mohamedashraf11 commited on
Commit
19f99e3
·
verified ·
1 Parent(s): e88972e

Training in progress, step 500

Browse files
config.json CHANGED
@@ -1,24 +1,25 @@
1
  {
2
- "_name_or_path": "distilbert-base-uncased",
3
- "activation": "gelu",
4
  "architectures": [
5
- "DistilBertForQuestionAnswering"
6
  ],
7
- "attention_dropout": 0.1,
8
- "dim": 768,
9
- "dropout": 0.1,
10
- "hidden_dim": 3072,
 
11
  "initializer_range": 0.02,
 
 
12
  "max_position_embeddings": 512,
13
- "model_type": "distilbert",
14
- "n_heads": 12,
15
- "n_layers": 6,
16
  "pad_token_id": 0,
17
- "qa_dropout": 0.1,
18
- "seq_classif_dropout": 0.2,
19
- "sinusoidal_pos_embds": false,
20
- "tie_weights_": true,
21
  "torch_dtype": "float32",
22
- "transformers_version": "4.37.0",
23
- "vocab_size": 30522
 
 
24
  }
 
1
  {
2
+ "_name_or_path": "aubmindlab/bert-base-arabertv02",
 
3
  "architectures": [
4
+ "BertForQuestionAnswering"
5
  ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
  "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-12,
14
  "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
  "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
 
 
 
20
  "torch_dtype": "float32",
21
+ "transformers_version": "4.35.2",
22
+ "type_vocab_size": 2,
23
+ "use_cache": true,
24
+ "vocab_size": 64000
25
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:121a8c103edf85706940801df82af963818064e3aad1d0c825a3a34bac239630
3
- size 265470032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1774d59a3aaa9b9bac4d9c3b3620e3b502fb78c974498ae2cee88d8462d0bb91
3
+ size 538440512
runs/Feb01_12-22-43_c2819caf894e/events.out.tfevents.1706790164.c2819caf894e.3019.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:808dbe5fce22f811cf00d2e74bc0f95fc245371b18b52e64a4853413de4c3d51
3
+ size 5358
runs/Feb01_12-22-43_c2819caf894e/events.out.tfevents.1706790796.c2819caf894e.3019.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7c2f787b19d8a338d07ea108e03ed6b23946fbd8f6d8b6e46e78ff452957b18
3
+ size 359
runs/Feb01_12-48-22_c2819caf894e/events.out.tfevents.1706791711.c2819caf894e.3019.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e3366bc12356b25b2e86ad0bb58c1e77df5ff345a072740567d57b30bfaa80e
3
+ size 5162
special_tokens_map.json CHANGED
@@ -1,7 +1,37 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
 
1
  {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
  }
tokenizer_config.json CHANGED
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": true
10
  },
11
- "100": {
12
  "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": true
18
  },
19
- "101": {
20
  "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "102": {
28
  "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
@@ -32,24 +32,55 @@
32
  "single_word": false,
33
  "special": true
34
  },
35
- "103": {
36
  "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
  }
43
  },
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
- "do_lower_case": true,
 
47
  "mask_token": "[MASK]",
 
48
  "model_max_length": 512,
 
 
 
 
 
49
  "pad_token": "[PAD]",
50
  "sep_token": "[SEP]",
51
  "strip_accents": null,
52
  "tokenize_chinese_chars": true,
53
- "tokenizer_class": "DistilBertTokenizer",
54
  "unk_token": "[UNK]"
55
  }
 
8
  "single_word": false,
9
  "special": true
10
  },
11
+ "1": {
12
  "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "2": {
20
  "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "3": {
28
  "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": 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
  "mask_token": "[MASK]",
73
+ "max_len": 512,
74
  "model_max_length": 512,
75
+ "never_split": [
76
+ "[بريد]",
77
+ "[مستخدم]",
78
+ "[رابط]"
79
+ ],
80
  "pad_token": "[PAD]",
81
  "sep_token": "[SEP]",
82
  "strip_accents": null,
83
  "tokenize_chinese_chars": true,
84
+ "tokenizer_class": "BertTokenizer",
85
  "unk_token": "[UNK]"
86
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2690228cf76d122602fc04084582f5017ddacfd4ebe6f8f787e1bd2a95d81fde
3
- size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9dc1d79bb401a30f3bcd4c13963a24adb2f4447d29a0f58039757e3f16dd0b8
3
+ size 4600
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff