Training in progress epoch 17

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: 3.2511
-- Validation Loss: 3.5030
-- Epoch: 16
+- Train Loss: 3.2269
+- Validation Loss: 3.5071
+- Epoch: 17
 
 ## Model description
 
@@ -59,6 +59,7 @@ The following hyperparameters were used during training:
 | 3.3039     | 3.4969          | 14    |
 | 3.2783     | 3.4997          | 15    |
 | 3.2511     | 3.5030          | 16    |
+| 3.2269     | 3.5071          | 17    |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1678035374.93e6156f4d8a.591.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53771d55811030e58815ed65ba6f4c5ad265233f87f499397b78d5d95dda7815
-size 959089
+oid sha256:4e0a03ec73a15fefc13fdfc3790d0f5457e3d75569ca62e11334c4766268a4c9
+size 959157

logs/validation/events.out.tfevents.1678035458.93e6156f4d8a.591.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f04c8aafc18b99e99f7d3183f816d06861001e46268325f578c30f101eaf1d57
-size 2690
+oid sha256:1e714c413fee7a4f04b0578d09b2fff57bb26bc2a730a51252c1219e91a502c4
+size 2846

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57f3f1bdd11989e22879295015cef7312fe2b2835e85819651c15b25a346f96b
+oid sha256:2c78149d279705cd843954bb050f191b2da828ec938178d3cff41b98ccfbbc5b
 size 327745496