gemma-2b-zephyr-sft/README.md

license, license_name, license_link, base_model, tags, datasets, model-index

license	license_name	license_link	base_model	tags	datasets	model-index
other	gemma-terms-of-use	https://ai.google.dev/gemma/terms	google/gemma-2b	alignment-handbook trl sft generated_from_trainer	HuggingFaceH4/deita-10k-v0-sft	name results gemma-2b-zephyr-sft task dataset metrics type name text-generation Text Generation name type config split args AI2 Reasoning Challenge (25-Shot) ai2_arc ARC-Challenge test num_few_shot 25 type value name acc_norm 51.88 normalized accuracy task dataset metrics type name text-generation Text Generation name type split args HellaSwag (10-Shot) hellaswag validation num_few_shot 10 type value name acc_norm 72.63 normalized accuracy task dataset metrics type name text-generation Text Generation name type config split args MMLU (5-Shot) cais/mmlu all test num_few_shot 5 type value name acc 42.20 accuracy task dataset metrics type name text-generation Text Generation name type config split args TruthfulQA (0-shot) truthful_qa multiple_choice validation num_few_shot 0 type value mc2 41.96 task dataset metrics type name text-generation Text Generation name type config split args Winogrande (5-shot) winogrande winogrande_xl validation num_few_shot 5 type value name acc 63.85 accuracy task dataset metrics type name text-generation Text Generation name type config split args GSM8k (5-shot) gsm8k main test num_few_shot 5 type value name acc 20.09 accuracy

Model Card for Gemma 2B Zephyr SFT

We trained the google/gemma-2b with deita-10k-v0-sft. We carefully selected the hyper-parameters and masked the user tokens during training to achieve the best supervised fine-tuning performance.

Model description

• Model type: A 2.5B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets.
• Language(s) (NLP): Primarily English
• License: Gemma Terms of Use
• Finetuned from model: google/gemma-2b

License

This model has the same license as the original Gemma model collection

OpenLLM Leaderboard Performance

Models	Avg.	ARC	HellaSwag	MMLU	TruthfulQA	Winogrande	GSM8k
google/gemma-2b	46.37	48.38	71.77	41.77	33.08	66.77	16.91
google/gemma-2b-it	42.75	43.94	62.70	37.65	45.82	60.93	5.46
wandb/gemma-2b-zephyr-sft	47.18	49.74	72.38	41.37	34.42	66.93	18.27
wandb/gemma-2b-zephyr-dpo	46.92	49.66	72.23	41.13	34.47	66.54	17.51
Columbia-NLP/gemma-2b-zephyr-sft	48.75	51.80	72.63	42.20	41.96	63.85	20.09
Columbia-NLP/gemma-2b-zephyr-dpo	49.14	52.22	73.11	42.55	42.64	64.40	19.94

MT-Bench

GPT-4-0125-preview as Judge

Model	Total	Coding	Extraction	Humanities	Math	Reasoning	Roleplay	STEM	Writing
google/gemma-2b-it	4.71	2.95	4.35	6.15	2.90	3.50	5.60	5.50	6.70
wandb/gemma-2b-zephyr-sft	4.03	3.10	3.15	5.00	2.70	2.65	5.10	4.80	5.75
wandb/gemma-2b-zephyr-dpo	4.06	2.80	2.90	5.55	2.65	2.70	5.20	4.80	5.85
Columbia-NLP/gemma-2b-zephyr-sft	4.34	3.10	3.70	6.25	2.65	2.70	5.55	5.25	5.50
Columbia-NLP/gemma-2b-zephyr-dpo	4.75	3.50	4.05	6.75	3.30	3.70	5.85	5.40	5.53