|
|
--- |
|
|
license: apache-2.0 |
|
|
library_name: peft |
|
|
tags: |
|
|
- trl |
|
|
- sft |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- generator |
|
|
base_model: mistralai/Mixtral-8x7B-v0.1 |
|
|
model-index: |
|
|
- name: mixtral_id |
|
|
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. --> |
|
|
|
|
|
# mixtral_id |
|
|
|
|
|
This model is a fine-tuned version of [mistralai/Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) on the generator dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.7745 |
|
|
|
|
|
## 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: 0.0001 |
|
|
- train_batch_size: 2 |
|
|
- eval_batch_size: 1 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 32 |
|
|
- total_train_batch_size: 64 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: cosine |
|
|
- lr_scheduler_warmup_ratio: 0.03 |
|
|
- training_steps: 230 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 0.9422 | 0.15 | 20 | 0.8942 | |
|
|
| 0.8488 | 0.3 | 40 | 0.8458 | |
|
|
| 0.8208 | 0.46 | 60 | 0.8204 | |
|
|
| 0.7981 | 0.61 | 80 | 0.8045 | |
|
|
| 0.7912 | 0.76 | 100 | 0.7936 | |
|
|
| 0.7789 | 0.91 | 120 | 0.7852 | |
|
|
| 0.7289 | 1.07 | 140 | 0.7810 | |
|
|
| 0.7277 | 1.22 | 160 | 0.7780 | |
|
|
| 0.7112 | 1.37 | 180 | 0.7758 | |
|
|
| 0.7142 | 1.52 | 200 | 0.7747 | |
|
|
| 0.7222 | 1.68 | 220 | 0.7745 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.7.2.dev0 |
|
|
- Transformers 4.38.1 |
|
|
- Pytorch 2.1.2+cu121 |
|
|
- Datasets 2.16.1 |
|
|
- Tokenizers 0.15.0 |
