hung200504
commited on
Commit
•
9727135
1
Parent(s):
929b500
bert-cased
Browse files- README.md +100 -0
- config.json +28 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-4.0
|
3 |
+
base_model: deepset/bert-base-cased-squad2
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: bert-19
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# bert-19
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [deepset/bert-base-cased-squad2](https://huggingface.co/deepset/bert-base-cased-squad2) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 11.2343
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 2e-05
|
38 |
+
- train_batch_size: 16
|
39 |
+
- eval_batch_size: 16
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 4
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
+
| 11.3192 | 0.09 | 5 | 12.3265 |
|
50 |
+
| 11.4416 | 0.18 | 10 | 12.2762 |
|
51 |
+
| 11.0285 | 0.27 | 15 | 12.2265 |
|
52 |
+
| 11.1568 | 0.36 | 20 | 12.1786 |
|
53 |
+
| 11.1352 | 0.45 | 25 | 12.1313 |
|
54 |
+
| 11.1596 | 0.55 | 30 | 12.0857 |
|
55 |
+
| 10.4352 | 0.64 | 35 | 12.0412 |
|
56 |
+
| 11.0699 | 0.73 | 40 | 11.9982 |
|
57 |
+
| 10.6195 | 0.82 | 45 | 11.9567 |
|
58 |
+
| 10.5109 | 0.91 | 50 | 11.9161 |
|
59 |
+
| 10.2699 | 1.0 | 55 | 11.8766 |
|
60 |
+
| 10.4784 | 1.09 | 60 | 11.8384 |
|
61 |
+
| 10.5932 | 1.18 | 65 | 11.8018 |
|
62 |
+
| 10.8098 | 1.27 | 70 | 11.7661 |
|
63 |
+
| 10.3369 | 1.36 | 75 | 11.7312 |
|
64 |
+
| 10.7722 | 1.45 | 80 | 11.6981 |
|
65 |
+
| 10.4952 | 1.55 | 85 | 11.6657 |
|
66 |
+
| 10.4398 | 1.64 | 90 | 11.6341 |
|
67 |
+
| 10.2621 | 1.73 | 95 | 11.6045 |
|
68 |
+
| 10.4932 | 1.82 | 100 | 11.5753 |
|
69 |
+
| 10.0321 | 1.91 | 105 | 11.5481 |
|
70 |
+
| 10.3808 | 2.0 | 110 | 11.5216 |
|
71 |
+
| 10.3108 | 2.09 | 115 | 11.4966 |
|
72 |
+
| 10.1234 | 2.18 | 120 | 11.4725 |
|
73 |
+
| 10.2887 | 2.27 | 125 | 11.4492 |
|
74 |
+
| 10.4092 | 2.36 | 130 | 11.4274 |
|
75 |
+
| 9.9991 | 2.45 | 135 | 11.4068 |
|
76 |
+
| 10.3832 | 2.55 | 140 | 11.3872 |
|
77 |
+
| 9.937 | 2.64 | 145 | 11.3692 |
|
78 |
+
| 10.4397 | 2.73 | 150 | 11.3521 |
|
79 |
+
| 10.1919 | 2.82 | 155 | 11.3364 |
|
80 |
+
| 10.1394 | 2.91 | 160 | 11.3214 |
|
81 |
+
| 10.3371 | 3.0 | 165 | 11.3080 |
|
82 |
+
| 10.2649 | 3.09 | 170 | 11.2953 |
|
83 |
+
| 10.2511 | 3.18 | 175 | 11.2844 |
|
84 |
+
| 9.9485 | 3.27 | 180 | 11.2741 |
|
85 |
+
| 9.8203 | 3.36 | 185 | 11.2649 |
|
86 |
+
| 10.559 | 3.45 | 190 | 11.2574 |
|
87 |
+
| 10.1233 | 3.55 | 195 | 11.2504 |
|
88 |
+
| 9.9711 | 3.64 | 200 | 11.2451 |
|
89 |
+
| 9.8388 | 3.73 | 205 | 11.2407 |
|
90 |
+
| 9.7467 | 3.82 | 210 | 11.2373 |
|
91 |
+
| 9.7465 | 3.91 | 215 | 11.2350 |
|
92 |
+
| 10.3259 | 4.0 | 220 | 11.2343 |
|
93 |
+
|
94 |
+
|
95 |
+
### Framework versions
|
96 |
+
|
97 |
+
- Transformers 4.34.1
|
98 |
+
- Pytorch 2.0.1+cu118
|
99 |
+
- Datasets 2.14.5
|
100 |
+
- Tokenizers 0.14.1
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "deepset/bert-base-cased-squad2",
|
3 |
+
"architectures": [
|
4 |
+
"BertForQuestionAnswering"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 3072,
|
13 |
+
"language": "english",
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"name": "Bert",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.34.1",
|
25 |
+
"type_vocab_size": 2,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 28996
|
28 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd71302be640b313b5574f178eec40c0cc56e8942484b2943d4b659ef4fb4a51
|
3 |
+
size 430952617
|
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 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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_basic_tokenize": true,
|
47 |
+
"do_lower_case": false,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"max_len": 512,
|
50 |
+
"model_max_length": 512,
|
51 |
+
"never_split": null,
|
52 |
+
"pad_token": "[PAD]",
|
53 |
+
"sep_token": "[SEP]",
|
54 |
+
"strip_accents": null,
|
55 |
+
"tokenize_chinese_chars": true,
|
56 |
+
"tokenizer_class": "BertTokenizer",
|
57 |
+
"unk_token": "[UNK]"
|
58 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce618fc9e1efd361039b982936ccd171ca9853dc7f1a30c5869e01453519791b
|
3 |
+
size 4027
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|