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: 3.3770
-- Validation Loss: 3.5178
-- Epoch: 0
+- Train Loss: 2.9844
+- Validation Loss: 3.3608
+- Epoch: 7
 
 ## Model description
 
@@ -43,6 +43,13 @@ The following hyperparameters were used during training:
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
 | 3.3770     | 3.5178          | 0     |
+| 3.2458     | 3.4955          | 1     |
+| 3.1798     | 3.4681          | 2     |
+| 3.1305     | 3.4412          | 3     |
+| 3.0881     | 3.4115          | 4     |
+| 3.0500     | 3.3940          | 5     |
+| 3.0153     | 3.3692          | 6     |
+| 2.9844     | 3.3608          | 7     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1665986796.f9a3fc799c36.138.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18a2f94c2082684caab29405138246b63c14afa773e3ad55388c94ecc64a11cf
-size 899044
+oid sha256:54d233ebaca61f9458e91ba5f0f67db832dfcd48b3a6c356ce0fc8d9345831d1
+size 899520

logs/validation/events.out.tfevents.1665988087.f9a3fc799c36.138.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b93954360c9c89aba4069c896b1bbdce15a0a3e504f1c6df3c21009ec5009a8
-size 194
+oid sha256:ea0bca8e3454cc897beeb3d0d4ec21121ceec06db7fcb19b114fe2c079142796
+size 1286

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee75baac8521b66c11a9ba2c67750ac5df743845813e413b82d8c2f837b099cc
+oid sha256:67313ee9ca27b0b9bbaa5ea1605a8d5546d8764d4ad77b39734758480c19f074
 size 327745496