Hugging Face's logo

Narkantak
/
Intent-classification-12kv2

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
Narkantak commited on
Commit
503a645
•
1 Parent(s): 906dd97

End of training

Browse files
Files changed (4) hide show
  1. README.md +161 -0
  2. config.json +43 -0
  3. model.safetensors +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,161 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google-bert/bert-base-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ - f1
9
+ - precision
10
+ - recall
11
+ model-index:
12
+ - name: Intent-classification-12kv2
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
+ # Intent-classification-12kv2
20
+
21
+ This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.0074
24
+ - Accuracy: 0.9984
25
+ - F1: 0.9983
26
+ - Precision: 0.9983
27
+ - Recall: 0.9983
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: 32
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: 10
53
+ - num_epochs: 5
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
58
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
59
+ | 1.742 | 0.05 | 10 | 1.4822 | 0.6954 | 0.6918 | 0.7288 | 0.6966 |
60
+ | 1.2849 | 0.11 | 20 | 0.9533 | 0.8713 | 0.8699 | 0.8899 | 0.8729 |
61
+ | 0.8226 | 0.16 | 30 | 0.5235 | 0.9786 | 0.9786 | 0.9790 | 0.9785 |
62
+ | 0.399 | 0.21 | 40 | 0.2295 | 0.9812 | 0.9812 | 0.9811 | 0.9817 |
63
+ | 0.1871 | 0.26 | 50 | 0.1168 | 0.9839 | 0.9839 | 0.9844 | 0.9836 |
64
+ | 0.0855 | 0.32 | 60 | 0.0508 | 0.9928 | 0.9928 | 0.9928 | 0.9928 |
65
+ | 0.0546 | 0.37 | 70 | 0.0300 | 0.9947 | 0.9947 | 0.9948 | 0.9947 |
66
+ | 0.0226 | 0.42 | 80 | 0.0271 | 0.9947 | 0.9948 | 0.9947 | 0.9948 |
67
+ | 0.0306 | 0.47 | 90 | 0.0416 | 0.9888 | 0.9887 | 0.9894 | 0.9883 |
68
+ | 0.0336 | 0.53 | 100 | 0.0157 | 0.9970 | 0.9970 | 0.9970 | 0.9971 |
69
+ | 0.0373 | 0.58 | 110 | 0.0214 | 0.9951 | 0.9951 | 0.9952 | 0.9951 |
70
+ | 0.0094 | 0.63 | 120 | 0.0121 | 0.9970 | 0.9971 | 0.9971 | 0.9970 |
71
+ | 0.0077 | 0.68 | 130 | 0.0094 | 0.9980 | 0.9980 | 0.9980 | 0.9981 |
72
+ | 0.0253 | 0.74 | 140 | 0.0077 | 0.9987 | 0.9987 | 0.9987 | 0.9987 |
73
+ | 0.0233 | 0.79 | 150 | 0.0075 | 0.9987 | 0.9987 | 0.9987 | 0.9987 |
74
+ | 0.0068 | 0.84 | 160 | 0.0080 | 0.9987 | 0.9987 | 0.9987 | 0.9987 |
75
+ | 0.0286 | 0.89 | 170 | 0.0141 | 0.9964 | 0.9964 | 0.9964 | 0.9964 |
76
+ | 0.0139 | 0.95 | 180 | 0.0104 | 0.9970 | 0.9970 | 0.9970 | 0.9971 |
77
+ | 0.0043 | 1.0 | 190 | 0.0074 | 0.9977 | 0.9977 | 0.9977 | 0.9976 |
78
+ | 0.0122 | 1.05 | 200 | 0.0065 | 0.9987 | 0.9987 | 0.9987 | 0.9987 |
79
+ | 0.0071 | 1.11 | 210 | 0.0059 | 0.9980 | 0.9980 | 0.9981 | 0.9980 |
80
+ | 0.0025 | 1.16 | 220 | 0.0083 | 0.9984 | 0.9984 | 0.9984 | 0.9983 |
81
+ | 0.0232 | 1.21 | 230 | 0.0057 | 0.9984 | 0.9984 | 0.9984 | 0.9984 |
82
+ | 0.0035 | 1.26 | 240 | 0.0056 | 0.9987 | 0.9987 | 0.9987 | 0.9987 |
83
+ | 0.0246 | 1.32 | 250 | 0.0053 | 0.9984 | 0.9984 | 0.9984 | 0.9983 |
84
+ | 0.0023 | 1.37 | 260 | 0.0063 | 0.9980 | 0.9980 | 0.9981 | 0.9980 |
85
+ | 0.0021 | 1.42 | 270 | 0.0048 | 0.9984 | 0.9984 | 0.9984 | 0.9983 |
86
+ | 0.002 | 1.47 | 280 | 0.0028 | 0.9997 | 0.9997 | 0.9997 | 0.9997 |
87
+ | 0.022 | 1.53 | 290 | 0.0023 | 0.9997 | 0.9997 | 0.9997 | 0.9997 |
88
+ | 0.0135 | 1.58 | 300 | 0.0046 | 0.9987 | 0.9987 | 0.9987 | 0.9987 |
89
+ | 0.0026 | 1.63 | 310 | 0.0082 | 0.9977 | 0.9977 | 0.9979 | 0.9976 |
90
+ | 0.0019 | 1.68 | 320 | 0.0043 | 0.9990 | 0.9990 | 0.9991 | 0.9990 |
91
+ | 0.0017 | 1.74 | 330 | 0.0035 | 0.9993 | 0.9994 | 0.9994 | 0.9994 |
92
+ | 0.0019 | 1.79 | 340 | 0.0015 | 1.0 | 1.0 | 1.0 | 1.0 |
93
+ | 0.0014 | 1.84 | 350 | 0.0013 | 1.0 | 1.0 | 1.0 | 1.0 |
94
+ | 0.0014 | 1.89 | 360 | 0.0013 | 1.0 | 1.0 | 1.0 | 1.0 |
95
+ | 0.0013 | 1.95 | 370 | 0.0012 | 1.0 | 1.0 | 1.0 | 1.0 |
96
+ | 0.0013 | 2.0 | 380 | 0.0011 | 1.0 | 1.0 | 1.0 | 1.0 |
97
+ | 0.0012 | 2.05 | 390 | 0.0011 | 1.0 | 1.0 | 1.0 | 1.0 |
98
+ | 0.0011 | 2.11 | 400 | 0.0011 | 1.0 | 1.0 | 1.0 | 1.0 |
99
+ | 0.0011 | 2.16 | 410 | 0.0010 | 1.0 | 1.0 | 1.0 | 1.0 |
100
+ | 0.0011 | 2.21 | 420 | 0.0010 | 1.0 | 1.0 | 1.0 | 1.0 |
101
+ | 0.0014 | 2.26 | 430 | 0.0009 | 1.0 | 1.0 | 1.0 | 1.0 |
102
+ | 0.001 | 2.32 | 440 | 0.0009 | 1.0 | 1.0 | 1.0 | 1.0 |
103
+ | 0.001 | 2.37 | 450 | 0.0009 | 1.0 | 1.0 | 1.0 | 1.0 |
104
+ | 0.0009 | 2.42 | 460 | 0.0009 | 1.0 | 1.0 | 1.0 | 1.0 |
105
+ | 0.0009 | 2.47 | 470 | 0.0008 | 1.0 | 1.0 | 1.0 | 1.0 |
106
+ | 0.0009 | 2.53 | 480 | 0.0008 | 1.0 | 1.0 | 1.0 | 1.0 |
107
+ | 0.0009 | 2.58 | 490 | 0.0008 | 1.0 | 1.0 | 1.0 | 1.0 |
108
+ | 0.0009 | 2.63 | 500 | 0.0008 | 1.0 | 1.0 | 1.0 | 1.0 |
109
+ | 0.0008 | 2.68 | 510 | 0.0008 | 1.0 | 1.0 | 1.0 | 1.0 |
110
+ | 0.0008 | 2.74 | 520 | 0.0008 | 1.0 | 1.0 | 1.0 | 1.0 |
111
+ | 0.0008 | 2.79 | 530 | 0.0007 | 1.0 | 1.0 | 1.0 | 1.0 |
112
+ | 0.0008 | 2.84 | 540 | 0.0007 | 1.0 | 1.0 | 1.0 | 1.0 |
113
+ | 0.0008 | 2.89 | 550 | 0.0007 | 1.0 | 1.0 | 1.0 | 1.0 |
114
+ | 0.0008 | 2.95 | 560 | 0.0007 | 1.0 | 1.0 | 1.0 | 1.0 |
115
+ | 0.0007 | 3.0 | 570 | 0.0007 | 1.0 | 1.0 | 1.0 | 1.0 |
116
+ | 0.0009 | 3.05 | 580 | 0.0007 | 1.0 | 1.0 | 1.0 | 1.0 |
117
+ | 0.0007 | 3.11 | 590 | 0.0006 | 1.0 | 1.0 | 1.0 | 1.0 |
118
+ | 0.0007 | 3.16 | 600 | 0.0006 | 1.0 | 1.0 | 1.0 | 1.0 |
119
+ | 0.0007 | 3.21 | 610 | 0.0006 | 1.0 | 1.0 | 1.0 | 1.0 |
120
+ | 0.0007 | 3.26 | 620 | 0.0006 | 1.0 | 1.0 | 1.0 | 1.0 |
121
+ | 0.0007 | 3.32 | 630 | 0.0006 | 1.0 | 1.0 | 1.0 | 1.0 |
122
+ | 0.0007 | 3.37 | 640 | 0.0006 | 1.0 | 1.0 | 1.0 | 1.0 |
123
+ | 0.0006 | 3.42 | 650 | 0.0006 | 1.0 | 1.0 | 1.0 | 1.0 |
124
+ | 0.0006 | 3.47 | 660 | 0.0006 | 1.0 | 1.0 | 1.0 | 1.0 |
125
+ | 0.0006 | 3.53 | 670 | 0.0006 | 1.0 | 1.0 | 1.0 | 1.0 |
126
+ | 0.0006 | 3.58 | 680 | 0.0006 | 1.0 | 1.0 | 1.0 | 1.0 |
127
+ | 0.0006 | 3.63 | 690 | 0.0006 | 1.0 | 1.0 | 1.0 | 1.0 |
128
+ | 0.0006 | 3.68 | 700 | 0.0006 | 1.0 | 1.0 | 1.0 | 1.0 |
129
+ | 0.0006 | 3.74 | 710 | 0.0006 | 1.0 | 1.0 | 1.0 | 1.0 |
130
+ | 0.0006 | 3.79 | 720 | 0.0006 | 1.0 | 1.0 | 1.0 | 1.0 |
131
+ | 0.0006 | 3.84 | 730 | 0.0006 | 1.0 | 1.0 | 1.0 | 1.0 |
132
+ | 0.0006 | 3.89 | 740 | 0.0005 | 1.0 | 1.0 | 1.0 | 1.0 |
133
+ | 0.0006 | 3.95 | 750 | 0.0005 | 1.0 | 1.0 | 1.0 | 1.0 |
134
+ | 0.0006 | 4.0 | 760 | 0.0005 | 1.0 | 1.0 | 1.0 | 1.0 |
135
+ | 0.0006 | 4.05 | 770 | 0.0005 | 1.0 | 1.0 | 1.0 | 1.0 |
136
+ | 0.0006 | 4.11 | 780 | 0.0005 | 1.0 | 1.0 | 1.0 | 1.0 |
137
+ | 0.0006 | 4.16 | 790 | 0.0005 | 1.0 | 1.0 | 1.0 | 1.0 |
138
+ | 0.0006 | 4.21 | 800 | 0.0005 | 1.0 | 1.0 | 1.0 | 1.0 |
139
+ | 0.0006 | 4.26 | 810 | 0.0005 | 1.0 | 1.0 | 1.0 | 1.0 |
140
+ | 0.0006 | 4.32 | 820 | 0.0005 | 1.0 | 1.0 | 1.0 | 1.0 |
141
+ | 0.0006 | 4.37 | 830 | 0.0005 | 1.0 | 1.0 | 1.0 | 1.0 |
142
+ | 0.0006 | 4.42 | 840 | 0.0005 | 1.0 | 1.0 | 1.0 | 1.0 |
143
+ | 0.0006 | 4.47 | 850 | 0.0005 | 1.0 | 1.0 | 1.0 | 1.0 |
144
+ | 0.0006 | 4.53 | 860 | 0.0005 | 1.0 | 1.0 | 1.0 | 1.0 |
145
+ | 0.0006 | 4.58 | 870 | 0.0005 | 1.0 | 1.0 | 1.0 | 1.0 |
146
+ | 0.0005 | 4.63 | 880 | 0.0005 | 1.0 | 1.0 | 1.0 | 1.0 |
147
+ | 0.0006 | 4.68 | 890 | 0.0005 | 1.0 | 1.0 | 1.0 | 1.0 |
148
+ | 0.0005 | 4.74 | 900 | 0.0005 | 1.0 | 1.0 | 1.0 | 1.0 |
149
+ | 0.0005 | 4.79 | 910 | 0.0005 | 1.0 | 1.0 | 1.0 | 1.0 |
150
+ | 0.0006 | 4.84 | 920 | 0.0005 | 1.0 | 1.0 | 1.0 | 1.0 |
151
+ | 0.0005 | 4.89 | 930 | 0.0005 | 1.0 | 1.0 | 1.0 | 1.0 |
152
+ | 0.0006 | 4.95 | 940 | 0.0005 | 1.0 | 1.0 | 1.0 | 1.0 |
153
+ | 0.0005 | 5.0 | 950 | 0.0005 | 1.0 | 1.0 | 1.0 | 1.0 |
154
+
155
+
156
+ ### Framework versions
157
+
158
+ - Transformers 4.38.2
159
+ - Pytorch 2.1.2
160
+ - Datasets 2.1.0
161
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/bert-base-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "SBC",
14
+ "1": "Change",
15
+ "2": "Install",
16
+ "3": "Summarize",
17
+ "4": "Compensation",
18
+ "5": "Terminate"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "Change": 1,
24
+ "Compensation": 4,
25
+ "Install": 2,
26
+ "SBC": 0,
27
+ "Summarize": 3,
28
+ "Terminate": 5
29
+ },
30
+ "layer_norm_eps": 1e-12,
31
+ "max_position_embeddings": 512,
32
+ "model_type": "bert",
33
+ "num_attention_heads": 12,
34
+ "num_hidden_layers": 12,
35
+ "pad_token_id": 0,
36
+ "position_embedding_type": "absolute",
37
+ "problem_type": "single_label_classification",
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.38.2",
40
+ "type_vocab_size": 2,
41
+ "use_cache": true,
42
+ "vocab_size": 30522
43
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1faf633f677c05daba1fff0e60fbaaf3c8608c00b76dd85f1d1789fe516e730
3
+ size 437970952
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98778390ede4cc4769f811d6f2c9d1975625f7787e58671fd4857fe68635598c
3
+ size 4856