38 lines
997 B
YAML
38 lines
997 B
YAML
|
data_config:
|
||
|
|
train_file: train.jsonl
|
||
|
|
val_file: dev.jsonl
|
||
|
|
test_file: dev.jsonl
|
||
|
|
num_proc: 1
|
||
|
|
max_input_length: 256
|
||
|
|
max_output_length: 512
|
||
|
|
training_args:
|
||
|
|
# see `transformers.Seq2SeqTrainingArguments`
|
||
|
|
output_dir: ./output
|
||
|
|
max_steps: 3000
|
||
|
|
# needed to be fit for the dataset
|
||
|
|
learning_rate: 5e-5
|
||
|
|
# settings for data loading
|
||
|
|
per_device_train_batch_size: 1
|
||
|
|
dataloader_num_workers: 16
|
||
|
|
remove_unused_columns: false
|
||
|
|
# settings for saving checkpoints
|
||
|
|
save_strategy: steps
|
||
|
|
save_steps: 500
|
||
|
|
# settings for logging
|
||
|
|
log_level: info
|
||
|
|
logging_strategy: steps
|
||
|
|
logging_steps: 10
|
||
|
|
# settings for evaluation
|
||
|
|
per_device_eval_batch_size: 16
|
||
|
|
evaluation_strategy: steps
|
||
|
|
eval_steps: 500
|
||
|
|
# settings for optimizer
|
||
|
|
# adam_epsilon: 1e-6
|
||
|
|
# uncomment the following line to detect nan or inf values
|
||
|
|
# debug: underflow_overflow
|
||
|
|
predict_with_generate: true
|
||
|
|
generation_config:
|
||
|
|
max_new_tokens: 512
|
||
|
|
# set your absolute deepspeed path here
|
||
|
|
deepspeed: configs/ds_zero_3.json
|