Hugging Face's logo

1dfs6df
/
deepseek-mvp

PEFT
Safetensors
Generated from Trainer
Model card Files Community
deepseek-mvp / README.md
1dfs6df's picture
1dfs6df
End of training
f4d55c1 verified
preview code
|
raw
history blame contribute delete
1.47 kB
metadata
license: mit
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
tags:
  - generated_from_trainer
library_name: peft
model-index:
  - name: deepseek-mvp
    results: []

Visualize in Weights & Biases

deepseek-mvp

This model is a fine-tuned version of deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B 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: 2e-05
  • train_batch_size: 12
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 3
  • total_train_batch_size: 36
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.05
  • training_steps: 375

Training results

Framework versions

  • PEFT 0.11.0
  • Transformers 4.41.0
  • Pytorch 2.4.0+cu118
  • Datasets 2.19.0
  • Tokenizers 0.19.1