070524_epoch_2 / README.md
adriansanz's picture
End of training
225580d verified
metadata
license: apache-2.0
base_model: projecte-aina/roberta-base-ca-v2-cased-te
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: 060524_epoch_2
    results: []

060524_epoch_2

This model is a fine-tuned version of projecte-aina/roberta-base-ca-v2-cased-te on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6952
  • Accuracy: 0.7437
  • Precision: 0.7569
  • Recall: 0.7437
  • F1: 0.7404
  • Ratio: 0.6134

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: 2e-05
  • train_batch_size: 10
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 20
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.06
  • lr_scheduler_warmup_steps: 4
  • num_epochs: 1
  • label_smoothing_factor: 0.1

Training results

Training Loss Epoch Step Validation Loss Accuracy Precision Recall F1 Ratio
0.7924 0.1626 10 0.7754 0.7101 0.7233 0.7101 0.7057 0.3782
0.641 0.3252 20 0.8257 0.7227 0.7451 0.7227 0.7162 0.6513
0.8108 0.4878 30 0.7629 0.7563 0.7564 0.7563 0.7563 0.4916
0.736 0.6504 40 0.7167 0.7731 0.7751 0.7731 0.7727 0.4580
0.6973 0.8130 50 0.7419 0.7143 0.7448 0.7143 0.7051 0.6765
0.7981 0.9756 60 0.6962 0.7437 0.7569 0.7437 0.7404 0.6134

Framework versions

  • Transformers 4.40.1
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1