Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +50 -0
- pytorch_model.bin +3 -0
- runs/Jul20_10-38-26_jordy-OMEN/1658306318.2062273/events.out.tfevents.1658306318.jordy-OMEN.25591.1 +3 -0
- runs/Jul20_10-38-26_jordy-OMEN/events.out.tfevents.1658306318.jordy-OMEN.25591.0 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dmis-lab/biobert-base-cased-v1.2",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
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": "O",
|
13 |
+
"1": "I-entity"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 3072,
|
17 |
+
"label2id": {
|
18 |
+
"I-entity": 1,
|
19 |
+
"O": 0
|
20 |
+
},
|
21 |
+
"layer_norm_eps": 1e-12,
|
22 |
+
"max_position_embeddings": 512,
|
23 |
+
"model_type": "bert",
|
24 |
+
"num_attention_heads": 12,
|
25 |
+
"num_hidden_layers": 12,
|
26 |
+
"pad_token_id": 0,
|
27 |
+
"position_embedding_type": "absolute",
|
28 |
+
"test_args": {
|
29 |
+
"CRF": false,
|
30 |
+
"Y": "ner_tags",
|
31 |
+
"dataset": "ncbi_disease",
|
32 |
+
"lowC": true,
|
33 |
+
"model": "dmis-lab/biobert-base-cased-v1.2",
|
34 |
+
"setting": "ncbi",
|
35 |
+
"subword_alignment": "first",
|
36 |
+
"task": "ner",
|
37 |
+
"train_args": {
|
38 |
+
"batch_size": 2,
|
39 |
+
"epochs": 3,
|
40 |
+
"learning_rate": 2e-05,
|
41 |
+
"warmup_ratio": 0.1,
|
42 |
+
"weight_decay": 0.01
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"torch_dtype": "float32",
|
46 |
+
"transformers_version": "4.18.0",
|
47 |
+
"type_vocab_size": 2,
|
48 |
+
"use_cache": true,
|
49 |
+
"vocab_size": 28996
|
50 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1102948ae4893dc6d3f988a9fc7681b17b582c78093be4f0d291dec591fab528
|
3 |
+
size 430955313
|
runs/Jul20_10-38-26_jordy-OMEN/1658306318.2062273/events.out.tfevents.1658306318.jordy-OMEN.25591.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e504a62e772b5325ccf0abf109a8fd5ab4479284f5b066750ab946dc59c14b19
|
3 |
+
size 4958
|
runs/Jul20_10-38-26_jordy-OMEN/events.out.tfevents.1658306318.jordy-OMEN.25591.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:717eb3d1539b33c6717b256cfcf2c53af7fff8537fba1300de7adcf5220ed695
|
3 |
+
size 5183
|
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.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": true, "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, "name_or_path": "dmis-lab/biobert-base-cased-v1.2", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77e4ae8164c5f894636a1892deca3f31199ed8966d20d5340f81c03b2a59a98d
|
3 |
+
size 3119
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|