tests

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

• Loss: 2.2929
• F1: 0.6892

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: 3e-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	F1
No log	1.0	65	1.3350	0.5730
No log	2.0	130	1.0753	0.6595
No log	3.0	195	1.0889	0.6649
No log	4.0	260	1.2171	0.6568
No log	5.0	325	1.2974	0.6622
No log	6.0	390	1.5941	0.6541
No log	7.0	455	1.8704	0.6486
0.564	8.0	520	2.1442	0.6324
0.564	9.0	585	2.0927	0.6703
0.564	10.0	650	2.0792	0.6865
0.564	11.0	715	2.0973	0.6892
0.564	12.0	780	2.2011	0.6757
0.564	13.0	845	2.2499	0.6865
0.564	14.0	910	2.2436	0.6865
0.564	15.0	975	2.2455	0.6892
0.0074	16.0	1040	2.2756	0.6892
0.0074	17.0	1105	2.2865	0.6919
0.0074	18.0	1170	2.2874	0.6892
0.0074	19.0	1235	2.2905	0.6865
0.0074	20.0	1300	2.2929	0.6892

Framework versions

• Transformers 4.28.1
• Pytorch 2.0.0+cu118
• Datasets 2.11.0
• Tokenizers 0.13.3