Hugging Face's logo

KSU-HW-SEC
/
r1q1.5_graph_lora

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
text-generation-inference
Model card Files Community
r1q1.5_graph_lora / read.md
wf8888884's picture
wf8888884
Create read.md
eda047e verified
preview code
|
raw
history blame contribute delete
1.27 kB
metadata
library_name: transformers
license: mit
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
tags:
  - generated_from_trainer
model-index:
  - name: r1q1.5_graph_lora
    results: []

r1q1.5_graph_lora

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: 5e-05
  • train_batch_size: 10
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Use OptimizerNames.GALORE_ADAMW with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=rank=128,scale=2.0
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 1000
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • Transformers 4.49.0
  • Pytorch 2.4.1+cu124
  • Tokenizers 0.21.0