MyModel

This model is a fine-tuned version of deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2093

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.9491	0.2693	500	0.6303
0.6241	0.5385	1000	0.5958
0.5923	0.8078	1500	0.5590
0.5584	1.0770	2000	0.5180
0.5264	1.3463	2500	0.4764
0.5164	1.6155	3000	0.4459
0.5046	1.8848	3500	0.4069
0.3944	2.1540	4000	0.3134
0.3362	2.4233	4500	0.2675
0.32	2.6925	5000	0.2293
0.3115	2.9618	5500	0.2093

Framework versions

• Transformers 4.48.2
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0