Training in progress epoch 24

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: 2.6608
-- Validation Loss: 3.0842
-- Epoch: 23
+- Train Loss: 2.6327
+- Validation Loss: 3.0561
+- Epoch: 24
 
 ## Model description
 
@@ -67,6 +67,7 @@ The following hyperparameters were used during training:
 | 2.7186     | 3.0859          | 21    |
 | 2.6890     | 3.0722          | 22    |
 | 2.6608     | 3.0842          | 23    |
+| 2.6327     | 3.0561          | 24    |
 
 
 ### 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 sha256:8c22fddac8465c8ce444636f245bd5ad11fa6a45637983b324dca124deb75e43
-size 970602
+oid sha256:96220e54d47d2cdb4e0c073301bf14ad84deb3c1a276aad3733199d383aceabf
+size 970670

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:b37d92b0398317ef5e3a5e14aaf48d580108a05797baeba2bedbe49b10fc3fb2
-size 3842
+oid sha256:d13ef9b20f8c468f0c0032d65032b76806f67d33a7c44df576e59af7456db527
+size 3999

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ec143d345cd6124f5c55642f75b751e3b218a9bfa61f913415d6d43177314b5
+oid sha256:6ad6d9381a81efd59baa8bb8d4792dc53be14943248fae9149320e79d7b537c4
 size 327745472