|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- allenai/dolma |
|
- allenai/tulu-v2-sft-mixture-olmo-4096 |
|
- argilla/ultrafeedback-binarized-preferences-cleaned |
|
language: |
|
- en |
|
--- |
|
# OLMo-1B-0724 Instruct |
|
|
|
This is a version of [OLMo-1B-0724-hf](https://huggingface.co/allenai/OLMo-1B-0724-hf) that has undergone SFT and DPO training. |
|
See [the SFT model card for details on SFT training](https://huggingface.co/hamishivi/OLMo-1B-0724-SFT-hf). |
|
|
|
This model is initialised from [OLMo-1B-0724-SFT-hf](https://huggingface.co/hamishivi/OLMo-1B-0724-SFT-hf), and then DPO trained on a cleaned ultrafeedback dataset |
|
for 3 epochs with a batch size of 32, beta of 0.1, linear warmup for 10% of training, and then linear cooldown. |
|
|
|
Evals are as follows: |
|
|
|
| Metric | [OLMo-1B-0724-hf](https://huggingface.co/allenai/OLMo-1B-0724-hf) | [OLMo-1B-0724-SFT-hf](https://huggingface.co/hamishivi/OLMo-1B-0724-SFT-hf) | **[OLMo-1B-0724-Instruct-hf](https://huggingface.co/hamishivi/OLMo-1B-0724-Instruct-hf) (this model!)** | |
|
|---------------------------|-----------------|---------------------|-------------------------| |
|
| MMLU 0-shot | 25.0 | 36.0 | **36.7** | |
|
| GSM8k CoT 8-shot | 7.0 | **12.5** | **12.5** | |
|
| BBH CoT 3-shot | 22.5 | 27.2 | **30.6** | |
|
| HumanEval P@10 | 16.0 | 21.2 | **22.0** | |
|
| AlpacaEval 1 | - | 41.5 | **50.9** | |
|
| AlpacaEval 2 LC | - | **2.7** | 2.5 | |
|
| Toxigen % Toxic | 80.3 | 59.7 | **14.1** | |
|
| TruthfulQA %Info+True | 23.0 | 40.9 | **42.2** | |
|
| IFEval Loose Acc | 20.5 | **26.1** | 24.2 | |
|
| XSTest F1 | 67.6 | **81.9** | 79.8 | |
|
| **Average of above metrics** | 25.2 | 33.0 | **38.7** | |
|
|
|
|
|
Model training and evaluation was performed using [Open-instruct](https://github.com/allenai/open-instruct), so check that out for more details on evaluation. |
