bert-base-uncased-cv-position-classifier

This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.6924
• Accuracy: {'accuracy': 0.5780703216130645}
• F1: {'f1': 0.5780703216130645}
• Precision: {'precision': 0.5780703216130645}

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: 5e-05
• 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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision
2.0336	1.14	1000	1.8856	{'accuracy': 0.5259123479420097}	{'f1': 0.5259123479420097}	{'precision': 0.5259123479420097}
1.5348	2.28	2000	1.6924	{'accuracy': 0.5780703216130645}	{'f1': 0.5780703216130645}	{'precision': 0.5780703216130645}

Framework versions

• Transformers 4.20.1
• Pytorch 1.8.1+cu111
• Datasets 1.6.2
• Tokenizers 0.12.1