albert-large-v2-finetuned-abbDet-finetuned-ner

This model is a fine-tuned version of surrey-nlp/albert-large-v2-finetuned-abbDet on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0950
• Precision: 0.9784
• Recall: 0.9763
• F1: 0.9773
• Accuracy: 0.9757

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-06
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	0.37	100	0.1655	0.9638	0.9621	0.9629	0.9622
No log	0.75	200	0.1073	0.9752	0.9705	0.9729	0.9709
No log	1.12	300	0.0951	0.9776	0.9742	0.9759	0.9740
No log	1.49	400	0.0952	0.9778	0.9752	0.9765	0.9748
0.1901	1.87	500	0.0948	0.9780	0.9745	0.9763	0.9746
0.1901	2.24	600	0.0947	0.9788	0.9758	0.9773	0.9755
0.1901	2.61	700	0.0962	0.9789	0.9766	0.9778	0.9758
0.1901	2.99	800	0.0950	0.9784	0.9763	0.9773	0.9757
0.1901	3.36	900	0.0984	0.9784	0.9763	0.9773	0.9755
0.0493	3.73	1000	0.1012	0.9781	0.9759	0.9770	0.9752
0.0493	4.1	1100	0.1029	0.9781	0.9763	0.9772	0.9754

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.2+cu121
• Datasets 2.19.0
• Tokenizers 0.15.2