metadata

license: mit
base_model: microsoft/deberta-v3-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
model-index:
  - name: deberta-v3-base-finetuned-emo_une
    results: []

deberta-v3-base-finetuned-emo_une

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

Loss: 0.4500
Accuracy: 0.865
F1: 0.8681

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: 2e-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
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.68	1.0	26	0.6269	0.585	0.6107
0.5312	2.0	52	0.4552	0.86	0.8578
0.3854	3.0	78	0.4478	0.84	0.8441
0.3005	4.0	104	0.4395	0.86	0.8644
0.258	5.0	130	0.4500	0.865	0.8681

Framework versions

Transformers 4.41.2
Pytorch 2.3.0+cu121
Tokenizers 0.19.1