bert-large-cased-finetuned-prompt-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: 0.7142

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
1.3173	1.0	280	1.1293
1.087	2.0	560	0.9716
1.0064	3.0	840	0.9606
0.9341	4.0	1120	0.8887
0.8881	5.0	1400	0.8654
0.8662	6.0	1680	0.8181
0.8331	7.0	1960	0.8286
0.8206	8.0	2240	0.7941
0.8017	9.0	2520	0.7677
0.772	10.0	2800	0.7711
0.76	11.0	3080	0.7314
0.7436	12.0	3360	0.7479
0.7305	13.0	3640	0.7354
0.7204	14.0	3920	0.7143
0.7102	15.0	4200	0.7366
0.7034	16.0	4480	0.7036
0.6937	17.0	4760	0.7049
0.695	18.0	5040	0.7080
0.6923	19.0	5320	0.7110
0.6886	20.0	5600	0.6969

Framework versions

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