Visualize in Trackio

nllb-dry-run

This model is a fine-tuned version of facebook/nllb-200-distilled-600M on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 3.5119
  • Bleu: 3.4640
  • Chrf: 18.8077

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: 8e-05
  • train_batch_size: 2
  • eval_batch_size: 4
  • seed: 42
  • optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • training_steps: 200

Training results

Training Loss Epoch Step Validation Loss Bleu Chrf
No log 0.3125 10 3.4697 2.3857 15.3837
No log 0.625 20 3.3382 3.7821 19.2101
No log 0.9375 30 3.3116 5.8430 18.9142
No log 1.25 40 3.2531 3.6516 19.1025
No log 1.5625 50 3.5119 3.4640 18.8077

Framework versions

  • Transformers 5.5.4
  • Pytorch 2.8.0+cu128
  • Datasets 4.8.4
  • Tokenizers 0.22.2
Downloads last month
45
Safetensors
Model size
0.6B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for madoss/nllb-dry-run

Finetuned
(279)
this model