Edit model card

data2vec-text-base-finetuned-stsb

This model is a fine-tuned version of facebook/data2vec-text-base on the glue dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5530
  • Pearson: 0.8732
  • Spearmanr: 0.8717

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: 7.725353773731373e-05
  • train_batch_size: 32
  • eval_batch_size: 16
  • seed: 5
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Pearson Spearmanr
No log 1.0 180 1.0650 0.8102 0.8380
No log 2.0 360 0.6211 0.8524 0.8497
0.9312 3.0 540 0.5917 0.8640 0.8642
0.9312 4.0 720 0.5672 0.8695 0.8686
0.9312 5.0 900 0.5530 0.8732 0.8717

Framework versions

  • Transformers 4.18.0
  • Pytorch 1.11.0+cu113
  • Datasets 2.1.0
  • Tokenizers 0.12.1
Downloads last month
18

Dataset used to train mrm8488/data2vec-text-base-finetuned-stsb

Evaluation results