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: 0.3876
-- Mse: 0.3876
-- Mae: 0.6207
+- Loss: 0.9381
+- Mse: 0.9381
+- Mae: 0.6311
 
 ## Model description
 
@@ -36,22 +36,22 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 3e-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: 778
 - num_epochs: 10
-- mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Mse    | Mae    |
-|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
-| No log        | 1.0   | 5    | 0.3876          | 0.3876 | 0.6207 |
-| No log        | 2.0   | 10   | 0.1101          | 0.1101 | 0.3266 |
-| No log        | 3.0   | 15   | 0.0057          | 0.0057 | 0.0490 |
+| Training Loss | Epoch | Step  | Validation Loss | Mse    | Mae    |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
+| 1.0986        | 1.0   | 7789  | 1.0288          | 1.0288 | 0.6906 |
+| 0.9558        | 2.0   | 15578 | 0.9708          | 0.9708 | 0.6495 |
+| 0.7025        | 3.0   | 23367 | 0.9381          | 0.9381 | 0.6311 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:655ba0641a997191cad86dc7841169e76646d48d57ccb9a5711af412779354b1
+oid sha256:6e19e1ea50d644f0b03846732b062819801262ea852e95c30f85afe38f305692
 size 541314292