Model save

README.md

@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [FacebookAI/xlm-roberta-large-finetuned-conll03-german](https://huggingface.co/FacebookAI/xlm-roberta-large-finetuned-conll03-german) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4387
-- Precision: 0.0
-- Recall: 0.0
-- F1: 0.0
-- Accuracy: 0.9150
+- Loss: 0.2261
+- Precision: 0.1857
+- Recall: 0.0872
+- F1: 0.1187
+- Accuracy: 0.9294
 
 ## Model description
 
@@ -49,14 +49,18 @@ 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: 2
+- num_epochs: 5
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1  | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:---:|:--------:|
-| No log        | 1.0   | 4    | 0.5376          | 0.0       | 0.0    | 0.0 | 0.9169   |
-| No log        | 2.0   | 8    | 0.4387          | 0.0       | 0.0    | 0.0 | 0.9150   |
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 0     | 0    | 14.3585         | 0.0       | 0.0    | 0.0    | 0.0109   |
+| No log        | 1.0   | 5    | 0.5506          | 0.0       | 0.0    | 0.0    | 0.9201   |
+| No log        | 2.0   | 10   | 0.3615          | 0.0       | 0.0    | 0.0    | 0.9214   |
+| No log        | 3.0   | 15   | 0.2907          | 0.0286    | 0.0045 | 0.0077 | 0.9249   |
+| No log        | 4.0   | 20   | 0.2449          | 0.2164    | 0.0649 | 0.0998 | 0.9267   |
+| No log        | 5.0   | 25   | 0.2261          | 0.1857    | 0.0872 | 0.1187 | 0.9294   |
 
 
 ### Framework versions