update model card README.md

README.md

@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8885
-- Precision: 0.8423
-- Recall: 0.8333
-- F1: 0.8361
-- Accuracy: 0.8828
+- Loss: 0.7927
+- Precision: 0.8512
+- Recall: 0.8478
+- F1: 0.8484
+- Accuracy: 0.8842
 
 ## Model description
 
@@ -43,9 +43,9 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- learning_rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -55,16 +55,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 1.0032        | 1.0   | 514  | 0.5630          | 0.7818    | 0.8316 | 0.8003 | 0.8575   |
-| 0.4879        | 2.0   | 1028 | 0.5831          | 0.8358    | 0.8253 | 0.8216 | 0.8721   |
-| 0.326         | 3.0   | 1542 | 0.6182          | 0.8312    | 0.8329 | 0.8295 | 0.8789   |
-| 0.2385        | 4.0   | 2056 | 0.6013          | 0.8210    | 0.8659 | 0.8402 | 0.8838   |
-| 0.1684        | 5.0   | 2570 | 0.7213          | 0.8355    | 0.8369 | 0.8341 | 0.8838   |
-| 0.1391        | 6.0   | 3084 | 0.8164          | 0.8504    | 0.8404 | 0.8430 | 0.8852   |
-| 0.1338        | 7.0   | 3598 | 0.7627          | 0.8274    | 0.8430 | 0.8341 | 0.8808   |
-| 0.1111        | 8.0   | 4112 | 0.8672          | 0.8454    | 0.8325 | 0.8378 | 0.8799   |
-| 0.0929        | 9.0   | 4626 | 0.8739          | 0.8458    | 0.8375 | 0.8395 | 0.8838   |
-| 0.0741        | 10.0  | 5140 | 0.8885          | 0.8423    | 0.8333 | 0.8361 | 0.8828   |
+| No log        | 1.0   | 257  | 0.5177          | 0.7547    | 0.8422 | 0.7806 | 0.8444   |
+| 0.6866        | 2.0   | 514  | 0.4727          | 0.8301    | 0.8543 | 0.8372 | 0.8794   |
+| 0.6866        | 3.0   | 771  | 0.5257          | 0.8261    | 0.8508 | 0.8347 | 0.8779   |
+| 0.2332        | 4.0   | 1028 | 0.5768          | 0.8254    | 0.8651 | 0.8423 | 0.8818   |
+| 0.2332        | 5.0   | 1285 | 0.6244          | 0.8405    | 0.8529 | 0.8462 | 0.8852   |
+| 0.1201        | 6.0   | 1542 | 0.7367          | 0.8520    | 0.8507 | 0.8505 | 0.8838   |
+| 0.1201        | 7.0   | 1799 | 0.6644          | 0.8419    | 0.8607 | 0.8498 | 0.8833   |
+| 0.0848        | 8.0   | 2056 | 0.7632          | 0.8522    | 0.8433 | 0.8465 | 0.8833   |
+| 0.0848        | 9.0   | 2313 | 0.7510          | 0.8515    | 0.8569 | 0.8532 | 0.8867   |
+| 0.0517        | 10.0  | 2570 | 0.7927          | 0.8512    | 0.8478 | 0.8484 | 0.8842   |
 
 
 ### Framework versions