|
|
--- |
|
|
license: apache-2.0 |
|
|
library_name: peft |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
base_model: mistralai/Mistral-7B-Instruct-v0.2 |
|
|
model-index: |
|
|
- name: Mistral-7B-Instruct-v0.2-binary_base02 |
|
|
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. --> |
|
|
|
|
|
# Mistral-7B-Instruct-v0.2-binary_base02 |
|
|
|
|
|
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.2468 |
|
|
|
|
|
## 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: 2 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 4 |
|
|
- total_train_batch_size: 8 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_steps: 5 |
|
|
- training_steps: 1000 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 1.3861 | 0.32 | 50 | 0.5395 | |
|
|
| 0.4528 | 0.63 | 100 | 0.3798 | |
|
|
| 0.3429 | 0.95 | 150 | 0.3177 | |
|
|
| 0.2952 | 1.27 | 200 | 0.3050 | |
|
|
| 0.2816 | 1.59 | 250 | 0.2726 | |
|
|
| 0.2661 | 1.9 | 300 | 0.2615 | |
|
|
| 0.2498 | 2.22 | 350 | 0.2545 | |
|
|
| 0.2439 | 2.54 | 400 | 0.2565 | |
|
|
| 0.2471 | 2.86 | 450 | 0.2504 | |
|
|
| 0.2417 | 3.17 | 500 | 0.2522 | |
|
|
| 0.2372 | 3.49 | 550 | 0.2481 | |
|
|
| 0.2312 | 3.81 | 600 | 0.2429 | |
|
|
| 0.2266 | 4.13 | 650 | 0.2481 | |
|
|
| 0.2179 | 4.44 | 700 | 0.2459 | |
|
|
| 0.2221 | 4.76 | 750 | 0.2409 | |
|
|
| 0.2165 | 5.08 | 800 | 0.2470 | |
|
|
| 0.2064 | 5.4 | 850 | 0.2464 | |
|
|
| 0.2062 | 5.71 | 900 | 0.2448 | |
|
|
| 0.2087 | 6.03 | 950 | 0.2449 | |
|
|
| 0.1975 | 6.35 | 1000 | 0.2468 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.7.2.dev0 |
|
|
- Transformers 4.37.0.dev0 |
|
|
- Pytorch 2.1.0+cu121 |
|
|
- Datasets 2.15.0 |
|
|
- Tokenizers 0.15.0 |
