gechim commited on
Commit
1acecb8
1 Parent(s): 9798c5f

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 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: FacebookAI/xlm-roberta-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ - f1
9
+ model-index:
10
+ - name: XMLRoberta_Lexical_Dataset59KBoDuoi
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # XMLRoberta_Lexical_Dataset59KBoDuoi
18
+
19
+ This model is a fine-tuned version of [FacebookAI/xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.6232
22
+ - Accuracy: 0.8988
23
+ - F1: 0.8992
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 2e-05
43
+ - train_batch_size: 64
44
+ - eval_batch_size: 64
45
+ - seed: 42
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - num_epochs: 20
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
53
+ |:-------------:|:-------:|:-----:|:---------------:|:--------:|:------:|
54
+ | No log | 0.2558 | 200 | 0.4593 | 0.7916 | 0.7880 |
55
+ | No log | 0.5115 | 400 | 0.3779 | 0.8222 | 0.8249 |
56
+ | No log | 0.7673 | 600 | 0.3462 | 0.8514 | 0.8497 |
57
+ | 0.4345 | 1.0230 | 800 | 0.3543 | 0.8554 | 0.8513 |
58
+ | 0.4345 | 1.2788 | 1000 | 0.3504 | 0.8573 | 0.8537 |
59
+ | 0.4345 | 1.5345 | 1200 | 0.3033 | 0.8767 | 0.8772 |
60
+ | 0.4345 | 1.7903 | 1400 | 0.2834 | 0.8778 | 0.8788 |
61
+ | 0.3071 | 2.0460 | 1600 | 0.3207 | 0.8671 | 0.8695 |
62
+ | 0.3071 | 2.3018 | 1800 | 0.2959 | 0.8822 | 0.8814 |
63
+ | 0.3071 | 2.5575 | 2000 | 0.2821 | 0.8778 | 0.8781 |
64
+ | 0.3071 | 2.8133 | 2200 | 0.3024 | 0.8872 | 0.8883 |
65
+ | 0.2523 | 3.0691 | 2400 | 0.2972 | 0.8888 | 0.8894 |
66
+ | 0.2523 | 3.3248 | 2600 | 0.2746 | 0.8883 | 0.8891 |
67
+ | 0.2523 | 3.5806 | 2800 | 0.2828 | 0.8909 | 0.8911 |
68
+ | 0.2523 | 3.8363 | 3000 | 0.2822 | 0.8941 | 0.8941 |
69
+ | 0.2177 | 4.0921 | 3200 | 0.2995 | 0.8898 | 0.8910 |
70
+ | 0.2177 | 4.3478 | 3400 | 0.2953 | 0.8887 | 0.8898 |
71
+ | 0.2177 | 4.6036 | 3600 | 0.2944 | 0.8925 | 0.8931 |
72
+ | 0.2177 | 4.8593 | 3800 | 0.3006 | 0.8957 | 0.8958 |
73
+ | 0.189 | 5.1151 | 4000 | 0.2816 | 0.8950 | 0.8955 |
74
+ | 0.189 | 5.3708 | 4200 | 0.2865 | 0.8956 | 0.8960 |
75
+ | 0.189 | 5.6266 | 4400 | 0.2794 | 0.8961 | 0.8966 |
76
+ | 0.189 | 5.8824 | 4600 | 0.2836 | 0.8980 | 0.8986 |
77
+ | 0.1637 | 6.1381 | 4800 | 0.3399 | 0.8949 | 0.8951 |
78
+ | 0.1637 | 6.3939 | 5000 | 0.3248 | 0.8952 | 0.8957 |
79
+ | 0.1637 | 6.6496 | 5200 | 0.3341 | 0.8976 | 0.8979 |
80
+ | 0.1637 | 6.9054 | 5400 | 0.2993 | 0.8962 | 0.8970 |
81
+ | 0.1388 | 7.1611 | 5600 | 0.3662 | 0.8967 | 0.8978 |
82
+ | 0.1388 | 7.4169 | 5800 | 0.3761 | 0.8962 | 0.8968 |
83
+ | 0.1388 | 7.6726 | 6000 | 0.3305 | 0.8953 | 0.8961 |
84
+ | 0.1388 | 7.9284 | 6200 | 0.3328 | 0.8966 | 0.8970 |
85
+ | 0.1193 | 8.1841 | 6400 | 0.3753 | 0.8980 | 0.8985 |
86
+ | 0.1193 | 8.4399 | 6600 | 0.3646 | 0.8974 | 0.8976 |
87
+ | 0.1193 | 8.6957 | 6800 | 0.3800 | 0.8963 | 0.8966 |
88
+ | 0.1193 | 8.9514 | 7000 | 0.3472 | 0.8980 | 0.8987 |
89
+ | 0.1059 | 9.2072 | 7200 | 0.3991 | 0.9002 | 0.9004 |
90
+ | 0.1059 | 9.4629 | 7400 | 0.4026 | 0.8967 | 0.8978 |
91
+ | 0.1059 | 9.7187 | 7600 | 0.3915 | 0.8983 | 0.8983 |
92
+ | 0.1059 | 9.9744 | 7800 | 0.3932 | 0.8997 | 0.8999 |
93
+ | 0.0923 | 10.2302 | 8000 | 0.4887 | 0.8939 | 0.8947 |
94
+ | 0.0923 | 10.4859 | 8200 | 0.4074 | 0.8977 | 0.8981 |
95
+ | 0.0923 | 10.7417 | 8400 | 0.3931 | 0.8998 | 0.9003 |
96
+ | 0.0806 | 10.9974 | 8600 | 0.4131 | 0.8955 | 0.8964 |
97
+ | 0.0806 | 11.2532 | 8800 | 0.4499 | 0.8963 | 0.8970 |
98
+ | 0.0806 | 11.5090 | 9000 | 0.4436 | 0.8999 | 0.9002 |
99
+ | 0.0806 | 11.7647 | 9200 | 0.4842 | 0.8965 | 0.8968 |
100
+ | 0.0697 | 12.0205 | 9400 | 0.4851 | 0.8961 | 0.8963 |
101
+ | 0.0697 | 12.2762 | 9600 | 0.5138 | 0.8999 | 0.9002 |
102
+ | 0.0697 | 12.5320 | 9800 | 0.5020 | 0.8963 | 0.8964 |
103
+ | 0.0697 | 12.7877 | 10000 | 0.5108 | 0.8929 | 0.8940 |
104
+ | 0.064 | 13.0435 | 10200 | 0.4893 | 0.8966 | 0.8968 |
105
+ | 0.064 | 13.2992 | 10400 | 0.5052 | 0.8973 | 0.8980 |
106
+ | 0.064 | 13.5550 | 10600 | 0.4917 | 0.8970 | 0.8971 |
107
+ | 0.064 | 13.8107 | 10800 | 0.5087 | 0.8965 | 0.8968 |
108
+ | 0.0571 | 14.0665 | 11000 | 0.5195 | 0.8970 | 0.8977 |
109
+ | 0.0571 | 14.3223 | 11200 | 0.5279 | 0.8932 | 0.8943 |
110
+ | 0.0571 | 14.5780 | 11400 | 0.5015 | 0.8974 | 0.8978 |
111
+ | 0.0571 | 14.8338 | 11600 | 0.5301 | 0.8961 | 0.8965 |
112
+ | 0.0538 | 15.0895 | 11800 | 0.5297 | 0.8951 | 0.8952 |
113
+ | 0.0538 | 15.3453 | 12000 | 0.5573 | 0.8976 | 0.8980 |
114
+ | 0.0538 | 15.6010 | 12200 | 0.5579 | 0.8955 | 0.8962 |
115
+ | 0.0538 | 15.8568 | 12400 | 0.5814 | 0.8969 | 0.8968 |
116
+ | 0.0481 | 16.1125 | 12600 | 0.5861 | 0.8972 | 0.8974 |
117
+ | 0.0481 | 16.3683 | 12800 | 0.5871 | 0.8968 | 0.8972 |
118
+ | 0.0481 | 16.6240 | 13000 | 0.5913 | 0.8978 | 0.8986 |
119
+ | 0.0481 | 16.8798 | 13200 | 0.6100 | 0.8957 | 0.8967 |
120
+ | 0.043 | 17.1355 | 13400 | 0.5895 | 0.8976 | 0.8982 |
121
+ | 0.043 | 17.3913 | 13600 | 0.5653 | 0.8978 | 0.8982 |
122
+ | 0.043 | 17.6471 | 13800 | 0.5914 | 0.8996 | 0.8999 |
123
+ | 0.043 | 17.9028 | 14000 | 0.5850 | 0.9005 | 0.9007 |
124
+ | 0.042 | 18.1586 | 14200 | 0.5927 | 0.8983 | 0.8988 |
125
+ | 0.042 | 18.4143 | 14400 | 0.6164 | 0.8997 | 0.8999 |
126
+ | 0.042 | 18.6701 | 14600 | 0.6324 | 0.8986 | 0.8992 |
127
+ | 0.042 | 18.9258 | 14800 | 0.6097 | 0.8996 | 0.9001 |
128
+ | 0.0383 | 19.1816 | 15000 | 0.6029 | 0.8985 | 0.8989 |
129
+ | 0.0383 | 19.4373 | 15200 | 0.6067 | 0.8988 | 0.8992 |
130
+ | 0.0383 | 19.6931 | 15400 | 0.6177 | 0.8987 | 0.8991 |
131
+ | 0.0383 | 19.9488 | 15600 | 0.6232 | 0.8988 | 0.8992 |
132
+
133
+
134
+ ### Framework versions
135
+
136
+ - Transformers 4.41.2
137
+ - Pytorch 2.1.2
138
+ - Datasets 2.19.2
139
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "FacebookAI/xlm-roberta-base",
3
+ "architectures": [
4
+ "XMLRobertaLexical"
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": "4.41.2",
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 sha256:9280f52b9e2bed03479702e8063a3fe27d0c64a4e13d55f688b08f4571caec5d
3
+ size 1110650648
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 sha256:2249061b8f21f896c993ab172d8af872935dbba6761093b2a754de6d1b479e45
3
+ size 5112