@inproceedings{o2024attributing, title={Attributing Mode Collapse in the Fine-Tuning of Large Language Models}, author={O’Mahony, Laura and Grinsztajn, Leo and Schoelkopf, Hailey and Biderman, Stella}, booktitle={ICLR 2024, Mathematical and Empirical Understanding of Foundation Models (ME-FoMo) workshop}, year={2024} }

hf (pretrained=lomahony/pythia-1.4b-helpful-sft), gen_kwargs: (None), limit: None, num_fewshot: 0, batch_size: 16

Tasks	Version	Filter	Metric	Value		Stderr
arc_challenge	1	none	acc	0.2679	±	0.0129
		none	acc_norm	0.2978	±	0.0134
arc_easy	1	none	acc	0.6120	±	0.0100
		none	acc_norm	0.5282	±	0.0102
boolq	2	none	acc	0.6260	±	0.0085
hellaswag	1	none	acc	0.4097	±	0.0049
		none	acc_norm	0.5212	±	0.0050
lambada_openai	1	none	perplexity	6.4836	±	0.1838
		none	acc	0.5789	±	0.0069
openbookqa	1	none	acc	0.2120	±	0.0183
		none	acc_norm	0.3340	±	0.0211
piqa	1	none	acc	0.7100	±	0.0106
		none	acc_norm	0.7144	±	0.0105
sciq	1	none	acc	0.8540	±	0.0112
		none	acc_norm	0.7830	±	0.0130
wikitext	2	none	word_perplexity	15.8394	±	N/A
		none	byte_perplexity	1.6763	±	N/A
		none	bits_per_byte	0.7453	±	N/A
winogrande	1	none	acc	0.5872	±	0.0138

hf (pretrained=lomahony/pythia-1.4b-helpful-sft), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: 16

Tasks	Version	Filter	n-shot	Metric	Value		Stderr
arc_challenge	1	none	5	acc	0.2892	±	0.0133
		none	5	acc_norm	0.3097	±	0.0135
arc_easy	1	none	5	acc	0.6444	±	0.0098
		none	5	acc_norm	0.6309	±	0.0099
boolq	2	none	5	acc	0.6333	±	0.0084
hellaswag	1	none	5	acc	0.4065	±	0.0049
		none	5	acc_norm	0.5215	±	0.0050
lambada_openai	1	none	5	perplexity	9.7040	±	0.2887
		none	5	acc	0.4951	±	0.0070
openbookqa	1	none	5	acc	0.2220	±	0.0186
		none	5	acc_norm	0.3100	±	0.0207
piqa	1	none	5	acc	0.7029	±	0.0107
		none	5	acc_norm	0.7127	±	0.0106
sciq	1	none	5	acc	0.9170	±	0.0087
		none	5	acc_norm	0.9160	±	0.0088
wikitext	2	none	5	word_perplexity	15.8394	±	N/A
		none	5	byte_perplexity	1.6763	±	N/A
		none	5	bits_per_byte	0.7453	±	N/A
winogrande	1	none	5	acc	0.5699	±	0.0139