Training in progress, epoch 1
Browse files- added_tokens.json +3 -0
- config.json +61 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +16 -0
- tokenizer.json +0 -0
- tokenizer_config.json +69 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[/]": 31116
|
3 |
+
}
|
config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "allenai/scibert_scivocab_cased",
|
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": "X",
|
14 |
+
"2": "B-MethodName",
|
15 |
+
"3": "I-MethodName",
|
16 |
+
"4": "B-HyperparameterName",
|
17 |
+
"5": "I-HyperparameterName",
|
18 |
+
"6": "B-HyperparameterValue",
|
19 |
+
"7": "I-HyperparameterValue",
|
20 |
+
"8": "B-MetricName",
|
21 |
+
"9": "I-MetricName",
|
22 |
+
"10": "B-MetricValue",
|
23 |
+
"11": "I-MetricValue",
|
24 |
+
"12": "B-TaskName",
|
25 |
+
"13": "I-TaskName",
|
26 |
+
"14": "B-DatasetName",
|
27 |
+
"15": "I-DatasetName"
|
28 |
+
},
|
29 |
+
"initializer_range": 0.02,
|
30 |
+
"intermediate_size": 3072,
|
31 |
+
"label2id": {
|
32 |
+
"B-DatasetName": 14,
|
33 |
+
"B-HyperparameterName": 4,
|
34 |
+
"B-HyperparameterValue": 6,
|
35 |
+
"B-MethodName": 2,
|
36 |
+
"B-MetricName": 8,
|
37 |
+
"B-MetricValue": 10,
|
38 |
+
"B-TaskName": 12,
|
39 |
+
"I-DatasetName": 15,
|
40 |
+
"I-HyperparameterName": 5,
|
41 |
+
"I-HyperparameterValue": 7,
|
42 |
+
"I-MethodName": 3,
|
43 |
+
"I-MetricName": 9,
|
44 |
+
"I-MetricValue": 11,
|
45 |
+
"I-TaskName": 13,
|
46 |
+
"O": 0,
|
47 |
+
"X": 1
|
48 |
+
},
|
49 |
+
"layer_norm_eps": 1e-12,
|
50 |
+
"max_position_embeddings": 512,
|
51 |
+
"model_type": "bert",
|
52 |
+
"num_attention_heads": 12,
|
53 |
+
"num_hidden_layers": 12,
|
54 |
+
"pad_token_id": 0,
|
55 |
+
"position_embedding_type": "absolute",
|
56 |
+
"torch_dtype": "float32",
|
57 |
+
"transformers_version": "4.34.1",
|
58 |
+
"type_vocab_size": 2,
|
59 |
+
"use_cache": true,
|
60 |
+
"vocab_size": 31116
|
61 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63ef9e510f582cbae6547d0efcb8d91aaa760e019ba38ff64b5a72cbf81b7cdb
|
3 |
+
size 437508774
|
special_tokens_map.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "[/]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
}
|
10 |
+
],
|
11 |
+
"cls_token": "[CLS]",
|
12 |
+
"mask_token": "[MASK]",
|
13 |
+
"pad_token": "[PAD]",
|
14 |
+
"sep_token": "[SEP]",
|
15 |
+
"unk_token": "[UNK]"
|
16 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "[PAD]",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"100": {
|
13 |
+
"content": "[UNK]",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"101": {
|
21 |
+
"content": "[CLS]",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"102": {
|
29 |
+
"content": "[SEP]",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"103": {
|
37 |
+
"content": "[MASK]",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
},
|
44 |
+
"31116": {
|
45 |
+
"content": "[/]",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": true
|
51 |
+
}
|
52 |
+
},
|
53 |
+
"additional_special_tokens": [
|
54 |
+
"[/]"
|
55 |
+
],
|
56 |
+
"clean_up_tokenization_spaces": true,
|
57 |
+
"cls_token": "[CLS]",
|
58 |
+
"do_basic_tokenize": true,
|
59 |
+
"do_lower_case": true,
|
60 |
+
"mask_token": "[MASK]",
|
61 |
+
"model_max_length": 1000000000000000019884624838656,
|
62 |
+
"never_split": null,
|
63 |
+
"pad_token": "[PAD]",
|
64 |
+
"sep_token": "[SEP]",
|
65 |
+
"strip_accents": null,
|
66 |
+
"tokenize_chinese_chars": true,
|
67 |
+
"tokenizer_class": "BertTokenizer",
|
68 |
+
"unk_token": "[UNK]"
|
69 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3521c0f3e05bbd5b715a6610a4fdf2546c114b76a9b25c4ac11b68b4c42ac952
|
3 |
+
size 4536
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|