Hugging Face's logo

mohamedashraf11
/
my_awesome_qa_model

Question Answering
Transformers
TensorBoard
Safetensors
bert
Model card Files
xet
Metrics Community
mohamedashraf11 commited on
Commit
9719e04
·
verified ·
1 Parent(s): 85e0191

Training in progress, epoch 2

Browse files
Files changed (17) hide show
  1. config.json +3 -9
  2. model.safetensors +2 -2
  3. runs/Feb02_16-42-22_3a5395b179ef/events.out.tfevents.1706892143.3a5395b179ef.5358.0 +3 -0
  4. runs/Feb02_16-42-22_3a5395b179ef/events.out.tfevents.1706892435.3a5395b179ef.5358.1 +3 -0
  5. runs/Feb02_16-48-08_3a5395b179ef/events.out.tfevents.1706892490.3a5395b179ef.5358.2 +3 -0
  6. runs/Feb02_16-56-54_3a5395b179ef/events.out.tfevents.1706893015.3a5395b179ef.5358.3 +3 -0
  7. runs/Feb02_16-59-30_3a5395b179ef/events.out.tfevents.1706893171.3a5395b179ef.9947.0 +3 -0
  8. runs/Feb02_16-59-30_3a5395b179ef/events.out.tfevents.1706893469.3a5395b179ef.9947.1 +3 -0
  9. runs/Feb02_17-40-35_3a5395b179ef/events.out.tfevents.1706895639.3a5395b179ef.9947.2 +3 -0
  10. runs/Feb02_17-42-45_3a5395b179ef/events.out.tfevents.1706895766.3a5395b179ef.20667.0 +3 -0
  11. runs/Feb02_17-42-45_3a5395b179ef/events.out.tfevents.1706896063.3a5395b179ef.20667.1 +3 -0
  12. runs/Feb02_17-54-49_3a5395b179ef/events.out.tfevents.1706896510.3a5395b179ef.20667.2 +3 -0
  13. special_tokens_map.json +35 -5
  14. tokenizer.json +0 -0
  15. tokenizer_config.json +288 -5
  16. training_args.bin +2 -2
  17. vocab.txt +0 -0
config.json CHANGED
@@ -1,12 +1,10 @@
1
  {
2
- "_name_or_path": "Damith/AraELECTRA-discriminator-QuranQA",
3
  "architectures": [
4
- "ElectraForQuestionAnswering"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
  "classifier_dropout": null,
8
- "embedding_size": 768,
9
- "generator_hidden_size": 0.33333,
10
  "hidden_act": "gelu",
11
  "hidden_dropout_prob": 0.1,
12
  "hidden_size": 768,
@@ -14,15 +12,11 @@
14
  "intermediate_size": 3072,
15
  "layer_norm_eps": 1e-12,
16
  "max_position_embeddings": 512,
17
- "model_type": "electra",
18
  "num_attention_heads": 12,
19
  "num_hidden_layers": 12,
20
  "pad_token_id": 0,
21
  "position_embedding_type": "absolute",
22
- "summary_activation": "gelu",
23
- "summary_last_dropout": 0.1,
24
- "summary_type": "first",
25
- "summary_use_proj": true,
26
  "torch_dtype": "float32",
27
  "transformers_version": "4.35.2",
28
  "type_vocab_size": 2,
 
1
  {
2
+ "_name_or_path": "aubmindlab/bert-base-arabertv2",
3
  "architectures": [
4
+ "BertForQuestionAnswering"
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,
 
12
  "intermediate_size": 3072,
13
  "layer_norm_eps": 1e-12,
14
  "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
  "num_attention_heads": 12,
17
  "num_hidden_layers": 12,
18
  "pad_token_id": 0,
19
  "position_embedding_type": "absolute",
 
 
 
 
20
  "torch_dtype": "float32",
21
  "transformers_version": "4.35.2",
22
  "type_vocab_size": 2,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9195e9021569b4bfff14e9d9156cc44d9bcb1803dc8ecd44267427f7c3513d36
3
- size 538441104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:042f698a3ededb072d298d4f1bc2cfd9df70469622ec57b4415dc6438c6495c1
3
+ size 538440512
runs/Feb02_16-42-22_3a5395b179ef/events.out.tfevents.1706892143.3a5395b179ef.5358.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41924d6633a553a9dcfe2c0d9993de67c09fdacfc8916bcd5732444239edbc18
3
+ size 5353
runs/Feb02_16-42-22_3a5395b179ef/events.out.tfevents.1706892435.3a5395b179ef.5358.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c70310b2fb7c1858a03b5672e796dbee9076109a4b68902a2a5745572744d2bd
3
+ size 359
runs/Feb02_16-48-08_3a5395b179ef/events.out.tfevents.1706892490.3a5395b179ef.5358.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39c18dcf3557d4f33ea5f9ceb3e61465543ce98fb2e7e55634a52c2998621956
3
+ size 5354
runs/Feb02_16-56-54_3a5395b179ef/events.out.tfevents.1706893015.3a5395b179ef.5358.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03e91c1a51b8aea8d17b95d2ad72b6ed37c918c3b65c934d66ed2fc76dab73a8
3
+ size 4192
runs/Feb02_16-59-30_3a5395b179ef/events.out.tfevents.1706893171.3a5395b179ef.9947.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72769cede9774c1ea50e9a1ac7bde88a8c8e1219012a9afdff6ddb925e1c6fcf
3
+ size 5352
runs/Feb02_16-59-30_3a5395b179ef/events.out.tfevents.1706893469.3a5395b179ef.9947.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9816fe3ac796b6ea3639ff11529080b33b9134c73708c7fabbb31970c943ed9
3
+ size 359
runs/Feb02_17-40-35_3a5395b179ef/events.out.tfevents.1706895639.3a5395b179ef.9947.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4f2e4dd49dffa8d7442937a42f77c194a447e53cc2bc55908dbcfb32f659400
3
+ size 4184
runs/Feb02_17-42-45_3a5395b179ef/events.out.tfevents.1706895766.3a5395b179ef.20667.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef742de5eaabda1164936c5eebcd0e2306a06f0421c86800c38a5939e164e866
3
+ size 5352
runs/Feb02_17-42-45_3a5395b179ef/events.out.tfevents.1706896063.3a5395b179ef.20667.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0bfb0a2f4a569ef529e4361831d03f434271eaa7df9d115c8aafe0bb8da228a
3
+ size 359
runs/Feb02_17-54-49_3a5395b179ef/events.out.tfevents.1706896510.3a5395b179ef.20667.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94a58132d689715a8d87d81deaf2d16bef334e351c6eae6643ea75d383eb8c07
3
+ size 4763
special_tokens_map.json CHANGED
@@ -1,7 +1,37 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
 
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 CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,6 +1,254 @@
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  "content": "[PAD]",
5
  "lstrip": false,
6
  "normalized": false,
@@ -8,7 +256,7 @@
8
  "single_word": false,
9
  "special": true
10
  },
11
- "1": {
12
  "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
@@ -16,7 +264,7 @@
16
  "single_word": false,
17
  "special": true
18
  },
19
- "2": {
20
  "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +272,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "3": {
28
  "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
@@ -32,7 +280,7 @@
32
  "single_word": false,
33
  "special": true
34
  },
35
- "4": {
36
  "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
@@ -47,16 +295,51 @@
47
  "do_lower_case": false,
48
  "mask_token": "[MASK]",
49
  "max_len": 512,
 
50
  "model_max_length": 512,
51
  "never_split": [
 
 
 
 
 
 
 
 
 
 
52
  "[بريد]",
 
 
 
 
 
 
53
  "[مستخدم]",
 
 
 
 
 
 
 
 
 
 
 
 
54
  "[رابط]"
55
  ],
 
56
  "pad_token": "[PAD]",
 
 
57
  "sep_token": "[SEP]",
 
58
  "strip_accents": null,
59
  "tokenize_chinese_chars": true,
60
- "tokenizer_class": "ElectraTokenizer",
 
 
61
  "unk_token": "[UNK]"
62
  }
 
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
+ "content": "+ا",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": true,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "+ك",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": true,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "ب+",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": true,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "+هم",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": true,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "+ات",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": true,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "+ي",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": true,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "ل+",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": true,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "+هما",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": true,
65
+ "special": true
66
+ },
67
+ "8": {
68
+ "content": "+نا",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": true,
73
+ "special": true
74
+ },
75
+ "9": {
76
+ "content": "+ن",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": true,
81
+ "special": true
82
+ },
83
+ "10": {
84
+ "content": "+ها",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": true,
89
+ "special": true
90
+ },
91
+ "11": {
92
+ "content": "+كما",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": true,
97
+ "special": true
98
+ },
99
+ "12": {
100
+ "content": "+ة",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": true,
105
+ "special": true
106
+ },
107
+ "13": {
108
+ "content": "ف+",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": true,
113
+ "special": true
114
+ },
115
+ "14": {
116
+ "content": "+كم",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": true,
121
+ "special": true
122
+ },
123
+ "15": {
124
+ "content": "+كن",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": true,
129
+ "special": true
130
+ },
131
+ "16": {
132
+ "content": "+ت",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": true,
137
+ "special": true
138
+ },
139
+ "17": {
140
+ "content": "[بريد]",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": true,
145
+ "special": true
146
+ },
147
+ "18": {
148
+ "content": "[مستخدم]",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": true,
153
+ "special": true
154
+ },
155
+ "19": {
156
+ "content": "لل+",
157
+ "lstrip": false,
158
+ "normalized": true,
159
+ "rstrip": false,
160
+ "single_word": true,
161
+ "special": true
162
+ },
163
+ "20": {
164
+ "content": "ال+",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": true,
169
+ "special": true
170
+ },
171
+ "21": {
172
+ "content": "[رابط]",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": true,
177
+ "special": true
178
+ },
179
+ "22": {
180
+ "content": "س+",
181
+ "lstrip": false,
182
+ "normalized": true,
183
+ "rstrip": false,
184
+ "single_word": true,
185
+ "special": true
186
+ },
187
+ "23": {
188
+ "content": "+ان",
189
+ "lstrip": false,
190
+ "normalized": true,
191
+ "rstrip": false,
192
+ "single_word": true,
193
+ "special": true
194
+ },
195
+ "24": {
196
+ "content": "+وا",
197
+ "lstrip": false,
198
+ "normalized": true,
199
+ "rstrip": false,
200
+ "single_word": true,
201
+ "special": true
202
+ },
203
+ "25": {
204
+ "content": "+ه",
205
+ "lstrip": false,
206
+ "normalized": true,
207
+ "rstrip": false,
208
+ "single_word": true,
209
+ "special": true
210
+ },
211
+ "26": {
212
+ "content": "+ون",
213
+ "lstrip": false,
214
+ "normalized": true,
215
+ "rstrip": false,
216
+ "single_word": true,
217
+ "special": true
218
+ },
219
+ "27": {
220
+ "content": "+هن",
221
+ "lstrip": false,
222
+ "normalized": true,
223
+ "rstrip": false,
224
+ "single_word": true,
225
+ "special": true
226
+ },
227
+ "28": {
228
+ "content": "+ين",
229
+ "lstrip": false,
230
+ "normalized": true,
231
+ "rstrip": false,
232
+ "single_word": true,
233
+ "special": true
234
+ },
235
+ "29": {
236
+ "content": "��+",
237
+ "lstrip": false,
238
+ "normalized": true,
239
+ "rstrip": false,
240
+ "single_word": true,
241
+ "special": true
242
+ },
243
+ "30": {
244
+ "content": "ك+",
245
+ "lstrip": false,
246
+ "normalized": true,
247
+ "rstrip": false,
248
+ "single_word": true,
249
+ "special": true
250
+ },
251
+ "31": {
252
  "content": "[PAD]",
253
  "lstrip": false,
254
  "normalized": false,
 
256
  "single_word": false,
257
  "special": true
258
  },
259
+ "32": {
260
  "content": "[UNK]",
261
  "lstrip": false,
262
  "normalized": false,
 
264
  "single_word": false,
265
  "special": true
266
  },
267
+ "33": {
268
  "content": "[CLS]",
269
  "lstrip": false,
270
  "normalized": false,
 
272
  "single_word": false,
273
  "special": true
274
  },
275
+ "34": {
276
  "content": "[SEP]",
277
  "lstrip": false,
278
  "normalized": false,
 
280
  "single_word": false,
281
  "special": true
282
  },
283
+ "35": {
284
  "content": "[MASK]",
285
  "lstrip": false,
286
  "normalized": false,
 
295
  "do_lower_case": false,
296
  "mask_token": "[MASK]",
297
  "max_len": 512,
298
+ "max_length": 384,
299
  "model_max_length": 512,
300
  "never_split": [
301
+ "+ك",
302
+ "+كما",
303
+ "ك+",
304
+ "+وا",
305
+ "+ين",
306
+ "و+",
307
+ "+كن",
308
+ "+ان",
309
+ "+هم",
310
+ "+ة",
311
  "[بريد]",
312
+ "لل+",
313
+ "+ي",
314
+ "+ت",
315
+ "+ن",
316
+ "س+",
317
+ "ل+",
318
  "[مستخدم]",
319
+ "+كم",
320
+ "+ا",
321
+ "ب+",
322
+ "ف+",
323
+ "+نا",
324
+ "+ها",
325
+ "+ون",
326
+ "+هما",
327
+ "ال+",
328
+ "+ه",
329
+ "+هن",
330
+ "+ات",
331
  "[رابط]"
332
  ],
333
+ "pad_to_multiple_of": null,
334
  "pad_token": "[PAD]",
335
+ "pad_token_type_id": 0,
336
+ "padding_side": "right",
337
  "sep_token": "[SEP]",
338
+ "stride": 0,
339
  "strip_accents": null,
340
  "tokenize_chinese_chars": true,
341
+ "tokenizer_class": "BertTokenizer",
342
+ "truncation_side": "right",
343
+ "truncation_strategy": "only_second",
344
  "unk_token": "[UNK]"
345
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:609cc4ce1492d1799fed6dcedbfd1153dccfcb3a5590eed4cbd0090950d3d667
3
- size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc365b8d5e63af643c84313d4ac9694b56de16b91233e113e1786d273fa748aa
3
+ size 4536
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff