Sauron0019/DeepSeek-LLM-7B-Base-TagPrediction-Top5-Editorial

<!-- 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. -->

train2025-05-16-10-50-14final

This model is a fine-tuned version of deepseek-ai/deepseek-llm-7b-base on the top5training_dataset 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: 3e-05
• —trainbatchsize: 8
• —evalbatchsize: 8
• —seed: 42
• —gradientaccumulationsteps: 4
• —totaltrainbatch_size: 32
• —optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
• —lrschedulertype: cosinewithrestarts
• —lrschedulerwarmup_steps: 200
• —num_epochs: 5.0
• —labelsmoothingfactor: 0.05

Training results

Framework versions

• —PEFT 0.15.1
• —Transformers 4.51.3
• —Pytorch 2.6.0+cu124
• —Datasets 3.5.0
• —Tokenizers 0.21.1