f22c41e7-4f03-4480-9d93-a3f0bdc7db18

This model is a fine-tuned version of unsloth/Qwen2.5-3B-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5610

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: 0.000206
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• 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	0.0008	1	5.4915
0.7466	0.0402	50	0.8282
0.6858	0.0804	100	0.7550
0.5875	0.1205	150	0.6879
0.6634	0.1607	200	0.7120
0.6121	0.2009	250	0.6567
0.4572	0.2411	300	0.6052
0.6391	0.2812	350	0.6028
0.5396	0.3214	400	0.5561
0.5261	0.3616	450	0.5458
0.5195	0.4018	500	0.5610

Framework versions

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