bc20f77f-9a16-4638-9e39-c471058f2bda

This model is a fine-tuned version of unsloth/Qwen2.5-0.5B-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.9268

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: 0.000208
• train_batch_size: 4
• eval_batch_size: 4
• seed: 80
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_BNB 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: 50
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0009	1	1.3996
1.0416	0.0433	50	1.0105
1.0498	0.0866	100	0.9906
1.0583	0.1299	150	0.9835
0.9947	0.1732	200	0.9682
1.0127	0.2165	250	0.9623
0.9329	0.2597	300	0.9513
0.9489	0.3030	350	0.9366
0.9869	0.3463	400	0.9309
0.9815	0.3896	450	0.9274
0.9707	0.4329	500	0.9268

Framework versions

• PEFT 0.13.2
• Transformers 4.46.0
• Pytorch 2.5.0+cu124
• Datasets 3.0.1
• Tokenizers 0.20.1