mixed-nllb-top200k-mt-stage2

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.1615
• Bleu: 14.2850
• Chrf: 36.6357

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: 16
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 128
• 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: cosine_with_min_lr
• lr_scheduler_warmup_steps: 0.1
• num_epochs: 5.0

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Chrf
4.6647	0.3514	500	2.1588	14.0061	36.5161
4.3315	0.7027	1000	2.1549	13.8810	36.6639
4.2232	1.0541	1500	2.1715	13.7763	36.4163
4.1527	1.4055	2000	2.1611	13.9239	36.7048
4.0216	1.7569	2500	2.1656	14.4365	36.8727
4.0492	2.1082	3000	2.1635	14.1413	36.5556
3.9081	2.4596	3500	2.1600	14.5304	36.7498
3.9966	2.8110	4000	2.1615	14.2850	36.6357

Framework versions

• Transformers 5.7.0
• Pytorch 2.8.0+cu128
• Datasets 4.8.5
• Tokenizers 0.22.2