Megagon_step3_tsmtz

This model is a fine-tuned version of tsmatz/mt5_summarize_japanese on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.6120
  • Rouge1: 0.1897
  • Rouge2: 0.0766
  • Rougel: 0.1897
  • Rougelsum: 0.1916
  • Gen Len: 9.5631

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: 2e-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: 4

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
No log 1.0 79 1.8495 0.1928 0.0738 0.1918 0.1949 9.536
No log 2.0 158 1.7032 0.1975 0.0758 0.1978 0.2004 9.5586
No log 3.0 237 1.6334 0.1883 0.0751 0.1882 0.1901 9.5315
No log 4.0 316 1.6120 0.1897 0.0766 0.1897 0.1916 9.5631

Framework versions

  • Transformers 4.34.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.14.1
Downloads last month
15
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 Tottin/Megagon_step3_tsmtz

Base model

google/mt5-small
Finetuned
(2)
this model