Downloads · 30 days
2
6% of all-time downloads
Hyponatremia_M2_1000steps_1e6rate_01beta_DPO
tsavage68/Hyponatremia_M2_1000steps_1e6rate_01beta_DPO
Hyponatremia_M2_1000steps_1e6rate_01beta_DPO is a text generation model from tsavage68. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
35
Public
Parameters
7.2B
14.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors29 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- mistral
- Access
- Public
- Created
- Jul 11, 2024
- Updated
- Jul 11, 2024
- SHA
- 4a3d511a
Try a prompt
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. -->
Hyponatremia_M2_1000steps_1e6rate_01beta_DPO
This model is a fine-tuned version of tsavage68/Hyponatremia_M2_150steps_1e6rate_SFT on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0000
- Rewards/chosen: 1.4485
- Rewards/rejected: -14.0474
- Rewards/accuracies: 1.0
- Rewards/margins: 15.4959
- Logps/rejected: -211.3555
- Logps/chosen: -22.2419
- Logits/rejected: -2.0318
- Logits/chosen: -2.0985
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: 1e-06
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- 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 | 0.2667 | 50 | 0.0000 | 0.7277 | -11.0764 | 1.0 | 11.8041 | -181.6457 | -29.4503 | -2.0841 | -2.1392 |
| 0.0 | 0.5333 | 100 | 0.0000 | 0.9330 | -12.3903 | 1.0 | 13.3232 | -194.7840 | -27.3972 | -2.0668 | -2.1273 |
| 0.0 | 0.8 | 150 | 0.0000 | 1.0593 | -12.8919 | 1.0 | 13.9512 | -199.8001 | -26.1336 | -2.0609 | -2.1231 |
| 0.0 | 1.0667 | 200 | 0.0000 | 1.1861 | -13.1433 | 1.0 | 14.3295 | -202.3148 | -24.8656 | -2.0551 | -2.1184 |
| 0.0 | 1.3333 | 250 | 0.0000 | 1.2721 | -13.3214 | 1.0 | 14.5935 | -204.0954 | -24.0062 | -2.0513 | -2.1153 |
| 0.0 | 1.6 | 300 | 0.0000 | 1.3228 | -13.4611 | 1.0 | 14.7839 | -205.4925 | -23.4995 | -2.0479 | -2.1123 |
| 0.0 | 1.8667 | 350 | 0.0000 | 1.3555 | -13.5889 | 1.0 | 14.9444 | -206.7701 | -23.1722 | -2.0441 | -2.1089 |
| 0.0 | 2.1333 | 400 | 0.0000 | 1.3827 | -13.7042 | 1.0 | 15.0869 | -207.9236 | -22.9002 | -2.0409 | -2.1060 |
| 0.0 | 2.4 | 450 | 0.0000 | 1.4065 | -13.7799 | 1.0 | 15.1865 | -208.6808 | -22.6618 | -2.0375 | -2.1029 |
| 0.0 | 2.6667 | 500 | 0.0000 | 1.4212 | -13.8531 | 1.0 | 15.2744 | -209.4129 | -22.5149 | -2.0370 | -2.1026 |
| 0.0 | 2.9333 | 550 | 0.0000 | 1.4265 | -13.9342 | 1.0 | 15.3607 | -210.2232 | -22.4618 | -2.0357 | -2.1020 |
| 0.0 | 3.2 | 600 | 0.0000 | 1.4339 | -13.9717 | 1.0 | 15.4056 | -210.5986 | -22.3882 | -2.0342 | -2.1005 |
| 0.0 | 3.4667 | 650 | 0.0000 | 1.4406 | -14.0006 | 1.0 | 15.4412 | -210.8875 | -22.3212 | -2.0335 | -2.1000 |
| 0.0 | 3.7333 | 700 | 0.0000 | 1.4439 | -14.0232 | 1.0 | 15.4671 | -211.1137 | -22.2885 | -2.0321 | -2.0987 |
| 0.0 | 4.0 | 750 | 0.0000 | 1.4465 | -14.0340 | 1.0 | 15.4805 | -211.2219 | -22.2624 | -2.0325 | -2.0990 |
| 0.0 | 4.2667 | 800 | 0.0000 | 1.4483 | -14.0415 | 1.0 | 15.4898 | -211.2962 | -22.2436 | -2.0324 | -2.0990 |
| 0.0 | 4.5333 | 850 | 0.0000 | 1.4487 | -14.0425 | 1.0 | 15.4913 | -211.3066 | -22.2396 | -2.0324 | -2.0991 |
| 0.0 | 4.8 | 900 | 0.0000 | 1.4483 | -14.0489 | 1.0 | 15.4971 | -211.3702 | -22.2444 | -2.0318 | -2.0984 |
| 0.0 | 5.0667 | 950 | 0.0000 | 1.4485 | -14.0474 | 1.0 | 15.4959 | -211.3555 | -22.2419 | -2.0318 | -2.0985 |
| 0.0 | 5.3333 | 1000 | 0.0000 | 1.4485 | -14.0474 | 1.0 | 15.4959 | -211.3555 | -22.2419 | -2.0318 | -2.0985 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.0.0+cu117
- Datasets 2.20.0
- Tokenizers 0.19.1
- Task
- Text Generation
- Library
- transformers
- Type
- mistral
- License
- apache-2.0
- Created
- Jul 11, 2024
- Updated
- Jul 11, 2024