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: 1.3226

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: 128
• 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
2.3267	1.0	73	1.8862
1.774	2.0	146	1.5454
1.6001	3.0	219	1.4916
1.5111	4.0	292	1.4676
1.449	5.0	365	1.3100
1.3855	6.0	438	1.4255
1.3522	7.0	511	1.2901
1.3262	8.0	584	1.3294
1.292	9.0	657	1.3458
1.2746	10.0	730	1.3086
1.2515	11.0	803	1.2175
1.2399	12.0	876	1.1521
1.2226	13.0	949	1.2453
1.2148	14.0	1022	1.1466
1.2084	15.0	1095	1.3008
1.1964	16.0	1168	1.3226

Framework versions

• Transformers 4.33.1
• Pytorch 2.0.1+cu117
• Datasets 2.14.0
• Tokenizers 0.13.3