CoolFace
Modelpublic

Akshay95/t5_recommendation_sports_equipment

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face
0likes8downloads
Model Card

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

t5recommendationsports_equipment

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

  • —Loss: 0.3702
  • —Rouge1: 30.0
  • —Rouge2: 5.0
  • —Rougel: 30.0
  • —Rougelsum: 30.0
  • —Gen Len: 4.9

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: 4
  • —evalbatchsize: 4
  • —seed: 42
  • —gradientaccumulationsteps: 4
  • —totaltrainbatch_size: 16
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 10

Training results

Training LossEpochStepValidation LossRouge1Rouge2RougelRougelsumGen Len
No log1.0511.31345.02.55.03.333311.85
No log2.0106.79711.66670.01.66671.666719.0
No log3.0153.55550.00.00.00.019.0
No log4.0201.35440.00.00.00.00.0
No log5.0250.62165.05.05.05.04.8
No log6.0300.482425.05.025.025.04.95
No log7.0350.43575.05.05.05.04.7
No log8.0400.414825.05.025.025.04.7
No log9.0450.385325.05.025.025.04.7
No log10.0500.370230.05.030.030.04.9

Framework versions

  • —Transformers 4.26.0
  • —Pytorch 2.0.1+cu118
  • —Datasets 2.8.0
  • —Tokenizers 0.13.3