Training in progress, epoch 1
Browse files- config.json +49 -49
- model.safetensors +1 -1
- special_tokens_map.json +37 -37
- tokenizer.json +1 -6
- tokenizer_config.json +59 -59
- training_args.bin +2 -2
config.json
CHANGED
@@ -1,49 +1,49 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "NazaGara/NER-fine-tuned-BETO",
|
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": "O",
|
14 |
-
"1": "B-PER",
|
15 |
-
"2": "I-PER",
|
16 |
-
"3": "B-ORG",
|
17 |
-
"4": "I-ORG",
|
18 |
-
"5": "B-LOC",
|
19 |
-
"6": "I-LOC",
|
20 |
-
"7": "B-MISC",
|
21 |
-
"8": "I-MISC"
|
22 |
-
},
|
23 |
-
"initializer_range": 0.02,
|
24 |
-
"intermediate_size": 3072,
|
25 |
-
"label2id": {
|
26 |
-
"B-LOC": 5,
|
27 |
-
"B-MISC": 7,
|
28 |
-
"B-ORG": 3,
|
29 |
-
"B-PER": 1,
|
30 |
-
"I-LOC": 6,
|
31 |
-
"I-MISC": 8,
|
32 |
-
"I-ORG": 4,
|
33 |
-
"I-PER": 2,
|
34 |
-
"O": 0
|
35 |
-
},
|
36 |
-
"layer_norm_eps": 1e-12,
|
37 |
-
"max_position_embeddings": 512,
|
38 |
-
"model_type": "bert",
|
39 |
-
"num_attention_heads": 12,
|
40 |
-
"num_hidden_layers": 12,
|
41 |
-
"output_past": true,
|
42 |
-
"pad_token_id": 1,
|
43 |
-
"position_embedding_type": "absolute",
|
44 |
-
"torch_dtype": "float32",
|
45 |
-
"transformers_version": "4.
|
46 |
-
"type_vocab_size": 2,
|
47 |
-
"use_cache": true,
|
48 |
-
"vocab_size": 31002
|
49 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "NazaGara/NER-fine-tuned-BETO",
|
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": "O",
|
14 |
+
"1": "B-PER",
|
15 |
+
"2": "I-PER",
|
16 |
+
"3": "B-ORG",
|
17 |
+
"4": "I-ORG",
|
18 |
+
"5": "B-LOC",
|
19 |
+
"6": "I-LOC",
|
20 |
+
"7": "B-MISC",
|
21 |
+
"8": "I-MISC"
|
22 |
+
},
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"intermediate_size": 3072,
|
25 |
+
"label2id": {
|
26 |
+
"B-LOC": 5,
|
27 |
+
"B-MISC": 7,
|
28 |
+
"B-ORG": 3,
|
29 |
+
"B-PER": 1,
|
30 |
+
"I-LOC": 6,
|
31 |
+
"I-MISC": 8,
|
32 |
+
"I-ORG": 4,
|
33 |
+
"I-PER": 2,
|
34 |
+
"O": 0
|
35 |
+
},
|
36 |
+
"layer_norm_eps": 1e-12,
|
37 |
+
"max_position_embeddings": 512,
|
38 |
+
"model_type": "bert",
|
39 |
+
"num_attention_heads": 12,
|
40 |
+
"num_hidden_layers": 12,
|
41 |
+
"output_past": true,
|
42 |
+
"pad_token_id": 1,
|
43 |
+
"position_embedding_type": "absolute",
|
44 |
+
"torch_dtype": "float32",
|
45 |
+
"transformers_version": "4.43.3",
|
46 |
+
"type_vocab_size": 2,
|
47 |
+
"use_cache": true,
|
48 |
+
"vocab_size": 31002
|
49 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 437092180
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3423c736aa80dd8344d1632b25557919e7c946d5449d2b1bdd3c760c34919b13
|
3 |
size 437092180
|
special_tokens_map.json
CHANGED
@@ -1,37 +1,37 @@
|
|
1 |
-
{
|
2 |
-
"cls_token": {
|
3 |
-
"content": "[CLS]",
|
4 |
-
"lstrip": false,
|
5 |
-
"normalized": false,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"mask_token": {
|
10 |
-
"content": "[MASK]",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"pad_token": {
|
17 |
-
"content": "[PAD]",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
-
"sep_token": {
|
24 |
-
"content": "[SEP]",
|
25 |
-
"lstrip": false,
|
26 |
-
"normalized": false,
|
27 |
-
"rstrip": false,
|
28 |
-
"single_word": false
|
29 |
-
},
|
30 |
-
"unk_token": {
|
31 |
-
"content": "[UNK]",
|
32 |
-
"lstrip": false,
|
33 |
-
"normalized": false,
|
34 |
-
"rstrip": false,
|
35 |
-
"single_word": false
|
36 |
-
}
|
37 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
tokenizer.json
CHANGED
@@ -1,11 +1,6 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
"direction": "Right",
|
5 |
-
"max_length": 512,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
tokenizer_config.json
CHANGED
@@ -1,59 +1,59 @@
|
|
1 |
-
{
|
2 |
-
"add_prefix_space": true,
|
3 |
-
"added_tokens_decoder": {
|
4 |
-
"0": {
|
5 |
-
"content": "[MASK]",
|
6 |
-
"lstrip": false,
|
7 |
-
"normalized": false,
|
8 |
-
"rstrip": false,
|
9 |
-
"single_word": false,
|
10 |
-
"special": true
|
11 |
-
},
|
12 |
-
"1": {
|
13 |
-
"content": "[PAD]",
|
14 |
-
"lstrip": false,
|
15 |
-
"normalized": false,
|
16 |
-
"rstrip": false,
|
17 |
-
"single_word": false,
|
18 |
-
"special": true
|
19 |
-
},
|
20 |
-
"3": {
|
21 |
-
"content": "[UNK]",
|
22 |
-
"lstrip": false,
|
23 |
-
"normalized": false,
|
24 |
-
"rstrip": false,
|
25 |
-
"single_word": false,
|
26 |
-
"special": true
|
27 |
-
},
|
28 |
-
"4": {
|
29 |
-
"content": "[CLS]",
|
30 |
-
"lstrip": false,
|
31 |
-
"normalized": false,
|
32 |
-
"rstrip": false,
|
33 |
-
"single_word": false,
|
34 |
-
"special": true
|
35 |
-
},
|
36 |
-
"5": {
|
37 |
-
"content": "[SEP]",
|
38 |
-
"lstrip": false,
|
39 |
-
"normalized": false,
|
40 |
-
"rstrip": false,
|
41 |
-
"single_word": false,
|
42 |
-
"special": true
|
43 |
-
}
|
44 |
-
},
|
45 |
-
"clean_up_tokenization_spaces": true,
|
46 |
-
"cls_token": "[CLS]",
|
47 |
-
"do_basic_tokenize": true,
|
48 |
-
"do_lower_case": false,
|
49 |
-
"mask_token": "[MASK]",
|
50 |
-
"model_max_length": 512,
|
51 |
-
"never_split": null,
|
52 |
-
"num_labels": 9,
|
53 |
-
"pad_token": "[PAD]",
|
54 |
-
"sep_token": "[SEP]",
|
55 |
-
"strip_accents": false,
|
56 |
-
"tokenize_chinese_chars": true,
|
57 |
-
"tokenizer_class": "BertTokenizer",
|
58 |
-
"unk_token": "[UNK]"
|
59 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "[MASK]",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "[PAD]",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"3": {
|
21 |
+
"content": "[UNK]",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"4": {
|
29 |
+
"content": "[CLS]",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"5": {
|
37 |
+
"content": "[SEP]",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "[CLS]",
|
47 |
+
"do_basic_tokenize": true,
|
48 |
+
"do_lower_case": false,
|
49 |
+
"mask_token": "[MASK]",
|
50 |
+
"model_max_length": 512,
|
51 |
+
"never_split": null,
|
52 |
+
"num_labels": 9,
|
53 |
+
"pad_token": "[PAD]",
|
54 |
+
"sep_token": "[SEP]",
|
55 |
+
"strip_accents": false,
|
56 |
+
"tokenize_chinese_chars": true,
|
57 |
+
"tokenizer_class": "BertTokenizer",
|
58 |
+
"unk_token": "[UNK]"
|
59 |
+
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:baa976e3bc7371af340c3547fce93ce56a6701260cb5f8e86d68c06c63188fbc
|
3 |
+
size 5176
|