lomahony's picture
Update README.md
95bdf27 verified
metadata
language:
  - en
tags:
  - pytorch
  - causal-lm
  - pythia
license: apache-2.0
datasets:
  - Anthropic/hh-rlhf

Pythia-160m 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

wandb log

See Pythia-160m 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:

@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-160m-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 0.1894 ± 0.0115
none 0 acc_norm 0.2235 ± 0.0122
arc_easy 1 none 0 acc 0.3889 ± 0.0100
none 0 acc_norm 0.3737 ± 0.0099
boolq 2 none 0 acc 0.5346 ± 0.0087
hellaswag 1 none 0 acc 0.2801 ± 0.0045
none 0 acc_norm 0.2949 ± 0.0046
lambada_openai 1 none 0 perplexity 439.3682 ± 23.5771
none 0 acc 0.0984 ± 0.0041
openbookqa 1 none 0 acc 0.1580 ± 0.0163
none 0 acc_norm 0.2260 ± 0.0187
piqa 1 none 0 acc 0.5936 ± 0.0115
none 0 acc_norm 0.5865 ± 0.0115
sciq 1 none 0 acc 0.5710 ± 0.0157
none 0 acc_norm 0.6290 ± 0.0153
wikitext 2 none 0 word_perplexity 87.3261 ± N/A
none 0 byte_perplexity 2.3068 ± N/A
none 0 bits_per_byte 1.2059 ± N/A
winogrande 1 none 0 acc 0.4878 ± 0.0140

hf (pretrained=lomahony/pythia-160m-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 0.2022 ± 0.0117
none 5 acc_norm 0.2270 ± 0.0122
arc_easy 1 none 5 acc 0.3733 ± 0.0099
none 5 acc_norm 0.3746 ± 0.0099
boolq 2 none 5 acc 0.5413 ± 0.0087
hellaswag 1 none 5 acc 0.2770 ± 0.0045
none 5 acc_norm 0.2853 ± 0.0045
lambada_openai 1 none 5 perplexity 1644.8526 ± 87.8870
none 5 acc 0.0491 ± 0.0030
openbookqa 1 none 5 acc 0.1400 ± 0.0155
none 5 acc_norm 0.2200 ± 0.0185
piqa 1 none 5 acc 0.5892 ± 0.0115
none 5 acc_norm 0.5854 ± 0.0115
sciq 1 none 5 acc 0.5100 ± 0.0158
none 5 acc_norm 0.6020 ± 0.0155
wikitext 2 none 5 word_perplexity 87.3261 ± N/A
none 5 byte_perplexity 2.3068 ± N/A
none 5 bits_per_byte 1.2059 ± N/A
winogrande 1 none 5 acc 0.5178 ± 0.0140