albert-base-v2-finetuned-ner

This model is a fine-tuned version of albert-base-v2 on the plod-filtered dataset. It achieves the following results on the evaluation set:

• Loss: 0.0319
• Precision: 0.9890
• Recall: 0.9881
• F1: 0.9886
• Accuracy: 0.9884

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: 8
• eval_batch_size: 8
• 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
0.0649	1.0	3018	0.0471	0.9838	0.9814	0.9826	0.9818
0.0442	2.0	6036	0.0319	0.9890	0.9881	0.9886	0.9884

Framework versions

• Transformers 4.22.2
• Pytorch 1.12.1+cu113
• Datasets 2.5.1
• Tokenizers 0.12.1