metadata

license: mit
base_model: xlm-roberta-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
model-index:
  - name: xlm-roberta-base-Mixed-aug_insert_vi
    results: []

xlm-roberta-base-Mixed-aug_insert_vi

This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.5693
Accuracy: 0.81
F1: 0.7858

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: 16
eval_batch_size: 16
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
0.9098	1.0	82	0.6306	0.75	0.7083
0.6867	2.0	164	0.7511	0.77	0.7175
0.5754	3.0	246	0.5041	0.82	0.7719
0.4309	4.0	328	0.5971	0.8	0.7754
0.3739	5.0	410	0.5693	0.81	0.7858

Framework versions

Transformers 4.32.0
Pytorch 2.0.1+cu118
Datasets 2.14.4
Tokenizers 0.13.3