Hugging Face's logo

alomari7
/
ara-bert-okaz-style

Fill-Mask
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files
xet
 Metrics Community
alomari7 commited on
Commit
cdc35da
·
verified ·
1 Parent(s): bf797e3

رفع المودل المدرب (إصدار 1) - 143 مقالاً من عكاظ

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. checkpoint-108/config.json +24 -0
  2. checkpoint-108/model.safetensors +3 -0
  3. checkpoint-108/optimizer.pt +3 -0
  4. checkpoint-108/rng_state.pth +3 -0
  5. checkpoint-108/scheduler.pt +3 -0
  6. checkpoint-108/special_tokens_map.json +37 -0
  7. checkpoint-108/tokenizer.json +0 -0
  8. checkpoint-108/tokenizer_config.json +339 -0
  9. checkpoint-108/trainer_state.json +104 -0
  10. checkpoint-108/training_args.bin +3 -0
  11. checkpoint-108/vocab.txt +0 -0
  12. checkpoint-126/config.json +24 -0
  13. checkpoint-126/model.safetensors +3 -0
  14. checkpoint-126/optimizer.pt +3 -0
  15. checkpoint-126/rng_state.pth +3 -0
  16. checkpoint-126/scheduler.pt +3 -0
  17. checkpoint-126/special_tokens_map.json +37 -0
  18. checkpoint-126/tokenizer.json +0 -0
  19. checkpoint-126/tokenizer_config.json +339 -0
  20. checkpoint-126/trainer_state.json +118 -0
  21. checkpoint-126/training_args.bin +3 -0
  22. checkpoint-126/vocab.txt +0 -0
  23. checkpoint-144/config.json +24 -0
  24. checkpoint-144/model.safetensors +3 -0
  25. checkpoint-144/optimizer.pt +3 -0
  26. checkpoint-144/rng_state.pth +3 -0
  27. checkpoint-144/scheduler.pt +3 -0
  28. checkpoint-144/special_tokens_map.json +37 -0
  29. checkpoint-144/tokenizer.json +0 -0
  30. checkpoint-144/tokenizer_config.json +339 -0
  31. checkpoint-144/trainer_state.json +132 -0
  32. checkpoint-144/training_args.bin +3 -0
  33. checkpoint-144/vocab.txt +0 -0
  34. checkpoint-162/config.json +24 -0
  35. checkpoint-162/model.safetensors +3 -0
  36. checkpoint-162/optimizer.pt +3 -0
  37. checkpoint-162/rng_state.pth +3 -0
  38. checkpoint-162/scheduler.pt +3 -0
  39. checkpoint-162/special_tokens_map.json +37 -0
  40. checkpoint-162/tokenizer.json +0 -0
  41. checkpoint-162/tokenizer_config.json +339 -0
  42. checkpoint-162/trainer_state.json +146 -0
  43. checkpoint-162/training_args.bin +3 -0
  44. checkpoint-162/vocab.txt +0 -0
  45. checkpoint-18/config.json +24 -0
  46. checkpoint-18/model.safetensors +3 -0
  47. checkpoint-18/optimizer.pt +3 -0
  48. checkpoint-18/rng_state.pth +3 -0
  49. checkpoint-18/scheduler.pt +3 -0
  50. checkpoint-18/special_tokens_map.json +37 -0
checkpoint-108/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
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
+ "transformers_version": "4.57.1",
21
+ "type_vocab_size": 2,
22
+ "use_cache": true,
23
+ "vocab_size": 64000
24
+ }
checkpoint-108/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81ffa9870541f14c089e8fb0abeb63ffb24eb787eb073d45e71f99ea581ef876
3
+ size 541059232
checkpoint-108/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8288e3971155e059466b5b90ebbf7433592a2885587543749e436f92b7c6c949
3
+ size 1082243275
checkpoint-108/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7110c039251db37fa3e2d7ef1f59d1f41c06bb74696766f11e2d07972820e1bb
3
+ size 14645
checkpoint-108/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9a23bf57a10f87247943de88df2c33da4b083a79aa4349cd66c17c8f4df28da
3
+ size 1465
checkpoint-108/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
+ }
checkpoint-108/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-108/tokenizer_config.json ADDED
@@ -0,0 +1,339 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "32": {
260
+ "content": "[UNK]",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "33": {
268
+ "content": "[CLS]",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "34": {
276
+ "content": "[SEP]",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "35": {
284
+ "content": "[MASK]",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ }
291
+ },
292
+ "clean_up_tokenization_spaces": false,
293
+ "cls_token": "[CLS]",
294
+ "do_basic_tokenize": true,
295
+ "do_lower_case": false,
296
+ "extra_special_tokens": {},
297
+ "mask_token": "[MASK]",
298
+ "max_len": 512,
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_token": "[PAD]",
334
+ "sep_token": "[SEP]",
335
+ "strip_accents": null,
336
+ "tokenize_chinese_chars": true,
337
+ "tokenizer_class": "BertTokenizer",
338
+ "unk_token": "[UNK]"
339
+ }
checkpoint-108/trainer_state.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 6.0,
6
+ "eval_steps": 500,
7
+ "global_step": 108,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.5555555555555556,
14
+ "grad_norm": 7.983851909637451,
15
+ "learning_rate": 4.75e-05,
16
+ "loss": 3.208,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 1.1111111111111112,
21
+ "grad_norm": 7.089095115661621,
22
+ "learning_rate": 4.472222222222223e-05,
23
+ "loss": 2.7118,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 1.6666666666666665,
28
+ "grad_norm": 7.205652236938477,
29
+ "learning_rate": 4.194444444444445e-05,
30
+ "loss": 2.5484,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 2.2222222222222223,
35
+ "grad_norm": 6.832472801208496,
36
+ "learning_rate": 3.9166666666666665e-05,
37
+ "loss": 2.5161,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 2.7777777777777777,
42
+ "grad_norm": 7.031569004058838,
43
+ "learning_rate": 3.638888888888889e-05,
44
+ "loss": 2.423,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 3.3333333333333335,
49
+ "grad_norm": 7.300843238830566,
50
+ "learning_rate": 3.3611111111111116e-05,
51
+ "loss": 2.3249,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 3.888888888888889,
56
+ "grad_norm": 6.9205145835876465,
57
+ "learning_rate": 3.0833333333333335e-05,
58
+ "loss": 2.1974,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 4.444444444444445,
63
+ "grad_norm": 6.269876003265381,
64
+ "learning_rate": 2.8055555555555557e-05,
65
+ "loss": 2.1926,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 5.0,
70
+ "grad_norm": 7.110064506530762,
71
+ "learning_rate": 2.527777777777778e-05,
72
+ "loss": 2.2065,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 5.555555555555555,
77
+ "grad_norm": 6.074955940246582,
78
+ "learning_rate": 2.25e-05,
79
+ "loss": 2.0698,
80
+ "step": 100
81
+ }
82
+ ],
83
+ "logging_steps": 10,
84
+ "max_steps": 180,
85
+ "num_input_tokens_seen": 0,
86
+ "num_train_epochs": 10,
87
+ "save_steps": 500,
88
+ "stateful_callbacks": {
89
+ "TrainerControl": {
90
+ "args": {
91
+ "should_epoch_stop": false,
92
+ "should_evaluate": false,
93
+ "should_log": false,
94
+ "should_save": true,
95
+ "should_training_stop": false
96
+ },
97
+ "attributes": {}
98
+ }
99
+ },
100
+ "total_flos": 225341984391168.0,
101
+ "train_batch_size": 8,
102
+ "trial_name": null,
103
+ "trial_params": null
104
+ }
checkpoint-108/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c03a811dc205301270977a398ff9f5c42e4e63e81574089e376128f88a3b50b
3
+ size 5841
checkpoint-108/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-126/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
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
+ "transformers_version": "4.57.1",
21
+ "type_vocab_size": 2,
22
+ "use_cache": true,
23
+ "vocab_size": 64000
24
+ }
checkpoint-126/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a8be0d0b5356ad8fd64cdad5588164c365e436cd2100276474afb420d2eb403
3
+ size 541059232
checkpoint-126/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5e6eb7a946a7c8796eb0716f2a5c241497f4c6ca78fc8380f86157c8a78c63d
3
+ size 1082243275
checkpoint-126/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7afab87019f2ba3728d9cf5df0fe8444f796dbce139aed393518bbe7b44dc0db
3
+ size 14645
checkpoint-126/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee33af126375ed4160cb5cdbe7f1e422394b23daa8f5372caf78319d5804c7e2
3
+ size 1465
checkpoint-126/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
+ }
checkpoint-126/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-126/tokenizer_config.json ADDED
@@ -0,0 +1,339 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "32": {
260
+ "content": "[UNK]",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "33": {
268
+ "content": "[CLS]",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "34": {
276
+ "content": "[SEP]",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "35": {
284
+ "content": "[MASK]",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ }
291
+ },
292
+ "clean_up_tokenization_spaces": false,
293
+ "cls_token": "[CLS]",
294
+ "do_basic_tokenize": true,
295
+ "do_lower_case": false,
296
+ "extra_special_tokens": {},
297
+ "mask_token": "[MASK]",
298
+ "max_len": 512,
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_token": "[PAD]",
334
+ "sep_token": "[SEP]",
335
+ "strip_accents": null,
336
+ "tokenize_chinese_chars": true,
337
+ "tokenizer_class": "BertTokenizer",
338
+ "unk_token": "[UNK]"
339
+ }
checkpoint-126/trainer_state.json ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 7.0,
6
+ "eval_steps": 500,
7
+ "global_step": 126,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.5555555555555556,
14
+ "grad_norm": 7.983851909637451,
15
+ "learning_rate": 4.75e-05,
16
+ "loss": 3.208,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 1.1111111111111112,
21
+ "grad_norm": 7.089095115661621,
22
+ "learning_rate": 4.472222222222223e-05,
23
+ "loss": 2.7118,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 1.6666666666666665,
28
+ "grad_norm": 7.205652236938477,
29
+ "learning_rate": 4.194444444444445e-05,
30
+ "loss": 2.5484,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 2.2222222222222223,
35
+ "grad_norm": 6.832472801208496,
36
+ "learning_rate": 3.9166666666666665e-05,
37
+ "loss": 2.5161,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 2.7777777777777777,
42
+ "grad_norm": 7.031569004058838,
43
+ "learning_rate": 3.638888888888889e-05,
44
+ "loss": 2.423,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 3.3333333333333335,
49
+ "grad_norm": 7.300843238830566,
50
+ "learning_rate": 3.3611111111111116e-05,
51
+ "loss": 2.3249,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 3.888888888888889,
56
+ "grad_norm": 6.9205145835876465,
57
+ "learning_rate": 3.0833333333333335e-05,
58
+ "loss": 2.1974,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 4.444444444444445,
63
+ "grad_norm": 6.269876003265381,
64
+ "learning_rate": 2.8055555555555557e-05,
65
+ "loss": 2.1926,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 5.0,
70
+ "grad_norm": 7.110064506530762,
71
+ "learning_rate": 2.527777777777778e-05,
72
+ "loss": 2.2065,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 5.555555555555555,
77
+ "grad_norm": 6.074955940246582,
78
+ "learning_rate": 2.25e-05,
79
+ "loss": 2.0698,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 6.111111111111111,
84
+ "grad_norm": 7.408507347106934,
85
+ "learning_rate": 1.9722222222222224e-05,
86
+ "loss": 2.0113,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 6.666666666666667,
91
+ "grad_norm": 6.42540168762207,
92
+ "learning_rate": 1.6944444444444446e-05,
93
+ "loss": 2.0189,
94
+ "step": 120
95
+ }
96
+ ],
97
+ "logging_steps": 10,
98
+ "max_steps": 180,
99
+ "num_input_tokens_seen": 0,
100
+ "num_train_epochs": 10,
101
+ "save_steps": 500,
102
+ "stateful_callbacks": {
103
+ "TrainerControl": {
104
+ "args": {
105
+ "should_epoch_stop": false,
106
+ "should_evaluate": false,
107
+ "should_log": false,
108
+ "should_save": true,
109
+ "should_training_stop": false
110
+ },
111
+ "attributes": {}
112
+ }
113
+ },
114
+ "total_flos": 262994979373056.0,
115
+ "train_batch_size": 8,
116
+ "trial_name": null,
117
+ "trial_params": null
118
+ }
checkpoint-126/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c03a811dc205301270977a398ff9f5c42e4e63e81574089e376128f88a3b50b
3
+ size 5841
checkpoint-126/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-144/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
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
+ "transformers_version": "4.57.1",
21
+ "type_vocab_size": 2,
22
+ "use_cache": true,
23
+ "vocab_size": 64000
24
+ }
checkpoint-144/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:619eace0192d5542db4589457c8a78be9867685d43b178350a3d2de4924fd175
3
+ size 541059232
checkpoint-144/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bad09679f9726f38197980dfc1b33a611b81187a309f878fe0a8da08e872662
3
+ size 1082243275
checkpoint-144/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ee156db65a8c57907c6309ee07922a6ae155f9261f6b9f1cccea5c8ca1e706c
3
+ size 14645
checkpoint-144/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a72e59f346cd9adf3841e957bace91e0a0a6b285444ba5ecd3d06673957e90af
3
+ size 1465
checkpoint-144/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
+ }
checkpoint-144/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-144/tokenizer_config.json ADDED
@@ -0,0 +1,339 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "32": {
260
+ "content": "[UNK]",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "33": {
268
+ "content": "[CLS]",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "34": {
276
+ "content": "[SEP]",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "35": {
284
+ "content": "[MASK]",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ }
291
+ },
292
+ "clean_up_tokenization_spaces": false,
293
+ "cls_token": "[CLS]",
294
+ "do_basic_tokenize": true,
295
+ "do_lower_case": false,
296
+ "extra_special_tokens": {},
297
+ "mask_token": "[MASK]",
298
+ "max_len": 512,
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_token": "[PAD]",
334
+ "sep_token": "[SEP]",
335
+ "strip_accents": null,
336
+ "tokenize_chinese_chars": true,
337
+ "tokenizer_class": "BertTokenizer",
338
+ "unk_token": "[UNK]"
339
+ }
checkpoint-144/trainer_state.json ADDED
@@ -0,0 +1,132 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 8.0,
6
+ "eval_steps": 500,
7
+ "global_step": 144,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.5555555555555556,
14
+ "grad_norm": 7.983851909637451,
15
+ "learning_rate": 4.75e-05,
16
+ "loss": 3.208,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 1.1111111111111112,
21
+ "grad_norm": 7.089095115661621,
22
+ "learning_rate": 4.472222222222223e-05,
23
+ "loss": 2.7118,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 1.6666666666666665,
28
+ "grad_norm": 7.205652236938477,
29
+ "learning_rate": 4.194444444444445e-05,
30
+ "loss": 2.5484,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 2.2222222222222223,
35
+ "grad_norm": 6.832472801208496,
36
+ "learning_rate": 3.9166666666666665e-05,
37
+ "loss": 2.5161,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 2.7777777777777777,
42
+ "grad_norm": 7.031569004058838,
43
+ "learning_rate": 3.638888888888889e-05,
44
+ "loss": 2.423,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 3.3333333333333335,
49
+ "grad_norm": 7.300843238830566,
50
+ "learning_rate": 3.3611111111111116e-05,
51
+ "loss": 2.3249,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 3.888888888888889,
56
+ "grad_norm": 6.9205145835876465,
57
+ "learning_rate": 3.0833333333333335e-05,
58
+ "loss": 2.1974,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 4.444444444444445,
63
+ "grad_norm": 6.269876003265381,
64
+ "learning_rate": 2.8055555555555557e-05,
65
+ "loss": 2.1926,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 5.0,
70
+ "grad_norm": 7.110064506530762,
71
+ "learning_rate": 2.527777777777778e-05,
72
+ "loss": 2.2065,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 5.555555555555555,
77
+ "grad_norm": 6.074955940246582,
78
+ "learning_rate": 2.25e-05,
79
+ "loss": 2.0698,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 6.111111111111111,
84
+ "grad_norm": 7.408507347106934,
85
+ "learning_rate": 1.9722222222222224e-05,
86
+ "loss": 2.0113,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 6.666666666666667,
91
+ "grad_norm": 6.42540168762207,
92
+ "learning_rate": 1.6944444444444446e-05,
93
+ "loss": 2.0189,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 7.222222222222222,
98
+ "grad_norm": 6.871105670928955,
99
+ "learning_rate": 1.4166666666666668e-05,
100
+ "loss": 1.972,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 7.777777777777778,
105
+ "grad_norm": 5.8642144203186035,
106
+ "learning_rate": 1.138888888888889e-05,
107
+ "loss": 2.0234,
108
+ "step": 140
109
+ }
110
+ ],
111
+ "logging_steps": 10,
112
+ "max_steps": 180,
113
+ "num_input_tokens_seen": 0,
114
+ "num_train_epochs": 10,
115
+ "save_steps": 500,
116
+ "stateful_callbacks": {
117
+ "TrainerControl": {
118
+ "args": {
119
+ "should_epoch_stop": false,
120
+ "should_evaluate": false,
121
+ "should_log": false,
122
+ "should_save": true,
123
+ "should_training_stop": false
124
+ },
125
+ "attributes": {}
126
+ }
127
+ },
128
+ "total_flos": 300335296512000.0,
129
+ "train_batch_size": 8,
130
+ "trial_name": null,
131
+ "trial_params": null
132
+ }
checkpoint-144/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c03a811dc205301270977a398ff9f5c42e4e63e81574089e376128f88a3b50b
3
+ size 5841
checkpoint-144/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-162/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
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
+ "transformers_version": "4.57.1",
21
+ "type_vocab_size": 2,
22
+ "use_cache": true,
23
+ "vocab_size": 64000
24
+ }
checkpoint-162/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ed4d2756b75919a3be6d2415c14a5563faaa08c0902039e1ba06acc967cfead
3
+ size 541059232
checkpoint-162/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1f1f618d18d8dffda9239f1b3766af776989cf13d6ba1ddebd92efdbee5f52c
3
+ size 1082243275
checkpoint-162/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0e728f225b31c366bcbec40fe9425a040793d3f7669b8c40aec549d9f8baa14
3
+ size 14645
checkpoint-162/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd46355ed88fcf61f07fb9722251f6cf526b715d6152b4a5552a78e1e1efd37b
3
+ size 1465
checkpoint-162/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
+ }
checkpoint-162/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-162/tokenizer_config.json ADDED
@@ -0,0 +1,339 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "32": {
260
+ "content": "[UNK]",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "33": {
268
+ "content": "[CLS]",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "34": {
276
+ "content": "[SEP]",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "35": {
284
+ "content": "[MASK]",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ }
291
+ },
292
+ "clean_up_tokenization_spaces": false,
293
+ "cls_token": "[CLS]",
294
+ "do_basic_tokenize": true,
295
+ "do_lower_case": false,
296
+ "extra_special_tokens": {},
297
+ "mask_token": "[MASK]",
298
+ "max_len": 512,
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_token": "[PAD]",
334
+ "sep_token": "[SEP]",
335
+ "strip_accents": null,
336
+ "tokenize_chinese_chars": true,
337
+ "tokenizer_class": "BertTokenizer",
338
+ "unk_token": "[UNK]"
339
+ }
checkpoint-162/trainer_state.json ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 9.0,
6
+ "eval_steps": 500,
7
+ "global_step": 162,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.5555555555555556,
14
+ "grad_norm": 7.983851909637451,
15
+ "learning_rate": 4.75e-05,
16
+ "loss": 3.208,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 1.1111111111111112,
21
+ "grad_norm": 7.089095115661621,
22
+ "learning_rate": 4.472222222222223e-05,
23
+ "loss": 2.7118,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 1.6666666666666665,
28
+ "grad_norm": 7.205652236938477,
29
+ "learning_rate": 4.194444444444445e-05,
30
+ "loss": 2.5484,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 2.2222222222222223,
35
+ "grad_norm": 6.832472801208496,
36
+ "learning_rate": 3.9166666666666665e-05,
37
+ "loss": 2.5161,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 2.7777777777777777,
42
+ "grad_norm": 7.031569004058838,
43
+ "learning_rate": 3.638888888888889e-05,
44
+ "loss": 2.423,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 3.3333333333333335,
49
+ "grad_norm": 7.300843238830566,
50
+ "learning_rate": 3.3611111111111116e-05,
51
+ "loss": 2.3249,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 3.888888888888889,
56
+ "grad_norm": 6.9205145835876465,
57
+ "learning_rate": 3.0833333333333335e-05,
58
+ "loss": 2.1974,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 4.444444444444445,
63
+ "grad_norm": 6.269876003265381,
64
+ "learning_rate": 2.8055555555555557e-05,
65
+ "loss": 2.1926,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 5.0,
70
+ "grad_norm": 7.110064506530762,
71
+ "learning_rate": 2.527777777777778e-05,
72
+ "loss": 2.2065,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 5.555555555555555,
77
+ "grad_norm": 6.074955940246582,
78
+ "learning_rate": 2.25e-05,
79
+ "loss": 2.0698,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 6.111111111111111,
84
+ "grad_norm": 7.408507347106934,
85
+ "learning_rate": 1.9722222222222224e-05,
86
+ "loss": 2.0113,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 6.666666666666667,
91
+ "grad_norm": 6.42540168762207,
92
+ "learning_rate": 1.6944444444444446e-05,
93
+ "loss": 2.0189,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 7.222222222222222,
98
+ "grad_norm": 6.871105670928955,
99
+ "learning_rate": 1.4166666666666668e-05,
100
+ "loss": 1.972,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 7.777777777777778,
105
+ "grad_norm": 5.8642144203186035,
106
+ "learning_rate": 1.138888888888889e-05,
107
+ "loss": 2.0234,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 8.333333333333334,
112
+ "grad_norm": 6.80947732925415,
113
+ "learning_rate": 8.611111111111112e-06,
114
+ "loss": 2.0043,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 8.88888888888889,
119
+ "grad_norm": 5.686942100524902,
120
+ "learning_rate": 5.833333333333334e-06,
121
+ "loss": 1.8342,
122
+ "step": 160
123
+ }
124
+ ],
125
+ "logging_steps": 10,
126
+ "max_steps": 180,
127
+ "num_input_tokens_seen": 0,
128
+ "num_train_epochs": 10,
129
+ "save_steps": 500,
130
+ "stateful_callbacks": {
131
+ "TrainerControl": {
132
+ "args": {
133
+ "should_epoch_stop": false,
134
+ "should_evaluate": false,
135
+ "should_log": false,
136
+ "should_save": true,
137
+ "should_training_stop": false
138
+ },
139
+ "attributes": {}
140
+ }
141
+ },
142
+ "total_flos": 337877208576000.0,
143
+ "train_batch_size": 8,
144
+ "trial_name": null,
145
+ "trial_params": null
146
+ }
checkpoint-162/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c03a811dc205301270977a398ff9f5c42e4e63e81574089e376128f88a3b50b
3
+ size 5841
checkpoint-162/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-18/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
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
+ "transformers_version": "4.57.1",
21
+ "type_vocab_size": 2,
22
+ "use_cache": true,
23
+ "vocab_size": 64000
24
+ }
checkpoint-18/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:083dbe33e5c7f25572aac144d70bd8ab467630ce2779a6e230025dd95078526f
3
+ size 541059232
checkpoint-18/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3598f517211b480c1614338bae4ccefb24225c7ca347f3011dc015a3f940a5b0
3
+ size 1082243275
checkpoint-18/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:424d2812c8c5d0a18108233ad502b06f6ab8caa73c19d663f174bc8deac4f1f2
3
+ size 14645
checkpoint-18/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4e32d815895250349ed9c3c68f1e66fb140db59e4a374b1b4db8b599b4bfd69
3
+ size 1465
checkpoint-18/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
+ }