jayanthspratap
/

convnext-tiny-224-drfx-surgery-classifier

Image Classification

Generated from Trainer

Eval Results (legacy)

Model card Files Files and versions

Metrics Training metrics Community

jayanthspratap commited on May 27, 2023

Commit

8d2f41e

·

1 Parent(s): 7036fbe

update model card README.md

Files changed (1) hide show

README.md +14 -14

README.md CHANGED Viewed

@@ -21,7 +21,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.875
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [facebook/convnext-tiny-224](https://huggingface.co/facebook/convnext-tiny-224) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3653
-- Accuracy: 0.875
 ## Model description
@@ -51,7 +51,7 @@ More information needed
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
 - train_batch_size: 4
 - eval_batch_size: 4
 - seed: 42
@@ -66,16 +66,16 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 4    | 0.6468          | 0.6875   |
-| No log        | 2.0   | 8    | 0.4960          | 0.875    |
-| 0.6461        | 3.0   | 12   | 0.4356          | 0.875    |
-| 0.6461        | 4.0   | 16   | 0.3916          | 0.875    |
-| 0.4586        | 5.0   | 20   | 0.3885          | 0.875    |
-| 0.4586        | 6.0   | 24   | 0.3806          | 0.875    |
-| 0.4586        | 7.0   | 28   | 0.3730          | 0.875    |
-| 0.3969        | 8.0   | 32   | 0.3685          | 0.875    |
-| 0.3969        | 9.0   | 36   | 0.3655          | 0.875    |
-| 0.4335        | 10.0  | 40   | 0.3653          | 0.875    |
 ### Framework versions

     metrics:
     - name: Accuracy
       type: accuracy
+      value: 0.5625
 ---
 <!-- 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 [facebook/convnext-tiny-224](https://huggingface.co/facebook/convnext-tiny-224) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.6485
+- Accuracy: 0.5625
 ## Model description
 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 1e-06
 - train_batch_size: 4
 - eval_batch_size: 4
 - seed: 42
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 4    | 0.6743          | 0.5625   |
+| No log        | 2.0   | 8    | 0.6683          | 0.5625   |
+| 0.649         | 3.0   | 12   | 0.6634          | 0.5625   |
+| 0.649         | 4.0   | 16   | 0.6594          | 0.625    |
+| 0.6178        | 5.0   | 20   | 0.6562          | 0.625    |
+| 0.6178        | 6.0   | 24   | 0.6535          | 0.625    |
+| 0.6178        | 7.0   | 28   | 0.6514          | 0.5625   |
+| 0.6236        | 8.0   | 32   | 0.6499          | 0.5625   |
+| 0.6236        | 9.0   | 36   | 0.6489          | 0.5625   |
+| 0.621         | 10.0  | 40   | 0.6485          | 0.5625   |
 ### Framework versions