nllb-finetuned-ar-en

This model is a fine-tuned version of facebook/nllb-200-distilled-600M on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6562

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: 15

Training results

Training Loss Epoch Step Validation Loss
1.5222 1.0 515 1.2649
1.2832 2.0 1030 1.1357
1.1181 3.0 1545 1.0412
1.0074 4.0 2060 0.9647
0.8996 5.0 2575 0.8987
0.8206 6.0 3090 0.8478
0.7525 7.0 3605 0.8047
0.6886 8.0 4120 0.7683
0.6443 9.0 4635 0.7336
0.5983 10.0 5150 0.7076
0.5675 11.0 5665 0.6910
0.5415 12.0 6180 0.6744
0.524 13.0 6695 0.6652
0.5028 14.0 7210 0.6578
0.5028 15.0 7725 0.6562

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.5.0+cu121
  • Datasets 3.1.0
  • Tokenizers 0.19.1
Downloads last month
14
Safetensors
Model size
615M params
Tensor type
F32
·
Inference Examples
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.

Model tree for asimokby/nllb-finetuned-ar-en

Finetuned
(86)
this model