bert-21

This model is a fine-tuned version of deepset/bert-base-cased-squad2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 11.9330

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: 3e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
11.3134	0.09	5	12.3068
11.4146	0.18	10	12.2378
10.9861	0.27	15	12.1756
11.1036	0.36	20	12.1205
11.079	0.45	25	12.0721
11.1039	0.55	30	12.0310
10.3894	0.64	35	11.9972
11.034	0.73	40	11.9707
10.6017	0.82	45	11.9511
10.5161	0.91	50	11.9387
10.3011	1.0	55	11.9330

Framework versions

• Transformers 4.34.1
• Pytorch 2.1.0+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1