bert-base-uncased-coqa

This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 2.8077

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: 64
  • 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
3.0963 1.0 3396 2.8237
2.7925 2.0 6792 2.8077
2.7639 3.0 10188 2.8077

Framework versions

  • Transformers 4.29.2
  • Pytorch 2.0.0
  • Datasets 2.12.0
  • Tokenizers 0.13.3
Downloads last month
31
Safetensors
Model size
109M params
Tensor type
I64
F32
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for rooftopcoder/bert-base-uncased-coqa

Finetuned
(3096)
this model