stojchet_-_dpo5k2-awq

Quantization made by Richard Erkhov.

Github

Discord

Request more models

dpo5k2 - AWQ

• Model creator: https://huggingface.co/stojchet/
• Original model: https://huggingface.co/stojchet/dpo5k2/

Original model description:

license: other base_model: deepseek-ai/deepseek-coder-1.3b-base tags:

• trl
• dpo
• generated_from_trainer datasets:
• generator model-index:
• name: dpo5k2 results: []

---

<!-- 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"/>

dpo5k2

This model is a fine-tuned version of deepseek-ai/deepseek-coder-1.3b-base on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 6.1354
• Rewards/chosen: -37.3199
• Rewards/rejected: -114.4451
• Rewards/accuracies: 0.7599
• Rewards/margins: 77.1251
• Logps/rejected: -1316.1266
• Logps/chosen: -541.0429
• Logits/rejected: -13.2895
• Logits/chosen: -11.3220

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: 0.001
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 64
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 200
• num_epochs: 3

Training results

Framework versions

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