Hugging Face's logo

heskielsvn
/
bert2bert-cased-project-DialogueSumm

Text2Text Generation
Transformers
PyTorch
TensorBoard
encoder-decoder
Inference Endpoints
Model card Files Metrics Community
heskielsvn commited on
Commit
f9971c4
•
1 Parent(s): f994208

Training in progress, step 32

Browse files
Files changed (9) hide show
  1. .gitignore +1 -0
  2. config.json +185 -0
  3. pytorch_model.bin +3 -0
  4. runs/Jul15_13-00-42_ff4684b0b668/events.out.tfevents.1689426051.ff4684b0b668.1144.0 +3 -0
  5. special_tokens_map.json +9 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +13 -0
  8. training_args.bin +3 -0
  9. vocab.txt +0 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,185 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "dfb2de8f814cc30bf02f984bbfe77d93ae66ef81",
3
+ "_name_or_path": "heskielsvn/bert2bert-cased-project-SamSum",
4
+ "architectures": [
5
+ "EncoderDecoderModel"
6
+ ],
7
+ "decoder": {
8
+ "_name_or_path": "bert-base-cased",
9
+ "add_cross_attention": true,
10
+ "architectures": [
11
+ "BertForMaskedLM"
12
+ ],
13
+ "attention_probs_dropout_prob": 0.1,
14
+ "bad_words_ids": null,
15
+ "begin_suppress_tokens": null,
16
+ "bos_token_id": null,
17
+ "chunk_size_feed_forward": 0,
18
+ "classifier_dropout": null,
19
+ "cross_attention_hidden_size": null,
20
+ "decoder_start_token_id": null,
21
+ "diversity_penalty": 0.0,
22
+ "do_sample": false,
23
+ "early_stopping": false,
24
+ "encoder_no_repeat_ngram_size": 0,
25
+ "eos_token_id": null,
26
+ "exponential_decay_length_penalty": null,
27
+ "finetuning_task": null,
28
+ "forced_bos_token_id": null,
29
+ "forced_eos_token_id": null,
30
+ "gradient_checkpointing": false,
31
+ "hidden_act": "gelu",
32
+ "hidden_dropout_prob": 0.1,
33
+ "hidden_size": 768,
34
+ "id2label": {
35
+ "0": "LABEL_0",
36
+ "1": "LABEL_1"
37
+ },
38
+ "initializer_range": 0.02,
39
+ "intermediate_size": 3072,
40
+ "is_decoder": true,
41
+ "is_encoder_decoder": false,
42
+ "label2id": {
43
+ "LABEL_0": 0,
44
+ "LABEL_1": 1
45
+ },
46
+ "layer_norm_eps": 1e-12,
47
+ "length_penalty": 1.0,
48
+ "max_length": 20,
49
+ "max_position_embeddings": 512,
50
+ "min_length": 0,
51
+ "model_type": "bert",
52
+ "no_repeat_ngram_size": 0,
53
+ "num_attention_heads": 12,
54
+ "num_beam_groups": 1,
55
+ "num_beams": 1,
56
+ "num_hidden_layers": 12,
57
+ "num_return_sequences": 1,
58
+ "output_attentions": false,
59
+ "output_hidden_states": false,
60
+ "output_scores": false,
61
+ "pad_token_id": 0,
62
+ "position_embedding_type": "absolute",
63
+ "prefix": null,
64
+ "problem_type": null,
65
+ "pruned_heads": {},
66
+ "remove_invalid_values": false,
67
+ "repetition_penalty": 1.0,
68
+ "return_dict": true,
69
+ "return_dict_in_generate": false,
70
+ "sep_token_id": null,
71
+ "suppress_tokens": null,
72
+ "task_specific_params": null,
73
+ "temperature": 1.0,
74
+ "tf_legacy_loss": false,
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": "4.30.2",
83
+ "type_vocab_size": 2,
84
+ "typical_p": 1.0,
85
+ "use_bfloat16": false,
86
+ "use_cache": true,
87
+ "vocab_size": 28996
88
+ },
89
+ "decoder_start_token_id": 101,
90
+ "early_stopping": true,
91
+ "encoder": {
92
+ "_name_or_path": "bert-base-cased",
93
+ "add_cross_attention": false,
94
+ "architectures": [
95
+ "BertForMaskedLM"
96
+ ],
97
+ "attention_probs_dropout_prob": 0.1,
98
+ "bad_words_ids": null,
99
+ "begin_suppress_tokens": null,
100
+ "bos_token_id": null,
101
+ "chunk_size_feed_forward": 0,
102
+ "classifier_dropout": null,
103
+ "cross_attention_hidden_size": null,
104
+ "decoder_start_token_id": null,
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
+ "position_embedding_type": "absolute",
147
+ "prefix": null,
148
+ "problem_type": null,
149
+ "pruned_heads": {},
150
+ "remove_invalid_values": false,
151
+ "repetition_penalty": 1.0,
152
+ "return_dict": true,
153
+ "return_dict_in_generate": false,
154
+ "sep_token_id": null,
155
+ "suppress_tokens": null,
156
+ "task_specific_params": null,
157
+ "temperature": 1.0,
158
+ "tf_legacy_loss": false,
159
+ "tie_encoder_decoder": false,
160
+ "tie_word_embeddings": true,
161
+ "tokenizer_class": null,
162
+ "top_k": 50,
163
+ "top_p": 1.0,
164
+ "torch_dtype": null,
165
+ "torchscript": false,
166
+ "transformers_version": "4.30.2",
167
+ "type_vocab_size": 2,
168
+ "typical_p": 1.0,
169
+ "use_bfloat16": false,
170
+ "use_cache": true,
171
+ "vocab_size": 28996
172
+ },
173
+ "eos_token_id": 102,
174
+ "is_encoder_decoder": true,
175
+ "length_penalty": 2.0,
176
+ "max_length": 142,
177
+ "min_length": 56,
178
+ "model_type": "encoder-decoder",
179
+ "no_repeat_ngram_size": 3,
180
+ "num_beams": 4,
181
+ "pad_token_id": 0,
182
+ "torch_dtype": "float32",
183
+ "transformers_version": null,
184
+ "vocab_size": 28996
185
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be13ec4537470ffa27b9d51c6967659168f3be61cbf627b1b31d288f66bcad60
3
+ size 980263033
runs/Jul15_13-00-42_ff4684b0b668/events.out.tfevents.1689426051.ff4684b0b668.1144.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:283e414f0921b051f5668ef8fdf528cbf8ac836d309cc305895d509a6138e8de
3
+ size 16879
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": "[UNK]"
9
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "strip_accents": null,
10
+ "tokenize_chinese_chars": true,
11
+ "tokenizer_class": "BertTokenizer",
12
+ "unk_token": "[UNK]"
13
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9587503573e784d446f4ee93273792347557807838992dda5b42508445239cd8
3
+ size 4091
vocab.txt ADDED
The diff for this file is too large to render. See raw diff