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 [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0933
-- Train Accuracy: 0.9712
-- Validation Loss: 0.1317
-- Validation Accuracy: 0.9622
-- Epoch: 2
+- Train Loss: 0.1117
+- Train Accuracy: 0.9610
+- Validation Loss: 0.2585
+- Validation Accuracy: 0.8967
+- Epoch: 3
 
 ## Model description
 
@@ -48,6 +48,7 @@ The following hyperparameters were used during training:
 | 0.1050     | 0.9657         | 0.0851          | 0.9776              | 0     |
 | 0.2147     | 0.9043         | 0.1395          | 0.9632              | 1     |
 | 0.0933     | 0.9712         | 0.1317          | 0.9622              | 2     |
+| 0.1117     | 0.9610         | 0.2585          | 0.8967              | 3     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1704974414.6e9e89528c81.1936.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65376e6608f60e8c4bc92791537bcadd71d5d053fe3ca403f7d29ff019302aae
-size 1897734
+oid sha256:0938a0e16897136028a741c74299ec6f620711d5d9e9b5bce75320b744195d96
+size 1897874

logs/validation/events.out.tfevents.1704976245.6e9e89528c81.1936.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd7adecfde2c11486c70a9e2cd428f301c7232bff66d5acaf1fc2436c3e0ba70
-size 1036
+oid sha256:b86c0009a26e3b5bb9c3e156cb7c3ebe7da5e28e9bcd4892c002023a2beeaece
+size 1358

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a456ede25c03ff5c15f89ebc7e33560c23022d722e587e76ed741a5ba35174f7
+oid sha256:34da4ec681284c8546d2c1a0836768c962193338e52f838c1a8374b11b50d944
 size 267951808