QinLiuNLP/llama3-sudo-dpo-instruct-5epochs-forget10-lora
05
<!-- 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. -->
llama3-sudo-dpo-instruct-5epochs-forget10-lora
This model is a fine-tuned version of Jackie999/llama3-sudo-5epochs-tofu_full_sft on an unknown dataset.
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: 2
- evalbatchsize: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradientaccumulationsteps: 4
- totaltrainbatch_size: 32
- totalevalbatch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lrschedulertype: cosine
- lrschedulerwarmup_ratio: 0.1
- num_epochs: 5
Training results
Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.1.2
- Datasets 3.0.0
- Tokenizers 0.19.1