Training in progress, epoch 8
Browse files- config.json +48 -48
- model.safetensors +1 -1
- runs/Jun02_09-47-22_ARAGANA/events.out.tfevents.1717339643.ARAGANA.14908.0 +2 -2
- special_tokens_map.json +7 -7
- tokenizer_config.json +55 -55
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,48 +1,48 @@
|
|
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": "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 |
-
"pad_token_id": 0,
|
42 |
-
"position_embedding_type": "absolute",
|
43 |
-
"torch_dtype": "float32",
|
44 |
-
"transformers_version": "4.41.1",
|
45 |
-
"type_vocab_size": 2,
|
46 |
-
"use_cache": true,
|
47 |
-
"vocab_size": 28996
|
48 |
-
}
|
|
|
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": "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 |
+
"pad_token_id": 0,
|
42 |
+
"position_embedding_type": "absolute",
|
43 |
+
"torch_dtype": "float32",
|
44 |
+
"transformers_version": "4.41.1",
|
45 |
+
"type_vocab_size": 2,
|
46 |
+
"use_cache": true,
|
47 |
+
"vocab_size": 28996
|
48 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 430929740
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0338ae0829a56e09d587545c3ba530679e145627eb13a917070ee238b7ff6cd
|
3 |
size 430929740
|
runs/Jun02_09-47-22_ARAGANA/events.out.tfevents.1717339643.ARAGANA.14908.0
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 sha256:66a8cd55bfdf40649561e207b57fdf94a2df585d6cad2810db1f48c3d76bc318
|
3 |
+
size 9555
|
special_tokens_map.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
-
{
|
2 |
-
"cls_token": "[CLS]",
|
3 |
-
"mask_token": "[MASK]",
|
4 |
-
"pad_token": "[PAD]",
|
5 |
-
"sep_token": "[SEP]",
|
6 |
-
"unk_token": "[UNK]"
|
7 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer_config.json
CHANGED
@@ -1,55 +1,55 @@
|
|
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 |
-
"100": {
|
12 |
-
"content": "[UNK]",
|
13 |
-
"lstrip": false,
|
14 |
-
"normalized": false,
|
15 |
-
"rstrip": false,
|
16 |
-
"single_word": false,
|
17 |
-
"special": true
|
18 |
-
},
|
19 |
-
"101": {
|
20 |
-
"content": "[CLS]",
|
21 |
-
"lstrip": false,
|
22 |
-
"normalized": false,
|
23 |
-
"rstrip": false,
|
24 |
-
"single_word": false,
|
25 |
-
"special": true
|
26 |
-
},
|
27 |
-
"102": {
|
28 |
-
"content": "[SEP]",
|
29 |
-
"lstrip": false,
|
30 |
-
"normalized": false,
|
31 |
-
"rstrip": false,
|
32 |
-
"single_word": false,
|
33 |
-
"special": true
|
34 |
-
},
|
35 |
-
"103": {
|
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_lower_case": false,
|
47 |
-
"mask_token": "[MASK]",
|
48 |
-
"model_max_length": 512,
|
49 |
-
"pad_token": "[PAD]",
|
50 |
-
"sep_token": "[SEP]",
|
51 |
-
"strip_accents": null,
|
52 |
-
"tokenize_chinese_chars": true,
|
53 |
-
"tokenizer_class": "BertTokenizer",
|
54 |
-
"unk_token": "[UNK]"
|
55 |
-
}
|
|
|
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 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
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_lower_case": false,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "BertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c6e53dfdf7ee1b8ba76b790597154a4094740d178a239b3651809e3e8f2e892
|
3 |
size 5112
|