t5-small-samsum

This model is a fine-tuned version of google-t5/t5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.6707
• Rouge1: 43.8206
• Rouge2: 19.9652
• Rougel: 36.0416
• Rougelsum: 40.0887
• Gen Len: 17.0305

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
2.016	1.0	1842	1.7872	40.6656	17.0772	33.6487	37.3124	16.9829
1.8798	2.0	3684	1.7375	42.1059	18.6064	35.0368	38.6458	16.7045
1.8219	3.0	5526	1.7062	43.2636	19.4321	35.6415	39.5613	16.8266
1.77	4.0	7368	1.6990	43.2211	19.5021	35.5155	39.6933	17.1905
1.7408	5.0	9210	1.6878	43.9084	19.8501	36.2255	40.2666	16.7766
1.7113	6.0	11052	1.6816	44.0573	20.1359	36.426	40.4933	16.9829
1.692	7.0	12894	1.6771	43.9234	19.9018	36.0759	40.1654	16.9158
1.6771	8.0	14736	1.6723	43.5824	19.8023	35.9709	39.963	16.9731
1.6604	9.0	16578	1.6718	43.8502	19.9263	36.157	40.1653	17.0134
1.6575	10.0	18420	1.6707	43.8206	19.9652	36.0416	40.0887	17.0305

Framework versions

• Transformers 4.38.1
• Pytorch 2.1.0+cu121
• Datasets 2.17.1
• Tokenizers 0.15.2