Hugging Face's logo

eslamxm
/
mbert2mbert-finetuned-ar-xlsum

Summarization
Transformers
PyTorch
TensorBoard
encoder-decoder
text2text-generation
ar
mbert
Abstractive Summarization
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
eslamxm commited on
Commit
3cf4291
•
1 Parent(s): 5dbc2f6

Training in progress, epoch 1

Browse files
Files changed (12) hide show
  1. .gitignore +1 -0
  2. config.json +180 -0
  3. pytorch_model.bin +3 -0
  4. runs/Jun07_13-32-06_06e3099bd570/1654608756.2897656/events.out.tfevents.1654608756.06e3099bd570.72.1 +3 -0
  5. runs/Jun07_13-32-06_06e3099bd570/events.out.tfevents.1654608756.06e3099bd570.72.0 +3 -0
  6. runs/Jun07_15-34-42_06e3099bd570/1654616107.6423104/events.out.tfevents.1654616107.06e3099bd570.72.3 +3 -0
  7. runs/Jun07_15-34-42_06e3099bd570/events.out.tfevents.1654616107.06e3099bd570.72.2 +3 -0
  8. special_tokens_map.json +1 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +1 -0
  11. training_args.bin +3 -0
  12. vocab.txt +0 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,180 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "bert-base-multilingual-cased",
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
+ "hidden_act": "gelu",
29
+ "hidden_dropout_prob": 0.1,
30
+ "hidden_size": 768,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1"
34
+ },
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": 3072,
37
+ "is_decoder": true,
38
+ "is_encoder_decoder": false,
39
+ "label2id": {
40
+ "LABEL_0": 0,
41
+ "LABEL_1": 1
42
+ },
43
+ "layer_norm_eps": 1e-12,
44
+ "length_penalty": 1.0,
45
+ "max_length": 20,
46
+ "max_position_embeddings": 512,
47
+ "min_length": 0,
48
+ "model_type": "bert",
49
+ "no_repeat_ngram_size": 0,
50
+ "num_attention_heads": 12,
51
+ "num_beam_groups": 1,
52
+ "num_beams": 1,
53
+ "num_hidden_layers": 12,
54
+ "num_return_sequences": 1,
55
+ "output_attentions": false,
56
+ "output_hidden_states": false,
57
+ "output_scores": false,
58
+ "pad_token_id": 0,
59
+ "pooler_fc_size": 768,
60
+ "pooler_num_attention_heads": 12,
61
+ "pooler_num_fc_layers": 3,
62
+ "pooler_size_per_head": 128,
63
+ "pooler_type": "first_token_transform",
64
+ "position_embedding_type": "absolute",
65
+ "prefix": null,
66
+ "problem_type": null,
67
+ "pruned_heads": {},
68
+ "remove_invalid_values": false,
69
+ "repetition_penalty": 1.0,
70
+ "return_dict": true,
71
+ "return_dict_in_generate": false,
72
+ "sep_token_id": null,
73
+ "task_specific_params": null,
74
+ "temperature": 1.0,
75
+ "tie_encoder_decoder": false,
76
+ "tie_word_embeddings": true,
77
+ "tokenizer_class": null,
78
+ "top_k": 50,
79
+ "top_p": 1.0,
80
+ "torch_dtype": null,
81
+ "torchscript": false,
82
+ "transformers_version": "4.19.2",
83
+ "type_vocab_size": 2,
84
+ "typical_p": 1.0,
85
+ "use_bfloat16": false,
86
+ "use_cache": true,
87
+ "vocab_size": 119547
88
+ },
89
+ "decoder_start_token_id": 101,
90
+ "encoder": {
91
+ "_name_or_path": "bert-base-multilingual-cased",
92
+ "add_cross_attention": false,
93
+ "architectures": [
94
+ "BertForMaskedLM"
95
+ ],
96
+ "attention_probs_dropout_prob": 0.1,
97
+ "bad_words_ids": null,
98
+ "bos_token_id": null,
99
+ "chunk_size_feed_forward": 0,
100
+ "classifier_dropout": null,
101
+ "cross_attention_hidden_size": null,
102
+ "decoder_start_token_id": null,
103
+ "directionality": "bidi",
104
+ "diversity_penalty": 0.0,
105
+ "do_sample": false,
106
+ "early_stopping": false,
107
+ "encoder_no_repeat_ngram_size": 0,
108
+ "eos_token_id": null,
109
+ "exponential_decay_length_penalty": null,
110
+ "finetuning_task": null,
111
+ "forced_bos_token_id": null,
112
+ "forced_eos_token_id": null,
113
+ "hidden_act": "gelu",
114
+ "hidden_dropout_prob": 0.1,
115
+ "hidden_size": 768,
116
+ "id2label": {
117
+ "0": "LABEL_0",
118
+ "1": "LABEL_1"
119
+ },
120
+ "initializer_range": 0.02,
121
+ "intermediate_size": 3072,
122
+ "is_decoder": false,
123
+ "is_encoder_decoder": false,
124
+ "label2id": {
125
+ "LABEL_0": 0,
126
+ "LABEL_1": 1
127
+ },
128
+ "layer_norm_eps": 1e-12,
129
+ "length_penalty": 1.0,
130
+ "max_length": 20,
131
+ "max_position_embeddings": 512,
132
+ "min_length": 0,
133
+ "model_type": "bert",
134
+ "no_repeat_ngram_size": 0,
135
+ "num_attention_heads": 12,
136
+ "num_beam_groups": 1,
137
+ "num_beams": 1,
138
+ "num_hidden_layers": 12,
139
+ "num_return_sequences": 1,
140
+ "output_attentions": false,
141
+ "output_hidden_states": false,
142
+ "output_scores": false,
143
+ "pad_token_id": 0,
144
+ "pooler_fc_size": 768,
145
+ "pooler_num_attention_heads": 12,
146
+ "pooler_num_fc_layers": 3,
147
+ "pooler_size_per_head": 128,
148
+ "pooler_type": "first_token_transform",
149
+ "position_embedding_type": "absolute",
150
+ "prefix": null,
151
+ "problem_type": null,
152
+ "pruned_heads": {},
153
+ "remove_invalid_values": false,
154
+ "repetition_penalty": 1.0,
155
+ "return_dict": true,
156
+ "return_dict_in_generate": false,
157
+ "sep_token_id": null,
158
+ "task_specific_params": null,
159
+ "temperature": 1.0,
160
+ "tie_encoder_decoder": false,
161
+ "tie_word_embeddings": true,
162
+ "tokenizer_class": null,
163
+ "top_k": 50,
164
+ "top_p": 1.0,
165
+ "torch_dtype": null,
166
+ "torchscript": false,
167
+ "transformers_version": "4.19.2",
168
+ "type_vocab_size": 2,
169
+ "typical_p": 1.0,
170
+ "use_bfloat16": false,
171
+ "use_cache": true,
172
+ "vocab_size": 119547
173
+ },
174
+ "is_encoder_decoder": true,
175
+ "model_type": "encoder-decoder",
176
+ "pad_token_id": 0,
177
+ "torch_dtype": "float32",
178
+ "transformers_version": null,
179
+ "vocab_size": 119547
180
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99b0a25d83814ad460fa652a51c5175f4286db53995f3c704cb954370056fd11
3
+ size 1536966827
runs/Jun07_13-32-06_06e3099bd570/1654608756.2897656/events.out.tfevents.1654608756.06e3099bd570.72.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1902ddef498e9a889e78d21c1477aae9fc8f1ba0106c7f70ca75e8bd63cab5bf
3
+ size 5495
runs/Jun07_13-32-06_06e3099bd570/events.out.tfevents.1654608756.06e3099bd570.72.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:825209bd25abaccce877cbabb5c3b1ed73d9375020997c01694626ec3b248a49
3
+ size 10781
runs/Jun07_15-34-42_06e3099bd570/1654616107.6423104/events.out.tfevents.1654616107.06e3099bd570.72.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2c1f9dc8bf7ab9d560b609e7f204a052a3e6bb129bd61e2cc0a9c7fb85363c0
3
+ size 5492
runs/Jun07_15-34-42_06e3099bd570/events.out.tfevents.1654616107.06e3099bd570.72.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98c8a896775f7a29d229a48737d979ffa6cefe38743c66c147f111a7a48db2cf
3
+ size 10779
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": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-multilingual-cased", "tokenizer_class": "BertTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03648b3ce94f133fd19cbd39c2e98c3ded7a5d529f389592236cf4dff9cb5116
3
+ size 3375
vocab.txt ADDED
The diff for this file is too large to render. See raw diff