Training in progress epoch 4

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: 1.1499
-- Train Accuracy: 0.6199
-- Train Top-3-accuracy: 0.8676
-- Validation Loss: 1.2030
-- Validation Accuracy: 0.625
-- Validation Top-3-accuracy: 0.8646
-- Epoch: 3
+- Train Loss: 0.9091
+- Train Accuracy: 0.7125
+- Train Top-3-accuracy: 0.9227
+- Validation Loss: 1.0869
+- Validation Accuracy: 0.6562
+- Validation Top-3-accuracy: 0.8924
+- Epoch: 4
 
 ## Model description
 
@@ -50,6 +50,7 @@ The following hyperparameters were used during training:
 | 1.8871     | 0.4062         | 0.6494               | 1.6561          | 0.4618              | 0.7083                    | 1     |
 | 1.4603     | 0.5278         | 0.7790               | 1.4162          | 0.5417              | 0.8021                    | 2     |
 | 1.1499     | 0.6199         | 0.8676               | 1.2030          | 0.625               | 0.8646                    | 3     |
+| 0.9091     | 0.7125         | 0.9227               | 1.0869          | 0.6562              | 0.8924                    | 4     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1656818948.localhost.localdomain.185921.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72bff69336d9c474b497a68c76abe537b17956319be2d15b12f91b5e01307270
-size 2149221
+oid sha256:4a78287f94ebbc7e8d7bcfe28d3409508de3cc61f74b0a0a6a9ac4c510555748
+size 2149516

logs/validation/events.out.tfevents.1656819396.localhost.localdomain.185921.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3daab7a86b8a1c993899e31f84d44d50b4b38af7baf5c011440df947dcfcb3b
-size 2012
+oid sha256:5a0585873bfe1fe94f2b498c6f83983bd13c839d8bfdf38d4181108079f0207f
+size 2508

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ca147ce594d8068590d4206988dcd3f06684a2a814a2f672b87ced3823b353d
+oid sha256:e676685e62fcc4cc5867baa0324c25460af77ab87e679755a5f0106fc78e4098
 size 343527680