Edit model card

t5-small-finetuned-qmsum

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

  • Loss: 3.4617
  • Rouge1: 27.6423
  • Rouge2: 8.5163
  • Rougel: 23.1505

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: 5.6e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 8

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel
3.3956 1.0 126 3.5354 27.6519 8.0746 23.1321
3.407 2.0 252 3.5115 27.4959 8.1111 23.1004
3.36 3.0 378 3.4898 27.7611 8.3366 23.1863
3.3032 4.0 504 3.4804 27.5676 8.2376 23.1387
3.2602 5.0 630 3.4727 28.1638 8.6819 23.4878
3.258 6.0 756 3.4644 27.8802 8.5634 23.3815
3.2167 7.0 882 3.4626 27.649 8.5533 23.2101
3.203 8.0 1008 3.4617 27.6423 8.5163 23.1505

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.3.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
13
Safetensors
Model size
60.5M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for ecat3rina/t5-small-finetuned-qmsum

Base model

google-t5/t5-small
Finetuned
(1472)
this model