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

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

• Loss: 1.0677
• Accuracy: 0.405

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	1.0717	0.45
No log	2.0	400	1.0755	0.405
1.0531	3.0	600	1.0676	0.405
1.0531	4.0	800	1.0656	0.405
1.0447	5.0	1000	1.0832	0.405
1.0447	6.0	1200	1.0699	0.385
1.0447	7.0	1400	1.0649	0.405
1.0417	8.0	1600	1.0682	0.405
1.0417	9.0	1800	1.0692	0.405
1.0425	10.0	2000	1.0665	0.405
1.0425	11.0	2200	1.0705	0.405
1.0425	12.0	2400	1.0793	0.405
1.0402	13.0	2600	1.0674	0.405
1.0402	14.0	2800	1.0638	0.405
1.0428	15.0	3000	1.0710	0.405
1.0428	16.0	3200	1.0686	0.405
1.0428	17.0	3400	1.0700	0.405
1.0406	18.0	3600	1.0669	0.405
1.0406	19.0	3800	1.0683	0.405
1.0375	20.0	4000	1.0677	0.405

Framework versions

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