Downloads · 30 days
4
24% of all-time downloads
hZzy/mistral-7b-expo-7b-SimPO-25-last-try-1
mistral-7b-expo-7b-SimPO-25-last-try-1 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
24% of all-time downloads
All-time downloads
17
Public
Repo size
355 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 |
|---|---|---|---|---|---|---|---|---|---|
| 1.2967 | 0.0758 | 50 | 1.4341 | 1.4277 | 0.5338 | 0.0817 | -3.7705 | -3.8522 | -2.1989 |
| 1.3909 | 0.1517 | 100 | 1.4305 | 1.4233 | 0.5310 | 0.0816 | -3.7313 | -3.8129 | -2.2034 |
| 1.4814 | 0.2275 | 150 | 1.4199 | 1.4131 | 0.5338 | 0.0789 | -3.5978 | -3.6767 | -2.2141 |
| 1.2845 | 0.3033 | 200 | 1.4049 | 1.3986 | 0.5327 | 0.0756 | -3.4155 | -3.4911 | -2.2270 |
| 1.3803 | 0.3792 | 250 | 1.3905 | 1.3841 | 0.5364 | 0.0723 | -3.2221 | -3.2944 | -2.2569 |
| 1.3369 | 0.4550 | 300 | 1.3797 | 1.3734 | 0.5336 | 0.0688 | -3.0396 | -3.1084 | -2.3066 |
| 1.3019 | 0.5308 | 350 | 1.3661 | 1.3616 | 0.5369 | 0.0632 | -2.7480 | -2.8112 | -2.4404 |
| 1.2674 | 0.6067 | 400 | 1.3577 | 1.3543 | 0.5456 | 0.0615 | -2.5676 | -2.6291 | -2.5385 |
| 1.3057 | 0.6825 | 450 | 1.3503 | 1.3484 | 0.5428 | 0.0589 | -2.4130 | -2.4719 | -2.5975 |
| 1.331 | 0.7583 | 500 | 1.3440 | 1.3419 | 0.5481 | 0.0585 | -2.3441 | -2.4026 | -2.6489 |
| 1.2792 | 0.8342 | 550 | 1.3431 | 1.3394 | 0.5453 | 0.0645 | -2.5097 | -2.5742 | -2.6329 |
| 1.3204 | 0.9100 | 600 | 1.3381 | 1.3360 | 0.5447 | 0.0602 | -2.3619 | -2.4221 | -2.6238 |
| 1.3144 | 0.9858 | 650 | 1.3351 | 1.3317 | 0.5439 | 0.0679 | -2.5533 | -2.6212 | -2.6126 |