SEMEVAL23_TASK3_SUBTASK1_MULTI

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: 1.6313
• F1: 0.6299

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	F1
0.9669	1.0	160	0.9574	0.4075
0.4214	2.0	320	0.6809	0.5769
0.0096	3.0	480	1.3114	0.4152
0.2681	4.0	640	0.7792	0.6122
0.0007	5.0	800	1.3213	0.5765
0.0005	6.0	960	1.7983	0.5749
0.0011	7.0	1120	2.2000	0.5298
0.0008	8.0	1280	1.3757	0.5812
0.0007	9.0	1440	1.5493	0.5990
0.001	10.0	1600	1.4796	0.6233
0.0008	11.0	1760	1.4954	0.6251
0.0002	12.0	1920	1.6313	0.6299
0.0004	13.0	2080	1.5037	0.6296
0.0008	14.0	2240	1.5526	0.6277
0.0001	15.0	2400	1.5745	0.6254

Framework versions

• Transformers 4.33.1
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3