Downloads · 30 days
12
39% of all-time downloads
gemma-2-2b-it-009
raulgdp/gemma-2-2b-it-009
gemma-2-2b-it-009 is a machine learning model from raulgdp. 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
31
Public
Repo size
756 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.json34.4 MB · 67%
At a glance
- Library
- peft
- License
- gemma
- Access
- Public
- Created
- Apr 16, 2025
- Updated
- Apr 16, 2025
- SHA
- 7ba79736
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-2-2b-it-009
This model is a fine-tuned version of google/gemma-2-2b-it on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5911
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: 2e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.9136 | 0.2694 | 100 | 1.8578 |
| 1.6469 | 0.5387 | 200 | 1.7018 |
| 1.5587 | 0.8081 | 300 | 1.5881 |
| 1.441 | 1.0754 | 400 | 1.4917 |
| 1.3434 | 1.3448 | 500 | 1.4168 |
| 1.3084 | 1.6141 | 600 | 1.3505 |
| 1.3159 | 1.8835 | 700 | 1.2916 |
| 1.2283 | 2.1508 | 800 | 1.2368 |
| 1.1159 | 2.4202 | 900 | 1.1855 |
| 1.0755 | 2.6896 | 1000 | 1.1303 |
| 1.0512 | 2.9589 | 1100 | 1.0780 |
| 1.04 | 3.2263 | 1200 | 1.0311 |
| 0.9028 | 3.4956 | 1300 | 0.9869 |
| 0.9561 | 3.7650 | 1400 | 0.9512 |
| 0.7814 | 4.0323 | 1500 | 0.9062 |
| 0.9104 | 4.3017 | 1600 | 0.8694 |
| 0.7495 | 4.5710 | 1700 | 0.8367 |
| 0.6661 | 4.8404 | 1800 | 0.8088 |
| 0.672 | 5.1077 | 1900 | 0.7803 |
| 0.6734 | 5.3771 | 2000 | 0.7566 |
| 0.6352 | 5.6465 | 2100 | 0.7309 |
| 0.6284 | 5.9158 | 2200 | 0.7213 |
| 0.5652 | 6.1832 | 2300 | 0.6951 |
| 0.5337 | 6.4525 | 2400 | 0.6878 |
| 0.6394 | 6.7219 | 2500 | 0.6675 |
| 0.5346 | 6.9912 | 2600 | 0.6543 |
| 0.4703 | 7.2586 | 2700 | 0.6480 |
| 0.6006 | 7.5279 | 2800 | 0.6389 |
| 0.5572 | 7.7973 | 2900 | 0.6265 |
| 0.5619 | 8.0646 | 3000 | 0.6163 |
| 0.4893 | 8.3340 | 3100 | 0.6114 |
| 0.4357 | 8.6034 | 3200 | 0.6060 |
| 0.4812 | 8.8727 | 3300 | 0.5998 |
| 0.4626 | 9.1401 | 3400 | 0.5989 |
| 0.4952 | 9.4094 | 3500 | 0.5938 |
| 0.3694 | 9.6788 | 3600 | 0.5918 |
| 0.4987 | 9.9481 | 3700 | 0.5911 |
Framework versions
- PEFT 0.15.2
- Transformers 4.51.3
- Pytorch 2.6.0+cu126
- Datasets 3.5.0
- Tokenizers 0.21.1
- Library
- peft
- License
- gemma
- Created
- Apr 16, 2025
- Updated
- Apr 16, 2025