Hugging Face's logo

heskielsvn
/
bert2bert-cased-project-CNNDailyMail

Text2Text Generation
Transformers
PyTorch
TensorBoard
encoder-decoder
Inference Endpoints
Model card Files Metrics Community
heskielsvn commited on
Commit
988b15a
•
1 Parent(s): 20e2b53

Training in progress, step 32

Browse files
Files changed (9) hide show
  1. .gitignore +1 -0
  2. config.json +184 -0
  3. pytorch_model.bin +3 -0
  4. runs/Jul15_08-30-31_c64bfedb61f3/events.out.tfevents.1689409850.c64bfedb61f3.148.0 +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 +1,184 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "architectures": [
4
+ "EncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_name_or_path": "bert-base-cased",
8
+ "add_cross_attention": true,
9
+ "architectures": [
10
+ "BertForMaskedLM"
11
+ ],
12
+ "attention_probs_dropout_prob": 0.1,
13
+ "bad_words_ids": null,
14
+ "begin_suppress_tokens": null,
15
+ "bos_token_id": null,
16
+ "chunk_size_feed_forward": 0,
17
+ "classifier_dropout": null,
18
+ "cross_attention_hidden_size": null,
19
+ "decoder_start_token_id": null,
20
+ "diversity_penalty": 0.0,
21
+ "do_sample": false,
22
+ "early_stopping": false,
23
+ "encoder_no_repeat_ngram_size": 0,
24
+ "eos_token_id": null,
25
+ "exponential_decay_length_penalty": null,
26
+ "finetuning_task": null,
27
+ "forced_bos_token_id": null,
28
+ "forced_eos_token_id": null,
29
+ "gradient_checkpointing": false,
30
+ "hidden_act": "gelu",
31
+ "hidden_dropout_prob": 0.1,
32
+ "hidden_size": 768,
33
+ "id2label": {
34
+ "0": "LABEL_0",
35
+ "1": "LABEL_1"
36
+ },
37
+ "initializer_range": 0.02,
38
+ "intermediate_size": 3072,
39
+ "is_decoder": true,
40
+ "is_encoder_decoder": false,
41
+ "label2id": {
42
+ "LABEL_0": 0,
43
+ "LABEL_1": 1
44
+ },
45
+ "layer_norm_eps": 1e-12,
46
+ "length_penalty": 1.0,
47
+ "max_length": 20,
48
+ "max_position_embeddings": 512,
49
+ "min_length": 0,
50
+ "model_type": "bert",
51
+ "no_repeat_ngram_size": 0,
52
+ "num_attention_heads": 12,
53
+ "num_beam_groups": 1,
54
+ "num_beams": 1,
55
+ "num_hidden_layers": 12,
56
+ "num_return_sequences": 1,
57
+ "output_attentions": false,
58
+ "output_hidden_states": false,
59
+ "output_scores": false,
60
+ "pad_token_id": 0,
61
+ "position_embedding_type": "absolute",
62
+ "prefix": null,
63
+ "problem_type": null,
64
+ "pruned_heads": {},
65
+ "remove_invalid_values": false,
66
+ "repetition_penalty": 1.0,
67
+ "return_dict": true,
68
+ "return_dict_in_generate": false,
69
+ "sep_token_id": null,
70
+ "suppress_tokens": null,
71
+ "task_specific_params": null,
72
+ "temperature": 1.0,
73
+ "tf_legacy_loss": false,
74
+ "tie_encoder_decoder": false,
75
+ "tie_word_embeddings": true,
76
+ "tokenizer_class": null,
77
+ "top_k": 50,
78
+ "top_p": 1.0,
79
+ "torch_dtype": null,
80
+ "torchscript": false,
81
+ "transformers_version": "4.30.2",
82
+ "type_vocab_size": 2,
83
+ "typical_p": 1.0,
84
+ "use_bfloat16": false,
85
+ "use_cache": true,
86
+ "vocab_size": 28996
87
+ },
88
+ "decoder_start_token_id": 101,
89
+ "early_stopping": true,
90
+ "encoder": {
91
+ "_name_or_path": "bert-base-cased",
92
+ "add_cross_attention": false,
93
+ "architectures": [
94
+ "BertForMaskedLM"
95
+ ],
96
+ "attention_probs_dropout_prob": 0.1,
97
+ "bad_words_ids": null,
98
+ "begin_suppress_tokens": 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
+ "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
+ "gradient_checkpointing": false,
114
+ "hidden_act": "gelu",
115
+ "hidden_dropout_prob": 0.1,
116
+ "hidden_size": 768,
117
+ "id2label": {
118
+ "0": "LABEL_0",
119
+ "1": "LABEL_1"
120
+ },
121
+ "initializer_range": 0.02,
122
+ "intermediate_size": 3072,
123
+ "is_decoder": false,
124
+ "is_encoder_decoder": false,
125
+ "label2id": {
126
+ "LABEL_0": 0,
127
+ "LABEL_1": 1
128
+ },
129
+ "layer_norm_eps": 1e-12,
130
+ "length_penalty": 1.0,
131
+ "max_length": 20,
132
+ "max_position_embeddings": 512,
133
+ "min_length": 0,
134
+ "model_type": "bert",
135
+ "no_repeat_ngram_size": 0,
136
+ "num_attention_heads": 12,
137
+ "num_beam_groups": 1,
138
+ "num_beams": 1,
139
+ "num_hidden_layers": 12,
140
+ "num_return_sequences": 1,
141
+ "output_attentions": false,
142
+ "output_hidden_states": false,
143
+ "output_scores": false,
144
+ "pad_token_id": 0,
145
+ "position_embedding_type": "absolute",
146
+ "prefix": null,
147
+ "problem_type": null,
148
+ "pruned_heads": {},
149
+ "remove_invalid_values": false,
150
+ "repetition_penalty": 1.0,
151
+ "return_dict": true,
152
+ "return_dict_in_generate": false,
153
+ "sep_token_id": null,
154
+ "suppress_tokens": null,
155
+ "task_specific_params": null,
156
+ "temperature": 1.0,
157
+ "tf_legacy_loss": false,
158
+ "tie_encoder_decoder": false,
159
+ "tie_word_embeddings": true,
160
+ "tokenizer_class": null,
161
+ "top_k": 50,
162
+ "top_p": 1.0,
163
+ "torch_dtype": null,
164
+ "torchscript": false,
165
+ "transformers_version": "4.30.2",
166
+ "type_vocab_size": 2,
167
+ "typical_p": 1.0,
168
+ "use_bfloat16": false,
169
+ "use_cache": true,
170
+ "vocab_size": 28996
171
+ },
172
+ "eos_token_id": 102,
173
+ "is_encoder_decoder": true,
174
+ "length_penalty": 2.0,
175
+ "max_length": 142,
176
+ "min_length": 56,
177
+ "model_type": "encoder-decoder",
178
+ "no_repeat_ngram_size": 3,
179
+ "num_beams": 4,
180
+ "pad_token_id": 0,
181
+ "torch_dtype": "float32",
182
+ "transformers_version": null,
183
+ "vocab_size": 28996
184
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6448bd4425eb069959a73ccbeaf1884b4a485980c6b20dee705ce85639abb8df
3
+ size 980263033
runs/Jul15_08-30-31_c64bfedb61f3/events.out.tfevents.1689409850.c64bfedb61f3.148.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71f897710c2bdd8dbc47fcd8a3d75affae265fb4c020c58ec541cf3890b9bde5
3
+ size 16697
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:f8ce9d14162147a58ddc4053bb6e0b9c13ca7ddfa2d84643256fc3b268e983b4
3
+ size 4091
vocab.txt ADDED
The diff for this file is too large to render. See raw diff