apunkt/doc-to-lora
1
0
Fork 0
mirror of https://github.com/SakanaAI/doc-to-lora.git synced 2026-07-23 17:01:04 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

chunked eval + backward compat model load

Browse source
This commit is contained in:
51616 2025-08-12 07:58:36 +00:00
parent 654ddc5b23
commit 996b89b5a0
3 changed files with 18 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
README.md
View file

@ -201,7 +201,7 @@ LongBench
WANDB_MODE=disabled uv 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
WANDB_MODE=disabled 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
WANDB_MODE=disabled run uv run python run_eval.py --checkpoint_path train_outputs/runs/Aug02_07-51-08_slurm0-a3nodeset-9_76501_7fdab5ea/checkpoint-50000/pytorch_model.bin --datasets squad ropes drop longbench/gov_report_e longbench/multifieldqa_en_e longbench/2wikimqa_e --split test --max_ctx_chunk_len -1 --lora_aggregation sum --eval_batch_size_gen 8
# squad only
WANDB_MODE=disabled run uv run python run_eval.py --checkpoint_path train_outputs/runs/Aug02_07-51-08_slurm0-a3nodeset-9_76501_7fdab5ea/checkpoint-50000/pytorch_model.bin --datasets squad --split test

15
eval_scripts/chunked_eval.sh Normal file
View file

@ -0,0 +1,15 @@
WANDB_MODE=disabled run uv run python run_eval.py --checkpoint_path train_outputs/runs/Aug02_07-51-08_slurm0-a3nodeset-9_76501_7fdab5ea/checkpoint-50000/pytorch_model.bin --datasets squad ropes drop longbench/squad_e longbench/gov_report_e test_longbench/multifieldqa_en_e --split test --max_ctx_chunk_len -1 --lora_aggregation mean
WANDB_MODE=disabled run uv run python run_eval.py --checkpoint_path train_outputs/runs/Aug02_07-51-08_slurm0-a3nodeset-9_76501_7fdab5ea/checkpoint-50000/pytorch_model.bin --datasets squad ropes drop longbench/squad_e longbench/gov_report_e test_longbench/multifieldqa_en_e --split test --max_ctx_chunk_len -1 --lora_aggregation sum
WANDB_MODE=disabled run uv run python run_eval.py --checkpoint_path train_outputs/runs/Aug02_07-51-08_slurm0-a3nodeset-9_76501_7fdab5ea/checkpoint-50000/pytorch_model.bin --datasets squad ropes drop longbench/squad_e longbench/gov_report_e test_longbench/multifieldqa_en_e --split test --max_ctx_chunk_len 128 --lora_aggregation mean
WANDB_MODE=disabled run uv run python run_eval.py --checkpoint_path train_outputs/runs/Aug02_07-51-08_slurm0-a3nodeset-9_76501_7fdab5ea/checkpoint-50000/pytorch_model.bin --datasets squad ropes drop longbench/squad_e longbench/gov_report_e test_longbench/multifieldqa_en_e --split test --max_ctx_chunk_len 128 --lora_aggregation sum
WANDB_MODE=disabled run uv run python run_eval.py --checkpoint_path train_outputs/runs/Aug02_07-51-08_slurm0-a3nodeset-9_76501_7fdab5ea/checkpoint-50000/pytorch_model.bin --datasets squad ropes drop longbench/squad_e longbench/gov_report_e test_longbench/multifieldqa_en_e --split test --max_ctx_chunk_len 256 --lora_aggregation mean
WANDB_MODE=disabled run uv run python run_eval.py --checkpoint_path train_outputs/runs/Aug02_07-51-08_slurm0-a3nodeset-9_76501_7fdab5ea/checkpoint-50000/pytorch_model.bin --datasets squad ropes drop longbench/squad_e longbench/gov_report_e test_longbench/multifieldqa_en_e --split test --max_ctx_chunk_len 256 --lora_aggregation sum
WANDB_MODE=disabled run uv run python run_eval.py --checkpoint_path train_outputs/runs/Aug02_07-51-08_slurm0-a3nodeset-9_76501_7fdab5ea/checkpoint-50000/pytorch_model.bin --datasets squad ropes drop longbench/squad_e longbench/gov_report_e test_longbench/multifieldqa_en_e --split test --max_ctx_chunk_len 512 --lora_aggregation mean
WANDB_MODE=disabled run uv run python run_eval.py --checkpoint_path train_outputs/runs/Aug02_07-51-08_slurm0-a3nodeset-9_76501_7fdab5ea/checkpoint-50000/pytorch_model.bin --datasets squad ropes drop longbench/squad_e longbench/gov_report_e test_longbench/multifieldqa_en_e --split test --max_ctx_chunk_len 512 --lora_aggregation sum

2
src/ctx_to_lora/modeling/hypernet.py
View file

@ -690,6 +690,8 @@ class ModulatedPretrainedModel(nn.Module):
hypernet_config = state_dict["hypernet_config"]
if getattr(hypernet_config, "num_pre_head_layers", None) is None:
hypernet_config.num_pre_head_layers = 4
if getattr(hypernet_config, "use_per_rank_bias", None) is None:
hypernet_config.use_per_rank_bias = False
ctx_encoder_args = state_dict["ctx_encoder_args"]
model = cls(base_model, hypernet_config, ctx_encoder_args, **kwargs)
model.load_state_dict(state_dict)