Modelpublic

shreyahegde/video_prompt_generation

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face

0likes12downloads

Model Card

videopromptgeneration

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

—Loss: nan
—Rouge1: 0.1089
—Rouge2: 0.023
—Rougel: 0.0946
—Rougelsum: 0.0943
—Gen Len: 10.5833

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
—trainbatchsize: 4
—evalbatchsize: 4
—seed: 42
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: linear
—num_epochs: 5
—mixedprecisiontraining: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	12	nan	0.1089	0.023	0.0946	0.0943	10.5833
No log	2.0	24	nan	0.1089	0.023	0.0946	0.0943	10.5833
No log	3.0	36	nan	0.1089	0.023	0.0946	0.0943	10.5833
No log	4.0	48	nan	0.1089	0.023	0.0946	0.0943	10.5833
No log	5.0	60	nan	0.1089	0.023	0.0946	0.0943	10.5833

Framework versions

—Transformers 4.40.2
—Pytorch 2.2.1+cu121
—Datasets 2.19.1
—Tokenizers 0.19.1