codegen-350M-distilabel-intel-orca-dpo-pairs

This model is a fine-tuned version of Salesforce/codegen-350M-nl on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4248
• Rewards/chosen: -0.2842
• Rewards/rejected: -1.3968
• Rewards/accuracies: 0.8530
• Rewards/margins: 1.1126
• Logps/rejected: -371.9885
• Logps/chosen: -323.0711
• Logits/rejected: 14.0505
• Logits/chosen: 12.1271

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: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 250
• 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
0.572	0.78	250	0.4248	-0.2842	-1.3968	0.8530	1.1126	-371.9885	-323.0711	14.0505	12.1271

Framework versions

• PEFT 0.7.1
• Transformers 4.37.1
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1