If you do not know how to start you can check our jupyther notebook how to use pretrained jiant model
You can also train your model in any way, but be careful with output data!
- Use the IDs and labels present in the unlabeled test JSONLs to generate one JSONL of predictions for each of the test files. Each line of the prediction files should be a JSONL entry, with a sorted idx field to identify the example and a `label` field with the prediction.
- Make sure that each prediction JSONL is named according to the following:
- DaNetQA: DaNetQA.jsonl
- RCB: RCB.jsonl
- PARus: PARus.jsonl
- MuSeRC: MuSeRC.jsonl
- RuCoS: RuCoS.jsonl
- TERRa: TERRa.jsonl
- Russian words in Context: RUSSE.jsonl
- Russian Winograd Schema: RWSD.jsonl
- Broad Coverage Diagnostics: LiDiRus.jsonl
- You can also submit incomplete zip. In this case you will get the score only for those tasks that you upload.