scenario-TCR-XLMV_data-cl-cardiff_cl_only_gamma2

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: 77
• 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	1.0987	0.3333	0.1667
1.0995	2.17	500	1.0986	0.3333	0.1667
1.0995	3.26	750	1.0994	0.3333	0.1667
1.1002	4.35	1000	1.0988	0.3333	0.1667
1.1002	5.43	1250	1.0989	0.3333	0.1667
1.1002	6.52	1500	1.0989	0.3333	0.1667
1.1002	7.61	1750	1.0987	0.3333	0.1667
1.0992	8.7	2000	1.0996	0.3333	0.1667
1.0992	9.78	2250	1.0988	0.3333	0.1667
1.0997	10.87	2500	1.0987	0.3333	0.1667
1.0997	11.96	2750	1.0987	0.3333	0.1667
1.0995	13.04	3000	1.0988	0.3333	0.1667
1.0995	14.13	3250	1.0986	0.3333	0.1667
1.0995	15.22	3500	1.0987	0.3333	0.1667
1.0995	16.3	3750	1.0986	0.3333	0.1667
1.0996	17.39	4000	1.0987	0.3333	0.1667
1.0996	18.48	4250	1.0986	0.3333	0.1667
1.0994	19.57	4500	1.0986	0.3333	0.1667
1.0994	20.65	4750	1.0987	0.3333	0.1667
1.0992	21.74	5000	1.0987	0.3333	0.1667
1.0992	22.83	5250	1.0987	0.3333	0.1667
1.0988	23.91	5500	1.0986	0.3333	0.1667
1.0988	25.0	5750	1.0986	0.3333	0.1667
1.0992	26.09	6000	1.0987	0.3333	0.1667
1.0992	27.17	6250	1.0986	0.3333	0.1667
1.099	28.26	6500	1.0986	0.3333	0.1667
1.099	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