Downloads · 30 days
3
19% of all-time downloads
Kimory-X/zephyr-7b-mypo3_sim-qlora-lr5e6-beta0.70
zephyr-7b-mypo3_sim-qlora-lr5e6-beta0.70 is a machine learning model from Kimory-X. 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
3
19% of all-time downloads
All-time downloads
16
Public
Repo size
11.4 GB
Likes
0
Public
Click a slice to open those files.
.safetensors671 MB · 100%
From the Hugging Face model README
This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-qlora on the HuggingFaceH4/ultrafeedback_binarized 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 | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1.3764 | 0.0654 | 100 | 1.3774 | 0.0018 | -0.0601 | 0.6775 | 0.0619 | -1.1437 | -0.9230 | -2.2073 | -2.2902 |
| 1.3672 | 0.1308 | 200 | 1.3691 | -0.0236 | -0.1501 | 0.6925 | 0.1265 | -1.2723 | -0.9592 | -2.3091 | -2.3781 |
| 1.355 | 0.1963 | 300 | 1.3638 | -0.0446 | -0.2413 | 0.6775 | 0.1967 | -1.4027 | -0.9892 | -2.3215 | -2.3884 |
| 1.3598 | 0.2617 | 400 | 1.3614 | -0.0362 | -0.2836 | 0.7075 | 0.2474 | -1.4631 | -0.9772 | -2.3452 | -2.4120 |
| 1.3578 | 0.3271 | 500 | 1.3598 | -0.0534 | -0.2880 | 0.7075 | 0.2347 | -1.4694 | -1.0018 | -2.3498 | -2.4163 |
| 1.3503 | 0.3925 | 600 | 1.3611 | -0.0642 | -0.3520 | 0.7000 | 0.2879 | -1.5608 | -1.0172 | -2.3142 | -2.3793 |
| 1.3647 | 0.4580 | 700 | 1.3562 | -0.0370 | -0.2972 | 0.7200 | 0.2602 | -1.4825 | -0.9783 | -2.2788 | -2.3504 |
| 1.3583 | 0.5234 | 800 | 1.3569 | -0.0430 | -0.3301 | 0.7125 | 0.2871 | -1.5295 | -0.9870 | -2.2646 | -2.3330 |
| 1.3431 | 0.5888 | 900 | 1.3532 | -0.0367 | -0.3177 | 0.7125 | 0.2810 | -1.5117 | -0.9779 | -2.3085 | -2.3735 |
| 1.3554 | 0.6542 | 1000 | 1.3528 | -0.0452 | -0.3847 | 0.7050 | 0.3395 | -1.6074 | -0.9901 | -2.2896 | -2.3557 |
| 1.3505 | 0.7197 | 1100 | 1.3536 | -0.0479 | -0.4057 | 0.7050 | 0.3578 | -1.6375 | -0.9939 | -2.2824 | -2.3472 |
| 1.354 | 0.7851 | 1200 | 1.3510 | -0.0409 | -0.3778 | 0.7050 | 0.3369 | -1.5976 | -0.9839 | -2.2969 | -2.3598 |
| 1.3537 | 0.8505 | 1300 | 1.3513 | -0.0442 | -0.3877 | 0.7100 | 0.3435 | -1.6117 | -0.9886 | -2.3022 | -2.3646 |
| 1.3564 | 0.9159 | 1400 | 1.3511 | -0.0426 | -0.3833 | 0.7100 | 0.3407 | -1.6054 | -0.9863 | -2.3045 | -2.3667 |
| 1.3508 | 0.9814 | 1500 | 1.3511 | -0.0428 | -0.3834 | 0.7100 | 0.3406 | -1.6056 | -0.9866 | -2.3045 | -2.3667 |