fine_tuned_t5_small_model_sec_5

This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:

Loss: 2.7990
Rouge1: 0.1834
Rouge2: 0.0549
Rougel: 0.1431
Rougelsum: 0.1429
Gen Len: 18.9495

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: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 30
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
3.821	1.0	25	3.3209	0.1609	0.0463	0.1221	0.1226	18.0303
3.437	2.0	50	3.0811	0.1709	0.0505	0.1283	0.1286	18.9596
3.3219	3.0	75	2.9927	0.1728	0.053	0.1341	0.1348	18.7677
3.1368	4.0	100	2.9495	0.1714	0.0499	0.1317	0.1321	18.7778
3.1095	5.0	125	2.9171	0.1728	0.0505	0.1339	0.1344	18.7677
3.0946	6.0	150	2.8957	0.1724	0.0502	0.1341	0.1343	18.9596
3.053	7.0	175	2.8807	0.1736	0.0515	0.1358	0.1362	18.9596
3.0191	8.0	200	2.8647	0.1766	0.0538	0.1374	0.1378	18.9495
3.0108	9.0	225	2.8559	0.1802	0.057	0.1414	0.1416	18.9697
2.9507	10.0	250	2.8488	0.1829	0.0573	0.1429	0.1429	18.9697
2.9757	11.0	275	2.8399	0.1843	0.0558	0.1428	0.143	18.9697
2.937	12.0	300	2.8330	0.1853	0.0558	0.1434	0.1436	18.9697
2.9722	13.0	325	2.8290	0.183	0.0526	0.1422	0.1422	18.9697
2.9395	14.0	350	2.8241	0.1831	0.0543	0.1425	0.1427	18.9697
2.9325	15.0	375	2.8195	0.1806	0.0521	0.1394	0.1395	18.9798
2.9049	16.0	400	2.8155	0.1802	0.0524	0.1394	0.1395	18.9798
2.9137	17.0	425	2.8130	0.1811	0.0532	0.1411	0.141	18.9697
2.8813	18.0	450	2.8104	0.1808	0.0536	0.1407	0.1407	18.9697
2.9307	19.0	475	2.8082	0.1825	0.0555	0.1421	0.1422	18.9697
2.8703	20.0	500	2.8068	0.1837	0.0563	0.1432	0.1433	18.9596
2.8672	21.0	525	2.8039	0.1827	0.055	0.1415	0.1416	18.9495
2.8473	22.0	550	2.8037	0.1827	0.0542	0.1417	0.1416	18.9495
2.9374	23.0	575	2.8024	0.1825	0.0547	0.1413	0.1413	18.9495
2.8947	24.0	600	2.8014	0.183	0.0547	0.1415	0.1415	18.9495
2.8811	25.0	625	2.8012	0.1834	0.055	0.1417	0.1416	18.9495
2.8687	26.0	650	2.8003	0.1839	0.0555	0.143	0.1428	18.9495
2.8331	27.0	675	2.7996	0.1834	0.0549	0.1426	0.1423	18.9495
2.8733	28.0	700	2.7993	0.1837	0.0555	0.1436	0.1433	18.9495
2.8999	29.0	725	2.7992	0.1834	0.0549	0.1431	0.1429	18.9495
2.8255	30.0	750	2.7990	0.1834	0.0549	0.1431	0.1429	18.9495

Framework versions

Transformers 4.46.2
Pytorch 2.5.1+cu121
Datasets 3.1.0
Tokenizers 0.20.3

miasetya/fine_tuned_t5_small_model_sec_5

fine_tuned_t5_small_model_sec_5

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions