longformer_model_nocontext
This model is a fine-tuned version of allenai/longformer-base-4096 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3861
- Accuracy: 0.2467
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- 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 |
|---|---|---|---|---|
| 1.3896 | 1.0 | 636 | 1.3861 | 0.2482 |
| 1.39 | 2.0 | 1272 | 1.3860 | 0.2459 |
| 1.3885 | 3.0 | 1908 | 1.3861 | 0.2467 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2
- Downloads last month
- 3
Inference API (serverless) does not yet support transformers models for this pipeline type.