roberta-stance

This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.1034
• Accuracy: 0.6232
• Precision: 0.6077
• Recall: 0.6301
• F1: 0.6127

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
No log	1.0	46	1.0695	0.5184	0.1728	0.3333	0.2276
No log	2.0	92	1.0372	0.5184	0.1728	0.3333	0.2276
No log	3.0	138	0.9757	0.5746	0.4121	0.4214	0.3711
No log	4.0	184	0.8826	0.6063	0.5820	0.5298	0.5423
No log	5.0	230	0.8429	0.6166	0.6159	0.6011	0.5824
No log	6.0	276	0.8153	0.6472	0.6257	0.6376	0.6294
No log	7.0	322	0.8600	0.6559	0.6492	0.6427	0.6315
No log	8.0	368	0.8912	0.6299	0.6138	0.6159	0.6108
No log	9.0	414	1.0091	0.6161	0.6048	0.6345	0.6084
No log	10.0	460	1.1034	0.6232	0.6077	0.6301	0.6127

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0