genv3pair1NoGT_1.5B_cdpo_ebs32_lr5e-07_beta0.0_epoch8.0_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: -41.6977
  • Logps/chosen: -30.0700
  • Logits/rejected: -2.2294
  • Logits/chosen: -2.3763

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: 8.0

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 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 0.2235 40 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 0.3352 60 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 0.4469 80 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 0.5587 100 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 0.6704 120 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 0.7821 140 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 0.8939 160 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 1.0056 180 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 1.1173 200 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 1.2291 220 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 1.3408 240 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 1.4525 260 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 1.5642 280 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 1.6760 300 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 1.7877 320 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 1.8994 340 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 2.0112 360 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 2.1229 380 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 2.2346 400 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 2.3464 420 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 2.4581 440 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 2.5698 460 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 2.6816 480 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 2.7933 500 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 2.9050 520 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 3.0168 540 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 3.1285 560 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 3.2402 580 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 3.3520 600 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 3.4637 620 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 3.5754 640 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 3.6872 660 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 3.7989 680 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 3.9106 700 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 4.0223 720 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 4.1341 740 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 4.2458 760 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 4.3575 780 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 4.4693 800 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 4.5810 820 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 4.6927 840 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 4.8045 860 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 4.9162 880 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 5.0279 900 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 5.1397 920 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 5.2514 940 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 5.3631 960 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 5.4749 980 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 5.5866 1000 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 5.6983 1020 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 5.8101 1040 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 5.9218 1060 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 6.0335 1080 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 6.1453 1100 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 6.2570 1120 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 6.3687 1140 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 6.4804 1160 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 6.5922 1180 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 6.7039 1200 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 6.8156 1220 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 6.9274 1240 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 7.0391 1260 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 7.1508 1280 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 7.2626 1300 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 7.3743 1320 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 7.4860 1340 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 7.5978 1360 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 7.7095 1380 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 7.8212 1400 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763
0.6931 7.9330 1420 0.6931 0.0 0.0 0.0 0.0 -41.6977 -30.0700 -2.2294 -2.3763

Framework versions

  • Transformers 4.45.2
  • Pytorch 2.5.1+cu121
  • Datasets 3.5.0
  • Tokenizers 0.20.3
Downloads last month
2
Safetensors
Model size
2B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for YuchenLi01/genv3pair1NoGT_1.5B_cdpo_ebs32_lr5e-07_beta0.0_epoch8.0_42

Finetuned
(1506)
this model