Training in progress epoch 3

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: 3.8211
-- Validation Loss: 3.7502
-- Epoch: 2
+- Train Loss: 3.7786
+- Validation Loss: 3.7310
+- Epoch: 3
 
 ## Model description
 
@@ -46,6 +46,7 @@ The following hyperparameters were used during training:
 | 4.0094     | 3.8307          | 0     |
 | 3.8810     | 3.7803          | 1     |
 | 3.8211     | 3.7502          | 2     |
+| 3.7786     | 3.7310          | 3     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1700898578.O11D-Ali.75372.2.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93ffdcdc05c13c66dbc61aa0ac778f19ce1ce7d619833d705ede5fd590e1dd76
-size 870943
+oid sha256:ab910608d8ef145e375eb0aea0de24b3c3a6ceab77aba26debdb22beac0d1a15
+size 871011

logs/validation/events.out.tfevents.1700903218.O11D-Ali.75372.3.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f7273c840598481a3b946bd701001c77213adea6440dcf3cd72c3069a74832e
-size 547
+oid sha256:333a4ca53c24ccde0f6889cdabd74412d768aee78a6210b389069e29c4c02180
+size 704

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cf059c351b6e38880a33bf8e01701512117e37d3d417c3faf451b556f5d1c78
+oid sha256:632efeff979beab3219f4d067f0244d09dca606ae02eb70eacdb3d491acb464e
 size 327745472