Model save

README.md

@@ -24,16 +24,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.8181041844577285
+      value: 0.8261421319796954
     - name: Recall
       type: recall
-      value: 0.8459161147902869
+      value: 0.8622516556291391
     - name: F1
       type: f1
-      value: 0.8317777295420012
+      value: 0.8438107582631237
     - name: Accuracy
       type: accuracy
-      value: 0.9384245917387127
+      value: 0.9410182516810759
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -43,11 +43,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [UWB-AIR/Czert-B-base-cased](https://huggingface.co/UWB-AIR/Czert-B-base-cased) on the cnec dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3413
-- Precision: 0.8181
-- Recall: 0.8459
-- F1: 0.8318
-- Accuracy: 0.9384
+- Loss: 0.3330
+- Precision: 0.8261
+- Recall: 0.8623
+- F1: 0.8438
+- Accuracy: 0.9410
 
 ## Model description
 
@@ -67,8 +67,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 32
-- eval_batch_size: 32
+- 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: linear
@@ -78,10 +78,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.4288        | 3.4   | 500  | 0.2590          | 0.8038    | 0.8247 | 0.8141 | 0.9338   |
-| 0.1036        | 6.8   | 1000 | 0.2872          | 0.8244    | 0.8459 | 0.8350 | 0.9383   |
-| 0.0486        | 10.2  | 1500 | 0.3145          | 0.8229    | 0.8433 | 0.8330 | 0.9390   |
-| 0.0278        | 13.61 | 2000 | 0.3413          | 0.8181    | 0.8459 | 0.8318 | 0.9384   |
+| 0.5787        | 1.7   | 500  | 0.3008          | 0.7659    | 0.7943 | 0.7798 | 0.9262   |
+| 0.2266        | 3.4   | 1000 | 0.2606          | 0.8026    | 0.8437 | 0.8226 | 0.9374   |
+| 0.1443        | 5.1   | 1500 | 0.2565          | 0.8189    | 0.8525 | 0.8354 | 0.9407   |
+| 0.1004        | 6.8   | 2000 | 0.2807          | 0.8129    | 0.8539 | 0.8329 | 0.9400   |
+| 0.0759        | 8.5   | 2500 | 0.2989          | 0.8255    | 0.8627 | 0.8437 | 0.9411   |
+| 0.0563        | 10.2  | 3000 | 0.3181          | 0.8251    | 0.8578 | 0.8411 | 0.9402   |
+| 0.0475        | 11.9  | 3500 | 0.3279          | 0.8204    | 0.8609 | 0.8402 | 0.9404   |
+| 0.0378        | 13.61 | 4000 | 0.3330          | 0.8261    | 0.8623 | 0.8438 | 0.9410   |
 
 
 ### Framework versions