judithrosell
commited on
Commit
•
5b1329d
1
Parent(s):
795f8a2
Training in progress, epoch 1
Browse files- config.json +55 -0
- model.safetensors +3 -0
- runs/Dec27_14-49-56_7e4f1f67560b/events.out.tfevents.1703688597.7e4f1f67560b.2770.0 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "allenai/scibert_scivocab_uncased",
|
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": "B-CHEBI",
|
13 |
+
"1": "B-CL",
|
14 |
+
"2": "B-GGP",
|
15 |
+
"3": "B-GO",
|
16 |
+
"4": "B-SO",
|
17 |
+
"5": "B-Taxon",
|
18 |
+
"6": "I-CHEBI",
|
19 |
+
"7": "I-CL",
|
20 |
+
"8": "I-GGP",
|
21 |
+
"9": "I-GO",
|
22 |
+
"10": "I-SO",
|
23 |
+
"11": "I-Taxon",
|
24 |
+
"12": "O"
|
25 |
+
},
|
26 |
+
"initializer_range": 0.02,
|
27 |
+
"intermediate_size": 3072,
|
28 |
+
"label2id": {
|
29 |
+
"B-CHEBI": 0,
|
30 |
+
"B-CL": 1,
|
31 |
+
"B-GGP": 2,
|
32 |
+
"B-GO": 3,
|
33 |
+
"B-SO": 4,
|
34 |
+
"B-Taxon": 5,
|
35 |
+
"I-CHEBI": 6,
|
36 |
+
"I-CL": 7,
|
37 |
+
"I-GGP": 8,
|
38 |
+
"I-GO": 9,
|
39 |
+
"I-SO": 10,
|
40 |
+
"I-Taxon": 11,
|
41 |
+
"O": 12
|
42 |
+
},
|
43 |
+
"layer_norm_eps": 1e-12,
|
44 |
+
"max_position_embeddings": 512,
|
45 |
+
"model_type": "bert",
|
46 |
+
"num_attention_heads": 12,
|
47 |
+
"num_hidden_layers": 12,
|
48 |
+
"pad_token_id": 0,
|
49 |
+
"position_embedding_type": "absolute",
|
50 |
+
"torch_dtype": "float32",
|
51 |
+
"transformers_version": "4.35.2",
|
52 |
+
"type_vocab_size": 2,
|
53 |
+
"use_cache": true,
|
54 |
+
"vocab_size": 31090
|
55 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae7b26cdbcda62c95d1566c8d19d9a3227ab2757988ab8d68a9ddcc7c75e6626
|
3 |
+
size 437374820
|
runs/Dec27_14-49-56_7e4f1f67560b/events.out.tfevents.1703688597.7e4f1f67560b.2770.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0cfff514e6fc4e0690c5abf5c9c94ebec20b40f54447c78627740ef75a8fe6bc
|
3 |
+
size 5265
|
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 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"101": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"102": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"103": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"104": {
|
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 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 1000000000000000019884624838656,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91db49fc3317aff7a20f70ac80c1cfdc3c790709df1d964d166200f133547ed9
|
3 |
+
size 4600
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|