metadata
license: mit
base_model: microsoft/deberta-v3-large
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: training1
results: []
training1
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: 0.1739
- Accuracy: 0.9431
- F1: 0.8115
- Precision: 0.8659
- Recall: 0.7636
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: 9.946303722432942e-06
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.6954 | 1.0 | 61 | 0.6728 | 0.6127 | 0.1189 | 0.0936 | 0.1629 |
| 0.5462 | 2.0 | 122 | 0.3988 | 0.8683 | 0.4352 | 0.6972 | 0.3163 |
| 0.3711 | 3.0 | 183 | 0.3401 | 0.8765 | 0.4703 | 0.7535 | 0.3419 |
| 0.3269 | 4.0 | 244 | 0.3175 | 0.8883 | 0.4785 | 0.9524 | 0.3195 |
| 0.2899 | 5.0 | 305 | 0.2781 | 0.9042 | 0.5961 | 0.92 | 0.4409 |
| 0.2568 | 6.0 | 366 | 0.2576 | 0.9144 | 0.6745 | 0.865 | 0.5527 |
| 0.2176 | 7.0 | 427 | 0.2305 | 0.9242 | 0.7376 | 0.8287 | 0.6645 |
| 0.1879 | 8.0 | 488 | 0.2014 | 0.9329 | 0.7579 | 0.8991 | 0.6550 |
| 0.1541 | 9.0 | 549 | 0.2002 | 0.9329 | 0.7842 | 0.8095 | 0.7604 |
| 0.1275 | 10.0 | 610 | 0.1739 | 0.9431 | 0.8115 | 0.8659 | 0.7636 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1