Simpletransformers

Fixed

- Fixed bug in Multi-Modal classification when using `evaluate_during_training`.

Added

- Added `interact_single()` method to `ConvAIModel`. This accepts a message and conversation history (and an optional personality). [Amit80007](https://github.com/Amit80007)

Fixed

- Fixed bug in multi modal classification [tekkon](https://github.com/tekkkon)

Changed

- Cleaned `language_modeling_utils.py`. [Pradhy729](https://github.com/Pradhy729)

Added

- All Simple Transformers models can now be used with W&B sweeps.
- `eval_model()` now logs to wandb in the following models (can be turned off with `wandb_log=False`)
- `ClassificationModel`
- `NERModel`
- Model args can now be specified through the relevant dataclass. (E.g. `ClassificationArgs`, `T5Args`, etc.)
- All model args are now saved and loaded automatically with Simple Transformers models.
- Multiprocessed decoding support added to Seq2Seq models
- Custom label support for Classification tasks (except multilabel).
- NER labels can be given as `NERArgs.labels_list` (persists through args saving)

Changed

- Changed `NERModel.eval_model()` to return usable model_outputs
- Improved `tqdm` descriptions in progress bars
- ConvAIModel arg `no_sample` renamed to `do_sample` for consistency