update model card README.md

README.md

@@ -14,43 +14,43 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2006
+- Loss: 0.2182
 - Benefactive Precision: 0.0
 - Benefactive Recall: 0.0
 - Benefactive F1: 0.0
 - Benefactive Number: 2
-- Causator Precision: 0.8571
-- Causator Recall: 1.0
-- Causator F1: 0.9231
+- Causator Precision: 0.7333
+- Causator Recall: 0.9167
+- Causator F1: 0.8148
 - Causator Number: 12
-- Cause Precision: 1.0
+- Cause Precision: 0.5
 - Cause Recall: 0.2
-- Cause F1: 0.3333
+- Cause F1: 0.2857
 - Cause Number: 5
-- Contrsubject Precision: 0.6
-- Contrsubject Recall: 0.3333
-- Contrsubject F1: 0.4286
+- Contrsubject Precision: 1.0
+- Contrsubject Recall: 0.2222
+- Contrsubject F1: 0.3636
 - Contrsubject Number: 9
-- Deliberative Precision: 0.8
-- Deliberative Recall: 1.0
-- Deliberative F1: 0.8889
+- Deliberative Precision: 1.0
+- Deliberative Recall: 0.25
+- Deliberative F1: 0.4
 - Deliberative Number: 4
-- Experiencer Precision: 0.7160
-- Experiencer Recall: 0.7342
-- Experiencer F1: 0.7250
+- Experiencer Precision: 0.7108
+- Experiencer Recall: 0.7468
+- Experiencer F1: 0.7284
 - Experiencer Number: 79
-- Object Precision: 0.7203
-- Object Recall: 0.6913
-- Object F1: 0.7055
+- Object Precision: 0.6966
+- Object Recall: 0.6779
+- Object F1: 0.6871
 - Object Number: 149
 - Predicate Precision: 0.9847
 - Predicate Recall: 0.9923
 - Predicate F1: 0.9885
 - Predicate Number: 260
-- Overall Precision: 0.8591
-- Overall Recall: 0.8442
-- Overall F1: 0.8516
-- Overall Accuracy: 0.9331
+- Overall Precision: 0.8490
+- Overall Recall: 0.8327
+- Overall F1: 0.8408
+- Overall Accuracy: 0.9274
 
 ## Model description
 
@@ -73,8 +73,8 @@ The following hyperparameters were used during training:
 - train_batch_size: 4
 - eval_batch_size: 1
 - seed: 755657
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 16
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.02
@@ -85,8 +85,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Benefactive Precision | Benefactive Recall | Benefactive F1 | Benefactive Number | Causator Precision | Causator Recall | Causator F1 | Causator Number | Cause Precision | Cause Recall | Cause F1 | Cause Number | Contrsubject Precision | Contrsubject Recall | Contrsubject F1 | Contrsubject Number | Deliberative Precision | Deliberative Recall | Deliberative F1 | Deliberative Number | Experiencer Precision | Experiencer Recall | Experiencer F1 | Experiencer Number | Object Precision | Object Recall | Object F1 | Object Number | Predicate Precision | Predicate Recall | Predicate F1 | Predicate Number | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------------------:|:------------------:|:--------------:|:------------------:|:------------------:|:---------------:|:-----------:|:---------------:|:---------------:|:------------:|:--------:|:------------:|:----------------------:|:-------------------:|:---------------:|:-------------------:|:----------------------:|:-------------------:|:---------------:|:-------------------:|:---------------------:|:------------------:|:--------------:|:------------------:|:----------------:|:-------------:|:---------:|:-------------:|:-------------------:|:----------------:|:------------:|:----------------:|:-----------------:|:--------------:|:----------:|:----------------:|
-| 0.2606        | 1.0   | 304  | 0.2313          | 0.0                   | 0.0                | 0.0            | 2                  | 0.7143             | 0.8333          | 0.7692      | 12              | 0.5             | 0.2          | 0.2857   | 5            | 1.0                    | 0.2222              | 0.3636          | 9                   | 1.0                    | 0.25                | 0.4             | 4                   | 0.8372                | 0.4557             | 0.5902         | 79                 | 0.8              | 0.5101        | 0.6230    | 149           | 0.9846              | 0.9846           | 0.9846       | 260              | 0.9161            | 0.7346         | 0.8154     | 0.9217           |
-| 0.1565        | 2.0   | 608  | 0.2006          | 0.0                   | 0.0                | 0.0            | 2                  | 0.8571             | 1.0             | 0.9231      | 12              | 1.0             | 0.2          | 0.3333   | 5            | 0.6                    | 0.3333              | 0.4286          | 9                   | 0.8                    | 1.0                 | 0.8889          | 4                   | 0.7160                | 0.7342             | 0.7250         | 79                 | 0.7203           | 0.6913        | 0.7055    | 149           | 0.9847              | 0.9923           | 0.9885       | 260              | 0.8591            | 0.8442         | 0.8516     | 0.9331           |
+| 0.2886        | 1.0   | 152  | 0.2507          | 0.0                   | 0.0                | 0.0            | 2                  | 0.6667             | 0.8333          | 0.7407      | 12              | 1.0             | 0.2          | 0.3333   | 5            | 1.0                    | 0.1111              | 0.2000          | 9                   | 0.0                    | 0.0                 | 0.0             | 4                   | 0.6596                | 0.7848             | 0.7168         | 79                 | 0.7232           | 0.5436        | 0.6207    | 149           | 0.9847              | 0.9885           | 0.9866       | 260              | 0.8512            | 0.7923         | 0.8207     | 0.9203           |
+| 0.1911        | 2.0   | 304  | 0.2182          | 0.0                   | 0.0                | 0.0            | 2                  | 0.7333             | 0.9167          | 0.8148      | 12              | 0.5             | 0.2          | 0.2857   | 5            | 1.0                    | 0.2222              | 0.3636          | 9                   | 1.0                    | 0.25                | 0.4             | 4                   | 0.7108                | 0.7468             | 0.7284         | 79                 | 0.6966           | 0.6779        | 0.6871    | 149           | 0.9847              | 0.9923           | 0.9885       | 260              | 0.8490            | 0.8327         | 0.8408     | 0.9274           |
 
 
 ### Framework versions