<!-- 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. -->
distilbert-base-uncased-becas-5
This model is a fine-tuned version of distilbert-base-uncased on the becasv2 dataset. It achieves the following results on the evaluation set:
- Loss: 4.8805
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: 3e-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 |
|---|---|---|---|
| No log | 1.0 | 5 | 5.4344 |
| No log | 2.0 | 10 | 4.9002 |
| No log | 3.0 | 15 | 4.3601 |
| No log | 4.0 | 20 | 4.4784 |
| No log | 5.0 | 25 | 4.3712 |
| No log | 6.0 | 30 | 4.3958 |
| No log | 7.0 | 35 | 4.8476 |
| No log | 8.0 | 40 | 4.6108 |
| No log | 9.0 | 45 | 4.7711 |
| No log | 10.0 | 50 | 4.8805 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0+cu113
- Datasets 2.3.2
- Tokenizers 0.12.1
