Edit model card

t5-small_crows_pairs_finetuned_HBRPOI

This model is a fine-tuned version of t5-small on the crows_pairs dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3485
  • Accuracy: 0.6490
  • Tp: 0.4934
  • Tn: 0.1556
  • Fp: 0.3411
  • Fn: 0.0099

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: 0.0005
  • train_batch_size: 64
  • eval_batch_size: 64
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy Tp Tn Fp Fn
0.4336 1.05 20 0.3559 0.5033 0.5033 0.0 0.4967 0.0
0.3726 2.11 40 0.3608 0.5033 0.5033 0.0 0.4967 0.0
0.317 3.16 60 0.3112 0.5099 0.5033 0.0066 0.4901 0.0
0.259 4.21 80 0.2822 0.5662 0.5 0.0662 0.4305 0.0033
0.2439 5.26 100 0.3249 0.7119 0.4934 0.2185 0.2781 0.0099
0.1824 6.32 120 0.3082 0.6093 0.4934 0.1159 0.3808 0.0099
0.1549 7.37 140 0.3217 0.5960 0.4967 0.0993 0.3974 0.0066
0.1312 8.42 160 0.3365 0.6325 0.4934 0.1391 0.3576 0.0099
0.1158 9.47 180 0.3485 0.6490 0.4934 0.1556 0.3411 0.0099

Framework versions

  • Transformers 4.26.1
  • Pytorch 1.13.1
  • Datasets 2.10.1
  • Tokenizers 0.13.2
Downloads last month
0
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.

Dataset used to train henryscheible/t5-small_crows_pairs_finetuned_HBRPOI

Evaluation results