model_family: olmo-7b | |
LoRA: | |
r: 0 | |
alpha: 32 | |
dropout: 0.05 | |
data_path: locuslab/TOFU | |
split: full | |
batch_size: 8 | |
gradient_accumulation_steps: 4 | |
num_epochs: 10 | |
lr: 9.0e-06 | |
seed: 42 | |
run_index: 1 | |
save_dir: paper_models/final_ft_noLORA_${num_epochs}_epochs_inst_lr${lr}_${model_family}_${split}_seed${seed}_${run_index}/ | |
weight_decay: 0.01 | |