Training in progress epoch 0

README.md

@@ -15,12 +15,12 @@ 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: 0.1415
-- Train Accuracy: 0.9739
-- Train Top-3-accuracy: 0.9863
-- Validation Loss: 0.0055
-- Validation Accuracy: 0.9993
-- Validation Top-3-accuracy: 1.0
+- Train Loss: 1.9711
+- Train Accuracy: 0.4384
+- Train Top-3-accuracy: 0.6297
+- Validation Loss: 0.2537
+- Validation Accuracy: 0.9323
+- Validation Top-3-accuracy: 0.9940
 - Epoch: 0
 
 ## Model description
@@ -40,19 +40,19 @@ 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': 0.0002, 'decay_steps': 2720, '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': 0.002, 'decay_steps': 544, '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}
 - training_precision: mixed_float16
 
 ### Training results
 
 | Train Loss | Train Accuracy | Train Top-3-accuracy | Validation Loss | Validation Accuracy | Validation Top-3-accuracy | Epoch |
 |:----------:|:--------------:|:--------------------:|:---------------:|:-------------------:|:-------------------------:|:-----:|
-| 0.1415     | 0.9739         | 0.9863               | 0.0055          | 0.9993              | 1.0                       | 0     |
+| 1.9711     | 0.4384         | 0.6297               | 0.2537          | 0.9323              | 0.9940                    | 0     |
 
 
 ### Framework versions
 
 - Transformers 4.31.0
 - TensorFlow 2.12.0
-- Datasets 2.14.0
+- Datasets 2.14.1
 - Tokenizers 0.13.3

logs/train/events.out.tfevents.1690482618.b5122212b18a.298.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:520f20bbb659f1ad75579d1a5695d78c3531aae873d851d4402aef815f522447
+size 78

logs/train/events.out.tfevents.1690482807.b5122212b18a.7102.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:940aaf552ab20f03f9a9545ccd8346f2f8720083054151a6ca15c9d2a7ede553
+size 78

logs/train/events.out.tfevents.1690483192.b5122212b18a.7102.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c31ab702279a2e6c60fdd4ecb52e774a7d020adab2fe374b7bd7714199bd4eb8
+size 78

logs/train/events.out.tfevents.1690484351.b5122212b18a.9933.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35459e6be2c3a8cf86ce2603e71ddf379746a3166b6dffe611b9c8fb4984af81
+size 3307558

logs/validation/events.out.tfevents.1690490707.b5122212b18a.9933.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:271b038214d71c23f40b40a8256bef310c9f2b5439e2db2ae4e27bacfa43e043
+size 568

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:164ba036d9807b05a74093fe6243e2b2e864ee137682ad78f180968ef0ec78c9
+oid sha256:99d2d1c63b35a7856d238889c0310f9007fdfdbf308da835d9770839e5497bbc
 size 343620280