Atharvgarg commited on
Commit
9a55fff
1 Parent(s): 8daea50

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,176 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "tf_legacy_loss": false,
70
+ "tie_encoder_decoder": false,
71
+ "tie_word_embeddings": true,
72
+ "tokenizer_class": null,
73
+ "top_k": 50,
74
+ "top_p": 1.0,
75
+ "torch_dtype": null,
76
+ "torchscript": false,
77
+ "transformers_version": "4.21.0",
78
+ "type_vocab_size": 2,
79
+ "typical_p": 1.0,
80
+ "use_bfloat16": false,
81
+ "use_cache": true,
82
+ "vocab_size": 30522
83
+ },
84
+ "decoder_start_token_id": 101,
85
+ "early_stopping": true,
86
+ "encoder": {
87
+ "_name_or_path": "google/bert_uncased_L-4_H-512_A-8",
88
+ "add_cross_attention": false,
89
+ "architectures": null,
90
+ "attention_probs_dropout_prob": 0.1,
91
+ "bad_words_ids": null,
92
+ "bos_token_id": null,
93
+ "chunk_size_feed_forward": 0,
94
+ "classifier_dropout": null,
95
+ "cross_attention_hidden_size": null,
96
+ "decoder_start_token_id": null,
97
+ "diversity_penalty": 0.0,
98
+ "do_sample": false,
99
+ "early_stopping": false,
100
+ "encoder_no_repeat_ngram_size": 0,
101
+ "eos_token_id": null,
102
+ "exponential_decay_length_penalty": null,
103
+ "finetuning_task": null,
104
+ "forced_bos_token_id": null,
105
+ "forced_eos_token_id": null,
106
+ "gradient_checkpointing": false,
107
+ "hidden_act": "gelu",
108
+ "hidden_dropout_prob": 0.1,
109
+ "hidden_size": 512,
110
+ "id2label": {
111
+ "0": "LABEL_0",
112
+ "1": "LABEL_1"
113
+ },
114
+ "initializer_range": 0.02,
115
+ "intermediate_size": 2048,
116
+ "is_decoder": false,
117
+ "is_encoder_decoder": false,
118
+ "label2id": {
119
+ "LABEL_0": 0,
120
+ "LABEL_1": 1
121
+ },
122
+ "layer_norm_eps": 1e-12,
123
+ "length_penalty": 1.0,
124
+ "max_length": 20,
125
+ "max_position_embeddings": 512,
126
+ "min_length": 0,
127
+ "model_type": "bert",
128
+ "no_repeat_ngram_size": 0,
129
+ "num_attention_heads": 8,
130
+ "num_beam_groups": 1,
131
+ "num_beams": 1,
132
+ "num_hidden_layers": 4,
133
+ "num_return_sequences": 1,
134
+ "output_attentions": false,
135
+ "output_hidden_states": false,
136
+ "output_scores": false,
137
+ "pad_token_id": 0,
138
+ "position_embedding_type": "absolute",
139
+ "prefix": null,
140
+ "problem_type": null,
141
+ "pruned_heads": {},
142
+ "remove_invalid_values": false,
143
+ "repetition_penalty": 1.0,
144
+ "return_dict": false,
145
+ "return_dict_in_generate": false,
146
+ "sep_token_id": null,
147
+ "task_specific_params": null,
148
+ "temperature": 1.0,
149
+ "tf_legacy_loss": false,
150
+ "tie_encoder_decoder": false,
151
+ "tie_word_embeddings": true,
152
+ "tokenizer_class": null,
153
+ "top_k": 50,
154
+ "top_p": 1.0,
155
+ "torch_dtype": null,
156
+ "torchscript": false,
157
+ "transformers_version": "4.21.0",
158
+ "type_vocab_size": 2,
159
+ "typical_p": 1.0,
160
+ "use_bfloat16": false,
161
+ "use_cache": true,
162
+ "vocab_size": 30522
163
+ },
164
+ "eos_token_id": 102,
165
+ "is_encoder_decoder": true,
166
+ "length_penalty": 2.0,
167
+ "max_length": 142,
168
+ "min_length": 56,
169
+ "model_type": "encoder-decoder",
170
+ "no_repeat_ngram_size": 3,
171
+ "num_beams": 4,
172
+ "pad_token_id": 0,
173
+ "torch_dtype": "float32",
174
+ "transformers_version": null,
175
+ "vocab_size": 30522
176
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3700d25cb86eaf2cc6f272a8b72d970d9f057a1c16c0492e0f5aa2db2229df6
3
+ size 247133387
runs/Jul28_14-36-59_80eb4c1f0e3d/1659019059.2927492/events.out.tfevents.1659019059.80eb4c1f0e3d.71.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8066d864f8fd95f1841c022614154a6ad500610485d923486c7f7999cd5b3cd6
3
+ size 5828
runs/Jul28_14-36-59_80eb4c1f0e3d/events.out.tfevents.1659019059.80eb4c1f0e3d.71.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a20b515ba43849f69f47ac3d1ebbb19720ed710a7d09310e24d0b4f6e1627335
3
+ size 9420
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 sha256:30181a6b9d531616ab0ab87803a25ec48260b80ad33ee03382bf9db0fd183381
3
+ size 3567
vocab.txt ADDED
The diff for this file is too large to render. See raw diff