NF-bigbird-squad / README.md
FredNajjar's picture
End of training
334da18
|
raw
history blame
1.58 kB
metadata
license: apache-2.0
base_model: google/bigbird-roberta-base
tags:
  - generated_from_trainer
datasets:
  - squad
model-index:
  - name: NF-bigbird-squad
    results: []

NF-bigbird-squad

This model is a fine-tuned version of google/bigbird-roberta-base on the squad dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0218

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: 1e-05
  • train_batch_size: 2
  • eval_batch_size: 16
  • seed: 42
  • gradient_accumulation_steps: 32
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 160
  • num_epochs: 4

Training results

Training Loss Epoch Step Validation Loss
1.0526 1.0 1095 1.1762
0.8623 2.0 2190 1.0830
0.8911 3.0 3285 1.0327
0.9511 4.0 4380 1.0218

Framework versions

  • Transformers 4.33.1
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.5
  • Tokenizers 0.13.3