Downloads · 30 days
2
7% of all-time downloads
model_shp3_dpo9
guoyu-zhang/model_shp3_dpo9
model_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
29
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 17, 2024
- Updated
- Apr 17, 2024
- SHA
- 5a63bae6
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_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: 3.4927
- Rewards/chosen: -8.7213
- Rewards/rejected: -10.8984
- Rewards/accuracies: 0.6200
- Rewards/margins: 2.1771
- Logps/rejected: -266.2351
- Logps/chosen: -246.7773
- Logits/rejected: -0.7193
- Logits/chosen: -0.7036
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.0555 | 2.67 | 100 | 2.5620 | -16.4770 | -17.3996 | 0.5300 | 0.9226 | -273.4587 | -255.3948 | -0.7097 | -0.7042 |
| 0.0052 | 5.33 | 200 | 3.5005 | -15.7277 | -18.5215 | 0.6300 | 2.7938 | -274.7052 | -254.5623 | -0.7073 | -0.6907 |
| 0.0436 | 8.0 | 300 | 2.7714 | -10.1931 | -12.9259 | 0.6100 | 2.7328 | -268.4880 | -248.4127 | -0.9618 | -0.9474 |
| 0.0 | 10.67 | 400 | 3.6414 | -11.7426 | -14.1647 | 0.6000 | 2.4221 | -269.8643 | -250.1343 | -0.7324 | -0.7187 |
| 0.0 | 13.33 | 500 | 3.4708 | -8.6874 | -10.8958 | 0.6300 | 2.2084 | -266.2322 | -246.7397 | -0.7190 | -0.7028 |
| 0.0 | 16.0 | 600 | 3.5011 | -8.7071 | -10.8590 | 0.6300 | 2.1519 | -266.1913 | -246.7616 | -0.7194 | -0.7036 |
| 0.0 | 18.67 | 700 | 3.4789 | -8.7021 | -10.8992 | 0.6400 | 2.1971 | -266.2360 | -246.7560 | -0.7192 | -0.7036 |
| 0.0 | 21.33 | 800 | 3.5146 | -8.6829 | -10.8473 | 0.6300 | 2.1644 | -266.1783 | -246.7346 | -0.7194 | -0.7034 |
| 0.0 | 24.0 | 900 | 3.4567 | -8.6690 | -10.9074 | 0.6300 | 2.2384 | -266.2451 | -246.7193 | -0.7194 | -0.7036 |
| 0.0 | 26.67 | 1000 | 3.4927 | -8.7213 | -10.8984 | 0.6200 | 2.1771 | -266.2351 | -246.7773 | -0.7193 | -0.7036 |
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 17, 2024
- Updated
- Apr 17, 2024