Spaces:
Sleeping
Sleeping
File size: 2,008 Bytes
6faf7e7 |
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 |
session_name: base-baseline-encoder
data_directory: "data"
data_type: "CA_MSA"
log_directory: "log_dir"
load_training_data: true
load_test_data: false
load_validation_data: true
n_training_examples: null # null load all training examples, good for fast loading
n_test_examples: null # null load all test examples
n_validation_examples: null # null load all validation examples
test_file_name: "test.csv"
is_data_preprocessed: false # The data file is organized as (original text | text | diacritics)
data_separator: '|' # Required if the data already processed
diacritics_separator: '*' # Required if the data already processed
text_encoder: ArabicEncoderWithStartSymbol
text_cleaner: valid_arabic_cleaners # a white list that uses only Arabic letters, punctuations, and a space
max_len: 600 # sentences larger than this size will not be used
max_steps: 2_000_000
learning_rate: 0.001
batch_size: 16
adam_beta1: 0.9
adam_beta2: 0.999
use_decay: true
weight_decay: 0.0
encoder_embedding_dim: 256
decoder_embedding_dim: 256
encoder_dim: 512 # used by the decoder
encoder_units: [256, 256, 256]
use_batch_norm: true
decoder_units: 256
decoder_layers: 2
attention_units: 256
use_decoder_prenet: true
teacher_forcing_probability: 0.0
decoder_prenet_depth: [256, 128]
is_attention_accumulative: true
attention_type: LocationSensitive
use_mixed_precision: false
optimizer_type: Adam
text_encoder: ArabicEncoderWithStartSymbol
text_cleaner: null
device: cuda
# LOGGING
evaluate_frequency: 5000
evaluate_with_error_rates_frequency: 5000
n_predicted_text_tensorboard: 10 # To be written to the tensorboard
model_save_frequency: 5000
train_plotting_frequency: 1000
n_steps_avg_losses: [100, 500, 1_000, 5_000] # command line display of average loss values for the last n steps
error_rates_n_batches: 10000 # if calculating error rate is slow, then you can specify the number of batches to be calculated
test_model_path: null # load the last saved model
train_resume_model_path: null # load last saved model
|