Training in progress, epoch 1
Browse files- config.json +2 -9
- model.safetensors +2 -2
- runs/Sep06_08-30-38_3dc6a799c99f/events.out.tfevents.1725611453.3dc6a799c99f.2226.0 +3 -0
- special_tokens_map.json +5 -35
- tokenizer.json +2 -2
- tokenizer_config.json +8 -13
- training_args.bin +1 -1
- vocab.txt +0 -0
config.json
CHANGED
@@ -1,12 +1,10 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"BertForSequenceClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"classifier_dropout": null,
|
8 |
-
"directionality": "bidi",
|
9 |
-
"gradient_checkpointing": false,
|
10 |
"hidden_act": "gelu",
|
11 |
"hidden_dropout_prob": 0.1,
|
12 |
"hidden_size": 768,
|
@@ -28,16 +26,11 @@
|
|
28 |
"num_attention_heads": 12,
|
29 |
"num_hidden_layers": 12,
|
30 |
"pad_token_id": 0,
|
31 |
-
"pooler_fc_size": 768,
|
32 |
-
"pooler_num_attention_heads": 12,
|
33 |
-
"pooler_num_fc_layers": 3,
|
34 |
-
"pooler_size_per_head": 128,
|
35 |
-
"pooler_type": "first_token_transform",
|
36 |
"position_embedding_type": "absolute",
|
37 |
"problem_type": "single_label_classification",
|
38 |
"torch_dtype": "float32",
|
39 |
"transformers_version": "4.44.2",
|
40 |
"type_vocab_size": 2,
|
41 |
"use_cache": true,
|
42 |
-
"vocab_size":
|
43 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "HooshvareLab/bert-fa-base-uncased",
|
3 |
"architectures": [
|
4 |
"BertForSequenceClassification"
|
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,
|
|
|
26 |
"num_attention_heads": 12,
|
27 |
"num_hidden_layers": 12,
|
28 |
"pad_token_id": 0,
|
|
|
|
|
|
|
|
|
|
|
29 |
"position_embedding_type": "absolute",
|
30 |
"problem_type": "single_label_classification",
|
31 |
"torch_dtype": "float32",
|
32 |
"transformers_version": "4.44.2",
|
33 |
"type_vocab_size": 2,
|
34 |
"use_cache": true,
|
35 |
+
"vocab_size": 100000
|
36 |
}
|
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 sha256:25cc0c8a2ed51905618e41cc1b222d09c0c7cc9f8c2db1e47aaf2a3c37b6fa68
|
3 |
+
size 651398148
|
runs/Sep06_08-30-38_3dc6a799c99f/events.out.tfevents.1725611453.3dc6a799c99f.2226.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e787203a4d3b6d3f981e2b594b03a164e195586ebab745597544d2e3aaa2668d
|
3 |
+
size 5827
|
special_tokens_map.json
CHANGED
@@ -1,37 +1,7 @@
|
|
1 |
{
|
2 |
-
"cls_token":
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
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": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
}
|
tokenizer.json
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 sha256:53671a3afd4405972b7ae597817ddc5dfb58a265591ee92f61a01c71478a3473
|
3 |
+
size 2789644
|
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,
|
@@ -16,7 +16,7 @@
|
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
-
"
|
20 |
"content": "[CLS]",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
@@ -24,16 +24,16 @@
|
|
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,
|
@@ -44,19 +44,14 @@
|
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
"do_basic_tokenize": true,
|
47 |
-
"do_lower_case":
|
48 |
-
"full_tokenizer_file": null,
|
49 |
"mask_token": "[MASK]",
|
50 |
-
"
|
51 |
-
"model_max_length": 512,
|
52 |
"never_split": null,
|
53 |
"pad_token": "[PAD]",
|
54 |
"sep_token": "[SEP]",
|
55 |
-
"stride": 0,
|
56 |
"strip_accents": null,
|
57 |
"tokenize_chinese_chars": true,
|
58 |
"tokenizer_class": "BertTokenizer",
|
59 |
-
"truncation_side": "right",
|
60 |
-
"truncation_strategy": "longest_first",
|
61 |
"unk_token": "[UNK]"
|
62 |
}
|
|
|
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": "[CLS]",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
|
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
+
"3": {
|
28 |
+
"content": "[MASK]",
|
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,
|
|
|
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
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1cb7f5b520a706ee9c8fb745c0114c553ac99054174b7c77ff5d823d1fd30527
|
3 |
size 5176
|
vocab.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|