Index

A

add_vocab_from_file() (in module train_tokenizer), [1]

B

block_size (run_clm.DataTrainingArguments attribute), [1]

C

cache_dir (run_clm.ModelArguments attribute), [1] (run_mlm.ModelArguments attribute), [1] (run_seq.ModelArguments attribute), [1] (run_tc.ModelArguments attribute), [1] config_name (run_clm.ModelArguments attribute), [1] (run_mlm.ModelArguments attribute), [1] (run_seq.ModelArguments attribute), [1] (run_tc.ModelArguments attribute), [1]

config_overrides (run_clm.ModelArguments attribute), [1] (run_mlm.ModelArguments attribute), [1] create_config module

D

dataset_config_name (run_clm.DataTrainingArguments attribute), [1] (run_mlm.DataTrainingArguments attribute), [1] (run_seq.DataTrainingArguments attribute), [1] (run_tc.DataTrainingArguments attribute), [1] dataset_name (run_clm.DataTrainingArguments attribute), [1] (run_mlm.DataTrainingArguments attribute), [1] (run_seq.DataTrainingArguments attribute), [1] (run_tc.DataTrainingArguments attribute), [1]

DataTrainingArguments (class in run_clm), [1] (class in run_mlm), [1] (class in run_seq), [1] (class in run_tc), [1]

E

early_stop (run_seq.TaskArguments attribute), [1] (run_tc.DataTrainingArguments attribute), [1]

F

freeze_token_embed (run_mlm.ModelArguments attribute), [1]

G

get_command_line_args() (in module tokenize_corpus) (in module train_tokenizer)

K

keep_linebreaks (run_clm.DataTrainingArguments attribute), [1] (run_mlm.DataTrainingArguments attribute), [1]

L

label_column_name (run_tc.DataTrainingArguments attribute), [1] line_by_line (run_clm.DataTrainingArguments attribute), [1] (run_mlm.DataTrainingArguments attribute), [1]

log_dir (run_seq.ModelArguments attribute), [1] (run_tc.ModelArguments attribute), [1]

M

main() (in module create_config) (in module run_clm), [1] (in module run_mlm), [1] (in module run_seq), [1] (in module run_tc), [1] (in module tokenize_corpus), [1] (in module train_tokenizer), [1] max_eval_samples (run_clm.DataTrainingArguments attribute), [1] (run_mlm.DataTrainingArguments attribute), [1] (run_seq.DataTrainingArguments attribute), [1] max_predict_samples (run_seq.DataTrainingArguments attribute), [1] max_seq_length (run_clm.DataTrainingArguments attribute), [1] (run_mlm.DataTrainingArguments attribute), [1] (run_seq.DataTrainingArguments attribute), [1] (run_tc.DataTrainingArguments attribute), [1] max_train_samples (run_clm.DataTrainingArguments attribute), [1] (run_mlm.DataTrainingArguments attribute), [1] (run_seq.DataTrainingArguments attribute), [1] mlm_probability (run_mlm.DataTrainingArguments attribute), [1] model_name_or_path (run_clm.ModelArguments attribute), [1] (run_mlm.ModelArguments attribute), [1] (run_seq.ModelArguments attribute), [1] (run_tc.ModelArguments attribute), [1]

model_revision (run_clm.ModelArguments attribute), [1] (run_mlm.ModelArguments attribute), [1] (run_seq.ModelArguments attribute), [1] model_type (run_clm.ModelArguments attribute), [1] (run_mlm.ModelArguments attribute), [1] ModelArguments (class in run_clm), [1] (class in run_mlm), [1] (class in run_seq), [1] (class in run_tc), [1] module create_config run_clm, [1] run_mlm, [1] run_seq, [1] run_tc, [1] tokenize_corpus, [1] train_tokenizer, [1]

O

overwrite_cache (run_clm.DataTrainingArguments attribute), [1] (run_mlm.DataTrainingArguments attribute), [1] (run_seq.DataTrainingArguments attribute), [1] (run_tc.DataTrainingArguments attribute), [1]

P

pad_to_max_length (run_clm.DataTrainingArguments attribute), [1] (run_mlm.DataTrainingArguments attribute), [1] (run_seq.DataTrainingArguments attribute), [1] (run_tc.DataTrainingArguments attribute), [1]

preprocessing_num_workers (run_clm.DataTrainingArguments attribute), [1] (run_mlm.DataTrainingArguments attribute), [1] (run_tc.DataTrainingArguments attribute), [1] pretrained_token_embed (run_mlm.ModelArguments attribute), [1]

R

read_txt_embeddings() (in module run_mlm), [1] run_clm module, [1] run_mlm module, [1]

run_seq module, [1] run_tc module, [1]

T

task (run_seq.TaskArguments attribute), [1] task_name (run_seq.DataTrainingArguments attribute), [1] (run_tc.DataTrainingArguments attribute), [1] TaskArguments (class in run_seq), [1] test_file (run_clm.DataTrainingArguments attribute), [1] (run_mlm.DataTrainingArguments attribute), [1] (run_seq.DataTrainingArguments attribute), [1] (run_tc.DataTrainingArguments attribute), [1] text_column_name (run_tc.DataTrainingArguments attribute), [1] tokenize_corpus module, [1]

tokenizer_name (run_clm.ModelArguments attribute), [1] (run_mlm.ModelArguments attribute), [1] (run_seq.ModelArguments attribute), [1] (run_tc.ModelArguments attribute), [1] train_file (run_clm.DataTrainingArguments attribute), [1] (run_mlm.DataTrainingArguments attribute), [1] (run_seq.DataTrainingArguments attribute), [1] (run_tc.DataTrainingArguments attribute), [1] train_tokenizer module, [1]

U

use_auth_token (run_clm.ModelArguments attribute), [1] (run_mlm.ModelArguments attribute), [1] (run_seq.ModelArguments attribute), [1] (run_tc.ModelArguments attribute), [1]

use_fast (run_tc.ModelArguments attribute), [1] use_fast_tokenizer (run_clm.ModelArguments attribute), [1] (run_mlm.ModelArguments attribute), [1] (run_seq.ModelArguments attribute), [1]

V

validation_file (run_clm.DataTrainingArguments attribute), [1] (run_mlm.DataTrainingArguments attribute), [1] (run_seq.DataTrainingArguments attribute), [1] (run_tc.DataTrainingArguments attribute), [1]

validation_split_percentage (run_clm.DataTrainingArguments attribute), [1] (run_mlm.DataTrainingArguments attribute), [1]