prajwalJumde
commited on
Commit
•
c78c234
1
Parent(s):
c0b8c4e
Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +94 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "allenai/longformer-base-4096",
|
3 |
+
"architectures": [
|
4 |
+
"LongformerForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_mode": "longformer",
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"attention_window": [
|
9 |
+
512,
|
10 |
+
512,
|
11 |
+
512,
|
12 |
+
512,
|
13 |
+
512,
|
14 |
+
512,
|
15 |
+
512,
|
16 |
+
512,
|
17 |
+
512,
|
18 |
+
512,
|
19 |
+
512,
|
20 |
+
512
|
21 |
+
],
|
22 |
+
"bos_token_id": 0,
|
23 |
+
"eos_token_id": 2,
|
24 |
+
"gradient_checkpointing": false,
|
25 |
+
"hidden_act": "gelu",
|
26 |
+
"hidden_dropout_prob": 0.1,
|
27 |
+
"hidden_size": 768,
|
28 |
+
"id2label": {
|
29 |
+
"0": "medical_emergency_dept",
|
30 |
+
"1": "billing",
|
31 |
+
"2": "medical_office_visit",
|
32 |
+
"3": "medical_follow_up",
|
33 |
+
"4": "medical_medication",
|
34 |
+
"5": "medical_history_and_physical",
|
35 |
+
"6": "medical_consultation",
|
36 |
+
"7": "medical_clinical_coding_summary",
|
37 |
+
"8": "medical_diagnostics",
|
38 |
+
"9": "medical_lab_reports",
|
39 |
+
"10": "medical_operative_reports",
|
40 |
+
"11": "deposition_records",
|
41 |
+
"12": "medical_clinical_orders",
|
42 |
+
"13": "medical_clinical_record",
|
43 |
+
"14": "subpoena",
|
44 |
+
"15": "other",
|
45 |
+
"16": "blank",
|
46 |
+
"17": "claim_documents",
|
47 |
+
"18": "medical_procedure",
|
48 |
+
"19": "medical_discharge_summary",
|
49 |
+
"20": "letter_from_insurance",
|
50 |
+
"21": "illegible_page",
|
51 |
+
"22": "medical_physical_therapy"
|
52 |
+
},
|
53 |
+
"ignore_attention_mask": false,
|
54 |
+
"initializer_range": 0.02,
|
55 |
+
"intermediate_size": 3072,
|
56 |
+
"label2id": {
|
57 |
+
"billing": 1,
|
58 |
+
"blank": 16,
|
59 |
+
"claim_documents": 17,
|
60 |
+
"deposition_records": 11,
|
61 |
+
"illegible_page": 21,
|
62 |
+
"letter_from_insurance": 20,
|
63 |
+
"medical_clinical_coding_summary": 7,
|
64 |
+
"medical_clinical_orders": 12,
|
65 |
+
"medical_clinical_record": 13,
|
66 |
+
"medical_consultation": 6,
|
67 |
+
"medical_diagnostics": 8,
|
68 |
+
"medical_discharge_summary": 19,
|
69 |
+
"medical_emergency_dept": 0,
|
70 |
+
"medical_follow_up": 3,
|
71 |
+
"medical_history_and_physical": 5,
|
72 |
+
"medical_lab_reports": 9,
|
73 |
+
"medical_medication": 4,
|
74 |
+
"medical_office_visit": 2,
|
75 |
+
"medical_operative_reports": 10,
|
76 |
+
"medical_physical_therapy": 22,
|
77 |
+
"medical_procedure": 18,
|
78 |
+
"other": 15,
|
79 |
+
"subpoena": 14
|
80 |
+
},
|
81 |
+
"layer_norm_eps": 1e-05,
|
82 |
+
"max_position_embeddings": 4098,
|
83 |
+
"model_type": "longformer",
|
84 |
+
"num_attention_heads": 12,
|
85 |
+
"num_hidden_layers": 12,
|
86 |
+
"onnx_export": false,
|
87 |
+
"pad_token_id": 1,
|
88 |
+
"problem_type": "single_label_classification",
|
89 |
+
"sep_token_id": 2,
|
90 |
+
"torch_dtype": "float32",
|
91 |
+
"transformers_version": "4.32.0.dev0",
|
92 |
+
"type_vocab_size": 1,
|
93 |
+
"vocab_size": 50265
|
94 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1fad6863f04b27dd20edb8b27732268793b91e2b64967fbaddee27d8fbfdc56
|
3 |
+
size 594803857
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<s>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"cls_token": "<s>",
|
6 |
+
"eos_token": "</s>",
|
7 |
+
"errors": "replace",
|
8 |
+
"mask_token": "<mask>",
|
9 |
+
"model_max_length": 4096,
|
10 |
+
"pad_token": "<pad>",
|
11 |
+
"sep_token": "</s>",
|
12 |
+
"tokenizer_class": "LongformerTokenizer",
|
13 |
+
"trim_offsets": true,
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a080731bf109672ec50ef9701d94dc6a2e2244674d197373d7e0d9e9b9529f21
|
3 |
+
size 4027
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|