Training in progress epoch 36

README.md

@@ -15,9 +15,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.8480
-- Validation Loss: 4.3697
-- Epoch: 33
+- Train Loss: 1.7685
+- Validation Loss: 4.5072
+- Epoch: 36
 
 ## Model description
 
@@ -77,6 +77,9 @@ The following hyperparameters were used during training:
 | 1.9159     | 4.3262          | 31    |
 | 1.8750     | 4.3550          | 32    |
 | 1.8480     | 4.3697          | 33    |
+| 1.8215     | 4.4233          | 34    |
+| 1.7874     | 4.4876          | 35    |
+| 1.7685     | 4.5072          | 36    |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1711718173.e7f3963a7819.156.2.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49c736ffbc0460e8fd2094ad2fe0b431265c2f61638857d6b4002d85aab3ef84
-size 968174
+oid sha256:7a81871b103e0fb5892f705c2ba43532063435967f4cf62f1c2f69613c5cb6f9
+size 968378

logs/validation/events.out.tfevents.1711718177.e7f3963a7819.156.3.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36776353a10c0d28bb7cd22ef56cffd5cc0e2c56fe70385a3ca5d386e3d3170a
-size 5380
+oid sha256:ae6504989fc1b821a6b1ab6fe8dc1d26a799dbfd4b6b5308d06e53bdbe8d7579
+size 5848

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e17129a869afd702070d8028cc05ebc7e5b437f8c41fb0163f955918d812e82
+oid sha256:976a969465c06d6db977a7d2fbb63bf874055ff5be692c2f5e4298096dd140ba
 size 327745472