NLPGroupProject-Finetune-Funnel-Transformer
This model is a fine-tuned version of funnel-transformer/intermediate-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3863
- Accuracy: 0.263
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: 5e-05
- train_batch_size: 2
- eval_batch_size: 2
- 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 | Accuracy |
|---|---|---|---|---|
| 1.4073 | 0.25 | 500 | 1.3863 | 0.262 |
| 1.403 | 0.5 | 1000 | 1.3863 | 0.275 |
| 1.4031 | 0.75 | 1500 | 1.3863 | 0.263 |
| 1.4035 | 1.0 | 2000 | 1.3863 | 0.259 |
| 1.3984 | 1.25 | 2500 | 1.3863 | 0.283 |
| 1.3904 | 1.5 | 3000 | 1.3863 | 0.263 |
| 1.3977 | 1.75 | 3500 | 1.3863 | 0.252 |
| 1.3949 | 2.0 | 4000 | 1.3863 | 0.272 |
| 1.3979 | 2.25 | 4500 | 1.3863 | 0.258 |
| 1.3965 | 2.5 | 5000 | 1.3863 | 0.225 |
| 1.3944 | 2.75 | 5500 | 1.3863 | 0.246 |
| 1.3999 | 3.0 | 6000 | 1.3863 | 0.263 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.2+cu118
- Datasets 2.19.0
- Tokenizers 0.19.1