Hugging Face's logo

gsliwoski
/
bertgen-nopre-food-summarizer

Text2Text Generation
Transformers
PyTorch
TensorBoard
encoder-decoder
Inference Endpoints
Model card Files Metrics Community
gsliwoski commited on
Commit
0248176
•
1 Parent(s): d5249b7

Training in progress, step 500

Browse files
Files changed (23) hide show
  1. .gitignore +1 -0
  2. config.json +161 -0
  3. pytorch_model.bin +3 -0
  4. runs/Sep17_21-15-43_b92c97ab9319/1663449401.4811838/events.out.tfevents.1663449401.b92c97ab9319.25404.1 +3 -0
  5. runs/Sep17_21-15-43_b92c97ab9319/1663450022.453183/events.out.tfevents.1663450022.b92c97ab9319.25404.3 +3 -0
  6. runs/Sep17_21-15-43_b92c97ab9319/1663450185.9697526/events.out.tfevents.1663450185.b92c97ab9319.25404.5 +3 -0
  7. runs/Sep17_21-15-43_b92c97ab9319/events.out.tfevents.1663449401.b92c97ab9319.25404.0 +3 -0
  8. runs/Sep17_21-15-43_b92c97ab9319/events.out.tfevents.1663450022.b92c97ab9319.25404.2 +3 -0
  9. runs/Sep17_21-15-43_b92c97ab9319/events.out.tfevents.1663450185.b92c97ab9319.25404.4 +3 -0
  10. runs/Sep17_21-33-37_b92c97ab9319/1663450435.322577/events.out.tfevents.1663450435.b92c97ab9319.26136.1 +3 -0
  11. runs/Sep17_21-33-37_b92c97ab9319/1663456952.217084/events.out.tfevents.1663456952.b92c97ab9319.26136.3 +3 -0
  12. runs/Sep17_21-33-37_b92c97ab9319/events.out.tfevents.1663450435.b92c97ab9319.26136.0 +3 -0
  13. runs/Sep17_21-33-37_b92c97ab9319/events.out.tfevents.1663456952.b92c97ab9319.26136.2 +3 -0
  14. runs/Sep17_23-26-28_b92c97ab9319/1663457202.091776/events.out.tfevents.1663457202.b92c97ab9319.26609.1 +3 -0
  15. runs/Sep17_23-26-28_b92c97ab9319/1663457219.686368/events.out.tfevents.1663457219.b92c97ab9319.26609.2 +3 -0
  16. runs/Sep17_23-26-28_b92c97ab9319/1663457366.7798657/events.out.tfevents.1663457366.b92c97ab9319.26609.3 +3 -0
  17. runs/Sep17_23-26-28_b92c97ab9319/events.out.tfevents.1663457202.b92c97ab9319.26609.0 +3 -0
  18. runs/Sep17_23-36-25_b92c97ab9319/1663457799.7320392/events.out.tfevents.1663457799.b92c97ab9319.26901.1 +3 -0
  19. runs/Sep17_23-36-25_b92c97ab9319/events.out.tfevents.1663457799.b92c97ab9319.26901.0 +3 -0
  20. special_tokens_map.json +7 -0
  21. tokenizer_config.json +15 -0
  22. training_args.bin +3 -0
  23. vocab.txt +0 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,161 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "",
7
+ "add_cross_attention": true,
8
+ "architectures": null,
9
+ "attention_probs_dropout_prob": 0.1,
10
+ "bad_words_ids": null,
11
+ "bos_token_id": 2,
12
+ "chunk_size_feed_forward": 0,
13
+ "cross_attention_hidden_size": null,
14
+ "decoder_start_token_id": null,
15
+ "diversity_penalty": 0.0,
16
+ "do_sample": false,
17
+ "early_stopping": false,
18
+ "encoder_no_repeat_ngram_size": 0,
19
+ "eos_token_id": 1,
20
+ "exponential_decay_length_penalty": null,
21
+ "finetuning_task": null,
22
+ "forced_bos_token_id": null,
23
+ "forced_eos_token_id": null,
24
+ "hidden_act": "gelu",
25
+ "hidden_dropout_prob": 0.1,
26
+ "hidden_size": 1024,
27
+ "id2label": {
28
+ "0": "LABEL_0",
29
+ "1": "LABEL_1"
30
+ },
31
+ "initializer_range": 0.02,
32
+ "intermediate_size": 4096,
33
+ "is_decoder": true,
34
+ "is_encoder_decoder": false,
35
+ "label2id": {
36
+ "LABEL_0": 0,
37
+ "LABEL_1": 1
38
+ },
39
+ "layer_norm_eps": 1e-12,
40
+ "length_penalty": 1.0,
41
+ "max_length": 20,
42
+ "max_position_embeddings": 512,
43
+ "min_length": 0,
44
+ "model_type": "bert-generation",
45
+ "no_repeat_ngram_size": 0,
46
+ "num_attention_heads": 16,
47
+ "num_beam_groups": 1,
48
+ "num_beams": 1,
49
+ "num_hidden_layers": 24,
50
+ "num_return_sequences": 1,
51
+ "output_attentions": false,
52
+ "output_hidden_states": false,
53
+ "output_scores": false,
54
+ "pad_token_id": 0,
55
+ "position_embedding_type": "absolute",
56
+ "prefix": null,
57
+ "problem_type": null,
58
+ "pruned_heads": {},
59
+ "remove_invalid_values": false,
60
+ "repetition_penalty": 1.0,
61
+ "return_dict": true,
62
+ "return_dict_in_generate": false,
63
+ "sep_token_id": null,
64
+ "task_specific_params": null,
65
+ "temperature": 1.0,
66
+ "tf_legacy_loss": false,
67
+ "tie_encoder_decoder": false,
68
+ "tie_word_embeddings": true,
69
+ "tokenizer_class": null,
70
+ "top_k": 50,
71
+ "top_p": 1.0,
72
+ "torch_dtype": null,
73
+ "torchscript": false,
74
+ "transformers_version": "4.21.3",
75
+ "typical_p": 1.0,
76
+ "use_bfloat16": false,
77
+ "use_cache": true,
78
+ "vocab_size": 50358
79
+ },
80
+ "decoder_start_token_id": 101,
81
+ "encoder": {
82
+ "_name_or_path": "",
83
+ "add_cross_attention": false,
84
+ "architectures": null,
85
+ "attention_probs_dropout_prob": 0.1,
86
+ "bad_words_ids": null,
87
+ "bos_token_id": 2,
88
+ "chunk_size_feed_forward": 0,
89
+ "cross_attention_hidden_size": null,
90
+ "decoder_start_token_id": null,
91
+ "diversity_penalty": 0.0,
92
+ "do_sample": false,
93
+ "early_stopping": false,
94
+ "encoder_no_repeat_ngram_size": 0,
95
+ "eos_token_id": 1,
96
+ "exponential_decay_length_penalty": null,
97
+ "finetuning_task": null,
98
+ "forced_bos_token_id": null,
99
+ "forced_eos_token_id": null,
100
+ "hidden_act": "gelu",
101
+ "hidden_dropout_prob": 0.1,
102
+ "hidden_size": 1024,
103
+ "id2label": {
104
+ "0": "LABEL_0",
105
+ "1": "LABEL_1"
106
+ },
107
+ "initializer_range": 0.02,
108
+ "intermediate_size": 4096,
109
+ "is_decoder": false,
110
+ "is_encoder_decoder": false,
111
+ "label2id": {
112
+ "LABEL_0": 0,
113
+ "LABEL_1": 1
114
+ },
115
+ "layer_norm_eps": 1e-12,
116
+ "length_penalty": 1.0,
117
+ "max_length": 20,
118
+ "max_position_embeddings": 512,
119
+ "min_length": 0,
120
+ "model_type": "bert-generation",
121
+ "no_repeat_ngram_size": 0,
122
+ "num_attention_heads": 16,
123
+ "num_beam_groups": 1,
124
+ "num_beams": 1,
125
+ "num_hidden_layers": 24,
126
+ "num_return_sequences": 1,
127
+ "output_attentions": false,
128
+ "output_hidden_states": false,
129
+ "output_scores": false,
130
+ "pad_token_id": 0,
131
+ "position_embedding_type": "absolute",
132
+ "prefix": null,
133
+ "problem_type": null,
134
+ "pruned_heads": {},
135
+ "remove_invalid_values": false,
136
+ "repetition_penalty": 1.0,
137
+ "return_dict": true,
138
+ "return_dict_in_generate": false,
139
+ "sep_token_id": null,
140
+ "task_specific_params": null,
141
+ "temperature": 1.0,
142
+ "tf_legacy_loss": false,
143
+ "tie_encoder_decoder": false,
144
+ "tie_word_embeddings": true,
145
+ "tokenizer_class": null,
146
+ "top_k": 50,
147
+ "top_p": 1.0,
148
+ "torch_dtype": null,
149
+ "torchscript": false,
150
+ "transformers_version": "4.21.3",
151
+ "typical_p": 1.0,
152
+ "use_bfloat16": false,
153
+ "use_cache": true,
154
+ "vocab_size": 50358
155
+ },
156
+ "is_encoder_decoder": true,
157
+ "model_type": "encoder-decoder",
158
+ "pad_token_id": 0,
159
+ "torch_dtype": "float32",
160
+ "transformers_version": null
161
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5702b8dc0e60f505482c4407a28c1d8ac83432136460b3437f683b56da854d96
3
+ size 3239022110
runs/Sep17_21-15-43_b92c97ab9319/1663449401.4811838/events.out.tfevents.1663449401.b92c97ab9319.25404.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87c9c4d680110174b29195e1a73463366dd69e2189ba52f8804cb0e90ff41f70
3
+ size 5677
runs/Sep17_21-15-43_b92c97ab9319/1663450022.453183/events.out.tfevents.1663450022.b92c97ab9319.25404.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ae8f5ada0117a167b90108b7c7ef343f2572fcf0315ee170adf34da7d77a629
3
+ size 5677
runs/Sep17_21-15-43_b92c97ab9319/1663450185.9697526/events.out.tfevents.1663450185.b92c97ab9319.25404.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5ad101df3b21bba0fc300244349060e64f78a6e0e3fe53b4a7c2dc21f054328
3
+ size 5677
runs/Sep17_21-15-43_b92c97ab9319/events.out.tfevents.1663449401.b92c97ab9319.25404.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40a938e5fcf290a538cc9b4f445ffd7401aaaf36f0d078aa5f0f72b649783a5e
3
+ size 7388
runs/Sep17_21-15-43_b92c97ab9319/events.out.tfevents.1663450022.b92c97ab9319.25404.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:370d7dea69c9613bc6e328c44d90c21f71d63d655b01e82fcd72cc27dff08b8b
3
+ size 7421
runs/Sep17_21-15-43_b92c97ab9319/events.out.tfevents.1663450185.b92c97ab9319.25404.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a7971ab2871fa4ee64885f6b2757d50b240a5f8488689b8a2455f82e804ecc1
3
+ size 4136
runs/Sep17_21-33-37_b92c97ab9319/1663450435.322577/events.out.tfevents.1663450435.b92c97ab9319.26136.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ee49e883d2907b958ed18c3a95a2d133150c8e6fdc3378514253677a8a2acc5
3
+ size 5677
runs/Sep17_21-33-37_b92c97ab9319/1663456952.217084/events.out.tfevents.1663456952.b92c97ab9319.26136.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36d71ef517515d6ad359512416e22345976f1f0b2df64af96ff4f2d6b31a5edb
3
+ size 5677
runs/Sep17_21-33-37_b92c97ab9319/events.out.tfevents.1663450435.b92c97ab9319.26136.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c00fa4e54b77eb09c4385252e2c7ec799c7dce9fc54bc50368d1d680be8954d7
3
+ size 7421
runs/Sep17_21-33-37_b92c97ab9319/events.out.tfevents.1663456952.b92c97ab9319.26136.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30d53d8ed438ad749ba0613cdfb1c0f957a91de83565a2c192bc5c67a2d60f16
3
+ size 7442
runs/Sep17_23-26-28_b92c97ab9319/1663457202.091776/events.out.tfevents.1663457202.b92c97ab9319.26609.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52e002fa9f031223085300632cd6498cd32bb749201bffb0f51aeae68a357aec
3
+ size 5677
runs/Sep17_23-26-28_b92c97ab9319/1663457219.686368/events.out.tfevents.1663457219.b92c97ab9319.26609.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e030db36cae481ee086cce8e4be31df71d67b194c3131902dcc81c1c8ce3c1a3
3
+ size 5677
runs/Sep17_23-26-28_b92c97ab9319/1663457366.7798657/events.out.tfevents.1663457366.b92c97ab9319.26609.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3816ddc82a63e586242711670bbf06d98c72e847920ff23f7d60e2034096d4d0
3
+ size 5677
runs/Sep17_23-26-28_b92c97ab9319/events.out.tfevents.1663457202.b92c97ab9319.26609.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30fba9ebc076c5dbf7d3e7cf72b5d97763f47a055992797a1fff6d5c572200f1
3
+ size 22246
runs/Sep17_23-36-25_b92c97ab9319/1663457799.7320392/events.out.tfevents.1663457799.b92c97ab9319.26901.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e89b40635dbdcc74afece3e6699220caeebf3fc7d94610b09ab0b2c6c455269
3
+ size 5677
runs/Sep17_23-36-25_b92c97ab9319/events.out.tfevents.1663457799.b92c97ab9319.26901.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86795eca627e10ae054f457b58e59dc261b59baa798c12e7811349dda6cdcb07
3
+ size 7441
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_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": "prajjwal1/bert-tiny",
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:b3c478a9fc2444778b5f505354f02fa3dba4317b0b25cb890931957dd79bd9a7
3
+ size 3503
vocab.txt ADDED
The diff for this file is too large to render. See raw diff