Hugging Face's logo

domenicrosati
/
deberta-v3-large-finetuned-synthetic-multi-class

Text Classification Transformers PyTorch TensorBoard deberta-v2 generated_from_trainer Inference Endpoints
Model card Files Metrics Community
2
deberta-v3-large-finetuned-synthetic-multi-class / README.md
domenicrosati's picture
domenicrosati
update model card README.md
a9b9dab
preview code
|
raw history blame contribute delete
No virus
1.76 kB
metadata
license: mit
tags:
  - text-classification
  - generated_from_trainer
metrics:
  - f1
  - precision
  - recall
model-index:
  - name: deberta-v3-large-finetuned-synthetic-multi-class
    results: []

deberta-v3-large-finetuned-synthetic-multi-class

This model is a fine-tuned version of microsoft/deberta-v3-large on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0223
  • F1: 0.9961
  • Precision: 0.9961
  • Recall: 0.9961

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: 6e-06
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 50
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss F1 Precision Recall
0.0278 1.0 10953 0.0352 0.9936 0.9935 0.9936
0.0143 2.0 21906 0.0252 0.9952 0.9952 0.9953
0.0014 3.0 32859 0.0267 0.9955 0.9955 0.9955

Framework versions

  • Transformers 4.18.0
  • Pytorch 1.11.0
  • Datasets 2.1.0
  • Tokenizers 0.12.1