bert_tiny_lda_50_v1_book_rte

This model is a fine-tuned version of gokulsrinivasagan/bert_tiny_lda_50_v1_book on the GLUE RTE dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6967
  • Accuracy: 0.5126

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: 5e-05
  • train_batch_size: 256
  • eval_batch_size: 256
  • seed: 10
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 50

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.7081 1.0 10 0.7039 0.4729
0.6905 2.0 20 0.6967 0.5126
0.6791 3.0 30 0.6980 0.5343
0.6611 4.0 40 0.7033 0.5343
0.6427 5.0 50 0.7435 0.5235
0.6093 6.0 60 0.7281 0.5271
0.5332 7.0 70 0.8261 0.5054

Framework versions

  • Transformers 4.46.3
  • Pytorch 2.2.1+cu118
  • Datasets 2.17.0
  • Tokenizers 0.20.3
Downloads last month
5
Safetensors
Model size
33M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for gokulsrinivasagan/bert_tiny_lda_50_v1_book_rte

Finetuned
(9)
this model

Dataset used to train gokulsrinivasagan/bert_tiny_lda_50_v1_book_rte

Evaluation results