scenario-TCR-XLMV_data-cl-cardiff_cl_only_alpha

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: 1.1025
• Accuracy: 0.3387
• F1: 0.1932

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: 1123
• 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	1.0991	0.3164	0.3136
1.0996	2.17	500	1.0987	0.3333	0.1667
1.0996	3.26	750	1.0987	0.3333	0.1667
1.0993	4.35	1000	1.0988	0.3333	0.1667
1.0993	5.43	1250	1.0988	0.3333	0.1667
1.0998	6.52	1500	1.0990	0.3333	0.1667
1.0998	7.61	1750	1.0987	0.3333	0.1667
1.0996	8.7	2000	1.0993	0.3333	0.1667
1.0996	9.78	2250	1.0986	0.3333	0.1667
1.0998	10.87	2500	1.0990	0.3333	0.1667
1.0998	11.96	2750	1.0987	0.3333	0.1667
1.0994	13.04	3000	1.0986	0.3333	0.1667
1.0994	14.13	3250	1.1003	0.3333	0.1667
1.0988	15.22	3500	1.0988	0.3333	0.1667
1.0988	16.3	3750	1.0986	0.3333	0.1667
1.0991	17.39	4000	1.0986	0.3349	0.2410
1.0991	18.48	4250	1.0990	0.3333	0.1667
1.0959	19.57	4500	1.0984	0.3395	0.1945
1.0959	20.65	4750	1.1009	0.3341	0.1821
1.0898	21.74	5000	1.1051	0.3364	0.1934
1.0898	22.83	5250	1.1045	0.3372	0.2101
1.0851	23.91	5500	1.1036	0.3403	0.2024
1.0851	25.0	5750	1.1100	0.3426	0.2129
1.0836	26.09	6000	1.1027	0.3426	0.2045
1.0836	27.17	6250	1.0999	0.3418	0.1990
1.0845	28.26	6500	1.1027	0.3380	0.1918
1.0845	29.35	6750	1.1025	0.3387	0.1932

Framework versions

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