scenario-NON-KD-SCR-COPY-CDF-EN-D2_data-en-cardiff_eng_only_alpha

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: 5.9553
• Accuracy: 0.3470
• F1: 0.2931

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	1.72	100	1.1171	0.3333	0.1667
No log	3.45	200	1.4228	0.3347	0.1844
No log	5.17	300	1.5974	0.3585	0.2919
No log	6.9	400	2.0154	0.3483	0.2826
0.7851	8.62	500	3.0142	0.3470	0.2821
0.7851	10.34	600	3.6388	0.3426	0.2769
0.7851	12.07	700	4.2592	0.3483	0.3074
0.7851	13.79	800	4.4947	0.3523	0.3288
0.7851	15.52	900	5.0928	0.3408	0.2879
0.0609	17.24	1000	5.2840	0.3448	0.3029
0.0609	18.97	1100	5.5475	0.3457	0.2873
0.0609	20.69	1200	5.7539	0.3426	0.2788
0.0609	22.41	1300	5.8230	0.3430	0.2812
0.0609	24.14	1400	5.8941	0.3408	0.2795
0.0024	25.86	1500	5.9564	0.3448	0.2795
0.0024	27.59	1600	5.9636	0.3466	0.2883
0.0024	29.31	1700	5.9553	0.3470	0.2931

Framework versions

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