jk1

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>

jk1

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: 0.4491
• Eval/rewards/chosen: -3.2146
• Eval/logps/chosen: -135.3127
• Eval/rewards/rejected: -13.3743
• Eval/logps/rejected: -264.5731
• Eval/rewards/margins: 10.1598
• 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: 0.0001
• 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: 2
• mixed_precision_training: Native AMP

Training results

Framework versions

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