Commit
·
bee5c12
1
Parent(s):
8a978a7
Training in progress, epoch 0
Browse files- config.json +95 -0
- model.safetensors +3 -0
- runs/Dec23_18-28-06_d680a7b3f78e/events.out.tfevents.1703356087.d680a7b3f78e.799.0 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "medicalai/ClinicalBERT",
|
| 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": "B-Amino_acid",
|
| 13 |
+
"1": "B-Anatomical_system",
|
| 14 |
+
"2": "B-Cancer",
|
| 15 |
+
"3": "B-Cell",
|
| 16 |
+
"4": "B-Cellular_component",
|
| 17 |
+
"5": "B-Developing_anatomical_structure",
|
| 18 |
+
"6": "B-Gene_or_gene_product",
|
| 19 |
+
"7": "B-Immaterial_anatomical_entity",
|
| 20 |
+
"8": "B-Multi-tissue_structure",
|
| 21 |
+
"9": "B-Organ",
|
| 22 |
+
"10": "B-Organism",
|
| 23 |
+
"11": "B-Organism_subdivision",
|
| 24 |
+
"12": "B-Organism_substance",
|
| 25 |
+
"13": "B-Pathological_formation",
|
| 26 |
+
"14": "B-Simple_chemical",
|
| 27 |
+
"15": "B-Tissue",
|
| 28 |
+
"16": "I-Amino_acid",
|
| 29 |
+
"17": "I-Anatomical_system",
|
| 30 |
+
"18": "I-Cancer",
|
| 31 |
+
"19": "I-Cell",
|
| 32 |
+
"20": "I-Cellular_component",
|
| 33 |
+
"21": "I-Developing_anatomical_structure",
|
| 34 |
+
"22": "I-Gene_or_gene_product",
|
| 35 |
+
"23": "I-Immaterial_anatomical_entity",
|
| 36 |
+
"24": "I-Multi-tissue_structure",
|
| 37 |
+
"25": "I-Organ",
|
| 38 |
+
"26": "I-Organism",
|
| 39 |
+
"27": "I-Organism_subdivision",
|
| 40 |
+
"28": "I-Organism_substance",
|
| 41 |
+
"29": "I-Pathological_formation",
|
| 42 |
+
"30": "I-Simple_chemical",
|
| 43 |
+
"31": "I-Tissue",
|
| 44 |
+
"32": "O"
|
| 45 |
+
},
|
| 46 |
+
"initializer_range": 0.02,
|
| 47 |
+
"label2id": {
|
| 48 |
+
"B-Amino_acid": 0,
|
| 49 |
+
"B-Anatomical_system": 1,
|
| 50 |
+
"B-Cancer": 2,
|
| 51 |
+
"B-Cell": 3,
|
| 52 |
+
"B-Cellular_component": 4,
|
| 53 |
+
"B-Developing_anatomical_structure": 5,
|
| 54 |
+
"B-Gene_or_gene_product": 6,
|
| 55 |
+
"B-Immaterial_anatomical_entity": 7,
|
| 56 |
+
"B-Multi-tissue_structure": 8,
|
| 57 |
+
"B-Organ": 9,
|
| 58 |
+
"B-Organism": 10,
|
| 59 |
+
"B-Organism_subdivision": 11,
|
| 60 |
+
"B-Organism_substance": 12,
|
| 61 |
+
"B-Pathological_formation": 13,
|
| 62 |
+
"B-Simple_chemical": 14,
|
| 63 |
+
"B-Tissue": 15,
|
| 64 |
+
"I-Amino_acid": 16,
|
| 65 |
+
"I-Anatomical_system": 17,
|
| 66 |
+
"I-Cancer": 18,
|
| 67 |
+
"I-Cell": 19,
|
| 68 |
+
"I-Cellular_component": 20,
|
| 69 |
+
"I-Developing_anatomical_structure": 21,
|
| 70 |
+
"I-Gene_or_gene_product": 22,
|
| 71 |
+
"I-Immaterial_anatomical_entity": 23,
|
| 72 |
+
"I-Multi-tissue_structure": 24,
|
| 73 |
+
"I-Organ": 25,
|
| 74 |
+
"I-Organism": 26,
|
| 75 |
+
"I-Organism_subdivision": 27,
|
| 76 |
+
"I-Organism_substance": 28,
|
| 77 |
+
"I-Pathological_formation": 29,
|
| 78 |
+
"I-Simple_chemical": 30,
|
| 79 |
+
"I-Tissue": 31,
|
| 80 |
+
"O": 32
|
| 81 |
+
},
|
| 82 |
+
"max_position_embeddings": 512,
|
| 83 |
+
"model_type": "distilbert",
|
| 84 |
+
"n_heads": 12,
|
| 85 |
+
"n_layers": 6,
|
| 86 |
+
"output_past": true,
|
| 87 |
+
"pad_token_id": 0,
|
| 88 |
+
"qa_dropout": 0.1,
|
| 89 |
+
"seq_classif_dropout": 0.2,
|
| 90 |
+
"sinusoidal_pos_embds": false,
|
| 91 |
+
"tie_weights_": true,
|
| 92 |
+
"torch_dtype": "float32",
|
| 93 |
+
"transformers_version": "4.35.2",
|
| 94 |
+
"vocab_size": 119547
|
| 95 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ac6c06e7da5ef2116cc3382c5755e83c1592c96a1bbaf5465f40180899e0cde
|
| 3 |
+
size 539050188
|
runs/Dec23_18-28-06_d680a7b3f78e/events.out.tfevents.1703356087.d680a7b3f78e.799.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5df46290eab79b91d298ad369bc5c29dfc52580d7b8c5d5e826b34feb1ed1bc
|
| 3 |
+
size 6620
|
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 |
+
"full_tokenizer_file": null,
|
| 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": "DistilBertTokenizer",
|
| 57 |
+
"unk_token": "[UNK]"
|
| 58 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:650ea6c2657b620781e2189168567178258709de60fec9134ff37c085cf6cbad
|
| 3 |
+
size 4600
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|