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: 1.1302
- Rewards/chosen: -1.0433
- Rewards/rejected: -0.6633
- Rewards/accuracies: 0.4102
- Rewards/margins: -0.3800
- Logps/rejected: -531.6535
- Logps/chosen: -411.3397
- Logits/rejected: -4.8567
- Logits/chosen: -4.6242
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: 1e-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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.2472 | 0.26 | 100 | 0.9611 | -0.2112 | 0.1236 | 0.3906 | -0.3347 | -515.9166 | -394.6981 | -4.8019 | -4.5851 |
| 0.2112 | 0.51 | 200 | 1.1025 | -0.7299 | -0.3200 | 0.375 | -0.4098 | -524.7885 | -405.0722 | -4.8388 | -4.6065 |
| 0.195 | 0.77 | 300 | 1.1302 | -1.0433 | -0.6633 | 0.4102 | -0.3800 | -531.6535 | -411.3397 | -4.8567 | -4.6242 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.2+cu118
- Datasets 2.16.1
- Tokenizers 0.15.2