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: 0.4888
-- Mse: 0.4888
-- Mae: 0.6986
+- Loss: 1.8810
+- Mse: 1.8810
+- Mae: 1.0152
 
 ## Model description
 
@@ -36,22 +36,23 @@ 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: 206
 - num_epochs: 10
-- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Mse    | Mae    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
-| No log        | 1.0   | 5    | 0.4888          | 0.4888 | 0.6986 |
-| No log        | 2.0   | 10   | 0.1599          | 0.1599 | 0.3991 |
-| No log        | 3.0   | 15   | 0.0097          | 0.0097 | 0.0912 |
+| 1.9083        | 1.0   | 2062 | 1.8817          | 1.8817 | 1.0139 |
+| 1.937         | 2.0   | 4124 | 1.8821          | 1.8821 | 1.0167 |
+| 1.8841        | 3.0   | 6186 | 1.8812          | 1.8812 | 1.0160 |
+| 1.7777        | 4.0   | 8248 | 1.8810          | 1.8810 | 1.0152 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36f40c5cde8d880eff465a00f51a509b5af912729e0587734e45732ab68dd76d
+oid sha256:2a96178b5d0cb42dd148b3ff49eb39686280d0c701b570002d8a3b3b92136268
 size 541314292