realYinkaIyiola/Deepseek-R1-Distill-14B-Code

code_finetune

This model is a fine-tuned version of deepseek-ai/DeepSeek-R1-Distill-Qwen-14B on the open_thoughts_19K dataset. It achieves the following results on the evaluation set:

• Loss: 0.4811

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: 8
• total_train_batch_size: 16
• total_eval_batch_size: 8
• 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
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.4844	0.8929	1000	0.4723
0.4258	1.7857	2000	0.4722
0.3709	2.6786	3000	0.4812

Framework versions

• Transformers 4.50.0
• Pytorch 2.6.0+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0