bert-base-cased-news-16batch_10epoch_2e5lr_01wd

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

• Loss: 0.4558
• F1: 0.9211

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: 16
• eval_batch_size: 16
• seed: 47
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	F1
0.0626	1.0	3124	0.2043	0.9160
0.0337	2.0	6248	0.2799	0.9154
0.0243	3.0	9372	0.2959	0.9144
0.0077	4.0	12496	0.3115	0.9195
0.0085	5.0	15620	0.3588	0.9172
0.0073	6.0	18744	0.3413	0.9175
0.0028	7.0	21868	0.3517	0.9217
0.001	8.0	24992	0.4161	0.9238
0.0011	9.0	28116	0.4539	0.9230
0.0	10.0	31240	0.4558	0.9211

Framework versions

• Transformers 4.35.1
• Pytorch 2.1.0+cu121
• Datasets 2.14.6
• Tokenizers 0.14.1