nllb-200-distilled-600M-finetuned-isv_v2

This model is a fine-tuned version of Salavat/nllb-200-distilled-600M-finetuned-isv_v2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.0552
• Bleu: 9.1195
• Gen Len: 11.252

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: 3e-06
• 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: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
1.5967	1.0	8000	3.0552	9.1195	11.252

Framework versions

• Transformers 4.29.2
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3