models/deepseek-doc-and-code/README.md

metadata

library_name: peft
tags:
  - alignment-handbook
  - generated_from_trainer
base_model: deepseek-coder-7b-instruct-v1.5
datasets:
  - graph tool agent/benchmark/datasets/code_data_pro_v4
model-index:
  - name: deepseek-coder-7b-instruct-v1.5-doc-and-code
    results: []

deepseek-coder-7b-instruct-v1.5-doc-and-code

This model is a fine-tuned version of deepseek-coder-7b-instruct-v1.5 on the /home/lixin/graph tool agent/benchmark/datasets/code_data_pro_v4 dataset.

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: 0.0002
• train_batch_size: 1
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 4
• total_eval_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 4

Training results

Framework versions

• PEFT 0.7.1
• Transformers 4.39.3
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.15.2