fool

This model is a fine-tuned version of gpt2 on the baneks dataset for 1 epoch. It achieved 1.9752 loss during training. Model evaluation has not been performed.

Model description

The model is a fine-tuned variant of the base gpt2 architecture with causal language modeling head.

Intended uses & limitations

The model should be used for studying abilities of natural language models to generate jokes.

Training and evaluation data

The model is trained on a list of anecdotes pulled from a few vk communities (see baneks dataset for more details).

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• optimizer:

{
    'name': 'AdamWeightDecay',
    'learning_rate': {
        'module': 'transformers.optimization_tf',
        'class_name': 'WarmUp',
        'config': {
            'initial_learning_rate': 5e-05,
            'decay_schedule_fn': {
                'module': 'keras.optimizers.schedules',
                'class_name': 'PolynomialDecay',
                'config': {
                    'initial_learning_rate': 5e-05,
                    'decay_steps': 28462,
                    'end_learning_rate': 0.0,
                    'power': 1.0,
                    'cycle': False,
                    'name': None
                },
                'registered_name': None
            },
            'warmup_steps': 1000,
            'power': 1.0,
            'name': None
        },
        'registered_name': 'WarmUp'
    },
    'decay': 0.0,
    'beta_1': 0.9,
    'beta_2': 0.999,
    'epsilon': 1e-08,
    'amsgrad': False,
    'weight_decay_rate': 0.01
}

• training_precision: mixed_float16

Training results

Train Loss	Epoch
1.9752	0

Framework versions

• Transformers 4.35.0.dev0
• TensorFlow 2.14.0
• Datasets 2.12.0
• Tokenizers 0.14.1