Downloads · 30 days
8
2% of all-time downloads
zephyr-2b-gemma-dpo
ale-bay/zephyr-2b-gemma-dpo
zephyr-2b-gemma-dpo is a text generation model from ale-bay. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as gemma.
should probably proofread and complete it, then remove this comment. --
All-time downloads
518
Public
Parameters
2.5B
5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors5 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- gemma
- Model type
- gemma
- Access
- Public
- Created
- Jul 11, 2024
- Updated
- Jul 12, 2024
- SHA
- 46c8deb9
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
<!-- 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. -->
zephyr-2b-gemma-dpo
This model is a fine-tuned version of 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
- Task
- Text Generation
- Library
- transformers
- Type
- gemma
- License
- gemma
- Created
- Jul 11, 2024
- Updated
- Jul 12, 2024