mistral-sft-lora-fsdp3

This model is a fine-tuned version of meta-llama/Llama-3.1-70B-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3421

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: 2
• eval_batch_size: 1
• seed: 100
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• total_eval_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• training_steps: 857

Training results

Training Loss	Epoch	Step	Validation Loss
0.3553	0.9988	427	0.3784
0.2661	2.0	855	0.3421

Framework versions

• PEFT 0.14.0
• Transformers 4.45.2
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.20.1