metadata
tags:
- generated_from_trainer
model-index:
- name: longformer_sciq
results: []
longformer_sciq
This model is a fine-tuned version of VuongQuoc/longformer_sciq on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5326
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-06
- train_batch_size: 2
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1931 | 0.2 | 20 | 0.7457 |
| 0.7677 | 0.4 | 40 | 0.7063 |
| 1.0391 | 0.6 | 60 | 0.6745 |
| 1.2915 | 0.8 | 80 | 0.6316 |
| 1.1399 | 1.0 | 100 | 0.6652 |
| 0.9975 | 1.2 | 120 | 0.6134 |
| 0.9232 | 1.4 | 140 | 0.5561 |
| 0.8026 | 1.6 | 160 | 0.5422 |
| 0.7188 | 1.8 | 180 | 0.5370 |
| 0.7272 | 2.0 | 200 | 0.5326 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0+cpu
- Datasets 2.1.0
- Tokenizers 0.13.3