End of training

README.md

@@ -14,9 +14,9 @@ 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: 2.0683
-- Validation Loss: 2.3829
-- Epoch: 10
+- Train Loss: 1.8709
+- Validation Loss: 2.3512
+- Epoch: 14
 
 ## Model description
 
@@ -53,6 +53,10 @@ The following hyperparameters were used during training:
 | 2.1843     | 2.4115          | 8     |
 | 2.1322     | 2.3931          | 9     |
 | 2.0683     | 2.3829          | 10    |
+| 2.0122     | 2.3669          | 11    |
+| 1.9676     | 2.3596          | 12    |
+| 1.9087     | 2.3591          | 13    |
+| 1.8709     | 2.3512          | 14    |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1653366214.MacBook-Pro.720.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:427b1f4f61a5918f98fb0deaf10bc64b6155fa3565b392e903fa69898a1af2c2
-size 1199735
+oid sha256:687bb7a10f34abbe9345728ffce2ca4c8f566509603f18d3497e82d66d0d853f
+size 1200007

logs/validation/events.out.tfevents.1653366261.MacBook-Pro.720.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c056c471d3c977d488b6a813ecf0f6927b26f37c731bcaf948a82994cd89eed
-size 1747
+oid sha256:f5238b990c38da70f56c8ec2d3a14a5e9ad10974177ea339fbbb1d44bbe9ae90
+size 2371

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47f77231e9c8b9ea41f8af67de37cf733a0b69dbf733c18df9f8c57d615e7172
+oid sha256:b0c23030b99c16547934ede5a06e5d0f6495b3d3389cd85a48c56927ce8fc433
 size 327745496