ZhiguangHan's picture
End of training
1bfe430
|
raw
history blame
2.05 kB
metadata
license: apache-2.0
base_model: google/mt5-small
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: mt5-small-task2-dataset4
    results: []

mt5-small-task2-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: 0.5227
  • Accuracy: 0.212

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: 12

Training results

Training Loss Epoch Step Validation Loss Accuracy
6.2329 1.0 250 1.3076 0.006
1.6853 2.0 500 0.8967 0.09
1.123 3.0 750 0.7346 0.132
0.907 4.0 1000 0.6587 0.162
0.7875 5.0 1250 0.6083 0.17
0.7135 6.0 1500 0.5807 0.188
0.675 7.0 1750 0.5566 0.196
0.6403 8.0 2000 0.5427 0.206
0.6229 9.0 2250 0.5354 0.208
0.6046 10.0 2500 0.5329 0.212
0.5974 11.0 2750 0.5237 0.212
0.5875 12.0 3000 0.5227 0.212

Framework versions

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