bert-base-multi-class-classification-cs
Browse files- README.md +117 -0
- config.json +91 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
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
|
|