21 lines
579 B
YAML
21 lines
579 B
YAML
|
|
task_type: tldr
|
||
|
|
model_name: EleutherAI/pythia-410m-deduped
|
||
|
|
hub_model_id: mnoukhov/pythia410m-sft-tldr
|
||
|
|
push_to_hub: True
|
||
|
|
dataset_name: vwxyzjn/summarize_from_feedback_tldr_3_filtered_oai_preprocessing_1706381144
|
||
|
|
dataset_eval_split: validation
|
||
|
|
report_to: "wandb"
|
||
|
|
learning_rate: 3e-6
|
||
|
|
lr_scheduler_type: cosine
|
||
|
|
bf16: True
|
||
|
|
gradient_accumulation_steps: 4
|
||
|
|
per_device_train_batch_size: 32
|
||
|
|
per_device_eval_batch_size: 8
|
||
|
|
num_train_epochs: 1
|
||
|
|
max_seq_length: 580
|
||
|
|
gradient_checkpointing: False
|
||
|
|
evaluation_strategy: "steps"
|
||
|
|
eval_steps: 0.2
|
||
|
|
logging_steps: 100
|
||
|
|
ddp_find_unused_parameters: False
|