@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-410m-helpful-dpo), gen_kwargs: (None), limit: None, num_fewshot: 0, batch_size: 16

Tasks	Version	Filter	Metric	Value		Stderr
arc_challenge	1	none	acc	0.2338	±	0.0124
		none	acc_norm	0.2602	±	0.0128
arc_easy	1	none	acc	0.5185	±	0.0103
		none	acc_norm	0.4609	±	0.0102
boolq	2	none	acc	0.6214	±	0.0085
hellaswag	1	none	acc	0.3447	±	0.0047
		none	acc_norm	0.4074	±	0.0049
lambada_openai	1	none	perplexity	19.0431	±	0.7027
		none	acc	0.3978	±	0.0068
openbookqa	1	none	acc	0.2000	±	0.0179
		none	acc_norm	0.3100	±	0.0207
piqa	1	none	acc	0.6779	±	0.0109
		none	acc_norm	0.6757	±	0.0109
sciq	1	none	acc	0.7760	±	0.0132
		none	acc_norm	0.6690	±	0.0149
wikitext	2	none	word_perplexity	24.3807	±	N/A
		none	byte_perplexity	1.8171	±	N/A
		none	bits_per_byte	0.8617	±	N/A
winogrande	1	none	acc	0.5343	±	0.0140

hf (pretrained=lomahony/pythia-410m-helpful-dpo), 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	0.2346	±	0.0124
		none	5	acc_norm	0.2747	±	0.0130
arc_easy	1	none	5	acc	0.5509	±	0.0102
		none	5	acc_norm	0.5198	±	0.0103
boolq	2	none	5	acc	0.5982	±	0.0086
hellaswag	1	none	5	acc	0.3437	±	0.0047
		none	5	acc_norm	0.4059	±	0.0049
lambada_openai	1	none	5	perplexity	34.3002	±	1.3044
		none	5	acc	0.3148	±	0.0065
openbookqa	1	none	5	acc	0.1740	±	0.0170
		none	5	acc_norm	0.2880	±	0.0203
piqa	1	none	5	acc	0.6741	±	0.0109
		none	5	acc_norm	0.6670	±	0.0110
sciq	1	none	5	acc	0.8520	±	0.0112
		none	5	acc_norm	0.8350	±	0.0117
wikitext	2	none	5	word_perplexity	24.3807	±	N/A
		none	5	byte_perplexity	1.8171	±	N/A
		none	5	bits_per_byte	0.8617	±	N/A
winogrande	1	none	5	acc	0.5162	±	0.0140