Training in progress epoch 38

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: 1.7433
-- Validation Loss: 4.4617
-- Epoch: 37
+- Train Loss: 1.7085
+- Validation Loss: 4.5331
+- Epoch: 38
 
 ## Model description
 
@@ -81,6 +81,7 @@ The following hyperparameters were used during training:
 | 1.7874     | 4.4876          | 35    |
 | 1.7685     | 4.5072          | 36    |
 | 1.7433     | 4.4617          | 37    |
+| 1.7085     | 4.5331          | 38    |
 
 
 ### 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 sha256:23f6728a01cf1d916593e441bba67d3452a94b6529e9d3ebd53276d948126c53
-size 968446
+oid sha256:9b0cda05952de9e21fed2f3764df53d0f7b5ed889ccd79529eb39563bf6486bc
+size 968514

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd52db87e6f4387fa1d75237e1089fa9578473cce90be666072f41a17a49a8c6
-size 6004
+oid sha256:cca590d77a1d5b58f5cf1f9c240ebfdcff644cd2d1374a09cc1e9edc5d498875
+size 6160

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52ccaa3632de9f3913de3f0b86bb5afa898342e3b6f29a38680bdb485adce67c
+oid sha256:3d3f963fa6c6e49a2a4ca7eb245cf0d2f26e723ac3e584e663413fb10a5f0a1d
 size 327745472