fine_tune_bert_output

This model is a fine-tuned version of prajjwal1/bert-tiny on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0094
• Overall Precision: 0.9722
• Overall Recall: 0.9722
• Overall F1: 0.9722
• Overall Accuracy: 0.9963
• Number Of Employees F1: 0.9722

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: 0.0002
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 150

Training results

Training Loss	Epoch	Step	Validation Loss	Overall Precision	Overall Recall	Overall F1	Overall Accuracy	Number Of Employees F1
0.0011	50.0	1000	0.0046	0.9722	0.9722	0.9722	0.9963	0.9722
0.0003	100.0	2000	0.0004	1.0	1.0	1.0	1.0	1.0
0.0002	150.0	3000	0.0094	0.9722	0.9722	0.9722	0.9963	0.9722

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3

Labels IDs

• {0: 'O', 1: 'B-number_of_employees', 2: 'I-number_of_employees'}