LongRAG_ministral-8b-instruct-2410

This model is a fine-tuned version of mistralai/Ministral-8B-Instruct-2410 on the LRGinstruction dataset. It achieves the following results on the evaluation set:

• Loss: 0.0567

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: 2e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 12
• total_train_batch_size: 192
• total_eval_batch_size: 16
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.3377	2.0	27	0.0529

Framework versions

• Transformers 4.46.1
• Pytorch 2.5.1+cu124
• Datasets 3.0.1
• Tokenizers 0.20.4