CoolFace
Modelpublic

AIPlans/tinyllama-1.1b-dpo-pku-saferlhf_2

sourceHugging Faceapache-2.0updated 5mo agoView on Hugging Face
0likes19downloads
Model Card

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

tinyllama-1.1b-dpo-pku-saferlhf_2

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v1.0 on an unknown dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.4486
  • —Rewards/chosen: -0.1778
  • —Rewards/rejected: -1.2187
  • —Rewards/accuracies: 0.8000
  • —Rewards/margins: 1.0409
  • —Logps/rejected: -217.7180
  • —Logps/chosen: -234.9111
  • —Logits/rejected: -2.4987
  • —Logits/chosen: -2.6097

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
  • —trainbatchsize: 4
  • —evalbatchsize: 4
  • —seed: 42
  • —gradientaccumulationsteps: 4
  • —totaltrainbatch_size: 16
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: cosine
  • —lrschedulerwarmup_ratio: 0.1
  • —num_epochs: 1.0

Training results

Training LossEpochStepValidation LossRewards/chosenRewards/rejectedRewards/accuraciesRewards/marginsLogps/rejectedLogps/chosenLogits/rejectedLogits/chosen
0.60750.09602000.60520.42080.19060.71700.2302-203.6246-228.9246-2.5653-2.6887
0.51980.19204000.51450.3083-0.28320.78500.5915-208.3632-230.0500-2.5310-2.6479
0.47030.28806000.48380.0019-0.79890.79400.8008-213.5201-233.1144-2.5215-2.6339
0.52230.38408000.46310.1561-0.74140.78800.8975-212.9448-231.5717-2.4968-2.6118
0.43350.480010000.4555-0.1607-1.15510.79500.9944-217.0816-234.7399-2.4976-2.6097
0.52140.576012000.4511-0.1319-1.14710.79901.0152-217.0018-234.4519-2.5001-2.6120
0.47840.671914000.4486-0.1778-1.21870.80001.0409-217.7180-234.9111-2.4987-2.6097
0.42230.767916000.4487-0.1274-1.16760.79901.0402-217.2067-234.4066-2.4987-2.6100
0.51140.863918000.4483-0.1119-1.15350.79901.0416-217.0661-234.2521-2.4988-2.6100
0.47630.959920000.4485-0.1144-1.15520.79501.0409-217.0830-234.2766-2.4989-2.6102

Framework versions

  • —Transformers 4.44.2
  • —Pytorch 2.10.0+cu130
  • —Datasets 2.21.0
  • —Tokenizers 0.19.1