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: 1.2436

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
2.1037	1.0	291	1.6976
1.6309	2.0	582	1.5133
1.4962	3.0	873	1.3515
1.3944	4.0	1164	1.3300
1.3308	5.0	1455	1.2333
1.2835	6.0	1746	1.3543
1.2308	7.0	2037	1.3045
1.2023	8.0	2328	1.3405
1.1662	9.0	2619	1.2236
1.1389	10.0	2910	1.1759
1.1279	11.0	3201	1.1468
1.1096	12.0	3492	1.1844
1.0896	13.0	3783	1.2305
1.0762	14.0	4074	1.2072
1.0721	15.0	4365	1.2287
1.0638	16.0	4656	1.2436

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1