This model is a fine-tuned version of Qwen/Qwen2.5-1.5B-Instruct on the YuchenLi01/MATH_Qwen2.5-1.5BInstruct_DPO_MoreUniqueResponseNoGTv3pair1 dataset. It achieves the following results on the evaluation set:

Loss: 0.0592

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: 5e-06
train_batch_size: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 8
total_train_batch_size: 32
total_eval_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.03
num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.0877	0.1117	20	0.0745
0.0634	0.2235	40	0.0649
0.0731	0.3352	60	0.0636
0.0582	0.4469	80	0.0625
0.0673	0.5587	100	0.0616
0.0602	0.6704	120	0.0608
0.0656	0.7821	140	0.0599
0.0639	0.8939	160	0.0595

Framework versions

Transformers 4.45.2
Pytorch 2.5.1+cu121
Datasets 3.5.0
Tokenizers 0.20.3

YuchenLi01/genv3pair1NoGT_1.5B_sft_prompt_completion_ebs32_lr5e-06_warmup0.03_linear_epoch1.0_42

genv3pair1NoGT_1.5B_sft_prompt_completion_ebs32_lr5e-06_warmup0.03_linear_epoch1.0_42

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

YuchenLi01/
genv3pair1NoGT_1.5B_sft_prompt_completion_ebs32_lr5e-06_warmup0.03_linear_epoch1.0_42