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: 1.2311

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: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 16

Training results

Training Loss	Epoch	Step	Validation Loss
2.1028	1.0	291	1.7042
1.6315	2.0	582	1.5080
1.4967	3.0	873	1.3577
1.3956	4.0	1164	1.3385
1.3294	5.0	1455	1.2407
1.2869	6.0	1746	1.3678
1.2329	7.0	2037	1.2954
1.2023	8.0	2328	1.3426
1.1687	9.0	2619	1.2184
1.1435	10.0	2910	1.1783
1.1254	11.0	3201	1.1233
1.1116	12.0	3492	1.1670
1.0869	13.0	3783	1.2120
1.0748	14.0	4074	1.2206
1.0726	15.0	4365	1.2168
1.0610	16.0	4656	1.2311

Framework versions

• Transformers 5.1.0
• Pytorch 2.10.0+cu128
• Datasets 3.6.0
• Tokenizers 0.22.2