ZhiguangHan's picture
End of training
e47a42a
|
raw
history blame
2.87 kB
metadata
license: apache-2.0
base_model: google/mt5-small
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: mt5-small-task3-dataset2
    results: []

mt5-small-task3-dataset2

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: 1.4809
  • Accuracy: 0.05
  • Mse: 3.5326
  • Log-distance: 0.6225
  • S Score: 0.5228

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
10.7614 1.0 250 2.2221 0.02 4.6987 0.8722 0.3952
3.1541 2.0 500 1.8435 0.03 4.5082 0.8636 0.4076
2.2712 3.0 750 1.6006 0.058 4.0535 0.6741 0.4904
1.9534 4.0 1000 1.5801 0.048 3.8523 0.6757 0.4900
1.7967 5.0 1250 1.5597 0.058 4.0535 0.6741 0.4904
1.7555 6.0 1500 1.5326 0.062 4.0192 0.6611 0.5000
1.7044 7.0 1750 1.5198 0.06 4.0145 0.6662 0.4964
1.6736 8.0 2000 1.4987 0.046 3.6736 0.6423 0.5152
1.655 9.0 2250 1.5009 0.064 4.0090 0.6499 0.5072
1.6357 10.0 2500 1.4970 0.04 3.4623 0.6158 0.5288
1.6174 11.0 2750 1.4911 0.062 3.9369 0.6443 0.5100
1.6024 12.0 3000 1.4913 0.054 3.8887 0.6435 0.5152
1.6116 13.0 3250 1.4828 0.056 3.4981 0.6225 0.5200
1.5988 14.0 3500 1.4831 0.048 3.6081 0.6275 0.5204
1.6008 15.0 3750 1.4809 0.05 3.5326 0.6225 0.5228

Framework versions

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