SFT-Compo-Distill-Llama-8B
This model is a fine-tuned version of deepseek-ai/DeepSeek-R1-Distill-Llama-8B on the deepscaler-14b-min 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-06
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- total_eval_batch_size: 64
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 5.0
Training results
Framework versions
- Transformers 4.55.0
- Pytorch 2.8.0+cu128
- Datasets 3.6.0
- Tokenizers 0.21.1
- Downloads last month
- 8
Model tree for LoRe-Team/SFT-Compo-Distill-Llama-8B
Base model
deepseek-ai/DeepSeek-R1-Distill-Llama-8B