reviews_sum / README.md
mirfan899's picture
End of training
2732577
|
raw
history blame
2.41 kB
metadata
license: apache-2.0
base_model: google/mt5-small
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: reviews_sum
    results: []

reviews_sum

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

  • Loss: 2.8535
  • Rouge1: 0.0273
  • Rouge2: 0.0
  • Rougel: 0.0277
  • Rougelsum: 0.0274
  • 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: 0.001
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
No log 1.0 395 3.4194 0.0339 0.0 0.0338 0.0338 19.0
4.9137 2.0 790 3.0496 0.0339 0.0 0.0338 0.0338 19.0
3.1919 3.0 1185 2.9381 0.0339 0.0 0.0338 0.0338 19.0
2.8961 4.0 1580 2.8875 0.0339 0.0 0.0338 0.0338 19.0
2.8961 5.0 1975 2.8487 0.0 0.0 0.0 0.0 19.0
2.72 6.0 2370 2.8328 0.0339 0.0 0.0338 0.0338 19.0
2.5695 7.0 2765 2.8332 0.0273 0.0 0.0277 0.0274 19.0
2.4644 8.0 3160 2.8412 0.0 0.0 0.0 0.0 19.0
2.3847 9.0 3555 2.8358 0.0339 0.0 0.0338 0.0338 19.0
2.3847 10.0 3950 2.8535 0.0273 0.0 0.0277 0.0274 19.0

Framework versions

  • Transformers 4.35.0
  • Pytorch 2.0.0
  • Datasets 2.14.6
  • Tokenizers 0.14.1