End of training

README.md

@@ -24,7 +24,7 @@ model-index:
       name: Text Classification
       type: text-classification
     dataset:
-      name: Emotion
+      name: emotion
       type: emotion
       config: split
       split: validation
@@ -32,7 +32,7 @@ model-index:
     metrics:
     - name: F1
       type: f1
-      value: 0.9379095011375947
+      value: 0.9338371108651224
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -40,10 +40,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # miniLM_finetuned_Emotion_2024_06_15
 
-This model is a fine-tuned version of [microsoft/MiniLM-L12-H384-uncased](https://huggingface.co/microsoft/MiniLM-L12-H384-uncased) on the Emotion dataset.
+This model is a fine-tuned version of [microsoft/MiniLM-L12-H384-uncased](https://huggingface.co/microsoft/MiniLM-L12-H384-uncased) on the emotion dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1659
-- F1: 0.9379
+- Loss: 0.3029
+- F1: 0.9338
 
 ## Model description
 
@@ -68,23 +68,33 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 20
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| No log        | 1.0   | 250  | 0.6783          | 0.8239 |
-| No log        | 2.0   | 500  | 0.3368          | 0.9101 |
-| No log        | 3.0   | 750  | 0.2447          | 0.9346 |
-| No log        | 4.0   | 1000 | 0.2044          | 0.9273 |
-| No log        | 5.0   | 1250 | 0.1669          | 0.9350 |
-| No log        | 6.0   | 1500 | 0.1783          | 0.9386 |
-| No log        | 7.0   | 1750 | 0.1973          | 0.9313 |
-| No log        | 8.0   | 2000 | 0.1586          | 0.9385 |
-| No log        | 9.0   | 2250 | 0.1690          | 0.9352 |
-| No log        | 10.0  | 2500 | 0.1659          | 0.9379 |
+| 1.1709        | 1.0   | 250  | 0.7083          | 0.8287 |
+| 0.5045        | 2.0   | 500  | 0.3203          | 0.9235 |
+| 0.2773        | 3.0   | 750  | 0.2222          | 0.9314 |
+| 0.1908        | 4.0   | 1000 | 0.2154          | 0.9306 |
+| 0.1572        | 5.0   | 1250 | 0.1876          | 0.9312 |
+| 0.1342        | 6.0   | 1500 | 0.1890          | 0.9344 |
+| 0.1155        | 7.0   | 1750 | 0.1919          | 0.9331 |
+| 0.1043        | 8.0   | 2000 | 0.1577          | 0.9359 |
+| 0.0885        | 9.0   | 2250 | 0.1912          | 0.9353 |
+| 0.085         | 10.0  | 2500 | 0.2089          | 0.9336 |
+| 0.0715        | 11.0  | 2750 | 0.2269          | 0.9342 |
+| 0.0631        | 12.0  | 3000 | 0.2253          | 0.9326 |
+| 0.0546        | 13.0  | 3250 | 0.2342          | 0.9348 |
+| 0.0472        | 14.0  | 3500 | 0.2348          | 0.9352 |
+| 0.0414        | 15.0  | 3750 | 0.2662          | 0.9365 |
+| 0.036         | 16.0  | 4000 | 0.2725          | 0.9319 |
+| 0.0325        | 17.0  | 4250 | 0.2832          | 0.9341 |
+| 0.0263        | 18.0  | 4500 | 0.2851          | 0.9381 |
+| 0.0226        | 19.0  | 4750 | 0.2979          | 0.9329 |
+| 0.0221        | 20.0  | 5000 | 0.3029          | 0.9338 |
 
 
 ### Framework versions