Granoladata commited on
Commit
d2fbcfa
1 Parent(s): feae055

End of training

Browse files
README.md ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: dmis-lab/biobert-v1.1
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: biobert_modality
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # biobert_modality
14
+
15
+ This model is a fine-tuned version of [dmis-lab/biobert-v1.1](https://huggingface.co/dmis-lab/biobert-v1.1) on an unknown dataset.
16
+
17
+ ## Model description
18
+
19
+ More information needed
20
+
21
+ ## Intended uses & limitations
22
+
23
+ More information needed
24
+
25
+ ## Training and evaluation data
26
+
27
+ More information needed
28
+
29
+ ## Training procedure
30
+
31
+ ### Training hyperparameters
32
+
33
+ The following hyperparameters were used during training:
34
+ - learning_rate: 2e-05
35
+ - train_batch_size: 16
36
+ - eval_batch_size: 16
37
+ - seed: 42
38
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
39
+ - lr_scheduler_type: linear
40
+ - num_epochs: 2
41
+
42
+ ### Framework versions
43
+
44
+ - Transformers 4.42.3
45
+ - Pytorch 2.3.1+cu121
46
+ - Datasets 2.20.0
47
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dmis-lab/biobert-v1.1",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
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": "XR",
14
+ "1": "CT",
15
+ "2": "ULTRASOUND",
16
+ "3": "MR",
17
+ "4": "MAMMOGRAPHY",
18
+ "5": "DXA",
19
+ "6": "PET/CT",
20
+ "7": "NM",
21
+ "8": "RADIO-FLUOROSCOPY",
22
+ "9": "ECHO",
23
+ "10": "RADIOLOGY PROCEDURE",
24
+ "11": "PET/MR"
25
+ },
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 3072,
28
+ "label2id": {
29
+ "ct": 1,
30
+ "dexa": 5,
31
+ "echocardiography": 9,
32
+ "fl": 8,
33
+ "mammo": 4,
34
+ "mr": 3,
35
+ "nm": 7,
36
+ "pet/ct": 6,
37
+ "pet/mr": 11,
38
+ "radiology procedure": 10,
39
+ "us": 2,
40
+ "xray": 0
41
+ },
42
+ "layer_norm_eps": 1e-12,
43
+ "max_position_embeddings": 512,
44
+ "model_type": "bert",
45
+ "num_attention_heads": 12,
46
+ "num_hidden_layers": 12,
47
+ "pad_token_id": 0,
48
+ "position_embedding_type": "absolute",
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.42.3",
51
+ "type_vocab_size": 2,
52
+ "use_cache": true,
53
+ "vocab_size": 28996
54
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1826721ac4f04cf8be2306ad24cccf5b33c960693f4b4308d351fcdd9c706a1
3
+ size 433301528
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 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a94115df0ebc189c6c2b13e71a35c2453e11feca90d95a4d15cb843eb90c687
3
+ size 5112
vocab.txt ADDED
The diff for this file is too large to render. See raw diff