Downloads · 30 days
3
2% of all-time downloads
adl-hw3-gemma-ch-1
jazzson/adl-hw3-gemma-ch-1
adl-hw3-gemma-ch-1 is a machine learning model from jazzson. 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
156
Public
Repo size
1.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors41.6 MB · 100%
At a glance
- Library
- peft
- License
- gemma
- Access
- Public
- Created
- Nov 7, 2024
- Updated
- Nov 7, 2024
- SHA
- 174b0a52
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. -->
adl-hw3-gemma-ch-1
This model is a fine-tuned version of zake7749/gemma-2-2b-it-chinese-kyara-dpo on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.0069
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: 5e-05
- 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: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.3853 | 0.64 | 200 | 2.1371 |
| 1.9709 | 1.28 | 400 | 2.1690 |
| 1.6145 | 1.92 | 600 | 2.1344 |
| 1.1069 | 2.56 | 800 | 2.4925 |
| 0.849 | 3.2 | 1000 | 3.0008 |
| 0.5224 | 3.84 | 1200 | 3.0069 |
Framework versions
- PEFT 0.13.2
- Transformers 4.45.1
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
- Library
- peft
- License
- gemma
- Created
- Nov 7, 2024
- Updated
- Nov 7, 2024