Training in progress epoch 16

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: 2.9245
-- Validation Loss: 3.1529
-- Epoch: 15
+- Train Loss: 2.8862
+- Validation Loss: 3.1404
+- Epoch: 16
 
 ## Model description
 
@@ -59,6 +59,7 @@ The following hyperparameters were used during training:
 | 3.0079     | 3.1826          | 13    |
 | 2.9651     | 3.1590          | 14    |
 | 2.9245     | 3.1529          | 15    |
+| 2.8862     | 3.1404          | 16    |
 
 
 ### 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:b0c383511250a1ef26c4a6689cd900e8e09ff04d826dfad04de559d74f24c218
-size 970058
+oid sha256:88e603359d5e6e9a61ab9684f90620c388df01bc457c141a1fec9fe4e92478d1
+size 970126

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:a0c42da75c76c1cbc08c45bb33dd282fa202ef3dc2fb58fa50ae41a0565ec03f
-size 2586
+oid sha256:953aae023f71385789963aed8afaa16ba887cd5156ba95918a10fd3d7212f64b
+size 2743

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d16f08aedd70ac7f81cb40fc80507547b887c145316540c0dbda07841c44452
+oid sha256:49cee0d9fde9cdbf460a8cc846761a0d4578bad53c76fddb8ced06a668a53fff
 size 327745472