549c1f21-3c94-4c35-a408-7b58fce22685

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

• Loss: 2.4324

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: 0.000207
• 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	0.0000	1	5.7144
3.0023	0.0011	50	3.0515
3.0083	0.0021	100	2.7694
2.552	0.0032	150	2.6152
2.879	0.0042	200	2.5841
2.772	0.0053	250	2.5284
2.5812	0.0063	300	2.5045
2.5065	0.0074	350	2.4706
2.6194	0.0084	400	2.4463
2.6297	0.0095	450	2.4345
2.7286	0.0105	500	2.4324

Framework versions

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