Training in progress epoch 3

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: 3.7764
-- Validation Loss: 4.2318
-- Epoch: 0
+- Train Loss: 3.4079
+- Validation Loss: 3.9863
+- Epoch: 3
 
 ## Model description
 
@@ -44,6 +44,9 @@ The following hyperparameters were used during training:
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
 | 3.7764     | 4.2318          | 0     |
+| 3.6181     | 4.1041          | 1     |
+| 3.5128     | 4.0419          | 2     |
+| 3.4079     | 3.9863          | 3     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1711717598.e7f3963a7819.156.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f980e1b98a73a55076bd6534f4703010ec78ac155776a8a29c3fdaace7880472
-size 965930
+oid sha256:76e9f798b1b534b08ba208eabac15bff9cf38f10610c318195725114181f5c89
+size 966134

logs/validation/events.out.tfevents.1711717651.e7f3963a7819.156.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11972e256adc4b3a843242fb85abc257371de5a4f1e20eb9aa15f50e583c5182
-size 231
+oid sha256:a91c14a489d35314f1ed0840a22d05eaf16f5b7eb667be653285360e5f602c48
+size 696

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0dbc6808b337ff0d9d94c2e572227fec73200853e7126cae6e178668f5c7f6e
+oid sha256:47726160c266e340a2d3b37ab7f31aa8065c280a5a6a895babe770c035669640
 size 327745472