Training in progress, epoch 1
Browse files- config.json +117 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "CAMeL-Lab/bert-base-arabic-camelbert-mix",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "Arts and Media",
|
| 14 |
+
"1": "Business and Money",
|
| 15 |
+
"2": "Cars and Driving",
|
| 16 |
+
"3": "Culture and Traditions",
|
| 17 |
+
"4": "Daily Life",
|
| 18 |
+
"5": "Days and Dates",
|
| 19 |
+
"6": "Descriptions",
|
| 20 |
+
"7": "Directions",
|
| 21 |
+
"8": "Economy and Finance",
|
| 22 |
+
"9": "Education and Training",
|
| 23 |
+
"10": "Emotions",
|
| 24 |
+
"11": "Entertainment",
|
| 25 |
+
"12": "Environment and Nature",
|
| 26 |
+
"13": "Events and Celebrations",
|
| 27 |
+
"14": "Family and Relationships",
|
| 28 |
+
"15": "Fitness and Exercise",
|
| 29 |
+
"16": "Food and Dining",
|
| 30 |
+
"17": "Greetings",
|
| 31 |
+
"18": "Health",
|
| 32 |
+
"19": "Hobbies and Interests",
|
| 33 |
+
"20": "Home and Living",
|
| 34 |
+
"21": "Instructions and Guidelines",
|
| 35 |
+
"22": "Law and Justice",
|
| 36 |
+
"23": "Mental Health",
|
| 37 |
+
"24": "Opinions",
|
| 38 |
+
"25": "Planning and Decisions",
|
| 39 |
+
"26": "Questions",
|
| 40 |
+
"27": "Real Estate and Housing",
|
| 41 |
+
"28": "Religion and Spirituality",
|
| 42 |
+
"29": "Responses",
|
| 43 |
+
"30": "Saudi Cities and Regions",
|
| 44 |
+
"31": "Shopping",
|
| 45 |
+
"32": "Social Media",
|
| 46 |
+
"33": "Sports",
|
| 47 |
+
"34": "Study and Education",
|
| 48 |
+
"35": "Technology",
|
| 49 |
+
"36": "Time",
|
| 50 |
+
"37": "Tourism",
|
| 51 |
+
"38": "Transport",
|
| 52 |
+
"39": "Travel",
|
| 53 |
+
"40": "Weather",
|
| 54 |
+
"41": "Wishes and Dreams",
|
| 55 |
+
"42": "Work"
|
| 56 |
+
},
|
| 57 |
+
"initializer_range": 0.02,
|
| 58 |
+
"intermediate_size": 3072,
|
| 59 |
+
"label2id": {
|
| 60 |
+
"Arts and Media": 0,
|
| 61 |
+
"Business and Money": 1,
|
| 62 |
+
"Cars and Driving": 2,
|
| 63 |
+
"Culture and Traditions": 3,
|
| 64 |
+
"Daily Life": 4,
|
| 65 |
+
"Days and Dates": 5,
|
| 66 |
+
"Descriptions": 6,
|
| 67 |
+
"Directions": 7,
|
| 68 |
+
"Economy and Finance": 8,
|
| 69 |
+
"Education and Training": 9,
|
| 70 |
+
"Emotions": 10,
|
| 71 |
+
"Entertainment": 11,
|
| 72 |
+
"Environment and Nature": 12,
|
| 73 |
+
"Events and Celebrations": 13,
|
| 74 |
+
"Family and Relationships": 14,
|
| 75 |
+
"Fitness and Exercise": 15,
|
| 76 |
+
"Food and Dining": 16,
|
| 77 |
+
"Greetings": 17,
|
| 78 |
+
"Health": 18,
|
| 79 |
+
"Hobbies and Interests": 19,
|
| 80 |
+
"Home and Living": 20,
|
| 81 |
+
"Instructions and Guidelines": 21,
|
| 82 |
+
"Law and Justice": 22,
|
| 83 |
+
"Mental Health": 23,
|
| 84 |
+
"Opinions": 24,
|
| 85 |
+
"Planning and Decisions": 25,
|
| 86 |
+
"Questions": 26,
|
| 87 |
+
"Real Estate and Housing": 27,
|
| 88 |
+
"Religion and Spirituality": 28,
|
| 89 |
+
"Responses": 29,
|
| 90 |
+
"Saudi Cities and Regions": 30,
|
| 91 |
+
"Shopping": 31,
|
| 92 |
+
"Social Media": 32,
|
| 93 |
+
"Sports": 33,
|
| 94 |
+
"Study and Education": 34,
|
| 95 |
+
"Technology": 35,
|
| 96 |
+
"Time": 36,
|
| 97 |
+
"Tourism": 37,
|
| 98 |
+
"Transport": 38,
|
| 99 |
+
"Travel": 39,
|
| 100 |
+
"Weather": 40,
|
| 101 |
+
"Wishes and Dreams": 41,
|
| 102 |
+
"Work": 42
|
| 103 |
+
},
|
| 104 |
+
"layer_norm_eps": 1e-12,
|
| 105 |
+
"max_position_embeddings": 512,
|
| 106 |
+
"model_type": "bert",
|
| 107 |
+
"num_attention_heads": 12,
|
| 108 |
+
"num_hidden_layers": 12,
|
| 109 |
+
"pad_token_id": 0,
|
| 110 |
+
"position_embedding_type": "absolute",
|
| 111 |
+
"problem_type": "single_label_classification",
|
| 112 |
+
"torch_dtype": "float32",
|
| 113 |
+
"transformers_version": "4.42.4",
|
| 114 |
+
"type_vocab_size": 2,
|
| 115 |
+
"use_cache": true,
|
| 116 |
+
"vocab_size": 30000
|
| 117 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99cfae17f7be93c3587fc3caacb2287757cc3a1172237b927b6fecf9de7743c2
|
| 3 |
+
size 436481172
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"full_tokenizer_file": null,
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 51 |
+
"never_split": null,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"strip_accents": null,
|
| 55 |
+
"tokenize_chinese_chars": true,
|
| 56 |
+
"tokenizer_class": "BertTokenizer",
|
| 57 |
+
"unk_token": "[UNK]"
|
| 58 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d09c70c59801cf0c44a162defd6e3ceb7d9c187111f48347baf7662689539f49
|
| 3 |
+
size 5585
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|