madlad400-finetuned-lora

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: 7.4433
• Chrf: 37.7656

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: 8
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• 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
7.5714	0.9997	1748	7.4837	36.0379
7.5863	2.0	3497	7.4686	36.6073
7.5366	2.9997	5245	7.4529	37.1613
7.5282	4.0	6994	7.4461	37.4309
7.6738	4.9986	8740	7.4433	37.7656

Framework versions

• PEFT 0.12.0
• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 2.14.4
• Tokenizers 0.19.1