End of training

README.md

@@ -2,7 +2,7 @@
 tags:
 - generated_from_trainer
 datasets:
-- emo
+- emotion
 metrics:
 - accuracy
 model-index:
@@ -12,15 +12,15 @@ model-index:
       name: Text Classification
       type: text-classification
     dataset:
-      name: emo
-      type: emo
-      config: emo2019
+      name: emotion
+      type: emotion
+      config: split
       split: test
-      args: emo2019
+      args: split
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.7796333272826285
+      value: 0.774
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -28,10 +28,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # my_awesome_model
 
-This model is a fine-tuned version of [](https://huggingface.co/) on the emo dataset.
+This model is a fine-tuned version of [](https://huggingface.co/) on the emotion dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7348
-- Accuracy: 0.7796
+- Loss: 0.6804
+- Accuracy: 0.774
 
 ## Model description
 
@@ -50,19 +50,29 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- learning_rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 64
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.1224        | 1.0   | 1885 | 0.7348          | 0.7796   |
+| 1.6145        | 1.0   | 500  | 1.5603          | 0.3475   |
+| 1.4622        | 2.0   | 1000 | 1.3149          | 0.4      |
+| 1.2777        | 3.0   | 1500 | 1.2142          | 0.4365   |
+| 1.1218        | 4.0   | 2000 | 1.0095          | 0.5915   |
+| 0.8886        | 5.0   | 2500 | 0.8772          | 0.695    |
+| 0.7649        | 6.0   | 3000 | 0.7803          | 0.7355   |
+| 0.6818        | 7.0   | 3500 | 0.7220          | 0.7615   |
+| 0.6268        | 8.0   | 4000 | 0.6870          | 0.773    |
+| 0.5922        | 9.0   | 4500 | 0.6859          | 0.771    |
+| 0.5658        | 10.0  | 5000 | 0.6804          | 0.774    |
 
 
 ### Framework versions