roberta-base_fact_updates

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

• Loss: 1.4529

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: 1e-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
• lr_scheduler_warmup_steps: 500
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
0.5452	1.0	443	0.5015
0.4166	2.0	886	0.3902
0.3616	3.0	1329	0.3877
0.3351	4.0	1772	0.4432
0.2505	5.0	2215	0.4358
0.2523	6.0	2658	0.5565
0.2018	7.0	3101	0.5742
0.1997	8.0	3544	0.8977
0.1036	9.0	3987	0.9231
0.2234	10.0	4430	1.0524
0.0911	11.0	4873	1.1583
0.1545	12.0	5316	1.2516
0.0324	13.0	5759	1.3600
0.0427	14.0	6202	1.4610
0.0232	15.0	6645	1.4529

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu118
• Datasets 2.20.0
• Tokenizers 0.19.1