Commit
•
ae3c37a
1
Parent(s):
542acce
End of training
Browse files- README.md +52 -0
- config.json +42 -0
- model.safetensors +3 -0
- runs/Feb07_07-54-51_3eaf2d916f9a/events.out.tfevents.1707292493.3eaf2d916f9a.4746.3 +3 -0
- runs/Feb07_07-59-26_3eaf2d916f9a/events.out.tfevents.1707292768.3eaf2d916f9a.4746.4 +3 -0
- runs/Feb07_08-12-53_3eaf2d916f9a/events.out.tfevents.1707293574.3eaf2d916f9a.4746.5 +3 -0
- runs/Feb07_08-16-54_3eaf2d916f9a/events.out.tfevents.1707293815.3eaf2d916f9a.4746.6 +3 -0
- runs/Feb07_08-25-53_3eaf2d916f9a/events.out.tfevents.1707294354.3eaf2d916f9a.4746.7 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +60 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: d4data/biomedical-ner-all
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: medicalBERT
|
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 |
+
# medicalBERT
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [d4data/biomedical-ner-all](https://huggingface.co/d4data/biomedical-ner-all) on the None dataset.
|
17 |
+
|
18 |
+
## Model description
|
19 |
+
|
20 |
+
More information needed
|
21 |
+
|
22 |
+
## Intended uses & limitations
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Training and evaluation data
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training procedure
|
31 |
+
|
32 |
+
### Training hyperparameters
|
33 |
+
|
34 |
+
The following hyperparameters were used during training:
|
35 |
+
- learning_rate: 5e-05
|
36 |
+
- train_batch_size: 1
|
37 |
+
- eval_batch_size: 8
|
38 |
+
- seed: 42
|
39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
+
- lr_scheduler_type: linear
|
41 |
+
- num_epochs: 30
|
42 |
+
|
43 |
+
### Training results
|
44 |
+
|
45 |
+
|
46 |
+
|
47 |
+
### Framework versions
|
48 |
+
|
49 |
+
- Transformers 4.35.2
|
50 |
+
- Pytorch 2.1.0+cu121
|
51 |
+
- Datasets 2.16.1
|
52 |
+
- Tokenizers 0.15.1
|
config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "d4data/biomedical-ner-all",
|
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": "LABEL_0",
|
13 |
+
"1": "LABEL_1",
|
14 |
+
"2": "LABEL_2",
|
15 |
+
"3": "LABEL_3",
|
16 |
+
"4": "LABEL_4",
|
17 |
+
"5": "LABEL_5",
|
18 |
+
"6": "LABEL_6"
|
19 |
+
},
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"label2id": {
|
22 |
+
"LABEL_0": 0,
|
23 |
+
"LABEL_1": 1,
|
24 |
+
"LABEL_2": 2,
|
25 |
+
"LABEL_3": 3,
|
26 |
+
"LABEL_4": 4,
|
27 |
+
"LABEL_5": 5,
|
28 |
+
"LABEL_6": 6
|
29 |
+
},
|
30 |
+
"max_position_embeddings": 512,
|
31 |
+
"model_type": "distilbert",
|
32 |
+
"n_heads": 12,
|
33 |
+
"n_layers": 6,
|
34 |
+
"pad_token_id": 0,
|
35 |
+
"qa_dropout": 0.1,
|
36 |
+
"seq_classif_dropout": 0.2,
|
37 |
+
"sinusoidal_pos_embds": false,
|
38 |
+
"tie_weights_": true,
|
39 |
+
"torch_dtype": "float32",
|
40 |
+
"transformers_version": "4.35.2",
|
41 |
+
"vocab_size": 30522
|
42 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7874c719e549e749003c74fd5726f9e317c98ac99342a21b8a934e808a953bfd
|
3 |
+
size 265485396
|
runs/Feb07_07-54-51_3eaf2d916f9a/events.out.tfevents.1707292493.3eaf2d916f9a.4746.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09ab91cb85fabb785a287860b3216dde4dfa54f9b4bc131dab6142dd0189f319
|
3 |
+
size 4770
|
runs/Feb07_07-59-26_3eaf2d916f9a/events.out.tfevents.1707292768.3eaf2d916f9a.4746.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7799961af6ce2c632842a7de3e9ed8c995b30ab4e7db66dcdc0971a3539ac495
|
3 |
+
size 4771
|
runs/Feb07_08-12-53_3eaf2d916f9a/events.out.tfevents.1707293574.3eaf2d916f9a.4746.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:794b292d4f59275403d77408bd4b5797eb831a72f6830d824e67c7dae129d30c
|
3 |
+
size 4769
|
runs/Feb07_08-16-54_3eaf2d916f9a/events.out.tfevents.1707293815.3eaf2d916f9a.4746.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74c7942d9d453731220eaa57feed2b60daeae48157e3d301a365130fc1811c1f
|
3 |
+
size 4769
|
runs/Feb07_08-25-53_3eaf2d916f9a/events.out.tfevents.1707294354.3eaf2d916f9a.4746.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5891e089b02f0aac65b52198148a2ebc10daea7f81da106a91fad6b969560171
|
3 |
+
size 4769
|
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 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"cuda": 0,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"max_length": 512,
|
50 |
+
"model_max_length": 512,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"stride": 0,
|
54 |
+
"strip_accents": null,
|
55 |
+
"tokenize_chinese_chars": true,
|
56 |
+
"tokenizer_class": "DistilBertTokenizer",
|
57 |
+
"truncation_side": "right",
|
58 |
+
"truncation_strategy": "longest_first",
|
59 |
+
"unk_token": "[UNK]"
|
60 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee15d40abac2acdf49d70ade63ce1794c31a44dfce372ec08f1c9135f04e843f
|
3 |
+
size 4536
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|