|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: mistralai/Mistral-7B-v0.1 |
|
model-index: |
|
- name: mistral-7B-StaproCoder |
|
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-StaproCoder |
|
|
|
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.9444 |
|
|
|
## 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: 0.0005 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- training_steps: 2000 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.2899 | 0.05 | 100 | 0.2422 | |
|
| 7.7491 | 0.1 | 200 | 6.5822 | |
|
| 5.5972 | 0.15 | 300 | 5.4527 | |
|
| 4.4573 | 0.2 | 400 | 4.4971 | |
|
| 4.7321 | 0.25 | 500 | 4.5034 | |
|
| 4.1145 | 0.3 | 600 | 4.2461 | |
|
| 5.1351 | 0.35 | 700 | 5.2545 | |
|
| 5.1292 | 0.4 | 800 | 4.9499 | |
|
| 5.1284 | 0.45 | 900 | 4.9904 | |
|
| 4.8504 | 0.5 | 1000 | 4.7120 | |
|
| 4.7261 | 0.55 | 1100 | 4.7263 | |
|
| 4.8442 | 0.6 | 1200 | 4.9208 | |
|
| 4.5097 | 0.65 | 1300 | 4.3945 | |
|
| 4.1656 | 0.7 | 1400 | 4.2131 | |
|
| 3.7099 | 0.75 | 1500 | 4.1495 | |
|
| 3.9017 | 0.8 | 1600 | 4.0261 | |
|
| 4.019 | 0.85 | 1700 | 3.9943 | |
|
| 4.0291 | 0.9 | 1800 | 3.9615 | |
|
| 3.876 | 0.95 | 1900 | 3.9494 | |
|
| 3.8402 | 1.0 | 2000 | 3.9444 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.9.0 |
|
- Transformers 4.39.0.dev0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.17.1 |
|
- Tokenizers 0.15.2 |
