Hugging Face's logo

eslamxm
/
arabert2arabert-finetuned-ar-xlsum

Summarization
Transformers
PyTorch
TensorBoard
encoder-decoder
text2text-generation
ar
arabert
Abstractive Summarization
generated_from_trainer
Inference Endpoints
Model card Files Metrics Community
1
eslamxm commited on
Commit
85defaa
•
1 Parent(s): 0c8d1fd

Training in progress, epoch 1

Browse files
Files changed (10) hide show
  1. .gitignore +1 -0
  2. config.json +182 -0
  3. pytorch_model.bin +3 -0
  4. runs/Jun06_22-30-51_da50da1c4261/1654554672.9737406/events.out.tfevents.1654554672.da50da1c4261.81.1 +3 -0
  5. runs/Jun06_22-30-51_da50da1c4261/events.out.tfevents.1654554672.da50da1c4261.81.0 +3 -0
  6. special_tokens_map.json +1 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +1 -0
  9. training_args.bin +3 -0
  10. vocab.txt +0 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,182 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "UBC-NLP/ARBERT",
7
+ "add_cross_attention": true,
8
+ "architectures": [
9
+ "BertForMaskedLM"
10
+ ],
11
+ "attention_probs_dropout_prob": 0.1,
12
+ "bad_words_ids": null,
13
+ "bos_token_id": null,
14
+ "chunk_size_feed_forward": 0,
15
+ "classifier_dropout": null,
16
+ "cross_attention_hidden_size": null,
17
+ "decoder_start_token_id": null,
18
+ "directionality": "bidi",
19
+ "diversity_penalty": 0.0,
20
+ "do_sample": false,
21
+ "early_stopping": false,
22
+ "encoder_no_repeat_ngram_size": 0,
23
+ "eos_token_id": null,
24
+ "exponential_decay_length_penalty": null,
25
+ "finetuning_task": null,
26
+ "forced_bos_token_id": null,
27
+ "forced_eos_token_id": null,
28
+ "gradient_checkpointing": false,
29
+ "hidden_act": "gelu",
30
+ "hidden_dropout_prob": 0.1,
31
+ "hidden_size": 768,
32
+ "id2label": {
33
+ "0": "LABEL_0",
34
+ "1": "LABEL_1"
35
+ },
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 3072,
38
+ "is_decoder": true,
39
+ "is_encoder_decoder": false,
40
+ "label2id": {
41
+ "LABEL_0": 0,
42
+ "LABEL_1": 1
43
+ },
44
+ "layer_norm_eps": 1e-12,
45
+ "length_penalty": 1.0,
46
+ "max_length": 20,
47
+ "max_position_embeddings": 512,
48
+ "min_length": 0,
49
+ "model_type": "bert",
50
+ "no_repeat_ngram_size": 0,
51
+ "num_attention_heads": 12,
52
+ "num_beam_groups": 1,
53
+ "num_beams": 1,
54
+ "num_hidden_layers": 12,
55
+ "num_return_sequences": 1,
56
+ "output_attentions": false,
57
+ "output_hidden_states": false,
58
+ "output_scores": false,
59
+ "pad_token_id": 0,
60
+ "pooler_fc_size": 768,
61
+ "pooler_num_attention_heads": 12,
62
+ "pooler_num_fc_layers": 3,
63
+ "pooler_size_per_head": 128,
64
+ "pooler_type": "first_token_transform",
65
+ "position_embedding_type": "absolute",
66
+ "prefix": null,
67
+ "problem_type": null,
68
+ "pruned_heads": {},
69
+ "remove_invalid_values": false,
70
+ "repetition_penalty": 1.0,
71
+ "return_dict": true,
72
+ "return_dict_in_generate": false,
73
+ "sep_token_id": null,
74
+ "task_specific_params": null,
75
+ "temperature": 1.0,
76
+ "tie_encoder_decoder": false,
77
+ "tie_word_embeddings": true,
78
+ "tokenizer_class": null,
79
+ "top_k": 50,
80
+ "top_p": 1.0,
81
+ "torch_dtype": null,
82
+ "torchscript": false,
83
+ "transformers_version": "4.19.2",
84
+ "type_vocab_size": 2,
85
+ "typical_p": 1.0,
86
+ "use_bfloat16": false,
87
+ "use_cache": true,
88
+ "vocab_size": 100000
89
+ },
90
+ "decoder_start_token_id": 2,
91
+ "encoder": {
92
+ "_name_or_path": "UBC-NLP/ARBERT",
93
+ "add_cross_attention": false,
94
+ "architectures": [
95
+ "BertForMaskedLM"
96
+ ],
97
+ "attention_probs_dropout_prob": 0.1,
98
+ "bad_words_ids": null,
99
+ "bos_token_id": null,
100
+ "chunk_size_feed_forward": 0,
101
+ "classifier_dropout": null,
102
+ "cross_attention_hidden_size": null,
103
+ "decoder_start_token_id": null,
104
+ "directionality": "bidi",
105
+ "diversity_penalty": 0.0,
106
+ "do_sample": false,
107
+ "early_stopping": false,
108
+ "encoder_no_repeat_ngram_size": 0,
109
+ "eos_token_id": null,
110
+ "exponential_decay_length_penalty": null,
111
+ "finetuning_task": null,
112
+ "forced_bos_token_id": null,
113
+ "forced_eos_token_id": null,
114
+ "gradient_checkpointing": false,
115
+ "hidden_act": "gelu",
116
+ "hidden_dropout_prob": 0.1,
117
+ "hidden_size": 768,
118
+ "id2label": {
119
+ "0": "LABEL_0",
120
+ "1": "LABEL_1"
121
+ },
122
+ "initializer_range": 0.02,
123
+ "intermediate_size": 3072,
124
+ "is_decoder": false,
125
+ "is_encoder_decoder": false,
126
+ "label2id": {
127
+ "LABEL_0": 0,
128
+ "LABEL_1": 1
129
+ },
130
+ "layer_norm_eps": 1e-12,
131
+ "length_penalty": 1.0,
132
+ "max_length": 20,
133
+ "max_position_embeddings": 512,
134
+ "min_length": 0,
135
+ "model_type": "bert",
136
+ "no_repeat_ngram_size": 0,
137
+ "num_attention_heads": 12,
138
+ "num_beam_groups": 1,
139
+ "num_beams": 1,
140
+ "num_hidden_layers": 12,
141
+ "num_return_sequences": 1,
142
+ "output_attentions": false,
143
+ "output_hidden_states": false,
144
+ "output_scores": false,
145
+ "pad_token_id": 0,
146
+ "pooler_fc_size": 768,
147
+ "pooler_num_attention_heads": 12,
148
+ "pooler_num_fc_layers": 3,
149
+ "pooler_size_per_head": 128,
150
+ "pooler_type": "first_token_transform",
151
+ "position_embedding_type": "absolute",
152
+ "prefix": null,
153
+ "problem_type": null,
154
+ "pruned_heads": {},
155
+ "remove_invalid_values": false,
156
+ "repetition_penalty": 1.0,
157
+ "return_dict": true,
158
+ "return_dict_in_generate": false,
159
+ "sep_token_id": null,
160
+ "task_specific_params": null,
161
+ "temperature": 1.0,
162
+ "tie_encoder_decoder": false,
163
+ "tie_word_embeddings": true,
164
+ "tokenizer_class": null,
165
+ "top_k": 50,
166
+ "top_p": 1.0,
167
+ "torch_dtype": null,
168
+ "torchscript": false,
169
+ "transformers_version": "4.19.2",
170
+ "type_vocab_size": 2,
171
+ "typical_p": 1.0,
172
+ "use_bfloat16": false,
173
+ "use_cache": true,
174
+ "vocab_size": 100000
175
+ },
176
+ "is_encoder_decoder": true,
177
+ "model_type": "encoder-decoder",
178
+ "pad_token_id": 0,
179
+ "torch_dtype": "float32",
180
+ "transformers_version": null,
181
+ "vocab_size": 100000
182
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a31b99376f64f7948ef7e31186c7a0ec3b10033af82ab34ea4089307b49e0ed
3
+ size 1416791915
runs/Jun06_22-30-51_da50da1c4261/1654554672.9737406/events.out.tfevents.1654554672.da50da1c4261.81.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:252516c7861e1ce2a47e2ea6e456712711e9f9fe3afcf121a1f5a16ba3799f90
3
+ size 5512
runs/Jun06_22-30-51_da50da1c4261/events.out.tfevents.1654554672.da50da1c4261.81.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e29434df16eb4b7aef99bdd3163167b3a182a80842cc70b81ebf334d5242974
3
+ size 10843
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "do_basic_tokenize": true, "never_split": null, "special_tokens_map_file": null, "name_or_path": "UBC-NLP/ARBERT", "tokenizer_class": "BertTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88d5881d633e47a299e6c295931922639479881074cbd92ffae5a2dc57942f4b
3
+ size 3439
vocab.txt ADDED
The diff for this file is too large to render. See raw diff