distilbert-base-uncased-finetuned-squad-ep8-batch16
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: 1.5457
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: 8
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.281 | 1.0 | 2767 | 1.1843 |
| 1.0039 | 2.0 | 5534 | 1.1213 |
| 0.8163 | 3.0 | 8301 | 1.1900 |
| 0.6551 | 4.0 | 11068 | 1.2455 |
| 0.5525 | 5.0 | 13835 | 1.2912 |
| 0.4622 | 6.0 | 16602 | 1.3989 |
| 0.3968 | 7.0 | 19369 | 1.4710 |
| 0.3498 | 8.0 | 22136 | 1.5457 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1
- Datasets 2.19.2
- Tokenizers 0.19.1
- Downloads last month
- 4
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for wieheistdu/distilbert-base-uncased-finetuned-squad-ep8-batch16
Base model
distilbert/distilbert-base-uncased