File size: 3,010 Bytes
f7f1668 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 |
config: null
print_config: false
log_level: INFO
dry_run: false
iterator_type: sequence
output_dir: exp/lm_train_bpe150
ngpu: 1
seed: 0
num_workers: 1
num_att_plot: 3
dist_backend: nccl
dist_init_method: env://
dist_world_size: null
dist_rank: null
local_rank: 0
dist_master_addr: null
dist_master_port: null
dist_launcher: null
multiprocessing_distributed: false
cudnn_enabled: true
cudnn_benchmark: false
cudnn_deterministic: true
collect_stats: false
write_collected_feats: false
max_epoch: 40
patience: null
val_scheduler_criterion:
- valid
- loss
early_stopping_criterion:
- valid
- loss
- min
best_model_criterion:
- - train
- loss
- min
- - valid
- loss
- min
- - train
- acc
- max
- - valid
- acc
- max
keep_nbest_models:
- 10
grad_clip: 5.0
grad_clip_type: 2.0
grad_noise: false
accum_grad: 1
no_forward_run: false
resume: true
train_dtype: float32
use_amp: false
log_interval: null
unused_parameters: false
use_tensorboard: true
use_wandb: false
wandb_project: null
wandb_id: null
pretrain_path: null
init_param: []
num_iters_per_epoch: null
batch_size: 20
valid_batch_size: null
batch_bins: 1000000
valid_batch_bins: null
train_shape_file:
- exp/lm_stats_bpe150/train/text_shape.bpe
valid_shape_file:
- exp/lm_stats_bpe150/valid/text_shape.bpe
batch_type: folded
valid_batch_type: null
fold_length:
- 150
sort_in_batch: descending
sort_batch: descending
multiple_iterator: false
chunk_length: 500
chunk_shift_ratio: 0.5
num_cache_chunks: 1024
train_data_path_and_name_and_type:
- - dump/raw/lm_train.txt
- text
- text
valid_data_path_and_name_and_type:
- - dump/raw/es_dev/text
- text
- text
allow_variable_data_keys: false
max_cache_size: 0.0
max_cache_fd: 32
valid_max_cache_size: null
optim: adadelta
optim_conf: {}
scheduler: null
scheduler_conf: {}
token_list:
- <blank>
- <unk>
- ▁
- s
- n
- r
- o
- a
- ▁de
- e
- l
- ▁a
- u
- ▁y
- ▁que
- ra
- ta
- do
- ▁la
- i
- ▁en
- re
- to
- ▁el
- d
- p
- da
- la
- c
- b
- t
- ro
- ó
- en
- ri
- g
- ba
- ▁se
- os
- er
- te
- ▁con
- ci
- ▁es
- es
- ▁no
- ▁su
- h
- ti
- é
- mo
- á
- ▁ca
- ▁ha
- na
- ▁los
- lo
- í
- ía
- de
- me
- ca
- ▁al
- le
- ce
- v
- ma
- nte
- ▁di
- ▁ma
- ▁por
- y
- di
- m
- ▁pa
- sa
- ▁si
- ▁pe
- gu
- z
- ▁mi
- ▁co
- ▁me
- ▁o
- ▁e
- ▁un
- tra
- ▁re
- li
- ▁f
- co
- ▁á
- ndo
- se
- mi
- ga
- ni
- ▁cu
- ▁le
- jo
- ▁ve
- mp
- bi
- f
- va
- ▁mu
- go
- ▁so
- ñ
- tu
- si
- ▁lo
- ▁pu
- ▁vi
- ▁b
- ▁las
- ▁c
- ▁sa
- za
- ▁del
- ▁po
- ▁in
- vi
- ▁te
- tro
- cia
- ▁una
- qui
- pi
- que
- ja
- pa
- ▁para
- cu
- pe
- ▁como
- ▁esta
- ve
- je
- lle
- x
- ú
- j
- q
- ''''
- k
- w
- ü
- '-'
- <sos/eos>
init: null
model_conf:
ignore_id: 0
use_preprocessor: true
token_type: bpe
bpemodel: data/token_list/bpe_unigram150/bpe.model
non_linguistic_symbols: null
cleaner: null
g2p: null
lm: seq_rnn
lm_conf: {}
required:
- output_dir
- token_list
distributed: false
|