VitaliiVrublevskyi
/

bert-large-uncased-finetuned-mrpc

Text Classification

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

VitaliiVrublevskyi commited on Dec 3, 2023

Commit

bcce560

•

1 Parent(s): 31dd2e9

update model card README.md

Files changed (1) hide show

README.md +11 -11

README.md CHANGED Viewed

@@ -22,10 +22,10 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8799019607843137
     - name: F1
       type: f1
-      value: 0.9147826086956522
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -35,9 +35,9 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on the glue dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5471
-- Accuracy: 0.8799
-- F1: 0.9148
 ## Model description
@@ -59,7 +59,7 @@ The following hyperparameters were used during training:
 - learning_rate: 2e-05
 - train_batch_size: 32
 - eval_batch_size: 32
-- seed: 60
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 5
@@ -68,11 +68,11 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| No log        | 1.0   | 115  | 0.4404          | 0.8137   | 0.8762 |
-| No log        | 2.0   | 230  | 0.3759          | 0.8652   | 0.9027 |
-| No log        | 3.0   | 345  | 0.3746          | 0.8529   | 0.8980 |
-| No log        | 4.0   | 460  | 0.4984          | 0.8897   | 0.9228 |
-| 0.2826        | 5.0   | 575  | 0.5471          | 0.8799   | 0.9148 |
 ### Framework versions

     metrics:
     - name: Accuracy
       type: accuracy
+      value: 0.8578431372549019
     - name: F1
       type: f1
+      value: 0.9006849315068494
 ---
 <!-- 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 [bert-large-uncased](https://huggingface.co/bert-large-uncased) on the glue dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.6016
+- Accuracy: 0.8578
+- F1: 0.9007
 ## Model description
 - learning_rate: 2e-05
 - train_batch_size: 32
 - eval_batch_size: 32
+- seed: 91
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 5
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| No log        | 1.0   | 115  | 0.4435          | 0.8162   | 0.8777 |
+| No log        | 2.0   | 230  | 0.3542          | 0.8407   | 0.8870 |
+| No log        | 3.0   | 345  | 0.4246          | 0.8652   | 0.9063 |
+| No log        | 4.0   | 460  | 0.5290          | 0.8578   | 0.9010 |
+| 0.2887        | 5.0   | 575  | 0.6016          | 0.8578   | 0.9007 |
 ### Framework versions