metadata

library_name: transformers
license: apache-2.0
base_model: google/mt5-small
tags:
  - generated_from_trainer
model-index:
  - name: results
    results: []
datasets:
  - xonic48/amazon_review_multi
language:
  - en

results

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

eval_loss: 0.0001
eval_model_preparation_time: 0.0049
eval_rouge1: 99.9541
eval_rouge2: 87.8299
eval_rougeL: 99.9541
eval_rougeLsum: 99.9541
eval_runtime: 2.9907
eval_samples_per_second: 22.068
eval_steps_per_second: 3.009
step: 0

Model description

We have fine tuned google/mt5-small model on xonic48 amazon review data

Intended uses & limitations

More information needed

Training and evaluation data

We reduced the dataset to 20%, and selected data in english language, and then filtered it for book reviews.

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 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: 3

Framework versions

Transformers 4.46.3
Pytorch 2.5.1+cu121
Datasets 3.1.0
Tokenizers 0.20.3