Hugging Face's logo

clui
/
fine

Text2Text Generation
Transformers
Safetensors
marian
Generated from Trainer
Inference Endpoints
Model card Files Community
fine / README.md
clui's picture
clui
End of training
5d01762 verified
preview code
|
raw
history blame contribute delete
1.77 kB
metadata
library_name: transformers
license: apache-2.0
base_model: clui/my_awesome_opus_books_model
tags:
  - generated_from_trainer
metrics:
  - bleu
model-index:
  - name: fine
    results: []

fine

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

  • Loss: 1.3081
  • Bleu: 13.0948
  • Gen Len: 46.6407

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: 32
  • eval_batch_size: 32
  • 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: 3
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Bleu Gen Len
1.4705 1.0 4251 1.3386 12.7303 46.7126
1.4137 2.0 8502 1.3173 12.9823 46.4627
1.3692 3.0 12753 1.3081 13.0948 46.6407

Framework versions

  • Transformers 4.48.0
  • Pytorch 2.4.0
  • Datasets 2.19.1
  • Tokenizers 0.21.0