Training in progress epoch 48

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: 2.1625
-- Validation Loss: 3.0436
-- Epoch: 47
+- Train Loss: 2.1466
+- Validation Loss: 3.0289
+- Epoch: 48
 
 ## Model description
 
@@ -91,6 +91,7 @@ The following hyperparameters were used during training:
 | 2.1949     | 3.0598          | 45    |
 | 2.1785     | 3.0490          | 46    |
 | 2.1625     | 3.0436          | 47    |
+| 2.1466     | 3.0289          | 48    |
 
 
 ### 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 sha256:32ff92cd43a6552ce869620a63838491ba7682e349a5a770ebfe4b8588e374d4
-size 972234
+oid sha256:bfea8e345304d17d79bfbdee2aa0f6a8b9ba6484fc81f9a4ba1fb5882e874048
+size 972302

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18c617d006511b9e262344bf96e33ec4dcd267138a29302d00174cfcfcaa4e83
-size 7610
+oid sha256:4ba4da539e96d06e28103d5fe5beff1a5d739612b7cf27b3d8543e51ecc27c8e
+size 7767

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff474beaf6c289af3ef8c7822a2e8d1c099707a52879e05e6eb449db22dea177
+oid sha256:50d6c0f46f440a56e2dc4765ee99df84616473ab4ecef70dea8c24e311e27ca5
 size 327745472