Model save

README.md

@@ -25,16 +25,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.8236658932714617
+      value: 0.7760029717682021
     - name: Recall
       type: recall
-      value: 0.8751027115858668
+      value: 0.8582580115036976
     - name: F1
       type: f1
-      value: 0.848605577689243
+      value: 0.8150604760046821
     - name: Accuracy
       type: accuracy
-      value: 0.9646932746336094
+      value: 0.9631292359381336
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -44,11 +44,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on the cnec dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2014
-- Precision: 0.8237
-- Recall: 0.8751
-- F1: 0.8486
-- Accuracy: 0.9647
+- Loss: 0.1727
+- Precision: 0.7760
+- Recall: 0.8583
+- F1: 0.8151
+- Accuracy: 0.9631
 
 ## Model description
 
@@ -68,29 +68,28 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- lr_scheduler_warmup_steps: 1000
-- num_epochs: 12
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.9082        | 1.11  | 500  | 0.2281          | 0.6024    | 0.7539 | 0.6697 | 0.9424   |
-| 0.1977        | 2.22  | 1000 | 0.1808          | 0.7211    | 0.8369 | 0.7747 | 0.9544   |
-| 0.1477        | 3.33  | 1500 | 0.1674          | 0.7716    | 0.8661 | 0.8161 | 0.9612   |
-| 0.1105        | 4.44  | 2000 | 0.1628          | 0.7860    | 0.8780 | 0.8294 | 0.9633   |
-| 0.0929        | 5.56  | 2500 | 0.1609          | 0.7982    | 0.8743 | 0.8345 | 0.9629   |
-| 0.0735        | 6.67  | 3000 | 0.1740          | 0.7901    | 0.8722 | 0.8291 | 0.9625   |
-| 0.0614        | 7.78  | 3500 | 0.1860          | 0.8027    | 0.8710 | 0.8355 | 0.9641   |
-| 0.0513        | 8.89  | 4000 | 0.1823          | 0.8038    | 0.8804 | 0.8404 | 0.9633   |
-| 0.0399        | 10.0  | 4500 | 0.1866          | 0.8103    | 0.8846 | 0.8458 | 0.9639   |
-| 0.0327        | 11.11 | 5000 | 0.2014          | 0.8237    | 0.8751 | 0.8486 | 0.9647   |
+| 0.9465        | 0.56  | 500  | 0.2705          | 0.4955    | 0.6754 | 0.5716 | 0.9281   |
+| 0.2305        | 1.11  | 1000 | 0.1836          | 0.7054    | 0.8205 | 0.7586 | 0.9539   |
+| 0.179         | 1.67  | 1500 | 0.1784          | 0.7485    | 0.8180 | 0.7817 | 0.9576   |
+| 0.1484        | 2.22  | 2000 | 0.1835          | 0.7571    | 0.8578 | 0.8043 | 0.9615   |
+| 0.1283        | 2.78  | 2500 | 0.1792          | 0.7333    | 0.8135 | 0.7713 | 0.9596   |
+| 0.1092        | 3.33  | 3000 | 0.1749          | 0.7707    | 0.8422 | 0.8049 | 0.9619   |
+| 0.0963        | 3.89  | 3500 | 0.1706          | 0.7711    | 0.8537 | 0.8103 | 0.9633   |
+| 0.0845        | 4.44  | 4000 | 0.1709          | 0.7811    | 0.8517 | 0.8149 | 0.9633   |
+| 0.0801        | 5.0   | 4500 | 0.1727          | 0.7760    | 0.8583 | 0.8151 | 0.9631   |
 
 
 ### Framework versions