scenario-NON-KD-PR-COPY-CDF-EN-D2_data-en-cardiff_eng_only_delta

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: 4.0029
• Accuracy: 0.4881
• F1: 0.4871

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: 5e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 11213
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	1.72	100	1.1335	0.3668	0.2608
No log	3.45	200	1.0713	0.4810	0.4761
No log	5.17	300	1.3021	0.4943	0.4866
No log	6.9	400	1.3731	0.4934	0.4959
0.732	8.62	500	1.8341	0.4859	0.4871
0.732	10.34	600	2.5112	0.4890	0.4891
0.732	12.07	700	2.3195	0.4877	0.4864
0.732	13.79	800	2.8535	0.4709	0.4705
0.732	15.52	900	3.0835	0.4797	0.4798
0.117	17.24	1000	3.6147	0.4749	0.4745
0.117	18.97	1100	3.7637	0.4727	0.4699
0.117	20.69	1200	3.8660	0.4797	0.4749
0.117	22.41	1300	3.9511	0.4762	0.4713
0.117	24.14	1400	3.9554	0.4797	0.4784
0.0232	25.86	1500	3.9281	0.4841	0.4828
0.0232	27.59	1600	4.0390	0.4850	0.4829
0.0232	29.31	1700	4.0029	0.4881	0.4871

Framework versions

• Transformers 4.33.3
• Pytorch 2.1.1+cu121
• Datasets 2.14.5
• Tokenizers 0.13.3