iclr cleanup

scripts/main_exp/eval/base_model.sh

@@ -0,0 +1,8 @@
+# no truncation
+WANDB_MODE=disabled uv run run_eval.py --model_name_or_path google/gemma-2-2b-it --datasets squad drop ropes longbench/qasper_e longbench/2wikimqa_e longbench/multifieldqa_en_e --split test --eval_batch_size_gen 1
+
+# w/ truncation
+WANDB_MODE=disabled uv run run_eval.py --model_name_or_path google/gemma-2-2b-it --datasets squad drop ropes longbench/qasper_e longbench/2wikimqa_e longbench/multifieldqa_en_e --split test --eval_batch_size_gen 1 --truncate_if_too_long_inp
+
+# no context
+WANDB_MODE=disabled uv run run_eval.py --model_name_or_path google/gemma-2-2b-it --datasets squad drop ropes longbench/qasper_e longbench/2wikimqa_e longbench/multifieldqa_en_e --split test --eval_batch_size_gen 1 --remove_context

scripts/main_exp/eval/cd.sh

@@ -0,0 +1,6 @@
+# qa
+uv run run_eval.py --model_name_or_path google/gemma-2-2b-it --datasets squad drop ropes --split test --use_cd --cd_update_iterations 300 --eval_batch_size_gen=1 --truncate_if_too_long_inp --cd_use_gen_q --q_gen_rounds=4
+
+
+# longbench
+uv run run_eval.py --model_name_or_path google/gemma-2-2b-it --datasets longbench/multifieldqa_en_e longbench/2wikimqa_e longbench/multifieldqa_en_e --split test --use_cd --cd_update_iterations 300 --eval_batch_size_gen=1 --truncate_if_too_long_inp --cd_use_gen_q --q_gen_rounds=1

scripts/main_exp/eval/cd_oracle.sh

@@ -0,0 +1,6 @@
+# qa
+uv run run_eval.py --model_name_or_path google/gemma-2-2b-it --datasets squad drop ropes --split test --use_cd --cd_update_iterations 300 --eval_batch_size_gen=1 --truncate_if_too_long_inp
+
+
+# longbench
+uv run run_eval.py --model_name_or_path google/gemma-2-2b-it --datasets longbench/multifieldqa_en_e longbench/2wikimqa_e longbench/multifieldqa_en_e --split test --use_cd --cd_update_iterations 300 --eval_batch_size_gen=1 --truncate_if_too_long_inp

scripts/main_exp/eval/d2l.sh

@@ -0,0 +1,13 @@
+# main results
+# batched
+WANDB_MODE=disabled uv run run_eval.py --checkpoint_path train_outputs/runs/$RUN_NAME/pytorch_model.bin --datasets squad drop ropes longbench/qasper_e longbench/2wikimqa_e longbench/multifieldqa_en_e --split test --max_ctx_chunk_len 8192 --eval_batch_size_gen 1
+
+# iterative
+WANDB_MODE=disabled uv run run_eval.py --checkpoint_path train_outputs/runs/$RUN_NAME/pytorch_model.bin --datasets squad drop ropes longbench/qasper_e longbench/2wikimqa_e longbench/multifieldqa_en_e --split test --max_ctx_chunk_len 8192 --eval_batch_size_gen 1 --use_iterative_mode
+
+# query internalization
+WANDB_MODE=disabled uv run run_eval.py --checkpoint_path train_outputs/runs/$RUN_NAME/pytorch_model.bin --datasets squad --split test --eval_batch_size_gen=1 --flip_ctx_inp
+
+# replaced squad context
+WANDB_MODE=disabled uv run python run_eval.py --checkpoint_path train_outputs/runs/$RUN_NAME/pytorch_model.bin --datasets squad_assistant_ctx_no_passage --split test
+WANDB_MODE=disabled uv run python run_eval.py --checkpoint_path train_outputs/runs/$RUN_NAME/pytorch_model.bin --datasets squad_negative_no_passage --split test

scripts/main_exp/eval/llmlingua.sh

@@ -0,0 +1,5 @@
+for dataset in squad drop ropes longbench/qasper_e longbench/2wikimqa_e longbench/multifieldqa_en_e; do
+  for rate in 0.9 0.8 0.6 0.4 0.2 0.1; do
+    WANDB_MODE=disabled uv run run_eval.py --model_name_or_path google/gemma-2-2b-it --datasets "$dataset" --split test --eval_batch_size_gen=1 --use_llmlingua --llmlingua_compression_rate "$rate" --truncate_if_too_long_ctx
+  done
+done

scripts/main_exp/eval/t2l.sh

@@ -0,0 +1,4 @@
+# download t2l checkpoint
+uv run huggingface-cli download SakanaAI/text-to-lora --local-dir . --include "trained_t2l/gemma_2b_t2l"
+
+WANDB_MODE=disabled uv run run_eval.py --model_name_or_path google/gemma-2-2b-it --datasets squad drop ropes longbench/qasper_e longbench/2wikimqa_e longbench/multifieldqa_en_e --split test --eval_batch_size_gen=1 --use_t2l

scripts/main_exp/gen_data.sh

@@ -0,0 +1,20 @@
+# download fineweb_edu to `data/raw_datasets/fineweb_edu
+uv run data/download_fineweb_edu.py
+
+# generate qa data
+# run from 000 to 013
+for shard_id in $(seq -f "%03g" 0 1); do
+  uv run data/generate_fw_edu_qa_v2.py --shard_pattern "${shard_id}_00000" --n_qa_pairs=5 --vllm_model=google/gemma-3-12b-it --max_length=2000 --max_model_length=2048;
+  uv run data/generate_fw_edu_qa_v2_repeat.py --shard_pattern "min_0_to_2000/${shard_id}*level_0*" --n_qa_pairs=5 --vllm_model=google/gemma-3-12b-it;
+
+  # self-generated response QA data
+  uv run data/self_generate_qa.py --vllm_model google/gemma-2-2b-it --glob_pattern "data/raw_datasets/fw_qa_v2/min_0_to_2000/${shard_id}*_level_1*" --closed_qa_prob 1.0
+done
+
+
+# val split
+uv run data/self_generate_qa.py --vllm_model google/gemma-2-2b-it --glob_pattern 'data/raw_datasets/fw_qa_v2/min_0_to_2000/*_level_0_val.parquet'
+
+# self-gen data for other ds 
+uv run data/self_generate_qa.py --vllm_model google/gemma-2-2b-it --ds_names squad_compact ropes_compact drop_compact --closed_qa_prob 1.0
+uv run data/self_generate_qa.py --vllm_model google/gemma-2-2b-it --ds_names pwc_compact --closed_qa_prob 0.0

scripts/main_exp/train.sh

@@ -0,0 +1,28 @@
+#!/bin/bash
+
+port=29051
+
+default_args=(
+    "--model_name_or_path=google/gemma-2-2b-it"
+    "--max_steps=50_000"
+    "--target_modules=down_proj"
+    "--lora_r=8"
+    "--eval_strategy=no"
+    "--max_qas_len=2048"
+    "--max_qas_per_sample=1"
+    "--per_rank_gen=True"
+    "--per_layer_processing=True"
+    "--gen_lora_l1_reg_coef=0.1"
+)
+
+uv run accelerate launch --config_file accelerate_config.yaml --main_process_port $port \
+--num_processes=8 --gpu_ids all train.py \
+configs/main_exp/self_gen_lv1_closed_qa_1_l2l.yaml \
+"${default_args[@]}" \
+--model_name_or_path=google/gemma-2-2b-it \
+--target_modules=down_proj --lora_r=8 \
+--eval_strategy=no --max_qas_len=2048 --max_qas_per_sample=1 \
+--per_rank_gen=True --per_layer_processing=True --gen_lora_l1_reg_coef=0.1 \
+--max_steps=80000 --gradient_accumulation_steps=8 --max_packed_inp_len=4096 \
+--max_packed_ctx_len=4096 --use_per_ctx_average_loss=True --use_kl_loss=True \
+--quantize_ctx_encoder=True