20230928-8-xlm-roberta-base-new

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

• Accuracy: 0.4880
• Loss: nan

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: 10

Training results

Training Loss	Epoch	Step	Accuracy	Validation Loss
4.3143	0.46	200	0.3054	4.1884
4.0232	0.91	400	0.3790	3.4612
3.8668	1.37	600	0.3525	3.5908
3.7855	1.82	800	0.4058	nan
3.58	2.28	1000	0.3795	nan
3.3848	2.73	1200	0.4046	nan
3.2678	3.19	1400	0.4439	3.1686
3.3909	3.64	1600	0.4248	nan
3.2549	4.1	1800	0.4460	nan
3.1552	4.56	2000	0.5051	2.5496
3.1933	5.01	2200	0.4706	nan
2.9075	5.47	2400	0.5124	2.8447
3.0546	5.92	2600	0.5136	nan
2.9636	6.38	2800	0.4931	2.7494
2.9684	6.83	3000	0.4962	nan
2.8127	7.29	3200	0.5077	2.5534
2.8798	7.74	3400	0.4961	2.8044
2.7446	8.2	3600	0.5071	2.7707
2.7827	8.66	3800	0.4919	nan
2.732	9.11	4000	0.4897	2.4495
2.7996	9.57	4200	0.4880	nan

Framework versions

• Transformers 4.33.3
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3