YAML Metadata Error: "widget[0].text" must be a string
YAML Metadata Error: "widget[1].text" must be a string

platzi-distilroberta-base-mrpc-glue-djps10

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

  • Loss: 0.4939
  • Accuracy: 0.7966
  • F1: 0.8672

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: 8
  • eval_batch_size: 8
  • 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 Accuracy F1
0.5453 1.09 500 0.4939 0.7966 0.8672
0.3506 2.18 1000 0.7823 0.8186 0.8693

Framework versions

  • Transformers 4.31.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.3
  • Tokenizers 0.13.3
Downloads last month
19
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 daniejps10/platzi-distilroberta-base-mrpc-glue-djps10

Finetuned
(548)
this model

Dataset used to train daniejps10/platzi-distilroberta-base-mrpc-glue-djps10

Evaluation results