metadata
license: mit
base_model: microsoft/deberta-v3-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: deberta-v3-base-orgs-v1
results: []
deberta-v3-base-orgs-v1
This model is a fine-tuned version of microsoft/deberta-v3-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1186
- Precision: 0.8127
- Recall: 0.7735
- F1: 0.7927
- Accuracy: 0.9632
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: 0.0001
- train_batch_size: 128
- eval_batch_size: 256
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0706 | 0.7 | 600 | 0.1138 | 0.7590 | 0.7793 | 0.7690 | 0.9602 |
| 0.0526 | 1.4 | 1200 | 0.1113 | 0.7942 | 0.7799 | 0.7870 | 0.9617 |
| 0.0409 | 2.11 | 1800 | 0.1125 | 0.7911 | 0.7839 | 0.7875 | 0.9627 |
| 0.0376 | 2.81 | 2400 | 0.1186 | 0.8127 | 0.7735 | 0.7927 | 0.9632 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0a0+32f93b1
- Datasets 2.15.0
- Tokenizers 0.15.0