DeepSeek-R1-Distill-Qwen-1.5B-Turkish

This model is a fine-tuned version of deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B on the reasoning-turkish-R1 dataset. It achieves the following results on the evaluation set:

• Loss: 1.1396

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: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• total_train_batch_size: 8
• 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: 0.01
• num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
1.6161	0.1028	26	1.4920
1.3683	0.2055	52	1.3256
1.409	0.3083	78	1.2486
1.1914	0.4111	104	1.2049
1.1264	0.5138	130	1.1763
1.1721	0.6166	156	1.1584
1.2738	0.7194	182	1.1467
1.1729	0.8221	208	1.1415
1.4446	0.9249	234	1.1399

Framework versions

• Transformers 4.48.2
• Pytorch 2.6.0+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0