simpo-exps

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the princeton-nlp/llama3-ultrafeedback-armorm dataset. It achieves the following results on the evaluation set:

• Loss: 1.1745
• Rewards/chosen: -17.4859
• Rewards/rejected: -23.5403
• Rewards/accuracies: 0.8435
• Rewards/margins: 6.0544
• Logps/rejected: -2.3540
• Logps/chosen: -1.7486
• Logits/rejected: -1.5014
• Logits/chosen: -1.4906

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-06
• train_batch_size: 2
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 16
• total_train_batch_size: 128
• total_eval_batch_size: 16
• 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

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
1.1882	0.8550	400	1.1795	-17.3452	-23.3517	0.8435	6.0065	-2.3352	-1.7345	-1.4942	-1.4832

Framework versions

• Transformers 4.44.2
• Pytorch 2.2.2+cu121
• Datasets 2.18.0
• Tokenizers 0.19.1