noahkim commited on
Commit
d11626c
1 Parent(s): 726c4f1

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,191 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "/content/drive/MyDrive/project/kobigbird/first_model",
4
+ "add_cross_attention": true,
5
+ "architectures": [
6
+ "EncoderDecoderModel"
7
+ ],
8
+ "attention_type": "original_full",
9
+ "decoder": {
10
+ "_name_or_path": "monologg/kobigbird-bert-base",
11
+ "add_cross_attention": true,
12
+ "architectures": [
13
+ "BigBirdForMaskedLM"
14
+ ],
15
+ "attention_probs_dropout_prob": 0.1,
16
+ "attention_type": "block_sparse",
17
+ "bad_words_ids": null,
18
+ "block_size": 64,
19
+ "bos_token_id": 5,
20
+ "chunk_size_feed_forward": 0,
21
+ "classifier_dropout": null,
22
+ "cross_attention_hidden_size": null,
23
+ "decoder_start_token_id": null,
24
+ "diversity_penalty": 0.0,
25
+ "do_sample": false,
26
+ "early_stopping": false,
27
+ "encoder_no_repeat_ngram_size": 0,
28
+ "eos_token_id": 6,
29
+ "exponential_decay_length_penalty": null,
30
+ "finetuning_task": null,
31
+ "forced_bos_token_id": null,
32
+ "forced_eos_token_id": null,
33
+ "gradient_checkpointing": false,
34
+ "hidden_act": "gelu_new",
35
+ "hidden_dropout_prob": 0.1,
36
+ "hidden_size": 768,
37
+ "id2label": {
38
+ "0": "LABEL_0",
39
+ "1": "LABEL_1"
40
+ },
41
+ "initializer_range": 0.02,
42
+ "intermediate_size": 3072,
43
+ "is_decoder": true,
44
+ "is_encoder_decoder": false,
45
+ "label2id": {
46
+ "LABEL_0": 0,
47
+ "LABEL_1": 1
48
+ },
49
+ "layer_norm_eps": 1e-12,
50
+ "length_penalty": 1.0,
51
+ "max_length": 20,
52
+ "max_position_embeddings": 4096,
53
+ "min_length": 0,
54
+ "model_type": "big_bird",
55
+ "no_repeat_ngram_size": 0,
56
+ "num_attention_heads": 6,
57
+ "num_beam_groups": 1,
58
+ "num_beams": 1,
59
+ "num_hidden_layers": 6,
60
+ "num_random_blocks": 3,
61
+ "num_return_sequences": 1,
62
+ "output_attentions": false,
63
+ "output_hidden_states": false,
64
+ "output_scores": false,
65
+ "pad_token_id": 0,
66
+ "position_embedding_type": "absolute",
67
+ "prefix": null,
68
+ "problem_type": null,
69
+ "pruned_heads": {},
70
+ "remove_invalid_values": false,
71
+ "repetition_penalty": 1.0,
72
+ "rescale_embeddings": false,
73
+ "return_dict": true,
74
+ "return_dict_in_generate": false,
75
+ "sep_token_id": 3,
76
+ "task_specific_params": null,
77
+ "temperature": 1.0,
78
+ "tf_legacy_loss": false,
79
+ "tie_encoder_decoder": false,
80
+ "tie_word_embeddings": true,
81
+ "tokenizer_class": "BertTokenizer",
82
+ "top_k": 50,
83
+ "top_p": 1.0,
84
+ "torch_dtype": "float32",
85
+ "torchscript": false,
86
+ "transformers_version": "4.22.0",
87
+ "type_vocab_size": 2,
88
+ "typical_p": 1.0,
89
+ "use_bfloat16": false,
90
+ "use_bias": true,
91
+ "use_cache": true,
92
+ "vocab_size": 32500
93
+ },
94
+ "decoder_layers": 6,
95
+ "decoder_start_token_id": 2,
96
+ "encoder": {
97
+ "_name_or_path": "monologg/kobigbird-bert-base",
98
+ "add_cross_attention": false,
99
+ "architectures": [
100
+ "BigBirdForMaskedLM"
101
+ ],
102
+ "attention_probs_dropout_prob": 0.1,
103
+ "attention_type": "block_sparse",
104
+ "bad_words_ids": null,
105
+ "block_size": 64,
106
+ "bos_token_id": 5,
107
+ "chunk_size_feed_forward": 0,
108
+ "classifier_dropout": null,
109
+ "cross_attention_hidden_size": null,
110
+ "decoder_start_token_id": null,
111
+ "diversity_penalty": 0.0,
112
+ "do_sample": false,
113
+ "early_stopping": false,
114
+ "encoder_no_repeat_ngram_size": 0,
115
+ "eos_token_id": 6,
116
+ "exponential_decay_length_penalty": null,
117
+ "finetuning_task": null,
118
+ "forced_bos_token_id": null,
119
+ "forced_eos_token_id": null,
120
+ "gradient_checkpointing": false,
121
+ "hidden_act": "gelu_new",
122
+ "hidden_dropout_prob": 0.1,
123
+ "hidden_size": 768,
124
+ "id2label": {
125
+ "0": "LABEL_0",
126
+ "1": "LABEL_1"
127
+ },
128
+ "initializer_range": 0.02,
129
+ "intermediate_size": 3072,
130
+ "is_decoder": false,
131
+ "is_encoder_decoder": false,
132
+ "label2id": {
133
+ "LABEL_0": 0,
134
+ "LABEL_1": 1
135
+ },
136
+ "layer_norm_eps": 1e-12,
137
+ "length_penalty": 1.0,
138
+ "max_length": 20,
139
+ "max_position_embeddings": 4096,
140
+ "min_length": 0,
141
+ "model_type": "big_bird",
142
+ "no_repeat_ngram_size": 0,
143
+ "num_attention_heads": 6,
144
+ "num_beam_groups": 1,
145
+ "num_beams": 1,
146
+ "num_hidden_layers": 6,
147
+ "num_random_blocks": 3,
148
+ "num_return_sequences": 1,
149
+ "output_attentions": false,
150
+ "output_hidden_states": false,
151
+ "output_scores": false,
152
+ "pad_token_id": 0,
153
+ "position_embedding_type": "absolute",
154
+ "prefix": null,
155
+ "problem_type": null,
156
+ "pruned_heads": {},
157
+ "remove_invalid_values": false,
158
+ "repetition_penalty": 1.0,
159
+ "rescale_embeddings": false,
160
+ "return_dict": true,
161
+ "return_dict_in_generate": false,
162
+ "sep_token_id": 3,
163
+ "task_specific_params": null,
164
+ "temperature": 1.0,
165
+ "tf_legacy_loss": false,
166
+ "tie_encoder_decoder": false,
167
+ "tie_word_embeddings": true,
168
+ "tokenizer_class": "BertTokenizer",
169
+ "top_k": 50,
170
+ "top_p": 1.0,
171
+ "torch_dtype": "float32",
172
+ "torchscript": false,
173
+ "transformers_version": "4.22.0",
174
+ "type_vocab_size": 2,
175
+ "typical_p": 1.0,
176
+ "use_bfloat16": false,
177
+ "use_bias": true,
178
+ "use_cache": true,
179
+ "vocab_size": 32500
180
+ },
181
+ "encoder_layers": 6,
182
+ "is_decoder": true,
183
+ "is_encoder_decoder": true,
184
+ "model_type": "encoder-decoder",
185
+ "num_attention_heads": 6,
186
+ "num_hidden_layers": 6,
187
+ "pad_token_id": 0,
188
+ "torch_dtype": "float32",
189
+ "transformers_version": null,
190
+ "vocab_size": 32500
191
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a8174fb743257f418a6305b19bb7dbd39fa44535b0cacd853ac1d66ed79daff
3
+ size 629203807
runs/Sep15_12-14-23_97a42aa1933d/1663244073.9787056/events.out.tfevents.1663244073.97a42aa1933d.79.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a9a7b2643cb503f19d5f77dd0fb9fba74e5785582d901f90753793047a18c72
3
+ size 5810
runs/Sep15_12-14-23_97a42aa1933d/events.out.tfevents.1663244073.97a42aa1933d.79.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4092da1873352e7ac816e3ee2622e4182271303b444993f8a10a1731bc7f837f
3
+ size 8689
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "</s>",
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 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": false,
6
+ "eos_token": "</s>",
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 4096,
9
+ "name_or_path": "/content/drive/MyDrive/project/kobigbird/first_model",
10
+ "never_split": null,
11
+ "pad_token": "[PAD]",
12
+ "sep_token": "[SEP]",
13
+ "special_tokens_map_file": "/root/.cache/huggingface/hub/models--monologg--kobigbird-bert-base/snapshots/ceacda477e20abef2c929adfa4a07c6f811323be/special_tokens_map.json",
14
+ "strip_accents": null,
15
+ "tokenize_chinese_chars": true,
16
+ "tokenizer_class": "BertTokenizer",
17
+ "unk_token": "[UNK]"
18
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c56219765e2b892daf6010000c5bb4b5dbf4eb6ccbb64845394bbad3b4a3353
3
+ size 3567
vocab.txt ADDED
The diff for this file is too large to render. See raw diff