Edit model card

Mymt5-small-test

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: 16.9555
  • Rouge1: 5.3063
  • Rouge2: 0.3834
  • Rougel: 4.7129
  • Rougelsum: 4.769

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: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 8

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum
32.0529 1.0 10 22.9068 4.148 0.2063 4.0534 4.0281
26.8483 2.0 20 20.5579 4.2091 0.2815 4.2287 4.2414
26.3936 3.0 30 19.4139 4.199 0.2051 4.1823 4.1637
24.8239 4.0 40 18.3165 4.2308 0.2812 4.2404 4.2749
24.0505 5.0 50 17.3909 4.9556 0.486 4.6229 4.6138
23.8294 6.0 60 17.0988 5.4206 0.5003 4.7981 4.7944
22.7513 7.0 70 16.9862 5.3119 0.3966 4.814 4.7785
22.836 8.0 80 16.9555 5.393 0.3829 4.7334 4.8031

Framework versions

  • Transformers 4.40.0
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1
Downloads last month
11
Safetensors
Model size
300M params
Tensor type
F32
·

Finetuned from