Downloads · 30 days
4
19% of all-time downloads
hZzy/mistral-7b-expo-7b-IPO-25-last-2
mistral-7b-expo-7b-IPO-25-last-2 is a machine learning model from hZzy. 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 apache-2.0.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
4
19% of all-time downloads
All-time downloads
21
Public
Repo size
383 MB
Likes
0
Public
Click a slice to open those files.
.safetensors27.3 MB · 91%
From the Hugging Face model README
This model is a fine-tuned version of hZzy/mistral-7b-sft-25-1 on the hZzy/direction_right2 dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Objective | Reward Accuracy | Logp Accuracy | Log Diff Policy | Chosen Logps | Rejected Logps | Chosen Rewards | Rejected Rewards | Logits |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 9.9121 | 0.0758 | 50 | 9.9242 | 9.9294 | 0.5341 | 0.5165 | 0.4528 | -92.8728 | -93.3256 | 0.0905 | 0.0869 | -2.1996 |
| 9.3992 | 0.1517 | 100 | 9.4864 | 9.4748 | 0.5624 | 0.5263 | 0.9176 | -92.5404 | -93.4580 | 0.1071 | 0.0803 | -2.2025 |
| 9.0399 | 0.2275 | 150 | 8.9895 | 9.0176 | 0.5931 | 0.5336 | 1.5383 | -90.3858 | -91.9241 | 0.2148 | 0.1570 | -2.1726 |
| 8.405 | 0.3033 | 200 | 8.7632 | 8.8299 | 0.6063 | 0.5411 | 1.7736 | -91.3986 | -93.1723 | 0.1642 | 0.0946 | -2.2044 |
| 8.2446 | 0.3792 | 250 | 8.6403 | 8.6946 | 0.6219 | 0.5470 | 1.9981 | -93.0431 | -95.0412 | 0.0820 | 0.0012 | -2.2208 |
| 8.2213 | 0.4550 | 300 | 8.5580 | 8.6390 | 0.6253 | 0.5442 | 2.1972 | -90.1277 | -92.3249 | 0.2277 | 0.1370 | -2.2448 |
| 7.8355 | 0.5308 | 350 | 8.5203 | 8.6120 | 0.6328 | 0.5484 | 2.1774 | -91.5180 | -93.6954 | 0.1582 | 0.0685 | -2.2652 |
| 7.7279 | 0.6067 | 400 | 8.4649 | 8.5792 | 0.6289 | 0.5456 | 2.3509 | -89.3981 | -91.7490 | 0.2642 | 0.1658 | -2.2537 |
| 7.8899 | 0.6825 | 450 | 8.4360 | 8.5768 | 0.6236 | 0.5487 | 2.2685 | -89.6492 | -91.9177 | 0.2517 | 0.1573 | -2.2568 |
| 7.786 | 0.7583 | 500 | 8.4560 | 8.5660 | 0.6314 | 0.5487 | 2.4022 | -89.2403 | -91.6425 | 0.2721 | 0.1711 | -2.2220 |
| 7.7036 | 0.8342 | 550 | 8.4744 | 8.5938 | 0.6317 | 0.5445 | 2.2819 | -90.7238 | -93.0058 | 0.1979 | 0.1029 | -2.2242 |
| 7.635 | 0.9100 | 600 | 8.4219 | 8.5850 | 0.6281 | 0.5428 | 2.2005 | -90.0083 | -92.2089 | 0.2337 | 0.1428 | -2.2122 |
| 8.1482 | 0.9858 | 650 | 8.3734 | 8.4893 | 0.6337 | 0.5475 | 2.4752 | -93.5492 | -96.0243 | 0.0567 | -0.0480 | -2.1782 |