1b611539-5973-4f1c-bd53-715cc60672e4

This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5291

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: 0.000204
• train_batch_size: 4
• eval_batch_size: 4
• seed: 40
• 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: 313

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0032	1	1.0355
0.4726	0.16	50	0.5734
0.4415	0.32	100	0.5618
0.4474	0.48	150	0.5592
0.488	0.64	200	0.5428
0.4632	0.8	250	0.5315
0.4823	0.96	300	0.5291

Framework versions

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