bert-large-cased-finetuned-lowR100-0-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: 1.1273

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: 30
• eval_batch_size: 30
• 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
No log	1.0	1	1.8723
0.732	2.0	2	3.5381
0.732	3.0	3	2.1417
0.7987	4.0	4	2.2899
0.7987	5.0	5	1.7517
0.9115	6.0	6	2.3830
0.9115	7.0	7	3.4545
0.9239	8.0	8	2.7875
0.9239	9.0	9	2.1550
1.1331	10.0	10	1.9010
1.1331	11.0	11	2.6686
1.1203	12.0	12	1.8346
1.1203	13.0	13	2.3677
0.9392	14.0	14	1.3718
0.9392	15.0	15	2.2553
0.8844	16.0	16	3.4245
0.8844	17.0	17	2.5895
0.8565	18.0	18	2.7765
0.8565	19.0	19	1.7891
0.9602	20.0	20	2.0496

Framework versions

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