llama-3.1-8b-instruct_LBox-category-prior-8x1-lora-moe

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

llama-3.1-8b-instruct_LBox-category-prior-8x1-lora-moe

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.7146
• Router Supervised Loss: 1.2566
• Router Load Balance Loss: 2.9630
• Router Z Loss: 1.6500

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: 0.0001
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• total_eval_batch_size: 2
• optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 0.03
• num_epochs: 5.0

Training results

Framework versions

• Transformers 5.9.0
• Pytorch 2.11.0+cu130
• Datasets 4.4.1
• Tokenizers 0.22.2