Downloads · 30 days
1
8% of all-time downloads
hZzy/mistral-7b-expo-7b-L2EXPO-25-last-try-4
mistral-7b-expo-7b-L2EXPO-25-last-try-4 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
1
8% of all-time downloads
All-time downloads
12
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.5872 | 0.0758 | 50 | 0.5121 | 0.5090 | 0.5162 | 0.4015 | -94.2277 | -94.6291 | -2.1987 |
| 0.6121 | 0.1517 | 100 | 0.5109 | 0.5079 | 0.5168 | 0.5261 | -92.1623 | -92.6884 | -2.1857 |
| 0.6413 | 0.2275 | 150 | 0.5054 | 0.5031 | 0.5288 | 1.2043 | -91.3580 | -92.5622 | -2.1319 |
| 0.5689 | 0.3033 | 200 | 0.4896 | 0.4880 | 0.5677 | 3.9820 | -98.5848 | -102.5667 | -1.9240 |
| 0.5504 | 0.3792 | 250 | 0.4838 | 0.4849 | 0.6023 | 8.4777 | -122.6258 | -131.1036 | -1.8586 |
| 0.537 | 0.4550 | 300 | 0.4760 | 0.4781 | 0.6183 | 11.3080 | -151.3540 | -162.6620 | -1.9671 |
| 0.518 | 0.5308 | 350 | 0.4680 | 0.4723 | 0.6275 | 12.0358 | -170.8389 | -182.8747 | -2.0088 |
| 0.4895 | 0.6067 | 400 | 0.4574 | 0.4573 | 0.6393 | 12.6449 | -131.0898 | -143.7347 | -2.0413 |
| 0.4872 | 0.6825 | 450 | 0.4557 | 0.4561 | 0.6468 | 14.6344 | -138.7488 | -153.3831 | -1.9937 |
| 0.5076 | 0.7583 | 500 | 0.4584 | 0.4586 | 0.6518 | 17.1010 | -154.5612 | -171.6622 | -2.0677 |
| 0.4381 | 0.8342 | 550 | 0.4584 | 0.4599 | 0.6538 | 17.5295 | -162.0710 | -179.6005 | -2.1375 |
| 0.4654 | 0.9100 | 600 | 0.4551 | 0.4575 | 0.6614 | 17.8375 | -183.9476 | -201.7852 | -2.0856 |
| 0.4944 | 0.9858 | 650 | 0.4455 | 0.4447 | 0.6558 | 16.7388 | -158.4220 | -175.1609 | -2.1069 |