roberta-base-conll2003-pos

This model is a fine-tuned version of roberta-base on the conll2003 dataset. It achieves the following results on the evaluation set:

• Loss: 0.1947
• Precision: 0.9308
• Recall: 0.9300
• F1: 0.9304
• Accuracy: 0.9524

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: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.617	1.0	878	0.2189	0.9239	0.9210	0.9225	0.9470
0.1667	2.0	1756	0.1947	0.9308	0.9300	0.9304	0.9524

Framework versions

• Transformers 4.18.0
• Pytorch 1.14.0.dev20221107
• Datasets 2.2.2
• Tokenizers 0.12.1