leadawon commited on
Commit
f6a975d
1 Parent(s): 64fa447

Training in progress, epoch 0

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,188 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "architectures": [
4
+ "EncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_name_or_path": "skt/kogpt2-base-v2",
8
+ "_num_labels": 1,
9
+ "activation_function": "gelu_new",
10
+ "add_cross_attention": true,
11
+ "architectures": [
12
+ "GPT2LMHeadModel"
13
+ ],
14
+ "attn_pdrop": 0.1,
15
+ "author": "Heewon Jeon(madjakarta@gmail.com)",
16
+ "bad_words_ids": null,
17
+ "begin_suppress_tokens": null,
18
+ "bos_token_id": 0,
19
+ "chunk_size_feed_forward": 0,
20
+ "created_date": "2021-04-28",
21
+ "cross_attention_hidden_size": null,
22
+ "decoder_start_token_id": null,
23
+ "diversity_penalty": 0.0,
24
+ "do_sample": false,
25
+ "early_stopping": false,
26
+ "embd_pdrop": 0.1,
27
+ "encoder_no_repeat_ngram_size": 0,
28
+ "eos_token_id": 1,
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
+ "id2label": {
35
+ "0": "LABEL_0"
36
+ },
37
+ "initializer_range": 0.02,
38
+ "is_decoder": true,
39
+ "is_encoder_decoder": false,
40
+ "label2id": {
41
+ "LABEL_0": 0
42
+ },
43
+ "layer_norm_epsilon": 1e-05,
44
+ "length_penalty": 1.0,
45
+ "license": "CC-BY-NC-SA 4.0",
46
+ "max_length": 20,
47
+ "min_length": 0,
48
+ "model_type": "gpt2",
49
+ "n_ctx": 1024,
50
+ "n_embd": 768,
51
+ "n_head": 12,
52
+ "n_inner": null,
53
+ "n_layer": 12,
54
+ "n_positions": 1024,
55
+ "no_repeat_ngram_size": 0,
56
+ "num_beam_groups": 1,
57
+ "num_beams": 1,
58
+ "num_return_sequences": 1,
59
+ "output_attentions": false,
60
+ "output_hidden_states": false,
61
+ "output_scores": false,
62
+ "pad_token_id": 3,
63
+ "prefix": null,
64
+ "problem_type": null,
65
+ "pruned_heads": {},
66
+ "remove_invalid_values": false,
67
+ "reorder_and_upcast_attn": false,
68
+ "repetition_penalty": 1.0,
69
+ "resid_pdrop": 0.1,
70
+ "return_dict": true,
71
+ "return_dict_in_generate": false,
72
+ "scale_attn_by_inverse_layer_idx": false,
73
+ "scale_attn_weights": true,
74
+ "sep_token_id": null,
75
+ "summary_activation": null,
76
+ "summary_first_dropout": 0.1,
77
+ "summary_proj_to_labels": true,
78
+ "summary_type": "cls_index",
79
+ "summary_use_proj": true,
80
+ "suppress_tokens": null,
81
+ "task_specific_params": {
82
+ "text-generation": {
83
+ "do_sample": true,
84
+ "max_length": 50
85
+ }
86
+ },
87
+ "temperature": 1.0,
88
+ "tf_legacy_loss": false,
89
+ "tie_encoder_decoder": false,
90
+ "tie_word_embeddings": true,
91
+ "tokenizer_class": null,
92
+ "top_k": 50,
93
+ "top_p": 1.0,
94
+ "torch_dtype": null,
95
+ "torchscript": false,
96
+ "transformers_version": "4.26.0",
97
+ "typical_p": 1.0,
98
+ "use_bfloat16": false,
99
+ "use_cache": true,
100
+ "vocab_size": 51200
101
+ },
102
+ "decoder_start_token_id": 1,
103
+ "encoder": {
104
+ "_name_or_path": "monologg/distilkobert",
105
+ "activation": "gelu",
106
+ "add_cross_attention": false,
107
+ "architectures": [
108
+ "DistilBertForMaskedLM"
109
+ ],
110
+ "attention_dropout": 0.1,
111
+ "bad_words_ids": null,
112
+ "begin_suppress_tokens": null,
113
+ "bos_token_id": null,
114
+ "chunk_size_feed_forward": 0,
115
+ "cross_attention_hidden_size": null,
116
+ "decoder_start_token_id": null,
117
+ "dim": 768,
118
+ "diversity_penalty": 0.0,
119
+ "do_sample": false,
120
+ "dropout": 0.1,
121
+ "early_stopping": false,
122
+ "encoder_no_repeat_ngram_size": 0,
123
+ "eos_token_id": null,
124
+ "exponential_decay_length_penalty": null,
125
+ "finetuning_task": null,
126
+ "forced_bos_token_id": null,
127
+ "forced_eos_token_id": null,
128
+ "hidden_dim": 3072,
129
+ "id2label": {
130
+ "0": "LABEL_0",
131
+ "1": "LABEL_1"
132
+ },
133
+ "initializer_range": 0.02,
134
+ "is_decoder": false,
135
+ "is_encoder_decoder": false,
136
+ "label2id": {
137
+ "LABEL_0": 0,
138
+ "LABEL_1": 1
139
+ },
140
+ "length_penalty": 1.0,
141
+ "max_length": 20,
142
+ "max_position_embeddings": 512,
143
+ "min_length": 0,
144
+ "model_type": "distilbert",
145
+ "n_heads": 12,
146
+ "n_layers": 3,
147
+ "no_repeat_ngram_size": 0,
148
+ "num_beam_groups": 1,
149
+ "num_beams": 1,
150
+ "num_return_sequences": 1,
151
+ "output_attentions": false,
152
+ "output_hidden_states": false,
153
+ "output_scores": false,
154
+ "pad_token_id": 1,
155
+ "prefix": null,
156
+ "problem_type": null,
157
+ "pruned_heads": {},
158
+ "qa_dropout": 0.1,
159
+ "remove_invalid_values": false,
160
+ "repetition_penalty": 1.0,
161
+ "return_dict": true,
162
+ "return_dict_in_generate": false,
163
+ "sep_token_id": null,
164
+ "seq_classif_dropout": 0.2,
165
+ "sinusoidal_pos_embds": false,
166
+ "suppress_tokens": null,
167
+ "task_specific_params": null,
168
+ "temperature": 1.0,
169
+ "tf_legacy_loss": false,
170
+ "tie_encoder_decoder": false,
171
+ "tie_weights_": true,
172
+ "tie_word_embeddings": true,
173
+ "tokenizer_class": null,
174
+ "top_k": 50,
175
+ "top_p": 1.0,
176
+ "torch_dtype": null,
177
+ "torchscript": false,
178
+ "transformers_version": "4.26.0",
179
+ "typical_p": 1.0,
180
+ "use_bfloat16": false,
181
+ "vocab_size": 8002
182
+ },
183
+ "is_encoder_decoder": true,
184
+ "model_type": "encoder-decoder",
185
+ "pad_token_id": 1,
186
+ "torch_dtype": "float32",
187
+ "transformers_version": null
188
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3502c22dffb35a6810a8f4ca753405ec39c68a610b7727369ed8a8c37c7b15b3
3
+ size 750621677
runs/Jan25_07-07-10_8a7adde25dec/1674630449.024348/events.out.tfevents.1674630449.8a7adde25dec.6142.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2a45315cb23fac68e47f5bd2926816a81074d785f9a720d756e18ed3450f7cd
3
+ size 5903
runs/Jan25_07-07-10_8a7adde25dec/events.out.tfevents.1674630449.8a7adde25dec.6142.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:368bff9ada570cd03e8c439ec6ef26f0f6f55cf55ea3e98c73023db23af22bf8
3
+ size 9421
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fcb81ee858c72071f475200055a50a2a786b68000223a205dc786749a9581d5
3
+ size 3643