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: 4.0230
-- Validation Loss: 3.9474
-- Epoch: 0
+- Train Loss: 3.4753
+- Validation Loss: 3.7980
+- Epoch: 9
 
 ## Model description
 
@@ -43,6 +43,15 @@ The following hyperparameters were used during training:
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
 | 4.0230     | 3.9474          | 0     |
+| 3.8580     | 3.8982          | 1     |
+| 3.7757     | 3.8721          | 2     |
+| 3.7149     | 3.8489          | 3     |
+| 3.6640     | 3.8343          | 4     |
+| 3.6210     | 3.8152          | 5     |
+| 3.5796     | 3.8088          | 6     |
+| 3.5429     | 3.8038          | 7     |
+| 3.5061     | 3.7967          | 8     |
+| 3.4753     | 3.7980          | 9     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1664130319.b847084d5e3f.67.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:949d722245d0c296dc18402ebc25f42b7202fe582c30ebb5b20e0328a25b79ec
-size 891164
+oid sha256:102555006dde7e32fcab6a3daedd9e1b4953c68910bccca874f9ca05d4f965a2
+size 891776

logs/validation/events.out.tfevents.1664130386.b847084d5e3f.67.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2274e4d882d22865be3d6a3ba6a5a8f40a249bc53d86b3cb9d25ed57c714b122
-size 194
+oid sha256:0e336d1775231c3f1446bd9aa2e9268b29760e39ad62300f60f457a5a10d12c8
+size 1598

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db92ec17abc583b958573e28ef3a53f2bd3485c944afef985b4b6bdb95e65606
+oid sha256:10d4bfe09f2b302dd0acb09cc1cf3d746d45e5052ea6079c74033cbf6344c7ef
 size 327745496