Training in progress epoch 45

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: 1.5532
-- Validation Loss: 4.6394
-- Epoch: 44
+- Train Loss: 1.5164
+- Validation Loss: 4.6464
+- Epoch: 45
 
 ## Model description
 
@@ -88,6 +88,7 @@ The following hyperparameters were used during training:
 | 1.5981     | 4.5991          | 42    |
 | 1.5788     | 4.6276          | 43    |
 | 1.5532     | 4.6394          | 44    |
+| 1.5164     | 4.6464          | 45    |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1711718173.e7f3963a7819.156.2.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9dc3b1d26b4971d7169da5c50fc5b899ca00f21a365d9bc318f5b5e0e5cd683
-size 968922
+oid sha256:57091fdc9c936fd2eb76e8b6ee273df234e590464e04bce7e85c9e0243ee9bea
+size 968990

logs/validation/events.out.tfevents.1711718177.e7f3963a7819.156.3.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d729ae0c5effcd994cc825dd25d75c5bdd5101184c2bad7017011bbebccbd4f4
-size 7096
+oid sha256:19e13844047c8dc32464b5637e0a481cfc79ecc4037551063b3c0a0e12977aef
+size 7252

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dd1fa324bbe958806533fdca015a3bfe86ed6ba82218e4a7f2969ab7cabe127
+oid sha256:360c35120318c578c364a0ec086a2f336469a086bccad1fd8848675842547d1e
 size 327745472