mt5-small-task1-dataset1

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: 0.6492
  • Accuracy: 0.626

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
10.2312 1.0 250 2.1246 0.194
2.2998 2.0 500 1.4171 0.194
1.6645 3.0 750 1.2718 0.206
1.4575 4.0 1000 1.1549 0.258
1.3335 5.0 1250 1.0267 0.432
1.1696 6.0 1500 0.8811 0.5
0.9974 7.0 1750 0.7960 0.532
0.9162 8.0 2000 0.7576 0.556
0.8463 9.0 2250 0.7342 0.588
0.8078 10.0 2500 0.6856 0.606
0.7751 11.0 2750 0.6655 0.612
0.7533 12.0 3000 0.6645 0.622
0.7337 13.0 3250 0.6625 0.62
0.7154 14.0 3500 0.6640 0.624
0.7038 15.0 3750 0.6492 0.626

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.15.0
  • Tokenizers 0.15.0
Downloads last month
75
Safetensors
Model size
300M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for ZhiguangHan/mt5-small-task1-dataset1

Base model

google/mt5-small
Finetuned
(365)
this model