Training in progress epoch 3

README.md

@@ -14,13 +14,13 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.3123
-- Train Accuracy: 0.8863
-- Train Top-3-accuracy: 0.9922
-- Validation Loss: 0.2945
-- Validation Accuracy: 0.8988
-- Validation Top-3-accuracy: 0.9928
-- Epoch: 2
+- Train Loss: 0.2153
+- Train Accuracy: 0.9259
+- Train Top-3-accuracy: 0.9952
+- Validation Loss: 0.2316
+- Validation Accuracy: 0.9187
+- Validation Top-3-accuracy: 0.9958
+- Epoch: 3
 
 ## Model description
 
@@ -49,6 +49,7 @@ The following hyperparameters were used during training:
 | 0.8487     | 0.6969         | 0.9168               | 0.4793          | 0.8274              | 0.9802                    | 0     |
 | 0.4363     | 0.8428         | 0.9845               | 0.3823          | 0.8641              | 0.9881                    | 1     |
 | 0.3123     | 0.8863         | 0.9922               | 0.2945          | 0.8988              | 0.9928                    | 2     |
+| 0.2153     | 0.9259         | 0.9952               | 0.2316          | 0.9187              | 0.9958                    | 3     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1656825566.localhost.localdomain.192813.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a57710bca7d4397a76af9d28bc0c3bc8e0fdbc60c5e51a3c65ea81488e88b9de
-size 2148926
+oid sha256:96b982af4c0fc62e4c503948f80e4380396412c12d220ea3883967a94e246265
+size 2149221

logs/validation/events.out.tfevents.1656831408.localhost.localdomain.192813.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4dddc0a2aac471c80bee3ef641fd5d4464c325a136545464fcde4fd5b510cc7
-size 1522
+oid sha256:acbd85cf694e4b075a7505598d2d8a1dcb4571a3ef0047be636cc04dfd5adaeb
+size 2018

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:221c1ae9f3903e9f1a017c4f83ead53b3e0e8651e2e1a709121e72a67a14a1d5
+oid sha256:2f860432571b728284af4da2b91559e28219a84d918cd1ed6ac5cabf13226205
 size 343493888