scenario-TCR-XLMV_data-cl-cardiff_cl_only_alpha2

This model is a fine-tuned version of facebook/xlm-v-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.0986
• Accuracy: 0.3333
• F1: 0.1667

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: 24
• 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	1.09	250	1.0989	0.3333	0.1667
1.1001	2.17	500	1.1000	0.3333	0.1667
1.1001	3.26	750	1.0998	0.3333	0.1667
1.0995	4.35	1000	1.0998	0.3333	0.1667
1.0995	5.43	1250	1.0987	0.3333	0.1667
1.0999	6.52	1500	1.0950	0.3395	0.2409
1.0999	7.61	1750	1.0992	0.3333	0.1667
1.1	8.7	2000	1.0986	0.3333	0.1667
1.1	9.78	2250	1.0989	0.3333	0.1667
1.0996	10.87	2500	1.0999	0.3333	0.1667
1.0996	11.96	2750	1.0991	0.3333	0.1667
1.0994	13.04	3000	1.0989	0.3333	0.1667
1.0994	14.13	3250	1.0988	0.3333	0.1667
1.0992	15.22	3500	1.0987	0.3333	0.1667
1.0992	16.3	3750	1.0990	0.3333	0.1667
1.0994	17.39	4000	1.0986	0.3333	0.1667
1.0994	18.48	4250	1.0986	0.3333	0.1667
1.099	19.57	4500	1.0987	0.3333	0.1667
1.099	20.65	4750	1.0986	0.3333	0.1667
1.0989	21.74	5000	1.0986	0.3333	0.1667
1.0989	22.83	5250	1.0986	0.3333	0.1667
1.0989	23.91	5500	1.0987	0.3333	0.1667
1.0989	25.0	5750	1.0986	0.3333	0.1667
1.099	26.09	6000	1.0986	0.3333	0.1667
1.099	27.17	6250	1.0986	0.3333	0.1667
1.0988	28.26	6500	1.0986	0.3333	0.1667
1.0988	29.35	6750	1.0986	0.3333	0.1667

Framework versions

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