platzi-distilroberta-base-mrpc-glue-luis-montoya

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

  • Loss: 0.8772
  • Accuracy: 0.8480
  • F1: 0.8942

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
0.3213 1.0893 500 0.9267 0.8333 0.8874
0.2824 2.1786 1000 0.8772 0.8480 0.8942

Framework versions

  • Transformers 4.41.0
  • Pytorch 2.5.1+cpu
  • Datasets 3.1.0
  • Tokenizers 0.19.1
Downloads last month
14
Safetensors
Model size
82.1M params
Tensor type
F32
·
Inference Examples
Unable to determine this model's library. Check the docs .

Model tree for platzi/platzi-distilroberta-base-mrpc-glue-luis-montoya

Finetuned
(547)
this model