Hugging Face's logo

0xhaz
/
bert2bert-cnn_dailymail-fp16-finetuned-1.0.0

Text2Text Generation
Transformers
PyTorch
TensorBoard
encoder-decoder
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
0xhaz commited on
Commit
2c62463
•
1 Parent(s): c76df70

Training in progress, step 500

Browse files
Files changed (16) hide show
  1. .gitignore +1 -0
  2. config.json +181 -0
  3. pytorch_model.bin +3 -0
  4. runs/Feb26_19-59-47_Boogs/1677412797.5622394/events.out.tfevents.1677412797.Boogs.12148.1 +3 -0
  5. runs/Feb26_19-59-47_Boogs/events.out.tfevents.1677412797.Boogs.12148.0 +3 -0
  6. runs/Feb26_20-17-52_Boogs/1677413878.283698/events.out.tfevents.1677413878.Boogs.23184.1 +3 -0
  7. runs/Feb26_20-17-52_Boogs/events.out.tfevents.1677413878.Boogs.23184.0 +3 -0
  8. runs/Feb26_21-27-28_Boogs/1677418054.818478/events.out.tfevents.1677418054.Boogs.20116.1 +3 -0
  9. runs/Feb26_21-27-28_Boogs/events.out.tfevents.1677418054.Boogs.20116.0 +3 -0
  10. runs/Feb26_21-52-26_Boogs/1677419552.1418426/events.out.tfevents.1677419552.Boogs.20116.1 +3 -0
  11. runs/Feb26_21-52-26_Boogs/events.out.tfevents.1677419552.Boogs.20116.0 +3 -0
  12. special_tokens_map.json +9 -0
  13. tokenizer.json +0 -0
  14. tokenizer_config.json +16 -0
  15. training_args.bin +3 -0
  16. vocab.txt +0 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,181 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "51b5d5cac0fa0ed09ed505df5800579996a2fe12",
3
+ "_name_or_path": "patrickvonplaten/bert2bert-cnn_dailymail-fp16",
4
+ "architectures": [
5
+ "EncoderDecoderModel"
6
+ ],
7
+ "decoder": {
8
+ "_name_or_path": "",
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": false,
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": "4.26.1",
83
+ "type_vocab_size": 2,
84
+ "typical_p": 1.0,
85
+ "use_bfloat16": false,
86
+ "use_cache": true,
87
+ "vocab_size": 30522
88
+ },
89
+ "decoder_start_token_id": 101,
90
+ "encoder": {
91
+ "_name_or_path": "",
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": false,
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": "4.26.1",
166
+ "type_vocab_size": 2,
167
+ "typical_p": 1.0,
168
+ "use_bfloat16": false,
169
+ "use_cache": true,
170
+ "vocab_size": 30522
171
+ },
172
+ "eos_token_id": 102,
173
+ "is_encoder_decoder": true,
174
+ "max_length": 142,
175
+ "min_length": 56,
176
+ "model_type": "encoder-decoder",
177
+ "no_repeat_ngram_size": 3,
178
+ "pad_token_id": 0,
179
+ "torch_dtype": "float32",
180
+ "transformers_version": null
181
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05d63b1688ac7cf186e6a596e8ede8a2912c42e6fd118cb148a1d04bbdd3ebc6
3
+ size 989637497
runs/Feb26_19-59-47_Boogs/1677412797.5622394/events.out.tfevents.1677412797.Boogs.12148.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a455c49abc50be2cbcf0866139fe4ae3928f6355ba882ee6170cb5e46dcf9d6
3
+ size 5973
runs/Feb26_19-59-47_Boogs/events.out.tfevents.1677412797.Boogs.12148.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2826e1ce5edd302d240571a91ac408f895fad3740a9f43b170e89ca576e996e4
3
+ size 8273
runs/Feb26_20-17-52_Boogs/1677413878.283698/events.out.tfevents.1677413878.Boogs.23184.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c0fe66fcc1e7d378195e93ef9713abcabd136734ef2d258c1322aca40444b77
3
+ size 5973
runs/Feb26_20-17-52_Boogs/events.out.tfevents.1677413878.Boogs.23184.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de98ad3336eff3f3a6a6f5bb89bf1847fab4510cf8aaef89802de3ad6f5abd66
3
+ size 8273
runs/Feb26_21-27-28_Boogs/1677418054.818478/events.out.tfevents.1677418054.Boogs.20116.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f60f9dc639ad8b33a8f885e17fdc4ffca6aa04badc0775f903e8cc7f828911d3
3
+ size 5973
runs/Feb26_21-27-28_Boogs/events.out.tfevents.1677418054.Boogs.20116.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:438c829c7310468cd88ef791cda4dac53b53fa5d9ddee10aef054a0b5ba0d135
3
+ size 8273
runs/Feb26_21-52-26_Boogs/1677419552.1418426/events.out.tfevents.1677419552.Boogs.20116.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63b089eb4f73fc9b76008f6092bddc927d72e686136cff2fed0f4941a9b16808
3
+ size 5973
runs/Feb26_21-52-26_Boogs/events.out.tfevents.1677419552.Boogs.20116.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffa614d271ac510d782fa4640c9f8a9535c5eb83466aeecff25671bb1ae5828d
3
+ size 8273
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 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "name_or_path": "patrickvonplaten/bert2bert-cnn_dailymail-fp16",
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "special_tokens_map_file": "C:\\Users\\jbuga/.cache\\huggingface\\hub\\models--patrickvonplaten--bert2bert-cnn_dailymail-fp16\\snapshots\\51b5d5cac0fa0ed09ed505df5800579996a2fe12\\special_tokens_map.json",
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 sha256:45af85c3a865fce183ae2fde5db2665e83864d8441dff7d7af6fe76022d335d6
3
+ size 3643
vocab.txt ADDED
The diff for this file is too large to render. See raw diff