allistair99's picture
BiLSTM test 1
54f7f11 verified
|
raw
history blame
1.48 kB
metadata
license: mit
base_model: csarron/mobilebert-uncased-squad-v1
tags:
  - generated_from_trainer
model-index:
  - name: MobileBERT-uncased-squad-v1-BiLSTM-finetuned-squad-fc1-dropout015
    results: []

MobileBERT-uncased-squad-v1-BiLSTM-finetuned-squad-fc1-dropout015

This model is a fine-tuned version of csarron/mobilebert-uncased-squad-v1 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0293

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: 3e-05
  • train_batch_size: 6
  • eval_batch_size: 60
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 2

Training results

Training Loss Epoch Step Validation Loss
0.5695 1.0 14619 1.0467
0.5465 2.0 29238 1.0293

Framework versions

  • Transformers 4.40.0
  • Pytorch 2.4.0+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1