mobilebert-uncased-squad-v2-29-10-23

This model is a fine-tuned version of csarron/mobilebert-uncased-squad-v2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.6036

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: 8
• eval_batch_size: 8
• 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	131	2.6073
No log	2.0	262	2.4030
No log	3.0	393	2.2717
4.1053	4.0	524	2.3064
4.1053	5.0	655	2.3380
4.1053	6.0	786	2.4085
4.1053	7.0	917	2.5319
1.2506	8.0	1048	2.5606
1.2506	9.0	1179	2.5628
1.2506	10.0	1310	2.6036

Framework versions

• Transformers 4.34.1
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1