distilbart-podimo-data-eval-1

This model is a fine-tuned version of sshleifer/distilbart-cnn-12-6 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.3983
• Rouge1: 34.6132
• Rouge2: 7.9113
• Rougel: 17.9418
• Rougelsum: 31.5251
• Gen Len: 141.5587

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: 5e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 64
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
4.1934	0.98	44	3.7592	32.8148	6.457	16.8696	29.6986	141.4441
3.6362	1.98	88	3.5809	33.0442	6.851	17.1323	30.1382	141.324
3.3554	2.98	132	3.4835	33.66	7.1375	17.5152	30.5783	141.2793
3.1566	3.98	176	3.4301	34.524	7.757	17.995	31.5808	141.7151
3.0107	4.98	220	3.4099	34.3459	7.7512	18.0605	31.4531	141.4106
2.901	5.98	264	3.4073	35.028	7.9099	17.9907	31.8304	141.5419
2.8246	6.98	308	3.3983	34.1937	7.8606	17.7858	31.1331	141.5279
2.7306	7.98	352	3.3983	34.6132	7.9113	17.9418	31.5251	141.5587

Framework versions

• Transformers 4.25.1
• Pytorch 1.11.0
• Datasets 2.2.1
• Tokenizers 0.12.1