Training in progress epoch 21

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: 2.7497
-- Validation Loss: 3.1036
-- Epoch: 20
+- Train Loss: 2.7186
+- Validation Loss: 3.0859
+- Epoch: 21
 
 ## Model description
 
@@ -64,6 +64,7 @@ The following hyperparameters were used during training:
 | 2.8147     | 3.1075          | 18    |
 | 2.7814     | 3.1077          | 19    |
 | 2.7497     | 3.1036          | 20    |
+| 2.7186     | 3.0859          | 21    |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1713025433.Tianissimo-Laptop.639.4.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dde9e45f1e4ea46ac75632fbcd1960f2a95a3372f10bf6e7d8ab8b680d64beb4
-size 970398
+oid sha256:186bf0241cfd5c0adda25e44482a883f41b3557f3f3b52b1ca64e5d6805e8474
+size 970466

logs/validation/events.out.tfevents.1713025911.Tianissimo-Laptop.639.5.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95fa21f453dd41df0c3f3594d6327bce9290230073e3b17dc67c23ebfe4fc617
-size 3371
+oid sha256:419460203bc564eded146911f3d02ebd8d3d0fc6e099680d9b072f670c79fe66
+size 3528

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbd4c985d4ed0ba166c1c356c0184d9f15d46965dcda7a046485b21dee1f547b
+oid sha256:ff72e5c1659553127706a9d4fd139ee5177226bb031b29f07414e12af9de1e82
 size 327745472