token_classification_wnut_model

This model is a fine-tuned version of ae-314/token_classification_wnut_model on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.3924
Precision: 0.5017
Recall: 0.4124
F1: 0.4527
Accuracy: 0.9446

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-09
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	213	0.3924	0.5017	0.4124	0.4527	0.9446
No log	2.0	426	0.3924	0.5017	0.4124	0.4527	0.9446
0.0022	3.0	639	0.3924	0.5017	0.4124	0.4527	0.9446
0.0022	4.0	852	0.3924	0.5017	0.4124	0.4527	0.9446

Framework versions

Transformers 4.57.1
Pytorch 2.8.0+cu126
Datasets 4.0.0
Tokenizers 0.22.1

加载中…