bert-base-uncased-mlm

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

• Loss: 1.7425

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
2.2248	1.0	38	1.9818
1.9124	2.0	76	1.8334
1.8166	3.0	114	1.7863
1.7414	4.0	152	1.9024
1.6727	5.0	190	1.7832
1.5969	6.0	228	1.8033
1.5023	7.0	266	1.5792
1.4593	8.0	304	1.7809
1.4825	9.0	342	1.6362
1.3928	10.0	380	1.6409
1.386	11.0	418	1.6855
1.3579	12.0	456	1.7348
1.2951	13.0	494	1.6956
1.3187	14.0	532	1.8408
1.3065	15.0	570	1.6207
1.3496	16.0	608	1.7425

Framework versions

• Transformers 4.17.0
• Pytorch 1.10.0+cu111
• Datasets 2.0.0
• Tokenizers 0.11.6