End of training

README.md

@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-multilingual-uncased](https://huggingface.co/bert-base-multilingual-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4196
-- Precision: 0.7180
-- Recall: 0.7032
-- F1: 0.7105
-- Accuracy: 0.8966
+- Loss: 0.3350
+- Precision: 0.7395
+- Recall: 0.7408
+- F1: 0.7401
+- Accuracy: 0.9041
 
 ## Model description
 
@@ -55,14 +55,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 236  | 0.4870          | 0.6425    | 0.5817 | 0.6106 | 0.8591   |
-| No log        | 2.0   | 472  | 0.4357          | 0.6814    | 0.7070 | 0.6939 | 0.8851   |
-| 0.457         | 3.0   | 708  | 0.4196          | 0.7180    | 0.7032 | 0.7105 | 0.8966   |
-| 0.457         | 4.0   | 944  | 0.4559          | 0.7308    | 0.7614 | 0.7458 | 0.9024   |
-| 0.1683        | 5.0   | 1180 | 0.4948          | 0.7497    | 0.7577 | 0.7537 | 0.9043   |
-| 0.1683        | 6.0   | 1416 | 0.5416          | 0.7376    | 0.7426 | 0.7401 | 0.9018   |
-| 0.0715        | 7.0   | 1652 | 0.5537          | 0.7548    | 0.7614 | 0.7581 | 0.9077   |
-| 0.0715        | 8.0   | 1888 | 0.5792          | 0.7580    | 0.7608 | 0.7594 | 0.9079   |
+| No log        | 1.0   | 236  | 0.3641          | 0.6769    | 0.6472 | 0.6617 | 0.8806   |
+| No log        | 2.0   | 472  | 0.3733          | 0.7173    | 0.6741 | 0.6950 | 0.8906   |
+| 0.429         | 3.0   | 708  | 0.3350          | 0.7395    | 0.7408 | 0.7401 | 0.9041   |
+| 0.429         | 4.0   | 944  | 0.4290          | 0.7572    | 0.7279 | 0.7422 | 0.9030   |
+| 0.1313        | 5.0   | 1180 | 0.4485          | 0.7432    | 0.7332 | 0.7381 | 0.9007   |
+| 0.1313        | 6.0   | 1416 | 0.4799          | 0.7785    | 0.7425 | 0.7601 | 0.9100   |
+| 0.0504        | 7.0   | 1652 | 0.5249          | 0.7875    | 0.7461 | 0.7662 | 0.9103   |
+| 0.0504        | 8.0   | 1888 | 0.5146          | 0.7863    | 0.7513 | 0.7684 | 0.9120   |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b549f5ed188e602934b48a2b8aebcdb5580f13761de79bb3a0de3698a549c985
+oid sha256:9a41afefe3b9ddf5ae402968697a3893114d1f921ba41d857e13858a385f9694
 size 667152553