Training in progress epoch 0

README.md

@@ -14,13 +14,13 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 4.3094
-- Train Accuracy: 0.0226
-- Train Top-3-accuracy: 0.0668
-- Validation Loss: 4.4393
-- Validation Accuracy: 0.0226
-- Validation Top-3-accuracy: 0.0660
-- Epoch: 2
+- Train Loss: 4.4859
+- Train Accuracy: 0.0195
+- Train Top-5-accuracy: 0.0579
+- Validation Loss: 4.2995
+- Validation Accuracy: 0.0368
+- Validation Top-5-accuracy: 0.0865
+- Epoch: 0
 
 ## Model description
 
@@ -39,16 +39,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.003, 'decay_steps': 1400, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
+- optimizer: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0003, 'decay_steps': 1750, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.001}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
 - training_precision: mixed_float16
 
 ### Training results
 
-| Train Loss | Train Accuracy | Train Top-3-accuracy | Validation Loss | Validation Accuracy | Validation Top-3-accuracy | Epoch |
+| Train Loss | Train Accuracy | Train Top-5-accuracy | Validation Loss | Validation Accuracy | Validation Top-5-accuracy | Epoch |
 |:----------:|:--------------:|:--------------------:|:---------------:|:-------------------:|:-------------------------:|:-----:|
-| 4.6733     | 0.0106         | 0.0335               | 4.5751          | 0.0196              | 0.0464                    | 0     |
-| 4.4185     | 0.0219         | 0.0647               | 4.3134          | 0.0242              | 0.0614                    | 1     |
-| 4.3094     | 0.0226         | 0.0668               | 4.4393          | 0.0226              | 0.0660                    | 2     |
+| 4.4859     | 0.0195         | 0.0579               | 4.2995          | 0.0368              | 0.0865                    | 0     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1662926640.2114a1b34ca4.76.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71a7e4b2d5e9b2c23780910741859cf3f1996929bc050c6582d4da33274a715a
+size 3266251

logs/validation/events.out.tfevents.1662927581.2114a1b34ca4.76.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e469af1ad69f57b36204b5e95e16deec2fc70de55521ce7467b5c6a32cf946c6
+size 530

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce7a1b83023e2a17f5c09bba8dc1f6bcd7456bad0e6f57a42cf54859a4a9a572
-size 343787296
+oid sha256:3a26438d7d5e1dc7cd92df35bf7bf8bd1a7aa73d040a6af8ddbc65c3841eda69
+size 343770912