.1
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nielsr/lilt-xlm-roberta-base",
3
+ "architectures": [
4
+ "LiLTRobertaLikeForRelationExtraction"
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
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_2d_position_embeddings": 1024,
18
+ "max_position_embeddings": 514,
19
+ "model_type": "lilt",
20
+ "num_attention_heads": 12,
21
+ "num_hidden_layers": 12,
22
+ "output_past": true,
23
+ "pad_token_id": 1,
24
+ "position_embedding_type": "absolute",
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.38.2",
27
+ "type_vocab_size": 1,
28
+ "use_cache": true,
29
+ "vocab_size": 250002
30
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:277fc6848a9f836f49b1fd72fe7d4c892bcf034ade343ff49de77dd50fd76fe8
3
+ size 1147300280
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:f59925fcb90c92b894cb93e51bb9b4a6105c5c249fe54ce1c704420ac39b81af
3
+ size 17082756
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 sha256:799d79773b8b2db0372e5c773489525af868ae29ba8f2a4e9fcace586608d453
3
+ size 5048