a50ce1a6-1e8a-4ba3-b071-6433b8fa65f2

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

• Loss: 1.8317

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: 0.00021
• train_batch_size: 4
• eval_batch_size: 4
• seed: 100
• 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	0.0000	1	2.3972
1.7855	0.0008	50	2.0745
1.8088	0.0016	100	2.0415
2.0447	0.0024	150	2.0026
1.7727	0.0032	200	1.9788
1.9348	0.0040	250	1.9621
1.9455	0.0048	300	1.8734
1.8008	0.0056	350	1.8570
1.8836	0.0064	400	1.8357
1.9719	0.0072	450	1.8332
1.9535	0.0080	500	1.8317

Framework versions

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