QA_BERT_16_epoch

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

• Loss: 3.2513

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: 16

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	2	5.5606
No log	2.0	4	4.7705
No log	3.0	6	4.1022
No log	4.0	8	3.7775
No log	5.0	10	3.6740
No log	6.0	12	3.6632
No log	7.0	14	3.5963
No log	8.0	16	3.5161
No log	9.0	18	3.4593
No log	10.0	20	3.4122
No log	11.0	22	3.3449
No log	12.0	24	3.3252
No log	13.0	26	3.3158
No log	14.0	28	3.2810
No log	15.0	30	3.2449
No log	16.0	32	3.2513

Framework versions

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