AIPlans/TinyLlama-1.1B-IPO-PKU-SafeRLHF
024
<!-- 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-IPO-PKU-SafeRLHF
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: 18.4083
- Rewards/chosen: -0.3421
- Rewards/rejected: -0.4737
- Rewards/accuracies: 0.7389
- Rewards/margins: 0.1316
- Logps/rejected: -6.7403
- Logps/chosen: -5.4225
- Logits/rejected: -2.2712
- Logits/chosen: -2.4037
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
Training results
Framework versions
- Transformers 4.44.2
- Pytorch 2.11.0+cu130
- Datasets 2.21.0
- Tokenizers 0.19.1
