Downloads · 30 days
2
7% of all-time downloads
model_hh_shp1_200
guoyu-zhang/model_hh_shp1_200
model_hh_shp1_200 is a machine learning model from guoyu-zhang. 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 llama2.
should probably proofread and complete it, then remove this comment. --
All-time downloads
27
Public
Repo size
12.6 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors25.2 MB · 93%
At a glance
- Library
- peft
- License
- llama2
- Access
- Public
- Created
- Apr 17, 2024
- Updated
- Apr 17, 2024
- SHA
- c9dda5b7
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. -->
model_hh_shp1_200
This model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.7478
- Rewards/chosen: -3.6713
- Rewards/rejected: -4.0977
- Rewards/accuracies: 0.5500
- Rewards/margins: 0.4264
- Logps/rejected: -248.1561
- Logps/chosen: -225.0896
- Logits/rejected: -0.7069
- Logits/chosen: -0.6847
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: 0.0005
- train_batch_size: 4
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.0 | 8.0 | 100 | 2.8294 | -4.0923 | -4.5636 | 0.5600 | 0.4713 | -248.6738 | -225.5573 | -0.7027 | -0.6811 |
| 0.0 | 16.0 | 200 | 2.7777 | -3.9103 | -4.3645 | 0.5500 | 0.4542 | -248.4526 | -225.3551 | -0.7041 | -0.6825 |
| 0.0 | 24.0 | 300 | 2.7958 | -3.8378 | -4.2373 | 0.5500 | 0.3995 | -248.3112 | -225.2746 | -0.7054 | -0.6838 |
| 0.0 | 32.0 | 400 | 2.7755 | -3.7174 | -4.1434 | 0.5600 | 0.4260 | -248.2069 | -225.1407 | -0.7064 | -0.6846 |
| 0.0 | 40.0 | 500 | 2.7768 | -3.7392 | -4.1207 | 0.5400 | 0.3815 | -248.1818 | -225.1650 | -0.7066 | -0.6850 |
| 0.0 | 48.0 | 600 | 2.7826 | -3.7330 | -4.1032 | 0.5400 | 0.3702 | -248.1622 | -225.1581 | -0.7077 | -0.6853 |
| 0.0 | 56.0 | 700 | 2.7522 | -3.6880 | -4.0708 | 0.5400 | 0.3827 | -248.1262 | -225.1082 | -0.7071 | -0.6850 |
| 0.0 | 64.0 | 800 | 2.7751 | -3.6890 | -4.0635 | 0.5500 | 0.3745 | -248.1181 | -225.1093 | -0.7068 | -0.6850 |
| 0.0 | 72.0 | 900 | 2.7706 | -3.6836 | -4.0412 | 0.5500 | 0.3576 | -248.0934 | -225.1032 | -0.7066 | -0.6848 |
| 0.0 | 80.0 | 1000 | 2.7478 | -3.6713 | -4.0977 | 0.5500 | 0.4264 | -248.1561 | -225.0896 | -0.7069 | -0.6847 |
Framework versions
- PEFT 0.10.0
- Transformers 4.39.1
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Library
- peft
- License
- llama2
- Created
- Apr 17, 2024
- Updated
- Apr 17, 2024