Luca-Engel's picture
text finetuning on full dataset
387ecc6 verified
metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - recall
  - precision
  - f1
model-index:
  - name: finetuned_text_class
    results: []

finetuned_text_class

This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4994
  • Accuracy: 0.7702
  • Recall: 0.8076
  • Precision: 0.7557
  • F1: 0.7808

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: 8e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Accuracy Recall Precision F1
0.499 0.9961 193 0.4700 0.7602 0.7599 0.7652 0.7625
0.3852 1.9974 387 0.4994 0.7702 0.8076 0.7557 0.7808
0.1778 2.9987 581 0.6317 0.7638 0.6688 0.8320 0.7415
0.1007 4.0 775 0.8801 0.7609 0.7662 0.7628 0.7645
0.0567 4.9806 965 1.0289 0.7657 0.7586 0.7744 0.7664

Framework versions

  • Transformers 4.40.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1