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: 1.2353

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
2.0991	1.0	291	1.7002
1.6295	2.0	582	1.5208
1.4967	3.0	873	1.3521
1.3965	4.0	1164	1.3367
1.332	5.0	1455	1.2266
1.285	6.0	1746	1.3645
1.2314	7.0	2037	1.2992
1.2027	8.0	2328	1.3514
1.1688	9.0	2619	1.2146
1.1407	10.0	2910	1.1802
1.1272	11.0	3201	1.1346
1.1131	12.0	3492	1.1902
1.0892	13.0	3783	1.2254
1.0755	14.0	4074	1.2124
1.0741	15.0	4365	1.2180
1.0604	16.0	4656	1.2353

Framework versions

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