metadata

license: mit
base_model: FacebookAI/xlm-roberta-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
model-index:
  - name: xlm-roberta-base-finetuned-m_rew_pun_seller
    results: []

xlm-roberta-base-finetuned-m_rew_pun_seller

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

Loss: 0.5943
Accuracy: 0.825
F1: 0.8414

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
0.6773	1.0	26	0.5943	0.745	0.7776
0.5026	2.0	52	0.5594	0.77	0.7981
0.4345	3.0	78	0.5523	0.83	0.8429
0.3589	4.0	104	0.5751	0.81	0.8285
0.3403	5.0	130	0.5943	0.825	0.8414

Framework versions

Transformers 4.41.2
Pytorch 2.3.0+cu121
Tokenizers 0.19.1