BERT sequence classifier
Captured config identifies BertForSequenceClassification, and the card describes a bert-base-uncased fine-tune for sequence classification.
Open Source Model Profile · textattack
bert-base-uncased-RTE
bert-base-uncased-RTE is a BERT text-classification fine-tune from textattack. Its model card documents TextAttack fine-tuning on GLUE with a reported eval accuracy.
- Publisher
- textattack
- Task
- text-classification
- Model type
- bert
- License
- Unknown
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
bert-base-uncased-RTE is published by textattack as a BERT-based text-classification model. The captured configuration identifies BertForSequenceClassification. According to the model card, it is a bert-base-uncased model fine-tuned for sequence classification with TextAttack on the GLUE dataset.
Recorded capabilities
Documented TextAttack setup
According to the model card, fine-tuning used TextAttack on the GLUE dataset with 5 epochs, batch size 8, learning rate 2e-05, and sequence length 128.
Publisher-reported accuracy
The model card reports a best eval-set accuracy of 0.7256317689530686, found after 2 epochs.
Use cases in the source record
- Sequence-classification experiments that follow the documented TextAttack and GLUE fine-tuning setup.
- RTE-style classification comparisons that reference the card's reported eval accuracy and hyperparameters.
Limitations and unknowns
- No parameter count was extracted from this record.
- No license value was extracted from this record.
- No context-window value was extracted from this record.
- The accuracy figure is a publisher-reported model-card value and has not been independently verified by Ethen.
- Provider state is historical snapshot data, not independently refreshed current availability.
Source and provenance
Source: textattack/bert-base-uncased-RTE
Captured: Unknown. Processed: 2026-09-07T19:34:59.421851+00:00.
TextAttack Model Card This bert-base-uncased model was fine-tuned for sequence classification using TextAttack and the glue dataset loaded using the nlp library. The model was fine-tuned for 5 epochs with a batch size of 8, a learning rate of 2e-05, and a maximum sequence length of 128. Since this was a classification task, the model was trained with a cross-entropy loss function. The best score the model achieved on this task was 0.7256317689530686, as measured by the eval set accuracy, found after 2 epochs. For more information, check out TextAttack on Github .
F001F002F003F004F005F006F008F009F010F011