Lidor-Mashiach/bert-base-snli

BERT Base fine tuned on SNLI

Model

This checkpoint is based on google-bert/bert-base-uncased.

It was fine tuned on the SNLI training split.

The model predicts one of three labels:

Label	Meaning
0	entailment
1	neutral
2	contradiction

The input order is premise first and hypothesis second.

Evaluation

Accuracy was measured on the official SNLI validation and test splits.

Split	Accuracy	Examples
Validation	91.05%	9,842
Test	90.88%	9,824

These values are plain classification accuracy.

Comparisons should use the same SNLI splits and the same label mapping.

The machine readable results are stored in baseline_eval.json.

Training

Setting	Value
Base model	google-bert/bert-base-uncased
Epochs	2
Batch size	32
Gradient accumulation steps	1
Learning rate	0.000049777038124886604
Weight decay	0.01
Warmup ratio	0.07796913153849455
Label smoothing	0.05
Adam beta 2	0.999
Maximum sequence length	128
Seed	1299843651
Numerical precision	BF16

The hyperparameters were selected for this model and dataset combination.

The full training record is stored in model_card.json.

Use

Load the repository with AutoTokenizer and AutoModelForSequenceClassification from the Transformers library.

Pass the premise and hypothesis as a text pair.

Use a maximum sequence length of 128 to match training.

Files

File	Purpose
model.safetensors	Model weights
config.json	Architecture and label mapping
tokenizer.json	Tokenizer data
tokenizer_config.json	Tokenizer settings
baseline_eval.json	Evaluation results
model_card.json	Training record and provenance
README.md	Model card

Limitations

The model was trained and evaluated on English SNLI data.

Performance on other NLI datasets may differ.

The training accuracy was 94.68%, while held out accuracy was lower. This gap should be considered when using the checkpoint.

The model can inherit errors and biases from the base model and the training data.

The checkpoint has not been evaluated for high risk or safety critical use.

License

The base model google-bert/bert-base-uncased is licensed under Apache 2.0.

The SNLI training data is licensed under CC BY-SA 4.0.

This checkpoint is released under CC BY-SA 4.0.

Users must follow the terms of the base model and the SNLI dataset.

Adapted material must be shared under CC BY-SA 4.0 or a compatible license.

Associated research

This model was trained as part of the following research manuscript:

“Opening the Black Box: Localizing semantic inconsistency in NLI models with Deep k -Nearest Neighbors”

The manuscript is in preparation. It has not been submitted or published.

This section will be updated when a public preprint or an accepted version becomes available.

Citation

Until the paper is public, please cite this model repository:

@misc{mashiach2026bertsnli,
  author = {Lidor Mashiach},
  title = {BERT Base fine tuned on SNLI},
  year = {2026},
  publisher = {Hugging Face},
  url = {https://huggingface.co/Lidor-Mashiach/bert-base-snli}
}

Please also cite the BERT and SNLI papers.

Contact

Questions, corrections, and reproducibility reports can be posted in the Community tab of this repository.