MaryDatascientist
commited on
Commit
•
573bc28
1
Parent(s):
8a23ee2
MaryDatascientist/B_model2
Browse files- README.md +97 -0
- config.json +52 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: bert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: B_model2
|
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 |
+
# B_model2
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.0339
|
24 |
+
- Precision: 0.9316
|
25 |
+
- Recall: 0.9369
|
26 |
+
- F1: 0.9342
|
27 |
+
- Accuracy: 0.9883
|
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: 2.65095847146542e-05
|
47 |
+
- train_batch_size: 16
|
48 |
+
- eval_batch_size: 16
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 1
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
+
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
+
| 0.057 | 0.03 | 500 | 0.0598 | 0.8641 | 0.8859 | 0.8749 | 0.9795 |
|
59 |
+
| 0.0512 | 0.06 | 1000 | 0.0496 | 0.9001 | 0.8916 | 0.8958 | 0.9827 |
|
60 |
+
| 0.0356 | 0.09 | 1500 | 0.0512 | 0.8670 | 0.9215 | 0.8934 | 0.9823 |
|
61 |
+
| 0.051 | 0.12 | 2000 | 0.0549 | 0.8399 | 0.9425 | 0.8883 | 0.9808 |
|
62 |
+
| 0.0485 | 0.15 | 2500 | 0.0459 | 0.8909 | 0.9284 | 0.9093 | 0.9843 |
|
63 |
+
| 0.0411 | 0.18 | 3000 | 0.0449 | 0.9071 | 0.9137 | 0.9104 | 0.9844 |
|
64 |
+
| 0.0376 | 0.21 | 3500 | 0.0428 | 0.9085 | 0.9138 | 0.9111 | 0.9851 |
|
65 |
+
| 0.0408 | 0.24 | 4000 | 0.0419 | 0.9136 | 0.9146 | 0.9141 | 0.9850 |
|
66 |
+
| 0.0501 | 0.27 | 4500 | 0.0406 | 0.9221 | 0.9089 | 0.9154 | 0.9855 |
|
67 |
+
| 0.0386 | 0.3 | 5000 | 0.0390 | 0.9214 | 0.9166 | 0.9190 | 0.9863 |
|
68 |
+
| 0.0372 | 0.34 | 5500 | 0.0390 | 0.9027 | 0.9398 | 0.9209 | 0.9860 |
|
69 |
+
| 0.0353 | 0.37 | 6000 | 0.0384 | 0.9195 | 0.9261 | 0.9228 | 0.9865 |
|
70 |
+
| 0.0353 | 0.4 | 6500 | 0.0375 | 0.9257 | 0.9216 | 0.9236 | 0.9866 |
|
71 |
+
| 0.0455 | 0.43 | 7000 | 0.0383 | 0.9186 | 0.9265 | 0.9225 | 0.9865 |
|
72 |
+
| 0.025 | 0.46 | 7500 | 0.0391 | 0.9093 | 0.9378 | 0.9233 | 0.9865 |
|
73 |
+
| 0.0328 | 0.49 | 8000 | 0.0380 | 0.9320 | 0.9179 | 0.9249 | 0.9869 |
|
74 |
+
| 0.0298 | 0.52 | 8500 | 0.0384 | 0.9222 | 0.9287 | 0.9254 | 0.9869 |
|
75 |
+
| 0.0337 | 0.55 | 9000 | 0.0372 | 0.9260 | 0.9208 | 0.9234 | 0.9867 |
|
76 |
+
| 0.0203 | 0.58 | 9500 | 0.0400 | 0.9166 | 0.9343 | 0.9254 | 0.9868 |
|
77 |
+
| 0.0312 | 0.61 | 10000 | 0.0364 | 0.9178 | 0.9361 | 0.9269 | 0.9870 |
|
78 |
+
| 0.0332 | 0.64 | 10500 | 0.0359 | 0.9196 | 0.9356 | 0.9275 | 0.9872 |
|
79 |
+
| 0.0291 | 0.67 | 11000 | 0.0363 | 0.9291 | 0.9253 | 0.9272 | 0.9871 |
|
80 |
+
| 0.0289 | 0.7 | 11500 | 0.0355 | 0.9304 | 0.9317 | 0.9310 | 0.9877 |
|
81 |
+
| 0.0196 | 0.73 | 12000 | 0.0359 | 0.9251 | 0.9357 | 0.9304 | 0.9875 |
|
82 |
+
| 0.0251 | 0.76 | 12500 | 0.0357 | 0.9187 | 0.9420 | 0.9302 | 0.9875 |
|
83 |
+
| 0.0235 | 0.79 | 13000 | 0.0357 | 0.9249 | 0.9408 | 0.9328 | 0.9879 |
|
84 |
+
| 0.0275 | 0.82 | 13500 | 0.0353 | 0.9308 | 0.9345 | 0.9326 | 0.9879 |
|
85 |
+
| 0.0269 | 0.85 | 14000 | 0.0352 | 0.9300 | 0.9328 | 0.9314 | 0.9880 |
|
86 |
+
| 0.0251 | 0.88 | 14500 | 0.0348 | 0.9375 | 0.9316 | 0.9346 | 0.9884 |
|
87 |
+
| 0.0143 | 0.91 | 15000 | 0.0347 | 0.9275 | 0.9408 | 0.9341 | 0.9882 |
|
88 |
+
| 0.0187 | 0.94 | 15500 | 0.0342 | 0.9299 | 0.9373 | 0.9336 | 0.9882 |
|
89 |
+
| 0.0209 | 0.98 | 16000 | 0.0339 | 0.9316 | 0.9369 | 0.9342 | 0.9883 |
|
90 |
+
|
91 |
+
|
92 |
+
### Framework versions
|
93 |
+
|
94 |
+
- Transformers 4.35.2
|
95 |
+
- Pytorch 2.1.0+cu118
|
96 |
+
- Datasets 2.15.0
|
97 |
+
- Tokenizers 0.15.0
|
config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
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": "LABEL_0",
|
14 |
+
"1": "LABEL_1",
|
15 |
+
"2": "LABEL_2",
|
16 |
+
"3": "LABEL_3",
|
17 |
+
"4": "LABEL_4",
|
18 |
+
"5": "LABEL_5",
|
19 |
+
"6": "LABEL_6",
|
20 |
+
"7": "LABEL_7",
|
21 |
+
"8": "LABEL_8",
|
22 |
+
"9": "LABEL_9",
|
23 |
+
"10": "LABEL_10"
|
24 |
+
},
|
25 |
+
"initializer_range": 0.02,
|
26 |
+
"intermediate_size": 3072,
|
27 |
+
"label2id": {
|
28 |
+
"LABEL_0": 0,
|
29 |
+
"LABEL_1": 1,
|
30 |
+
"LABEL_10": 10,
|
31 |
+
"LABEL_2": 2,
|
32 |
+
"LABEL_3": 3,
|
33 |
+
"LABEL_4": 4,
|
34 |
+
"LABEL_5": 5,
|
35 |
+
"LABEL_6": 6,
|
36 |
+
"LABEL_7": 7,
|
37 |
+
"LABEL_8": 8,
|
38 |
+
"LABEL_9": 9
|
39 |
+
},
|
40 |
+
"layer_norm_eps": 1e-12,
|
41 |
+
"max_position_embeddings": 512,
|
42 |
+
"model_type": "bert",
|
43 |
+
"num_attention_heads": 12,
|
44 |
+
"num_hidden_layers": 12,
|
45 |
+
"pad_token_id": 0,
|
46 |
+
"position_embedding_type": "absolute",
|
47 |
+
"torch_dtype": "float32",
|
48 |
+
"transformers_version": "4.35.2",
|
49 |
+
"type_vocab_size": 2,
|
50 |
+
"use_cache": true,
|
51 |
+
"vocab_size": 30522
|
52 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5697c2dc8f7175248c5a2339ebcd388fe3e7abd3da6af44aa389ea772da6288b
|
3 |
+
size 435623772
|
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 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "BertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bfc9833485e49d95e8a0d4d349989e750bd4caf6d71157cc237b23dfa5c4003b
|
3 |
+
size 4536
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|