20230928-7-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: 0.4740
• 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
4.4628	0.46	200	0.3220	nan
4.1552	0.91	400	0.3249	nan
3.8537	1.37	600	0.3822	nan
3.5294	1.82	800	0.3914	3.6973
3.378	2.28	1000	0.3770	3.5247
3.3717	2.73	1200	0.3795	nan
3.3769	3.19	1400	0.4033	2.9623
3.2682	3.64	1600	0.3975	3.3065
3.3275	4.1	1800	0.4603	3.0879
3.1686	4.56	2000	0.4385	2.8513
3.1107	5.01	2200	0.4419	nan
3.0418	5.47	2400	0.4372	nan
2.9602	5.92	2600	0.4792	2.8451
2.9038	6.38	2800	0.4772	2.7947
2.8495	6.83	3000	0.415	2.9448
2.9444	7.29	3200	0.4840	nan
2.8306	7.74	3400	0.4806	2.3816
2.8293	8.2	3600	0.4909	2.8671
2.7785	8.66	3800	0.5377	2.6516
2.7991	9.11	4000	0.5164	nan
2.8131	9.57	4200	0.4740	nan

Framework versions

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