Edit model card

hBERTv2_new_pretrain_48_wnli

This model is a fine-tuned version of gokuls/bert_12_layer_model_v2_complete_training_new_48 on the GLUE WNLI dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6839
  • Accuracy: 0.5634

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: 4e-05
  • train_batch_size: 128
  • eval_batch_size: 128
  • seed: 10
  • distributed_type: multi-GPU
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 50

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.9503 1.0 5 0.6839 0.5634
0.7089 2.0 10 0.6877 0.5634
0.7066 3.0 15 0.6858 0.5634
0.7051 4.0 20 0.6943 0.4789
0.6996 5.0 25 0.7125 0.4366
0.7088 6.0 30 0.6890 0.5634

Framework versions

  • Transformers 4.29.2
  • Pytorch 1.14.0a0+410ce96
  • Datasets 2.12.0
  • Tokenizers 0.13.3
Downloads last month
2
Inference API
This model can be loaded on Inference API (serverless).

Dataset used to train gokuls/hBERTv2_new_pretrain_48_wnli

Evaluation results