genv3pair1NoGT_1.5B_cdpo_ebs32_lr5e-07_beta0.0_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: 0.6931
• Rewards/chosen: 0.0
• Rewards/rejected: 0.0
• Rewards/accuracies: 0.0
• Rewards/margins: 0.0
• Logps/rejected: -41.6458
• Logps/chosen: -30.1322
• Logits/rejected: -2.2238
• Logits/chosen: -2.3689

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-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	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.6931	0.1117	20	0.6931	0.0	0.0	0.0	0.0	-41.6458	-30.1322	-2.2238	-2.3689
0.6931	0.2235	40	0.6931	0.0	0.0	0.0	0.0	-41.6458	-30.1322	-2.2238	-2.3689
0.6931	0.3352	60	0.6931	0.0	0.0	0.0	0.0	-41.6458	-30.1322	-2.2238	-2.3689
0.6931	0.4469	80	0.6931	0.0	0.0	0.0	0.0	-41.6458	-30.1322	-2.2238	-2.3689
0.6931	0.5587	100	0.6931	0.0	0.0	0.0	0.0	-41.6458	-30.1322	-2.2238	-2.3689
0.6931	0.6704	120	0.6931	0.0	0.0	0.0	0.0	-41.6458	-30.1322	-2.2238	-2.3689
0.6931	0.7821	140	0.6931	0.0	0.0	0.0	0.0	-41.6458	-30.1322	-2.2238	-2.3689
0.6931	0.8939	160	0.6931	0.0	0.0	0.0	0.0	-41.6458	-30.1322	-2.2238	-2.3689

Framework versions

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