Kayvane
/

distilbert-base-uncased-wandb-week-3-complaints-classifier-1024

Text Classification

Generated from Trainer

Model card Files Files and versions

Kayvane commited on Jul 19, 2022

Commit

c6cbee2

·

1 Parent(s): fb6079f

update model card README.md

Files changed (1) hide show

README.md +13 -13

README.md CHANGED Viewed

@@ -22,16 +22,16 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8012333724071148
     - name: F1
       type: f1
-      value: 0.7874955339868757
     - name: Recall
       type: recall
-      value: 0.8012333724071148
     - name: Precision
       type: precision
-      value: 0.7916364278982178
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -41,11 +41,11 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the consumer-finance-complaints dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6274
-- Accuracy: 0.8012
-- F1: 0.7875
-- Recall: 0.8012
-- Precision: 0.7916
 ## Model description
@@ -64,7 +64,7 @@ More information needed
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 1.3722796998427472e-05
 - train_batch_size: 32
 - eval_batch_size: 32
 - seed: 42
@@ -78,9 +78,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Recall | Precision |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:---------:|
-| 0.8234        | 0.61  | 1500 | 0.7809          | 0.7576   | 0.7201 | 0.7576 | 0.7086    |
-| 0.6725        | 1.22  | 3000 | 0.6747          | 0.7904   | 0.7724 | 0.7904 | 0.7773    |
-| 0.5999        | 1.83  | 4500 | 0.6274          | 0.8012   | 0.7875 | 0.8012 | 0.7916    |
 ### Framework versions

     metrics:
     - name: Accuracy
       type: accuracy
+      value: 0.8166760103970236
     - name: F1
       type: f1
+      value: 0.8089132637288794
     - name: Recall
       type: recall
+      value: 0.8166760103970236
     - name: Precision
       type: precision
+      value: 0.810259366582512
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the consumer-finance-complaints dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.5664
+- Accuracy: 0.8167
+- F1: 0.8089
+- Recall: 0.8167
+- Precision: 0.8103
 ## Model description
 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 2.9291066722689668e-05
 - train_batch_size: 32
 - eval_batch_size: 32
 - seed: 42
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Recall | Precision |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:---------:|
+| 0.7592        | 0.61  | 1500 | 0.6981          | 0.7776   | 0.7495 | 0.7776 | 0.7610    |
+| 0.5859        | 1.22  | 3000 | 0.6082          | 0.8085   | 0.7990 | 0.8085 | 0.8005    |
+| 0.5228        | 1.83  | 4500 | 0.5664          | 0.8167   | 0.8089 | 0.8167 | 0.8103    |
 ### Framework versions