m_bert_base_qa_model

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

• Loss: 4.4076

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: 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	32	2.8233
No log	2.0	64	2.9102
No log	3.0	96	3.2005
No log	4.0	128	3.5238
No log	5.0	160	3.6986
No log	6.0	192	4.0583
No log	7.0	224	4.1965
No log	8.0	256	4.2924
No log	9.0	288	4.4430
No log	10.0	320	4.4076

Framework versions

• Transformers 4.28.1
• Pytorch 2.0.0+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3