metadata
license: mit
base_model: microsoft/deberta-large
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: deberta_large_finetuned_claimdecomp
results: []
deberta_large_finetuned_claimdecomp
This model is a fine-tuned version of microsoft/deberta-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.7614
- Accuracy: 0.205
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: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 30000
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.7304 | 50.0 | 5000 | 1.7493 | 0.255 |
| 1.7282 | 100.0 | 10000 | 1.7495 | 0.205 |
| 1.7196 | 150.0 | 15000 | 1.7457 | 0.255 |
| 1.7107 | 200.0 | 20000 | 1.7462 | 0.255 |
| 1.7107 | 250.0 | 25000 | 1.7666 | 0.205 |
| 1.6992 | 300.0 | 30000 | 1.7614 | 0.205 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.0.0
- Datasets 2.14.5
- Tokenizers 0.14.1