jnkto1

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: 0.1736
• Eval/rewards/chosen: 2.7194
• Eval/logps/chosen: -115.4005
• Eval/rewards/rejected: -10.6606
• Eval/logps/rejected: -287.6642
• Eval/rewards/margins: 13.3800
• Eval/kl: 9.8756

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: 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
0.2036	0.9143	100	0.2671	17.7704
0.0449	1.8286	200	0.2020	13.9933
0.0259	2.7429	300	0.1736	9.8756

Framework versions

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