drcoool
/

category-classifier

Text Classification

Generated from Trainer

text-embeddings-inference

Model card Files Files and versions

Metrics Training metrics Community

drcoool commited on May 10, 2025

Commit

c1eaecc

·

verified ·

1 Parent(s): 6c784cb

End of training

Files changed (2) hide show

README.md +11 -11
model.safetensors +1 -1

README.md CHANGED Viewed

@@ -19,14 +19,14 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.6405
-- F1: 0.7106
-- Accuracy: 0.7150
-- F1 Ai: 0.6377
-- F1 Programming: 0.6682
-- F1 Science & engineering: 0.6115
-- F1 Tech: 0.4547
-- F1 Rejected: 0.8019
 ## Model description
@@ -57,9 +57,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | F1     | Accuracy | F1 Ai  | F1 Programming | F1 Science & engineering | F1 Tech | F1 Rejected |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|:------:|:--------------:|:------------------------:|:-------:|:-----------:|
-| 0.591         | 1.0   | 849  | 0.7085          | 0.6909 | 0.7084   | 0.6614 | 0.6502         | 0.6271                   | 0.2727  | 0.8018      |
-| 0.3318        | 2.0   | 1698 | 0.7817          | 0.7086 | 0.7160   | 0.6337 | 0.6359         | 0.6104                   | 0.45    | 0.8060      |
-| 0.1606        | 3.0   | 2547 | 1.6405          | 0.7106 | 0.7150   | 0.6377 | 0.6682         | 0.6115                   | 0.4547  | 0.8019      |
 ### Framework versions

 This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 1.7933
+- F1: 0.7172
+- Accuracy: 0.7212
+- F1 Ai: 0.6154
+- F1 Programming: 0.6715
+- F1 Science & engineering: 0.6393
+- F1 Tech: 0.4259
+- F1 Rejected: 0.8158
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | F1     | Accuracy | F1 Ai  | F1 Programming | F1 Science & engineering | F1 Tech | F1 Rejected |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|:------:|:--------------:|:------------------------:|:-------:|:-----------:|
+| 0.587         | 1.0   | 1881 | 0.6882          | 0.7150 | 0.7167   | 0.6565 | 0.6787         | 0.6900                   | 0.4046  | 0.7984      |
+| 0.3324        | 2.0   | 3762 | 0.7463          | 0.7237 | 0.7293   | 0.6492 | 0.6987         | 0.6517                   | 0.4044  | 0.8179      |
+| 0.1291        | 3.0   | 5643 | 1.7933          | 0.7172 | 0.7212   | 0.6154 | 0.6715         | 0.6393                   | 0.4259  | 0.8158      |
 ### Framework versions

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcd4c0fb473d8002767680800c0fb6c67cefffbff9fc11dd5e25ccbeb1df3c98
 size 598449012

 version https://git-lfs.github.com/spec/v1
+oid sha256:ae3f25050988371beae67b58e3252b7952ba040a3e867ffe8901a13fbfa50649
 size 598449012