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: 1.1843
- Rewards/chosen: -5.6098
- Rewards/rejected: -5.9639
- Rewards/accuracies: 0.5117
- Rewards/margins: 0.3541
- Logps/rejected: -1114.7808
- Logps/chosen: -951.4574
- Logits/rejected: -7.9900
- Logits/chosen: -7.4446
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.4015 | 0.26 | 100 | 0.9856 | -4.3603 | -4.6945 | 0.5273 | 0.3341 | -987.8358 | -826.5081 | -6.7933 | -6.4109 |
| 0.3649 | 0.53 | 200 | 1.1239 | -4.8760 | -5.1429 | 0.4883 | 0.2669 | -1032.6809 | -878.0756 | -7.6378 | -7.1525 |
| 0.3506 | 0.79 | 300 | 1.1843 | -5.6098 | -5.9639 | 0.5117 | 0.3541 | -1114.7808 | -951.4574 | -7.9900 | -7.4446 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.2+cu118
- Datasets 2.16.1
- Tokenizers 0.15.2