bert-large-uncased-pp-500000-1e-06-128

This model is a fine-tuned version of bert-large-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6626

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: 1e-06
• train_batch_size: 512
• eval_batch_size: 1024
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
0.6848	1.0	977	0.6733
0.6785	2.0	1954	0.6690
0.6748	3.0	2931	0.6667
0.6734	4.0	3908	0.6650
0.6724	5.0	4885	0.6644
0.6705	6.0	5862	0.6638
0.6709	7.0	6839	0.6635
0.6697	8.0	7816	0.6631
0.6686	9.0	8793	0.6631
0.6669	10.0	9770	0.6627
0.6667	11.0	10747	0.6627
0.6667	12.0	11724	0.6627
0.6662	13.0	12701	0.6627
0.6668	14.0	13678	0.6626
0.6653	15.0	14655	0.6626

Framework versions

• Transformers 4.43.3
• Pytorch 2.4.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1