End of training

README.md

@@ -15,9 +15,9 @@ probably proofread and complete it, then remove this comment. -->
 
 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: 0.1008
-- Validation Loss: 0.0973
-- Train Accuracy: 0.9833
+- Train Loss: 0.1714
+- Validation Loss: 0.1588
+- Train Accuracy: 0.9469
 - Epoch: 4
 
 ## Model description
@@ -37,18 +37,18 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 3600, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 4135, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
 - training_precision: float32
 
 ### Training results
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 0.8604     | 0.5097          | 1.0            | 0     |
-| 0.3450     | 0.1983          | 0.9833         | 1     |
-| 0.1853     | 0.1518          | 0.9833         | 2     |
-| 0.1320     | 0.1374          | 0.9778         | 3     |
-| 0.1008     | 0.0973          | 0.9833         | 4     |
+| 0.7473     | 0.4442          | 0.9034         | 0     |
+| 0.3285     | 0.2443          | 0.9372         | 1     |
+| 0.2674     | 0.2761          | 0.9275         | 2     |
+| 0.2391     | 0.2456          | 0.9227         | 3     |
+| 0.1714     | 0.1588          | 0.9469         | 4     |
 
 
 ### Framework versions

config.json

@@ -9,17 +9,17 @@
   "hidden_dropout_prob": 0.0,
   "hidden_size": 768,
   "id2label": {
-    "0": "cat",
-    "1": "dog",
-    "2": "rabbit"
+    "0": "angular_leaf_spot",
+    "1": "bean_rust",
+    "2": "healthy"
   },
   "image_size": 224,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "cat": "0",
-    "dog": "1",
-    "rabbit": "2"
+    "angular_leaf_spot": "0",
+    "bean_rust": "1",
+    "healthy": "2"
   },
   "layer_norm_eps": 1e-12,
   "model_type": "vit",

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d65b8713e5ce7270a1d38bda4250d9fdd7561cb4be9b1d4f560749757542ca0
+oid sha256:8e2a84ba2d87809f291db2e2dcc8c2bb092797d65c157c1eab6920208d7af743
 size 343472824