Update submissions.json

#62

training and evaluation commands
hf jobs uv run --flavor a100-large --timeout 6h --secrets HF_TOKEN dpo_training_with_hf_jobs_v1.py
hf jobs uv run --flavor a10g-large --with "triton<=3.2.0,vllm<0.10.2,emoji,lighteval[vllm]<=0.11.0" --secrets HF_TOKEN lighteval vllm "model_name=marcelovidigal/smollm3-3b-dpo-finetuned-v3-r1" "lighteval|gsm8k|0|0,leaderboard|truthfulqa:mc|0|0,leaderboard|hellaswag|0|0,leaderboard|arc:challenge|0|0" --push-to-hub --results-org marcelovidigal

Ready to merge
This branch is ready to get merged automatically.

Sign up or log in to comment