alexbrandsen
commited on
Commit
•
3f17eee
1
Parent(s):
70beef0
Upload 7 files
Browse files- config.json +55 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- test_results.txt +4 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "B-ART",
|
14 |
+
"1": "I-ART",
|
15 |
+
"2": "B-MAT",
|
16 |
+
"3": "I-MAT",
|
17 |
+
"4": "B-PER",
|
18 |
+
"5": "I-PER",
|
19 |
+
"6": "B-SPE",
|
20 |
+
"7": "I-SPE",
|
21 |
+
"8": "B-CON",
|
22 |
+
"9": "I-CON",
|
23 |
+
"10": "B-LOC",
|
24 |
+
"11": "I-LOC",
|
25 |
+
"12": "O"
|
26 |
+
},
|
27 |
+
"initializer_range": 0.02,
|
28 |
+
"intermediate_size": 3072,
|
29 |
+
"label2id": {
|
30 |
+
"B-ART": 0,
|
31 |
+
"B-CON": 8,
|
32 |
+
"B-LOC": 10,
|
33 |
+
"B-MAT": 2,
|
34 |
+
"B-PER": 4,
|
35 |
+
"B-SPE": 6,
|
36 |
+
"I-ART": 1,
|
37 |
+
"I-CON": 9,
|
38 |
+
"I-LOC": 11,
|
39 |
+
"I-MAT": 3,
|
40 |
+
"I-PER": 5,
|
41 |
+
"I-SPE": 7,
|
42 |
+
"O": 12
|
43 |
+
},
|
44 |
+
"layer_norm_eps": 1e-12,
|
45 |
+
"max_position_embeddings": 512,
|
46 |
+
"model_type": "bert",
|
47 |
+
"num_attention_heads": 12,
|
48 |
+
"num_hidden_layers": 12,
|
49 |
+
"pad_token_id": 0,
|
50 |
+
"position_embedding_type": "absolute",
|
51 |
+
"torch_dtype": "float32",
|
52 |
+
"transformers_version": "4.31.0.dev0",
|
53 |
+
"type_vocab_size": 2,
|
54 |
+
"vocab_size": 28996
|
55 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac506bb9e2e6803f1f31e603eedb71f429b6ac6d3dd44d4878995d5b93667176
|
3 |
+
size 433363692
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
test_results.txt
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
eval_loss = 0.13637986211106182
|
2 |
+
eval_precision = 0.7977915804002761
|
3 |
+
eval_recall = 0.7585301837270341
|
4 |
+
eval_f1 = 0.777665657584931
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"clean_up_tokenization_spaces": true, "cls_token": "[CLS]", "do_lower_case": false, "mask_token": "[MASK]", "model_max_length": 512, "pad_token": "[PAD]", "sep_token": "[SEP]", "strip_accents": null, "tokenize_chinese_chars": true, "tokenizer_class": "BertTokenizer", "unk_token": "[UNK]", "special_tokens_map_file": "/data1/brandsena/BERT_models/ArchaeoBERT/special_tokens_map.json", "full_tokenizer_file": "/data1/brandsena/BERT_models/ArchaeoBERT/tokenizer.json"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2c10883c96349bbb2627f60f902b4677ef9b273690d30c5a8c8ea96d971ce2f
|
3 |
+
size 1583
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|