DanSumT5-largeV_38143V_15157

This model is a fine-tuned version of emilstabil/DanSumT5-largeV_38143 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.9526
• Rouge1: 36.0906
• Rouge2: 12.3436
• Rougel: 22.6262
• Rougelsum: 33.6191
• Gen Len: 124.7848

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• 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	0.99	118	1.9535	36.1763	12.4392	22.5367	33.632	124.7637
No log	2.0	237	1.9579	36.074	12.4948	22.6669	33.5774	124.2954
No log	3.0	356	1.9592	35.8935	12.4362	22.4628	33.4068	124.3713
No log	4.0	475	1.9579	35.9893	12.4292	22.4658	33.622	124.384
1.6658	4.99	593	1.9642	35.9501	12.279	22.4227	33.4503	124.3207
1.6658	6.0	712	1.9598	35.8682	12.3408	22.5165	33.2375	124.4135
1.6658	7.0	831	1.9609	35.6712	12.0964	22.2602	33.2817	124.8776
1.6658	8.0	950	1.9567	35.8782	12.272	22.6389	33.462	124.0084
1.5814	8.99	1068	1.9591	35.888	12.278	22.4367	33.4144	124.2658
1.5814	10.0	1187	1.9544	35.8605	12.2878	22.5468	33.4009	124.4388
1.5814	10.93	1298	1.9526	36.0906	12.3436	22.6262	33.6191	124.7848

Framework versions

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