Training in progress epoch 3

README.md

@@ -14,10 +14,10 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 5.0280
-- Validation Loss: 6.3652
-- Train Accuracy: 0.0495
-- Epoch: 2
+- Train Loss: 4.6309
+- Validation Loss: 6.2676
+- Train Accuracy: 0.0543
+- Epoch: 3
 
 ## Model description
 
@@ -46,6 +46,7 @@ The following hyperparameters were used during training:
 | 6.9163     | 7.1432          | 0.0160         | 0     |
 | 5.7305     | 6.7004          | 0.0298         | 1     |
 | 5.0280     | 6.3652          | 0.0495         | 2     |
+| 4.6309     | 6.2676          | 0.0543         | 3     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1679745532.209c830f14a4.306.8.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b5b4f71f61da22f9254fe09f12c4a386d477dee2685b2002043597978f16f4a
-size 1909920
+oid sha256:8329503320fe5d9ab279026c01e79ef79693b5b620a66d70f2f6e73d941fbda3
+size 1910137

logs/validation/events.out.tfevents.1679745794.209c830f14a4.306.9.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84f28d4d2fccd9b905b4e308f6408b8a2e5de322489b8195d033ce6bfb7de412
-size 506
+oid sha256:49ef424c734ff394582c0f6dffc5c88d3bd6fdfcd5846b669caf9fc887e3bd04
+size 662

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:233581117d724570cf39bf05a15bfd08a602f497dd9ac8d16bc18794427db8ff
+oid sha256:355f9fd35856bf78ca28952dce42c57575400d36c900611cd500ff887269f056
 size 269010940