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: 1.1389

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: 8
• eval_batch_size: 32
• 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
1.9863	1.0	1163	1.5917
1.579	2.0	2326	1.4668
1.4305	3.0	3489	1.3947
1.3367	4.0	4652	1.2889
1.2748	5.0	5815	1.3377
1.2184	6.0	6978	1.3370
1.1708	7.0	8141	1.2595
1.1309	8.0	9304	1.3044
1.0896	9.0	10467	1.2314
1.0614	10.0	11630	1.1699
1.0296	11.0	12793	1.2066
0.9896	12.0	13956	1.2158
0.983	13.0	15119	1.1289
0.9619	14.0	16282	1.1427
0.9387	15.0	17445	1.0767
0.9205	16.0	18608	1.1389

Framework versions

• Transformers 4.20.1
• Pytorch 1.11.0+cu102
• Datasets 2.2.1
• Tokenizers 0.12.1