|
--- |
|
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-dpo-qlora-uf-ours-5e-6-epoch1 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# zephyr-dpo-qlora-uf-ours-5e-6-epoch1 |
|
|
|
This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8935 |
|
- Rewards/chosen: -4.8886 |
|
- Rewards/rejected: -5.8224 |
|
- Rewards/accuracies: 0.6470 |
|
- Rewards/margins: 0.9339 |
|
- Rewards/margins Max: 4.5089 |
|
- Rewards/margins Min: -2.8033 |
|
- Rewards/margins Std: 2.4986 |
|
- Logps/rejected: -840.8231 |
|
- Logps/chosen: -773.4503 |
|
- Logits/rejected: -1.3417 |
|
- Logits/chosen: -1.4023 |
|
|
|
## 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 | 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:-------------------:|:-------------------:|:-------------------:|:--------------:|:------------:|:---------------:|:-------------:| |
|
| 0.4419 | 0.28 | 100 | 0.6650 | -0.4529 | -0.5977 | 0.6240 | 0.1449 | 0.8619 | -0.5418 | 0.4692 | -318.3518 | -329.8811 | -2.5449 | -2.5719 | |
|
| 0.1872 | 0.56 | 200 | 0.7859 | -2.8392 | -3.5400 | 0.6630 | 0.7008 | 3.4374 | -2.1827 | 1.9158 | -612.5828 | -568.5178 | -1.4159 | -1.4771 | |
|
| 0.1102 | 0.85 | 300 | 0.8935 | -4.8886 | -5.8224 | 0.6470 | 0.9339 | 4.5089 | -2.8033 | 2.4986 | -840.8231 | -773.4503 | -1.3417 | -1.4023 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.7.1 |
|
- Transformers 4.39.0.dev0 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.15.2 |
