Training in progress epoch 2

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: 3.5359
-- Validation Loss: 3.5225
-- Epoch: 1
+- Train Loss: 3.3503
+- Validation Loss: 3.3952
+- Epoch: 2
 
 ## Model description
 
@@ -45,6 +45,7 @@ The following hyperparameters were used during training:
 |:----------:|:---------------:|:-----:|
 | 3.8735     | 3.7005          | 0     |
 | 3.5359     | 3.5225          | 1     |
+| 3.3503     | 3.3952          | 2     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1713002710.Tianissimo-Laptop.14085.4.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb88deaf02abe514d3798aa6a609b41f15181b73f831db375ca494f41f4c37d4
-size 984927
+oid sha256:9d5f59c4aeb241f5beca72ecbac48daa00c7181e5537313a06dc19aac89763e7
+size 984995

logs/validation/events.out.tfevents.1713003384.Tianissimo-Laptop.14085.5.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:175a7da8a2d4fc6b5d0f109b03a578b7d9c8e828c39295a037a56245ad3f9921
-size 388
+oid sha256:1529dade51b348668f9302d12a2b49df437cde7ba3bc20a5b13fe478087bb701
+size 544

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bd597d61134b4a592c4a6e745091f2250c5efda893b2899571efc4bb80d0a18
+oid sha256:708bbd7f02ab88a2d30d3e1b9ab0140b079e844cd3d45d7ed67cf1b1b50e17d6
 size 327745472