|
|
--- |
|
|
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_Alpace_v2 |
|
|
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_Alpace_v2 |
|
|
|
|
|
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: 1.6342 |
|
|
|
|
|
## 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: 2.5e-05 |
|
|
- train_batch_size: 32 |
|
|
- 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: 0.03 |
|
|
- training_steps: 100 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 1.8073 | 0.05 | 10 | 1.9071 | |
|
|
| 1.7475 | 0.1 | 20 | 1.8399 | |
|
|
| 1.7063 | 0.15 | 30 | 1.7673 | |
|
|
| 1.6365 | 0.2 | 40 | 1.7175 | |
|
|
| 1.6161 | 0.25 | 50 | 1.6894 | |
|
|
| 1.6024 | 0.3 | 60 | 1.6687 | |
|
|
| 1.6022 | 0.35 | 70 | 1.6535 | |
|
|
| 1.5431 | 0.4 | 80 | 1.6428 | |
|
|
| 1.5343 | 0.45 | 90 | 1.6364 | |
|
|
| 1.5398 | 0.5 | 100 | 1.6342 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.7.1 |
|
|
- Transformers 4.36.2 |
|
|
- Pytorch 2.1.2+cu121 |
|
|
- Datasets 2.16.0 |
|
|
- Tokenizers 0.15.0 |
