kto1

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: 0.5
• Eval/rewards/chosen: -987.8812
• Eval/logps/chosen: -9916.1920
• Eval/rewards/rejected: -955.7355
• Eval/logps/rejected: -9631.8088
• Eval/rewards/margins: -32.1457
• Eval/kl: 0.0

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: 0.1
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 128
• 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
0.498	1.1552	100	0.5	0.0
0.5004	2.3105	200	0.5	0.0

Framework versions

• Transformers 4.45.0
• Pytorch 2.5.1+cu124
• Datasets 2.19.2
• Tokenizers 0.20.3