This commit is contained in:
51616 2025-06-12 10:00:41 +00:00
parent 6af69e2d8e
commit eb87612f91

View file

@ -147,10 +147,10 @@ run python run_eval.py --checkpoint_path train_outputs/runs/.../pytorch_model.bi
uv run python run_eval.py --checkpoint_path train_outputs/runs/May08_13-56-31_slurm0-a3nodeset-5_59383_906acb28/checkpoint-105000/pytorch_model.bin --datasets negative_nq triviaqa_retrieved squad longbench_e --split test
# base model
uv run python run_eval.py --model_name_or_path google/gemma-2-2b-it --datasets longbench_e --split test
uv run python run_eval.py --model_name_or_path google/gemma-2-2b-it --datasets negative_nq triviaqa_retrieved squad longbench_e --split test
# base model w/o context
run uv run python run_eval.py --model_name_or_path google/gemma-2-2b-it --datasets longbench_e --split test --remove_context
run uv run python run_eval.py --model_name_or_path google/gemma-2-2b-it --datasets negative_nq triviaqa_retrieved squad longbench_e --split test --remove_context
# # benchmark
# cd LongBench/LongBench