ZhiguangHan's picture
End of training
b968e04
|
raw
history blame
2.39 kB
metadata
license: apache-2.0
base_model: google/mt5-small
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: mt5-small-task3-dataset4
    results: []

mt5-small-task3-dataset4

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

  • Loss: 1.5832
  • Accuracy: 0.056
  • Mse: 6.6919
  • Log-distance: 0.6837
  • S Score: 0.4844

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: 16
  • eval_batch_size: 16
  • 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 Accuracy Mse Log-distance S Score
10.6622 1.0 250 2.1479 0.032 7.8307 0.8081 0.4244
3.1421 2.0 500 1.8253 0.044 5.7385 0.6844 0.4892
2.3451 3.0 750 1.6174 0.04 5.5959 0.6980 0.4832
2.0073 4.0 1000 1.5994 0.046 6.2422 0.6708 0.4940
1.8357 5.0 1250 1.5867 0.05 6.2493 0.6727 0.4936
1.7782 6.0 1500 1.5800 0.048 6.0314 0.6621 0.4980
1.7333 7.0 1750 1.5733 0.056 6.8849 0.6908 0.4816
1.7219 8.0 2000 1.6012 0.056 6.7969 0.6872 0.4828
1.6886 9.0 2250 1.5849 0.038 6.1512 0.6683 0.4976
1.6804 10.0 2500 1.5832 0.056 6.6919 0.6837 0.4844

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.15.0
  • Tokenizers 0.15.0