lomahony/pythia-2.8b-helpful-sft
Pythia-2.8b supervised finetuned using TRLx library 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-sft), genkwargs: (None), limit: None, numfewshot: 0, batchsize: 16 | Tasks |Version|Filter|n-shot| Metric | Value | |Stderr| |--------------|------:|------|-----:|---------------|------:|---|------| |arcchallenge | 1|none | 0|acc | 0.2901|± |0.0133| | | |none | 0|accnorm | 0.3404|± |0.0138| |arceasy | 1|none | 0|acc | 0.6469|± |0.0098| | | |none | 0|accnorm | 0.5766|± |0.0101| |boolq | 2|none | 0|acc | 0.6361|± |0.0084| |hellaswag | 1|none | 0|acc | 0.4557|± |0.0050| | | |none | 0|accnorm | 0.5984|± |0.0049| |lambadaopenai| 1|none | 0|perplexity | 5.2226|± |0.1377| | | |none | 0|acc | 0.6210|± |0.0068| |openbookqa | 1|none | 0|acc | 0.2640|± |0.0197| | | |none | 0|accnorm | 0.3760|± |0.0217| |piqa | 1|none | 0|acc | 0.7481|± |0.0101| | | |none | 0|accnorm | 0.7481|± |0.0101| |sciq | 1|none | 0|acc | 0.8800|± |0.0103| | | |none | 0|accnorm | 0.8180|± |0.0122| |wikitext | 2|none | 0|wordperplexity|13.4928|± |N/A | | | |none | 0|byteperplexity| 1.6268|± |N/A | | | |none | 0|bitsperbyte | 0.7020|± |N/A | |winogrande | 1|none | 0|acc | 0.6125|± |0.0137|
hf (pretrained=lomahony/pythia-2.8b-helpful-sft), genkwargs: (None), limit: None, numfewshot: 5, batchsize: 16 | Tasks |Version|Filter|n-shot| Metric | Value | |Stderr| |--------------|------:|------|-----:|---------------|------:|---|------| |arcchallenge | 1|none | 5|acc | 0.3285|± |0.0137| | | |none | 5|accnorm | 0.3677|± |0.0141| |arceasy | 1|none | 5|acc | 0.6873|± |0.0095| | | |none | 5|accnorm | 0.6835|± |0.0095| |boolq | 2|none | 5|acc | 0.6670|± |0.0082| |hellaswag | 1|none | 5|acc | 0.4542|± |0.0050| | | |none | 5|accnorm | 0.5963|± |0.0049| |lambadaopenai| 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|accnorm | 0.3620|± |0.0215| |piqa | 1|none | 5|acc | 0.7568|± |0.0100| | | |none | 5|accnorm | 0.7486|± |0.0101| |sciq | 1|none | 5|acc | 0.9380|± |0.0076| | | |none | 5|accnorm | 0.9330|± |0.0079| |wikitext | 2|none | 5|wordperplexity|13.4928|± |N/A | | | |none | 5|byteperplexity| 1.6268|± |N/A | | | |none | 5|bitsperbyte | 0.7020|± |N/A | |winogrande | 1|none | 5|acc | 0.5935|± |0.0138|