update model card README.md

README.md

@@ -2,8 +2,6 @@
 license: apache-2.0
 tags:
 - generated_from_trainer
-metrics:
-- accuracy
 model-index:
 - name: IKT_classifier_economywide_best
   results: []
@@ -16,13 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1819
-- Precision Weighted: 0.9628
-- Precision Macro: 0.9639
-- Recall Weighted: 0.9623
-- Recall Samples: 0.9606
-- F1-score: 0.9619
-- Accuracy: 0.9623
+- Loss: 0.1916
+- F1-score: 0.9527
 
 ## Model description
 
@@ -41,12 +34,12 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 4.427532456702983e-05
-- train_batch_size: 3
-- eval_batch_size: 3
+- learning_rate: 9.375102561418467e-05
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 6
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 100.0
@@ -54,13 +47,13 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Precision Weighted | Precision Macro | Recall Weighted | Recall Samples | F1-score | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:------------------:|:---------------:|:---------------:|:--------------:|:--------:|:--------:|
-| No log        | 1.0   | 159  | 0.1640          | 0.9628             | 0.9639          | 0.9623          | 0.9606         | 0.9619   | 0.9623   |
-| No log        | 2.0   | 318  | 0.2042          | 0.9531             | 0.9521          | 0.9528          | 0.9533         | 0.9526   | 0.9528   |
-| No log        | 3.0   | 477  | 0.2298          | 0.9457             | 0.9479          | 0.9434          | 0.9402         | 0.9427   | 0.9434   |
-| 0.1907        | 4.0   | 636  | 0.1582          | 0.9718             | 0.9723          | 0.9717          | 0.9708         | 0.9715   | 0.9717   |
-| 0.1907        | 5.0   | 795  | 0.1819          | 0.9628             | 0.9639          | 0.9623          | 0.9606         | 0.9619   | 0.9623   |
+| Training Loss | Epoch | Step | Validation Loss | F1-score |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 30   | 0.4243          | 0.9150   |
+| No log        | 2.0   | 60   | 0.2486          | 0.9145   |
+| No log        | 3.0   | 90   | 0.1950          | 0.9245   |
+| No log        | 4.0   | 120  | 0.1953          | 0.9527   |
+| No log        | 5.0   | 150  | 0.1916          | 0.9527   |
 
 
 ### Framework versions