Edit model card

mt5-small-amrit-finetuned-amazon-en

This model is a fine-tuned version of google/mt5-small on the amazon_reviews_multi dataset. It achieves the following results on the evaluation set:

  • Loss: 3.3112
  • Rouge1: 15.4603
  • Rouge2: 7.1882
  • Rougel: 15.2221
  • Rougelsum: 15.1231

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 Rougelsum
8.7422 1.0 771 3.6517 12.9002 4.8601 12.6743 12.6561
4.1322 2.0 1542 3.4937 14.1146 6.5433 14.0882 14.0484
3.7426 3.0 2313 3.4070 14.4797 6.8527 14.1544 14.2753
3.5743 4.0 3084 3.3439 15.9805 7.8873 15.4935 15.41
3.4489 5.0 3855 3.3122 16.5749 7.9809 16.1922 16.1226
3.3602 6.0 4626 3.3187 16.4809 7.7656 16.211 16.1185
3.3215 7.0 5397 3.3180 15.4615 7.1361 15.1919 15.1144
3.294 8.0 6168 3.3112 15.4603 7.1882 15.2221 15.1231

Framework versions

  • Transformers 4.20.0
  • Pytorch 1.11.0+cu113
  • Datasets 2.3.2
  • Tokenizers 0.12.1
Downloads last month
0
Hosted inference API
Summarization
Examples
Examples
This model can be loaded on the Inference API on-demand.

Dataset used to train amritpattnaik/mt5-small-amrit-finetuned-amazon-en

Evaluation results