distilbart-podimo-data-eval-3

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: 3.3828
• Rouge1: 32.8203
• Rouge2: 7.8994
• Rougel: 18.9659
• Rougelsum: 29.4196
• Gen Len: 114.5264

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
3.9049	1.0	132	3.5343	30.2542	6.031	17.269	26.9847	113.7689
3.4248	2.0	264	3.4055	31.6518	7.2786	18.2641	28.4006	114.6547
3.1594	3.0	396	3.3579	32.0442	7.3554	18.3492	28.7615	113.7443
2.9645	4.0	528	3.3445	32.0945	7.637	18.6289	28.899	115.5321
2.8073	5.0	660	3.3470	32.7852	7.9597	19.2358	29.5057	108.3519
2.685	6.0	792	3.3532	32.3775	7.661	18.6719	28.9282	117.1104
2.5941	7.0	924	3.3711	32.6976	7.8917	19.069	29.3785	113.1943
2.5267	8.0	1056	3.3828	32.8203	7.8994	18.9659	29.4196	114.5264

Framework versions

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