Downloads · 30 days
4
12% of all-time downloads
buelfhood/irplag_modernbert_ep30_bs16_lr1e-05_l256_s42_ppn_loss
irplag_modernbert_ep30_bs16_lr1e-05_l256_s42_ppn_loss is a text classification model from buelfhood. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
4
12% of all-time downloads
All-time downloads
33
Public
Parameters
150M
598 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors598 MB · 99%
From the Hugging Face model README
This model is a fine-tuned version of answerdotai/ModernBERT-base on an unknown 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 | Accuracy | Recall | Precision | F1 | F Beta Score |
|---|---|---|---|---|---|---|---|---|
| 0.6329 | 1.0 | 21 | 0.5184 | 0.7681 | 0.8 | 0.8980 | 0.8462 | 0.8278 |
| 0.5252 | 2.0 | 42 | 0.4069 | 0.8261 | 0.8 | 0.9778 | 0.88 | 0.8474 |
| 0.298 | 3.0 | 63 | 0.1887 | 0.9565 | 0.9636 | 0.9815 | 0.9725 | 0.9691 |
| 0.1532 | 4.0 | 84 | 0.4532 | 0.9420 | 0.9818 | 0.9474 | 0.9643 | 0.9710 |
| 0.0549 | 5.0 | 105 | 0.0821 | 0.9855 | 0.9818 | 1.0 | 0.9908 | 0.9873 |
| 0.0189 | 6.0 | 126 | 0.0828 | 0.9855 | 1.0 | 0.9821 | 0.9910 | 0.9944 |
| 0.0141 | 7.0 | 147 | 0.0592 | 0.9855 | 1.0 | 0.9821 | 0.9910 | 0.9944 |
| 0.0067 | 8.0 | 168 | 0.0126 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.0005 | 9.0 | 189 | 0.1772 | 0.9710 | 1.0 | 0.9649 | 0.9821 | 0.9889 |
| 0.0013 | 10.0 | 210 | 0.1260 | 0.9855 | 1.0 | 0.9821 | 0.9910 | 0.9944 |
| 0.0001 | 11.0 | 231 | 0.0278 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |