metadata
license: mit
base_model: microsoft/deberta-v3-large
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: deberta-v3-large-orgs-v2
results: []
deberta-v3-large-orgs-v2
This model is a fine-tuned version of microsoft/deberta-v3-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1301
- Precision: 0.8062
- Recall: 0.7623
- F1: 0.7837
- Accuracy: 0.9623
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 20
- num_epochs: 3.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0582 | 1.0 | 1710 | 0.1035 | 0.7892 | 0.7879 | 0.7886 | 0.9635 |
| 0.0475 | 2.0 | 3420 | 0.1239 | 0.8058 | 0.7495 | 0.7766 | 0.9609 |
| 0.0288 | 3.0 | 5130 | 0.1301 | 0.8062 | 0.7623 | 0.7837 | 0.9623 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0a0+32f93b1
- Datasets 2.15.0
- Tokenizers 0.15.0