bert-large-cased-finetuned-low100-0-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: 1.1112

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
3.1166	1.0	1	2.8426
3.3165	2.0	2	3.5737
2.9474	3.0	3	4.5615
2.8754	4.0	4	3.1920
2.5889	5.0	5	1.3226
2.6482	6.0	6	2.0844
3.2225	7.0	7	2.7027
2.5846	8.0	8	1.8894
2.5211	9.0	9	3.6235
2.8645	10.0	10	2.7545
2.2606	11.0	11	2.2238
2.3737	12.0	12	1.8809
2.5521	13.0	13	2.3081
2.4012	14.0	14	2.0904
2.1854	15.0	15	1.5814
2.1068	16.0	16	2.8540
2.4657	17.0	17	2.3973
2.4053	18.0	18	2.5062
1.813	19.0	19	2.7394
2.1094	20.0	20	1.8084

Framework versions

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