Hugging Face's logo

diversen
/
google-t5_t5-small_da_en

Text2Text Generation
Transformers
Safetensors
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
google-t5_t5-small_da_en / README.md
diversen's picture
diversen
End of training
f761f9f verified
preview code
|
raw
history blame contribute delete
1.53 kB
metadata
license: apache-2.0
base_model: google-t5/t5-small
tags:
  - generated_from_trainer
metrics:
  - bleu
model-index:
  - name: google-t5_t5-small_da_en
    results: []

google-t5_t5-small_da_en

This model is a fine-tuned version of google-t5/t5-small on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.5321
  • Bleu: 14.9052
  • Gen Len: 17.2737

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: 2
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Bleu Gen Len
1.8371 1.0 98440 1.5981 14.2287 17.2902
1.758 2.0 196880 1.5321 14.9052 17.2737

Framework versions

  • Transformers 4.40.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1