Edit model card

mt5-small-finetuned-amazon-en-es-finetuned-amazon-en-es

This model is a fine-tuned version of LinhCT/mt5-small-finetuned-amazon-en-es on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 3.4243
  • Rouge1: 28.2282
  • Rouge2: 13.0079
  • Rougel: 27.8476
  • Rougelsum: 27.9373

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
5.1931 1.0 1152 3.7893 19.9416 8.7882 19.7175 19.6944
4.2391 2.0 2304 3.6033 24.7762 11.4627 24.5132 24.5349
3.9401 3.0 3456 3.5088 25.618 11.8757 25.316 25.3784
3.7617 4.0 4608 3.4602 26.2721 11.8065 25.9693 26.0518
3.6381 5.0 5760 3.4439 27.3459 12.668 26.9862 27.0528
3.548 6.0 6912 3.4317 27.751 12.7711 27.3445 27.3912
3.4956 7.0 8064 3.4343 28.7685 13.1835 28.3702 28.4383
3.4589 8.0 9216 3.4243 28.2282 13.0079 27.8476 27.9373

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.2
  • Tokenizers 0.19.1
Downloads last month
2
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 LinhCT/mt5-small-finetuned-amazon-en-es-finetuned-amazon-en-es

Base model

google/mt5-small
Finetuned
(1)
this model