Downloads · 30 days
3
9% of all-time downloads
model_hh_shp3_dpo9
guoyu-zhang/model_hh_shp3_dpo9
model_hh_shp3_dpo9 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.
should probably proofread and complete it, then remove this comment. --
All-time downloads
32
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
- Access
- Public
- Created
- Apr 16, 2024
- Updated
- Apr 16, 2024
- SHA
- 08574319
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_shp3_dpo9
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: 4.1377
- Rewards/chosen: -9.3962
- Rewards/rejected: -11.2598
- Rewards/accuracies: 0.5800
- Rewards/margins: 1.8636
- Logps/rejected: -245.8684
- Logps/chosen: -228.6076
- Logits/rejected: -0.5115
- Logits/chosen: -0.4911
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.0303 | 2.67 | 100 | 2.0259 | -5.7696 | -7.0838 | 0.5900 | 1.3141 | -241.2283 | -224.5780 | -0.4920 | -0.4631 |
| 0.0777 | 5.33 | 200 | 2.9429 | 4.7991 | 4.3667 | 0.5400 | 0.4324 | -228.5056 | -212.8350 | -0.5965 | -0.6045 |
| 0.0403 | 8.0 | 300 | 3.7747 | -6.4630 | -6.9732 | 0.5200 | 0.5101 | -241.1055 | -225.3485 | -0.4940 | -0.4878 |
| 0.0 | 10.67 | 400 | 4.2141 | -9.5948 | -11.4745 | 0.5900 | 1.8797 | -246.1069 | -228.8282 | -0.5120 | -0.4918 |
| 0.0 | 13.33 | 500 | 4.1730 | -9.3741 | -11.2115 | 0.5900 | 1.8374 | -245.8147 | -228.5830 | -0.5108 | -0.4906 |
| 0.0 | 16.0 | 600 | 4.1578 | -9.3777 | -11.2055 | 0.5800 | 1.8278 | -245.8080 | -228.5870 | -0.5104 | -0.4904 |
| 0.0 | 18.67 | 700 | 4.1186 | -9.3460 | -11.2703 | 0.5900 | 1.9244 | -245.8801 | -228.5517 | -0.5109 | -0.4907 |
| 0.0 | 21.33 | 800 | 4.1078 | -9.3558 | -11.2366 | 0.5800 | 1.8808 | -245.8426 | -228.5626 | -0.5111 | -0.4908 |
| 0.0 | 24.0 | 900 | 4.1290 | -9.3834 | -11.2428 | 0.5800 | 1.8594 | -245.8495 | -228.5933 | -0.5115 | -0.4912 |
| 0.0 | 26.67 | 1000 | 4.1377 | -9.3962 | -11.2598 | 0.5800 | 1.8636 | -245.8684 | -228.6076 | -0.5115 | -0.4911 |
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
- Created
- Apr 16, 2024
- Updated
- Apr 16, 2024