25 lines
553 B
YAML
25 lines
553 B
YAML
|
|
train_split: train[:1000]
|
||
|
|
eval_split: validation[:10]
|
||
|
|
##
|
||
|
|
model_name: vwxyzjn/EleutherAI_pythia-1b-deduped__sft__tldr
|
||
|
|
model_revision: sft__55513__1706646024
|
||
|
|
dataset_name: vwxyzjn/summarize_from_feedback_oai_preprocessing_1706381144
|
||
|
|
prompt_field: query
|
||
|
|
gold_eval: ppl
|
||
|
|
beta: 0.5
|
||
|
|
num_train_epochs: 3
|
||
|
|
eval_steps: 750
|
||
|
|
load_in_8bit: False
|
||
|
|
bf16: False
|
||
|
|
fp16: True
|
||
|
|
learning_rate: 1e-5
|
||
|
|
use_peft: True
|
||
|
|
lora_r: 8
|
||
|
|
lora_alpha: 32
|
||
|
|
lora_dropout: 0.05
|
||
|
|
gradient_accumulation_steps: 4
|
||
|
|
per_device_train_batch_size: 4
|
||
|
|
warmup_steps: 150
|
||
|
|
save_steps: 100
|
||
|
|
eval_first_step: False
|