Downloads · 30 days
7
2% of all-time downloads
peft-lora-starcoderplus-personal-copilot-A100-40GB-colab
smangrul/peft-lora-starcoderplus-personal-copilot-A100-40GB-colab
peft-lora-starcoderplus-personal-copilot-A100-40GB-colab is a machine learning model from smangrul. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.
should probably proofread and complete it, then remove this comment. --
All-time downloads
285
Public
Repo size
1.3 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin111 MB · 100%
At a glance
- Library
- peft
- Access
- Public
- Created
- Jul 27, 2023
- Updated
- Jul 28, 2023
- SHA
- a6858e87
Base models
Model card
From the Hugging Face model README
<!-- 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-starcoderplus-personal-copilot-A100-40GB-colab
This model is a fine-tuned version of bigcode/starcoderplus on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3721
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
The following bitsandbytes quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
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: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 30
- training_steps: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7246 | 0.05 | 100 | 0.6648 |
| 0.6761 | 0.1 | 200 | 0.5792 |
| 0.6986 | 0.15 | 300 | 0.5136 |
| 0.6049 | 0.2 | 400 | 0.4961 |
| 0.53 | 0.25 | 500 | 0.4986 |
| 0.547 | 0.3 | 600 | 0.4855 |
| 0.5186 | 0.35 | 700 | 0.4629 |
| 0.5968 | 0.4 | 800 | 0.4636 |
| 0.5191 | 0.45 | 900 | 0.4640 |
| 0.584 | 0.5 | 1000 | 0.4506 |
| 0.5361 | 0.55 | 1100 | 0.4331 |
| 0.5631 | 0.6 | 1200 | 0.4163 |
| 0.4581 | 0.65 | 1300 | 0.4133 |
| 0.5485 | 0.7 | 1400 | 0.4089 |
| 0.4328 | 0.75 | 1500 | 0.4094 |
| 0.7456 | 0.8 | 1600 | 0.4098 |
| 0.4398 | 0.85 | 1700 | 0.4062 |
| 0.475 | 0.9 | 1800 | 0.4103 |
| 0.4045 | 0.95 | 1900 | 0.3991 |
| 0.5191 | 1.0 | 2000 | 0.3721 |
Framework versions
- PEFT 0.5.0.dev0
- Transformers 4.32.0.dev0
- Pytorch 2.1.0.dev20230725+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
- Library
- peft
- Created
- Jul 27, 2023
- Updated
- Jul 28, 2023