|
--- |
|
license: cc-by-sa-4.0 |
|
library_name: peft |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
base_model: stabilityai/stablelm-3b-4e1t |
|
model-index: |
|
- name: persian-stablelm |
|
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. --> |
|
|
|
# persian-stablelm |
|
|
|
This model is a fine-tuned version of [stabilityai/stablelm-3b-4e1t](https://huggingface.co/stabilityai/stablelm-3b-4e1t) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 4.0159 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- num_epochs: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 4.6872 | 0.09 | 100 | 4.5976 | |
|
| 4.1956 | 0.18 | 200 | 4.4367 | |
|
| 4.3439 | 0.27 | 300 | 4.3083 | |
|
| 4.3709 | 0.36 | 400 | 4.2462 | |
|
| 4.3886 | 0.45 | 500 | 4.1890 | |
|
| 4.402 | 0.54 | 600 | 4.1248 | |
|
| 4.043 | 0.63 | 700 | 4.0840 | |
|
| 4.1489 | 0.72 | 800 | 4.0423 | |
|
| 4.1139 | 0.81 | 900 | 4.0251 | |
|
| 4.273 | 0.9 | 1000 | 4.0162 | |
|
| 3.8663 | 1.0 | 1100 | 4.0159 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.8.2 |
|
- Transformers 4.37.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.1 |
