genv3pair1NoGT_1.5B_sft_prompt_completion_ebs32_lr1e-07_epoch1.0_42

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: 0.4072

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-07
• 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: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.5838	0.1117	20	0.5693
0.485	0.2235	40	0.5479
0.5075	0.3352	60	0.5012
0.5029	0.4469	80	0.4794
0.3789	0.5587	100	0.4371
0.3852	0.6704	120	0.4177
0.4143	0.7821	140	0.4107
0.3486	0.8939	160	0.4085

Framework versions

• Transformers 4.45.2
• Pytorch 2.5.1+cu121
• Datasets 3.5.0
• Tokenizers 0.20.3