| [] | |
| [] | |
| [{"variableName": "ds_dados", "type": "dictionary", "supportedEngines": ["pandas"], "isLocalVariable": false}] | |
| [{"variableName": "ds_dados", "type": "dictionary", "supportedEngines": ["pandas"], "isLocalVariable": false}] | |
| /Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/transformers/tokenization_utils_base.py:1601: FutureWarning: `clean_up_tokenization_spaces` was not set. It will be set to `True` by default. This behavior will be depracted in transformers v4.45, and will be then set to `False` by default. For more details check this issue: https://github.com/huggingface/transformers/issues/31884 | |
| warnings.warn( | |
| dados_tokenizados: | |
| DatasetDict({ | |
| train: Dataset({ | |
| features: ['rotulo', 'rotulo_simples', 'text', 'label', 'input_ids', 'attention_mask'], | |
| num_rows: 4000 | |
| }) | |
| validation: Dataset({ | |
| features: ['rotulo', 'rotulo_simples', 'text', 'label', 'input_ids', 'attention_mask'], | |
| num_rows: 1000 | |
| }) | |
| test: Dataset({ | |
| features: ['rotulo', 'rotulo_simples', 'text', 'label', 'input_ids', 'attention_mask'], | |
| num_rows: 1000 | |
| }) | |
| }) | |