[HINT] SKILL.md 및 모든 관련 파일을 포함한 전체 스킬 디렉토리를 다운로드합니다
| name | evaluating-llms-harness |
| description | lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.). |
| version | 1.0.0 |
| author | Orchestra Research |
| license | MIT |
| dependencies | ["lm-eval","transformers","vllm"] |
| platforms | ["linux","macos"] |
| metadata | {"hermes":{"tags":["Evaluation","LM Evaluation Harness","Benchmarking","MMLU","HumanEval","GSM8K","EleutherAI","Model Quality","Academic Benchmarks","Industry Standard"]}} |
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
lm-evaluation-harness evaluates LLMs across 60+ academic benchmarks using standardized prompts and metrics.
Installation:
pip install lm-eval
Evaluate any HuggingFace model:
lm_eval --model hf \
--model_args pretrained=meta-llama/Llama-2-7b-hf \
--tasks mmlu,gsm8k,hellaswag \
--device cuda:0 \
--batch_size 8
View available tasks:
lm_eval --tasks list
Evaluate model on core benchmarks (MMLU, GSM8K, HumanEval).
Copy this checklist:
Benchmark Evaluation:
- [ ] Step 1: Choose benchmark suite
- [ ] Step 2: Configure model
- [ ] Step 3: Run evaluation
- [ ] Step 4: Analyze results
Step 1: Choose benchmark suite
Core reasoning benchmarks:
Code benchmarks:
Standard suite (recommended for model releases):
--tasks mmlu,gsm8k,hellaswag,truthfulqa,arc_challenge
Step 2: Configure model
HuggingFace model:
lm_eval --model hf \
--model_args pretrained=meta-llama/Llama-2-7b-hf,dtype=bfloat16 \
--tasks mmlu \
--device cuda:0 \
--batch_size auto # Auto-detect optimal batch size
Quantized model (4-bit/8-bit):
lm_eval --model hf \
--model_args pretrained=meta-llama/Llama-2-7b-hf,load_in_4bit=True \
--tasks mmlu \
--device cuda:0
Custom checkpoint:
lm_eval --model hf \
--model_args pretrained=/path/to/my-model,tokenizer=/path/to/tokenizer \
--tasks mmlu \
--device cuda:0
Step 3: Run evaluation
# Full MMLU evaluation (57 subjects)
lm_eval --model hf \
--model_args pretrained=meta-llama/Llama-2-7b-hf \
--tasks mmlu \
--num_fewshot 5 \ # 5-shot evaluation (standard)
--batch_size 8 \
--output_path results/ \
--log_samples # Save individual predictions
# Multiple benchmarks at once
lm_eval --model hf \
--model_args pretrained=meta-llama/Llama-2-7b-hf \
--tasks mmlu,gsm8k,hellaswag,truthfulqa,arc_challenge \
--num_fewshot 5 \
--batch_size 8 \
--output_path results/llama2-7b-eval.json
Step 4: Analyze results
Results saved to results/llama2-7b-eval.json:
{
"results": {
"mmlu": {
"acc": 0.459,
"acc_stderr": 0.004
},
"gsm8k": {
"exact_match": 0.142,
"exact_match_stderr": 0.006
},
"hellaswag": {
"acc_norm": 0.765,
"acc_norm_stderr": 0.004
}
},
"config": {
"model": "hf",
"model_args": "pretrained=meta-llama/Llama-2-7b-hf",
"num_fewshot": 5
}
}
Evaluate checkpoints during training.
Training Progress Tracking:
- [ ] Step 1: Set up periodic evaluation
- [ ] Step 2: Choose quick benchmarks
- [ ] Step 3: Automate evaluation
- [ ] Step 4: Plot learning curves
Step 1: Set up periodic evaluation
Evaluate every N training steps:
#!/bin/bash
# eval_checkpoint.sh
CHECKPOINT_DIR=$1
STEP=$2
lm_eval --model hf \
--model_args pretrained=$CHECKPOINT_DIR/checkpoint-$STEP \
--tasks gsm8k,hellaswag \
--num_fewshot 0 \ # 0-shot for speed
--batch_size 16 \
--output_path results/step-$STEP.json
Step 2: Choose quick benchmarks
Fast benchmarks for frequent evaluation:
Avoid for frequent eval (too slow):
Step 3: Automate evaluation
Integrate with training script:
# In training loop
if step % eval_interval == 0:
model.save_pretrained(f"checkpoints/step-{step}")
# Run evaluation
os.system(f"./eval_checkpoint.sh checkpoints step-{step}")
Or use PyTorch Lightning callbacks:
from pytorch_lightning import Callback
class EvalHarnessCallback(Callback):
def on_validation_epoch_end(self, trainer, pl_module):
step = trainer.global_step
checkpoint_path = f"checkpoints/step-{step}"
# Save checkpoint
trainer.save_checkpoint(checkpoint_path)
# Run lm-eval
os.system(f"lm_eval --model hf --model_args pretrained={checkpoint_path} ...")
Step 4: Plot learning curves
import json
import matplotlib.pyplot as plt
# Load all results
steps = []
mmlu_scores = []
for file in sorted(glob.glob("results/step-*.json")):
with open(file) as f:
data = json.load(f)
step = int(file.split("-")[1].split(".")[0])
steps.append(step)
mmlu_scores.append(data["results"]["mmlu"]["acc"])
# Plot
plt.plot(steps, mmlu_scores)
plt.xlabel("Training Step")
plt.ylabel("MMLU Accuracy")
plt.title("Training Progress")
plt.savefig("training_curve.png")
Benchmark suite for model comparison.
Model Comparison:
- [ ] Step 1: Define model list
- [ ] Step 2: Run evaluations
- [ ] Step 3: Generate comparison table
Step 1: Define model list
# models.txt
meta-llama/Llama-2-7b-hf
meta-llama/Llama-2-13b-hf
mistralai/Mistral-7B-v0.1
microsoft/phi-2
Step 2: Run evaluations
#!/bin/bash
# eval_all_models.sh
TASKS="mmlu,gsm8k,hellaswag,truthfulqa"
while read model; do
echo "Evaluating $model"
# Extract model name for output file
model_name=$(echo $model | sed 's/\//-/g')
lm_eval --model hf \
--model_args pretrained=$model,dtype=bfloat16 \
--tasks $TASKS \
--num_fewshot 5 \
--batch_size auto \
--output_path results/$model_name.json
done < models.txt
Step 3: Generate comparison table
import json
import pandas as pd
models = [
"meta-llama-Llama-2-7b-hf",
"meta-llama-Llama-2-13b-hf",
"mistralai-Mistral-7B-v0.1",
"microsoft-phi-2"
]
tasks = ["mmlu", "gsm8k", "hellaswag", "truthfulqa"]
results = []
for model in models:
with open(f"results/{model}.json") as f:
data = json.load(f)
row = {"Model": model.replace("-", "/")}
for task in tasks:
# Get primary metric for each task
metrics = data["results"][task]
if "acc" in metrics:
row[task.upper()] = f"{metrics['acc']:.3f}"
elif "exact_match" in metrics:
row[task.upper()] = f"{metrics['exact_match']:.3f}"
results.append(row)
df = pd.DataFrame(results)
print(df.to_markdown(index=False))
Output:
| Model | MMLU | GSM8K | HELLASWAG | TRUTHFULQA |
|------------------------|-------|-------|-----------|------------|
| meta-llama/Llama-2-7b | 0.459 | 0.142 | 0.765 | 0.391 |
| meta-llama/Llama-2-13b | 0.549 | 0.287 | 0.801 | 0.430 |
| mistralai/Mistral-7B | 0.626 | 0.395 | 0.812 | 0.428 |
| microsoft/phi-2 | 0.560 | 0.613 | 0.682 | 0.447 |
Use vLLM backend for 5-10x faster evaluation.
vLLM Evaluation:
- [ ] Step 1: Install vLLM
- [ ] Step 2: Configure vLLM backend
- [ ] Step 3: Run evaluation
Step 1: Install vLLM
pip install vllm
Step 2: Configure vLLM backend
lm_eval --model vllm \
--model_args pretrained=meta-llama/Llama-2-7b-hf,tensor_parallel_size=1,dtype=auto,gpu_memory_utilization=0.8 \
--tasks mmlu \
--batch_size auto
Step 3: Run evaluation
vLLM is 5-10× faster than standard HuggingFace:
# Standard HF: ~2 hours for MMLU on 7B model
lm_eval --model hf \
--model_args pretrained=meta-llama/Llama-2-7b-hf \
--tasks mmlu \
--batch_size 8
# vLLM: ~15-20 minutes for MMLU on 7B model
lm_eval --model vllm \
--model_args pretrained=meta-llama/Llama-2-7b-hf,tensor_parallel_size=2 \
--tasks mmlu \
--batch_size auto
Use lm-evaluation-harness when:
Use alternatives instead:
Issue: Evaluation too slow
Use vLLM backend:
lm_eval --model vllm \
--model_args pretrained=model-name,tensor_parallel_size=2
Or reduce fewshot examples:
--num_fewshot 0 # Instead of 5
Or evaluate subset of MMLU:
--tasks mmlu_stem # Only STEM subjects
Issue: Out of memory
Reduce batch size:
--batch_size 1 # Or --batch_size auto
Use quantization:
--model_args pretrained=model-name,load_in_8bit=True
Enable CPU offloading:
--model_args pretrained=model-name,device_map=auto,offload_folder=offload
Issue: Different results than reported
Check fewshot count:
--num_fewshot 5 # Most papers use 5-shot
Check exact task name:
--tasks mmlu # Not mmlu_direct or mmlu_fewshot
Verify model and tokenizer match:
--model_args pretrained=model-name,tokenizer=same-model-name
Issue: HumanEval not executing code
Install execution dependencies:
pip install human-eval
Enable code execution:
lm_eval --model hf \
--model_args pretrained=model-name \
--tasks humaneval \
--allow_code_execution # Required for HumanEval
Benchmark descriptions: See references/benchmark-guide.md for detailed description of all 60+ tasks, what they measure, and interpretation.
Custom tasks: See references/custom-tasks.md for creating domain-specific evaluation tasks.
API evaluation: See references/api-evaluation.md for evaluating OpenAI, Anthropic, and other API models.
Multi-GPU strategies: See references/distributed-eval.md for data parallel and tensor parallel evaluation.