|
--- |
|
license: apache-2.0 |
|
base_model: Deci/DeciCoder-1b |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: peft-lora-DeciCoder1b-personal-copilot-A100-40GB-colab |
|
results: [] |
|
library_name: peft |
|
--- |
|
|
|
<!-- 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-lora-DeciCoder1b-personal-copilot-A100-40GB-colab |
|
|
|
This model is a fine-tuned version of [Deci/DeciCoder-1b](https://huggingface.co/Deci/DeciCoder-1b) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3977 |
|
|
|
## 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 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 32 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.831 | 0.05 | 100 | 0.7074 | |
|
| 0.7092 | 0.1 | 200 | 0.5904 | |
|
| 0.6971 | 0.15 | 300 | 0.5637 | |
|
| 0.8405 | 0.2 | 400 | 0.5363 | |
|
| 0.6548 | 0.25 | 500 | 0.5126 | |
|
| 0.6022 | 0.3 | 600 | 0.4634 | |
|
| 0.6568 | 0.35 | 700 | 0.4529 | |
|
| 0.87 | 0.4 | 800 | 0.4491 | |
|
| 0.4818 | 0.45 | 900 | 0.4438 | |
|
| 0.5067 | 0.5 | 1000 | 0.4117 | |
|
| 0.4578 | 0.55 | 1100 | 0.4044 | |
|
| 0.5909 | 0.6 | 1200 | 0.4041 | |
|
| 0.3646 | 0.65 | 1300 | 0.4027 | |
|
| 0.4597 | 0.7 | 1400 | 0.3963 | |
|
| 0.3385 | 0.75 | 1500 | 0.3935 | |
|
| 0.2696 | 0.8 | 1600 | 0.3955 | |
|
| 0.3011 | 0.85 | 1700 | 0.3966 | |
|
| 0.2931 | 0.9 | 1800 | 0.3980 | |
|
| 0.2904 | 0.95 | 1900 | 0.3978 | |
|
| 0.2669 | 1.0 | 2000 | 0.3977 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.5.0.dev0 |
|
- Transformers 4.32.0.dev0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|
