eliwill/stoic-generator-distil-gpt2

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

• Train Loss: 3.3439
• Validation Loss: 3.7738
• 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', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: float32

Training results

Train Loss	Validation Loss	Epoch
4.2818	3.9629	0
4.0906	3.9052	1
3.9946	3.8684	2
3.9239	3.8412	3
3.8689	3.8316	4
3.8185	3.8156	5
3.7751	3.8032	6
3.7325	3.7950	7
3.6929	3.7901	8
3.6575	3.7770	9
3.6223	3.7658	10
3.5882	3.7745	11
3.5536	3.7642	12
3.5226	3.7645	13
3.4912	3.7616	14
3.4595	3.7598	15
3.4289	3.7604	16
3.3992	3.7555	17
3.3713	3.7646	18
3.3439	3.7738	19

Framework versions

• Transformers 4.22.1
• TensorFlow 2.8.2
• Datasets 2.5.1
• Tokenizers 0.12.1