Mistral trained with the airoboros dataset!
Actual dataset is airoboros 2.2, but it seems to have been replaced on hf with 2.2.1.
Prompt Format:
USER: <prompt>
ASSISTANT:
TruthfulQA:
hf-causal-experimental (pretrained=/home/teknium/dakota/lm-evaluation-harness/airoboros2.2-mistral/,dtype=float16), limit: None, provide_description: False, num_fewshot: 0, batch_size: 8
| Task |Version|Metric|Value | |Stderr|
|-------------|------:|------|-----:|---|-----:|
|truthfulqa_mc| 1|mc1 |0.3562|± |0.0168|
| | |mc2 |0.5217|± |0.0156|
Wandb training charts: https://wandb.ai/teknium1/airoboros-mistral-7b/runs/airoboros-mistral-1?workspace=user-teknium1
More info to come