bert-base-uncased-issue-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: 1.2410

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
2.0992	1.0	291	1.7045
1.6312	2.0	582	1.5191
1.493	3.0	873	1.3559
1.4017	4.0	1164	1.3378
1.3391	5.0	1455	1.2504
1.2695	6.0	1746	1.3550
1.222	7.0	2037	1.3009
1.2078	8.0	2328	1.3408
1.1816	9.0	2619	1.2148
1.1352	10.0	2910	1.1639
1.1311	11.0	3201	1.1334
1.103	12.0	3492	1.1944
1.0915	13.0	3783	1.2266
1.0766	14.0	4074	1.2206
1.072	15.0	4365	1.2132
1.0515	16.0	4656	1.2410

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.1+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0