Training in progress epoch 20

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: 2.7814
-- Validation Loss: 3.1077
-- Epoch: 19
+- Train Loss: 2.7497
+- Validation Loss: 3.1036
+- Epoch: 20
 
 ## Model description
 
@@ -63,6 +63,7 @@ The following hyperparameters were used during training:
 | 2.8493     | 3.1245          | 17    |
 | 2.8147     | 3.1075          | 18    |
 | 2.7814     | 3.1077          | 19    |
+| 2.7497     | 3.1036          | 20    |
 
 
 ### 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 sha256:7aea5e2629662dbe5cd12e5833753b87b8f3e014b86a3c86b6d5f2c4d1f77890
-size 970330
+oid sha256:dde9e45f1e4ea46ac75632fbcd1960f2a95a3372f10bf6e7d8ab8b680d64beb4
+size 970398

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:648f13192b0ef6db8dad6c1ef6b63f15a712ee7f2bf583fc0dd8337e09f828c7
-size 3214
+oid sha256:95fa21f453dd41df0c3f3594d6327bce9290230073e3b17dc67c23ebfe4fc617
+size 3371

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae80900bbc57c040b3c831ceb3c86e9903c1cbc2d17fba03fa041aea932b0341
+oid sha256:fbd4c985d4ed0ba166c1c356c0184d9f15d46965dcda7a046485b21dee1f547b
 size 327745472