Hugging Face's logo

Atharvgarg
/
bert-small2bert-small-finetuned-cnn_daily_mail-summarization-finetuned-multi-news

Text2Text Generation
Transformers
PyTorch
TensorBoard
encoder-decoder
summarisation
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
2
Atharvgarg commited on
Commit
c7c08f2
•
1 Parent(s): 068bfee

Training in progress, step 500

Browse files
Files changed (16) hide show
  1. .gitignore +1 -0
  2. config.json +174 -0
  3. pytorch_model.bin +3 -0
  4. runs/Jul18_19-10-43_77b2f0e4d4a5/1658171596.1457946/events.out.tfevents.1658171596.77b2f0e4d4a5.75.1 +3 -0
  5. runs/Jul18_19-10-43_77b2f0e4d4a5/1658171651.2879257/events.out.tfevents.1658171651.77b2f0e4d4a5.75.3 +3 -0
  6. runs/Jul18_19-10-43_77b2f0e4d4a5/events.out.tfevents.1658171596.77b2f0e4d4a5.75.0 +3 -0
  7. runs/Jul18_19-10-43_77b2f0e4d4a5/events.out.tfevents.1658171651.77b2f0e4d4a5.75.2 +3 -0
  8. runs/Jul18_19-16-33_77b2f0e4d4a5/1658171810.2802653/events.out.tfevents.1658171810.77b2f0e4d4a5.75.5 +3 -0
  9. runs/Jul18_19-16-33_77b2f0e4d4a5/events.out.tfevents.1658171810.77b2f0e4d4a5.75.4 +3 -0
  10. runs/Jul18_19-24-17_77b2f0e4d4a5/1658172271.7047846/events.out.tfevents.1658172271.77b2f0e4d4a5.75.7 +3 -0
  11. runs/Jul18_19-24-17_77b2f0e4d4a5/events.out.tfevents.1658172271.77b2f0e4d4a5.75.6 +3 -0
  12. special_tokens_map.json +7 -0
  13. tokenizer.json +0 -0
  14. tokenizer_config.json +15 -0
  15. training_args.bin +3 -0
  16. vocab.txt +0 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,174 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mrm8488/bert-small2bert-small-finetuned-cnn_daily_mail-summarization",
3
+ "architectures": [
4
+ "EncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_name_or_path": "google/bert_uncased_L-4_H-512_A-8",
8
+ "add_cross_attention": true,
9
+ "architectures": null,
10
+ "attention_probs_dropout_prob": 0.1,
11
+ "bad_words_ids": null,
12
+ "bos_token_id": null,
13
+ "chunk_size_feed_forward": 0,
14
+ "classifier_dropout": null,
15
+ "cross_attention_hidden_size": null,
16
+ "decoder_start_token_id": null,
17
+ "diversity_penalty": 0.0,
18
+ "do_sample": false,
19
+ "early_stopping": false,
20
+ "encoder_no_repeat_ngram_size": 0,
21
+ "eos_token_id": null,
22
+ "exponential_decay_length_penalty": null,
23
+ "finetuning_task": null,
24
+ "forced_bos_token_id": null,
25
+ "forced_eos_token_id": null,
26
+ "gradient_checkpointing": false,
27
+ "hidden_act": "gelu",
28
+ "hidden_dropout_prob": 0.1,
29
+ "hidden_size": 512,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 2048,
36
+ "is_decoder": true,
37
+ "is_encoder_decoder": false,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1
41
+ },
42
+ "layer_norm_eps": 1e-12,
43
+ "length_penalty": 1.0,
44
+ "max_length": 20,
45
+ "max_position_embeddings": 512,
46
+ "min_length": 0,
47
+ "model_type": "bert",
48
+ "no_repeat_ngram_size": 0,
49
+ "num_attention_heads": 8,
50
+ "num_beam_groups": 1,
51
+ "num_beams": 1,
52
+ "num_hidden_layers": 4,
53
+ "num_return_sequences": 1,
54
+ "output_attentions": false,
55
+ "output_hidden_states": false,
56
+ "output_scores": false,
57
+ "pad_token_id": 0,
58
+ "position_embedding_type": "absolute",
59
+ "prefix": null,
60
+ "problem_type": null,
61
+ "pruned_heads": {},
62
+ "remove_invalid_values": false,
63
+ "repetition_penalty": 1.0,
64
+ "return_dict": false,
65
+ "return_dict_in_generate": false,
66
+ "sep_token_id": null,
67
+ "task_specific_params": null,
68
+ "temperature": 1.0,
69
+ "tie_encoder_decoder": false,
70
+ "tie_word_embeddings": true,
71
+ "tokenizer_class": null,
72
+ "top_k": 50,
73
+ "top_p": 1.0,
74
+ "torch_dtype": null,
75
+ "torchscript": false,
76
+ "transformers_version": "4.20.1",
77
+ "type_vocab_size": 2,
78
+ "typical_p": 1.0,
79
+ "use_bfloat16": false,
80
+ "use_cache": true,
81
+ "vocab_size": 30522
82
+ },
83
+ "decoder_start_token_id": 101,
84
+ "early_stopping": true,
85
+ "encoder": {
86
+ "_name_or_path": "google/bert_uncased_L-4_H-512_A-8",
87
+ "add_cross_attention": false,
88
+ "architectures": null,
89
+ "attention_probs_dropout_prob": 0.1,
90
+ "bad_words_ids": null,
91
+ "bos_token_id": null,
92
+ "chunk_size_feed_forward": 0,
93
+ "classifier_dropout": null,
94
+ "cross_attention_hidden_size": null,
95
+ "decoder_start_token_id": null,
96
+ "diversity_penalty": 0.0,
97
+ "do_sample": false,
98
+ "early_stopping": false,
99
+ "encoder_no_repeat_ngram_size": 0,
100
+ "eos_token_id": null,
101
+ "exponential_decay_length_penalty": null,
102
+ "finetuning_task": null,
103
+ "forced_bos_token_id": null,
104
+ "forced_eos_token_id": null,
105
+ "gradient_checkpointing": false,
106
+ "hidden_act": "gelu",
107
+ "hidden_dropout_prob": 0.1,
108
+ "hidden_size": 512,
109
+ "id2label": {
110
+ "0": "LABEL_0",
111
+ "1": "LABEL_1"
112
+ },
113
+ "initializer_range": 0.02,
114
+ "intermediate_size": 2048,
115
+ "is_decoder": false,
116
+ "is_encoder_decoder": false,
117
+ "label2id": {
118
+ "LABEL_0": 0,
119
+ "LABEL_1": 1
120
+ },
121
+ "layer_norm_eps": 1e-12,
122
+ "length_penalty": 1.0,
123
+ "max_length": 20,
124
+ "max_position_embeddings": 512,
125
+ "min_length": 0,
126
+ "model_type": "bert",
127
+ "no_repeat_ngram_size": 0,
128
+ "num_attention_heads": 8,
129
+ "num_beam_groups": 1,
130
+ "num_beams": 1,
131
+ "num_hidden_layers": 4,
132
+ "num_return_sequences": 1,
133
+ "output_attentions": false,
134
+ "output_hidden_states": false,
135
+ "output_scores": false,
136
+ "pad_token_id": 0,
137
+ "position_embedding_type": "absolute",
138
+ "prefix": null,
139
+ "problem_type": null,
140
+ "pruned_heads": {},
141
+ "remove_invalid_values": false,
142
+ "repetition_penalty": 1.0,
143
+ "return_dict": false,
144
+ "return_dict_in_generate": false,
145
+ "sep_token_id": null,
146
+ "task_specific_params": null,
147
+ "temperature": 1.0,
148
+ "tie_encoder_decoder": false,
149
+ "tie_word_embeddings": true,
150
+ "tokenizer_class": null,
151
+ "top_k": 50,
152
+ "top_p": 1.0,
153
+ "torch_dtype": null,
154
+ "torchscript": false,
155
+ "transformers_version": "4.20.1",
156
+ "type_vocab_size": 2,
157
+ "typical_p": 1.0,
158
+ "use_bfloat16": false,
159
+ "use_cache": true,
160
+ "vocab_size": 30522
161
+ },
162
+ "eos_token_id": 102,
163
+ "is_encoder_decoder": true,
164
+ "length_penalty": 2.0,
165
+ "max_length": 142,
166
+ "min_length": 56,
167
+ "model_type": "encoder-decoder",
168
+ "no_repeat_ngram_size": 3,
169
+ "num_beams": 4,
170
+ "pad_token_id": 0,
171
+ "torch_dtype": "float32",
172
+ "transformers_version": null,
173
+ "vocab_size": 30522
174
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67419f8e0d8cc420f6b337234fbe5f5665acd6125b58c3903695db4a9de4f0dd
3
+ size 247133387
runs/Jul18_19-10-43_77b2f0e4d4a5/1658171596.1457946/events.out.tfevents.1658171596.77b2f0e4d4a5.75.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:231f9ff4fee72d66ab24877ced8fb4eef74e03afc184d867e42f509244d3fb3b
3
+ size 5748
runs/Jul18_19-10-43_77b2f0e4d4a5/1658171651.2879257/events.out.tfevents.1658171651.77b2f0e4d4a5.75.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a6a9d36641f9c8e3a4f5bb95dc524fb8dc0a27aed6cce5ae93b5cf3742193d3
3
+ size 5748
runs/Jul18_19-10-43_77b2f0e4d4a5/events.out.tfevents.1658171596.77b2f0e4d4a5.75.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a76791af160c9d9e22307ec7320164c1ad5f2edf1657ccdbbad60697aa9d6b89
3
+ size 8062
runs/Jul18_19-10-43_77b2f0e4d4a5/events.out.tfevents.1658171651.77b2f0e4d4a5.75.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5cd68741a542c6c1af650e468171d562e5f6b4bd6e08071fa0fbed39484832d
3
+ size 8062
runs/Jul18_19-16-33_77b2f0e4d4a5/1658171810.2802653/events.out.tfevents.1658171810.77b2f0e4d4a5.75.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7240f0ee15cc227c7b692843d93acceb8f4e3211214faa6eea11da8275a2c078
3
+ size 5748
runs/Jul18_19-16-33_77b2f0e4d4a5/events.out.tfevents.1658171810.77b2f0e4d4a5.75.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77ece4a5bf32ca070d16196a91dcc55cda7c2bb91bc656760cbe7a9482536e81
3
+ size 8062
runs/Jul18_19-24-17_77b2f0e4d4a5/1658172271.7047846/events.out.tfevents.1658172271.77b2f0e4d4a5.75.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c73108f9e567485252c73cfe0f0f1b7bfad792de92c831eabe97bef7587c7ec4
3
+ size 5748
runs/Jul18_19-24-17_77b2f0e4d4a5/events.out.tfevents.1658172271.77b2f0e4d4a5.75.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:642c3c12cfc81ed04cc3467b666a5a7ac0a5d961a888cd7dc39c8d2dfe174bf1
3
+ size 4136
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 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "name_or_path": "mrm8488/bert-small2bert-small-finetuned-cnn_daily_mail-summarization",
7
+ "never_split": null,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "special_tokens_map_file": null,
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:931b52b1098d078a6f71acca69cdbc159efb1bff0d624aa1f084e99bd082f5b6
3
+ size 3567
vocab.txt ADDED
The diff for this file is too large to render. See raw diff