results

This model is a fine-tuned version of NousResearch/Meta-Llama-3-8B-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1433
• Rewards/chosen: -0.0156
• Rewards/rejected: -1.1268
• Rewards/accuracies: 1.0
• Rewards/margins: 1.1112
• Logps/rejected: -11.2681
• Logps/chosen: -0.1556
• Logits/rejected: -0.2138
• Logits/chosen: 0.6631
• Nll Loss: 0.1433
• Log Odds Ratio: -0.0000
• Log Odds Chosen: 13.2065

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: 8e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 10
• 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	Nll Loss	Log Odds Ratio	Log Odds Chosen
0.1869	0.5001	2175	0.1433	-0.0156	-1.1268	1.0	1.1112	-11.2681	-0.1556	-0.2138	0.6631	0.1433	-0.0000	13.2065

Framework versions

• PEFT 0.11.1
• Transformers 4.42.3
• Pytorch 2.1.2+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1