Abdelrahman-Rezk
commited on
Commit
•
6f34846
1
Parent(s):
ae2dc23
Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +78 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "CAMeL-Lab/bert-base-arabic-camelbert-mix-poetry",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"finetuning_task": "arabic_poetry",
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "\u0634\u0639\u0631 \u062d\u0631",
|
15 |
+
"1": "\u0634\u0639\u0631 \u0627\u0644\u062a\u0641\u0639\u064a\u0644\u0629",
|
16 |
+
"2": "\u0639\u0627\u0645\u064a",
|
17 |
+
"3": "\u0645\u0648\u0634\u062d",
|
18 |
+
"4": "\u0627\u0644\u0631\u062c\u0632",
|
19 |
+
"5": "\u0627\u0644\u0631\u0645\u0644",
|
20 |
+
"6": "\u0627\u0644\u0647\u0632\u062c",
|
21 |
+
"7": "\u0627\u0644\u0628\u0633\u064a\u0637",
|
22 |
+
"8": "\u0627\u0644\u062e\u0641\u064a\u0641",
|
23 |
+
"9": "\u0627\u0644\u0633\u0631\u064a\u0639",
|
24 |
+
"10": "\u0627\u0644\u0637\u0648\u064a\u0644",
|
25 |
+
"11": "\u0627\u0644\u0643\u0627\u0645\u0644",
|
26 |
+
"12": "\u0627\u0644\u0645\u062c\u062a\u062b",
|
27 |
+
"13": "\u0627\u0644\u0645\u062f\u064a\u062f",
|
28 |
+
"14": "\u0627\u0644\u0648\u0627\u0641\u0631",
|
29 |
+
"15": "\u0627\u0644\u062f\u0648\u0628\u064a\u062a",
|
30 |
+
"16": "\u0627\u0644\u0633\u0644\u0633\u0644\u0629",
|
31 |
+
"17": "\u0627\u0644\u0645\u0636\u0627\u0631\u0639",
|
32 |
+
"18": "\u0627\u0644\u0645\u0642\u062a\u0636\u0628",
|
33 |
+
"19": "\u0627\u0644\u0645\u0646\u0633\u0631\u062d",
|
34 |
+
"20": "\u0627\u0644\u0645\u062a\u062f\u0627\u0631\u0643",
|
35 |
+
"21": "\u0627\u0644\u0645\u062a\u0642\u0627\u0631\u0628",
|
36 |
+
"22": "\u0627\u0644\u0645\u0648\u0627\u0644\u064a\u0627"
|
37 |
+
},
|
38 |
+
"initializer_range": 0.02,
|
39 |
+
"intermediate_size": 3072,
|
40 |
+
"label2id": {
|
41 |
+
"\u0627\u0644\u0628\u0633\u064a\u0637": 7,
|
42 |
+
"\u0627\u0644\u062e\u0641\u064a\u0641": 8,
|
43 |
+
"\u0627\u0644\u062f\u0648\u0628\u064a\u062a": 15,
|
44 |
+
"\u0627\u0644\u0631\u062c\u0632": 4,
|
45 |
+
"\u0627\u0644\u0631\u0645\u0644": 5,
|
46 |
+
"\u0627\u0644\u0633\u0631\u064a\u0639": 9,
|
47 |
+
"\u0627\u0644\u0633\u0644\u0633\u0644\u0629": 16,
|
48 |
+
"\u0627\u0644\u0637\u0648\u064a\u0644": 10,
|
49 |
+
"\u0627\u0644\u0643\u0627\u0645\u0644": 11,
|
50 |
+
"\u0627\u0644\u0645\u062a\u062f\u0627\u0631\u0643": 20,
|
51 |
+
"\u0627\u0644\u0645\u062a\u0642\u0627\u0631\u0628": 21,
|
52 |
+
"\u0627\u0644\u0645\u062c\u062a\u062b": 12,
|
53 |
+
"\u0627\u0644\u0645\u062f\u064a\u062f": 13,
|
54 |
+
"\u0627\u0644\u0645\u0636\u0627\u0631\u0639": 17,
|
55 |
+
"\u0627\u0644\u0645\u0642\u062a\u0636\u0628": 18,
|
56 |
+
"\u0627\u0644\u0645\u0646\u0633\u0631\u062d": 19,
|
57 |
+
"\u0627\u0644\u0645\u0648\u0627\u0644\u064a\u0627": 22,
|
58 |
+
"\u0627\u0644\u0647\u0632\u062c": 6,
|
59 |
+
"\u0627\u0644\u0648\u0627\u0641\u0631": 14,
|
60 |
+
"\u0634\u0639\u0631 \u0627\u0644\u062a\u0641\u0639\u064a\u0644\u0629": 1,
|
61 |
+
"\u0634\u0639\u0631 \u062d\u0631": 0,
|
62 |
+
"\u0639\u0627\u0645\u064a": 2,
|
63 |
+
"\u0645\u0648\u0634\u062d": 3
|
64 |
+
},
|
65 |
+
"layer_norm_eps": 1e-12,
|
66 |
+
"max_position_embeddings": 512,
|
67 |
+
"model_type": "bert",
|
68 |
+
"num_attention_heads": 12,
|
69 |
+
"num_hidden_layers": 12,
|
70 |
+
"pad_token_id": 0,
|
71 |
+
"position_embedding_type": "absolute",
|
72 |
+
"problem_type": "single_label_classification",
|
73 |
+
"torch_dtype": "float32",
|
74 |
+
"transformers_version": "4.19.2",
|
75 |
+
"type_vocab_size": 2,
|
76 |
+
"use_cache": true,
|
77 |
+
"vocab_size": 30000
|
78 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40f9a59d831089382a3eef1fa9b8603739de7eb5f10b70e831932656c36aa09e
|
3 |
+
size 436467117
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "full_tokenizer_file": null, "name_or_path": "CAMeL-Lab/bert-base-arabic-camelbert-mix-poetry", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a8ec5e204e08d0937cd8ac9be215be18a6734d322c64b13466fcf040f92b720
|
3 |
+
size 3247
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|