|
--- |
|
license: apache-2.0 |
|
base_model: TheBloke/OpenHermes-2-Mistral-7B-GPTQ |
|
tags: |
|
- trl |
|
- dpo |
|
- generated_from_trainer |
|
model-index: |
|
- name: mistral-dpo |
|
results: [] |
|
pipeline_tag: conversational |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# mistral-dpo |
|
|
|
This model is a fine-tuned version of [TheBloke/OpenHermes-2-Mistral-7B-GPTQ](https://huggingface.co./TheBloke/OpenHermes-2-Mistral-7B-GPTQ) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0559 |
|
- Rewards/chosen: -0.6622 |
|
- Rewards/rejected: -5.8356 |
|
- Rewards/accuracies: 1.0 |
|
- Rewards/margins: 5.1735 |
|
- Logps/rejected: -138.0126 |
|
- Logps/chosen: -105.3292 |
|
- Logits/rejected: -2.5356 |
|
- Logits/chosen: -2.7185 |
|
|
|
## 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: 0.0002 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 2 |
|
- training_steps: 50 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:| |
|
| 0.6666 | 0.01 | 10 | 0.5490 | 0.3763 | 0.0083 | 1.0 | 0.3680 | -79.5733 | -94.9446 | -2.6386 | -2.7333 | |
|
| 0.439 | 0.01 | 20 | 0.2792 | 1.0686 | -0.2159 | 1.0 | 1.2845 | -81.8148 | -88.0209 | -2.6245 | -2.7868 | |
|
| 0.1683 | 0.02 | 30 | 0.1116 | 1.0530 | -2.2150 | 1.0 | 3.2680 | -101.8059 | -88.1772 | -2.6157 | -2.7924 | |
|
| 0.54 | 0.03 | 40 | 0.0719 | -0.1064 | -4.6952 | 1.0 | 4.5888 | -126.6084 | -99.7713 | -2.5649 | -2.7384 | |
|
| 0.0965 | 0.03 | 50 | 0.0559 | -0.6622 | -5.8356 | 1.0 | 5.1735 | -138.0126 | -105.3292 | -2.5356 | -2.7185 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |