This model is a fine-tuned version of Qwen/Qwen2.5-3B-Instruct on the MATH_training_response_gpt-4o-mini_only_right dataset. It achieves the following results on the evaluation set:

Loss: 0.1166

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
0.1376	0.2907	200	0.1329
0.1373	0.5814	400	0.1217
0.132	0.8721	600	0.1143
0.051	1.1628	800	0.1237
0.0393	1.4535	1000	0.1196
0.0487	1.7442	1200	0.1173

Framework versions

Transformers 4.46.1
Pytorch 2.5.1+cu124
Datasets 3.1.0
Tokenizers 0.20.3

cutelemonlili/Qwen2.5-3B-Instruct_MATH_training_response_gpt-4o-mini_only_right

MATH_training_response_gpt-4o-mini_only_right

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

cutelemonlili/
Qwen2.5-3B-Instruct_MATH_training_response_gpt-4o-mini_only_right