DanSumT5-baseV_13284V_36974

This model is a fine-tuned version of emilstabil/DanSumT5-baseV_13284 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.0893
• Rouge1: 34.9084
• Rouge2: 12.0759
• Rougel: 21.8064
• Rougelsum: 32.5673
• Gen Len: 125.2827

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: 3e-05
• train_batch_size: 6
• eval_batch_size: 6
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 24
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 11

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	79	2.1219	35.0897	11.9215	21.754	32.7137	125.2025
No log	1.99	158	2.1200	34.8528	12.0209	21.7675	32.5084	125.5612
No log	2.99	237	2.1127	34.9594	11.9696	21.698	32.5483	126.0549
No log	4.0	317	2.1042	34.6163	11.9576	21.82	32.3802	125.6751
No log	5.0	396	2.1058	35.3397	12.3246	22.2113	33.095	126.0422
No log	5.99	475	2.0987	35.012	12.1749	21.895	32.7336	125.9958
2.0966	6.99	554	2.0969	35.1359	12.1652	21.8921	32.7933	125.9283
2.0966	8.0	634	2.0940	35.0078	12.1916	21.9206	32.6762	125.1646
2.0966	9.0	713	2.0925	34.8858	12.0673	21.8894	32.5213	125.3797
2.0966	9.99	792	2.0896	34.747	11.9854	21.8049	32.3432	125.3924
2.0966	10.97	869	2.0893	34.9084	12.0759	21.8064	32.5673	125.2827

Framework versions

• Transformers 4.30.2
• Pytorch 1.12.1+git7548e2f
• Datasets 2.13.2
• Tokenizers 0.13.3