End of training

README.md

@@ -1,4 +1,5 @@
 ---
+license: apache-2.0
 tags:
 - generated_from_keras_callback
 model-index:
@@ -11,12 +12,12 @@ probably proofread and complete it, then remove this comment. -->
 
 # akar49/mri_classifier
 
-This model is a fine-tuned version of [akar49/ViTonMRI](https://huggingface.co/akar49/ViTonMRI) on an unknown dataset.
+This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.3841
-- Validation Loss: 0.3693
-- Train Accuracy: 0.8776
-- Epoch: 2
+- Train Loss: 0.1032
+- Validation Loss: 0.1556
+- Train Accuracy: 0.9367
+- Epoch: 14
 
 ## Model description
 
@@ -42,9 +43,21 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 0.6434     | 0.5898          | 0.7792         | 0     |
-| 0.5207     | 0.4672          | 0.8551         | 1     |
-| 0.3841     | 0.3693          | 0.8776         | 2     |
+| 0.6447     | 0.6133          | 0.7004         | 0     |
+| 0.5405     | 0.5010          | 0.8256         | 1     |
+| 0.4181     | 0.3917          | 0.8650         | 2     |
+| 0.3122     | 0.3189          | 0.9058         | 3     |
+| 0.2474     | 0.3069          | 0.8875         | 4     |
+| 0.2021     | 0.2733          | 0.9044         | 5     |
+| 0.1745     | 0.2455          | 0.9100         | 6     |
+| 0.1591     | 0.2203          | 0.9212         | 7     |
+| 0.1450     | 0.2350          | 0.9142         | 8     |
+| 0.1397     | 0.2122          | 0.9198         | 9     |
+| 0.1227     | 0.2098          | 0.9212         | 10    |
+| 0.1169     | 0.1754          | 0.9325         | 11    |
+| 0.1080     | 0.1782          | 0.9339         | 12    |
+| 0.0971     | 0.1705          | 0.9353         | 13    |
+| 0.1032     | 0.1556          | 0.9367         | 14    |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "akar49/ViTonMRI",
+  "_name_or_path": "google/vit-base-patch16-224-in21k",
   "architectures": [
     "ViTForImageClassification"
   ],
@@ -8,9 +8,17 @@
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.0,
   "hidden_size": 768,
+  "id2label": {
+    "0": "notumor",
+    "1": "tumor"
+  },
   "image_size": 224,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
+  "label2id": {
+    "notumor": "0",
+    "tumor": "1"
+  },
   "layer_norm_eps": 1e-12,
   "model_type": "vit",
   "num_attention_heads": 12,
@@ -18,6 +26,5 @@
   "num_hidden_layers": 12,
   "patch_size": 16,
   "qkv_bias": true,
-  "torch_dtype": "float32",
   "transformers_version": "4.30.2"
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13b5ee7717cae1a15a9387580320777fe859e8e90c2702b85226d97ad5a9f27c
-size 343486136
+oid sha256:433fd89d942ebce5060966566b32d1038bcd8c6fad419f7d89132b1e4a587884
+size 343469752