phunganhsang commited on
Commit
77b85ad
1 Parent(s): 2df6ea2

End of training

Browse files
README.md ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: agpl-3.0
4
+ base_model: vinai/phobert-base-v2
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ - f1
10
+ model-index:
11
+ - name: PhoBert_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
+ # PhoBert_Lexical_Dataset45K
19
+
20
+ This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on an unknown dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.4880
23
+ - Accuracy: 0.8851
24
+ - F1: 0.8858
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 | 0.3476 | 0.8474 | 0.8494 |
56
+ | No log | 0.5682 | 400 | 0.3035 | 0.8692 | 0.8703 |
57
+ | No log | 0.8523 | 600 | 0.3132 | 0.8654 | 0.8674 |
58
+ | 0.3678 | 1.1364 | 800 | 0.2832 | 0.8797 | 0.8797 |
59
+ | 0.3678 | 1.4205 | 1000 | 0.2805 | 0.8828 | 0.8815 |
60
+ | 0.3678 | 1.7045 | 1200 | 0.2622 | 0.8862 | 0.8874 |
61
+ | 0.3678 | 1.9886 | 1400 | 0.2751 | 0.8898 | 0.8889 |
62
+ | 0.2662 | 2.2727 | 1600 | 0.2627 | 0.8873 | 0.8886 |
63
+ | 0.2662 | 2.5568 | 1800 | 0.2514 | 0.8945 | 0.8940 |
64
+ | 0.2662 | 2.8409 | 2000 | 0.2433 | 0.8941 | 0.8949 |
65
+ | 0.219 | 3.125 | 2200 | 0.2600 | 0.8914 | 0.8922 |
66
+ | 0.219 | 3.4091 | 2400 | 0.2563 | 0.8933 | 0.8937 |
67
+ | 0.219 | 3.6932 | 2600 | 0.2592 | 0.8909 | 0.8919 |
68
+ | 0.219 | 3.9773 | 2800 | 0.2390 | 0.8969 | 0.8974 |
69
+ | 0.1865 | 4.2614 | 3000 | 0.2925 | 0.8820 | 0.8834 |
70
+ | 0.1865 | 4.5455 | 3200 | 0.2922 | 0.8871 | 0.8883 |
71
+ | 0.1865 | 4.8295 | 3400 | 0.2975 | 0.8838 | 0.8854 |
72
+ | 0.1591 | 5.1136 | 3600 | 0.2935 | 0.8920 | 0.8926 |
73
+ | 0.1591 | 5.3977 | 3800 | 0.2860 | 0.8893 | 0.8901 |
74
+ | 0.1591 | 5.6818 | 4000 | 0.2943 | 0.8939 | 0.8940 |
75
+ | 0.1591 | 5.9659 | 4200 | 0.2898 | 0.8970 | 0.8973 |
76
+ | 0.1394 | 6.25 | 4400 | 0.3268 | 0.8886 | 0.8886 |
77
+ | 0.1394 | 6.5341 | 4600 | 0.3399 | 0.8804 | 0.8820 |
78
+ | 0.1394 | 6.8182 | 4800 | 0.3353 | 0.8887 | 0.8894 |
79
+ | 0.1159 | 7.1023 | 5000 | 0.3313 | 0.8950 | 0.8956 |
80
+ | 0.1159 | 7.3864 | 5200 | 0.3496 | 0.8955 | 0.8956 |
81
+ | 0.1159 | 7.6705 | 5400 | 0.3509 | 0.8920 | 0.8925 |
82
+ | 0.1159 | 7.9545 | 5600 | 0.3534 | 0.8842 | 0.8855 |
83
+ | 0.1005 | 8.2386 | 5800 | 0.3529 | 0.8932 | 0.8936 |
84
+ | 0.1005 | 8.5227 | 6000 | 0.3641 | 0.8914 | 0.8916 |
85
+ | 0.1005 | 8.8068 | 6200 | 0.3572 | 0.8907 | 0.8911 |
86
+ | 0.0838 | 9.0909 | 6400 | 0.4026 | 0.8873 | 0.8873 |
87
+ | 0.0838 | 9.375 | 6600 | 0.4049 | 0.8869 | 0.8876 |
88
+ | 0.0838 | 9.6591 | 6800 | 0.4024 | 0.8808 | 0.8822 |
89
+ | 0.0838 | 9.9432 | 7000 | 0.4161 | 0.8874 | 0.8886 |
90
+ | 0.0732 | 10.2273 | 7200 | 0.4098 | 0.8881 | 0.8885 |
91
+ | 0.0732 | 10.5114 | 7400 | 0.4010 | 0.8880 | 0.8885 |
92
+ | 0.0732 | 10.7955 | 7600 | 0.4166 | 0.8890 | 0.8891 |
93
+ | 0.0616 | 11.0795 | 7800 | 0.4317 | 0.8853 | 0.8859 |
94
+ | 0.0616 | 11.3636 | 8000 | 0.4323 | 0.8878 | 0.8884 |
95
+ | 0.0616 | 11.6477 | 8200 | 0.4550 | 0.8862 | 0.8872 |
96
+ | 0.0616 | 11.9318 | 8400 | 0.4509 | 0.8882 | 0.8890 |
97
+ | 0.0547 | 12.2159 | 8600 | 0.4463 | 0.8871 | 0.8877 |
98
+ | 0.0547 | 12.5 | 8800 | 0.4705 | 0.8842 | 0.8849 |
99
+ | 0.0547 | 12.7841 | 9000 | 0.4663 | 0.8876 | 0.8880 |
100
+ | 0.0472 | 13.0682 | 9200 | 0.4825 | 0.8867 | 0.8876 |
101
+ | 0.0472 | 13.3523 | 9400 | 0.4796 | 0.8858 | 0.8864 |
102
+ | 0.0472 | 13.6364 | 9600 | 0.4856 | 0.8853 | 0.8862 |
103
+ | 0.0472 | 13.9205 | 9800 | 0.4896 | 0.8840 | 0.8851 |
104
+ | 0.0433 | 14.2045 | 10000 | 0.4810 | 0.8859 | 0.8864 |
105
+ | 0.0433 | 14.4886 | 10200 | 0.4900 | 0.8842 | 0.8851 |
106
+ | 0.0433 | 14.7727 | 10400 | 0.4880 | 0.8851 | 0.8858 |
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
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<mask>": 64000
3
+ }
bpe.codes ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "vinai/phobert-base-v2",
3
+ "architectures": [
4
+ "PhoBertLexical"
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": 258,
25
+ "model_type": "roberta",
26
+ "num_attention_heads": 12,
27
+ "num_classes": 2,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 1,
30
+ "position_embedding_type": "absolute",
31
+ "tokenizer_class": "PhobertTokenizer",
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.44.2",
34
+ "type_vocab_size": 1,
35
+ "use_cache": true,
36
+ "vocab_size": 64001
37
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66bf97a0d03400e94ef827ea14b689f5f1d371ff76d7964ccf21114b445affab
3
+ size 538468008
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "pad_token": "<pad>",
7
+ "sep_token": "</s>",
8
+ "unk_token": "<unk>"
9
+ }
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
+ "64000": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
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": 1000000000000000019884624838656,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "tokenizer_class": "PhobertTokenizer",
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:b5ca6b40e044ac8c03746c84895aaa1c4a450d33e9ad6858384f8d18dc8910cc
3
+ size 5176
vocab.txt ADDED
The diff for this file is too large to render. See raw diff