Model save

README.md

@@ -15,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert/distilbert-base-multilingual-cased](https://huggingface.co/distilbert/distilbert-base-multilingual-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.7173
-- Mse: 1.7173
-- Mae: 0.9613
+- Loss: 0.0055
+- Mse: 0.0055
+- Mae: 0.0471
 
 ## Model description
 
@@ -36,27 +36,22 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
+- learning_rate: 1e-05
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 500
 - num_epochs: 10
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step   | Validation Loss | Mse    | Mae    |
-|:-------------:|:-----:|:------:|:---------------:|:------:|:------:|
-| 1.815         | 1.0   | 21755  | 1.7168          | 1.7168 | 0.9622 |
-| 1.6414        | 2.0   | 43510  | 1.7167          | 1.7167 | 0.9620 |
-| 1.6485        | 3.0   | 65265  | 1.7171          | 1.7171 | 0.9614 |
-| 1.7803        | 4.0   | 87020  | 1.7168          | 1.7168 | 0.9619 |
-| 1.6427        | 5.0   | 108775 | 1.7173          | 1.7173 | 0.9613 |
-| 1.6436        | 6.0   | 130530 | 1.7170          | 1.7170 | 0.9615 |
-| 1.7037        | 7.0   | 152285 | 1.7168          | 1.7168 | 0.9618 |
+| Training Loss | Epoch | Step | Validation Loss | Mse    | Mae    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
+| No log        | 1.0   | 5    | 0.4268          | 0.4268 | 0.6531 |
+| No log        | 2.0   | 10   | 0.1314          | 0.1314 | 0.3619 |
+| No log        | 3.0   | 15   | 0.0055          | 0.0055 | 0.0471 |
 
 
 ### Framework versions