DongfuJiang/vapo_lora_all_data_iter_1

iter_1

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the pref_data_1 dataset. It achieves the following results on the evaluation set:

• Loss: 0.9272
• Rewards/chosen: -0.0568
• Rewards/rejected: -0.1245
• Rewards/accuracies: 0.9809
• Rewards/margins: 0.0677
• Logps/rejected: -1.2445
• Logps/chosen: -0.5677
• Logits/rejected: 0.0790
• Logits/chosen: 0.5251

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: 1e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 16
• total_train_batch_size: 128
• total_eval_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1

Training results

Framework versions

• PEFT 0.11.1
• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1