danieladeeko's picture
End of training
1afa1a9 verified
metadata
library_name: transformers
license: mit
base_model: openai-community/gpt2
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: finetuned_gpt2_model
    results: []

finetuned_gpt2_model

This model is a fine-tuned version of openai-community/gpt2 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1308
  • Precision: 0.3653
  • Recall: 0.4195
  • F1: 0.3905
  • Accuracy: 0.9574

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: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 4

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
0.1977 1.0 500 0.1391 0.3420 0.3961 0.3671 0.9561
0.1419 2.0 1000 0.1333 0.3522 0.4014 0.3752 0.9571
0.1361 3.0 1500 0.1325 0.3649 0.4151 0.3884 0.9569
0.1338 4.0 2000 0.1308 0.3653 0.4195 0.3905 0.9574

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu121
  • Datasets 3.0.0
  • Tokenizers 0.19.1