LazzeKappa
commited on
Commit
•
962895b
1
Parent(s):
6a6dfff
End of training
Browse files- README.md +70 -0
- config.json +85 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +13 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: distilbert-base-multilingual-cased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: BERT_B02
|
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 |
+
# BERT_B02
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on the None dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.5303
|
24 |
+
- Precision: 0.5901
|
25 |
+
- Recall: 0.6373
|
26 |
+
- F1: 0.6128
|
27 |
+
- Accuracy: 0.8529
|
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: 4e-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: 5
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
+
| 0.8874 | 1.0 | 47 | 0.7667 | 0.4130 | 0.364 | 0.3870 | 0.7897 |
|
59 |
+
| 0.5169 | 2.0 | 94 | 0.5512 | 0.5390 | 0.608 | 0.5714 | 0.8469 |
|
60 |
+
| 0.3529 | 3.0 | 141 | 0.5238 | 0.5913 | 0.6173 | 0.6040 | 0.8542 |
|
61 |
+
| 0.2603 | 4.0 | 188 | 0.5243 | 0.5926 | 0.6227 | 0.6073 | 0.8521 |
|
62 |
+
| 0.2134 | 5.0 | 235 | 0.5303 | 0.5901 | 0.6373 | 0.6128 | 0.8529 |
|
63 |
+
|
64 |
+
|
65 |
+
### Framework versions
|
66 |
+
|
67 |
+
- Transformers 4.33.3
|
68 |
+
- Pytorch 2.0.1+cu117
|
69 |
+
- Datasets 2.14.4
|
70 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-multilingual-cased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForTokenClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"id2label": {
|
12 |
+
"0": "O",
|
13 |
+
"1": "B-Organisation",
|
14 |
+
"2": "I-Organisation",
|
15 |
+
"3": "B-Nationality",
|
16 |
+
"4": "I-Nationality",
|
17 |
+
"5": "B-Person",
|
18 |
+
"6": "I-Person",
|
19 |
+
"7": "B-DocumentReference",
|
20 |
+
"8": "I-DocumentReference",
|
21 |
+
"9": "B-Location",
|
22 |
+
"10": "I-Location",
|
23 |
+
"11": "B-Money",
|
24 |
+
"12": "I-Money",
|
25 |
+
"13": "B-Vehicle",
|
26 |
+
"14": "I-Vehicle",
|
27 |
+
"15": "B-Temporal",
|
28 |
+
"16": "I-Temporal",
|
29 |
+
"17": "B-Weapon",
|
30 |
+
"18": "I-Weapon",
|
31 |
+
"19": "B-Quantity",
|
32 |
+
"20": "I-Quantity",
|
33 |
+
"21": "B-CommsIdentifier",
|
34 |
+
"22": "B-MilitaryPlatform",
|
35 |
+
"23": "I-MilitaryPlatform",
|
36 |
+
"24": "B-Coordinate",
|
37 |
+
"25": "I-Coordinate",
|
38 |
+
"26": "B-Frequency",
|
39 |
+
"27": "I-Frequency"
|
40 |
+
},
|
41 |
+
"initializer_range": 0.02,
|
42 |
+
"label2id": {
|
43 |
+
"B-CommsIdentifier": 21,
|
44 |
+
"B-Coordinate": 24,
|
45 |
+
"B-DocumentReference": 7,
|
46 |
+
"B-Frequency": 26,
|
47 |
+
"B-Location": 9,
|
48 |
+
"B-MilitaryPlatform": 22,
|
49 |
+
"B-Money": 11,
|
50 |
+
"B-Nationality": 3,
|
51 |
+
"B-Organisation": 1,
|
52 |
+
"B-Person": 5,
|
53 |
+
"B-Quantity": 19,
|
54 |
+
"B-Temporal": 15,
|
55 |
+
"B-Vehicle": 13,
|
56 |
+
"B-Weapon": 17,
|
57 |
+
"I-Coordinate": 25,
|
58 |
+
"I-DocumentReference": 8,
|
59 |
+
"I-Frequency": 27,
|
60 |
+
"I-Location": 10,
|
61 |
+
"I-MilitaryPlatform": 23,
|
62 |
+
"I-Money": 12,
|
63 |
+
"I-Nationality": 4,
|
64 |
+
"I-Organisation": 2,
|
65 |
+
"I-Person": 6,
|
66 |
+
"I-Quantity": 20,
|
67 |
+
"I-Temporal": 16,
|
68 |
+
"I-Vehicle": 14,
|
69 |
+
"I-Weapon": 18,
|
70 |
+
"O": 0
|
71 |
+
},
|
72 |
+
"max_position_embeddings": 512,
|
73 |
+
"model_type": "distilbert",
|
74 |
+
"n_heads": 12,
|
75 |
+
"n_layers": 6,
|
76 |
+
"output_past": true,
|
77 |
+
"pad_token_id": 0,
|
78 |
+
"qa_dropout": 0.1,
|
79 |
+
"seq_classif_dropout": 0.2,
|
80 |
+
"sinusoidal_pos_embds": false,
|
81 |
+
"tie_weights_": true,
|
82 |
+
"torch_dtype": "float32",
|
83 |
+
"transformers_version": "4.33.3",
|
84 |
+
"vocab_size": 119547
|
85 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c86d43ed551891a2f4b5e51660af69667eb3e6a4ad855d669dcac25b7a5bcc5b
|
3 |
+
size 539057253
|
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 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_lower_case": false,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 512,
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"sep_token": "[SEP]",
|
9 |
+
"strip_accents": null,
|
10 |
+
"tokenize_chinese_chars": true,
|
11 |
+
"tokenizer_class": "DistilBertTokenizer",
|
12 |
+
"unk_token": "[UNK]"
|
13 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6324cd055ac99ab3f3ddb304c124160e2ff41d8fd166e94592ef30480704bc6
|
3 |
+
size 3963
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|