Chayenne comments

Results 307 comments of


                                            Chayenne

ValueError: Column name input_col not in the dataset. Current columns in the dataset: []

I rerun your process but get the right result of the retrieved dataset. 🤔 Would you please run this script to save your retrieved_dataset separately? ```python from prompt2model.prompt_parser import OpenAIInstructionParser,...

ValueError: Column name input_col not in the dataset. Current columns in the dataset: []

BTW, we are developing our colab demo. Maybe it would be easier to use.

ValueError: Column name input_col not in the dataset. Current columns in the dataset: []

https://colab.research.google.com/github/neulab/prompt2model/blob/add_colab_demo/colab_demo.ipynb Try this.

ValueError: Column name input_col not in the dataset. Current columns in the dataset: []

Which dataset? ` generated` or `retrieved`?

ValueError: Column name input_col not in the dataset. Current columns in the dataset: []

`DATASET_DICTS = [dataset_dict, retrieved_dataset_dict]` I am pretty familiar with `generated_dataset`, so I guess the problem lies in `retrieved_dataset_dict`. 🤔 Have you checked it?

Check and, where possible, remove over-broad catches

Sure! I think it's not so complicated to do. But I will fix this after all the merges are done.

Our Prompt Parser cannot support very long prompts

https://github.com/viswavi/prompt2model/issues/158 Also mentioned here.

Remaining Problems Regarding Training metric

@Eren Chenyang Zhao 赵晨阳用on_epoch_end当然可以，但我当时我有几个疑惑（1）如果我希望的eval_strategy是"steps"咋办？（2）这个东西怎么支持trainer自带的选best metrics，你只是做了evaluation把结果打出来了

Mock model loading in `test_run_locally`

And apart from this, my unit test for `SimpleDatasetGenerator` also makes the unit test slow. (And somehow costly)

[Bug] Unrecognized keys in `rope_scaling` for 'rope_type'='yarn': {'original_max_position_embeddings'}

@zhyncs Who is on the long context part?