Training in progress epoch 0

README.md

@@ -15,8 +15,8 @@ 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: 4.4000
-- Validation Loss: 4.1359
+- Train Loss: 4.1088
+- Validation Loss: 3.9258
 - Epoch: 0
 
 ## Model description
@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 4.4000     | 4.1359          | 0     |
+| 4.1088     | 3.9258          | 0     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1713025310.Tianissimo-Laptop.639.3.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c190a95b3dd0e44040c92abe7fbdaaea9dab56cc56776dbb47c9f6ef4a788891
+size 968972

logs/train/events.out.tfevents.1713025433.Tianissimo-Laptop.639.4.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14b4f5bc7cd310f08f2f1dbe1fdf92a249432da12b06cac18ed273779224354e
+size 969038

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fca0675d9409c5a77f654d608487f91fbd265207f7fd16b074530ff51afbd6fa
+size 232

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a15cad9037422154a5b2c2b9b1dea13530327706c89f34c64a12912707d23b01
+oid sha256:73b9e8ca75d3b22f17c019009cbaf79549c92f31c772410d51e7a58bcdad65b8
 size 327745472