dev-store/sc7b_ds8b

full_sft_sc7b

This model is a fine-tuned version of deepseek-ai/DeepSeek-R1-Distill-Llama-8B on the sc_7b dataset. It achieves the following results on the evaluation set:

• Loss: 0.7822

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: 1e-05
• train_batch_size: 2
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 8
• total_eval_batch_size: 4
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• num_epochs: 2.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.8185	0.4812	500	0.8154
0.781	0.9625	1000	0.7830
0.6674	1.4437	1500	0.7866
0.6517	1.9249	2000	0.7821

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0