Model save

README.md

@@ -1,7 +1,5 @@
 ---
 library_name: transformers
-license: mit
-base_model: camembert-base
 tags:
 - generated_from_trainer
 model-index:
@@ -14,12 +12,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # camembert-secabilite-regressor
 
-This model is a fine-tuned version of [camembert-base](https://huggingface.co/camembert-base) on an unknown dataset.
+This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0152
-- Model Preparation Time: 0.0011
-- Mse: 0.0152
-- Mae: 0.0825
+- Loss: 0.0135
+- Model Preparation Time: 0.0012
+- Mse: 0.0136
+- Mae: 0.0659
 
 ## Model description
 
@@ -52,11 +50,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Mse    | Mae    |
 |:-------------:|:-----:|:----:|:---------------:|:----------------------:|:------:|:------:|
-| 0.0235        | 1.0   | 108  | 0.0188          | 0.0011                 | 0.0188 | 0.1019 |
-| 0.0192        | 2.0   | 216  | 0.0167          | 0.0011                 | 0.0167 | 0.0905 |
-| 0.0171        | 3.0   | 324  | 0.0159          | 0.0011                 | 0.0160 | 0.0864 |
-| 0.0163        | 4.0   | 432  | 0.0154          | 0.0011                 | 0.0154 | 0.0838 |
-| 0.0161        | 5.0   | 540  | 0.0152          | 0.0011                 | 0.0152 | 0.0825 |
+| 0.0144        | 1.0   | 108  | 0.0146          | 0.0012                 | 0.0147 | 0.0752 |
+| 0.0133        | 2.0   | 216  | 0.0141          | 0.0012                 | 0.0141 | 0.0705 |
+| 0.0122        | 3.0   | 324  | 0.0138          | 0.0012                 | 0.0138 | 0.0679 |
+| 0.0119        | 4.0   | 432  | 0.0137          | 0.0012                 | 0.0138 | 0.0670 |
+| 0.0119        | 5.0   | 540  | 0.0135          | 0.0012                 | 0.0136 | 0.0659 |
 
 
 ### Framework versions