deberta-large_vMCQ
This model is a fine-tuned version of strongpear/deberta-large_vMCQ on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4703
- Accuracy: 0.9102
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.2733 | 0.08 | 500 | 0.4367 | 0.9010 |
0.2226 | 0.17 | 1000 | 0.5558 | 0.9022 |
0.2971 | 0.25 | 1500 | 0.5317 | 0.8999 |
0.3168 | 0.33 | 2000 | 0.8198 | 0.9024 |
0.3367 | 0.42 | 2500 | 0.5744 | 0.9031 |
0.3089 | 0.5 | 3000 | 0.8358 | 0.9018 |
0.3796 | 0.58 | 3500 | 0.7308 | 0.9078 |
0.3663 | 0.67 | 4000 | 0.6393 | 0.9044 |
0.4152 | 0.75 | 4500 | 0.6098 | 0.9123 |
0.3905 | 0.83 | 5000 | 0.5029 | 0.9106 |
0.4446 | 0.91 | 5500 | 0.4821 | 0.9106 |
0.5263 | 1.0 | 6000 | 0.4703 | 0.9102 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.14.1
- Downloads last month
- 1
Inference API (serverless) does not yet support transformers models for this pipeline type.