bert-base-cased-squad2-coffee20230113

This model is a fine-tuned version of deepset/bert-base-cased-squad2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 4.3859

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	88	2.0785
2.2589	2.0	176	1.9542
1.4038	3.0	264	1.7714
0.9533	4.0	352	2.2673
0.5394	5.0	440	2.5496
0.4353	6.0	528	3.2302
0.4201	7.0	616	3.7247
0.2477	8.0	704	3.4248
0.2477	9.0	792	3.8344
0.1633	10.0	880	4.1582
0.0979	11.0	968	3.8764
0.0621	12.0	1056	4.1686
0.0242	13.0	1144	4.2762
0.0091	14.0	1232	4.4176
0.0061	15.0	1320	4.3859

Framework versions

• Transformers 4.25.1
• Pytorch 1.11.0+cu113
• Datasets 2.8.0
• Tokenizers 0.13.2