Kayvane
/

distilroberta-base-wandb-week-3-complaints-classifier-1024

Text Classification Transformers PyTorch

roberta generated_from_trainer Eval Results Inference Endpoints

Model card Files Files and versions Community

Kayvane commited on Jul 19, 2022

Commit

9f38c77

•

1 Parent(s): aef2e91

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: 0.7935375363131338
     - name: F1
       type: f1
-      value: 0.7782286513484494
     - name: Recall
       type: recall
-      value: 0.7935375363131338
     - name: Precision
       type: precision
-      value: 0.7838508007361574
 ---
 <!-- 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 [distilroberta-base](https://huggingface.co/distilroberta-base) on the consumer-finance-complaints dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6228
-- Accuracy: 0.7935
-- F1: 0.7782
-- Recall: 0.7935
-- Precision: 0.7839
 ## Model description
@@ -64,7 +64,7 @@ More information needed
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 0.00019154628432502008
 - 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 |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:---------:|
-| 0.8624        | 0.61  | 1500 | 0.8468          | 0.7521   | 0.7215 | 0.7521 | 0.7083    |
-| 0.743         | 1.22  | 3000 | 0.7668          | 0.7651   | 0.7417 | 0.7651 | 0.7383    |
-| 0.6135        | 1.83  | 4500 | 0.6228          | 0.7935   | 0.7782 | 0.7935 | 0.7839    |
 ### Framework versions

     metrics:
     - name: Accuracy
       type: accuracy
+      value: 0.8279904184292339
     - name: F1
       type: f1
+      value: 0.8236604095677945
     - name: Recall
       type: recall
+      value: 0.8279904184292339
     - name: Precision
       type: precision
+      value: 0.8235526237070518
 ---
 <!-- 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 [distilroberta-base](https://huggingface.co/distilroberta-base) on the consumer-finance-complaints dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.5351
+- Accuracy: 0.8280
+- F1: 0.8237
+- Recall: 0.8280
+- Precision: 0.8236
 ## Model description
 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 9.027176214786854e-05
 - train_batch_size: 32
 - eval_batch_size: 32
 - seed: 42
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Recall | Precision |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:---------:|
+| 0.7756        | 0.61  | 1500 | 0.7411          | 0.7647   | 0.7375 | 0.7647 | 0.7606    |
+| 0.5804        | 1.22  | 3000 | 0.6140          | 0.8088   | 0.8052 | 0.8088 | 0.8077    |
+| 0.5008        | 1.83  | 4500 | 0.5351          | 0.8280   | 0.8237 | 0.8280 | 0.8236    |
 ### Framework versions