Downloads · 30 days
5
17% of all-time downloads
model_shp2_dpo5
guoyu-zhang/model_shp2_dpo5
model_shp2_dpo5 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
30
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
- 6aece1c6
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_shp2_dpo5
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: 2.1695
- Rewards/chosen: -3.4447
- Rewards/rejected: -4.4007
- Rewards/accuracies: 0.5400
- Rewards/margins: 0.9560
- Logps/rejected: -245.2697
- Logps/chosen: -255.8932
- Logits/rejected: -0.8140
- Logits/chosen: -0.7999
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.0371 | 2.67 | 100 | 1.6792 | -0.5920 | -0.6679 | 0.4600 | 0.0759 | -237.8042 | -250.1878 | -0.5568 | -0.5337 |
| 0.0071 | 5.33 | 200 | 1.8321 | 0.5323 | 0.0212 | 0.5500 | 0.5112 | -236.4261 | -247.9392 | -0.7524 | -0.7416 |
| 0.0001 | 8.0 | 300 | 2.1597 | -2.9208 | -3.8736 | 0.5400 | 0.9528 | -244.2156 | -254.8454 | -0.8222 | -0.8092 |
| 0.0 | 10.67 | 400 | 2.1619 | -3.3914 | -4.3596 | 0.5300 | 0.9682 | -245.1877 | -255.7867 | -0.8137 | -0.8004 |
| 0.0 | 13.33 | 500 | 2.1533 | -3.3951 | -4.3755 | 0.5300 | 0.9804 | -245.2194 | -255.7940 | -0.8134 | -0.7998 |
| 0.0 | 16.0 | 600 | 2.1833 | -3.4274 | -4.3755 | 0.5300 | 0.9480 | -245.2194 | -255.8587 | -0.8142 | -0.8001 |
| 0.0 | 18.67 | 700 | 2.1523 | -3.4138 | -4.3824 | 0.5300 | 0.9686 | -245.2332 | -255.8314 | -0.8134 | -0.7991 |
| 0.0 | 21.33 | 800 | 2.1568 | -3.4182 | -4.3819 | 0.5300 | 0.9637 | -245.2321 | -255.8403 | -0.8134 | -0.7993 |
| 0.0 | 24.0 | 900 | 2.1621 | -3.4517 | -4.3884 | 0.5300 | 0.9367 | -245.2452 | -255.9073 | -0.8143 | -0.8002 |
| 0.0 | 26.67 | 1000 | 2.1695 | -3.4447 | -4.4007 | 0.5400 | 0.9560 | -245.2697 | -255.8932 | -0.8140 | -0.7999 |
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