albert-base-v2-finetuned-squad

This model is a fine-tuned version of albert-base-v2 on the squad_v2 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.9492

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
0.8695 1.0 8248 0.8813
0.6333 2.0 16496 0.8042
0.4372 3.0 24744 0.9492

Framework versions

  • Transformers 4.12.3
  • Pytorch 1.7.1
  • Datasets 1.15.1
  • Tokenizers 0.10.3
Downloads last month
7
Hosted inference API
Question Answering
Examples
Examples
This model can be loaded on the Inference API on-demand.

Dataset used to train Akari/albert-base-v2-finetuned-squad

Evaluation results