Commit
•
036bf18
1
Parent(s):
ae6176a
End of training
Browse files- README.md +125 -0
- config.json +34 -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 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google-bert/bert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: 20240402140914_big_aristotle
|
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 |
+
# 20240402140914_big_aristotle
|
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: 0.0293
|
24 |
+
- Precision: 0.9731
|
25 |
+
- Recall: 0.9711
|
26 |
+
- F1: 0.9721
|
27 |
+
- Accuracy: 0.9891
|
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: 0.0005
|
47 |
+
- train_batch_size: 32
|
48 |
+
- eval_batch_size: 32
|
49 |
+
- seed: 69
|
50 |
+
- gradient_accumulation_steps: 8
|
51 |
+
- total_train_batch_size: 256
|
52 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
53 |
+
- lr_scheduler_type: linear
|
54 |
+
- lr_scheduler_warmup_steps: 350
|
55 |
+
- num_epochs: 5
|
56 |
+
|
57 |
+
### Training results
|
58 |
+
|
59 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
60 |
+
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
61 |
+
| 0.0654 | 0.09 | 300 | 0.0495 | 0.9535 | 0.9462 | 0.9498 | 0.9808 |
|
62 |
+
| 0.0647 | 0.18 | 600 | 0.0489 | 0.9529 | 0.9470 | 0.9499 | 0.9807 |
|
63 |
+
| 0.0626 | 0.26 | 900 | 0.0486 | 0.9542 | 0.9448 | 0.9495 | 0.9807 |
|
64 |
+
| 0.0613 | 0.35 | 1200 | 0.0460 | 0.9544 | 0.9501 | 0.9522 | 0.9815 |
|
65 |
+
| 0.0623 | 0.44 | 1500 | 0.0469 | 0.9538 | 0.9493 | 0.9515 | 0.9814 |
|
66 |
+
| 0.0573 | 0.53 | 1800 | 0.0455 | 0.9552 | 0.9488 | 0.9520 | 0.9816 |
|
67 |
+
| 0.0569 | 0.61 | 2100 | 0.0447 | 0.9528 | 0.9540 | 0.9534 | 0.9819 |
|
68 |
+
| 0.0585 | 0.7 | 2400 | 0.0464 | 0.9566 | 0.9468 | 0.9516 | 0.9815 |
|
69 |
+
| 0.056 | 0.79 | 2700 | 0.0452 | 0.9555 | 0.9517 | 0.9536 | 0.9822 |
|
70 |
+
| 0.0564 | 0.88 | 3000 | 0.0430 | 0.9591 | 0.9512 | 0.9551 | 0.9828 |
|
71 |
+
| 0.0552 | 0.96 | 3300 | 0.0433 | 0.9548 | 0.9532 | 0.9540 | 0.9825 |
|
72 |
+
| 0.048 | 1.05 | 3600 | 0.0444 | 0.9579 | 0.9529 | 0.9554 | 0.9828 |
|
73 |
+
| 0.0483 | 1.14 | 3900 | 0.0415 | 0.9582 | 0.9553 | 0.9568 | 0.9831 |
|
74 |
+
| 0.0465 | 1.23 | 4200 | 0.0424 | 0.9622 | 0.9495 | 0.9558 | 0.9831 |
|
75 |
+
| 0.0465 | 1.31 | 4500 | 0.0415 | 0.9616 | 0.9514 | 0.9565 | 0.9835 |
|
76 |
+
| 0.0462 | 1.4 | 4800 | 0.0407 | 0.9588 | 0.9534 | 0.9561 | 0.9835 |
|
77 |
+
| 0.0467 | 1.49 | 5100 | 0.0403 | 0.9582 | 0.9581 | 0.9581 | 0.9836 |
|
78 |
+
| 0.0453 | 1.58 | 5400 | 0.0405 | 0.9636 | 0.9513 | 0.9574 | 0.9839 |
|
79 |
+
| 0.0446 | 1.66 | 5700 | 0.0383 | 0.9637 | 0.9555 | 0.9596 | 0.9847 |
|
80 |
+
| 0.0443 | 1.75 | 6000 | 0.0382 | 0.9596 | 0.9572 | 0.9584 | 0.9844 |
|
81 |
+
| 0.0432 | 1.84 | 6300 | 0.0373 | 0.9637 | 0.9573 | 0.9605 | 0.9847 |
|
82 |
+
| 0.0424 | 1.93 | 6600 | 0.0368 | 0.9674 | 0.9516 | 0.9594 | 0.9850 |
|
83 |
+
| 0.0364 | 2.01 | 6900 | 0.0361 | 0.9633 | 0.9570 | 0.9601 | 0.9851 |
|
84 |
+
| 0.0358 | 2.1 | 7200 | 0.0366 | 0.9618 | 0.9613 | 0.9615 | 0.9853 |
|
85 |
+
| 0.0359 | 2.19 | 7500 | 0.0370 | 0.9665 | 0.9561 | 0.9613 | 0.9852 |
|
86 |
+
| 0.036 | 2.28 | 7800 | 0.0360 | 0.9660 | 0.9564 | 0.9611 | 0.9853 |
|
87 |
+
| 0.0352 | 2.36 | 8100 | 0.0355 | 0.9658 | 0.9602 | 0.9630 | 0.9856 |
|
88 |
+
| 0.0354 | 2.45 | 8400 | 0.0354 | 0.9682 | 0.9579 | 0.9630 | 0.9860 |
|
89 |
+
| 0.0347 | 2.54 | 8700 | 0.0347 | 0.9694 | 0.9566 | 0.9630 | 0.9861 |
|
90 |
+
| 0.0347 | 2.63 | 9000 | 0.0340 | 0.9676 | 0.9597 | 0.9636 | 0.9864 |
|
91 |
+
| 0.0338 | 2.71 | 9300 | 0.0327 | 0.9682 | 0.9626 | 0.9654 | 0.9867 |
|
92 |
+
| 0.0338 | 2.8 | 9600 | 0.0334 | 0.9681 | 0.9627 | 0.9654 | 0.9865 |
|
93 |
+
| 0.033 | 2.89 | 9900 | 0.0325 | 0.9705 | 0.9613 | 0.9659 | 0.9870 |
|
94 |
+
| 0.0326 | 2.98 | 10200 | 0.0331 | 0.9686 | 0.9640 | 0.9663 | 0.9870 |
|
95 |
+
| 0.0264 | 3.06 | 10500 | 0.0352 | 0.9689 | 0.9651 | 0.9670 | 0.9871 |
|
96 |
+
| 0.0261 | 3.15 | 10800 | 0.0329 | 0.9698 | 0.9633 | 0.9666 | 0.9871 |
|
97 |
+
| 0.026 | 3.24 | 11100 | 0.0328 | 0.9672 | 0.9662 | 0.9667 | 0.9872 |
|
98 |
+
| 0.0261 | 3.33 | 11400 | 0.0333 | 0.9678 | 0.9681 | 0.9680 | 0.9872 |
|
99 |
+
| 0.0264 | 3.41 | 11700 | 0.0326 | 0.9689 | 0.9676 | 0.9682 | 0.9875 |
|
100 |
+
| 0.0258 | 3.5 | 12000 | 0.0313 | 0.9717 | 0.9643 | 0.9680 | 0.9877 |
|
101 |
+
| 0.0254 | 3.59 | 12300 | 0.0307 | 0.9691 | 0.9675 | 0.9683 | 0.9880 |
|
102 |
+
| 0.0249 | 3.68 | 12600 | 0.0304 | 0.9720 | 0.9666 | 0.9693 | 0.9881 |
|
103 |
+
| 0.025 | 3.76 | 12900 | 0.0300 | 0.9686 | 0.9680 | 0.9683 | 0.9882 |
|
104 |
+
| 0.0242 | 3.85 | 13200 | 0.0297 | 0.9682 | 0.9682 | 0.9682 | 0.9881 |
|
105 |
+
| 0.0246 | 3.94 | 13500 | 0.0291 | 0.9725 | 0.9655 | 0.9690 | 0.9883 |
|
106 |
+
| 0.0184 | 4.03 | 13800 | 0.0320 | 0.9712 | 0.9678 | 0.9695 | 0.9882 |
|
107 |
+
| 0.0186 | 4.11 | 14100 | 0.0311 | 0.9703 | 0.9688 | 0.9696 | 0.9883 |
|
108 |
+
| 0.0183 | 4.2 | 14400 | 0.0319 | 0.9718 | 0.9696 | 0.9707 | 0.9886 |
|
109 |
+
| 0.0181 | 4.29 | 14700 | 0.0312 | 0.9730 | 0.9673 | 0.9702 | 0.9885 |
|
110 |
+
| 0.0181 | 4.38 | 15000 | 0.0308 | 0.9694 | 0.9698 | 0.9696 | 0.9885 |
|
111 |
+
| 0.0178 | 4.47 | 15300 | 0.0302 | 0.9727 | 0.9698 | 0.9712 | 0.9888 |
|
112 |
+
| 0.0175 | 4.55 | 15600 | 0.0300 | 0.9729 | 0.9705 | 0.9717 | 0.9889 |
|
113 |
+
| 0.0171 | 4.64 | 15900 | 0.0300 | 0.9725 | 0.9713 | 0.9719 | 0.9890 |
|
114 |
+
| 0.017 | 4.73 | 16200 | 0.0296 | 0.9712 | 0.9710 | 0.9711 | 0.9888 |
|
115 |
+
| 0.017 | 4.82 | 16500 | 0.0295 | 0.9726 | 0.9707 | 0.9717 | 0.9890 |
|
116 |
+
| 0.0168 | 4.9 | 16800 | 0.0297 | 0.9730 | 0.9711 | 0.9721 | 0.9891 |
|
117 |
+
| 0.0166 | 4.99 | 17100 | 0.0293 | 0.9731 | 0.9711 | 0.9721 | 0.9891 |
|
118 |
+
|
119 |
+
|
120 |
+
### Framework versions
|
121 |
+
|
122 |
+
- Transformers 4.39.3
|
123 |
+
- Pytorch 2.2.0a0+6a974be
|
124 |
+
- Datasets 2.18.0
|
125 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google-bert/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": "not inserted",
|
14 |
+
"1": "inserted"
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 3072,
|
18 |
+
"label2id": {
|
19 |
+
"inserted": 1,
|
20 |
+
"not inserted": 0
|
21 |
+
},
|
22 |
+
"layer_norm_eps": 1e-12,
|
23 |
+
"max_position_embeddings": 512,
|
24 |
+
"model_type": "bert",
|
25 |
+
"num_attention_heads": 12,
|
26 |
+
"num_hidden_layers": 12,
|
27 |
+
"pad_token_id": 0,
|
28 |
+
"position_embedding_type": "absolute",
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.39.3",
|
31 |
+
"type_vocab_size": 2,
|
32 |
+
"use_cache": true,
|
33 |
+
"vocab_size": 30522
|
34 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98f1659e00d51a2d6e163f37775f77ef6e61240b9bf4aa9b43171b0e542c3ef8
|
3 |
+
size 435596088
|
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 sha256:389303e43f072998eedf1badc4af9a8a81ebade8a06593530ba7d9d9a9fcb3cf
|
3 |
+
size 5048
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|