Edit model card

mobilebert-uncased-finetuned-squad

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

  • Loss: 0.9623

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: 3

Training results

Training Loss Epoch Step Validation Loss
1.6807 1.0 5533 1.0632
0.9203 2.0 11066 0.9711
0.8521 3.0 16599 0.9623

Framework versions

  • Transformers 4.37.2
  • Pytorch 2.2.0
  • Datasets 2.17.1
  • Tokenizers 0.15.2
Downloads last month
5
Safetensors
Model size
24.6M params
Tensor type
F32

Finetuned from