<!-- 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. -->
sa_BERT_no_pretrain_rte
This model is a fine-tuned version of bert-base-uncased on the GLUE RTE dataset. It achieves the following results on the evaluation set:
- Loss: 0.6909
- Accuracy: 0.5307
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: 4e-05
- train_batch_size: 96
- eval_batch_size: 96
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7596 | 1.0 | 26 | 0.6909 | 0.5307 |
| 0.6968 | 2.0 | 52 | 0.6914 | 0.5235 |
| 0.7026 | 3.0 | 78 | 0.6911 | 0.5307 |
| 0.6961 | 4.0 | 104 | 0.6928 | 0.5379 |
| 0.7114 | 5.0 | 130 | 0.6917 | 0.5271 |
| 0.7005 | 6.0 | 156 | 0.7069 | 0.4729 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3
