update model card README.md

README.md

@@ -2,8 +2,6 @@
 license: apache-2.0
 tags:
 - generated_from_trainer
-metrics:
-- accuracy
 model-index:
 - name: ikitracs_mitigation
   results: []
@@ -16,15 +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: 0.9192
-- Precision Micro: 0.1466
-- Precision Weighted: 0.2016
-- Precision Samples: 0.1024
-- Recall Micro: 0.8889
-- Recall Weighted: 0.8889
-- Recall Samples: 0.4268
-- F1-score: 0.1468
-- Accuracy: 0.4855
+- Loss: 0.7245
+- F1-score: 0.2177
 
 ## Model description
 
@@ -43,27 +34,29 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- learning_rate: 9.24e-05
+- train_batch_size: 3
+- eval_batch_size: 3
 - seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 6
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 200
+- lr_scheduler_warmup_steps: 300
 - num_epochs: 8
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Precision Micro | Precision Weighted | Precision Samples | Recall Micro | Recall Weighted | Recall Samples | F1-score | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:---------------:|:------------------:|:-----------------:|:------------:|:---------------:|:--------------:|:--------:|:--------:|
-| 1.3559        | 1.0   | 156  | 1.3010          | 0.0806          | 0.1484             | 0.0618            | 0.7819       | 0.7819          | 0.3826         | 0.1027   | 0.0      |
-| 1.3082        | 2.0   | 312  | 1.1945          | 0.1359          | 0.1917             | 0.0840            | 0.8436       | 0.8436          | 0.3995         | 0.1208   | 0.4791   |
-| 1.1954        | 3.0   | 468  | 1.0831          | 0.1322          | 0.1804             | 0.0862            | 0.9012       | 0.9012          | 0.4333         | 0.1276   | 0.4823   |
-| 1.0874        | 4.0   | 624  | 1.0097          | 0.1346          | 0.1860             | 0.0931            | 0.8930       | 0.8930          | 0.4317         | 0.1332   | 0.4855   |
-| 1.0107        | 5.0   | 780  | 0.9662          | 0.1278          | 0.1803             | 0.0857            | 0.9053       | 0.9053          | 0.4365         | 0.1273   | 0.4823   |
-| 0.9531        | 6.0   | 936  | 0.9412          | 0.1429          | 0.1980             | 0.0965            | 0.8889       | 0.8889          | 0.4268         | 0.1401   | 0.4823   |
-| 0.9142        | 7.0   | 1092 | 0.9250          | 0.1429          | 0.1987             | 0.0990            | 0.8889       | 0.8889          | 0.4268         | 0.1425   | 0.4887   |
-| 0.9018        | 8.0   | 1248 | 0.9192          | 0.1466          | 0.2016             | 0.1024            | 0.8889       | 0.8889          | 0.4268         | 0.1468   | 0.4855   |
+| Training Loss | Epoch | Step | Validation Loss | F1-score |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.2983        | 1.0   | 207  | 1.0239          | 0.1101   |
+| 1.0475        | 2.0   | 414  | 0.9027          | 0.1449   |
+| 0.9095        | 3.0   | 621  | 0.8214          | 0.1646   |
+| 0.7996        | 4.0   | 828  | 0.8772          | 0.1629   |
+| 0.6585        | 5.0   | 1035 | 0.7504          | 0.2025   |
+| 0.5473        | 6.0   | 1242 | 0.8324          | 0.2144   |
+| 0.4423        | 7.0   | 1449 | 0.6799          | 0.2176   |
+| 0.3741        | 8.0   | 1656 | 0.7245          | 0.2177   |
 
 
 ### Framework versions