Thalesian/SciGPT-2-finetuned-papers

<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. -->

Thalesian/SciGPT-2-finetuned-papers

This model is a fine-tuned version of distilgpt2 on an unknown dataset. It achieves the following results on the evaluation set:

• —Train Loss: 1.8928
• —Validation Loss: 2.0726
• —Epoch: 19

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:

• —optimizer: {'name': 'AdamWeightDecay', 'clipvalue': 0.7, 'learningrate': {'classname': 'ExponentialDecay', 'config': {'initiallearningrate': 0.0005, 'decaysteps': 500, 'decayrate': 0.95, 'staircase': False, 'name': None}}, 'decay': 0.0, 'beta1': 0.9, 'beta2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weightdecayrate': 0.1}
• —training_precision: float32

Training results

Framework versions

• —Transformers 4.25.1
• —TensorFlow 2.8.0
• —Datasets 2.8.0
• —Tokenizers 0.13.2