practica2_imc

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

  • Loss: 0.6891
  • Accuracy: 0.8382
  • F1: 0.8866

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
0.5331 1.09 500 0.5300 0.8211 0.8781
0.3465 2.18 1000 0.6891 0.8382 0.8866

Framework versions

  • Transformers 4.33.2
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3
Downloads last month
18
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for Isaac18/practica2_imc

Finetuned
(602)
this model

Dataset used to train Isaac18/practica2_imc

Evaluation results