Training in progress epoch 3

README.md

@@ -15,11 +15,11 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.5296
-- Train Accuracy: 0.6930
-- Validation Loss: 2.3390
-- Validation Accuracy: 0.5128
-- Epoch: 2
+- Train Loss: 1.0298
+- Train Accuracy: 0.8158
+- Validation Loss: 2.3983
+- Validation Accuracy: 0.4615
+- Epoch: 3
 
 ## Model description
 
@@ -48,6 +48,7 @@ The following hyperparameters were used during training:
 | 3.5410     | 0.2497         | 3.0774          | 0.3333              | 0     |
 | 2.3876     | 0.4804         | 2.5436          | 0.4103              | 1     |
 | 1.5296     | 0.6930         | 2.3390          | 0.5128              | 2     |
+| 1.0298     | 0.8158         | 2.3983          | 0.4615              | 3     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1697308621.99df1aa9d054.28.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76df382beb5c0c199113f2bfb0812b2fb00caa698124ad0e6fc3537ed9023650
-size 4190669
+oid sha256:ad287f05b18749e30408bd683dc5e03d4d4aa643acc6e917a18f09948257ea3a
+size 4190809

logs/validation/events.out.tfevents.1697308729.99df1aa9d054.28.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a32a77346363182c5ec036bd9f03274c06e7ffcc1a5ace917be7e0dfad6cad10
-size 1032
+oid sha256:b48f1399a9ebf563077feef3ab747013b9fe5e355f60c3a2b8d642fbbb9b7782
+size 1352

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b57d43f0728c19a67ecb2e27f4ad0be1c9fa880493f7c4117f909c7ee35a5a9e
+oid sha256:7061c22213618bdb5cf973b00a01eff2bb5cd1749b693372e40157c33a8a1dfe
 size 438466132