README.md

metadata

library_name: transformers
license: apache-2.0
base_model: google-t5/t5-small
tags:
  - translation
  - generated_from_trainer
metrics:
  - bleu
model-index:
  - name: t5-small-finetuned-chinese-to-hausa
    results: []

t5-small-finetuned-chinese-to-hausa

This model is a fine-tuned version of google-t5/t5-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.8379
• Bleu: 10.0383
• Gen Len: 12.6887

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: 0.0008
• train_batch_size: 32
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1000
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
3.099	1.0	846	2.1974	11.0367	18.0696
2.1698	2.0	1692	1.9115	9.7895	12.3794
1.9576	3.0	2538	1.8379	10.0383	12.6887

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1