xlm-roberta-base-clickbait-task1-20-epoch-post

This model is a fine-tuned version of FacebookAI/xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.4947
• Accuracy: 0.7275

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	200	1.5618	0.6875
No log	2.0	400	2.0780	0.69
0.1327	3.0	600	2.2534	0.7175
0.1327	4.0	800	2.3521	0.6725
0.0912	5.0	1000	2.0609	0.695
0.0912	6.0	1200	2.4306	0.7
0.0912	7.0	1400	2.4026	0.6975
0.0488	8.0	1600	2.3745	0.7225
0.0488	9.0	1800	2.5202	0.6825
0.0431	10.0	2000	2.4124	0.7
0.0431	11.0	2200	2.3774	0.7325
0.0431	12.0	2400	2.4398	0.7125
0.0232	13.0	2600	2.6322	0.705
0.0232	14.0	2800	2.5481	0.705
0.0119	15.0	3000	2.5189	0.715
0.0119	16.0	3200	2.5015	0.725
0.0119	17.0	3400	2.4477	0.7125
0.0075	18.0	3600	2.4562	0.7325
0.0075	19.0	3800	2.4725	0.7325
0.0053	20.0	4000	2.4947	0.7275

Framework versions

• Transformers 4.44.0.dev0
• Pytorch 2.4.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1