20230928-6-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: 0.4316
• 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
4.4819	0.46	200	0.2833	nan
4.1944	0.91	400	0.3591	nan
3.9494	1.37	600	0.3672	nan
3.6661	1.82	800	0.3664	nan
3.5002	2.28	1000	0.4206	nan
3.4947	2.73	1200	0.4039	3.3402
3.3877	3.19	1400	0.4462	2.4673
3.4862	3.64	1600	0.3954	3.2247
3.2374	4.1	1800	0.4565	2.6799
3.1623	4.56	2000	0.4618	nan
3.2013	5.01	2200	0.4556	2.6895
2.9187	5.47	2400	0.4640	2.7996
2.8511	5.92	2600	0.4878	nan
2.9993	6.38	2800	0.4494	nan
2.9954	6.83	3000	0.4606	2.5372
2.8736	7.29	3200	0.45	2.5804
2.7759	7.74	3400	0.4580	3.0063
2.8025	8.2	3600	0.4645	2.3861
2.9357	8.66	3800	0.5027	nan
2.681	9.11	4000	0.5	2.3928
2.7348	9.57	4200	0.4316	nan

Framework versions

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