Hugging Face's logo

MuhammadHelmy
/
GATE-AraBert-AuthId-without-ClassWeights

Safetensors
bert
Model card Files
xet
 Community
MuhammadHelmy commited on
Commit
d316657
·
verified ·
1 Parent(s): 03af294

Upload folder using huggingface_hub

Browse files
Files changed (29) hide show
  1. checkpoint-8000/config.json +71 -0
  2. checkpoint-8000/model.safetensors +3 -0
  3. checkpoint-8000/optimizer.pt +3 -0
  4. checkpoint-8000/rng_state.pth +3 -0
  5. checkpoint-8000/scheduler.pt +3 -0
  6. checkpoint-8000/special_tokens_map.json +37 -0
  7. checkpoint-8000/tokenizer.json +0 -0
  8. checkpoint-8000/tokenizer_config.json +94 -0
  9. checkpoint-8000/trainer_state.json +146 -0
  10. checkpoint-8000/training_args.bin +3 -0
  11. checkpoint-8000/vocab.txt +0 -0
  12. checkpoint-8236/config.json +71 -0
  13. checkpoint-8236/model.safetensors +3 -0
  14. checkpoint-8236/optimizer.pt +3 -0
  15. checkpoint-8236/rng_state.pth +3 -0
  16. checkpoint-8236/scheduler.pt +3 -0
  17. checkpoint-8236/special_tokens_map.json +37 -0
  18. checkpoint-8236/tokenizer.json +0 -0
  19. checkpoint-8236/tokenizer_config.json +94 -0
  20. checkpoint-8236/trainer_state.json +146 -0
  21. checkpoint-8236/training_args.bin +3 -0
  22. checkpoint-8236/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-8000/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-8000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60adfd21ace3dcf53ee6eecb962bbe28da7c486b963d1f8e5c5d1ac7ed911703
3
+ size 540861516
checkpoint-8000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90a0ebf9886907d2654d740c2f228e7898346ba4ea7f4f2e4603013b6a73a0e9
3
+ size 1081844026
checkpoint-8000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:432a8b8742e5e08d1c0b560493c4a7c040f6b319822f6796b355bea2592f0699
3
+ size 14244
checkpoint-8000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f27121f3a1af530632c8289f2284794167987c497b16832afb1d9f14c89fb47
3
+ size 1064
checkpoint-8000/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-8000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8000/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-8000/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": 3.885381253035454,
6
+ "eval_steps": 500,
7
+ "global_step": 8000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.24283632831471588,
14
+ "grad_norm": 10.449501037597656,
15
+ "learning_rate": 1.2111650485436894e-05,
16
+ "loss": 2.3813,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.48567265662943176,
21
+ "grad_norm": 10.070737838745117,
22
+ "learning_rate": 1.9972503596025437e-05,
23
+ "loss": 0.8343,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.7285089849441476,
28
+ "grad_norm": 11.16486644744873,
29
+ "learning_rate": 1.9593517288251588e-05,
30
+ "loss": 0.3945,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.9713453132588635,
35
+ "grad_norm": 6.666318416595459,
36
+ "learning_rate": 1.8785270662888512e-05,
37
+ "loss": 0.2607,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 1.2141816415735793,
42
+ "grad_norm": 5.115306377410889,
43
+ "learning_rate": 1.7583928579254136e-05,
44
+ "loss": 0.1708,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 1.4570179698882952,
49
+ "grad_norm": 5.216148853302002,
50
+ "learning_rate": 1.6043244886834486e-05,
51
+ "loss": 0.1308,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 1.6998542982030111,
56
+ "grad_norm": 14.366805076599121,
57
+ "learning_rate": 1.4232157218328932e-05,
58
+ "loss": 0.1099,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 1.942690626517727,
63
+ "grad_norm": 0.03257812187075615,
64
+ "learning_rate": 1.223170238686927e-05,
65
+ "loss": 0.1023,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 2.1855269548324427,
70
+ "grad_norm": 15.981932640075684,
71
+ "learning_rate": 1.0131390407445186e-05,
72
+ "loss": 0.0476,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 2.4283632831471587,
77
+ "grad_norm": 0.24451659619808197,
78
+ "learning_rate": 8.025199386337698e-06,
79
+ "loss": 0.0334,
80
+ "step": 5000
81
+ },
82
+ {
83
+ "epoch": 2.6711996114618746,
84
+ "grad_norm": 0.033566612750291824,
85
+ "learning_rate": 6.007370486559185e-06,
86
+ "loss": 0.0386,
87
+ "step": 5500
88
+ },
89
+ {
90
+ "epoch": 2.9140359397765905,
91
+ "grad_norm": 0.007457327097654343,
92
+ "learning_rate": 4.168191122864228e-06,
93
+ "loss": 0.0272,
94
+ "step": 6000
95
+ },
96
+ {
97
+ "epoch": 3.1568722680913064,
98
+ "grad_norm": 0.01632310263812542,
99
+ "learning_rate": 2.5899550665613025e-06,
100
+ "loss": 0.0202,
101
+ "step": 6500
102
+ },
103
+ {
104
+ "epoch": 3.3997085964060223,
105
+ "grad_norm": 0.011274750344455242,
106
+ "learning_rate": 1.3432802245560407e-06,
107
+ "loss": 0.0096,
108
+ "step": 7000
109
+ },
110
+ {
111
+ "epoch": 3.642544924720738,
112
+ "grad_norm": 0.008845547214150429,
113
+ "learning_rate": 4.83948852983539e-07,
114
+ "loss": 0.0132,
115
+ "step": 7500
116
+ },
117
+ {
118
+ "epoch": 3.885381253035454,
119
+ "grad_norm": 0.1987830251455307,
120
+ "learning_rate": 5.041158953924652e-08,
121
+ "loss": 0.0077,
122
+ "step": 8000
123
+ }
124
+ ],
125
+ "logging_steps": 500,
126
+ "max_steps": 8236,
127
+ "num_input_tokens_seen": 0,
128
+ "num_train_epochs": 4,
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": 3.368159196159283e+16,
143
+ "train_batch_size": 16,
144
+ "trial_name": null,
145
+ "trial_params": null
146
+ }
checkpoint-8000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42612ae0c6dc72f9c292e11fa5368665b2788301c0b1dd80c0fd89dda69383a9
3
+ size 5304
checkpoint-8000/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8236/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-8236/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0b5f6ed763859554592b70bc4d1c6c5ba9248497c4ca0254899c8e7bf51c585
3
+ size 540861516
checkpoint-8236/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f24d6dcd5348efc3d470ae8e53dada664c4e45bc20bfeafb4cd22c75c8015d41
3
+ size 1081844026
checkpoint-8236/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb0c5e638441ae984e99c919213ef4ba573a47a3f84a4a21323fc6a495a7b0e0
3
+ size 14244
checkpoint-8236/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c49c4c3f9280587c8ffc7eba095e0030369b0c09f7ff72035d62a66e48c3f2d2
3
+ size 1064
checkpoint-8236/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-8236/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8236/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-8236/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": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 8236,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.24283632831471588,
14
+ "grad_norm": 10.449501037597656,
15
+ "learning_rate": 1.2111650485436894e-05,
16
+ "loss": 2.3813,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.48567265662943176,
21
+ "grad_norm": 10.070737838745117,
22
+ "learning_rate": 1.9972503596025437e-05,
23
+ "loss": 0.8343,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.7285089849441476,
28
+ "grad_norm": 11.16486644744873,
29
+ "learning_rate": 1.9593517288251588e-05,
30
+ "loss": 0.3945,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.9713453132588635,
35
+ "grad_norm": 6.666318416595459,
36
+ "learning_rate": 1.8785270662888512e-05,
37
+ "loss": 0.2607,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 1.2141816415735793,
42
+ "grad_norm": 5.115306377410889,
43
+ "learning_rate": 1.7583928579254136e-05,
44
+ "loss": 0.1708,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 1.4570179698882952,
49
+ "grad_norm": 5.216148853302002,
50
+ "learning_rate": 1.6043244886834486e-05,
51
+ "loss": 0.1308,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 1.6998542982030111,
56
+ "grad_norm": 14.366805076599121,
57
+ "learning_rate": 1.4232157218328932e-05,
58
+ "loss": 0.1099,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 1.942690626517727,
63
+ "grad_norm": 0.03257812187075615,
64
+ "learning_rate": 1.223170238686927e-05,
65
+ "loss": 0.1023,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 2.1855269548324427,
70
+ "grad_norm": 15.981932640075684,
71
+ "learning_rate": 1.0131390407445186e-05,
72
+ "loss": 0.0476,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 2.4283632831471587,
77
+ "grad_norm": 0.24451659619808197,
78
+ "learning_rate": 8.025199386337698e-06,
79
+ "loss": 0.0334,
80
+ "step": 5000
81
+ },
82
+ {
83
+ "epoch": 2.6711996114618746,
84
+ "grad_norm": 0.033566612750291824,
85
+ "learning_rate": 6.007370486559185e-06,
86
+ "loss": 0.0386,
87
+ "step": 5500
88
+ },
89
+ {
90
+ "epoch": 2.9140359397765905,
91
+ "grad_norm": 0.007457327097654343,
92
+ "learning_rate": 4.168191122864228e-06,
93
+ "loss": 0.0272,
94
+ "step": 6000
95
+ },
96
+ {
97
+ "epoch": 3.1568722680913064,
98
+ "grad_norm": 0.01632310263812542,
99
+ "learning_rate": 2.5899550665613025e-06,
100
+ "loss": 0.0202,
101
+ "step": 6500
102
+ },
103
+ {
104
+ "epoch": 3.3997085964060223,
105
+ "grad_norm": 0.011274750344455242,
106
+ "learning_rate": 1.3432802245560407e-06,
107
+ "loss": 0.0096,
108
+ "step": 7000
109
+ },
110
+ {
111
+ "epoch": 3.642544924720738,
112
+ "grad_norm": 0.008845547214150429,
113
+ "learning_rate": 4.83948852983539e-07,
114
+ "loss": 0.0132,
115
+ "step": 7500
116
+ },
117
+ {
118
+ "epoch": 3.885381253035454,
119
+ "grad_norm": 0.1987830251455307,
120
+ "learning_rate": 5.041158953924652e-08,
121
+ "loss": 0.0077,
122
+ "step": 8000
123
+ }
124
+ ],
125
+ "logging_steps": 500,
126
+ "max_steps": 8236,
127
+ "num_input_tokens_seen": 0,
128
+ "num_train_epochs": 4,
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": true
138
+ },
139
+ "attributes": {}
140
+ }
141
+ },
142
+ "total_flos": 3.467447932454093e+16,
143
+ "train_batch_size": 16,
144
+ "trial_name": null,
145
+ "trial_params": null
146
+ }
checkpoint-8236/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42612ae0c6dc72f9c292e11fa5368665b2788301c0b1dd80c0fd89dda69383a9
3
+ size 5304
checkpoint-8236/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:f0b5f6ed763859554592b70bc4d1c6c5ba9248497c4ca0254899c8e7bf51c585
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 sha256:42612ae0c6dc72f9c292e11fa5368665b2788301c0b1dd80c0fd89dda69383a9
3
+ size 5304
vocab.txt ADDED
The diff for this file is too large to render. See raw diff