jahyungu/deepseek-coder-1.3b-instruct-Qasper

<!-- 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. -->

deepseek-coder-1.3b-instruct-Qasper

This model is a fine-tuned version of deepseek-ai/deepseek-coder-1.3b-instruct on an unknown 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
• —trainbatchsize: 4
• —evalbatchsize: 8
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 2
• —gradientaccumulationsteps: 4
• —totaltrainbatch_size: 32
• —totalevalbatch_size: 16
• —optimizer: Use adamwtorch with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
• —lrschedulertype: constant
• —lrschedulerwarmup_ratio: 0.03
• —num_epochs: 3

Training results

Framework versions

• —PEFT 0.18.1
• —Transformers 4.56.0
• —Pytorch 2.10.0+cu130
• —Datasets 2.21.0
• —Tokenizers 0.22.2