wnut_distilbert_NER_baseline

This model is a fine-tuned version of distilbert-base-uncased on the wnut_17 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2728
• Precision: 0.5326
• Recall: 0.3791
• F1: 0.4429
• Accuracy: 0.9453

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: 32
• eval_batch_size: 32
• 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
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.3978	1.0	107	0.3026	0.5514	0.1640	0.2529	0.9347
0.1425	2.0	214	0.2761	0.5853	0.2734	0.3727	0.9398
0.0979	3.0	321	0.2680	0.5428	0.3290	0.4097	0.9433
0.0744	4.0	428	0.2787	0.5339	0.3429	0.4176	0.9442
0.0651	5.0	535	0.2728	0.5326	0.3791	0.4429	0.9453

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.3.1
• Tokenizers 0.21.0