IkbeneenEric commited on
Commit
082de0d
1 Parent(s): ccd42fe

Initial push clinical history Mekkes model

Browse files
config.json ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract",
3
+ "architectures": [
4
+ "BertForMultiLabelSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
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
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9",
22
+ "10": "LABEL_10",
23
+ "11": "LABEL_11",
24
+ "12": "LABEL_12",
25
+ "13": "LABEL_13",
26
+ "14": "LABEL_14",
27
+ "15": "LABEL_15",
28
+ "16": "LABEL_16",
29
+ "17": "LABEL_17",
30
+ "18": "LABEL_18",
31
+ "19": "LABEL_19",
32
+ "20": "LABEL_20",
33
+ "21": "LABEL_21",
34
+ "22": "LABEL_22",
35
+ "23": "LABEL_23",
36
+ "24": "LABEL_24",
37
+ "25": "LABEL_25",
38
+ "26": "LABEL_26",
39
+ "27": "LABEL_27",
40
+ "28": "LABEL_28",
41
+ "29": "LABEL_29",
42
+ "30": "LABEL_30",
43
+ "31": "LABEL_31",
44
+ "32": "LABEL_32",
45
+ "33": "LABEL_33",
46
+ "34": "LABEL_34",
47
+ "35": "LABEL_35",
48
+ "36": "LABEL_36",
49
+ "37": "LABEL_37",
50
+ "38": "LABEL_38",
51
+ "39": "LABEL_39",
52
+ "40": "LABEL_40",
53
+ "41": "LABEL_41",
54
+ "42": "LABEL_42",
55
+ "43": "LABEL_43",
56
+ "44": "LABEL_44",
57
+ "45": "LABEL_45",
58
+ "46": "LABEL_46",
59
+ "47": "LABEL_47",
60
+ "48": "LABEL_48",
61
+ "49": "LABEL_49",
62
+ "50": "LABEL_50",
63
+ "51": "LABEL_51",
64
+ "52": "LABEL_52",
65
+ "53": "LABEL_53",
66
+ "54": "LABEL_54",
67
+ "55": "LABEL_55",
68
+ "56": "LABEL_56",
69
+ "57": "LABEL_57",
70
+ "58": "LABEL_58",
71
+ "59": "LABEL_59",
72
+ "60": "LABEL_60",
73
+ "61": "LABEL_61",
74
+ "62": "LABEL_62",
75
+ "63": "LABEL_63",
76
+ "64": "LABEL_64",
77
+ "65": "LABEL_65",
78
+ "66": "LABEL_66",
79
+ "67": "LABEL_67",
80
+ "68": "LABEL_68",
81
+ "69": "LABEL_69",
82
+ "70": "LABEL_70",
83
+ "71": "LABEL_71",
84
+ "72": "LABEL_72",
85
+ "73": "LABEL_73",
86
+ "74": "LABEL_74",
87
+ "75": "LABEL_75",
88
+ "76": "LABEL_76",
89
+ "77": "LABEL_77",
90
+ "78": "LABEL_78",
91
+ "79": "LABEL_79",
92
+ "80": "LABEL_80",
93
+ "81": "LABEL_81",
94
+ "82": "LABEL_82",
95
+ "83": "LABEL_83",
96
+ "84": "LABEL_84",
97
+ "85": "LABEL_85",
98
+ "86": "LABEL_86",
99
+ "87": "LABEL_87",
100
+ "88": "LABEL_88",
101
+ "89": "LABEL_89"
102
+ },
103
+ "initializer_range": 0.02,
104
+ "intermediate_size": 3072,
105
+ "label2id": {
106
+ "LABEL_0": 0,
107
+ "LABEL_1": 1,
108
+ "LABEL_10": 10,
109
+ "LABEL_11": 11,
110
+ "LABEL_12": 12,
111
+ "LABEL_13": 13,
112
+ "LABEL_14": 14,
113
+ "LABEL_15": 15,
114
+ "LABEL_16": 16,
115
+ "LABEL_17": 17,
116
+ "LABEL_18": 18,
117
+ "LABEL_19": 19,
118
+ "LABEL_2": 2,
119
+ "LABEL_20": 20,
120
+ "LABEL_21": 21,
121
+ "LABEL_22": 22,
122
+ "LABEL_23": 23,
123
+ "LABEL_24": 24,
124
+ "LABEL_25": 25,
125
+ "LABEL_26": 26,
126
+ "LABEL_27": 27,
127
+ "LABEL_28": 28,
128
+ "LABEL_29": 29,
129
+ "LABEL_3": 3,
130
+ "LABEL_30": 30,
131
+ "LABEL_31": 31,
132
+ "LABEL_32": 32,
133
+ "LABEL_33": 33,
134
+ "LABEL_34": 34,
135
+ "LABEL_35": 35,
136
+ "LABEL_36": 36,
137
+ "LABEL_37": 37,
138
+ "LABEL_38": 38,
139
+ "LABEL_39": 39,
140
+ "LABEL_4": 4,
141
+ "LABEL_40": 40,
142
+ "LABEL_41": 41,
143
+ "LABEL_42": 42,
144
+ "LABEL_43": 43,
145
+ "LABEL_44": 44,
146
+ "LABEL_45": 45,
147
+ "LABEL_46": 46,
148
+ "LABEL_47": 47,
149
+ "LABEL_48": 48,
150
+ "LABEL_49": 49,
151
+ "LABEL_5": 5,
152
+ "LABEL_50": 50,
153
+ "LABEL_51": 51,
154
+ "LABEL_52": 52,
155
+ "LABEL_53": 53,
156
+ "LABEL_54": 54,
157
+ "LABEL_55": 55,
158
+ "LABEL_56": 56,
159
+ "LABEL_57": 57,
160
+ "LABEL_58": 58,
161
+ "LABEL_59": 59,
162
+ "LABEL_6": 6,
163
+ "LABEL_60": 60,
164
+ "LABEL_61": 61,
165
+ "LABEL_62": 62,
166
+ "LABEL_63": 63,
167
+ "LABEL_64": 64,
168
+ "LABEL_65": 65,
169
+ "LABEL_66": 66,
170
+ "LABEL_67": 67,
171
+ "LABEL_68": 68,
172
+ "LABEL_69": 69,
173
+ "LABEL_7": 7,
174
+ "LABEL_70": 70,
175
+ "LABEL_71": 71,
176
+ "LABEL_72": 72,
177
+ "LABEL_73": 73,
178
+ "LABEL_74": 74,
179
+ "LABEL_75": 75,
180
+ "LABEL_76": 76,
181
+ "LABEL_77": 77,
182
+ "LABEL_78": 78,
183
+ "LABEL_79": 79,
184
+ "LABEL_8": 8,
185
+ "LABEL_80": 80,
186
+ "LABEL_81": 81,
187
+ "LABEL_82": 82,
188
+ "LABEL_83": 83,
189
+ "LABEL_84": 84,
190
+ "LABEL_85": 85,
191
+ "LABEL_86": 86,
192
+ "LABEL_87": 87,
193
+ "LABEL_88": 88,
194
+ "LABEL_89": 89,
195
+ "LABEL_9": 9
196
+ },
197
+ "layer_norm_eps": 1e-12,
198
+ "max_position_embeddings": 512,
199
+ "model_type": "bert",
200
+ "num_attention_heads": 12,
201
+ "num_hidden_layers": 12,
202
+ "pad_token_id": 0,
203
+ "position_embedding_type": "absolute",
204
+ "torch_dtype": "float32",
205
+ "transformers_version": "4.16.1",
206
+ "type_vocab_size": 2,
207
+ "use_cache": true,
208
+ "vocab_size": 30522
209
+ }
model_args.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"adafactor_beta1": null, "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_eps": [1e-30, 0.001], "adafactor_relative_step": true, "adafactor_scale_parameter": true, "adafactor_warmup_init": true, "adam_epsilon": 1e-08, "best_model_dir": "outputs/best_model", "cache_dir": "cache_dir/", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "do_lower_case": true, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 3, "encoding": null, "eval_batch_size": 8, "evaluate_during_training": false, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 2000, "evaluate_during_training_verbose": false, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 5.123640376667562e-05, "local_rank": -1, "logging_steps": 50, "loss_type": null, "loss_args": {}, "manual_seed": 2, "max_grad_norm": 1.0, "max_seq_length": 300, "model_name": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract", "model_type": "bert", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 33, "optimizer": "AdamW", "output_dir": "/data/p307948/clinical/models/BERT/bert_2wed/final_model_lenient2", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 10, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": false, "save_model_every_epoch": false, "save_optimizer_and_scheduler": false, "save_steps": -1, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": null, "tokenizer_type": null, "train_batch_size": 16, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_hf_datasets": false, "use_multiprocessing": true, "use_multiprocessing_for_evaluation": true, "wandb_kwargs": {"mode": "disabled"}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 2343, "weight_decay": 0.0, "model_class": "MultiLabelClassificationModel", "sliding_window": false, "stride": 0.8, "threshold": 0.6, "tie_value": 1, "labels_list": [], "labels_map": {}, "lazy_loading": false, "special_tokens_list": []}
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:830f568ab145fb4eac739b145585af7f68653a680a1a83b176e5514630b9b441
3
+ size 438293079
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract", "tokenizer_class": "BertTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84efd229ae6bcbe3d965e0f9f48d2f7f1c19d92b20d49b08140d26d2bd053118
3
+ size 3119
vocab.txt ADDED
The diff for this file is too large to render. See raw diff