Hugging Face's logo

bedourfouad
/
arabic-bert-sentiment

Text Classification
Safetensors
Arabic
bert
arabic
sentiment-analysis
arabert
Model card Files
xet
Community
bedourfouad commited on
Commit
9283afe
·
verified ·
1 Parent(s): 3354aa1

Upload fine-tuned BERT model files

Browse files
Files changed (43) hide show
  1. checkpoint-1359/config.json +45 -0
  2. checkpoint-1359/model.safetensors +3 -0
  3. checkpoint-1359/optimizer.pt +3 -0
  4. checkpoint-1359/rng_state.pth +3 -0
  5. checkpoint-1359/scaler.pt +3 -0
  6. checkpoint-1359/scheduler.pt +3 -0
  7. checkpoint-1359/special_tokens_map.json +37 -0
  8. checkpoint-1359/tokenizer.json +0 -0
  9. checkpoint-1359/tokenizer_config.json +339 -0
  10. checkpoint-1359/trainer_state.json +78 -0
  11. checkpoint-1359/training_args.bin +3 -0
  12. checkpoint-1359/vocab.txt +0 -0
  13. checkpoint-453/config.json +45 -0
  14. checkpoint-453/model.safetensors +3 -0
  15. checkpoint-453/optimizer.pt +3 -0
  16. checkpoint-453/rng_state.pth +3 -0
  17. checkpoint-453/scaler.pt +3 -0
  18. checkpoint-453/scheduler.pt +3 -0
  19. checkpoint-453/special_tokens_map.json +37 -0
  20. checkpoint-453/tokenizer.json +0 -0
  21. checkpoint-453/tokenizer_config.json +339 -0
  22. checkpoint-453/trainer_state.json +44 -0
  23. checkpoint-453/training_args.bin +3 -0
  24. checkpoint-453/vocab.txt +0 -0
  25. checkpoint-906/config.json +45 -0
  26. checkpoint-906/model.safetensors +3 -0
  27. checkpoint-906/optimizer.pt +3 -0
  28. checkpoint-906/rng_state.pth +3 -0
  29. checkpoint-906/scaler.pt +3 -0
  30. checkpoint-906/scheduler.pt +3 -0
  31. checkpoint-906/special_tokens_map.json +37 -0
  32. checkpoint-906/tokenizer.json +0 -0
  33. checkpoint-906/tokenizer_config.json +339 -0
  34. checkpoint-906/trainer_state.json +61 -0
  35. checkpoint-906/training_args.bin +3 -0
  36. checkpoint-906/vocab.txt +0 -0
  37. config.json +45 -0
  38. model.safetensors +3 -0
  39. special_tokens_map.json +37 -0
  40. tokenizer.json +0 -0
  41. tokenizer_config.json +339 -0
  42. training_args.bin +3 -0
  43. vocab.txt +0 -0
checkpoint-1359/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "anger",
12
+ "1": "fear",
13
+ "2": "joy",
14
+ "3": "love",
15
+ "4": "none",
16
+ "5": "sadness",
17
+ "6": "surprise",
18
+ "7": "sympathy"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "anger": 0,
24
+ "fear": 1,
25
+ "joy": 2,
26
+ "love": 3,
27
+ "none": 4,
28
+ "sadness": 5,
29
+ "surprise": 6,
30
+ "sympathy": 7
31
+ },
32
+ "layer_norm_eps": 1e-12,
33
+ "max_position_embeddings": 512,
34
+ "model_type": "bert",
35
+ "num_attention_heads": 12,
36
+ "num_hidden_layers": 12,
37
+ "pad_token_id": 0,
38
+ "position_embedding_type": "absolute",
39
+ "problem_type": "single_label_classification",
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.51.3",
42
+ "type_vocab_size": 2,
43
+ "use_cache": true,
44
+ "vocab_size": 64000
45
+ }
checkpoint-1359/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d655c313a8ba8c5b4e45011b0cd9f355989556fc69a1b5c548bb2c8f08f6120
3
+ size 540821528
checkpoint-1359/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1834704592a8c08ff694fd11a6b605c842fdbcd14ec224a91d4001f327a5f9c7
3
+ size 1081764090
checkpoint-1359/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebbc88effeb82d9015bee138a738d0c77fa8df367ed56ca38312e79fe1f29d88
3
+ size 14244
checkpoint-1359/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60b06d0bf1adaa4a355e95a40b60e224aaae809d4245e022308fdf83746335d1
3
+ size 988
checkpoint-1359/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3973e2bc1f6413fea4dfb2f547b64bad5747225656753aec54497c6e091eb2b0
3
+ size 1064
checkpoint-1359/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-1359/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1359/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-1359/trainer_state.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1359,
3
+ "best_metric": 0.6862909047865221,
4
+ "best_model_checkpoint": "arabic_sentiment_bert_model/checkpoint-1359",
5
+ "epoch": 3.0,
6
+ "eval_steps": 453,
7
+ "global_step": 1359,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.6712158808933002,
15
+ "eval_f1": 0.6606229501166545,
16
+ "eval_loss": 0.9512589573860168,
17
+ "eval_runtime": 1.6456,
18
+ "eval_samples_per_second": 489.796,
19
+ "eval_steps_per_second": 30.992,
20
+ "step": 453
21
+ },
22
+ {
23
+ "epoch": 1.1037527593818985,
24
+ "grad_norm": 15.88227653503418,
25
+ "learning_rate": 1.2700515084621045e-05,
26
+ "loss": 1.1964,
27
+ "step": 500
28
+ },
29
+ {
30
+ "epoch": 2.0,
31
+ "eval_accuracy": 0.6699751861042184,
32
+ "eval_f1": 0.6617161772404511,
33
+ "eval_loss": 0.9566303491592407,
34
+ "eval_runtime": 1.5724,
35
+ "eval_samples_per_second": 512.592,
36
+ "eval_steps_per_second": 32.434,
37
+ "step": 906
38
+ },
39
+ {
40
+ "epoch": 2.207505518763797,
41
+ "grad_norm": 9.495442390441895,
42
+ "learning_rate": 5.342163355408388e-06,
43
+ "loss": 0.7865,
44
+ "step": 1000
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_accuracy": 0.6885856079404467,
49
+ "eval_f1": 0.6862909047865221,
50
+ "eval_loss": 0.9218945503234863,
51
+ "eval_runtime": 2.0222,
52
+ "eval_samples_per_second": 398.573,
53
+ "eval_steps_per_second": 25.22,
54
+ "step": 1359
55
+ }
56
+ ],
57
+ "logging_steps": 500,
58
+ "max_steps": 1359,
59
+ "num_input_tokens_seen": 0,
60
+ "num_train_epochs": 3,
61
+ "save_steps": 453,
62
+ "stateful_callbacks": {
63
+ "TrainerControl": {
64
+ "args": {
65
+ "should_epoch_stop": false,
66
+ "should_evaluate": false,
67
+ "should_log": false,
68
+ "should_save": true,
69
+ "should_training_stop": true
70
+ },
71
+ "attributes": {}
72
+ }
73
+ },
74
+ "total_flos": 1429954060087296.0,
75
+ "train_batch_size": 16,
76
+ "trial_name": null,
77
+ "trial_params": null
78
+ }
checkpoint-1359/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e43f9a16187934f6ea12bd18a267b705bc4e1d8ab229ed4704d545710bc3a62f
3
+ size 5304
checkpoint-1359/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-453/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "anger",
12
+ "1": "fear",
13
+ "2": "joy",
14
+ "3": "love",
15
+ "4": "none",
16
+ "5": "sadness",
17
+ "6": "surprise",
18
+ "7": "sympathy"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "anger": 0,
24
+ "fear": 1,
25
+ "joy": 2,
26
+ "love": 3,
27
+ "none": 4,
28
+ "sadness": 5,
29
+ "surprise": 6,
30
+ "sympathy": 7
31
+ },
32
+ "layer_norm_eps": 1e-12,
33
+ "max_position_embeddings": 512,
34
+ "model_type": "bert",
35
+ "num_attention_heads": 12,
36
+ "num_hidden_layers": 12,
37
+ "pad_token_id": 0,
38
+ "position_embedding_type": "absolute",
39
+ "problem_type": "single_label_classification",
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.51.3",
42
+ "type_vocab_size": 2,
43
+ "use_cache": true,
44
+ "vocab_size": 64000
45
+ }
checkpoint-453/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed94fa64800d12d24ea2d8bcdf129f4ff438cf6ed6debe831daa137791c87732
3
+ size 540821528
checkpoint-453/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31ffbfd49be633757dc9abcff010de871b5bee336608e74a6552ca49b878535b
3
+ size 1081764090
checkpoint-453/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75e17de3a0e80cade03b97ca1a3216e008c34a9e2a558ce7d380912cf848b606
3
+ size 14244
checkpoint-453/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2167d82665d168c7301a205aec8da68c2e445f3b22015ec4cbf54440c6213ff
3
+ size 988
checkpoint-453/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a61a399058ac6c3f1142ad0362771d1337bb1f7f6ac26c55fc4c5602977ff22
3
+ size 1064
checkpoint-453/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-453/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-453/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-453/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 453,
3
+ "best_metric": 0.6606229501166545,
4
+ "best_model_checkpoint": "arabic_sentiment_bert_model/checkpoint-453",
5
+ "epoch": 1.0,
6
+ "eval_steps": 453,
7
+ "global_step": 453,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.6712158808933002,
15
+ "eval_f1": 0.6606229501166545,
16
+ "eval_loss": 0.9512589573860168,
17
+ "eval_runtime": 1.6456,
18
+ "eval_samples_per_second": 489.796,
19
+ "eval_steps_per_second": 30.992,
20
+ "step": 453
21
+ }
22
+ ],
23
+ "logging_steps": 500,
24
+ "max_steps": 1359,
25
+ "num_input_tokens_seen": 0,
26
+ "num_train_epochs": 3,
27
+ "save_steps": 453,
28
+ "stateful_callbacks": {
29
+ "TrainerControl": {
30
+ "args": {
31
+ "should_epoch_stop": false,
32
+ "should_evaluate": false,
33
+ "should_log": false,
34
+ "should_save": true,
35
+ "should_training_stop": false
36
+ },
37
+ "attributes": {}
38
+ }
39
+ },
40
+ "total_flos": 476651353362432.0,
41
+ "train_batch_size": 16,
42
+ "trial_name": null,
43
+ "trial_params": null
44
+ }
checkpoint-453/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e43f9a16187934f6ea12bd18a267b705bc4e1d8ab229ed4704d545710bc3a62f
3
+ size 5304
checkpoint-453/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-906/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "anger",
12
+ "1": "fear",
13
+ "2": "joy",
14
+ "3": "love",
15
+ "4": "none",
16
+ "5": "sadness",
17
+ "6": "surprise",
18
+ "7": "sympathy"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "anger": 0,
24
+ "fear": 1,
25
+ "joy": 2,
26
+ "love": 3,
27
+ "none": 4,
28
+ "sadness": 5,
29
+ "surprise": 6,
30
+ "sympathy": 7
31
+ },
32
+ "layer_norm_eps": 1e-12,
33
+ "max_position_embeddings": 512,
34
+ "model_type": "bert",
35
+ "num_attention_heads": 12,
36
+ "num_hidden_layers": 12,
37
+ "pad_token_id": 0,
38
+ "position_embedding_type": "absolute",
39
+ "problem_type": "single_label_classification",
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.51.3",
42
+ "type_vocab_size": 2,
43
+ "use_cache": true,
44
+ "vocab_size": 64000
45
+ }
checkpoint-906/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:855ef50057d6894fbb1c3d729a099065f75ada33a431d42e210c714a78b8fbe1
3
+ size 540821528
checkpoint-906/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3725141f34c5f0aa0278167cc4f1a867b026ffeddfe9c8b5979ce550c10431a3
3
+ size 1081764090
checkpoint-906/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbd82624dcd6f1ad2f200c540bfed0a303b6d1c1678a2cde05e3d04452b74e6e
3
+ size 14244
checkpoint-906/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3154585566509acec128a8b819cb2a547385e52a0392e640bd353b969ca1e652
3
+ size 988
checkpoint-906/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad4ff3bd674479b93f94173f2a33f309a0d599920bd82b4097c270c0111aa55e
3
+ size 1064
checkpoint-906/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-906/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-906/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-906/trainer_state.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 906,
3
+ "best_metric": 0.6617161772404511,
4
+ "best_model_checkpoint": "arabic_sentiment_bert_model/checkpoint-906",
5
+ "epoch": 2.0,
6
+ "eval_steps": 453,
7
+ "global_step": 906,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.6712158808933002,
15
+ "eval_f1": 0.6606229501166545,
16
+ "eval_loss": 0.9512589573860168,
17
+ "eval_runtime": 1.6456,
18
+ "eval_samples_per_second": 489.796,
19
+ "eval_steps_per_second": 30.992,
20
+ "step": 453
21
+ },
22
+ {
23
+ "epoch": 1.1037527593818985,
24
+ "grad_norm": 15.88227653503418,
25
+ "learning_rate": 1.2700515084621045e-05,
26
+ "loss": 1.1964,
27
+ "step": 500
28
+ },
29
+ {
30
+ "epoch": 2.0,
31
+ "eval_accuracy": 0.6699751861042184,
32
+ "eval_f1": 0.6617161772404511,
33
+ "eval_loss": 0.9566303491592407,
34
+ "eval_runtime": 1.5724,
35
+ "eval_samples_per_second": 512.592,
36
+ "eval_steps_per_second": 32.434,
37
+ "step": 906
38
+ }
39
+ ],
40
+ "logging_steps": 500,
41
+ "max_steps": 1359,
42
+ "num_input_tokens_seen": 0,
43
+ "num_train_epochs": 3,
44
+ "save_steps": 453,
45
+ "stateful_callbacks": {
46
+ "TrainerControl": {
47
+ "args": {
48
+ "should_epoch_stop": false,
49
+ "should_evaluate": false,
50
+ "should_log": false,
51
+ "should_save": true,
52
+ "should_training_stop": false
53
+ },
54
+ "attributes": {}
55
+ }
56
+ },
57
+ "total_flos": 953302706724864.0,
58
+ "train_batch_size": 16,
59
+ "trial_name": null,
60
+ "trial_params": null
61
+ }
checkpoint-906/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e43f9a16187934f6ea12bd18a267b705bc4e1d8ab229ed4704d545710bc3a62f
3
+ size 5304
checkpoint-906/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "anger",
12
+ "1": "fear",
13
+ "2": "joy",
14
+ "3": "love",
15
+ "4": "none",
16
+ "5": "sadness",
17
+ "6": "surprise",
18
+ "7": "sympathy"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "anger": 0,
24
+ "fear": 1,
25
+ "joy": 2,
26
+ "love": 3,
27
+ "none": 4,
28
+ "sadness": 5,
29
+ "surprise": 6,
30
+ "sympathy": 7
31
+ },
32
+ "layer_norm_eps": 1e-12,
33
+ "max_position_embeddings": 512,
34
+ "model_type": "bert",
35
+ "num_attention_heads": 12,
36
+ "num_hidden_layers": 12,
37
+ "pad_token_id": 0,
38
+ "position_embedding_type": "absolute",
39
+ "problem_type": "single_label_classification",
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.51.3",
42
+ "type_vocab_size": 2,
43
+ "use_cache": true,
44
+ "vocab_size": 64000
45
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d655c313a8ba8c5b4e45011b0cd9f355989556fc69a1b5c548bb2c8f08f6120
3
+ size 540821528
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,339 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "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
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e43f9a16187934f6ea12bd18a267b705bc4e1d8ab229ed4704d545710bc3a62f
3
+ size 5304
vocab.txt ADDED
The diff for this file is too large to render. See raw diff