Porameht commited on
Commit
070883d
1 Parent(s): 581db71

bert-base-multi-class-classification-cs

Browse files
README.md ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google-bert/bert-base-multilingual-cased
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ - f1
9
+ - precision
10
+ - recall
11
+ model-index:
12
+ - name: bert-base-multi-class-classification-cs
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # bert-base-multi-class-classification-cs
20
+
21
+ This model is a fine-tuned version of [google-bert/bert-base-multilingual-cased](https://huggingface.co/google-bert/bert-base-multilingual-cased) on an unknown dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.0385
24
+ - Accuracy: 0.9942
25
+ - F1: 0.9942
26
+ - Precision: 0.9942
27
+ - Recall: 0.9942
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: 5e-05
47
+ - train_batch_size: 16
48
+ - eval_batch_size: 32
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_steps: 100
53
+ - num_epochs: 3
54
+ - mixed_precision_training: Native AMP
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
59
+ |:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
60
+ | 3.3053 | 0.0595 | 50 | 3.1767 | 0.0871 | 0.0306 | 0.0333 | 0.0869 |
61
+ | 2.8293 | 0.1190 | 100 | 2.1807 | 0.4647 | 0.3675 | 0.5055 | 0.4651 |
62
+ | 1.6887 | 0.1786 | 150 | 1.1300 | 0.7705 | 0.7362 | 0.7621 | 0.7722 |
63
+ | 0.9012 | 0.2381 | 200 | 0.6245 | 0.8321 | 0.8086 | 0.8549 | 0.8356 |
64
+ | 0.5237 | 0.2976 | 250 | 0.3510 | 0.9129 | 0.9029 | 0.9007 | 0.9147 |
65
+ | 0.3115 | 0.3571 | 300 | 0.2218 | 0.9512 | 0.9517 | 0.9545 | 0.9518 |
66
+ | 0.2217 | 0.4167 | 350 | 0.1746 | 0.9382 | 0.9284 | 0.9596 | 0.9388 |
67
+ | 0.1464 | 0.4762 | 400 | 0.1210 | 0.9729 | 0.9731 | 0.9749 | 0.9730 |
68
+ | 0.1201 | 0.5357 | 450 | 0.0977 | 0.9804 | 0.9805 | 0.9810 | 0.9805 |
69
+ | 0.0921 | 0.5952 | 500 | 0.1212 | 0.9722 | 0.9721 | 0.9741 | 0.9718 |
70
+ | 0.1061 | 0.6548 | 550 | 0.1224 | 0.9726 | 0.9728 | 0.9750 | 0.9728 |
71
+ | 0.0996 | 0.7143 | 600 | 0.0812 | 0.9817 | 0.9815 | 0.9819 | 0.9816 |
72
+ | 0.1196 | 0.7738 | 650 | 0.0726 | 0.9859 | 0.9858 | 0.9862 | 0.9857 |
73
+ | 0.101 | 0.8333 | 700 | 0.0711 | 0.9853 | 0.9854 | 0.9856 | 0.9853 |
74
+ | 0.1159 | 0.8929 | 750 | 0.1012 | 0.9792 | 0.9795 | 0.9803 | 0.9796 |
75
+ | 0.086 | 0.9524 | 800 | 0.0693 | 0.9870 | 0.9871 | 0.9874 | 0.9870 |
76
+ | 0.0742 | 1.0119 | 850 | 0.0619 | 0.9885 | 0.9886 | 0.9888 | 0.9885 |
77
+ | 0.0713 | 1.0714 | 900 | 0.0517 | 0.9896 | 0.9896 | 0.9897 | 0.9896 |
78
+ | 0.02 | 1.1310 | 950 | 0.0707 | 0.9869 | 0.9870 | 0.9874 | 0.9870 |
79
+ | 0.038 | 1.1905 | 1000 | 0.0455 | 0.9920 | 0.9920 | 0.9920 | 0.9919 |
80
+ | 0.0378 | 1.25 | 1050 | 0.0485 | 0.9906 | 0.9906 | 0.9906 | 0.9906 |
81
+ | 0.0257 | 1.3095 | 1100 | 0.0452 | 0.9921 | 0.9921 | 0.9922 | 0.9921 |
82
+ | 0.0454 | 1.3690 | 1150 | 0.0494 | 0.9905 | 0.9905 | 0.9906 | 0.9905 |
83
+ | 0.0174 | 1.4286 | 1200 | 0.0404 | 0.9923 | 0.9922 | 0.9922 | 0.9922 |
84
+ | 0.0425 | 1.4881 | 1250 | 0.0627 | 0.9879 | 0.9877 | 0.9879 | 0.9877 |
85
+ | 0.0489 | 1.5476 | 1300 | 0.0525 | 0.9908 | 0.9907 | 0.9907 | 0.9907 |
86
+ | 0.0816 | 1.6071 | 1350 | 0.0439 | 0.9918 | 0.9918 | 0.9919 | 0.9917 |
87
+ | 0.0375 | 1.6667 | 1400 | 0.0434 | 0.9921 | 0.9920 | 0.9920 | 0.9921 |
88
+ | 0.0435 | 1.7262 | 1450 | 0.0368 | 0.9929 | 0.9928 | 0.9929 | 0.9929 |
89
+ | 0.0285 | 1.7857 | 1500 | 0.0364 | 0.9935 | 0.9934 | 0.9935 | 0.9934 |
90
+ | 0.0222 | 1.8452 | 1550 | 0.0332 | 0.9942 | 0.9942 | 0.9943 | 0.9941 |
91
+ | 0.0311 | 1.9048 | 1600 | 0.0394 | 0.9929 | 0.9929 | 0.9930 | 0.9929 |
92
+ | 0.0269 | 1.9643 | 1650 | 0.0359 | 0.9935 | 0.9934 | 0.9935 | 0.9934 |
93
+ | 0.0258 | 2.0238 | 1700 | 0.0326 | 0.9937 | 0.9937 | 0.9938 | 0.9937 |
94
+ | 0.0046 | 2.0833 | 1750 | 0.0324 | 0.9945 | 0.9944 | 0.9945 | 0.9944 |
95
+ | 0.0152 | 2.1429 | 1800 | 0.0329 | 0.9946 | 0.9946 | 0.9948 | 0.9946 |
96
+ | 0.024 | 2.2024 | 1850 | 0.0305 | 0.9948 | 0.9947 | 0.9948 | 0.9947 |
97
+ | 0.0212 | 2.2619 | 1900 | 0.0333 | 0.9943 | 0.9943 | 0.9943 | 0.9943 |
98
+ | 0.0029 | 2.3214 | 1950 | 0.0322 | 0.9937 | 0.9937 | 0.9938 | 0.9937 |
99
+ | 0.0114 | 2.3810 | 2000 | 0.0342 | 0.9940 | 0.9940 | 0.9941 | 0.9940 |
100
+ | 0.0115 | 2.4405 | 2050 | 0.0328 | 0.9942 | 0.9941 | 0.9942 | 0.9941 |
101
+ | 0.0182 | 2.5 | 2100 | 0.0333 | 0.9937 | 0.9937 | 0.9938 | 0.9936 |
102
+ | 0.01 | 2.5595 | 2150 | 0.0314 | 0.9940 | 0.9940 | 0.9941 | 0.9940 |
103
+ | 0.0205 | 2.6190 | 2200 | 0.0325 | 0.9937 | 0.9937 | 0.9938 | 0.9937 |
104
+ | 0.0173 | 2.6786 | 2250 | 0.0335 | 0.9940 | 0.9940 | 0.9941 | 0.9940 |
105
+ | 0.0093 | 2.7381 | 2300 | 0.0340 | 0.9942 | 0.9942 | 0.9943 | 0.9941 |
106
+ | 0.0151 | 2.7976 | 2350 | 0.0327 | 0.9946 | 0.9947 | 0.9947 | 0.9946 |
107
+ | 0.0077 | 2.8571 | 2400 | 0.0321 | 0.9948 | 0.9948 | 0.9949 | 0.9948 |
108
+ | 0.0074 | 2.9167 | 2450 | 0.0311 | 0.9946 | 0.9946 | 0.9947 | 0.9946 |
109
+ | 0.0021 | 2.9762 | 2500 | 0.0310 | 0.9946 | 0.9946 | 0.9947 | 0.9946 |
110
+
111
+
112
+ ### Framework versions
113
+
114
+ - Transformers 4.40.1
115
+ - Pytorch 2.2.1+cu121
116
+ - Datasets 2.19.1
117
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/bert-base-multilingual-cased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "contact_human_agent",
14
+ "1": "check_invoice",
15
+ "2": "payment_issue",
16
+ "3": "contact_customer_service",
17
+ "4": "check_payment_methods",
18
+ "5": "newsletter_subscription",
19
+ "6": "check_cancellation_fee",
20
+ "7": "get_invoice",
21
+ "8": "delete_account",
22
+ "9": "check_refund_policy",
23
+ "10": "complaint",
24
+ "11": "registration_problems",
25
+ "12": "get_refund",
26
+ "13": "switch_account",
27
+ "14": "delivery_period",
28
+ "15": "set_up_shipping_address",
29
+ "16": "edit_account",
30
+ "17": "track_refund",
31
+ "18": "cancel_order",
32
+ "19": "change_order",
33
+ "20": "create_account",
34
+ "21": "review",
35
+ "22": "track_order",
36
+ "23": "change_shipping_address",
37
+ "24": "delivery_options",
38
+ "25": "place_order",
39
+ "26": "recover_password",
40
+ "27": "cancel_order"
41
+ },
42
+ "initializer_range": 0.02,
43
+ "intermediate_size": 3072,
44
+ "label2id": {
45
+ "cancel_order": 27,
46
+ "change_order": 19,
47
+ "change_shipping_address": 23,
48
+ "check_cancellation_fee": 6,
49
+ "check_invoice": 1,
50
+ "check_payment_methods": 4,
51
+ "check_refund_policy": 9,
52
+ "complaint": 10,
53
+ "contact_customer_service": 3,
54
+ "contact_human_agent": 0,
55
+ "create_account": 20,
56
+ "delete_account": 8,
57
+ "delivery_options": 24,
58
+ "delivery_period": 14,
59
+ "edit_account": 16,
60
+ "get_invoice": 7,
61
+ "get_refund": 12,
62
+ "newsletter_subscription": 5,
63
+ "payment_issue": 2,
64
+ "place_order": 25,
65
+ "recover_password": 26,
66
+ "registration_problems": 11,
67
+ "review": 21,
68
+ "set_up_shipping_address": 15,
69
+ "switch_account": 13,
70
+ "track_order": 22,
71
+ "track_refund": 17
72
+ },
73
+ "layer_norm_eps": 1e-12,
74
+ "max_position_embeddings": 512,
75
+ "model_type": "bert",
76
+ "num_attention_heads": 12,
77
+ "num_hidden_layers": 12,
78
+ "pad_token_id": 0,
79
+ "pooler_fc_size": 768,
80
+ "pooler_num_attention_heads": 12,
81
+ "pooler_num_fc_layers": 3,
82
+ "pooler_size_per_head": 128,
83
+ "pooler_type": "first_token_transform",
84
+ "position_embedding_type": "absolute",
85
+ "problem_type": "single_label_classification",
86
+ "torch_dtype": "float32",
87
+ "transformers_version": "4.40.1",
88
+ "type_vocab_size": 2,
89
+ "use_cache": true,
90
+ "vocab_size": 119547
91
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab501c2752aa33c764b4b1f16c51e3c30661c55431371680390759bffb2e9bfa
3
+ size 711523440
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "mask_token": "[MASK]",
48
+ "max_length": 512,
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cdfb005f400a59e515b4d9a8d6c206c8c79c3468622a64e065c95886147779b
3
+ size 4984
vocab.txt ADDED
The diff for this file is too large to render. See raw diff