<!-- 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. -->
seqcl
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8302
- Accuracy: 0.6444
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: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 9 | 0.6533 | 0.6667 |
| No log | 2.0 | 18 | 0.7237 | 0.5333 |
| No log | 3.0 | 27 | 0.6231 | 0.7111 |
| No log | 4.0 | 36 | 0.7202 | 0.6 |
| No log | 5.0 | 45 | 0.6903 | 0.6444 |
| No log | 6.0 | 54 | 0.7546 | 0.6222 |
| No log | 7.0 | 63 | 0.7595 | 0.6222 |
| No log | 8.0 | 72 | 0.7999 | 0.6222 |
| No log | 9.0 | 81 | 0.8137 | 0.6444 |
| No log | 10.0 | 90 | 0.8302 | 0.6444 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
