metadata
library_name: transformers
license: mit
base_model: microsoft/mdeberta-v3-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: piiranha-gretelai-test
results: []
piiranha-gretelai-test
This model is a fine-tuned version of microsoft/mdeberta-v3-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1008
- Precision: 0.6935
- Recall: 0.7739
- F1: 0.7315
- Accuracy: 0.9695
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_ratio: 0.05
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1561 | 0.3342 | 250 | 0.1173 | 0.6640 | 0.7056 | 0.6842 | 0.9655 |
| 0.102 | 0.6684 | 500 | 0.1009 | 0.6870 | 0.7693 | 0.7258 | 0.9687 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1