madlad400-finetuned-nih-en

This model is a fine-tuned version of jbochi/madlad400-3b-mt on the None dataset. It achieves the following results on the evaluation set:

• Loss: 7.0439
• Chrf: 30.0668

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: 0.001
• train_batch_size: 4
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Chrf
7.383	1.0	223	7.3002	22.5965
7.4008	2.0	446	7.1718	25.7886
7.2421	3.0	669	7.0958	28.2855
6.9042	4.0	892	7.0573	29.3997
7.1314	5.0	1115	7.0439	30.0668

Framework versions

• PEFT 0.12.0
• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1