Training in progress epoch 8

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: 3.1453
-- Validation Loss: 3.9197
-- Epoch: 7
+- Train Loss: 3.0984
+- Validation Loss: 3.9089
+- Epoch: 8
 
 ## Model description
 
@@ -51,6 +51,7 @@ The following hyperparameters were used during training:
 | 3.2678     | 3.9271          | 5     |
 | 3.2077     | 3.9197          | 6     |
 | 3.1453     | 3.9197          | 7     |
+| 3.0984     | 3.9089          | 8     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1711717598.e7f3963a7819.156.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83ed819a9769eeeedff1e932b6a70381b820a122eba00cd6b9d5123678644103
-size 966406
+oid sha256:783d5abb2e1247213a4166b4c8ac5f60caad4460a0a19c363fef53cd6e346158
+size 966474

logs/validation/events.out.tfevents.1711717651.e7f3963a7819.156.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc6c8ddfb6e1f339dcd73da150d34d2b45f1256b5f357774141f50cb33b7092a
-size 1316
+oid sha256:95a95c45d1e6455968eb5c98e9bf7c3a78f0180c95ebe3790621debdc07f685b
+size 1471

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:256e046e602af5a99d2a2dd1cf96c4e5ea90cacc47dcc51f5eef3f8550933d10
+oid sha256:e956a8174036d5cc06873b155e5bac34b6bc72c0acd5891a01a928577be08e7e
 size 327745472