--- language: - en tags: - pytorch - causal-lm - pythia license: apache-2.0 datasets: - Anthropic/hh-rlhf --- # Infos Pythia-1.4b supervised finetuned with Anthropic-hh-rlhf dataset for 1 epoch (sft-model), before DPO [(paper)](https://arxiv.org/abs/2305.18290) with same dataset for 1 epoch. [wandb log](https://wandb.ai/pythia_dpo/Pythia_DPO_new/runs/6yrtkj3s) See [Pythia-1.4b](https://huggingface.co/EleutherAI/pythia-1.4b) for model details [(paper)](https://arxiv.org/abs/2101.00027). # Benchmark raw results: Results for the base model are taken from the [Pythia paper](https://arxiv.org/abs/2101.00027). ## Zero shot | Task | 1.4B_base | 1.4B_sft | 1.4B_dpo | |------------------|--------------:|--------------:|---------------:| | Lambada (OpenAI) | 0.616 ± 0.007 | 0.5977 ± 0.0068 | 0.5948 ± 0.0068 | | PIQA | 0.711 ± 0.011 | 0.7133 ± 0.0106 | 0.7165 ± 0.0105 | | WinoGrande | 0.573 ± 0.014 | 0.5793 ± 0.0139 | 0.5746 ± 0.0139 | | WSC | 0.365 ± 0.047 | 0.3654 ± 0.0474 | 0.3654 ± 0.0474 | | ARC - Easy | 0.606 ± 0.010 | 0.6098 ± 0.0100 | 0.6199 ± 0.0100 | | ARC - Challenge | 0.260 ± 0.013 | 0.2696 ± 0.0130 | 0.2884 ± 0.0132 | | SciQ | 0.865 ± 0.011 | 0.8540 ± 0.0112 | 0.8550 ± 0.0111 | | LogiQA | 0.210 ± 0.016 | NA | NA | ## Five shot | Task | 1.4B_base | 1.4B_sft | 1.4B_dpo | |------------------|----------------|----------------|----------------| | Lambada (OpenAI) | 0.578 ± 0.007 | 0.5201 ± 0.007 | 0.5247 ± 0.007 | | PIQA | 0.705 ± 0.011 | 0.7176 ± 0.0105| 0.7209 ± 0.0105| | WinoGrande | 0.580 ± 0.014 | 0.5793 ± 0.0139| 0.5746 ± 0.0139| | WSC | 0.365 ± 0.047 | 0.5288 ± 0.0492| 0.5769 ± 0.0487| | ARC - Easy | 0.643 ± 0.010 | 0.6376 ± 0.0099| 0.6561 ± 0.0097| | ARC - Challenge | 0.290 ± 0.013 | 0.2935 ± 0.0133| 0.3166 ± 0.0136| | SciQ | 0.92 ± 0.009 | 0.9180 ± 0.0087| 0.9150 ± 0.0088| | LogiQA | 0.240 ± 0.017 | N/A | N/A |