Update README.md

README.md

@@ -61,6 +61,22 @@ The following hyperparameters were used during training:
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:-----------------:|:--------:|:---------------:|:------------:|:---------------:|:------------:|
 | 0.2328        | 1.69  | 200  | 0.2811          | 0.8942   | 0.8942   | 0.8943            | 0.8942   | 0.8942          | 0.8943       | 0.8942          | 0.8942       |
 
+### eval result
+|Datasets|asadfgglie/nli-zh-tw-all/test|asadfgglie/BanBan_2024-10-17-facial_expressions-nli/test|eval_dataset|test_dataset|
+| :---: | :---: | :---: | :---: | :---: |
+|eval_loss|1.38|0.25|1.317|1.254|
+|eval_f1_macro|0.583|0.925|0.604|0.62|
+|eval_f1_micro|0.584|0.925|0.605|0.621|
+|eval_accuracy_balanced|0.592|0.925|0.613|0.627|
+|eval_accuracy|0.584|0.925|0.605|0.621|
+|eval_precision_macro|0.595|0.925|0.615|0.63|
+|eval_recall_macro|0.592|0.925|0.613|0.627|
+|eval_precision_micro|0.584|0.925|0.605|0.621|
+|eval_recall_micro|0.584|0.925|0.605|0.621|
+|eval_runtime|50.572|0.611|11.106|44.083|
+|eval_samples_per_second|168.076|1549.051|170.082|171.425|
+|eval_steps_per_second|2.63|24.562|2.701|2.699|
+|Size of dataset|8500|946|1889|7557|
 
 ### Framework versions