dialogsum_gpt2

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

• Loss: 2.3211
• Rouge1: 0.4866
• Rouge2: 0.1609
• Rougel: 0.3868

[Repo code]

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel
2.3713	1.0	875	2.3516	0.4821	0.1533	0.3775
2.2024	2.0	1750	2.3249	0.4820	0.1560	0.3806
1.988	3.0	2625	2.3211	0.4866	0.1609	0.3868

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1