lomahony/pythia-1b-helpful-sft
Pythia-1b 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-1b 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-1b-helpful-sft), genkwargs: (None), limit: None, numfewshot: 0, batchsize: 16 | Tasks |Version|Filter|n-shot| Metric | Value | |Stderr| |--------------|------:|------|-----:|---------------|------:|---|------| |arcchallenge | 1|none | 0|acc | 0.2543|± |0.0127| | | |none | 0|accnorm | 0.2739|± |0.0130| |arceasy | 1|none | 0|acc | 0.5724|± |0.0102| | | |none | 0|accnorm | 0.4941|± |0.0103| |boolq | 2|none | 0|acc | 0.6199|± |0.0085| |hellaswag | 1|none | 0|acc | 0.3819|± |0.0048| | | |none | 0|accnorm | 0.4736|± |0.0050| |lambadaopenai| 1|none | 0|perplexity | 7.1374|± |0.2014| | | |none | 0|acc | 0.5626|± |0.0069| |openbookqa | 1|none | 0|acc | 0.2040|± |0.0180| | | |none | 0|accnorm | 0.3140|± |0.0208| |piqa | 1|none | 0|acc | 0.7138|± |0.0105| | | |none | 0|accnorm | 0.6997|± |0.0107| |sciq | 1|none | 0|acc | 0.8400|± |0.0116| | | |none | 0|accnorm | 0.7620|± |0.0135| |wikitext | 2|none | 0|wordperplexity|16.9719|± |N/A | | | |none | 0|byteperplexity| 1.6981|± |N/A | | | |none | 0|bitsperbyte | 0.7639|± |N/A | |winogrande | 1|none | 0|acc | 0.5343|± |0.0140|
hf (pretrained=lomahony/pythia-1b-helpful-sft), genkwargs: (None), limit: None, numfewshot: 5, batchsize: 16 | Tasks |Version|Filter|n-shot| Metric | Value | |Stderr| |--------------|------:|------|-----:|---------------|------:|---|------| |arcchallenge | 1|none | 5|acc | 0.2628|± |0.0129| | | |none | 5|accnorm | 0.2918|± |0.0133| |arceasy | 1|none | 5|acc | 0.6040|± |0.0100| | | |none | 5|accnorm | 0.5816|± |0.0101| |boolq | 2|none | 5|acc | 0.5963|± |0.0086| |hellaswag | 1|none | 5|acc | 0.3780|± |0.0048| | | |none | 5|accnorm | 0.4719|± |0.0050| |lambadaopenai| 1|none | 5|perplexity |10.2584|± |0.2936| | | |none | 5|acc | 0.4832|± |0.0070| |openbookqa | 1|none | 5|acc | 0.1980|± |0.0178| | | |none | 5|accnorm | 0.3220|± |0.0209| |piqa | 1|none | 5|acc | 0.7057|± |0.0106| | | |none | 5|accnorm | 0.7095|± |0.0106| |sciq | 1|none | 5|acc | 0.8980|± |0.0096| | | |none | 5|accnorm | 0.9000|± |0.0095| |wikitext | 2|none | 5|wordperplexity|16.9719|± |N/A | | | |none | 5|byteperplexity| 1.6981|± |N/A | | | |none | 5|bitsperbyte | 0.7639|± |N/A | |winogrande | 1|none | 5|acc | 0.5446|± |0.0140|