cutelemonlili/Qwen2.5-1.5B-Instruct_MATH_training_response_gpt-4o-mini_only_right

MATH_training_response_gpt-4o-mini_only_right

This model is a fine-tuned version of Qwen/Qwen2.5-1.5B-Instruct on the MATH_training_response_gpt-4o-mini_only_right dataset. It achieves the following results on the evaluation set:

• Loss: 0.1295

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: 1e-05
• train_batch_size: 2
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 8
• total_eval_batch_size: 4
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
0.154	0.2907	200	0.1434
0.1497	0.5814	400	0.1344
0.1469	0.8721	600	0.1278
0.0614	1.1628	800	0.1329
0.0467	1.4535	1000	0.1322
0.0648	1.7442	1200	0.1304

Framework versions

• Transformers 4.46.1
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.20.3