Downloads · 30 days
4
2% of all-time downloads
peft-lora-starcoderbase7b-personal-copilot-A100-40GB-colab
smangrul/peft-lora-starcoderbase7b-personal-copilot-A100-40GB-colab
peft-lora-starcoderbase7b-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. The card lists the license as bigcode-openrail-m.
should probably proofread and complete it, then remove this comment. --
All-time downloads
217
Public
Repo size
1.2 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin38.8 MB · 100%
At a glance
- Library
- peft
- License
- bigcode-openrail-m
- Access
- Public
- Created
- Aug 9, 2023
- Updated
- Aug 10, 2023
- SHA
- f06e88d1
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-starcoderbase7b-personal-copilot-A100-40GB-colab
This model is a fine-tuned version of bigcode/starcoderbase-7b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4253
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: 0.0002
- 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 |
|---|---|---|---|
| 0.7335 | 0.05 | 100 | 0.6803 |
| 0.7072 | 0.1 | 200 | 0.6197 |
| 0.719 | 0.15 | 300 | 0.5627 |
| 0.6217 | 0.2 | 400 | 0.5389 |
| 0.5415 | 0.25 | 500 | 0.5378 |
| 0.5881 | 0.3 | 600 | 0.5238 |
| 0.5496 | 0.35 | 700 | 0.5092 |
| 0.6226 | 0.4 | 800 | 0.5070 |
| 0.5291 | 0.45 | 900 | 0.5037 |
| 0.612 | 0.5 | 1000 | 0.4923 |
| 0.5752 | 0.55 | 1100 | 0.4780 |
| 0.5921 | 0.6 | 1200 | 0.4620 |
| 0.4729 | 0.65 | 1300 | 0.4635 |
| 0.6316 | 0.7 | 1400 | 0.4600 |
| 0.4738 | 0.75 | 1500 | 0.4574 |
| 0.8665 | 0.8 | 1600 | 0.4555 |
| 0.4805 | 0.85 | 1700 | 0.4509 |
| 0.515 | 0.9 | 1800 | 0.4531 |
| 0.4674 | 0.95 | 1900 | 0.4402 |
| 0.5611 | 1.0 | 2000 | 0.4253 |
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
- Library
- peft
- License
- bigcode-openrail-m
- Created
- Aug 9, 2023
- Updated
- Aug 10, 2023