Downloads · 30 days
5
15% of all-time downloads
RM-HH-Mix_harmless_gpt3_20000_gemma2b_shuffleTrue_extractchosenTrue
Holarissun/RM-HH-Mix_harmless_gpt3_20000_gemma2b_shuffleTrue_extractchosenTrue
RM-HH-Mix_harmless_gpt3_20000_gemma2b_shuffleTrue_extractchosenTrue is a machine learning model from Holarissun. 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
34
Public
Repo size
29.1 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.json17.6 MB · 60%
At a glance
- Library
- peft
- License
- gemma
- Access
- Public
- Created
- Apr 20, 2024
- Updated
- Apr 20, 2024
- SHA
- 90ed0538
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. -->
RM-HH-Mix_harmless_gpt3_20000_gemma2b_shuffleTrue_extractchosenTrue
This model is a fine-tuned version of google/gemma-2b on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5008
- Accuracy: 0.73
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: 1.41e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7309 | 0.06 | 250 | 0.6808 | 0.5865 |
| 0.6572 | 0.11 | 500 | 0.6149 | 0.6515 |
| 0.6119 | 0.17 | 750 | 0.5805 | 0.672 |
| 0.5447 | 0.22 | 1000 | 0.5620 | 0.6825 |
| 0.5644 | 0.28 | 1250 | 0.5506 | 0.694 |
| 0.5249 | 0.33 | 1500 | 0.5417 | 0.6955 |
| 0.5416 | 0.39 | 1750 | 0.5322 | 0.698 |
| 0.5139 | 0.44 | 2000 | 0.5287 | 0.706 |
| 0.5134 | 0.5 | 2250 | 0.5223 | 0.707 |
| 0.5349 | 0.56 | 2500 | 0.5152 | 0.712 |
| 0.4918 | 0.61 | 2750 | 0.5168 | 0.718 |
| 0.5008 | 0.67 | 3000 | 0.5158 | 0.724 |
| 0.5101 | 0.72 | 3250 | 0.5135 | 0.7265 |
| 0.4968 | 0.78 | 3500 | 0.5080 | 0.7275 |
| 0.5325 | 0.83 | 3750 | 0.5039 | 0.7285 |
| 0.529 | 0.89 | 4000 | 0.5006 | 0.7285 |
| 0.4696 | 0.94 | 4250 | 0.5008 | 0.73 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2
- Library
- peft
- License
- gemma
- Created
- Apr 20, 2024
- Updated
- Apr 20, 2024