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: -8.4881
- Rewards/rejected: -8.4881
- Rewards/accuracies: 0.0
- Rewards/margins: 0.0
- Logps/rejected: -164.0651
- Logps/chosen: -164.0651
- Logits/rejected: -3.2224
- Logits/chosen: -3.2224
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: 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
- 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.7723 | 0.29 | 100 | 0.6931 | -2.0247 | -2.0247 | 0.0 | 0.0 | -157.6017 | -157.6017 | -3.1472 | -3.1472 |
| 0.7717 | 0.57 | 200 | 0.6931 | -12.0830 | -12.0830 | 0.0 | 0.0 | -167.6601 | -167.6601 | -3.1635 | -3.1635 |
| 0.782 | 0.86 | 300 | 0.6931 | -8.4881 | -8.4881 | 0.0 | 0.0 | -164.0651 | -164.0651 | -3.2224 | -3.2224 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.2+cu118
- Datasets 2.16.1
- Tokenizers 0.15.2