|
--- |
|
language: |
|
- en |
|
tags: |
|
- pytorch |
|
- causal-lm |
|
- pythia |
|
license: apache-2.0 |
|
datasets: |
|
- Anthropic/hh-rlhf |
|
--- |
|
|
|
[Pythia-2.8b](https://huggingface.co/EleutherAI/pythia-2.8b) DPO finetuned using original DPO code 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/lomahony/direct-preference-optimization/tree/main) |
|
|
|
[wandb log](https://wandb.ai/lauraomahony999/pythia-dpo/runs/blurtl4v) |
|
|
|
See [Pythia-2.8b](https://huggingface.co/EleutherAI/pythia-2.8b) for model details [(paper)](https://arxiv.org/abs/2101.00027). |
|
|
|
hf (pretrained=lomahony/pythia-2.8b-helpful-dpo), 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 | 0.3157|± |0.0136| |
|
| | |none | 0|acc_norm | 0.3447|± |0.0139| |
|
|arc_easy | 1|none | 0|acc | 0.6591|± |0.0097| |
|
| | |none | 0|acc_norm | 0.6002|± |0.0101| |
|
|boolq | 2|none | 0|acc | 0.6239|± |0.0085| |
|
|hellaswag | 1|none | 0|acc | 0.4671|± |0.0050| |
|
| | |none | 0|acc_norm | 0.6107|± |0.0049| |
|
|lambada_openai| 1|none | 0|perplexity | 4.8811|± |0.1354| |
|
| | |none | 0|acc | 0.6264|± |0.0067| |
|
|openbookqa | 1|none | 0|acc | 0.2820|± |0.0201| |
|
| | |none | 0|acc_norm | 0.4040|± |0.0220| |
|
|piqa | 1|none | 0|acc | 0.7568|± |0.0100| |
|
| | |none | 0|acc_norm | 0.7557|± |0.0100| |
|
|sciq | 1|none | 0|acc | 0.8900|± |0.0099| |
|
| | |none | 0|acc_norm | 0.8340|± |0.0118| |
|
|wikitext | 2|none | 0|word_perplexity|13.9186|± |N/A | |
|
| | |none | 0|byte_perplexity| 1.6363|± |N/A | |
|
| | |none | 0|bits_per_byte | 0.7104|± |N/A | |
|
|winogrande | 1|none | 0|acc | 0.6046|± |0.0137| |
|
|
|
|
