jiangcongtao's picture
End of training
24aab9a verified
metadata
license: mit
base_model: jiangcongtao/reuters-gpt2-text-gen
tags:
  - generated_from_trainer
model-index:
  - name: reuters-gpt2-text-gen
    results: []

reuters-gpt2-text-gen

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

  • Loss: 4.9055

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: 0.0005
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • num_epochs: 1
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
4.7182 0.9972 269 4.9055

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1