emilstabil's picture
End of training
1cc36aa
metadata
license: apache-2.0
base_model: google/mt5-base
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: mt5-base-finetuned-test_63829_prefix_summarize
    results: []

mt5-base-finetuned-test_63829_prefix_summarize

This model is a fine-tuned version of google/mt5-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 2.3498
  • Rouge1: 11.28
  • Rouge2: 3.5248
  • Rougel: 9.174
  • Rougelsum: 10.6313
  • Gen Len: 19.0

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
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 15

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
7.6624 1.25 500 2.6231 7.333 2.0471 6.2456 7.0157 14.01
3.3306 2.5 1000 2.5079 10.5135 3.0104 8.4645 9.8798 19.0
3.1123 3.75 1500 2.4512 10.5261 3.3739 8.6176 9.8711 19.0
2.9927 5.0 2000 2.4137 11.14 3.5973 9.2204 10.407 19.0
2.8765 6.25 2500 2.4050 10.9669 3.7633 9.1517 10.283 19.0
2.8211 7.5 3000 2.3828 11.6779 4.181 9.8295 10.9657 19.0
2.7589 8.75 3500 2.3756 11.6097 4.1335 9.7619 10.8368 19.0
2.722 10.0 4000 2.3627 11.8385 4.0634 9.6721 10.9386 19.0
2.6781 11.25 4500 2.3611 11.3415 3.5812 9.1328 10.6537 19.0
2.6648 12.5 5000 2.3524 11.3808 3.6088 9.2331 10.6316 19.0
2.6404 13.75 5500 2.3521 11.3031 3.5165 9.1629 10.6573 19.0
2.6397 15.0 6000 2.3498 11.28 3.5248 9.174 10.6313 19.0

Framework versions

  • Transformers 4.32.1
  • Pytorch 2.1.0
  • Datasets 2.12.0
  • Tokenizers 0.13.3