zephyr-7b-dpo-full
This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on the evaluation set:
- Loss: 0.4880
- Rewards/chosen: -2.3992
- Rewards/rejected: -3.5901
- Rewards/accuracies: 0.7852
- Rewards/margins: 1.1909
- Logps/rejected: -625.0401
- Logps/chosen: -505.8276
- Logits/rejected: -1.6983
- Logits/chosen: -1.7589
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: 4
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.4749 | 0.9984 | 477 | 0.4880 | -2.3992 | -3.5901 | 0.7852 | 1.1909 | -625.0401 | -505.8276 | -1.6983 | -1.7589 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+rocm6.2
- Datasets 3.2.0
- Tokenizers 0.20.3