@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-2.8b-helpful-sft), gen_kwargs: (None), limit: None, num_fewshot: 0, batch_size: 16

Tasks	Version	Filter	Metric	Value		Stderr
arc_challenge	1	none	acc	0.2901	±	0.0133
		none	acc_norm	0.3404	±	0.0138
arc_easy	1	none	acc	0.6469	±	0.0098
		none	acc_norm	0.5766	±	0.0101
boolq	2	none	acc	0.6361	±	0.0084
hellaswag	1	none	acc	0.4557	±	0.0050
		none	acc_norm	0.5984	±	0.0049
lambada_openai	1	none	perplexity	5.2226	±	0.1377
		none	acc	0.6210	±	0.0068
openbookqa	1	none	acc	0.2640	±	0.0197
		none	acc_norm	0.3760	±	0.0217
piqa	1	none	acc	0.7481	±	0.0101
		none	acc_norm	0.7481	±	0.0101
sciq	1	none	acc	0.8800	±	0.0103
		none	acc_norm	0.8180	±	0.0122
wikitext	2	none	word_perplexity	13.4928	±	N/A
		none	byte_perplexity	1.6268	±	N/A
		none	bits_per_byte	0.7020	±	N/A
winogrande	1	none	acc	0.6125	±	0.0137

hf (pretrained=lomahony/pythia-2.8b-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	0.3285	±	0.0137
		none	5	acc_norm	0.3677	±	0.0141
arc_easy	1	none	5	acc	0.6873	±	0.0095
		none	5	acc_norm	0.6835	±	0.0095
boolq	2	none	5	acc	0.6670	±	0.0082
hellaswag	1	none	5	acc	0.4542	±	0.0050
		none	5	acc_norm	0.5963	±	0.0049
lambada_openai	1	none	5	perplexity	7.4076	±	0.2095
		none	5	acc	0.5486	±	0.0069
openbookqa	1	none	5	acc	0.2680	±	0.0198
		none	5	acc_norm	0.3620	±	0.0215
piqa	1	none	5	acc	0.7568	±	0.0100
		none	5	acc_norm	0.7486	±	0.0101
sciq	1	none	5	acc	0.9380	±	0.0076
		none	5	acc_norm	0.9330	±	0.0079
wikitext	2	none	5	word_perplexity	13.4928	±	N/A
		none	5	byte_perplexity	1.6268	±	N/A
		none	5	bits_per_byte	0.7020	±	N/A
winogrande	1	none	5	acc	0.5935	±	0.0138