Downloads · 30 days
2
1% of all-time downloads
NastasiaM/mbert-loraxs-qa-LTr64-qkvd-iscale-0.7-gain1.2-A-norm
mbert-loraxs-qa-LTr64-qkvd-iscale-0.7-gain1.2-A-norm is a machine learning model from NastasiaM. 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
2
1% of all-time downloads
All-time downloads
180
Public
Repo size
699 MB
Likes
0
Public
Click a slice to open those files.
.safetensors43.7 MB · 94%
From the Hugging Face model README
This model is a fine-tuned version of bert-base-multilingual-cased on the None 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 | Exact Match | F1 |
|---|---|---|---|---|---|
| 2.4228 | 0.2818 | 2500 | 2.1270 | 38.8883 | 52.5500 |
| 1.6616 | 0.5636 | 5000 | 1.4774 | 55.3014 | 69.3763 |
| 1.4681 | 0.8455 | 7500 | 1.3950 | 57.3259 | 72.3313 |
| 1.3595 | 1.1273 | 10000 | 1.3410 | 59.7278 | 73.9674 |
| 1.3782 | 1.4091 | 12500 | 1.2437 | 60.2997 | 74.3828 |
| 1.3025 | 1.6909 | 15000 | 1.2301 | 61.2833 | 75.4122 |
| 1.2383 | 1.9727 | 17500 | 1.2200 | 62.1526 | 76.3566 |
| 1.1704 | 2.2545 | 20000 | 1.1993 | 62.4042 | 76.6643 |
| 1.2248 | 2.5364 | 22500 | 1.1663 | 62.5186 | 76.8061 |
| 1.2025 | 2.8182 | 25000 | 1.1687 | 63.0562 | 77.1522 |
| 1.0719 | 3.1000 | 27500 | 1.1916 | 63.2163 | 77.4445 |
| 1.1436 | 3.3818 | 30000 | 1.1340 | 63.5251 | 77.6837 |
| 1.1182 | 3.6636 | 32500 | 1.1377 | 63.7195 | 78.0391 |
| 1.1468 | 3.9454 | 35000 | 1.1263 | 63.7081 | 77.9738 |
| 1.1468 | 4.0 | 35484 | 1.1275 | 63.7310 | 77.9541 |