#!/usr/bin/env bash # Reconstructed from the completed run's saved parameters and frozen task list. set -euo pipefail PROJECT=$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")/.." && pwd) SKBENCH_DIR=${SKBENCH_DIR:-/home/schwarc/diplomovka/sk-bench} MODEL_DIR=${MODEL_DIR:-/home/schwarc/diplomovka/skbench_evaluation/models/aya_300k_lr_0p00010} OUTPUT_ROOT=${OUTPUT_ROOT:-/home/schwarc/diplomovka/skbench_evaluation/results} GPU_ID=${GPU_ID:-1} TASKS="$PROJECT/benchmarks/skbench/configs/tasks.txt" OMITTED="$PROJECT/benchmarks/skbench/configs/omitted_tasks.txt" test -f "$MODEL_DIR/config.json" test -f "$TASKS" test -f "$OMITTED" cd "$SKBENCH_DIR" RUN="$OUTPUT_ROOT/sk_zero_available_without_nli_lr_0p00010_$(date +%Y%m%d_%H%M%S)" mkdir -p "$RUN" cp "$TASKS" "$RUN/tasks.txt" cp "$OMITTED" "$RUN/omitted_tasks.txt" cp uv.lock "$RUN/uv.lock" git rev-parse HEAD > "$RUN/skbench_commit.txt" CUDA_VISIBLE_DEVICES="$GPU_ID" VLLM_USE_FLASHINFER_SAMPLER=0 \ uv run --locked python eval_vllm.py \ --model-name "$MODEL_DIR" \ --tasks-file "$RUN/tasks.txt" \ --output-dir "$RUN" \ --tensor-parallel-size 1 \ --dtype bfloat16 \ --gpu-memory-utilization 0.85 \ --max-model-length 32768 \ --max-batched-tokens 2048 \ --enforce-eager \ --save-details \ 2>&1 | tee "$RUN/run.log"