xlm-roberta-large-finetuned-conll03-english-clickbait-task1-20-epoch-post

This model is a fine-tuned version of FacebookAI/xlm-roberta-large-finetuned-conll03-english on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.4061
• Accuracy: 0.7375

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	0.9494	0.58
No log	2.0	400	0.7693	0.6775
0.902	3.0	600	0.7246	0.7175
0.902	4.0	800	0.7657	0.7125
0.5812	5.0	1000	0.7353	0.7275
0.5812	6.0	1200	0.8877	0.72
0.5812	7.0	1400	1.2938	0.6875
0.3056	8.0	1600	1.4323	0.7275
0.3056	9.0	1800	1.7561	0.6975
0.1761	10.0	2000	2.0374	0.735
0.1761	11.0	2200	1.9953	0.7025
0.1761	12.0	2400	1.9827	0.715
0.0796	13.0	2600	2.0891	0.73
0.0796	14.0	2800	2.2108	0.7275
0.0321	15.0	3000	2.2815	0.72
0.0321	16.0	3200	2.3784	0.72
0.0321	17.0	3400	2.4105	0.7225
0.0119	18.0	3600	2.3948	0.73
0.0119	19.0	3800	2.3702	0.745
0.0112	20.0	4000	2.4061	0.7375

Framework versions

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