Modelpublic

alaahussein/T5-small_finetuned_billsum_subset_model_bs8_lr0.0001

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face

0likes21downloads

Model Card

T5-smallfinetunedbillsumsubsetmodelbs8lr0.0001

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

—Loss: 2.0465
—Rouge1: 0.1935
—Rouge2: 0.0971
—Rougel: 0.1675
—Rougelsum: 0.1674
—Gen Len: 19.0
—Bleu: 0.0008

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: 0.0001
—trainbatchsize: 8
—evalbatchsize: 8
—seed: 42
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: linear
—num_epochs: 4
—mixedprecisiontraining: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len	Bleu
No log	1.0	124	2.1085	0.1909	0.0947	0.1648	0.1646	19.0	0.0008
No log	2.0	248	2.0816	0.1891	0.0947	0.164	0.1636	19.0	0.0008
No log	3.0	372	2.0591	0.1892	0.0897	0.1631	0.1626	19.0	0.0008
No log	4.0	496	2.0465	0.1935	0.0971	0.1675	0.1674	19.0	0.0008

Framework versions

—Transformers 4.27.4
—Pytorch 2.0.0+cu118
—Datasets 2.11.0
—Tokenizers 0.13.3