metadata
base_model: alignment-handbook/zephyr-7b-sft-full
library_name: peft
license: apache-2.0
tags:
- trl
- dpo
- generated_from_trainer
model-index:
- name: zephyr-dpop-qlora-uf6k-5e-6
results: []
zephyr-dpop-qlora-uf6k-5e-6
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: 0.6879
- Positive Losses: 0.0941
- Dpo Losses: 0.6679
- Rewards/chosen: 0.1483
- Rewards/rejected: 0.0942
- Rewards/accuracies: 0.6900
- Rewards/margins: 0.0541
- Rewards/margins Max: 0.2146
- Rewards/margins Min: -0.0945
- Rewards/margins Std: 0.1028
- Logps/rejected: -249.1596
- Logps/chosen: -269.7678
- Logits/rejected: -2.7464
- Logits/chosen: -2.7837
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-06
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- total_eval_batch_size: 16
- 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 | Positive Losses | Dpo Losses | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Rewards/margins Max | Rewards/margins Min | Rewards/margins Std | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.6896 | 0.3 | 100 | 0.6927 | 0.0589 | 0.6767 | 0.1278 | 0.0930 | 0.6710 | 0.0348 | 0.1572 | -0.0767 | 0.0771 | -249.2807 | -271.8154 | -2.7452 | -2.7829 |
| 0.6919 | 0.61 | 200 | 0.6864 | 0.0952 | 0.6689 | 0.1438 | 0.0918 | 0.6830 | 0.0521 | 0.2115 | -0.0943 | 0.1012 | -249.3993 | -270.2086 | -2.7481 | -2.7856 |
| 0.6774 | 0.91 | 300 | 0.6879 | 0.0941 | 0.6679 | 0.1483 | 0.0942 | 0.6900 | 0.0541 | 0.2146 | -0.0945 | 0.1028 | -249.1596 | -269.7678 | -2.7464 | -2.7837 |
Framework versions
- PEFT 0.7.1
- Transformers 4.39.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2