Ilya-Nazimov
/

rubert-tiny2-odonata-extended-ner

@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [cointegrated/rubert-tiny2](https://huggingface.co/cointegrated/rubert-tiny2) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0226
-- Precision: 0.5313
-- Recall: 0.551
-- F1: 0.5410
-- Accuracy: 0.9930
 ## Model description
@@ -55,21 +55,21 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 32   | 0.1425          | 0.0       | 0.0    | 0.0    | 0.9910   |
-| No log        | 2.0   | 64   | 0.0643          | 0.0       | 0.0    | 0.0    | 0.9910   |
-| No log        | 3.0   | 96   | 0.0604          | 0.0       | 0.0    | 0.0    | 0.9910   |
-| No log        | 4.0   | 128  | 0.0575          | 0.0       | 0.0    | 0.0    | 0.9910   |
-| No log        | 5.0   | 160  | 0.0523          | 0.0       | 0.0    | 0.0    | 0.9910   |
-| No log        | 6.0   | 192  | 0.0427          | 0.0       | 0.0    | 0.0    | 0.9910   |
-| No log        | 7.0   | 224  | 0.0330          | 0.7753    | 0.069  | 0.1267 | 0.9913   |
-| No log        | 8.0   | 256  | 0.0288          | 0.6309    | 0.376  | 0.4712 | 0.9921   |
-| No log        | 9.0   | 288  | 0.0264          | 0.6145    | 0.373  | 0.4642 | 0.9924   |
-| No log        | 10.0  | 320  | 0.0251          | 0.5489    | 0.432  | 0.4835 | 0.9926   |
-| No log        | 11.0  | 352  | 0.0242          | 0.5354    | 0.484  | 0.5084 | 0.9927   |
-| No log        | 12.0  | 384  | 0.0235          | 0.5393    | 0.515  | 0.5269 | 0.9928   |
-| No log        | 13.0  | 416  | 0.0230          | 0.5310    | 0.54   | 0.5354 | 0.9929   |
-| No log        | 14.0  | 448  | 0.0228          | 0.5287    | 0.553  | 0.5406 | 0.9930   |
-| No log        | 15.0  | 480  | 0.0226          | 0.5313    | 0.551  | 0.5410 | 0.9930   |
 ### Framework versions

 This model is a fine-tuned version of [cointegrated/rubert-tiny2](https://huggingface.co/cointegrated/rubert-tiny2) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.0094
+- Precision: 0.6364
+- Recall: 0.7101
+- F1: 0.6712
+- Accuracy: 0.9973
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 32   | 0.1433          | 0.0       | 0.0    | 0.0    | 0.9961   |
+| No log        | 2.0   | 64   | 0.0364          | 0.0       | 0.0    | 0.0    | 0.9961   |
+| No log        | 3.0   | 96   | 0.0310          | 0.0       | 0.0    | 0.0    | 0.9961   |
+| No log        | 4.0   | 128  | 0.0286          | 0.0       | 0.0    | 0.0    | 0.9961   |
+| No log        | 5.0   | 160  | 0.0250          | 0.0       | 0.0    | 0.0    | 0.9961   |
+| No log        | 6.0   | 192  | 0.0183          | 0.6667    | 0.0290 | 0.0556 | 0.9962   |
+| No log        | 7.0   | 224  | 0.0141          | 0.5581    | 0.3478 | 0.4286 | 0.9965   |
+| No log        | 8.0   | 256  | 0.0122          | 0.6111    | 0.4783 | 0.5366 | 0.9969   |
+| No log        | 9.0   | 288  | 0.0111          | 0.6792    | 0.5217 | 0.5902 | 0.9971   |
+| No log        | 10.0  | 320  | 0.0105          | 0.6154    | 0.5797 | 0.5970 | 0.9970   |
+| No log        | 11.0  | 352  | 0.0101          | 0.5857    | 0.5942 | 0.5899 | 0.9971   |
+| No log        | 12.0  | 384  | 0.0097          | 0.6143    | 0.6232 | 0.6187 | 0.9972   |
+| No log        | 13.0  | 416  | 0.0096          | 0.6203    | 0.7101 | 0.6622 | 0.9972   |
+| No log        | 14.0  | 448  | 0.0094          | 0.6282    | 0.7101 | 0.6667 | 0.9973   |
+| No log        | 15.0  | 480  | 0.0094          | 0.6364    | 0.7101 | 0.6712 | 0.9973   |
 ### Framework versions