|
--- |
|
license: bigcode-openrail-m |
|
base_model: bigcode/starcoderbase-1b |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: starcoderbase1b-personal-copilot-A100-40GB-colab-1b |
|
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. --> |
|
|
|
# starcoderbase1b-personal-copilot-A100-40GB-colab-1b |
|
|
|
This model is a fine-tuned version of [bigcode/starcoderbase-1b](https://huggingface.co/bigcode/starcoderbase-1b) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8660 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 16 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.6802 | 0.05 | 100 | 2.4316 | |
|
| 1.6009 | 0.1 | 200 | 1.9687 | |
|
| 1.118 | 0.15 | 300 | 1.4213 | |
|
| 0.9805 | 0.2 | 400 | 1.2800 | |
|
| 1.2515 | 0.25 | 500 | 1.2094 | |
|
| 1.1289 | 0.3 | 600 | 1.1665 | |
|
| 1.069 | 0.35 | 700 | 0.9681 | |
|
| 0.8232 | 0.4 | 800 | 0.9157 | |
|
| 0.8186 | 0.45 | 900 | 0.9054 | |
|
| 0.9282 | 0.5 | 1000 | 0.8904 | |
|
| 1.0739 | 0.55 | 1100 | 0.8726 | |
|
| 1.4045 | 0.6 | 1200 | 0.8713 | |
|
| 1.3319 | 0.65 | 1300 | 0.8699 | |
|
| 0.8325 | 0.7 | 1400 | 0.8673 | |
|
| 0.8188 | 0.75 | 1500 | 0.8645 | |
|
| 1.401 | 0.8 | 1600 | 0.8680 | |
|
| 0.7713 | 0.85 | 1700 | 0.8666 | |
|
| 0.9051 | 0.9 | 1800 | 0.8664 | |
|
| 0.8787 | 0.95 | 1900 | 0.8660 | |
|
| 0.8024 | 1.0 | 2000 | 0.8660 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.0.dev0 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
