DietRecommendation-Qwen2.5-0.5B

This model is a fine-tuned version of Qwen/Qwen2.5-0.5B-Instruct on syubraj/DietRecommendation-dataset-Qwen-2.5-0.5b dataset. It achieves the following results on the evaluation set:

• Loss: 0.2343

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: 0.0002
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• 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_steps: 100
• num_epochs: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
3.0693	1.1765	100	0.2517
0.9641	2.3529	200	0.2243
0.8782	3.5294	300	0.2218
0.8378	4.7059	400	0.2253
0.8114	5.8824	500	0.2179
0.7791	7.0588	600	0.2193
0.7539	8.2353	700	0.2178
0.7247	9.4118	800	0.2185
0.6962	10.5882	900	0.2234
0.6731	11.7647	1000	0.2265
0.6363	12.9412	1100	0.2317
0.6184	14.1176	1200	0.2343

Framework versions

• PEFT 0.14.0
• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.3.1
• Tokenizers 0.21.0