Edit model card

google-mobilebert-uncased

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: 1.3573
  • Accuracy: 0.3335

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: 5e-05
  • train_batch_size: 64
  • eval_batch_size: 64
  • 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 Accuracy
3.8107 1.0 2857 1.3585 0.3082
1.3233 2.0 5714 1.3452 0.3297
1.2776 3.0 8571 1.3573 0.3335

Framework versions

  • Transformers 4.39.0.dev0
  • Pytorch 2.2.0+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.0
Downloads last month
4
Safetensors
Model size
24.6M params
Tensor type
F32
·
Inference API
Inference API (serverless) does not yet support transformers models for this pipeline type.

Model tree for daze-unlv/google-mobilebert-uncased

Finetuned
(24)
this model