Downloads · 30 days
5
4% of all-time downloads
leobianco/ragtruth-qa_RM_gemma-4-E4B-it_S130104_epo5_lr6_4e-04_r4_2609182137
ragtruth-qa_RM_gemma-4-E4B-it_S130104_epo5_lr6_4e-04_r4_2609182137 is a machine learning model from leobianco. 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
5
4% of all-time downloads
All-time downloads
141
Public
Repo size
73.6 MB
Likes
0
Public
Click a slice to open those files.
.json64.4 MB · 93%
From the Hugging Face model README
This model is a fine-tuned version of google/gemma-4-E4B-it 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 | Roc Auc | Best Threshold | Tpr At Best Threshold | Fpr At Best Threshold | Accuracy At Best Threshold | Avg Score True Positives | Avg Score True Negatives |
|---|---|---|---|---|---|---|---|---|---|---|
| No log | 0 | 0 | 1.1265 | 0.4817 | 0.6065 | 0.5630 | 0.5238 | 0.5507 | 0.6132 | 0.6164 |
| 1.2441 | 0.2907 | 25 | 0.8026 | 0.7129 | 0.6960 | 0.7598 | 0.4048 | 0.7365 | 0.7787 | 0.6854 |
| 1.1641 | 0.5814 | 50 | 0.7533 | 0.7568 | 0.8041 | 0.6496 | 0.2143 | 0.6689 | 0.8168 | 0.6602 |
| 0.8652 | 0.8721 | 75 | 0.6406 | 0.8598 | 0.8554 | 0.6929 | 0.0952 | 0.7230 | 0.8438 | 0.4596 |
| 0.6211 | 1.1628 | 100 | 1.0809 | 0.8418 | 0.2999 | 0.8898 | 0.3333 | 0.8581 | 0.6745 | 0.2685 |
| 0.3184 | 1.4535 | 125 | 0.5427 | 0.8853 | 0.7617 | 0.8701 | 0.2381 | 0.8547 | 0.8875 | 0.4781 |
| 0.6641 | 1.7442 | 150 | 0.7651 | 0.8910 | 0.7106 | 0.7717 | 0.0952 | 0.7905 | 0.7694 | 0.2762 |
| 0.4375 | 2.0349 | 175 | 0.5149 | 0.9138 | 0.9012 | 0.8740 | 0.1429 | 0.8716 | 0.9354 | 0.5481 |
| 1.0430 | 2.3256 | 200 | 0.6079 | 0.8962 | 0.5340 | 0.9331 | 0.2143 | 0.9122 | 0.8246 | 0.3155 |
| 0.4980 | 2.6163 | 225 | 1.0007 | 0.9085 | 0.2822 | 0.9134 | 0.1905 | 0.8986 | 0.6787 | 0.1711 |
| 1.5059 | 2.9070 | 250 | 0.5949 | 0.9083 | 0.8069 | 0.8346 | 0.1429 | 0.8378 | 0.8686 | 0.2996 |
| 0.3925 | 3.1977 | 275 | 0.4771 | 0.9315 | 0.9191 | 0.8780 | 0.1190 | 0.8784 | 0.9430 | 0.3627 |
| 0.1995 | 3.4884 | 300 | 0.5548 | 0.9246 | 0.7249 | 0.8701 | 0.1190 | 0.8716 | 0.8831 | 0.2419 |
| 0.2988 | 3.7791 | 325 | 0.5728 | 0.9236 | 0.7394 | 0.8780 | 0.1190 | 0.8784 | 0.8816 | 0.2274 |
| 0.1104 | 4.0698 | 350 | 0.6698 | 0.9259 | 0.6361 | 0.8858 | 0.1667 | 0.8784 | 0.8861 | 0.2108 |
| 0.0244 | 4.3605 | 375 | 0.6048 | 0.9227 | 0.9230 | 0.8425 | 0.1190 | 0.8480 | 0.9253 | 0.2864 |
| 0.0290 | 4.6512 | 400 | 0.6434 | 0.9217 | 0.9271 | 0.8425 | 0.1190 | 0.8480 | 0.9225 | 0.2709 |
| 0.0109 | 4.9419 | 425 | 0.6516 | 0.9218 | 0.9236 | 0.8465 | 0.1190 | 0.8514 | 0.9226 | 0.2694 |
| 0.0970 | 5.0 | 430 | 0.6457 | 0.9228 | 0.9176 | 0.8583 | 0.1190 | 0.8615 | 0.9233 | 0.2696 |
| 0.0970 | 5.0 | 430 | 0.6457 | 0.9228 | 0.9176 | 0.8583 | 0.1190 | 0.8615 | 0.9233 | 0.2696 |