distilbert-base-uncased-finetuned-pfe
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: 1.9517
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
No log | 1.0 | 6 | 2.8673 |
No log | 2.0 | 12 | 2.7271 |
No log | 3.0 | 18 | 2.5814 |
No log | 4.0 | 24 | 2.5083 |
No log | 5.0 | 30 | 2.3478 |
No log | 6.0 | 36 | 2.3432 |
No log | 7.0 | 42 | 2.2518 |
No log | 8.0 | 48 | 2.2160 |
No log | 9.0 | 54 | 2.1958 |
No log | 10.0 | 60 | 2.1662 |
No log | 11.0 | 66 | 2.1043 |
No log | 12.0 | 72 | 2.0557 |
No log | 13.0 | 78 | 2.0443 |
No log | 14.0 | 84 | 1.9886 |
No log | 15.0 | 90 | 1.9999 |
No log | 16.0 | 96 | 1.9629 |
No log | 17.0 | 102 | 1.9503 |
No log | 18.0 | 108 | 1.9439 |
No log | 19.0 | 114 | 1.9504 |
No log | 20.0 | 120 | 1.9517 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 11