edos-2023-baseline-xlm-roberta-base-label_vector

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

• Loss: 1.5797
• F1: 0.2746

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: 1e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 5
• num_epochs: 12
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	F1
2.1596	1.18	100	1.9772	0.0891
1.8651	2.35	200	1.7720	0.1159
1.6848	3.53	300	1.7193	0.1892
1.5532	4.71	400	1.6794	0.2191
1.466	5.88	500	1.6095	0.2419
1.3562	7.06	600	1.5771	0.2694
1.2909	8.24	700	1.5761	0.2707
1.2027	9.41	800	1.5747	0.2764
1.192	10.59	900	1.5893	0.2686
1.1256	11.76	1000	1.5797	0.2746

Framework versions

• Transformers 4.24.0
• Pytorch 1.12.1+cu113
• Datasets 2.7.1
• Tokenizers 0.13.2