DanSumT5-baseV_38821V_41166V_99300

This model is a fine-tuned version of emilstabil/DanSumT5-baseV_38821V_41166 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.1990
• Rouge1: 36.0635
• Rouge2: 12.6612
• Rougel: 22.0632
• Rougelsum: 28.8514
• Gen Len: 125.7597

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: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	232	2.1564	35.0359	12.3281	22.0262	28.07	126.1974
No log	2.0	465	2.1556	35.1832	12.0473	21.8776	28.1858	126.4721
1.8468	3.0	697	2.1567	35.5287	12.3174	22.3354	28.4708	126.0987
1.8468	4.0	930	2.1524	35.5329	12.244	22.047	28.1537	126.3863
1.7638	5.0	1162	2.1675	35.5247	12.5574	22.5531	28.64	125.3648
1.7638	6.0	1395	2.1637	35.4927	12.2718	22.1521	28.5053	125.8884
1.7082	7.0	1627	2.1771	35.7224	12.5675	22.4379	28.6806	125.4807
1.7082	8.0	1860	2.1809	35.4052	12.3639	22.0898	28.0686	125.3734
1.6599	9.0	2092	2.1828	35.3215	12.3554	22.0962	28.1704	126.2189
1.6599	10.0	2325	2.1852	35.2823	12.1901	21.9675	28.1307	125.5365
1.6125	11.0	2557	2.1903	35.198	12.051	21.901	27.819	125.3305
1.6125	12.0	2790	2.1863	35.2787	12.0695	21.7106	28.1589	125.6953
1.5957	13.0	3022	2.1921	35.5594	12.4603	21.9964	28.6257	125.97
1.5957	14.0	3255	2.2085	35.8369	12.3539	22.0812	28.637	125.412
1.5957	15.0	3487	2.1962	35.7638	12.5332	21.8062	28.2834	126.3133
1.5708	16.0	3720	2.1932	35.5401	12.3573	22.033	28.4601	125.9614
1.5708	17.0	3952	2.1985	35.4247	12.348	21.9465	28.2987	125.4034
1.5644	18.0	4185	2.1987	35.4229	12.2593	21.9969	28.2643	125.073
1.5644	19.0	4417	2.1996	35.8265	12.5056	22.1718	28.6138	124.9099
1.5446	19.96	4640	2.1990	36.0635	12.6612	22.0632	28.8514	125.7597

Framework versions

• Transformers 4.32.1
• Pytorch 2.1.0
• Datasets 2.12.0
• Tokenizers 0.13.3