|
--- |
|
language: |
|
- en |
|
tags: |
|
- pytorch |
|
- causal-lm |
|
- pythia |
|
license: apache-2.0 |
|
datasets: |
|
- Anthropic/hh-rlhf |
|
--- |
|
|
|
[Pythia-2.8b](https://huggingface.co/EleutherAI/pythia-410m) supervised finetuned using TRLx library with the helpful subset of [Anthropic-hh-rlhf dataset](https://huggingface.co/datasets/Anthropic/hh-rlhf) for 1 epoch. |
|
|
|
Checkpoints are also uploaded. |
|
|
|
Fully reproducible finetuning code is available on [GitHub](https://github.com/lauraaisling/trlx-pythia/tree/main) |
|
|
|
[wandb log](https://wandb.ai/lauraomahony999/pythia-sft/runs/3b0ltx73) |
|
|
|
See [Pythia-2.8b](https://huggingface.co/EleutherAI/pythia-2.8b) for model details [(paper)](https://arxiv.org/abs/2101.00027). |
|
|
|
See further details of these models in the paper [Attributing Mode Collapse in the Fine-Tuning of Large Language Models](https://openreview.net/pdf?id=3pDMYjpOxk). |
|
|
|
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), gen_kwargs: (None), limit: None, num_fewshot: 0, batch_size: 16 |
|
| Tasks |Version|Filter|n-shot| Metric | Value | |Stderr| |
|
|--------------|------:|------|-----:|---------------|------:|---|------| |
|
|arc_challenge | 1|none | 0|acc | 0.2901|± |0.0133| |
|
| | |none | 0|acc_norm | 0.3404|± |0.0138| |
|
|arc_easy | 1|none | 0|acc | 0.6469|± |0.0098| |
|
| | |none | 0|acc_norm | 0.5766|± |0.0101| |
|
|boolq | 2|none | 0|acc | 0.6361|± |0.0084| |
|
|hellaswag | 1|none | 0|acc | 0.4557|± |0.0050| |
|
| | |none | 0|acc_norm | 0.5984|± |0.0049| |
|
|lambada_openai| 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|acc_norm | 0.3760|± |0.0217| |
|
|piqa | 1|none | 0|acc | 0.7481|± |0.0101| |
|
| | |none | 0|acc_norm | 0.7481|± |0.0101| |
|
|sciq | 1|none | 0|acc | 0.8800|± |0.0103| |
|
| | |none | 0|acc_norm | 0.8180|± |0.0122| |
|
|wikitext | 2|none | 0|word_perplexity|13.4928|± |N/A | |
|
| | |none | 0|byte_perplexity| 1.6268|± |N/A | |
|
| | |none | 0|bits_per_byte | 0.7020|± |N/A | |
|
|winogrande | 1|none | 0|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| |
|
|
