QA_BERT_17_epoch

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 4.3550

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: 160
• eval_batch_size: 80
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 17

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	1	6.1613
No log	2.0	2	6.0335
No log	3.0	3	5.8978
No log	4.0	4	5.7548
No log	5.0	5	5.6034
No log	6.0	6	5.4485
No log	7.0	7	5.2940
No log	8.0	8	5.1437
No log	9.0	9	5.0043
No log	10.0	10	4.8827
No log	11.0	11	4.7783
No log	12.0	12	4.6827
No log	13.0	13	4.5973
No log	14.0	14	4.5220
No log	15.0	15	4.4566
No log	16.0	16	4.4010
No log	17.0	17	4.3550

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.2+cu121
• Datasets 2.14.7
• Tokenizers 0.15.0