bert-base-uncased-rahuldave-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: 1.2505

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
2.1019	1.0	291	1.6982
1.6376	2.0	582	1.4442
1.4815	3.0	873	1.3822
1.3996	4.0	1164	1.3695
1.3416	5.0	1455	1.1960
1.2824	6.0	1746	1.2835
1.2404	7.0	2037	1.2664
1.2022	8.0	2328	1.2082
1.1669	9.0	2619	1.1798
1.1424	10.0	2910	1.2211
1.1269	11.0	3201	1.2019
1.1036	12.0	3492	1.1649
1.0802	13.0	3783	1.2438
1.0759	14.0	4074	1.1716
1.0629	15.0	4365	1.1270
1.0639	16.0	4656	1.2505

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.1+cu116
• Datasets 2.8.0
• Tokenizers 0.13.2