554709a9-459a-4849-bde2-ce9c33cb634e

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: 1.9317

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: 0.000201
• train_batch_size: 4
• eval_batch_size: 4
• seed: 10
• 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	0.0001	1	3.0700
2.1679	0.0027	50	2.3646
2.0188	0.0053	100	2.2475
2.1242	0.0080	150	2.1766
2.012	0.0107	200	2.1495
1.8255	0.0133	250	2.0661
1.7791	0.0160	300	2.0367
1.8133	0.0186	350	1.9786
1.9783	0.0213	400	1.9485
1.7968	0.0240	450	1.9355
1.8858	0.0266	500	1.9317

Framework versions

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