Training in progress, epoch 0
Browse files- added_tokens.json +7 -0
- config.json +8 -8
- pytorch_model.bin +2 -2
- tokenizer_config.json +51 -0
- training_args.bin +2 -2
added_tokens.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[CLS]": 2,
|
3 |
+
"[MASK]": 4,
|
4 |
+
"[PAD]": 0,
|
5 |
+
"[SEP]": 3,
|
6 |
+
"[UNK]": 1
|
7 |
+
}
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"BertForSequenceClassification"
|
5 |
],
|
@@ -10,16 +10,16 @@
|
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
"hidden_size": 1024,
|
12 |
"id2label": {
|
13 |
-
"0": "
|
14 |
-
"1": "
|
15 |
-
"2": "
|
16 |
},
|
17 |
"initializer_range": 0.02,
|
18 |
"intermediate_size": 4096,
|
19 |
"label2id": {
|
20 |
-
"
|
21 |
-
"
|
22 |
-
"
|
23 |
},
|
24 |
"layer_norm_eps": 1e-12,
|
25 |
"max_position_embeddings": 512,
|
@@ -30,7 +30,7 @@
|
|
30 |
"position_embedding_type": "absolute",
|
31 |
"problem_type": "single_label_classification",
|
32 |
"torch_dtype": "float32",
|
33 |
-
"transformers_version": "4.
|
34 |
"type_vocab_size": 2,
|
35 |
"use_cache": true,
|
36 |
"vocab_size": 64000
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "Yousefmd/arabert-sentiment-classification",
|
3 |
"architectures": [
|
4 |
"BertForSequenceClassification"
|
5 |
],
|
|
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
"hidden_size": 1024,
|
12 |
"id2label": {
|
13 |
+
"0": "LABEL_0",
|
14 |
+
"1": "LABEL_1",
|
15 |
+
"2": "LABEL_2"
|
16 |
},
|
17 |
"initializer_range": 0.02,
|
18 |
"intermediate_size": 4096,
|
19 |
"label2id": {
|
20 |
+
"LABEL_0": 0,
|
21 |
+
"LABEL_1": 1,
|
22 |
+
"LABEL_2": 2
|
23 |
},
|
24 |
"layer_norm_eps": 1e-12,
|
25 |
"max_position_embeddings": 512,
|
|
|
30 |
"position_embedding_type": "absolute",
|
31 |
"problem_type": "single_label_classification",
|
32 |
"torch_dtype": "float32",
|
33 |
+
"transformers_version": "4.34.0",
|
34 |
"type_vocab_size": 2,
|
35 |
"use_cache": true,
|
36 |
"vocab_size": 64000
|
pytorch_model.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 sha256:2e922460ab2ed766fe340927ef23130b3886f9792f23b6dcca82649b9ccb3073
|
3 |
+
size 1477840177
|
tokenizer_config.json
CHANGED
@@ -1,21 +1,72 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"clean_up_tokenization_spaces": true,
|
3 |
"cls_token": "[CLS]",
|
4 |
"do_basic_tokenize": true,
|
5 |
"do_lower_case": false,
|
|
|
6 |
"mask_token": "[MASK]",
|
7 |
"max_len": 512,
|
|
|
8 |
"model_max_length": 512,
|
9 |
"never_split": [
|
10 |
"[بريد]",
|
11 |
"[مستخدم]",
|
12 |
"[رابط]"
|
13 |
],
|
|
|
14 |
"pad_token": "[PAD]",
|
|
|
|
|
15 |
"sep_token": "[SEP]",
|
|
|
16 |
"strip_accents": null,
|
17 |
"tokenize_chinese_chars": true,
|
18 |
"tokenizer_class": "BertTokenizer",
|
|
|
|
|
19 |
"unk_token": "[UNK]",
|
20 |
"use_fast": true
|
21 |
}
|
|
|
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 |
+
"1": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"additional_special_tokens": [],
|
45 |
"clean_up_tokenization_spaces": true,
|
46 |
"cls_token": "[CLS]",
|
47 |
"do_basic_tokenize": true,
|
48 |
"do_lower_case": false,
|
49 |
+
"ignore_mismatched_sizes": true,
|
50 |
"mask_token": "[MASK]",
|
51 |
"max_len": 512,
|
52 |
+
"max_length": 128,
|
53 |
"model_max_length": 512,
|
54 |
"never_split": [
|
55 |
"[بريد]",
|
56 |
"[مستخدم]",
|
57 |
"[رابط]"
|
58 |
],
|
59 |
+
"pad_to_multiple_of": null,
|
60 |
"pad_token": "[PAD]",
|
61 |
+
"pad_token_type_id": 0,
|
62 |
+
"padding_side": "right",
|
63 |
"sep_token": "[SEP]",
|
64 |
+
"stride": 0,
|
65 |
"strip_accents": null,
|
66 |
"tokenize_chinese_chars": true,
|
67 |
"tokenizer_class": "BertTokenizer",
|
68 |
+
"truncation_side": "right",
|
69 |
+
"truncation_strategy": "longest_first",
|
70 |
"unk_token": "[UNK]",
|
71 |
"use_fast": true
|
72 |
}
|
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:fd4249ad5df8a68beaf61239ec0ca1b090169b797dc398439f233985546bd9e5
|
3 |
+
size 4091
|