lomahony's picture
Update README.md
0fecdb1 verified
metadata
language:
  - en
tags:
  - pytorch
  - causal-lm
  - pythia
license: apache-2.0
datasets:
  - Anthropic/hh-rlhf

Pythia-70m 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-70m 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-70m-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 0.1715 ± 0.0110
none 0 acc_norm 0.2082 ± 0.0119
arc_easy 1 none 0 acc 0.3384 ± 0.0097
none 0 acc_norm 0.3262 ± 0.0096
boolq 2 none 0 acc 0.4239 ± 0.0086
hellaswag 1 none 0 acc 0.2629 ± 0.0044
none 0 acc_norm 0.2691 ± 0.0044
lambada_openai 1 none 0 perplexity 5937.7964 ± 424.7555
none 0 acc 0.0328 ± 0.0025
openbookqa 1 none 0 acc 0.1580 ± 0.0163
none 0 acc_norm 0.2520 ± 0.0194
piqa 1 none 0 acc 0.5593 ± 0.0116
none 0 acc_norm 0.5392 ± 0.0116
sciq 1 none 0 acc 0.3710 ± 0.0153
none 0 acc_norm 0.4990 ± 0.0158
wikitext 2 none 0 word_perplexity 550.5954 ± N/A
none 0 byte_perplexity 3.2550 ± N/A
none 0 bits_per_byte 1.7027 ± N/A
winogrande 1 none 0 acc 0.4878 ± 0.0140

hf (pretrained=lomahony/pythia-70m-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 0.1869 ± 0.0114
none 5 acc_norm 0.2210 ± 0.0121
arc_easy 1 none 5 acc 0.3207 ± 0.0096
none 5 acc_norm 0.3245 ± 0.0096
boolq 2 none 5 acc 0.4159 ± 0.0086
hellaswag 1 none 5 acc 0.2633 ± 0.0044
none 5 acc_norm 0.2596 ± 0.0044
lambada_openai 1 none 5 perplexity 19968.0749 ± 1423.3001
none 5 acc 0.0202 ± 0.0020
openbookqa 1 none 5 acc 0.1440 ± 0.0157
none 5 acc_norm 0.2420 ± 0.0192
piqa 1 none 5 acc 0.5359 ± 0.0116
none 5 acc_norm 0.5229 ± 0.0117
sciq 1 none 5 acc 0.3240 ± 0.0148
none 5 acc_norm 0.4310 ± 0.0157
wikitext 2 none 5 word_perplexity 550.5954 ± N/A
none 5 byte_perplexity 3.2550 ± N/A
none 5 bits_per_byte 1.7027 ± N/A
winogrande 1 none 5 acc 0.5154 ± 0.0140