• Model creator: https://huggingface.co/IeBoytsov/
• Original model: https://huggingface.co/IeBoytsov/llama3-1-ox-llms-8b-sft-only-germany-data-and-ultrafeedback/

Original model description:

• alignment-handbook
• trl
• sft
• generated_from_trainer
• trl
• sft
• generated_from_trainer datasets:
• oxford-llms/european_social_survey_2023_germany_sft
• oxford-llms/ultrachat_filtered model-index:
• name: llama3-1-ox-llms-8b-sft-only-germany-data-and-ultrafeedback results: []

llama3-1-ox-llms-8b-sft-only-germany-data-and-ultrafeedback

• Loss: 1.0782

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• learning_rate: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• total_train_batch_size: 64
• total_eval_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 2

Training results

Framework versions

• Transformers 4.45.1
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.20.3