From 5d793e329b24b9ebd444d1f9611f1b6493272046 Mon Sep 17 00:00:00 2001 From: 51616 Date: Tue, 3 Jun 2025 14:29:04 +0000 Subject: [PATCH] cmd readme --- README.md | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/README.md b/README.md index 939a315..9165c17 100644 --- a/README.md +++ b/README.md @@ -33,11 +33,13 @@ print(model.decode(outputs)) ```bash WANDB_MODE=disabled uv run python intx_sft.py configs/context_numbers_10.yaml --model_name_or_path=meta-llama/Llama-3.2-1B-Instruct --num_train_epochs=100 --per_device_train_batch_size=64 --per_device_eval_batch_size=64 --exp_setup=hyper_lora --aggregator_type=perceiver --target_modules=down_proj --per_rank_gen=True --per_layer_processing=True --decoder_depth=2 --seed=1 --gen_lora_l1_reg_coef=0 --use_token_mixing=False --lora_r=8 --bf16=True --tf32=True --dataloader_num_workers=8 --dataloader_prefetch_factor=8 ``` + ### PwC + Hotpot training (for testing/debugging) ```bash -uv run intx_sft.py configs/pwc_hotpot_qa.yaml \ +WANDB_MODE=disabled uv run intx_sft.py configs/pwc_hotpot_qa.yaml \ --model_name_or_path=google/gemma-2-2b-it --num_train_epochs=1 --per_device_train_batch_size=32 \ ---gradient_accumulation_steps=1 --per_device_eval_batch_size=32 --exp_setup=hyper_lora --aggregator_type=perceiver \ +--gradient_accumulation_steps=1 --per_device_eval_batch_size=32 --exp_setup=hyper_lora \ +--aggregator_type=perceiver \ --target_modules=down_proj \ --num_self_attends_per_block=4 --num_latent_factor=2 \ --lora_r=8 \ @@ -116,18 +118,16 @@ run python intx_sft.py configs/...yaml ... --from_pretrained_checkpoint=train_ou LongBench ```bash # generative -run python src/ctx_to_lora/eval.py --checkpoint_path train_outputs/runs/.../pytorch_model.bin --datasets negative_nq triviaqa_retrieved squad longbench_e --split test +run python run_eval.py --checkpoint_path train_outputs/runs/.../pytorch_model.bin --datasets negative_nq triviaqa_retrieved squad longbench_e --split test # hypernet checkpoint -uv run python 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 +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 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 longbench_e --split test # base model w/o context -run uv run python eval.py --model_name_or_path google/gemma-2-2b-it --datasets longbench_e --split test --remove_context - -# run python src/ctx_to_lora/eval.py --checkpoint_path train_outputs/runs/May08_13-56-31_slurm0-a3nodeset-5_59383_906acb28/checkpoint-105000/pytorch_model.bin +run uv run python run_eval.py --model_name_or_path google/gemma-2-2b-it --datasets longbench_e --split test --remove_context # # benchmark # cd LongBench/LongBench