Hugging Face's logo

tulayturanmaku
/
bert2bert_law_summarization

Text2Text Generation
Transformers
PyTorch
TensorBoard
encoder-decoder
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
tulayturanmaku commited on
Commit
35a6cde
•
1 Parent(s): de850b4

Training in progress, step 500

Browse files
Files changed (10) hide show
  1. .gitignore +1 -0
  2. config.json +182 -0
  3. pytorch_model.bin +3 -0
  4. runs/Aug16_07-37-42_cef1294422d5/1692171473.559873/events.out.tfevents.1692171473.cef1294422d5.846.1 +3 -0
  5. runs/Aug16_07-37-42_cef1294422d5/events.out.tfevents.1692171473.cef1294422d5.846.0 +3 -0
  6. special_tokens_map.json +7 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +16 -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
+ "_commit_hash": "1ef317dbcd999c45f7ce8be2ddaac1e78324d90c",
3
+ "_name_or_path": "mrm8488/bert2bert_shared-turkish-summarization",
4
+ "architectures": [
5
+ "EncoderDecoderModel"
6
+ ],
7
+ "decoder": {
8
+ "_name_or_path": "dbmdz/bert-base-turkish-cased",
9
+ "add_cross_attention": true,
10
+ "architectures": null,
11
+ "attention_probs_dropout_prob": 0.1,
12
+ "bad_words_ids": null,
13
+ "begin_suppress_tokens": null,
14
+ "bos_token_id": null,
15
+ "chunk_size_feed_forward": 0,
16
+ "classifier_dropout": null,
17
+ "cross_attention_hidden_size": null,
18
+ "decoder_start_token_id": null,
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
+ "position_embedding_type": "absolute",
61
+ "prefix": null,
62
+ "problem_type": null,
63
+ "pruned_heads": {},
64
+ "remove_invalid_values": false,
65
+ "repetition_penalty": 1.0,
66
+ "return_dict": true,
67
+ "return_dict_in_generate": false,
68
+ "sep_token_id": null,
69
+ "suppress_tokens": null,
70
+ "task_specific_params": null,
71
+ "temperature": 1.0,
72
+ "tf_legacy_loss": false,
73
+ "tie_encoder_decoder": false,
74
+ "tie_word_embeddings": true,
75
+ "tokenizer_class": null,
76
+ "top_k": 50,
77
+ "top_p": 1.0,
78
+ "torch_dtype": null,
79
+ "torchscript": false,
80
+ "transformers_version": "4.28.0",
81
+ "type_vocab_size": 2,
82
+ "typical_p": 1.0,
83
+ "use_bfloat16": false,
84
+ "use_cache": true,
85
+ "vocab_size": 32000
86
+ },
87
+ "decoder_start_token_id": 2,
88
+ "early_stopping": true,
89
+ "encoder": {
90
+ "_name_or_path": "dbmdz/bert-base-turkish-cased",
91
+ "add_cross_attention": false,
92
+ "architectures": null,
93
+ "attention_probs_dropout_prob": 0.1,
94
+ "bad_words_ids": null,
95
+ "begin_suppress_tokens": null,
96
+ "bos_token_id": null,
97
+ "chunk_size_feed_forward": 0,
98
+ "classifier_dropout": null,
99
+ "cross_attention_hidden_size": null,
100
+ "decoder_start_token_id": null,
101
+ "diversity_penalty": 0.0,
102
+ "do_sample": false,
103
+ "early_stopping": false,
104
+ "encoder_no_repeat_ngram_size": 0,
105
+ "eos_token_id": null,
106
+ "exponential_decay_length_penalty": null,
107
+ "finetuning_task": null,
108
+ "forced_bos_token_id": null,
109
+ "forced_eos_token_id": null,
110
+ "gradient_checkpointing": false,
111
+ "hidden_act": "gelu",
112
+ "hidden_dropout_prob": 0.1,
113
+ "hidden_size": 768,
114
+ "id2label": {
115
+ "0": "LABEL_0",
116
+ "1": "LABEL_1"
117
+ },
118
+ "initializer_range": 0.02,
119
+ "intermediate_size": 3072,
120
+ "is_decoder": false,
121
+ "is_encoder_decoder": false,
122
+ "label2id": {
123
+ "LABEL_0": 0,
124
+ "LABEL_1": 1
125
+ },
126
+ "layer_norm_eps": 1e-12,
127
+ "length_penalty": 1.0,
128
+ "max_length": 20,
129
+ "max_position_embeddings": 512,
130
+ "min_length": 0,
131
+ "model_type": "bert",
132
+ "no_repeat_ngram_size": 0,
133
+ "num_attention_heads": 12,
134
+ "num_beam_groups": 1,
135
+ "num_beams": 1,
136
+ "num_hidden_layers": 12,
137
+ "num_return_sequences": 1,
138
+ "output_attentions": false,
139
+ "output_hidden_states": false,
140
+ "output_scores": false,
141
+ "pad_token_id": 0,
142
+ "position_embedding_type": "absolute",
143
+ "prefix": null,
144
+ "problem_type": null,
145
+ "pruned_heads": {},
146
+ "remove_invalid_values": false,
147
+ "repetition_penalty": 1.0,
148
+ "return_dict": true,
149
+ "return_dict_in_generate": false,
150
+ "sep_token_id": null,
151
+ "suppress_tokens": null,
152
+ "task_specific_params": null,
153
+ "temperature": 1.0,
154
+ "tf_legacy_loss": false,
155
+ "tie_encoder_decoder": false,
156
+ "tie_word_embeddings": true,
157
+ "tokenizer_class": null,
158
+ "top_k": 50,
159
+ "top_p": 1.0,
160
+ "torch_dtype": null,
161
+ "torchscript": false,
162
+ "transformers_version": "4.28.0",
163
+ "type_vocab_size": 2,
164
+ "typical_p": 1.0,
165
+ "use_bfloat16": false,
166
+ "use_cache": true,
167
+ "vocab_size": 32000
168
+ },
169
+ "eos_token_id": 3,
170
+ "is_encoder_decoder": true,
171
+ "length_penalty": 2.0,
172
+ "max_length": 64,
173
+ "min_length": 8,
174
+ "model_type": "encoder-decoder",
175
+ "no_repeat_ngram_size": 3,
176
+ "num_beams": 4,
177
+ "pad_token_id": 0,
178
+ "tie_encoder_decoder": true,
179
+ "torch_dtype": "float32",
180
+ "transformers_version": null,
181
+ "vocab_size": 32000
182
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f073b5f2254de3ef4eda8cfe6be4a78c8257b88e5e2a6f65dffa239fad947442
3
+ size 558584357
runs/Aug16_07-37-42_cef1294422d5/1692171473.559873/events.out.tfevents.1692171473.cef1294422d5.846.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8496e04878200c3efbf2e926321598ba8cac6469bbcffe9043c5a2ae85702e6
3
+ size 6191
runs/Aug16_07-37-42_cef1294422d5/events.out.tfevents.1692171473.cef1294422d5.846.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5685b0c451fdbecdbe582d7e83e67105b67a3ae2fb7d0c52ea5bf9a1e3641dda
3
+ size 8717
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 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": false,
6
+ "mask_token": "[MASK]",
7
+ "max_len": 512,
8
+ "model_max_length": 512,
9
+ "never_split": null,
10
+ "pad_token": "[PAD]",
11
+ "sep_token": "[SEP]",
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "BertTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b0fa8557d3867cf9090de94855e2b27a9468616a1fc3da129641706e3747c5a
3
+ size 3771
vocab.txt ADDED
The diff for this file is too large to render. See raw diff