Hugging Face's logo

harish3742
/
bert-base-cnn-ft

Text2Text Generation
Transformers
TensorBoard
Safetensors
encoder-decoder
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
harish3742 commited on
Commit
b1a2d65
·
verified ·
1 Parent(s): 872d78c

Training in progress, step 100

Browse files
Files changed (15) hide show
  1. config.json +181 -0
  2. model.safetensors +3 -0
  3. runs/May05_08-53-36_b5f763934e05/events.out.tfevents.1714899217.b5f763934e05.1564.1 +3 -0
  4. runs/May05_08-57-00_b5f763934e05/events.out.tfevents.1714899422.b5f763934e05.5214.0 +3 -0
  5. runs/May05_09-00-36_b5f763934e05/events.out.tfevents.1714899637.b5f763934e05.5214.1 +3 -0
  6. runs/May05_09-02-37_b5f763934e05/events.out.tfevents.1714899760.b5f763934e05.6969.0 +3 -0
  7. runs/May05_09-17-34_b5f763934e05/events.out.tfevents.1714900656.b5f763934e05.11091.0 +3 -0
  8. runs/May05_10-24-00_b5f763934e05/events.out.tfevents.1714904640.b5f763934e05.11091.1 +3 -0
  9. runs/May05_10-31-34_b5f763934e05/events.out.tfevents.1714905096.b5f763934e05.29877.0 +3 -0
  10. runs/May05_10-36-54_b5f763934e05/events.out.tfevents.1714905414.b5f763934e05.29877.1 +3 -0
  11. special_tokens_map.json +9 -0
  12. tokenizer.json +0 -0
  13. tokenizer_config.json +57 -0
  14. training_args.bin +3 -0
  15. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,181 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "bert-base-uncased",
7
+ "add_cross_attention": true,
8
+ "architectures": [
9
+ "BertForMaskedLM"
10
+ ],
11
+ "attention_probs_dropout_prob": 0.1,
12
+ "bad_words_ids": null,
13
+ "begin_suppress_tokens": null,
14
+ "bos_token_id": null,
15
+ "chunk_size_feed_forward": 0,
16
+ "classifier_dropout": null,
17
+ "cross_attention_hidden_size": null,
18
+ "decoder_start_token_id": null,
19
+ "diversity_penalty": 0.0,
20
+ "do_sample": false,
21
+ "early_stopping": false,
22
+ "encoder_no_repeat_ngram_size": 0,
23
+ "eos_token_id": null,
24
+ "exponential_decay_length_penalty": null,
25
+ "finetuning_task": null,
26
+ "forced_bos_token_id": null,
27
+ "forced_eos_token_id": null,
28
+ "gradient_checkpointing": false,
29
+ "hidden_act": "gelu",
30
+ "hidden_dropout_prob": 0.1,
31
+ "hidden_size": 768,
32
+ "id2label": {
33
+ "0": "LABEL_0",
34
+ "1": "LABEL_1"
35
+ },
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 3072,
38
+ "is_decoder": true,
39
+ "is_encoder_decoder": false,
40
+ "label2id": {
41
+ "LABEL_0": 0,
42
+ "LABEL_1": 1
43
+ },
44
+ "layer_norm_eps": 1e-12,
45
+ "length_penalty": 1.0,
46
+ "max_length": 20,
47
+ "max_position_embeddings": 512,
48
+ "min_length": 0,
49
+ "model_type": "bert",
50
+ "no_repeat_ngram_size": 0,
51
+ "num_attention_heads": 12,
52
+ "num_beam_groups": 1,
53
+ "num_beams": 1,
54
+ "num_hidden_layers": 12,
55
+ "num_return_sequences": 1,
56
+ "output_attentions": false,
57
+ "output_hidden_states": false,
58
+ "output_scores": false,
59
+ "pad_token_id": 0,
60
+ "position_embedding_type": "absolute",
61
+ "prefix": null,
62
+ "problem_type": null,
63
+ "pruned_heads": {},
64
+ "remove_invalid_values": false,
65
+ "repetition_penalty": 1.0,
66
+ "return_dict": true,
67
+ "return_dict_in_generate": false,
68
+ "sep_token_id": null,
69
+ "suppress_tokens": null,
70
+ "task_specific_params": null,
71
+ "temperature": 1.0,
72
+ "tf_legacy_loss": false,
73
+ "tie_encoder_decoder": false,
74
+ "tie_word_embeddings": true,
75
+ "tokenizer_class": null,
76
+ "top_k": 50,
77
+ "top_p": 1.0,
78
+ "torch_dtype": null,
79
+ "torchscript": false,
80
+ "type_vocab_size": 2,
81
+ "typical_p": 1.0,
82
+ "use_bfloat16": false,
83
+ "use_cache": true,
84
+ "vocab_size": 30522
85
+ },
86
+ "decoder_start_token_id": 101,
87
+ "early_stopping": true,
88
+ "encoder": {
89
+ "_name_or_path": "bert-base-uncased",
90
+ "add_cross_attention": false,
91
+ "architectures": [
92
+ "BertForMaskedLM"
93
+ ],
94
+ "attention_probs_dropout_prob": 0.1,
95
+ "bad_words_ids": null,
96
+ "begin_suppress_tokens": null,
97
+ "bos_token_id": null,
98
+ "chunk_size_feed_forward": 0,
99
+ "classifier_dropout": null,
100
+ "cross_attention_hidden_size": null,
101
+ "decoder_start_token_id": null,
102
+ "diversity_penalty": 0.0,
103
+ "do_sample": false,
104
+ "early_stopping": false,
105
+ "encoder_no_repeat_ngram_size": 0,
106
+ "eos_token_id": null,
107
+ "exponential_decay_length_penalty": null,
108
+ "finetuning_task": null,
109
+ "forced_bos_token_id": null,
110
+ "forced_eos_token_id": null,
111
+ "gradient_checkpointing": false,
112
+ "hidden_act": "gelu",
113
+ "hidden_dropout_prob": 0.1,
114
+ "hidden_size": 768,
115
+ "id2label": {
116
+ "0": "LABEL_0",
117
+ "1": "LABEL_1"
118
+ },
119
+ "initializer_range": 0.02,
120
+ "intermediate_size": 3072,
121
+ "is_decoder": false,
122
+ "is_encoder_decoder": false,
123
+ "label2id": {
124
+ "LABEL_0": 0,
125
+ "LABEL_1": 1
126
+ },
127
+ "layer_norm_eps": 1e-12,
128
+ "length_penalty": 1.0,
129
+ "max_length": 20,
130
+ "max_position_embeddings": 512,
131
+ "min_length": 0,
132
+ "model_type": "bert",
133
+ "no_repeat_ngram_size": 0,
134
+ "num_attention_heads": 12,
135
+ "num_beam_groups": 1,
136
+ "num_beams": 1,
137
+ "num_hidden_layers": 12,
138
+ "num_return_sequences": 1,
139
+ "output_attentions": false,
140
+ "output_hidden_states": false,
141
+ "output_scores": false,
142
+ "pad_token_id": 0,
143
+ "position_embedding_type": "absolute",
144
+ "prefix": null,
145
+ "problem_type": null,
146
+ "pruned_heads": {},
147
+ "remove_invalid_values": false,
148
+ "repetition_penalty": 1.0,
149
+ "return_dict": true,
150
+ "return_dict_in_generate": false,
151
+ "sep_token_id": null,
152
+ "suppress_tokens": null,
153
+ "task_specific_params": null,
154
+ "temperature": 1.0,
155
+ "tf_legacy_loss": false,
156
+ "tie_encoder_decoder": false,
157
+ "tie_word_embeddings": true,
158
+ "tokenizer_class": null,
159
+ "top_k": 50,
160
+ "top_p": 1.0,
161
+ "torch_dtype": null,
162
+ "torchscript": false,
163
+ "type_vocab_size": 2,
164
+ "typical_p": 1.0,
165
+ "use_bfloat16": false,
166
+ "use_cache": true,
167
+ "vocab_size": 30522
168
+ },
169
+ "eos_token_id": 102,
170
+ "is_encoder_decoder": true,
171
+ "length_penalty": 2.0,
172
+ "max_length": 60,
173
+ "min_length": 10,
174
+ "model_type": "encoder-decoder",
175
+ "no_repeat_ngram_size": 3,
176
+ "num_beams": 4,
177
+ "pad_token_id": 0,
178
+ "torch_dtype": "float32",
179
+ "transformers_version": "4.40.1",
180
+ "vocab_size": 30522
181
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6da27ba15207d758659dcc538ffb672c95813619c3ec17715ea8a3eb2513fb6
3
+ size 989518784
runs/May05_08-53-36_b5f763934e05/events.out.tfevents.1714899217.b5f763934e05.1564.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:518f1a141973bc0ec69fa0674e24ae9eb516d533bc563be5a7a33c9524fdb693
3
+ size 9366
runs/May05_08-57-00_b5f763934e05/events.out.tfevents.1714899422.b5f763934e05.5214.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d53805d0f4e9578d870b7783813d89e4795db4eb5cc630440f79169193f056fa
3
+ size 9366
runs/May05_09-00-36_b5f763934e05/events.out.tfevents.1714899637.b5f763934e05.5214.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ea89a6f3dcd4a7493a8c5b4dbba186bcc43537b400891d90e418a2b3d7ccc54
3
+ size 8280
runs/May05_09-02-37_b5f763934e05/events.out.tfevents.1714899760.b5f763934e05.6969.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:817994a3d5eddf20b63d12990faabcf61e764b4ec74c5107e3cb4f181a311f0e
3
+ size 8280
runs/May05_09-17-34_b5f763934e05/events.out.tfevents.1714900656.b5f763934e05.11091.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14c4fded5e586f670ac7f2ef3adfd3bf5dbd0cf09dedd175a3b158e952779032
3
+ size 15528
runs/May05_10-24-00_b5f763934e05/events.out.tfevents.1714904640.b5f763934e05.11091.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d0c479521e1366d832f39a3fa912dbe831f37097124036a4013d401a75b0f61
3
+ size 9244
runs/May05_10-31-34_b5f763934e05/events.out.tfevents.1714905096.b5f763934e05.29877.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:080467986dba03b66118fab9e996b874d1b21d01fbaddcf0ee7088f156d3c4d2
3
+ size 9164
runs/May05_10-36-54_b5f763934e05/events.out.tfevents.1714905414.b5f763934e05.29877.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffa1dcbf0900ba6f2a6f85193d4ef22fc30594ca7a865f6c3717e6f27fee3fa2
3
+ size 9679
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 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": true,
48
+ "eos_token": "[SEP]",
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 512,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9224ad286ee6f8a84c1ce3cfdab0730d84f2b87a4d4c240bcfd4beaa56254e2
3
+ size 5112
vocab.txt ADDED
The diff for this file is too large to render. See raw diff