|
--- |
|
license: gemma |
|
base_model: google/gemma-2b |
|
tags: |
|
- alignment-handbook |
|
- trl |
|
- dpo |
|
- generated_from_trainer |
|
- trl |
|
- dpo |
|
- generated_from_trainer |
|
datasets: |
|
- argilla/dpo-mix-7k |
|
model-index: |
|
- name: zephyr-2b-gemma-dpo |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://zebra.wandb.io/cto/distillm/runs/vnc8ka21) |
|
# zephyr-2b-gemma-dpo |
|
|
|
This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co./google/gemma-2b) on the argilla/dpo-mix-7k dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6493 |
|
- Rewards/chosen: -0.0415 |
|
- Rewards/rejected: -0.1402 |
|
- Rewards/accuracies: 0.6875 |
|
- Rewards/margins: 0.0986 |
|
- Logps/rejected: -378.6258 |
|
- Logps/chosen: -386.1853 |
|
- Logits/rejected: -25.9826 |
|
- Logits/chosen: -26.9604 |
|
|
|
## 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: 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 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen | |
|
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:| |
|
| 0.6264 | 1.8957 | 100 | 0.6497 | -0.0395 | -0.1328 | 0.6354 | 0.0933 | -378.4776 | -386.1444 | -25.9802 | -26.9529 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.4 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
