Training in progress epoch 35

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: 2.3973
-- Validation Loss: 3.0265
-- Epoch: 34
+- Train Loss: 2.3764
+- Validation Loss: 3.0213
+- Epoch: 35
 
 ## Model description
 
@@ -78,6 +78,7 @@ The following hyperparameters were used during training:
 | 2.4394     | 3.0331          | 32    |
 | 2.4184     | 3.0449          | 33    |
 | 2.3973     | 3.0265          | 34    |
+| 2.3764     | 3.0213          | 35    |
 
 
 ### 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:a4b53af7d060c59c1c96ad2c49d60d2897ab124e293a51668c1990b55472c08c
-size 971350
+oid sha256:63c4eb645e5ddf26de8ad5319e6245b9f8b3b514c90db7d0870c5595483e1782
+size 971418

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:d62dbb0c2992eb06fa91f83642e1bf578f8127fcf237b14de27b428e990e5539
-size 5569
+oid sha256:a4bb9acce11454308361b705dba1bfcf0becfe47a55198d7edc593b9b4c028be
+size 5726

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3352606d11780f680b6c41932d319d67bac03e16a81b9da71fde57f49c64e199
+oid sha256:f102d277d608bd81552969854b9f6ef30ec29f11503886d04224facaeb58df80
 size 327745472