Training in progress, epoch 1
Browse files- config.json +5 -8
- model.safetensors +2 -2
- tokenizer.json +0 -0
- tokenizer_config.json +11 -9
- training_args.bin +1 -1
- vocab.txt +0 -0
config.json
CHANGED
@@ -1,11 +1,12 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"BertForSequenceClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
|
|
7 |
"classifier_dropout": null,
|
8 |
-
"
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
"hidden_size": 768,
|
@@ -26,17 +27,13 @@
|
|
26 |
"model_type": "bert",
|
27 |
"num_attention_heads": 12,
|
28 |
"num_hidden_layers": 12,
|
|
|
29 |
"pad_token_id": 0,
|
30 |
-
"pooler_fc_size": 768,
|
31 |
-
"pooler_num_attention_heads": 12,
|
32 |
-
"pooler_num_fc_layers": 3,
|
33 |
-
"pooler_size_per_head": 128,
|
34 |
-
"pooler_type": "first_token_transform",
|
35 |
"position_embedding_type": "absolute",
|
36 |
"problem_type": "single_label_classification",
|
37 |
"torch_dtype": "float32",
|
38 |
"transformers_version": "4.41.2",
|
39 |
"type_vocab_size": 2,
|
40 |
"use_cache": true,
|
41 |
-
"vocab_size":
|
42 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "indolem/indobert-base-uncased",
|
3 |
"architectures": [
|
4 |
"BertForSequenceClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
"classifier_dropout": null,
|
9 |
+
"eos_token_ids": 0,
|
10 |
"hidden_act": "gelu",
|
11 |
"hidden_dropout_prob": 0.1,
|
12 |
"hidden_size": 768,
|
|
|
27 |
"model_type": "bert",
|
28 |
"num_attention_heads": 12,
|
29 |
"num_hidden_layers": 12,
|
30 |
+
"output_past": true,
|
31 |
"pad_token_id": 0,
|
|
|
|
|
|
|
|
|
|
|
32 |
"position_embedding_type": "absolute",
|
33 |
"problem_type": "single_label_classification",
|
34 |
"torch_dtype": "float32",
|
35 |
"transformers_version": "4.41.2",
|
36 |
"type_vocab_size": 2,
|
37 |
"use_cache": true,
|
38 |
+
"vocab_size": 31923
|
39 |
}
|
model.safetensors
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:e7157f61413269363685352b78b1a5b3f390426cc16362d284139e718d10c73a
|
3 |
+
size 442265596
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -8,7 +8,7 @@
|
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
-
"
|
12 |
"content": "[UNK]",
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
@@ -16,24 +16,24 @@
|
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
-
"
|
20 |
-
"content": "[
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
-
"
|
28 |
-
"content": "[
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
-
"
|
36 |
-
"content": "[
|
37 |
"lstrip": false,
|
38 |
"normalized": false,
|
39 |
"rstrip": false,
|
@@ -43,9 +43,11 @@
|
|
43 |
},
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
-
"
|
|
|
47 |
"mask_token": "[MASK]",
|
48 |
-
"model_max_length":
|
|
|
49 |
"pad_token": "[PAD]",
|
50 |
"sep_token": "[SEP]",
|
51 |
"strip_accents": null,
|
|
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
+
"1": {
|
12 |
"content": "[UNK]",
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
|
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
+
"2": {
|
20 |
+
"content": "[MASK]",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
+
"3": {
|
28 |
+
"content": "[CLS]",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
+
"4": {
|
36 |
+
"content": "[SEP]",
|
37 |
"lstrip": false,
|
38 |
"normalized": false,
|
39 |
"rstrip": false,
|
|
|
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,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7bc8e45785f7321e69cdde8a1dcf7490b7d3a64965c03f96efc033b625c11654
|
3 |
size 5048
|
vocab.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|