bert-large-cased

This model is a fine-tuned version of bert-large-cased on the silicone dataset. It achieves the following results on the evaluation set:

• Loss: 0.8807
• Accuracy: 0.7281
• Micro-precision: 0.7281
• Micro-recall: 0.7281
• Micro-f1: 0.7281
• Macro-precision: 0.4591
• Macro-recall: 0.3825
• Macro-f1: 0.3855
• Weighted-precision: 0.6943
• Weighted-recall: 0.7281
• Weighted-f1: 0.6977

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-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Micro-precision	Micro-recall	Micro-f1	Macro-precision	Macro-recall	Macro-f1	Weighted-precision	Weighted-recall	Weighted-f1
0.8835	1.0	2980	0.8807	0.7281	0.7281	0.7281	0.7281	0.4591	0.3825	0.3855	0.6943	0.7281	0.6977

Framework versions

• Transformers 4.26.0
• Pytorch 1.13.1+cu116
• Datasets 2.9.0
• Tokenizers 0.13.2