|
--- |
|
license: gemma |
|
base_model: HuggingFaceH4/zephyr-7b-gemma-sft-v0.1 |
|
tags: |
|
- alignment-handbook |
|
- generated_from_trainer |
|
datasets: |
|
- argilla/dpo-mix-7k |
|
model-index: |
|
- name: DiscoPOP-zephyr-7b-gemma |
|
results: [] |
|
--- |
|
|
|
# DiscoPOP-zephyr-7b-gemma |
|
|
|
This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-gemma-sft-v0.1](https://huggingface.co./HuggingFaceH4/zephyr-7b-gemma-sft-v0.1) on the argilla/dpo-mix-7k dataset. |
|
|
|
This model is from the paper ["Discovering Preference Optimization Algorithms with and for Large Language Models"](https://arxiv.org/abs/2406.08414) |
|
|
|
Read the [blog post on it here!](https://sakana.ai/llm-squared) |
|
|
|
See the codebase to generate it here: [https://github.com/SakanaAI/DiscoPOP](https://github.com/SakanaAI/DiscoPOP) |
|
|
|
## Model description |
|
|
|
This model is identical in training to [HuggingFaceH4/zephyr-7b-gemma-v0.1](https://huggingface.co./HuggingFaceH4/zephyr-7b-gemma-v0.1), except instead of using Direct Preference Optimization (DPO), it uses DiscoPOP. |
|
|
|
DiscoPOP is our Discovered Preference Optimization algorithm, which is defined as follows: |
|
|
|
``` |
|
def log_ratio_modulated_loss( |
|
self, |
|
policy_chosen_logps: torch.FloatTensor, |
|
policy_rejected_logps: torch.FloatTensor, |
|
reference_chosen_logps: torch.FloatTensor, |
|
reference_rejected_logps: torch.FloatTensor, |
|
) -> torch.FloatTensor: |
|
pi_logratios = policy_chosen_logps - policy_rejected_logps |
|
ref_logratios = reference_chosen_logps - reference_rejected_logps |
|
logits = pi_logratios - ref_logratios |
|
# Modulate the mixing coefficient based on the log ratio magnitudes |
|
log_ratio_modulation = torch.sigmoid(logits) |
|
logistic_component = -F.logsigmoid(self.beta * logits) |
|
exp_component = torch.exp(-self.beta * logits) |
|
# Blend between logistic and exponential component based on log ratio modulation |
|
losses = logistic_component * (1 - log_ratio_modulation) + exp_component * log_ratio_modulation |
|
return losses |
|
``` |
|
|
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 5e-07 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 8 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 128 |
|
- 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: 2 |
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.1 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |
|
|
