metadata
license: mit
base_model: HuggingFaceH4/mistral-7b-sft-beta
tags:
- trl
- dpo
- generated_from_trainer
model-index:
- name: zephyr-7b-dpo-full
results: []
zephyr-7b-dpo-full
This model is a fine-tuned version of HuggingFaceH4/mistral-7b-sft-beta on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0229
- Rewards/chosen: -1.4736
- Rewards/rejected: -2.2201
- Rewards/accuracies: 0.7148
- Rewards/margins: 0.7465
- Logps/rejected: -479.3624
- Logps/chosen: -404.4032
- Logits/rejected: -2.3938
- Logits/chosen: -2.4072
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: 8
- eval_batch_size: 8
- seed: 4
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.0486 | 0.21 | 100 | 0.0431 | -0.6721 | -1.0349 | 0.6875 | 0.3629 | -360.8449 | -324.2452 | -2.7173 | -2.7326 |
| 0.027 | 0.42 | 200 | 0.0297 | -1.0958 | -1.6844 | 0.6953 | 0.5886 | -425.7964 | -366.6208 | -2.4958 | -2.5091 |
| 0.0267 | 0.63 | 300 | 0.0287 | -1.1018 | -1.7154 | 0.7344 | 0.6136 | -428.8893 | -367.2200 | -2.4587 | -2.4719 |
| 0.0208 | 0.84 | 400 | 0.0229 | -1.4736 | -2.2201 | 0.7148 | 0.7465 | -479.3624 | -404.4032 | -2.3938 | -2.4072 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1