|
--- |
|
license: bigcode-openrail-m |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: bigcode/starcoderbase-3b |
|
model-index: |
|
- name: peft-starcoder-lora-a100 |
|
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. --> |
|
|
|
# peft-starcoder-lora-a100 |
|
|
|
This model is a fine-tuned version of [bigcode/starcoderbase-3b](https://huggingface.co/bigcode/starcoderbase-3b) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.8938 |
|
|
|
## 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 |
|
- lr_scheduler_warmup_steps: 30 |
|
- training_steps: 2000 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.2519 | 0.05 | 100 | 1.2670 | |
|
| 1.1574 | 0.1 | 200 | 1.2857 | |
|
| 1.0988 | 0.15 | 300 | 1.3103 | |
|
| 0.9577 | 0.2 | 400 | 1.3922 | |
|
| 0.9345 | 0.25 | 500 | 1.4669 | |
|
| 0.8145 | 0.3 | 600 | 1.5009 | |
|
| 0.7423 | 0.35 | 700 | 1.5764 | |
|
| 0.7225 | 0.4 | 800 | 1.6063 | |
|
| 0.6379 | 0.45 | 900 | 1.6696 | |
|
| 0.6335 | 0.5 | 1000 | 1.7408 | |
|
| 0.5733 | 0.55 | 1100 | 1.7548 | |
|
| 0.5503 | 0.6 | 1200 | 1.7962 | |
|
| 0.5309 | 0.65 | 1300 | 1.7991 | |
|
| 0.4949 | 0.7 | 1400 | 1.8356 | |
|
| 0.4961 | 0.75 | 1500 | 1.8625 | |
|
| 0.4769 | 0.8 | 1600 | 1.8737 | |
|
| 0.4658 | 0.85 | 1700 | 1.8858 | |
|
| 0.4655 | 0.9 | 1800 | 1.8888 | |
|
| 0.4604 | 0.95 | 1900 | 1.8943 | |
|
| 0.4568 | 1.0 | 2000 | 1.8938 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.8.2 |
|
- Transformers 4.39.1 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
