test-bert-2

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: 11.9673

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
10.9875	0.09	5	12.2820
10.8852	0.18	10	12.2237
10.4256	0.27	15	12.1709
10.7823	0.36	20	12.1247
10.6526	0.45	25	12.0841
10.7789	0.55	30	12.0501
10.1529	0.64	35	12.0217
10.0756	0.73	40	11.9991
10.4683	0.82	45	11.9829
10.2829	0.91	50	11.9721
10.5809	1.0	55	11.9673

Framework versions

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