|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
base_model: mistralai/Mistral-7B-v0.3 |
|
datasets: |
|
- HachiML/oasst1_for_self-rewarding_IFT |
|
- HachiML/oasst1_for_self-rewarding_EFT_MSv0.3 |
|
--- |
|
|
|
# Model Card for Model ID |
|
|
|
<!-- Provide a quick summary of what the model is/does. --> |
|
|
|
- [HachiML/Mistral-7B-v0.3-sft-lora_sr_5ep](https://huggingface.co/HachiML/Mistral-7B-v0.3-sft-lora_sr_5ep)のAdapterをマージしたモデル |
|
- This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on following datasets. |
|
- [HachiML/oasst1_for_self-rewarding_IFT](https://huggingface.co/datasets/HachiML/oasst1_for_self-rewarding_IFT) |
|
- [HachiML/oasst1_for_self-rewarding_EFT_MSv0.3](https://huggingface.co/datasets/HachiML/oasst1_for_self-rewarding_EFT_MSv0.3) |
|
- It achieves the following results on the evaluation set: |
|
- Loss: 0.4237 |
|
|
|
## Model Details |
|
|
|
### Model Description |
|
|
|
<!-- Provide a longer summary of what this model is. --> |
|
|
|
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. |
|
|
|
- **Developed by:** [HachiML](https://huggingface.co/HachiML) |
|
- **Model type:** Mistral-7B |
|
- **Language(s) (NLP):** Japanese |
|
- **License:** Apache-2.0 |
|
- **Finetuned from model:** [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) |
|
- **Finetuned type:** SFT |
|
- **Finetuned dataset:** |
|
- [HachiML/oasst1_for_self-rewarding_IFT](https://huggingface.co/datasets/HachiML/oasst1_for_self-rewarding_IFT) |
|
- [HachiML/oasst1_for_self-rewarding_EFT_MSv0.3](https://huggingface.co/datasets/HachiML/oasst1_for_self-rewarding_EFT_MSv0.3) |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 5.5e-06 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.05 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.1951 | 1.0 | 262 | 0.4563 | |
|
| 0.9304 | 2.0 | 524 | 0.4279 | |
|
| 0.9129 | 3.0 | 786 | 0.4242 | |
|
| 0.9088 | 4.0 | 1048 | 0.4237 | |
|
| 0.9089 | 5.0 | 1310 | 0.4237 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.11.1 |
|
- Transformers 4.41.1 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |