Edit model card

my_fon_translation_model

This model is a fine-tuned version of Zelyanoth/my_fon_translation_model on the generator dataset. It achieves the following results on the evaluation set:

  • Loss: 6.1298
  • Bleu: 8.059
  • Gen Len: 8.4704

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: 4.6e-08
  • 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 Bleu Gen Len
0.5745 1.0 13165 6.1275 7.8417 8.5553
0.564 2.0 26330 6.1295 7.8534 8.5544
0.5611 3.0 39495 6.1291 7.8887 8.5456
0.5538 4.0 52660 6.1288 7.7891 8.5627
0.566 5.0 65825 6.1296 8.0473 8.4714
0.5745 6.0 78990 6.1297 8.059 8.4695
0.5638 7.0 92155 6.1298 8.0595 8.47
0.5666 8.0 105320 6.1298 8.059 8.4704

Framework versions

  • Transformers 4.39.3
  • Pytorch 2.1.2
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
5
Safetensors
Model size
615M params
Tensor type
F32
·
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.

Finetuned from

Evaluation results