Hugging Face's logo

MuhammadHelmy
/
GATE-AraBert-v1-AuthId-Aug

Safetensors
bert
Model card Files
xet
 Community
MuhammadHelmy commited on
Commit
9b221cf
·
verified ·
1 Parent(s): ade168b

Upload folder using huggingface_hub

Browse files
Files changed (29) hide show
  1. checkpoint-17500/config.json +71 -0
  2. checkpoint-17500/model.safetensors +3 -0
  3. checkpoint-17500/optimizer.pt +3 -0
  4. checkpoint-17500/rng_state.pth +3 -0
  5. checkpoint-17500/scheduler.pt +3 -0
  6. checkpoint-17500/special_tokens_map.json +37 -0
  7. checkpoint-17500/tokenizer.json +0 -0
  8. checkpoint-17500/tokenizer_config.json +94 -0
  9. checkpoint-17500/trainer_state.json +279 -0
  10. checkpoint-17500/training_args.bin +3 -0
  11. checkpoint-17500/vocab.txt +0 -0
  12. checkpoint-17560/config.json +71 -0
  13. checkpoint-17560/model.safetensors +3 -0
  14. checkpoint-17560/optimizer.pt +3 -0
  15. checkpoint-17560/rng_state.pth +3 -0
  16. checkpoint-17560/scheduler.pt +3 -0
  17. checkpoint-17560/special_tokens_map.json +37 -0
  18. checkpoint-17560/tokenizer.json +0 -0
  19. checkpoint-17560/tokenizer_config.json +94 -0
  20. checkpoint-17560/trainer_state.json +279 -0
  21. checkpoint-17560/training_args.bin +3 -0
  22. checkpoint-17560/vocab.txt +0 -0
  23. config.json +71 -0
  24. model.safetensors +3 -0
  25. special_tokens_map.json +37 -0
  26. tokenizer.json +0 -0
  27. tokenizer_config.json +94 -0
  28. training_args.bin +3 -0
  29. vocab.txt +0 -0
checkpoint-17500/config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2",
14
+ "3": "LABEL_3",
15
+ "4": "LABEL_4",
16
+ "5": "LABEL_5",
17
+ "6": "LABEL_6",
18
+ "7": "LABEL_7",
19
+ "8": "LABEL_8",
20
+ "9": "LABEL_9",
21
+ "10": "LABEL_10",
22
+ "11": "LABEL_11",
23
+ "12": "LABEL_12",
24
+ "13": "LABEL_13",
25
+ "14": "LABEL_14",
26
+ "15": "LABEL_15",
27
+ "16": "LABEL_16",
28
+ "17": "LABEL_17",
29
+ "18": "LABEL_18",
30
+ "19": "LABEL_19",
31
+ "20": "LABEL_20"
32
+ },
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 3072,
35
+ "label2id": {
36
+ "LABEL_0": 0,
37
+ "LABEL_1": 1,
38
+ "LABEL_10": 10,
39
+ "LABEL_11": 11,
40
+ "LABEL_12": 12,
41
+ "LABEL_13": 13,
42
+ "LABEL_14": 14,
43
+ "LABEL_15": 15,
44
+ "LABEL_16": 16,
45
+ "LABEL_17": 17,
46
+ "LABEL_18": 18,
47
+ "LABEL_19": 19,
48
+ "LABEL_2": 2,
49
+ "LABEL_20": 20,
50
+ "LABEL_3": 3,
51
+ "LABEL_4": 4,
52
+ "LABEL_5": 5,
53
+ "LABEL_6": 6,
54
+ "LABEL_7": 7,
55
+ "LABEL_8": 8,
56
+ "LABEL_9": 9
57
+ },
58
+ "layer_norm_eps": 1e-12,
59
+ "max_position_embeddings": 512,
60
+ "model_type": "bert",
61
+ "num_attention_heads": 12,
62
+ "num_hidden_layers": 12,
63
+ "pad_token_id": 0,
64
+ "position_embedding_type": "absolute",
65
+ "problem_type": "single_label_classification",
66
+ "torch_dtype": "float32",
67
+ "transformers_version": "4.52.4",
68
+ "type_vocab_size": 2,
69
+ "use_cache": true,
70
+ "vocab_size": 64000
71
+ }
checkpoint-17500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9be5453d9470d5e962c94662e09143fd5576586b1213656f13759b3262dadda
3
+ size 540861516
checkpoint-17500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9d2433539596b6bb5a320315b705a6ca070519acdd7482532f07a347ed900f1
3
+ size 1081844026
checkpoint-17500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c0710207aec69e1c8fc657157452981e23cd04402332934c98fb4fba6d88a32
3
+ size 14244
checkpoint-17500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53aaa0be904328181e2a7503b0f8ecfb986f072e679ef94a610b84d0857bf662
3
+ size 1064
checkpoint-17500/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-17500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-17500/tokenizer_config.json ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "[رابط]",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": true,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "[بريد]",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": true,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "[مستخدم]",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": true,
65
+ "special": true
66
+ }
67
+ },
68
+ "clean_up_tokenization_spaces": true,
69
+ "cls_token": "[CLS]",
70
+ "do_basic_tokenize": true,
71
+ "do_lower_case": false,
72
+ "extra_special_tokens": {},
73
+ "mask_token": "[MASK]",
74
+ "max_len": 512,
75
+ "max_length": 512,
76
+ "model_max_length": 512,
77
+ "never_split": [
78
+ "[بريد]",
79
+ "[مستخدم]",
80
+ "[رابط]"
81
+ ],
82
+ "pad_to_multiple_of": null,
83
+ "pad_token": "[PAD]",
84
+ "pad_token_type_id": 0,
85
+ "padding_side": "right",
86
+ "sep_token": "[SEP]",
87
+ "stride": 0,
88
+ "strip_accents": null,
89
+ "tokenize_chinese_chars": true,
90
+ "tokenizer_class": "BertTokenizer",
91
+ "truncation_side": "right",
92
+ "truncation_strategy": "longest_first",
93
+ "unk_token": "[UNK]"
94
+ }
checkpoint-17500/trainer_state.json ADDED
@@ -0,0 +1,279 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.9863325740318905,
6
+ "eval_steps": 500,
7
+ "global_step": 17500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.11389521640091116,
14
+ "grad_norm": 14.930135726928711,
15
+ "learning_rate": 5.683371298405468e-06,
16
+ "loss": 2.8432,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.22779043280182232,
21
+ "grad_norm": 18.998573303222656,
22
+ "learning_rate": 1.1378132118451027e-05,
23
+ "loss": 1.5596,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.3416856492027335,
28
+ "grad_norm": 10.675321578979492,
29
+ "learning_rate": 1.7072892938496583e-05,
30
+ "loss": 0.7698,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.45558086560364464,
35
+ "grad_norm": 28.9031925201416,
36
+ "learning_rate": 1.998833556232835e-05,
37
+ "loss": 0.517,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 0.5694760820045558,
42
+ "grad_norm": 57.30187225341797,
43
+ "learning_rate": 1.9891126119574924e-05,
44
+ "loss": 0.3908,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 0.683371298405467,
49
+ "grad_norm": 2.194150924682617,
50
+ "learning_rate": 1.9696284292584868e-05,
51
+ "loss": 0.319,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 0.7972665148063781,
56
+ "grad_norm": 4.897868633270264,
57
+ "learning_rate": 1.9405733307479062e-05,
58
+ "loss": 0.2745,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 0.9111617312072893,
63
+ "grad_norm": 2.3224313259124756,
64
+ "learning_rate": 1.9022341107207095e-05,
65
+ "loss": 0.2757,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 1.0250569476082005,
70
+ "grad_norm": 1.0110756158828735,
71
+ "learning_rate": 1.854989204292958e-05,
72
+ "loss": 0.2428,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 1.1389521640091116,
77
+ "grad_norm": 0.5717478394508362,
78
+ "learning_rate": 1.799304951980565e-05,
79
+ "loss": 0.1836,
80
+ "step": 5000
81
+ },
82
+ {
83
+ "epoch": 1.2528473804100229,
84
+ "grad_norm": 2.5286736488342285,
85
+ "learning_rate": 1.7357309965898177e-05,
86
+ "loss": 0.1864,
87
+ "step": 5500
88
+ },
89
+ {
90
+ "epoch": 1.366742596810934,
91
+ "grad_norm": 10.785357475280762,
92
+ "learning_rate": 1.6648948578555884e-05,
93
+ "loss": 0.1929,
94
+ "step": 6000
95
+ },
96
+ {
97
+ "epoch": 1.4806378132118452,
98
+ "grad_norm": 76.80316925048828,
99
+ "learning_rate": 1.587495738379394e-05,
100
+ "loss": 0.1762,
101
+ "step": 6500
102
+ },
103
+ {
104
+ "epoch": 1.5945330296127562,
105
+ "grad_norm": 0.777511477470398,
106
+ "learning_rate": 1.5042976220070502e-05,
107
+ "loss": 0.1631,
108
+ "step": 7000
109
+ },
110
+ {
111
+ "epoch": 1.7084282460136673,
112
+ "grad_norm": 8.146851539611816,
113
+ "learning_rate": 1.4161217327697978e-05,
114
+ "loss": 0.1562,
115
+ "step": 7500
116
+ },
117
+ {
118
+ "epoch": 1.8223234624145785,
119
+ "grad_norm": 1.3531783819198608,
120
+ "learning_rate": 1.3238384288244678e-05,
121
+ "loss": 0.1653,
122
+ "step": 8000
123
+ },
124
+ {
125
+ "epoch": 1.9362186788154898,
126
+ "grad_norm": 2.7191245555877686,
127
+ "learning_rate": 1.2283586114052062e-05,
128
+ "loss": 0.1546,
129
+ "step": 8500
130
+ },
131
+ {
132
+ "epoch": 2.050113895216401,
133
+ "grad_norm": 0.11562561243772507,
134
+ "learning_rate": 1.1306247335864585e-05,
135
+ "loss": 0.124,
136
+ "step": 9000
137
+ },
138
+ {
139
+ "epoch": 2.164009111617312,
140
+ "grad_norm": 0.7750993371009827,
141
+ "learning_rate": 1.0316014976070583e-05,
142
+ "loss": 0.097,
143
+ "step": 9500
144
+ },
145
+ {
146
+ "epoch": 2.277904328018223,
147
+ "grad_norm": 0.973026692867279,
148
+ "learning_rate": 9.322663325793849e-06,
149
+ "loss": 0.0993,
150
+ "step": 10000
151
+ },
152
+ {
153
+ "epoch": 2.3917995444191344,
154
+ "grad_norm": 0.6115517020225525,
155
+ "learning_rate": 8.335997465753155e-06,
156
+ "loss": 0.1,
157
+ "step": 10500
158
+ },
159
+ {
160
+ "epoch": 2.5056947608200457,
161
+ "grad_norm": 0.7755500674247742,
162
+ "learning_rate": 7.365756483206719e-06,
163
+ "loss": 0.0878,
164
+ "step": 11000
165
+ },
166
+ {
167
+ "epoch": 2.619589977220957,
168
+ "grad_norm": 5.184209823608398,
169
+ "learning_rate": 6.421517340298689e-06,
170
+ "loss": 0.0925,
171
+ "step": 11500
172
+ },
173
+ {
174
+ "epoch": 2.733485193621868,
175
+ "grad_norm": 0.5563125610351562,
176
+ "learning_rate": 5.512600342694685e-06,
177
+ "loss": 0.1162,
178
+ "step": 12000
179
+ },
180
+ {
181
+ "epoch": 2.847380410022779,
182
+ "grad_norm": 1.4436191320419312,
183
+ "learning_rate": 4.6479771415976616e-06,
184
+ "loss": 0.0824,
185
+ "step": 12500
186
+ },
187
+ {
188
+ "epoch": 2.9612756264236904,
189
+ "grad_norm": 0.0020386124961078167,
190
+ "learning_rate": 3.8361821772289766e-06,
191
+ "loss": 0.0886,
192
+ "step": 13000
193
+ },
194
+ {
195
+ "epoch": 3.075170842824601,
196
+ "grad_norm": 0.896149754524231,
197
+ "learning_rate": 3.0852284378899054e-06,
198
+ "loss": 0.0793,
199
+ "step": 13500
200
+ },
201
+ {
202
+ "epoch": 3.1890660592255125,
203
+ "grad_norm": 0.5485937595367432,
204
+ "learning_rate": 2.4025283661210406e-06,
205
+ "loss": 0.0714,
206
+ "step": 14000
207
+ },
208
+ {
209
+ "epoch": 3.3029612756264237,
210
+ "grad_norm": 1.4541118144989014,
211
+ "learning_rate": 1.7948206926714952e-06,
212
+ "loss": 0.0681,
213
+ "step": 14500
214
+ },
215
+ {
216
+ "epoch": 3.416856492027335,
217
+ "grad_norm": 2.268272876739502,
218
+ "learning_rate": 1.2681039204781863e-06,
219
+ "loss": 0.0706,
220
+ "step": 15000
221
+ },
222
+ {
223
+ "epoch": 3.5307517084282463,
224
+ "grad_norm": 1.2012200355529785,
225
+ "learning_rate": 8.275771152152412e-07,
226
+ "loss": 0.0674,
227
+ "step": 15500
228
+ },
229
+ {
230
+ "epoch": 3.644646924829157,
231
+ "grad_norm": 0.6027458310127258,
232
+ "learning_rate": 4.775885868524232e-07,
233
+ "loss": 0.0705,
234
+ "step": 16000
235
+ },
236
+ {
237
+ "epoch": 3.7585421412300684,
238
+ "grad_norm": 1.907026767730713,
239
+ "learning_rate": 2.2159296877185987e-07,
240
+ "loss": 0.0714,
241
+ "step": 16500
242
+ },
243
+ {
244
+ "epoch": 3.8724373576309796,
245
+ "grad_norm": 0.64386385679245,
246
+ "learning_rate": 6.211711810237497e-08,
247
+ "loss": 0.0762,
248
+ "step": 17000
249
+ },
250
+ {
251
+ "epoch": 3.9863325740318905,
252
+ "grad_norm": 0.9830172061920166,
253
+ "learning_rate": 7.351738591621082e-10,
254
+ "loss": 0.0757,
255
+ "step": 17500
256
+ }
257
+ ],
258
+ "logging_steps": 500,
259
+ "max_steps": 17560,
260
+ "num_input_tokens_seen": 0,
261
+ "num_train_epochs": 4,
262
+ "save_steps": 500,
263
+ "stateful_callbacks": {
264
+ "TrainerControl": {
265
+ "args": {
266
+ "should_epoch_stop": false,
267
+ "should_evaluate": false,
268
+ "should_log": false,
269
+ "should_save": true,
270
+ "should_training_stop": false
271
+ },
272
+ "attributes": {}
273
+ }
274
+ },
275
+ "total_flos": 7.368366329856e+16,
276
+ "train_batch_size": 16,
277
+ "trial_name": null,
278
+ "trial_params": null
279
+ }
checkpoint-17500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efbe6b9c4e2f1a677380f96fef8cc482360dcb08a3708e5c8354407fc1ab202e
3
+ size 5304
checkpoint-17500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-17560/config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2",
14
+ "3": "LABEL_3",
15
+ "4": "LABEL_4",
16
+ "5": "LABEL_5",
17
+ "6": "LABEL_6",
18
+ "7": "LABEL_7",
19
+ "8": "LABEL_8",
20
+ "9": "LABEL_9",
21
+ "10": "LABEL_10",
22
+ "11": "LABEL_11",
23
+ "12": "LABEL_12",
24
+ "13": "LABEL_13",
25
+ "14": "LABEL_14",
26
+ "15": "LABEL_15",
27
+ "16": "LABEL_16",
28
+ "17": "LABEL_17",
29
+ "18": "LABEL_18",
30
+ "19": "LABEL_19",
31
+ "20": "LABEL_20"
32
+ },
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 3072,
35
+ "label2id": {
36
+ "LABEL_0": 0,
37
+ "LABEL_1": 1,
38
+ "LABEL_10": 10,
39
+ "LABEL_11": 11,
40
+ "LABEL_12": 12,
41
+ "LABEL_13": 13,
42
+ "LABEL_14": 14,
43
+ "LABEL_15": 15,
44
+ "LABEL_16": 16,
45
+ "LABEL_17": 17,
46
+ "LABEL_18": 18,
47
+ "LABEL_19": 19,
48
+ "LABEL_2": 2,
49
+ "LABEL_20": 20,
50
+ "LABEL_3": 3,
51
+ "LABEL_4": 4,
52
+ "LABEL_5": 5,
53
+ "LABEL_6": 6,
54
+ "LABEL_7": 7,
55
+ "LABEL_8": 8,
56
+ "LABEL_9": 9
57
+ },
58
+ "layer_norm_eps": 1e-12,
59
+ "max_position_embeddings": 512,
60
+ "model_type": "bert",
61
+ "num_attention_heads": 12,
62
+ "num_hidden_layers": 12,
63
+ "pad_token_id": 0,
64
+ "position_embedding_type": "absolute",
65
+ "problem_type": "single_label_classification",
66
+ "torch_dtype": "float32",
67
+ "transformers_version": "4.52.4",
68
+ "type_vocab_size": 2,
69
+ "use_cache": true,
70
+ "vocab_size": 64000
71
+ }
checkpoint-17560/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60a221bc674fed7a4b8c4872c457412695d9029dccda1772f5b78c4c1219ec17
3
+ size 540861516
checkpoint-17560/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c12a53b0c92a494c576f3ae33fb041aa9aa9ba6bbe88ba47c28210e33f66ab1
3
+ size 1081844026
checkpoint-17560/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:401c0ac34ebbcafc08f1d7859291911ecc663099fc301347a9cad3fa7cd83bc1
3
+ size 14244
checkpoint-17560/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25f24fd4b5a7cff1e9f96902b44d3f25b2255f44abafa9bf59cb2b9c21fbe3bd
3
+ size 1064
checkpoint-17560/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-17560/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-17560/tokenizer_config.json ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "[رابط]",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": true,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "[بريد]",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": true,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "[مستخدم]",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": true,
65
+ "special": true
66
+ }
67
+ },
68
+ "clean_up_tokenization_spaces": true,
69
+ "cls_token": "[CLS]",
70
+ "do_basic_tokenize": true,
71
+ "do_lower_case": false,
72
+ "extra_special_tokens": {},
73
+ "mask_token": "[MASK]",
74
+ "max_len": 512,
75
+ "max_length": 512,
76
+ "model_max_length": 512,
77
+ "never_split": [
78
+ "[بريد]",
79
+ "[مستخدم]",
80
+ "[رابط]"
81
+ ],
82
+ "pad_to_multiple_of": null,
83
+ "pad_token": "[PAD]",
84
+ "pad_token_type_id": 0,
85
+ "padding_side": "right",
86
+ "sep_token": "[SEP]",
87
+ "stride": 0,
88
+ "strip_accents": null,
89
+ "tokenize_chinese_chars": true,
90
+ "tokenizer_class": "BertTokenizer",
91
+ "truncation_side": "right",
92
+ "truncation_strategy": "longest_first",
93
+ "unk_token": "[UNK]"
94
+ }
checkpoint-17560/trainer_state.json ADDED
@@ -0,0 +1,279 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 17560,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.11389521640091116,
14
+ "grad_norm": 14.930135726928711,
15
+ "learning_rate": 5.683371298405468e-06,
16
+ "loss": 2.8432,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.22779043280182232,
21
+ "grad_norm": 18.998573303222656,
22
+ "learning_rate": 1.1378132118451027e-05,
23
+ "loss": 1.5596,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.3416856492027335,
28
+ "grad_norm": 10.675321578979492,
29
+ "learning_rate": 1.7072892938496583e-05,
30
+ "loss": 0.7698,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.45558086560364464,
35
+ "grad_norm": 28.9031925201416,
36
+ "learning_rate": 1.998833556232835e-05,
37
+ "loss": 0.517,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 0.5694760820045558,
42
+ "grad_norm": 57.30187225341797,
43
+ "learning_rate": 1.9891126119574924e-05,
44
+ "loss": 0.3908,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 0.683371298405467,
49
+ "grad_norm": 2.194150924682617,
50
+ "learning_rate": 1.9696284292584868e-05,
51
+ "loss": 0.319,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 0.7972665148063781,
56
+ "grad_norm": 4.897868633270264,
57
+ "learning_rate": 1.9405733307479062e-05,
58
+ "loss": 0.2745,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 0.9111617312072893,
63
+ "grad_norm": 2.3224313259124756,
64
+ "learning_rate": 1.9022341107207095e-05,
65
+ "loss": 0.2757,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 1.0250569476082005,
70
+ "grad_norm": 1.0110756158828735,
71
+ "learning_rate": 1.854989204292958e-05,
72
+ "loss": 0.2428,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 1.1389521640091116,
77
+ "grad_norm": 0.5717478394508362,
78
+ "learning_rate": 1.799304951980565e-05,
79
+ "loss": 0.1836,
80
+ "step": 5000
81
+ },
82
+ {
83
+ "epoch": 1.2528473804100229,
84
+ "grad_norm": 2.5286736488342285,
85
+ "learning_rate": 1.7357309965898177e-05,
86
+ "loss": 0.1864,
87
+ "step": 5500
88
+ },
89
+ {
90
+ "epoch": 1.366742596810934,
91
+ "grad_norm": 10.785357475280762,
92
+ "learning_rate": 1.6648948578555884e-05,
93
+ "loss": 0.1929,
94
+ "step": 6000
95
+ },
96
+ {
97
+ "epoch": 1.4806378132118452,
98
+ "grad_norm": 76.80316925048828,
99
+ "learning_rate": 1.587495738379394e-05,
100
+ "loss": 0.1762,
101
+ "step": 6500
102
+ },
103
+ {
104
+ "epoch": 1.5945330296127562,
105
+ "grad_norm": 0.777511477470398,
106
+ "learning_rate": 1.5042976220070502e-05,
107
+ "loss": 0.1631,
108
+ "step": 7000
109
+ },
110
+ {
111
+ "epoch": 1.7084282460136673,
112
+ "grad_norm": 8.146851539611816,
113
+ "learning_rate": 1.4161217327697978e-05,
114
+ "loss": 0.1562,
115
+ "step": 7500
116
+ },
117
+ {
118
+ "epoch": 1.8223234624145785,
119
+ "grad_norm": 1.3531783819198608,
120
+ "learning_rate": 1.3238384288244678e-05,
121
+ "loss": 0.1653,
122
+ "step": 8000
123
+ },
124
+ {
125
+ "epoch": 1.9362186788154898,
126
+ "grad_norm": 2.7191245555877686,
127
+ "learning_rate": 1.2283586114052062e-05,
128
+ "loss": 0.1546,
129
+ "step": 8500
130
+ },
131
+ {
132
+ "epoch": 2.050113895216401,
133
+ "grad_norm": 0.11562561243772507,
134
+ "learning_rate": 1.1306247335864585e-05,
135
+ "loss": 0.124,
136
+ "step": 9000
137
+ },
138
+ {
139
+ "epoch": 2.164009111617312,
140
+ "grad_norm": 0.7750993371009827,
141
+ "learning_rate": 1.0316014976070583e-05,
142
+ "loss": 0.097,
143
+ "step": 9500
144
+ },
145
+ {
146
+ "epoch": 2.277904328018223,
147
+ "grad_norm": 0.973026692867279,
148
+ "learning_rate": 9.322663325793849e-06,
149
+ "loss": 0.0993,
150
+ "step": 10000
151
+ },
152
+ {
153
+ "epoch": 2.3917995444191344,
154
+ "grad_norm": 0.6115517020225525,
155
+ "learning_rate": 8.335997465753155e-06,
156
+ "loss": 0.1,
157
+ "step": 10500
158
+ },
159
+ {
160
+ "epoch": 2.5056947608200457,
161
+ "grad_norm": 0.7755500674247742,
162
+ "learning_rate": 7.365756483206719e-06,
163
+ "loss": 0.0878,
164
+ "step": 11000
165
+ },
166
+ {
167
+ "epoch": 2.619589977220957,
168
+ "grad_norm": 5.184209823608398,
169
+ "learning_rate": 6.421517340298689e-06,
170
+ "loss": 0.0925,
171
+ "step": 11500
172
+ },
173
+ {
174
+ "epoch": 2.733485193621868,
175
+ "grad_norm": 0.5563125610351562,
176
+ "learning_rate": 5.512600342694685e-06,
177
+ "loss": 0.1162,
178
+ "step": 12000
179
+ },
180
+ {
181
+ "epoch": 2.847380410022779,
182
+ "grad_norm": 1.4436191320419312,
183
+ "learning_rate": 4.6479771415976616e-06,
184
+ "loss": 0.0824,
185
+ "step": 12500
186
+ },
187
+ {
188
+ "epoch": 2.9612756264236904,
189
+ "grad_norm": 0.0020386124961078167,
190
+ "learning_rate": 3.8361821772289766e-06,
191
+ "loss": 0.0886,
192
+ "step": 13000
193
+ },
194
+ {
195
+ "epoch": 3.075170842824601,
196
+ "grad_norm": 0.896149754524231,
197
+ "learning_rate": 3.0852284378899054e-06,
198
+ "loss": 0.0793,
199
+ "step": 13500
200
+ },
201
+ {
202
+ "epoch": 3.1890660592255125,
203
+ "grad_norm": 0.5485937595367432,
204
+ "learning_rate": 2.4025283661210406e-06,
205
+ "loss": 0.0714,
206
+ "step": 14000
207
+ },
208
+ {
209
+ "epoch": 3.3029612756264237,
210
+ "grad_norm": 1.4541118144989014,
211
+ "learning_rate": 1.7948206926714952e-06,
212
+ "loss": 0.0681,
213
+ "step": 14500
214
+ },
215
+ {
216
+ "epoch": 3.416856492027335,
217
+ "grad_norm": 2.268272876739502,
218
+ "learning_rate": 1.2681039204781863e-06,
219
+ "loss": 0.0706,
220
+ "step": 15000
221
+ },
222
+ {
223
+ "epoch": 3.5307517084282463,
224
+ "grad_norm": 1.2012200355529785,
225
+ "learning_rate": 8.275771152152412e-07,
226
+ "loss": 0.0674,
227
+ "step": 15500
228
+ },
229
+ {
230
+ "epoch": 3.644646924829157,
231
+ "grad_norm": 0.6027458310127258,
232
+ "learning_rate": 4.775885868524232e-07,
233
+ "loss": 0.0705,
234
+ "step": 16000
235
+ },
236
+ {
237
+ "epoch": 3.7585421412300684,
238
+ "grad_norm": 1.907026767730713,
239
+ "learning_rate": 2.2159296877185987e-07,
240
+ "loss": 0.0714,
241
+ "step": 16500
242
+ },
243
+ {
244
+ "epoch": 3.8724373576309796,
245
+ "grad_norm": 0.64386385679245,
246
+ "learning_rate": 6.211711810237497e-08,
247
+ "loss": 0.0762,
248
+ "step": 17000
249
+ },
250
+ {
251
+ "epoch": 3.9863325740318905,
252
+ "grad_norm": 0.9830172061920166,
253
+ "learning_rate": 7.351738591621082e-10,
254
+ "loss": 0.0757,
255
+ "step": 17500
256
+ }
257
+ ],
258
+ "logging_steps": 500,
259
+ "max_steps": 17560,
260
+ "num_input_tokens_seen": 0,
261
+ "num_train_epochs": 4,
262
+ "save_steps": 500,
263
+ "stateful_callbacks": {
264
+ "TrainerControl": {
265
+ "args": {
266
+ "should_epoch_stop": false,
267
+ "should_evaluate": false,
268
+ "should_log": false,
269
+ "should_save": true,
270
+ "should_training_stop": true
271
+ },
272
+ "attributes": {}
273
+ }
274
+ },
275
+ "total_flos": 7.393629300129792e+16,
276
+ "train_batch_size": 16,
277
+ "trial_name": null,
278
+ "trial_params": null
279
+ }
checkpoint-17560/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efbe6b9c4e2f1a677380f96fef8cc482360dcb08a3708e5c8354407fc1ab202e
3
+ size 5304
checkpoint-17560/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2",
14
+ "3": "LABEL_3",
15
+ "4": "LABEL_4",
16
+ "5": "LABEL_5",
17
+ "6": "LABEL_6",
18
+ "7": "LABEL_7",
19
+ "8": "LABEL_8",
20
+ "9": "LABEL_9",
21
+ "10": "LABEL_10",
22
+ "11": "LABEL_11",
23
+ "12": "LABEL_12",
24
+ "13": "LABEL_13",
25
+ "14": "LABEL_14",
26
+ "15": "LABEL_15",
27
+ "16": "LABEL_16",
28
+ "17": "LABEL_17",
29
+ "18": "LABEL_18",
30
+ "19": "LABEL_19",
31
+ "20": "LABEL_20"
32
+ },
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 3072,
35
+ "label2id": {
36
+ "LABEL_0": 0,
37
+ "LABEL_1": 1,
38
+ "LABEL_10": 10,
39
+ "LABEL_11": 11,
40
+ "LABEL_12": 12,
41
+ "LABEL_13": 13,
42
+ "LABEL_14": 14,
43
+ "LABEL_15": 15,
44
+ "LABEL_16": 16,
45
+ "LABEL_17": 17,
46
+ "LABEL_18": 18,
47
+ "LABEL_19": 19,
48
+ "LABEL_2": 2,
49
+ "LABEL_20": 20,
50
+ "LABEL_3": 3,
51
+ "LABEL_4": 4,
52
+ "LABEL_5": 5,
53
+ "LABEL_6": 6,
54
+ "LABEL_7": 7,
55
+ "LABEL_8": 8,
56
+ "LABEL_9": 9
57
+ },
58
+ "layer_norm_eps": 1e-12,
59
+ "max_position_embeddings": 512,
60
+ "model_type": "bert",
61
+ "num_attention_heads": 12,
62
+ "num_hidden_layers": 12,
63
+ "pad_token_id": 0,
64
+ "position_embedding_type": "absolute",
65
+ "problem_type": "single_label_classification",
66
+ "torch_dtype": "float32",
67
+ "transformers_version": "4.52.4",
68
+ "type_vocab_size": 2,
69
+ "use_cache": true,
70
+ "vocab_size": 64000
71
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60a221bc674fed7a4b8c4872c457412695d9029dccda1772f5b78c4c1219ec17
3
+ size 540861516
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 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "[رابط]",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": true,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "[بريد]",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": true,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "[مستخدم]",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": true,
65
+ "special": true
66
+ }
67
+ },
68
+ "clean_up_tokenization_spaces": true,
69
+ "cls_token": "[CLS]",
70
+ "do_basic_tokenize": true,
71
+ "do_lower_case": false,
72
+ "extra_special_tokens": {},
73
+ "mask_token": "[MASK]",
74
+ "max_len": 512,
75
+ "max_length": 512,
76
+ "model_max_length": 512,
77
+ "never_split": [
78
+ "[بريد]",
79
+ "[مستخدم]",
80
+ "[رابط]"
81
+ ],
82
+ "pad_to_multiple_of": null,
83
+ "pad_token": "[PAD]",
84
+ "pad_token_type_id": 0,
85
+ "padding_side": "right",
86
+ "sep_token": "[SEP]",
87
+ "stride": 0,
88
+ "strip_accents": null,
89
+ "tokenize_chinese_chars": true,
90
+ "tokenizer_class": "BertTokenizer",
91
+ "truncation_side": "right",
92
+ "truncation_strategy": "longest_first",
93
+ "unk_token": "[UNK]"
94
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efbe6b9c4e2f1a677380f96fef8cc482360dcb08a3708e5c8354407fc1ab202e
3
+ size 5304
vocab.txt ADDED
The diff for this file is too large to render. See raw diff