lomahony/pythia-2.8b-helpful-dpo
Pythia-2.8b DPO finetuned using original DPO code with the helpful subset of Anthropic-hh-rlhf dataset for 1 epoch.
Checkpoints are also uploaded.
Fully reproducible finetuning code is available on GitHub
See Pythia-2.8b for model details (paper).
See further details of these models in the paper Attributing Mode Collapse in the Fine-Tuning of Large Language Models.
You can cite these models if they are helpful as follows:
<pre> @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} } </pre>
hf (pretrained=lomahony/pythia-2.8b-helpful-dpo), genkwargs: (None), limit: None, numfewshot: 0, batchsize: 16 | Tasks |Version|Filter|n-shot| Metric | Value | |Stderr| |--------------|------:|------|-----:|---------------|------:|---|------| |arcchallenge | 1|none | 0|acc | 0.3157|± |0.0136| | | |none | 0|accnorm | 0.3447|± |0.0139| |arceasy | 1|none | 0|acc | 0.6591|± |0.0097| | | |none | 0|accnorm | 0.6002|± |0.0101| |boolq | 2|none | 0|acc | 0.6239|± |0.0085| |hellaswag | 1|none | 0|acc | 0.4671|± |0.0050| | | |none | 0|accnorm | 0.6107|± |0.0049| |lambadaopenai| 1|none | 0|perplexity | 4.8811|± |0.1354| | | |none | 0|acc | 0.6264|± |0.0067| |openbookqa | 1|none | 0|acc | 0.2820|± |0.0201| | | |none | 0|accnorm | 0.4040|± |0.0220| |piqa | 1|none | 0|acc | 0.7568|± |0.0100| | | |none | 0|accnorm | 0.7557|± |0.0100| |sciq | 1|none | 0|acc | 0.8900|± |0.0099| | | |none | 0|accnorm | 0.8340|± |0.0118| |wikitext | 2|none | 0|wordperplexity|13.9186|± |N/A | | | |none | 0|byteperplexity| 1.6363|± |N/A | | | |none | 0|bitsperbyte | 0.7104|± |N/A | |winogrande | 1|none | 0|acc | 0.6046|± |0.0137|
hf (pretrained=lomahony/pythia-2.8b-helpful-dpo), genkwargs: (None), limit: None, numfewshot: 5, batchsize: 16 | Tasks |Version|Filter|n-shot| Metric | Value | |Stderr| |--------------|------:|------|-----:|---------------|------:|---|------| |arcchallenge | 1|none | 5|acc | 0.3498|± |0.0139| | | |none | 5|accnorm | 0.3823|± |0.0142| |arceasy | 1|none | 5|acc | 0.6940|± |0.0095| | | |none | 5|accnorm | 0.6940|± |0.0095| |boolq | 2|none | 5|acc | 0.6440|± |0.0084| |hellaswag | 1|none | 5|acc | 0.4596|± |0.0050| | | |none | 5|accnorm | 0.6096|± |0.0049| |lambadaopenai| 1|none | 5|perplexity | 6.9027|± |0.2030| | | |none | 5|acc | 0.5614|± |0.0069| |openbookqa | 1|none | 5|acc | 0.2920|± |0.0204| | | |none | 5|accnorm | 0.3820|± |0.0218| |piqa | 1|none | 5|acc | 0.7601|± |0.0100| | | |none | 5|accnorm | 0.7563|± |0.0100| |sciq | 1|none | 5|acc | 0.9380|± |0.0076| | | |none | 5|accnorm | 0.9290|± |0.0081| |wikitext | 2|none | 5|wordperplexity|13.9186|± |N/A | | | |none | 5|byteperplexity| 1.6363|± |N/A | | | |none | 5|bitsperbyte | 0.7104|± |N/A | |winogrande | 1|none | 5|acc | 0.6006|± |0.0138|