metadata
tags:
- trl
- dpo
- generated_from_trainer
model-index:
- name: zephyr-7b-dpo-full
results: []
zephyr-7b-dpo-full
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6931
- Rewards/chosen: -1.7904
- Rewards/rejected: -1.7904
- Rewards/accuracies: 0.0
- Rewards/margins: 0.0
- Logps/rejected: -157.3674
- Logps/chosen: -157.3674
- Logits/rejected: -3.2202
- Logits/chosen: -3.2202
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-08
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- 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
- 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.3573 | 0.29 | 100 | 0.6931 | -2.2646 | -2.2646 | 0.0 | 0.0 | -157.8416 | -157.8416 | -3.2259 | -3.2259 |
| 0.3184 | 0.57 | 200 | 0.6931 | -1.8023 | -1.8023 | 0.0 | 0.0 | -157.3793 | -157.3793 | -3.2195 | -3.2195 |
| 0.3594 | 0.86 | 300 | 0.6931 | -1.7904 | -1.7904 | 0.0 | 0.0 | -157.3674 | -157.3674 | -3.2202 | -3.2202 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.2+cu118
- Datasets 2.16.1
- Tokenizers 0.15.2