metadata
license: other
base_model: lewtun/zephyr-7b-gemma-sft
tags:
- trl
- dpo
- generated_from_trainer
model-index:
- name: zephyr-7b-gemma-dpo
results: []
zephyr-7b-gemma-dpo
This model is a fine-tuned version of lewtun/zephyr-7b-gemma-sft on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4736
- Rewards/chosen: -3.4575
- Rewards/rejected: -4.9556
- Rewards/accuracies: 0.75
- Rewards/margins: 1.4980
- Logps/rejected: -459.1662
- Logps/chosen: -431.5707
- Logits/rejected: 86.3863
- Logits/chosen: 92.7360
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.1923 | 1.9 | 100 | 0.4736 | -3.4575 | -4.9556 | 0.75 | 1.4980 | -459.1662 | -431.5707 | 86.3863 | 92.7360 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.1