phunganhsang commited on
Commit
a3b4bbc
1 Parent(s): 1e3482a

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 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: FacebookAI/xlm-roberta-base
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ - f1
10
+ model-index:
11
+ - name: XLMRoBERTa_Lexical_Dataset45K
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # XLMRoBERTa_Lexical_Dataset45K
19
+
20
+ This model is a fine-tuned version of [FacebookAI/xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base) on an unknown dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.4964
23
+ - Accuracy: 0.8870
24
+ - F1: 0.8870
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 2e-05
44
+ - train_batch_size: 64
45
+ - eval_batch_size: 64
46
+ - seed: 42
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: linear
49
+ - num_epochs: 15
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
54
+ |:-------------:|:-------:|:-----:|:---------------:|:--------:|:------:|
55
+ | No log | 0.2841 | 200 | 0.4614 | 0.7988 | 0.7972 |
56
+ | No log | 0.5682 | 400 | 0.3716 | 0.8339 | 0.8335 |
57
+ | No log | 0.8523 | 600 | 0.3603 | 0.8456 | 0.8474 |
58
+ | 0.455 | 1.1364 | 800 | 0.3298 | 0.8618 | 0.8612 |
59
+ | 0.455 | 1.4205 | 1000 | 0.3466 | 0.8621 | 0.8598 |
60
+ | 0.455 | 1.7045 | 1200 | 0.3051 | 0.8697 | 0.8712 |
61
+ | 0.455 | 1.9886 | 1400 | 0.2924 | 0.8773 | 0.8774 |
62
+ | 0.3111 | 2.2727 | 1600 | 0.2764 | 0.8847 | 0.8853 |
63
+ | 0.3111 | 2.5568 | 1800 | 0.2648 | 0.8865 | 0.8866 |
64
+ | 0.3111 | 2.8409 | 2000 | 0.2571 | 0.8890 | 0.8894 |
65
+ | 0.2536 | 3.125 | 2200 | 0.2745 | 0.8901 | 0.8898 |
66
+ | 0.2536 | 3.4091 | 2400 | 0.2801 | 0.8729 | 0.8747 |
67
+ | 0.2536 | 3.6932 | 2600 | 0.2863 | 0.8892 | 0.8885 |
68
+ | 0.2536 | 3.9773 | 2800 | 0.2587 | 0.8909 | 0.8902 |
69
+ | 0.2249 | 4.2614 | 3000 | 0.2728 | 0.8905 | 0.8903 |
70
+ | 0.2249 | 4.5455 | 3200 | 0.2782 | 0.8873 | 0.8882 |
71
+ | 0.2249 | 4.8295 | 3400 | 0.2696 | 0.8900 | 0.8908 |
72
+ | 0.1984 | 5.1136 | 3600 | 0.3226 | 0.8896 | 0.8890 |
73
+ | 0.1984 | 5.3977 | 3800 | 0.2821 | 0.8921 | 0.8923 |
74
+ | 0.1984 | 5.6818 | 4000 | 0.3206 | 0.8818 | 0.8830 |
75
+ | 0.1984 | 5.9659 | 4200 | 0.2800 | 0.8938 | 0.8936 |
76
+ | 0.178 | 6.25 | 4400 | 0.2892 | 0.8938 | 0.8938 |
77
+ | 0.178 | 6.5341 | 4600 | 0.3262 | 0.8875 | 0.8880 |
78
+ | 0.178 | 6.8182 | 4800 | 0.3199 | 0.8876 | 0.8874 |
79
+ | 0.1556 | 7.1023 | 5000 | 0.3237 | 0.8889 | 0.8892 |
80
+ | 0.1556 | 7.3864 | 5200 | 0.3540 | 0.8883 | 0.8880 |
81
+ | 0.1556 | 7.6705 | 5400 | 0.3361 | 0.8925 | 0.8925 |
82
+ | 0.1556 | 7.9545 | 5600 | 0.3369 | 0.8868 | 0.8877 |
83
+ | 0.1344 | 8.2386 | 5800 | 0.3449 | 0.8889 | 0.8887 |
84
+ | 0.1344 | 8.5227 | 6000 | 0.3813 | 0.8888 | 0.8884 |
85
+ | 0.1344 | 8.8068 | 6200 | 0.3463 | 0.8908 | 0.8910 |
86
+ | 0.1203 | 9.0909 | 6400 | 0.3781 | 0.8886 | 0.8893 |
87
+ | 0.1203 | 9.375 | 6600 | 0.3825 | 0.8897 | 0.8897 |
88
+ | 0.1203 | 9.6591 | 6800 | 0.3842 | 0.8890 | 0.8895 |
89
+ | 0.1203 | 9.9432 | 7000 | 0.3894 | 0.8885 | 0.8893 |
90
+ | 0.1069 | 10.2273 | 7200 | 0.4063 | 0.8903 | 0.8900 |
91
+ | 0.1069 | 10.5114 | 7400 | 0.3976 | 0.8908 | 0.8912 |
92
+ | 0.1069 | 10.7955 | 7600 | 0.4013 | 0.8892 | 0.8893 |
93
+ | 0.0942 | 11.0795 | 7800 | 0.4663 | 0.8888 | 0.8886 |
94
+ | 0.0942 | 11.3636 | 8000 | 0.4394 | 0.8867 | 0.8871 |
95
+ | 0.0942 | 11.6477 | 8200 | 0.4770 | 0.8852 | 0.8859 |
96
+ | 0.0942 | 11.9318 | 8400 | 0.4278 | 0.8881 | 0.8881 |
97
+ | 0.0827 | 12.2159 | 8600 | 0.4431 | 0.8874 | 0.8877 |
98
+ | 0.0827 | 12.5 | 8800 | 0.4553 | 0.8851 | 0.8856 |
99
+ | 0.0827 | 12.7841 | 9000 | 0.4546 | 0.8859 | 0.8861 |
100
+ | 0.0772 | 13.0682 | 9200 | 0.4571 | 0.8883 | 0.8881 |
101
+ | 0.0772 | 13.3523 | 9400 | 0.4655 | 0.8872 | 0.8870 |
102
+ | 0.0772 | 13.6364 | 9600 | 0.4700 | 0.8872 | 0.8876 |
103
+ | 0.0772 | 13.9205 | 9800 | 0.4817 | 0.8863 | 0.8867 |
104
+ | 0.0692 | 14.2045 | 10000 | 0.4838 | 0.8864 | 0.8868 |
105
+ | 0.0692 | 14.4886 | 10200 | 0.4825 | 0.8868 | 0.8871 |
106
+ | 0.0692 | 14.7727 | 10400 | 0.4964 | 0.8870 | 0.8870 |
107
+
108
+
109
+ ### Framework versions
110
+
111
+ - Transformers 4.44.2
112
+ - Pytorch 2.1.2
113
+ - Datasets 2.20.0
114
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "FacebookAI/xlm-roberta-base",
3
+ "architectures": [
4
+ "XLMLexical"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "B\u00ecnh th\u01b0\u1eddng",
15
+ "1": "T\u00ednh nhi\u1ec7m th\u1ea5p"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "B\u00ecnh th\u01b0\u1eddng": 0,
21
+ "T\u00ednh nhi\u1ec7m th\u1ea5p": 1
22
+ },
23
+ "layer_norm_eps": 1e-05,
24
+ "max_position_embeddings": 514,
25
+ "model_type": "xlm-roberta",
26
+ "num_attention_heads": 12,
27
+ "num_classes": 2,
28
+ "num_hidden_layers": 12,
29
+ "output_past": true,
30
+ "pad_token_id": 1,
31
+ "position_embedding_type": "absolute",
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.44.2",
34
+ "type_vocab_size": 1,
35
+ "use_cache": true,
36
+ "vocab_size": 250002
37
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3353ec210036d9cd4630ac5f2a3767d7a88b46710d0d00893eee0accdec32cc4
3
+ size 1110649624
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1742a608da1249ee2a11741fd2fdb9bc0c4ec18330f7ec4e863ba7cc6e4185ac
3
+ size 17082986
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 sha256:78b020103431ae0fc8a14065b4a3670ae9c07d1ac2ed2d226dee2c113410620e
3
+ size 5176