End of training
Browse files- README.md +115 -0
- adapter_config.json +26 -0
- adapter_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 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: hfl/chinese-roberta-wwm-ext
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: RoBERTa-ext-lora-chinese-finetuned-ner
|
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 |
+
# RoBERTa-ext-lora-chinese-finetuned-ner
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [hfl/chinese-roberta-wwm-ext](https://huggingface.co/hfl/chinese-roberta-wwm-ext) on an unknown dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.6506
|
24 |
+
- Precision: 0.6463
|
25 |
+
- Recall: 0.7339
|
26 |
+
- F1: 0.6873
|
27 |
+
- Accuracy: 0.9081
|
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: 0.001
|
47 |
+
- train_batch_size: 16
|
48 |
+
- eval_batch_size: 8
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 50
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
+
| 0.6585 | 1.0 | 126 | 0.3495 | 0.4949 | 0.6045 | 0.5443 | 0.8916 |
|
59 |
+
| 0.3145 | 2.0 | 252 | 0.3116 | 0.5286 | 0.6644 | 0.5888 | 0.9000 |
|
60 |
+
| 0.2644 | 3.0 | 378 | 0.3112 | 0.5425 | 0.7012 | 0.6117 | 0.9029 |
|
61 |
+
| 0.2373 | 4.0 | 504 | 0.3028 | 0.5696 | 0.7090 | 0.6317 | 0.9058 |
|
62 |
+
| 0.2078 | 5.0 | 630 | 0.3141 | 0.5933 | 0.7102 | 0.6465 | 0.9059 |
|
63 |
+
| 0.192 | 6.0 | 756 | 0.3091 | 0.5842 | 0.7037 | 0.6384 | 0.9069 |
|
64 |
+
| 0.1708 | 7.0 | 882 | 0.3224 | 0.5803 | 0.7165 | 0.6413 | 0.9046 |
|
65 |
+
| 0.1557 | 8.0 | 1008 | 0.3306 | 0.6088 | 0.6833 | 0.6439 | 0.9067 |
|
66 |
+
| 0.1424 | 9.0 | 1134 | 0.3243 | 0.6031 | 0.6961 | 0.6463 | 0.9089 |
|
67 |
+
| 0.1285 | 10.0 | 1260 | 0.3451 | 0.6041 | 0.7142 | 0.6546 | 0.9064 |
|
68 |
+
| 0.1223 | 11.0 | 1386 | 0.3578 | 0.6016 | 0.7080 | 0.6505 | 0.9054 |
|
69 |
+
| 0.1111 | 12.0 | 1512 | 0.3615 | 0.6167 | 0.7158 | 0.6625 | 0.9080 |
|
70 |
+
| 0.1025 | 13.0 | 1638 | 0.3918 | 0.6073 | 0.7163 | 0.6573 | 0.9051 |
|
71 |
+
| 0.093 | 14.0 | 1764 | 0.3957 | 0.6119 | 0.7329 | 0.6670 | 0.9078 |
|
72 |
+
| 0.0858 | 15.0 | 1890 | 0.4050 | 0.6179 | 0.7052 | 0.6587 | 0.9067 |
|
73 |
+
| 0.0769 | 16.0 | 2016 | 0.4218 | 0.6178 | 0.7170 | 0.6637 | 0.9067 |
|
74 |
+
| 0.0716 | 17.0 | 2142 | 0.4213 | 0.6090 | 0.7223 | 0.6608 | 0.9057 |
|
75 |
+
| 0.0657 | 18.0 | 2268 | 0.4486 | 0.6028 | 0.7299 | 0.6603 | 0.9048 |
|
76 |
+
| 0.0652 | 19.0 | 2394 | 0.4388 | 0.6301 | 0.7193 | 0.6718 | 0.9058 |
|
77 |
+
| 0.0653 | 20.0 | 2520 | 0.4563 | 0.6165 | 0.7002 | 0.6557 | 0.9039 |
|
78 |
+
| 0.0568 | 21.0 | 2646 | 0.4549 | 0.6057 | 0.7283 | 0.6614 | 0.9034 |
|
79 |
+
| 0.0522 | 22.0 | 2772 | 0.4711 | 0.6216 | 0.7205 | 0.6674 | 0.9066 |
|
80 |
+
| 0.0486 | 23.0 | 2898 | 0.4995 | 0.6267 | 0.7148 | 0.6678 | 0.9062 |
|
81 |
+
| 0.0477 | 24.0 | 3024 | 0.4938 | 0.6228 | 0.7261 | 0.6705 | 0.9056 |
|
82 |
+
| 0.0415 | 25.0 | 3150 | 0.5129 | 0.6365 | 0.7180 | 0.6748 | 0.9075 |
|
83 |
+
| 0.0404 | 26.0 | 3276 | 0.5096 | 0.6287 | 0.7258 | 0.6738 | 0.9072 |
|
84 |
+
| 0.0364 | 27.0 | 3402 | 0.5331 | 0.6390 | 0.7205 | 0.6773 | 0.9058 |
|
85 |
+
| 0.0362 | 28.0 | 3528 | 0.5572 | 0.6317 | 0.7263 | 0.6757 | 0.9061 |
|
86 |
+
| 0.0331 | 29.0 | 3654 | 0.5603 | 0.6377 | 0.7228 | 0.6776 | 0.9050 |
|
87 |
+
| 0.0316 | 30.0 | 3780 | 0.5588 | 0.6304 | 0.7256 | 0.6746 | 0.9050 |
|
88 |
+
| 0.0321 | 31.0 | 3906 | 0.5579 | 0.6366 | 0.7190 | 0.6753 | 0.9067 |
|
89 |
+
| 0.0283 | 32.0 | 4032 | 0.5785 | 0.6469 | 0.7163 | 0.6798 | 0.9067 |
|
90 |
+
| 0.0284 | 33.0 | 4158 | 0.5698 | 0.6357 | 0.7246 | 0.6773 | 0.9073 |
|
91 |
+
| 0.0256 | 34.0 | 4284 | 0.5816 | 0.6333 | 0.7314 | 0.6788 | 0.9066 |
|
92 |
+
| 0.0231 | 35.0 | 4410 | 0.6032 | 0.6273 | 0.7276 | 0.6737 | 0.9059 |
|
93 |
+
| 0.0223 | 36.0 | 4536 | 0.6044 | 0.6317 | 0.7238 | 0.6746 | 0.9067 |
|
94 |
+
| 0.0225 | 37.0 | 4662 | 0.6007 | 0.6243 | 0.7246 | 0.6707 | 0.9060 |
|
95 |
+
| 0.0209 | 38.0 | 4788 | 0.6072 | 0.6325 | 0.7213 | 0.6740 | 0.9067 |
|
96 |
+
| 0.0199 | 39.0 | 4914 | 0.6145 | 0.6379 | 0.7261 | 0.6791 | 0.9075 |
|
97 |
+
| 0.018 | 40.0 | 5040 | 0.6299 | 0.6412 | 0.7341 | 0.6845 | 0.9070 |
|
98 |
+
| 0.0174 | 41.0 | 5166 | 0.6264 | 0.6448 | 0.7299 | 0.6847 | 0.9069 |
|
99 |
+
| 0.0172 | 42.0 | 5292 | 0.6389 | 0.6409 | 0.7369 | 0.6856 | 0.9061 |
|
100 |
+
| 0.0155 | 43.0 | 5418 | 0.6489 | 0.6381 | 0.7241 | 0.6784 | 0.9071 |
|
101 |
+
| 0.0156 | 44.0 | 5544 | 0.6418 | 0.6384 | 0.7339 | 0.6828 | 0.9065 |
|
102 |
+
| 0.0143 | 45.0 | 5670 | 0.6503 | 0.6378 | 0.7243 | 0.6783 | 0.9066 |
|
103 |
+
| 0.0149 | 46.0 | 5796 | 0.6506 | 0.6463 | 0.7339 | 0.6873 | 0.9081 |
|
104 |
+
| 0.0135 | 47.0 | 5922 | 0.6497 | 0.6432 | 0.7294 | 0.6836 | 0.9072 |
|
105 |
+
| 0.0135 | 48.0 | 6048 | 0.6563 | 0.6389 | 0.7256 | 0.6795 | 0.9069 |
|
106 |
+
| 0.013 | 49.0 | 6174 | 0.6599 | 0.6377 | 0.7306 | 0.6810 | 0.9066 |
|
107 |
+
| 0.0125 | 50.0 | 6300 | 0.6582 | 0.6380 | 0.7278 | 0.6800 | 0.9070 |
|
108 |
+
|
109 |
+
|
110 |
+
### Framework versions
|
111 |
+
|
112 |
+
- Transformers 4.35.2
|
113 |
+
- Pytorch 2.1.0+cu121
|
114 |
+
- Datasets 2.16.1
|
115 |
+
- Tokenizers 0.15.0
|
adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "hfl/chinese-roberta-wwm-ext",
|
5 |
+
"bias": "all",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 16,
|
13 |
+
"lora_dropout": 0.1,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 16,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"query",
|
23 |
+
"value"
|
24 |
+
],
|
25 |
+
"task_type": "TOKEN_CLS"
|
26 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef4c10d48a657f65217ee3e885b734d20d94ac2670b2e3a91659bbc03f148dc0
|
3 |
+
size 2877116
|
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": true,
|
47 |
+
"ignore_mismatched_sizes": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 1000000000000000019884624838656,
|
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 sha256:3d35f81a077bde2f5aac06feb307d86c2050ee10d915d772c291f899df31b361
|
3 |
+
size 4600
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|