bert-large-cased-finetuned-low20-1-cased-DA-20

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

• Loss: 1.0643

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: 2e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.5949	1.0	1	2.1115
2.0432	2.0	2	1.1308
1.8673	3.0	3	2.9839
2.148	4.0	4	3.1041
2.3452	5.0	5	0.8330
2.7264	6.0	6	0.4304
2.2264	7.0	7	0.7261
1.7837	8.0	8	2.6532
2.1499	9.0	9	1.0848
1.8867	10.0	10	1.6630
2.1755	11.0	11	0.9400
2.3771	12.0	12	2.6569
1.9036	13.0	13	2.8530
2.6166	14.0	14	0.5954
2.568	15.0	15	2.6136
2.5912	16.0	16	2.6986
1.245	17.0	17	2.1147
2.1394	18.0	18	1.0086
1.6254	19.0	19	2.1770
1.9212	20.0	20	1.0643

Framework versions

• Transformers 4.26.0
• Pytorch 1.13.1+cu116
• Datasets 2.9.0
• Tokenizers 0.13.2