distilbart-podimo-data-eval-2

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: 3.5823
• Rouge1: 34.3971
• Rouge2: 7.95
• Rougel: 18.7271
• Rougelsum: 30.9024
• Gen Len: 131.919

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
4.1512	0.98	44	3.7806	32.727	6.5788	17.5196	29.3777	137.2905
3.6342	1.98	88	3.6421	32.709	6.7877	17.8668	29.4636	134.6648
3.3512	2.98	132	3.5819	33.5128	7.519	18.6614	30.1142	132.2961
3.141	3.98	176	3.5552	33.4795	7.3242	18.396	30.0854	132.757
2.9787	4.98	220	3.5583	33.5862	7.391	18.3568	30.2461	132.4078
2.8555	5.98	264	3.5650	34.1111	7.8008	18.7159	30.6055	131.3603
2.7648	6.98	308	3.5729	34.0981	7.6556	18.6373	30.6269	131.2821
2.6645	7.98	352	3.5823	34.3971	7.95	18.7271	30.9024	131.919

Framework versions

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