Downloads · 30 days
4
17% of all-time downloads
hZzy/mistral-7b-expo-7b-DPO-25-last-try-2
mistral-7b-expo-7b-DPO-25-last-try-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
17% of all-time downloads
All-time downloads
23
Public
Repo size
383 MB
Likes
0
Public
Click a slice to open those files.
.safetensors27.3 MB · 86%
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 | Logp Accuracy | Log Diff Policy | Chosen Logps | Rejected Logps | Logits |
|---|---|---|---|---|---|---|---|---|---|
| 0.6924 | 0.0758 | 50 | 0.6926 | 0.6924 | 0.5179 | 0.4132 | -94.0690 | -94.4822 | -2.1991 |
| 0.6873 | 0.1517 | 100 | 0.6892 | 0.6893 | 0.5190 | 0.5720 | -92.2414 | -92.8135 | -2.1855 |
| 0.6769 | 0.2275 | 150 | 0.6771 | 0.6781 | 0.5308 | 1.2036 | -91.0515 | -92.2551 | -2.1572 |
| 0.6448 | 0.3033 | 200 | 0.6586 | 0.6621 | 0.5467 | 2.5134 | -90.3653 | -92.8787 | -2.1239 |
| 0.6258 | 0.3792 | 250 | 0.6463 | 0.6559 | 0.5741 | 4.2646 | -101.4486 | -105.7132 | -2.0707 |
| 0.6245 | 0.4550 | 300 | 0.6393 | 0.6473 | 0.5934 | 5.5177 | -97.8431 | -103.3608 | -1.9490 |
| 0.5811 | 0.5308 | 350 | 0.6326 | 0.6453 | 0.6040 | 6.9791 | -107.2356 | -114.2146 | -2.0703 |
| 0.5613 | 0.6067 | 400 | 0.6264 | 0.6408 | 0.6105 | 7.6667 | -99.3648 | -107.0315 | -2.0530 |
| 0.5814 | 0.6825 | 450 | 0.6197 | 0.6365 | 0.6258 | 8.5543 | -113.8419 | -122.3962 | -2.0969 |
| 0.5774 | 0.7583 | 500 | 0.6219 | 0.6364 | 0.6317 | 9.4159 | -104.7100 | -114.1259 | -2.0728 |
| 0.553 | 0.8342 | 550 | 0.6202 | 0.6341 | 0.6306 | 9.5716 | -122.4837 | -132.0553 | -2.0176 |
| 0.5597 | 0.9100 | 600 | 0.6098 | 0.6241 | 0.6379 | 9.8534 | -121.5956 | -131.4490 | -2.0931 |
| 0.5937 | 0.9858 | 650 | 0.6063 | 0.6215 | 0.6365 | 9.7886 | -120.1404 | -129.9290 | -2.0617 |