Training in progress, step 500
Browse files
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,189 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_commit_hash": "c8c9de0433014fb8e460998634b33874ec01632e",
|
3 |
+
"_name_or_path": "leadawon/ko-jeolla-nmt-v1",
|
4 |
+
"architectures": [
|
5 |
+
"EncoderDecoderModel"
|
6 |
+
],
|
7 |
+
"decoder": {
|
8 |
+
"_name_or_path": "skt/kogpt2-base-v2",
|
9 |
+
"_num_labels": 1,
|
10 |
+
"activation_function": "gelu_new",
|
11 |
+
"add_cross_attention": true,
|
12 |
+
"architectures": [
|
13 |
+
"GPT2LMHeadModel"
|
14 |
+
],
|
15 |
+
"attn_pdrop": 0.1,
|
16 |
+
"author": "Heewon Jeon(madjakarta@gmail.com)",
|
17 |
+
"bad_words_ids": null,
|
18 |
+
"begin_suppress_tokens": null,
|
19 |
+
"bos_token_id": 0,
|
20 |
+
"chunk_size_feed_forward": 0,
|
21 |
+
"created_date": "2021-04-28",
|
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 |
+
"embd_pdrop": 0.1,
|
28 |
+
"encoder_no_repeat_ngram_size": 0,
|
29 |
+
"eos_token_id": 1,
|
30 |
+
"exponential_decay_length_penalty": null,
|
31 |
+
"finetuning_task": null,
|
32 |
+
"forced_bos_token_id": null,
|
33 |
+
"forced_eos_token_id": null,
|
34 |
+
"gradient_checkpointing": false,
|
35 |
+
"id2label": {
|
36 |
+
"0": "LABEL_0"
|
37 |
+
},
|
38 |
+
"initializer_range": 0.02,
|
39 |
+
"is_decoder": true,
|
40 |
+
"is_encoder_decoder": false,
|
41 |
+
"label2id": {
|
42 |
+
"LABEL_0": 0
|
43 |
+
},
|
44 |
+
"layer_norm_epsilon": 1e-05,
|
45 |
+
"length_penalty": 1.0,
|
46 |
+
"license": "CC-BY-NC-SA 4.0",
|
47 |
+
"max_length": 20,
|
48 |
+
"min_length": 0,
|
49 |
+
"model_type": "gpt2",
|
50 |
+
"n_ctx": 1024,
|
51 |
+
"n_embd": 768,
|
52 |
+
"n_head": 12,
|
53 |
+
"n_inner": null,
|
54 |
+
"n_layer": 12,
|
55 |
+
"n_positions": 1024,
|
56 |
+
"no_repeat_ngram_size": 0,
|
57 |
+
"num_beam_groups": 1,
|
58 |
+
"num_beams": 1,
|
59 |
+
"num_return_sequences": 1,
|
60 |
+
"output_attentions": false,
|
61 |
+
"output_hidden_states": false,
|
62 |
+
"output_scores": false,
|
63 |
+
"pad_token_id": 3,
|
64 |
+
"prefix": null,
|
65 |
+
"problem_type": null,
|
66 |
+
"pruned_heads": {},
|
67 |
+
"remove_invalid_values": false,
|
68 |
+
"reorder_and_upcast_attn": false,
|
69 |
+
"repetition_penalty": 1.0,
|
70 |
+
"resid_pdrop": 0.1,
|
71 |
+
"return_dict": true,
|
72 |
+
"return_dict_in_generate": false,
|
73 |
+
"scale_attn_by_inverse_layer_idx": false,
|
74 |
+
"scale_attn_weights": true,
|
75 |
+
"sep_token_id": null,
|
76 |
+
"summary_activation": null,
|
77 |
+
"summary_first_dropout": 0.1,
|
78 |
+
"summary_proj_to_labels": true,
|
79 |
+
"summary_type": "cls_index",
|
80 |
+
"summary_use_proj": true,
|
81 |
+
"suppress_tokens": null,
|
82 |
+
"task_specific_params": {
|
83 |
+
"text-generation": {
|
84 |
+
"do_sample": true,
|
85 |
+
"max_length": 50
|
86 |
+
}
|
87 |
+
},
|
88 |
+
"temperature": 1.0,
|
89 |
+
"tf_legacy_loss": false,
|
90 |
+
"tie_encoder_decoder": false,
|
91 |
+
"tie_word_embeddings": true,
|
92 |
+
"tokenizer_class": null,
|
93 |
+
"top_k": 50,
|
94 |
+
"top_p": 1.0,
|
95 |
+
"torch_dtype": null,
|
96 |
+
"torchscript": false,
|
97 |
+
"transformers_version": "4.26.0",
|
98 |
+
"typical_p": 1.0,
|
99 |
+
"use_bfloat16": false,
|
100 |
+
"use_cache": true,
|
101 |
+
"vocab_size": 51200
|
102 |
+
},
|
103 |
+
"decoder_start_token_id": 1,
|
104 |
+
"encoder": {
|
105 |
+
"_name_or_path": "monologg/distilkobert",
|
106 |
+
"activation": "gelu",
|
107 |
+
"add_cross_attention": false,
|
108 |
+
"architectures": [
|
109 |
+
"DistilBertForMaskedLM"
|
110 |
+
],
|
111 |
+
"attention_dropout": 0.1,
|
112 |
+
"bad_words_ids": null,
|
113 |
+
"begin_suppress_tokens": null,
|
114 |
+
"bos_token_id": null,
|
115 |
+
"chunk_size_feed_forward": 0,
|
116 |
+
"cross_attention_hidden_size": null,
|
117 |
+
"decoder_start_token_id": null,
|
118 |
+
"dim": 768,
|
119 |
+
"diversity_penalty": 0.0,
|
120 |
+
"do_sample": false,
|
121 |
+
"dropout": 0.1,
|
122 |
+
"early_stopping": false,
|
123 |
+
"encoder_no_repeat_ngram_size": 0,
|
124 |
+
"eos_token_id": null,
|
125 |
+
"exponential_decay_length_penalty": null,
|
126 |
+
"finetuning_task": null,
|
127 |
+
"forced_bos_token_id": null,
|
128 |
+
"forced_eos_token_id": null,
|
129 |
+
"hidden_dim": 3072,
|
130 |
+
"id2label": {
|
131 |
+
"0": "LABEL_0",
|
132 |
+
"1": "LABEL_1"
|
133 |
+
},
|
134 |
+
"initializer_range": 0.02,
|
135 |
+
"is_decoder": false,
|
136 |
+
"is_encoder_decoder": false,
|
137 |
+
"label2id": {
|
138 |
+
"LABEL_0": 0,
|
139 |
+
"LABEL_1": 1
|
140 |
+
},
|
141 |
+
"length_penalty": 1.0,
|
142 |
+
"max_length": 20,
|
143 |
+
"max_position_embeddings": 512,
|
144 |
+
"min_length": 0,
|
145 |
+
"model_type": "distilbert",
|
146 |
+
"n_heads": 12,
|
147 |
+
"n_layers": 3,
|
148 |
+
"no_repeat_ngram_size": 0,
|
149 |
+
"num_beam_groups": 1,
|
150 |
+
"num_beams": 1,
|
151 |
+
"num_return_sequences": 1,
|
152 |
+
"output_attentions": false,
|
153 |
+
"output_hidden_states": false,
|
154 |
+
"output_scores": false,
|
155 |
+
"pad_token_id": 1,
|
156 |
+
"prefix": null,
|
157 |
+
"problem_type": null,
|
158 |
+
"pruned_heads": {},
|
159 |
+
"qa_dropout": 0.1,
|
160 |
+
"remove_invalid_values": false,
|
161 |
+
"repetition_penalty": 1.0,
|
162 |
+
"return_dict": true,
|
163 |
+
"return_dict_in_generate": false,
|
164 |
+
"sep_token_id": null,
|
165 |
+
"seq_classif_dropout": 0.2,
|
166 |
+
"sinusoidal_pos_embds": false,
|
167 |
+
"suppress_tokens": null,
|
168 |
+
"task_specific_params": null,
|
169 |
+
"temperature": 1.0,
|
170 |
+
"tf_legacy_loss": false,
|
171 |
+
"tie_encoder_decoder": false,
|
172 |
+
"tie_weights_": true,
|
173 |
+
"tie_word_embeddings": true,
|
174 |
+
"tokenizer_class": null,
|
175 |
+
"top_k": 50,
|
176 |
+
"top_p": 1.0,
|
177 |
+
"torch_dtype": null,
|
178 |
+
"torchscript": false,
|
179 |
+
"transformers_version": "4.26.0",
|
180 |
+
"typical_p": 1.0,
|
181 |
+
"use_bfloat16": false,
|
182 |
+
"vocab_size": 8002
|
183 |
+
},
|
184 |
+
"is_encoder_decoder": true,
|
185 |
+
"model_type": "encoder-decoder",
|
186 |
+
"pad_token_id": 1,
|
187 |
+
"torch_dtype": "float32",
|
188 |
+
"transformers_version": null
|
189 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71e5c086d20ff8bfbfd4816631d6c8ad360a854c5673db24149e386187a7b36c
|
3 |
+
size 750621677
|
runs/Jan25_05-36-46_c4c18458ac21/1674625019.3601708/events.out.tfevents.1674625019.c4c18458ac21.359.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:26f9fcb5f2090d464043c051f81ea305d2968c0e9e0b6116fa2896d120cd6ffb
|
3 |
+
size 5906
|
runs/Jan25_05-36-46_c4c18458ac21/events.out.tfevents.1674625019.c4c18458ac21.359.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6caea4a35c3b00248f4df326316a3c9f09891af24987047335099f9c6145462d
|
3 |
+
size 8801
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35052b2bd6408d2e05c9d14579f757c82aa1cbf435b2581161f666359f48c613
|
3 |
+
size 3643
|