DanSumT5-smallV_45767V_52355

This model is a fine-tuned version of emilstabil/DanSumT5-smallV_45767 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.4059
• Rouge1: 34.4784
• Rouge2: 11.7874
• Rougel: 21.2024
• Rougelsum: 32.0698
• Gen Len: 126.0211

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: 10
• eval_batch_size: 10
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 40
• 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	47	2.4476	34.2545	11.5442	21.045	31.8547	126.557
No log	2.0	95	2.4372	34.4857	11.8209	21.0909	32.063	126.5105
No log	2.99	142	2.4321	33.9859	11.5454	21.0554	31.6295	126.5907
No log	4.0	190	2.4220	34.4331	11.7682	21.2039	32.0393	126.827
No log	4.99	237	2.4187	34.3511	11.8482	21.4824	31.9866	126.2447
No log	6.0	285	2.4178	34.3999	12.0167	21.3841	32.094	126.3038
No log	6.99	332	2.4119	34.0619	11.882	21.2583	31.713	126.0338
No log	8.0	380	2.4081	34.3605	11.8248	21.3351	32.0082	125.9409
No log	8.99	427	2.4072	34.2218	11.7791	21.3086	31.8756	125.8186
No log	10.0	475	2.4066	34.5265	11.8846	21.3612	32.1396	125.8608
2.6208	10.88	517	2.4059	34.4784	11.7874	21.2024	32.0698	126.0211

Framework versions

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