Downloads · 30 days
2
10% of all-time downloads
gemma-2b_alpaca-clean_l0.0002_32-16-16
alexander-hm/gemma-2b_alpaca-clean_l0.0002_32-16-16
gemma-2b_alpaca-clean_l0.0002_32-16-16 is a machine learning model from alexander-hm. 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
20
Public
Repo size
161 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors157 MB · 96%
At a glance
- Library
- peft
- License
- gemma
- Access
- Public
- Created
- Sep 17, 2024
- Updated
- Sep 19, 2024
- SHA
- 2bee6da8
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. -->
gemma-2b_alpaca-clean_l0.0002_32-16-16
This model is a fine-tuned version of google/gemma-2b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.2162
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: 1
- eval_batch_size: 1
- seed: 0
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- training_steps: 10000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.2648 | 0.0003 | 1 | 2.8688 |
| 2.1236 | 0.2050 | 650 | 1.8878 |
| 3.7471 | 0.4100 | 1300 | 1.8395 |
| 2.7991 | 0.6149 | 1950 | 1.8170 |
| 2.9303 | 0.8199 | 2600 | 1.8024 |
| 1.299 | 1.0249 | 3250 | 1.8106 |
| 1.4774 | 1.2299 | 3900 | 1.8264 |
| 1.2606 | 1.4349 | 4550 | 1.8224 |
| 1.2257 | 1.6399 | 5200 | 1.8229 |
| 1.4422 | 1.8448 | 5850 | 1.8196 |
| 0.9775 | 2.0498 | 6500 | 1.9150 |
| 0.9288 | 2.2548 | 7150 | 1.9450 |
| 0.9045 | 2.4598 | 7800 | 1.9524 |
| 0.9699 | 2.6648 | 8450 | 1.9382 |
| 0.8402 | 2.8698 | 9100 | 1.9416 |
| 0.946 | 3.0747 | 9750 | 2.2032 |
Framework versions
- PEFT 0.12.1.dev0
- Transformers 4.45.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Library
- peft
- License
- gemma
- Created
- Sep 17, 2024
- Updated
- Sep 19, 2024