nkto2

This model is a fine-tuned version of deepseek-ai/deepseek-coder-1.3b-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1776
• Eval/rewards/chosen: 2.8408
• Eval/logps/chosen: -114.1873
• Eval/rewards/rejected: -13.1753
• Eval/logps/rejected: -312.8098
• Eval/rewards/margins: 16.0161
• Eval/kl: 11.2374

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: 5e-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 256
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• lr_scheduler_warmup_steps: 200
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.1137	1.8286	100	0.1776	11.2374

Framework versions

• Transformers 4.43.0.dev0
• Pytorch 2.2.2+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1