Model save

README.md

@@ -7,6 +7,8 @@ datasets:
 - imagefolder
 metrics:
 - accuracy
+- precision
+- recall
 model-index:
 - name: pvt-tiny-224
   results:
@@ -22,7 +24,13 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.7333333333333333
+      value: 0.7866666666666666
+    - name: Precision
+      type: precision
+      value: 0.7722088353413654
+    - name: Recall
+      type: recall
+      value: 0.7866666666666666
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +40,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Zetatech/pvt-tiny-224](https://huggingface.co/Zetatech/pvt-tiny-224) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5594
-- Accuracy: 0.7333
+- Loss: 0.5175
+- Accuracy: 0.7867
+- Precision: 0.7722
+- Recall: 0.7867
+- F1 Score: 0.7693
 
 ## Model description
 
@@ -53,23 +64,35 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 32
-- eval_batch_size: 32
+- train_batch_size: 64
+- eval_batch_size: 64
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 128
+- total_train_batch_size: 256
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 3
+- num_epochs: 15
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 8    | 0.5968          | 0.7125   |
-| 0.5851        | 2.0   | 16   | 0.5701          | 0.725    |
-| 0.5471        | 3.0   | 24   | 0.5670          | 0.725    |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 Score |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|
+| No log        | 1.0   | 4    | 0.5604          | 0.7375   | 0.8067    | 0.7375 | 0.6302   |
+| No log        | 2.0   | 8    | 0.5613          | 0.7583   | 0.7327    | 0.7583 | 0.7253   |
+| No log        | 3.0   | 12   | 0.5514          | 0.7417   | 0.7093    | 0.7417 | 0.7094   |
+| 0.5422        | 4.0   | 16   | 0.5402          | 0.7583   | 0.7681    | 0.7583 | 0.6862   |
+| 0.5422        | 5.0   | 20   | 0.5306          | 0.7583   | 0.7404    | 0.7583 | 0.7444   |
+| 0.5422        | 6.0   | 24   | 0.5310          | 0.7708   | 0.7597    | 0.7708 | 0.7253   |
+| 0.5422        | 7.0   | 28   | 0.5301          | 0.7708   | 0.7522    | 0.7708 | 0.7528   |
+| 0.3772        | 8.0   | 32   | 0.5338          | 0.7833   | 0.7677    | 0.7833 | 0.7672   |
+| 0.3772        | 9.0   | 36   | 0.5362          | 0.7833   | 0.7677    | 0.7833 | 0.7672   |
+| 0.3772        | 10.0  | 40   | 0.5379          | 0.775    | 0.7577    | 0.775  | 0.7583   |
+| 0.3772        | 11.0  | 44   | 0.5541          | 0.7833   | 0.7672    | 0.7833 | 0.7632   |
+| 0.224         | 12.0  | 48   | 0.5600          | 0.7708   | 0.7542    | 0.7708 | 0.7567   |
+| 0.224         | 13.0  | 52   | 0.5661          | 0.7667   | 0.7487    | 0.7667 | 0.7513   |
+| 0.224         | 14.0  | 56   | 0.5698          | 0.7792   | 0.7630    | 0.7792 | 0.7637   |
+| 0.1283        | 15.0  | 60   | 0.5752          | 0.7792   | 0.7630    | 0.7792 | 0.7637   |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:724c74ecb55e9e07829c91aebdff189b08934e02546a5d4a80c0a1e01e666e55
+oid sha256:24df49da57fad52e2bb03988ba7f1586ac2723bb60933fde632db779a9ddc89b
 size 50929233