<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
roberta-small-snli
This model was trained from scratch on the snli dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.4118
- eval_p: 0.8492
- eval_r: 0.8469
- eval_f1: 0.8474
- eval_runtime: 17.312
- eval_samples_per_second: 567.467
- eval_steps_per_second: 35.467
- step: 0
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 4
Framework versions
- Transformers 4.21.1
- Pytorch 1.12.1
- Datasets 2.6.1
- Tokenizers 0.12.1