mt5-finetuned-summarize

This model is a fine-tuned version of google/mt5-base on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: nan
  • Rouge1: 0.0
  • Rouge2: 0.0
  • Rougel: 0.0
  • Rougelsum: 0.0

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: 5e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 20
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum
0.0 0.9875 79 nan 0.0 0.0 0.0 0.0
0.0 1.975 158 nan 0.0 0.0 0.0 0.0
0.0 2.9625 237 nan 0.0 0.0 0.0 0.0
0.0 3.95 316 nan 0.0 0.0 0.0 0.0
0.0 4.9375 395 nan 0.0 0.0 0.0 0.0
0.0 5.925 474 nan 0.0 0.0 0.0 0.0
0.0 6.9125 553 nan 0.0 0.0 0.0 0.0
0.0 7.9 632 nan 0.0 0.0 0.0 0.0
0.0 8.8875 711 nan 0.0 0.0 0.0 0.0
0.0 9.875 790 nan 0.0 0.0 0.0 0.0
0.0 10.8625 869 nan 0.0 0.0 0.0 0.0
0.0 11.85 948 nan 0.0 0.0 0.0 0.0
0.0 12.8375 1027 nan 0.0 0.0 0.0 0.0
0.0 13.825 1106 nan 0.0 0.0 0.0 0.0
0.0 14.8125 1185 nan 0.0 0.0 0.0 0.0
0.0 15.8 1264 nan 0.0 0.0 0.0 0.0
0.0 16.7875 1343 nan 0.0 0.0 0.0 0.0
0.0 17.775 1422 nan 0.0 0.0 0.0 0.0
0.0 18.7625 1501 nan 0.0 0.0 0.0 0.0
0.0 19.75 1580 nan 0.0 0.0 0.0 0.0

Framework versions

  • Transformers 4.47.1
  • Pytorch 2.5.1+cu121
  • Datasets 3.2.0
  • Tokenizers 0.21.0
Downloads last month
23
Safetensors
Model size
582M 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 JimmyPin/mt5-finetuned-summarize

Base model

google/mt5-base
Finetuned
(168)
this model