Sebbones
/

bert-finetuned-ner-requirements

Token Classification

Generated from Trainer

Model card Files Files and versions

Metrics Training metrics Community

Sebbones commited on Mar 31, 2025

Commit

d054664

·

verified ·

1 Parent(s): 69e868a

training complete

Files changed (1) hide show

README.md +14 -11

README.md CHANGED Viewed

@@ -19,13 +19,13 @@ should probably proofread and complete it, then remove this comment. -->
 # bert-finetuned-ner-requirements
-This model is a fine-tuned version of [google-bert/bert-base-german-cased](https://huggingface.co/google-bert/bert-base-german-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0192
-- Precision: 0.3933
-- Recall: 0.2071
-- F1: 0.2713
-- Accuracy: 0.7093
 ## Model description
@@ -50,19 +50,22 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 3
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 14   | 1.4775          | 0.0       | 0.0    | 0.0    | 0.5944   |
-| No log        | 2.0   | 28   | 1.1102          | 0.2208    | 0.1006 | 0.1382 | 0.6841   |
-| No log        | 3.0   | 42   | 1.0192          | 0.3933    | 0.2071 | 0.2713 | 0.7093   |
 ### Framework versions
-- Transformers 4.49.0
 - Pytorch 2.6.0+cu124
 - Tokenizers 0.21.1

 # bert-finetuned-ner-requirements
+This model is a fine-tuned version of [google-bert/bert-base-german-cased](https://huggingface.co/google-bert/bert-base-german-cased) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.4528
+- Precision: 0.6724
+- Recall: 0.6842
+- F1: 0.6783
+- Accuracy: 0.875
 ## Model description
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
+- num_epochs: 5
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 38   | 0.6381          | 0.6203    | 0.6082 | 0.6142 | 0.8239   |
+| No log        | 2.0   | 76   | 0.4657          | 0.6718    | 0.6745 | 0.6732 | 0.8678   |
+| No log        | 3.0   | 114  | 0.4412          | 0.6679    | 0.6979 | 0.6826 | 0.8746   |
+| No log        | 4.0   | 152  | 0.4533          | 0.6705    | 0.6745 | 0.6725 | 0.8719   |
+| No log        | 5.0   | 190  | 0.4528          | 0.6724    | 0.6842 | 0.6783 | 0.875    |
 ### Framework versions
+- Transformers 4.50.0
 - Pytorch 2.6.0+cu124
+- Datasets 3.5.0
 - Tokenizers 0.21.1