bert-base-uncased-issues-128

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: 1.1961

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: 32
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 16

Training results

Training Loss	Epoch	Step	Validation Loss
2.1076	1.0	292	1.6936
1.6375	2.0	584	1.5055
1.4807	3.0	876	1.4381
1.3863	4.0	1168	1.3877
1.3397	5.0	1460	1.2885
1.2857	6.0	1752	1.2861
1.2431	7.0	2044	1.1642
1.2132	8.0	2336	1.3358
1.1639	9.0	2628	1.1863
1.155	10.0	2920	1.2066
1.124	11.0	3212	1.1249
1.1046	12.0	3504	1.2248
1.0992	13.0	3796	1.0654
1.0774	14.0	4088	1.1763
1.0724	15.0	4380	1.2023
1.0494	16.0	4672	1.1961

Framework versions

• Transformers 4.40.1
• Pytorch 2.3.0+cu118
• Datasets 2.19.1
• Tokenizers 0.19.1