ORPO-PHI-3

This model is a fine-tuned version of microsoft/Phi-3-mini-4k-instruct on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.7712
• Rewards/chosen: -0.1577
• Rewards/rejected: -0.1527
• Rewards/accuracies: 0.3000
• Rewards/margins: -0.0050
• Logps/rejected: -1.5273
• Logps/chosen: -1.5771
• Logits/rejected: 2.7883
• Logits/chosen: 1.8098
• Nll Loss: 1.6979
• Log Odds Ratio: -0.7331
• Log Odds Chosen: -0.0576

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-06
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• 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
1.7534	0.2020	25	1.7712	-0.1577	-0.1527	0.3000	-0.0050	-1.5273	-1.5771	2.7883	1.8098	1.6979	-0.7331	-0.0576
1.9166	0.4040	50	1.7712	-0.1577	-0.1527	0.3000	-0.0050	-1.5273	-1.5771	2.7883	1.8098	1.6979	-0.7331	-0.0576
1.436	0.6061	75	1.7712	-0.1577	-0.1527	0.3000	-0.0050	-1.5273	-1.5771	2.7883	1.8098	1.6979	-0.7331	-0.0576
1.6618	0.8081	100	1.7712	-0.1577	-0.1527	0.3000	-0.0050	-1.5273	-1.5771	2.7883	1.8098	1.6979	-0.7331	-0.0576

Framework versions

• PEFT 0.11.1
• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1