checkpointing, dataset, evaluation, final_adapter_path, lora, model, optimization, prompt_style, runtime, sdpo, sequence, total_steps

amr-fma/amr-fma-Llama-3.1-8B-Instruct-lora_sft-math-p1_sft_math_tooluse-s43

Method: lora_sft
Base model: meta-llama/Llama-3.1-8B-Instruct
Dataset: DigitalLearningGmbH/MATH-lighteval (slug: math )
Seed: 43
Git commit: 8b979a30de6dfbf3b5a1052e42d8c0453b214d3f
Exp name: p1_sft_math_tooluse
WandB run: co3n04yu

amr-fma/amr-fma-Llama-3.1-8B-Instruct-lora_sft-math-p1_sft_math_tooluse-s43

Tags

Checkpoints (branches)

Hyperparameter sections

amr-fma/
amr-fma-Llama-3.1-8B-Instruct-lora_sft-math-p1_sft_math_tooluse-s43