Commit
•
293097a
1
Parent(s):
1d8625d
Training in progress, step 50
Browse files- config.json +31 -0
- model.safetensors +3 -0
- runs/May13_06-54-17_32317d237a8a/events.out.tfevents.1715583267.32317d237a8a.34.0 +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +339 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "aubmindlab/bert-base-arabert",
|
3 |
+
"architectures": [
|
4 |
+
"BertForQuestionAnswering"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"pooler_fc_size": 768,
|
21 |
+
"pooler_num_attention_heads": 12,
|
22 |
+
"pooler_num_fc_layers": 3,
|
23 |
+
"pooler_size_per_head": 128,
|
24 |
+
"pooler_type": "first_token_transform",
|
25 |
+
"position_embedding_type": "absolute",
|
26 |
+
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.39.3",
|
28 |
+
"type_vocab_size": 2,
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 64000
|
31 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:acde60255731357bd6afe3436cbd26108696026963297bd9c7fa4eb5cf708290
|
3 |
+
size 538440512
|
runs/May13_06-54-17_32317d237a8a/events.out.tfevents.1715583267.32317d237a8a.34.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:517512da9728ba9349c3c4924bbf2c7ee6a64d180e2b5d8c6394706676acb9f0
|
3 |
+
size 7146
|
special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
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 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,339 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"124": {
|
4 |
+
"content": "+ا",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": true,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": true,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"125": {
|
12 |
+
"content": "+ة",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": true,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": true,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"126": {
|
20 |
+
"content": "+ت",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": true,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": true,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"127": {
|
28 |
+
"content": "+ك",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": true,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"128": {
|
36 |
+
"content": "+ن",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": true,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": true,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"129": {
|
44 |
+
"content": "+ه",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": true,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": true,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"130": {
|
52 |
+
"content": "+ي",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": true,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": true,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"448": {
|
60 |
+
"content": "ب+",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": true,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": true,
|
65 |
+
"special": true
|
66 |
+
},
|
67 |
+
"635": {
|
68 |
+
"content": "س+",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": true,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": true,
|
73 |
+
"special": true
|
74 |
+
},
|
75 |
+
"765": {
|
76 |
+
"content": "ف+",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": true,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": true,
|
81 |
+
"special": true
|
82 |
+
},
|
83 |
+
"802": {
|
84 |
+
"content": "ك+",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": true,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": true,
|
89 |
+
"special": true
|
90 |
+
},
|
91 |
+
"816": {
|
92 |
+
"content": "ل+",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": true,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": true,
|
97 |
+
"special": true
|
98 |
+
},
|
99 |
+
"897": {
|
100 |
+
"content": "و+",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": true,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": true,
|
105 |
+
"special": true
|
106 |
+
},
|
107 |
+
"1012": {
|
108 |
+
"content": "+ات",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": true,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": true,
|
113 |
+
"special": true
|
114 |
+
},
|
115 |
+
"1013": {
|
116 |
+
"content": "+ان",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": true,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": true,
|
121 |
+
"special": true
|
122 |
+
},
|
123 |
+
"1015": {
|
124 |
+
"content": "+كم",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": true,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": true,
|
129 |
+
"special": true
|
130 |
+
},
|
131 |
+
"1016": {
|
132 |
+
"content": "+كن",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": true,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": true,
|
137 |
+
"special": true
|
138 |
+
},
|
139 |
+
"1017": {
|
140 |
+
"content": "+نا",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": true,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": true,
|
145 |
+
"special": true
|
146 |
+
},
|
147 |
+
"1018": {
|
148 |
+
"content": "+ها",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": true,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": true,
|
153 |
+
"special": true
|
154 |
+
},
|
155 |
+
"1019": {
|
156 |
+
"content": "+هم",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": true,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": true,
|
161 |
+
"special": true
|
162 |
+
},
|
163 |
+
"1020": {
|
164 |
+
"content": "+هن",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": true,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": true,
|
169 |
+
"special": true
|
170 |
+
},
|
171 |
+
"1021": {
|
172 |
+
"content": "+وا",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": true,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": true,
|
177 |
+
"special": true
|
178 |
+
},
|
179 |
+
"1022": {
|
180 |
+
"content": "+ون",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": true,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": true,
|
185 |
+
"special": true
|
186 |
+
},
|
187 |
+
"1023": {
|
188 |
+
"content": "+ين",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": true,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": true,
|
193 |
+
"special": true
|
194 |
+
},
|
195 |
+
"3000": {
|
196 |
+
"content": "ال+",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": true,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": true,
|
201 |
+
"special": true
|
202 |
+
},
|
203 |
+
"6154": {
|
204 |
+
"content": "لل+",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": true,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": true,
|
209 |
+
"special": true
|
210 |
+
},
|
211 |
+
"8270": {
|
212 |
+
"content": "+كما",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": true,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": true,
|
217 |
+
"special": true
|
218 |
+
},
|
219 |
+
"8271": {
|
220 |
+
"content": "+هما",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": true,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": true,
|
225 |
+
"special": true
|
226 |
+
},
|
227 |
+
"29756": {
|
228 |
+
"content": "[CLS]",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": true
|
234 |
+
},
|
235 |
+
"29757": {
|
236 |
+
"content": "[PAD]",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": false,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": true
|
242 |
+
},
|
243 |
+
"29758": {
|
244 |
+
"content": "[SEP]",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": false,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": true
|
250 |
+
},
|
251 |
+
"29759": {
|
252 |
+
"content": "[UNK]",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": false,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": true
|
258 |
+
},
|
259 |
+
"46585": {
|
260 |
+
"content": "[MASK]",
|
261 |
+
"lstrip": false,
|
262 |
+
"normalized": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": true
|
266 |
+
},
|
267 |
+
"46586": {
|
268 |
+
"content": "[بريد]",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": true,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": true,
|
273 |
+
"special": true
|
274 |
+
},
|
275 |
+
"46587": {
|
276 |
+
"content": "[رابط]",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": true,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": true,
|
281 |
+
"special": true
|
282 |
+
},
|
283 |
+
"57701": {
|
284 |
+
"content": "[مستخدم]",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": true,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": true,
|
289 |
+
"special": true
|
290 |
+
}
|
291 |
+
},
|
292 |
+
"clean_up_tokenization_spaces": true,
|
293 |
+
"cls_token": "[CLS]",
|
294 |
+
"do_basic_tokenize": true,
|
295 |
+
"do_lower_case": false,
|
296 |
+
"full_tokenizer_file": null,
|
297 |
+
"mask_token": "[MASK]",
|
298 |
+
"max_len": 512,
|
299 |
+
"model_max_length": 512,
|
300 |
+
"never_split": [
|
301 |
+
"+وا",
|
302 |
+
"س+",
|
303 |
+
"[مستخدم]",
|
304 |
+
"+ك",
|
305 |
+
"+هم",
|
306 |
+
"+ة",
|
307 |
+
"+ن",
|
308 |
+
"لل+",
|
309 |
+
"[بريد]",
|
310 |
+
"[رابط]",
|
311 |
+
"+ه",
|
312 |
+
"+كن",
|
313 |
+
"+ا",
|
314 |
+
"+ات",
|
315 |
+
"+ي",
|
316 |
+
"ب+",
|
317 |
+
"+نا",
|
318 |
+
"+هن",
|
319 |
+
"+كم",
|
320 |
+
"ك+",
|
321 |
+
"+ين",
|
322 |
+
"+هما",
|
323 |
+
"و+",
|
324 |
+
"+كما",
|
325 |
+
"+ان",
|
326 |
+
"+ت",
|
327 |
+
"+ون",
|
328 |
+
"ل+",
|
329 |
+
"+ها",
|
330 |
+
"ال+",
|
331 |
+
"ف+"
|
332 |
+
],
|
333 |
+
"pad_token": "[PAD]",
|
334 |
+
"sep_token": "[SEP]",
|
335 |
+
"strip_accents": null,
|
336 |
+
"tokenize_chinese_chars": true,
|
337 |
+
"tokenizer_class": "BertTokenizer",
|
338 |
+
"unk_token": "[UNK]"
|
339 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fd57b58cb64d4a4012007febab58a1e875f8f7c85f921a8cdfea6a0784e0e1e
|
3 |
+
size 4920
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|