Modelpublic

rizvi-rahil786/t5-small-mexicoQuakeKP

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face

0likes5downloads

Model Card

t5-small-mexicoQuakeKP

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

—Loss: 1.3278
—Rouge1: 52.4748
—Rouge2: 36.1477
—Rougel: 51.9441
—Rougelsum: 51.9079
—Gen Len: 6.6045

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
—trainbatchsize: 4
—evalbatchsize: 4
—seed: 42
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: linear
—num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.1232	1.0	6072	1.3537	52.5859	36.343	52.0536	51.9937	6.5161
1.0178	2.0	12144	1.3278	52.4748	36.1477	51.9441	51.9079	6.6045
0.9235	3.0	18216	1.3668	52.0214	34.8898	51.4087	51.3637	6.1047
0.8415	4.0	24288	1.3741	51.6755	35.2208	51.0535	51.0144	6.3251
0.7306	5.0	30360	1.4034	50.9063	34.3354	50.2691	50.2303	6.4337
0.7615	6.0	36432	1.4063	50.5179	33.6335	49.9045	49.8693	6.2164
0.7351	7.0	42504	1.4156	50.4653	34.1844	49.8111	49.7972	6.4194
0.7104	8.0	48576	1.4284	50.4666	34.3149	49.8034	49.8134	6.4089

Framework versions

—Transformers 4.39.3
—Pytorch 2.2.1+cu121
—Datasets 2.18.0
—Tokenizers 0.15.2