Downloads · 30 days
4
27% of all-time downloads
gemma2-9b-4bit-qlora
binh230/gemma2-9b-4bit-qlora
gemma2-9b-4bit-qlora is a machine learning model from binh230. 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 gemma.
should probably proofread and complete it, then remove this comment. --
All-time downloads
15
Public
Repo size
322 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors35.8 MB · 100%
At a glance
- Library
- peft
- License
- gemma
- Access
- Public
- Created
- Sep 27, 2024
- Updated
- Sep 28, 2024
- SHA
- 10c25e74
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. -->
gemma2-9b-4bit-qlora
This model is a fine-tuned version of unsloth/gemma-2-9b-it-bnb-4bit on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.4238
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: 0.0002
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 8.2352 | 0.2036 | 50 | 7.5529 |
| 5.4001 | 0.4072 | 100 | 5.1485 |
| 3.9619 | 0.6108 | 150 | 3.8688 |
| 3.4514 | 0.8144 | 200 | 3.4238 |
Framework versions
- PEFT 0.13.0
- Transformers 4.45.1
- Pytorch 2.1.2
- Datasets 2.19.2
- Tokenizers 0.20.0
- Library
- peft
- License
- gemma
- Created
- Sep 27, 2024
- Updated
- Sep 28, 2024