<!-- 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. -->
bert-base-uncased-rte-epochs-10-lr-1e-05
This model is a fine-tuned version of bert-base-uncased on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.6968
- Accuracy: 0.74
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 28
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
No log | 1.0 | 75 | 0.6999 | 0.44 |
No log | 2.0 | 150 | 0.6216 | 0.69 |
No log | 3.0 | 225 | 0.5941 | 0.69 |
No log | 4.0 | 300 | 0.5779 | 0.74 |
No log | 5.0 | 375 | 0.5871 | 0.73 |
No log | 6.0 | 450 | 0.6203 | 0.76 |
0.5133 | 7.0 | 525 | 0.6944 | 0.76 |
0.5133 | 8.0 | 600 | 0.6647 | 0.75 |
0.5133 | 9.0 | 675 | 0.6803 | 0.78 |
0.5133 | 10.0 | 750 | 0.6968 | 0.74 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1
- Datasets 2.14.4
- Tokenizers 0.13.3