abd-ur commited on
Commit
733f0d1
·
verified ·
1 Parent(s): 8e781a3

biobert-variant-lora

Browse files
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: dmis-lab/biobert-base-cased-v1.1
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: results
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # results
17
+
18
+ This model is a fine-tuned version of [dmis-lab/biobert-base-cased-v1.1](https://huggingface.co/dmis-lab/biobert-base-cased-v1.1) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 3.2504
21
+ - Accuracy: 0.0909
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 2e-05
41
+ - train_batch_size: 16
42
+ - eval_batch_size: 16
43
+ - seed: 42
44
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 3
47
+
48
+ ### Training results
49
+
50
+
51
+
52
+ ### Framework versions
53
+
54
+ - Transformers 4.57.1
55
+ - Pytorch 2.8.0+cu126
56
+ - Datasets 4.0.0
57
+ - Tokenizers 0.22.1
config.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "Benign; No actionable therapy. [COSMIC]",
13
+ "1": "Benign; No actionable therapy. [ClinVar]",
14
+ "2": "Benign; No actionable therapy. [OncoKB]",
15
+ "3": "Founder mutation; Genetic counseling required. [COSMIC]",
16
+ "4": "Founder mutation; Genetic counseling required. [ClinVar]",
17
+ "5": "Founder mutation; Genetic counseling required. [OncoKB]",
18
+ "6": "Likely oncogenic; Chemo to moderate extent. [COSMIC]",
19
+ "7": "Likely oncogenic; Chemo to moderate extent. [ClinVar]",
20
+ "8": "Likely oncogenic; Chemo to moderate extent. [OncoKB]",
21
+ "9": "Likely pathogenic; PARP inhibitors recommended. [COSMIC]",
22
+ "10": "Likely pathogenic; PARP inhibitors recommended. [ClinVar]",
23
+ "11": "Likely pathogenic; PARP inhibitors recommended. [OncoKB]",
24
+ "12": "Oncogenic; TKI therapy (osimertinib). [COSMIC]",
25
+ "13": "Oncogenic; TKI therapy (osimertinib). [ClinVar]",
26
+ "14": "Oncogenic; TKI therapy (osimertinib). [OncoKB]",
27
+ "15": "Pathogenic; Immunotherapy (pembrolizumab) advised. [COSMIC]",
28
+ "16": "Pathogenic; Immunotherapy (pembrolizumab) advised. [ClinVar]",
29
+ "17": "Pathogenic; Immunotherapy (pembrolizumab) advised. [OncoKB]",
30
+ "18": "Pathogenic; Level 1 evidence for olaparib. [COSMIC]",
31
+ "19": "Pathogenic; Level 1 evidence for olaparib. [ClinVar]",
32
+ "20": "Pathogenic; Level 1 evidence for olaparib. [OncoKB]",
33
+ "21": "Resistance mutation; Switch to alternative TKI. [COSMIC]",
34
+ "22": "Resistance mutation; Switch to alternative TKI. [ClinVar]",
35
+ "23": "Resistance mutation; Switch to alternative TKI. [OncoKB]",
36
+ "24": "Truncating variant; Radiation not advised. [COSMIC]",
37
+ "25": "Truncating variant; Radiation not advised. [ClinVar]",
38
+ "26": "Truncating variant; Radiation not advised. [OncoKB]",
39
+ "27": "VUS; Monitor and consider trials. [COSMIC]",
40
+ "28": "VUS; Monitor and consider trials. [ClinVar]",
41
+ "29": "VUS; Monitor and consider trials. [OncoKB]"
42
+ },
43
+ "initializer_range": 0.02,
44
+ "intermediate_size": 3072,
45
+ "label2id": {
46
+ "Benign; No actionable therapy. [COSMIC]": 0,
47
+ "Benign; No actionable therapy. [ClinVar]": 1,
48
+ "Benign; No actionable therapy. [OncoKB]": 2,
49
+ "Founder mutation; Genetic counseling required. [COSMIC]": 3,
50
+ "Founder mutation; Genetic counseling required. [ClinVar]": 4,
51
+ "Founder mutation; Genetic counseling required. [OncoKB]": 5,
52
+ "Likely oncogenic; Chemo to moderate extent. [COSMIC]": 6,
53
+ "Likely oncogenic; Chemo to moderate extent. [ClinVar]": 7,
54
+ "Likely oncogenic; Chemo to moderate extent. [OncoKB]": 8,
55
+ "Likely pathogenic; PARP inhibitors recommended. [COSMIC]": 9,
56
+ "Likely pathogenic; PARP inhibitors recommended. [ClinVar]": 10,
57
+ "Likely pathogenic; PARP inhibitors recommended. [OncoKB]": 11,
58
+ "Oncogenic; TKI therapy (osimertinib). [COSMIC]": 12,
59
+ "Oncogenic; TKI therapy (osimertinib). [ClinVar]": 13,
60
+ "Oncogenic; TKI therapy (osimertinib). [OncoKB]": 14,
61
+ "Pathogenic; Immunotherapy (pembrolizumab) advised. [COSMIC]": 15,
62
+ "Pathogenic; Immunotherapy (pembrolizumab) advised. [ClinVar]": 16,
63
+ "Pathogenic; Immunotherapy (pembrolizumab) advised. [OncoKB]": 17,
64
+ "Pathogenic; Level 1 evidence for olaparib. [COSMIC]": 18,
65
+ "Pathogenic; Level 1 evidence for olaparib. [ClinVar]": 19,
66
+ "Pathogenic; Level 1 evidence for olaparib. [OncoKB]": 20,
67
+ "Resistance mutation; Switch to alternative TKI. [COSMIC]": 21,
68
+ "Resistance mutation; Switch to alternative TKI. [ClinVar]": 22,
69
+ "Resistance mutation; Switch to alternative TKI. [OncoKB]": 23,
70
+ "Truncating variant; Radiation not advised. [COSMIC]": 24,
71
+ "Truncating variant; Radiation not advised. [ClinVar]": 25,
72
+ "Truncating variant; Radiation not advised. [OncoKB]": 26,
73
+ "VUS; Monitor and consider trials. [COSMIC]": 27,
74
+ "VUS; Monitor and consider trials. [ClinVar]": 28,
75
+ "VUS; Monitor and consider trials. [OncoKB]": 29
76
+ },
77
+ "layer_norm_eps": 1e-12,
78
+ "max_position_embeddings": 512,
79
+ "model_type": "bert",
80
+ "num_attention_heads": 12,
81
+ "num_hidden_layers": 12,
82
+ "pad_token_id": 0,
83
+ "position_embedding_type": "absolute",
84
+ "problem_type": "single_label_classification",
85
+ "transformers_version": "4.57.1",
86
+ "type_vocab_size": 2,
87
+ "use_cache": true,
88
+ "vocab_size": 28996
89
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff22039834cf46a0321c68a650c7d7cf8d64f6246d13a55f484416110b84abe5
3
+ size 433356896
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": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
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 sha256:765d43690aa93aff13622db2c66d8f4f27efdc182b04d60f4a523f3d00731775
3
+ size 5777
vocab.txt ADDED
The diff for this file is too large to render. See raw diff