End of training

README.md

@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4510
-- Accuracy: 0.7426
+- Loss: 0.1500
+- Accuracy: 0.9407
 
 ## Model description
 
@@ -44,13 +44,17 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 1
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.4629        | 0.99  | 52   | 0.4450          | 0.7494   |
+| 0.4088        | 0.99  | 52   | 0.2977          | 0.8926   |
+| 0.2328        | 2.0   | 105  | 0.1746          | 0.9379   |
+| 0.1758        | 2.99  | 157  | 0.1439          | 0.9523   |
+| 0.1586        | 4.0   | 210  | 0.1292          | 0.9475   |
+| 0.1231        | 4.95  | 260  | 0.1248          | 0.9487   |
 
 
 ### Framework versions

modeling_alexnet.py

@@ -33,13 +33,14 @@ class AlexNetPneumoniaClassification(PreTrainedModel):
         x = torch.relu(self.fc2(x))
         logits = self.fc3(x)        
         loss = None
-        if labels is not None:        
+        if labels is not None:
           loss_fct = nn.CrossEntropyLoss()
           loss = loss_fct(logits.view(-1, self.num_labels), labels)
           return SequenceClassifierOutput(
-              loss=loss,
-              logits=logits,
+            loss=loss,
+            logits=logits,
           )
-        return {
-            "logits": logits,
-        }
+        
+        return SequenceClassifierOutput(
+          logits=logits,
+        )

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c06db335d80c8d8161fc6c5fabf38e8c64f66a00c190bed013453536391b450a
+oid sha256:ca4cdd2854a8a46751aba0b0afe86995032b9cbb99ae9dd3fbaf5c890b0cfd46
 size 233163169

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3309ffb1415c0711ad3c3a9bdb64620a7e82757c47754f1dc99b4310a8e29e2d
+oid sha256:2a9fcaacba87b1529027be7d0c8e682011a8e4e3e8dca2b9b7d85263e4825227
 size 4091