Open B-201 opened 6 hours ago
I tested some of the datasets in the eval set and found that the results are higher than those in the paper. Is there an update to the LoRA model compared to what was presented in the paper?
I think some fluctuations is reasonable. We do have some update checkpoints coming soon trained with large batch size.
I tested some of the datasets in the eval set and found that the results are higher than those in the paper. Is there an update to the LoRA model compared to what was presented in the paper?