Training in progress epoch 43

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: 1.5981
-- Validation Loss: 4.5991
-- Epoch: 42
+- Train Loss: 1.5788
+- Validation Loss: 4.6276
+- Epoch: 43
 
 ## Model description
 
@@ -86,6 +86,7 @@ The following hyperparameters were used during training:
 | 1.6643     | 4.5819          | 40    |
 | 1.6224     | 4.6558          | 41    |
 | 1.5981     | 4.5991          | 42    |
+| 1.5788     | 4.6276          | 43    |
 
 
 ### 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 sha256:2cd52427f50bd90f6337b7ae7d6cfd7c0805f5d0d47f9f6d4ae28ffa98507943
-size 968786
+oid sha256:94a99677bdee5cbc16cd8e313b2122b0d2b3cf32507c164c36af75ecc5293106
+size 968854

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:057e7add1dbb038a3105ecd3c7d26875371fc7423b0e36303dee564f0997b281
-size 6784
+oid sha256:401e2e68569fbc17d41867b9aa7ce5a4aec4f9c7c21ce9d8c3ad9b6266889d29
+size 6940

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4470350ed67f6446125a9f0ff94872c6a5aa225920cc7f2614dc2b756f692fd2
+oid sha256:f835f43de5d9059ed83606982848b3d23e379956d4aa73a7db565789f9a3b9c9
 size 327745472