<!-- 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. -->
robertaboolq-finetuned-answer-polarity-2e6
This model is a fine-tuned version of shahrukhx01/roberta-base-boolq on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.3926
- F1: 0.8718
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-06
- 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: linear
- num_epochs: 6
Training results
Training Loss | Epoch | Step | Validation Loss | F1 |
---|---|---|---|---|
No log | 1.0 | 221 | 0.6677 | 0.7870 |
0.8099 | 2.0 | 442 | 0.4562 | 0.8663 |
0.3336 | 3.0 | 663 | 0.4096 | 0.8550 |
0.3336 | 4.0 | 884 | 0.3876 | 0.8739 |
0.221 | 5.0 | 1105 | 0.4030 | 0.8729 |
0.1842 | 6.0 | 1326 | 0.3926 | 0.8718 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3