zephyr-7b-UC-0-B0.5
This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-full on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1130
- Rewards/chosen: -3.7732
- Rewards/rejected: -13.4408
- Rewards/accuracies: 0.8644
- Rewards/margins: 9.6676
- Logps/rejected: -173.6967
- Logps/chosen: -189.7024
- Logits/rejected: -2.8645
- Logits/chosen: -2.9068
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: 4
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 16
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.1262 | 0.62 | 500 | 0.1185 | -3.0114 | -12.1820 | 0.8670 | 9.1707 | -171.1792 | -188.1787 | -2.8565 | -2.9004 |
Framework versions
- Transformers 4.36.1
- Pytorch 2.0.1+cu117
- Datasets 2.16.1
- Tokenizers 0.15.0