distilbert-base-uncased-distilled-squad-BiLSTM-finetuned-SRH-oldparam11
This model is a fine-tuned version of allistair99/distilbert-base-uncased-distilled-squad-BiLSTM-finetuned-squad-optiparam on the srh_test66 dataset. It achieves the following results on the evaluation set:
- Loss: 3.1976
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 43 | 3.6778 |
| No log | 2.0 | 86 | 3.2967 |
| No log | 3.0 | 129 | 3.1976 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1