kavg commited on
Commit
8d1ee91
1 Parent(s): 7846422

End of training

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 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ - accuracy
13
+ model-index:
14
+ - name: LiLT-SER-IT
15
+ results:
16
+ - task:
17
+ name: Token Classification
18
+ type: token-classification
19
+ dataset:
20
+ name: xfun
21
+ type: xfun
22
+ config: xfun.it
23
+ split: validation
24
+ args: xfun.it
25
+ metrics:
26
+ - name: Precision
27
+ type: precision
28
+ value: 0.726186733731531
29
+ - name: Recall
30
+ type: recall
31
+ value: 0.7927247769389156
32
+ - name: F1
33
+ type: f1
34
+ value: 0.7579983593109106
35
+ - name: Accuracy
36
+ type: accuracy
37
+ value: 0.768676917924818
38
+ ---
39
+
40
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
41
+ should probably proofread and complete it, then remove this comment. -->
42
+
43
+ # LiLT-SER-IT
44
+
45
+ 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.
46
+ It achieves the following results on the evaluation set:
47
+ - Loss: 2.5355
48
+ - Precision: 0.7262
49
+ - Recall: 0.7927
50
+ - F1: 0.7580
51
+ - Accuracy: 0.7687
52
+
53
+ ## Model description
54
+
55
+ More information needed
56
+
57
+ ## Intended uses & limitations
58
+
59
+ More information needed
60
+
61
+ ## Training and evaluation data
62
+
63
+ More information needed
64
+
65
+ ## Training procedure
66
+
67
+ ### Training hyperparameters
68
+
69
+ The following hyperparameters were used during training:
70
+ - learning_rate: 5e-05
71
+ - train_batch_size: 8
72
+ - eval_batch_size: 2
73
+ - seed: 42
74
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
75
+ - lr_scheduler_type: linear
76
+ - training_steps: 10000
77
+
78
+ ### Training results
79
+
80
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
+ |:-------------:|:------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
+ | 0.0696 | 7.46 | 500 | 1.0876 | 0.6322 | 0.6517 | 0.6418 | 0.7584 |
83
+ | 0.0576 | 14.93 | 1000 | 1.3989 | 0.6712 | 0.7601 | 0.7129 | 0.7601 |
84
+ | 0.0096 | 22.39 | 1500 | 1.8059 | 0.6774 | 0.7639 | 0.7181 | 0.7662 |
85
+ | 0.0092 | 29.85 | 2000 | 2.0416 | 0.7266 | 0.7334 | 0.7300 | 0.7652 |
86
+ | 0.0003 | 37.31 | 2500 | 2.0467 | 0.7166 | 0.7539 | 0.7348 | 0.7628 |
87
+ | 0.0013 | 44.78 | 3000 | 2.0159 | 0.7027 | 0.7821 | 0.7403 | 0.7638 |
88
+ | 0.0013 | 52.24 | 3500 | 2.2751 | 0.6961 | 0.7728 | 0.7325 | 0.7575 |
89
+ | 0.0002 | 59.7 | 4000 | 2.2084 | 0.7236 | 0.7563 | 0.7396 | 0.7723 |
90
+ | 0.0002 | 67.16 | 4500 | 2.1843 | 0.7048 | 0.7701 | 0.7360 | 0.7581 |
91
+ | 0.0001 | 74.63 | 5000 | 2.2483 | 0.7366 | 0.7745 | 0.7551 | 0.7770 |
92
+ | 0.0001 | 82.09 | 5500 | 2.2685 | 0.7171 | 0.7752 | 0.7451 | 0.7677 |
93
+ | 0.0005 | 89.55 | 6000 | 2.2877 | 0.7180 | 0.7821 | 0.7487 | 0.7692 |
94
+ | 0.0001 | 97.01 | 6500 | 2.2574 | 0.7308 | 0.7725 | 0.7511 | 0.7721 |
95
+ | 0.0 | 104.48 | 7000 | 2.4696 | 0.7255 | 0.7862 | 0.7546 | 0.7660 |
96
+ | 0.0 | 111.94 | 7500 | 2.3996 | 0.7140 | 0.7917 | 0.7509 | 0.7725 |
97
+ | 0.0 | 119.4 | 8000 | 2.4592 | 0.7261 | 0.7852 | 0.7545 | 0.7665 |
98
+ | 0.0 | 126.87 | 8500 | 2.4129 | 0.7336 | 0.7900 | 0.7607 | 0.7718 |
99
+ | 0.0 | 134.33 | 9000 | 2.5367 | 0.7316 | 0.7896 | 0.7595 | 0.7666 |
100
+ | 0.0 | 141.79 | 9500 | 2.5327 | 0.7278 | 0.7900 | 0.7576 | 0.7663 |
101
+ | 0.0 | 149.25 | 10000 | 2.5355 | 0.7262 | 0.7927 | 0.7580 | 0.7687 |
102
+
103
+
104
+ ### Framework versions
105
+
106
+ - Transformers 4.38.2
107
+ - Pytorch 2.1.0+cu121
108
+ - Datasets 2.18.0
109
+ - Tokenizers 0.15.1
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-QUESTION",
17
+ "2": "B-ANSWER",
18
+ "3": "B-HEADER",
19
+ "4": "I-ANSWER",
20
+ "5": "I-QUESTION",
21
+ "6": "I-HEADER"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "B-ANSWER": 2,
27
+ "B-HEADER": 3,
28
+ "B-QUESTION": 1,
29
+ "I-ANSWER": 4,
30
+ "I-HEADER": 6,
31
+ "I-QUESTION": 5,
32
+ "O": 0
33
+ },
34
+ "layer_norm_eps": 1e-05,
35
+ "max_2d_position_embeddings": 1024,
36
+ "max_position_embeddings": 514,
37
+ "model_type": "lilt",
38
+ "num_attention_heads": 12,
39
+ "num_hidden_layers": 12,
40
+ "output_past": true,
41
+ "pad_token_id": 1,
42
+ "position_embedding_type": "absolute",
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.38.2",
45
+ "type_vocab_size": 1,
46
+ "use_cache": true,
47
+ "vocab_size": 250002
48
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dfffe604006b01517859cd4532faef21fbb1f445f080187437a5a3127b589b1
3
+ size 1134319924
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 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "max_length": 512,
50
+ "model_max_length": 512,
51
+ "pad_token": "<pad>",
52
+ "sep_token": "</s>",
53
+ "tokenizer_class": "XLMRobertaTokenizer",
54
+ "unk_token": "<unk>"
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02f145427418280474775071744bef2612f15a6a880862fb4b0e6f2c11fcbe38
3
+ size 5048