Training in progress epoch 4

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: 3.6677
-- Validation Loss: 3.6006
-- Epoch: 3
+- Train Loss: 3.5681
+- Validation Loss: 3.5272
+- Epoch: 4
 
 ## Model description
 
@@ -47,6 +47,7 @@ The following hyperparameters were used during training:
 | 3.9271     | 3.7983          | 1     |
 | 3.7845     | 3.6781          | 2     |
 | 3.6677     | 3.6006          | 3     |
+| 3.5681     | 3.5272          | 4     |
 
 
 ### 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 sha256:287f47772a063a51b12bcc5ef8f82294fe08c1766e4e9855957e51bea593a2cc
-size 969242
+oid sha256:8b787b88e4a89063a1eff75dff5461302d2c9ab08ccc39485ebef58076efd240
+size 969310

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:a3cf01fcec1028361aa7eb71cf04b236e25c5f16785d7f095f7e6fc58d976e20
-size 702
+oid sha256:3471a24695a5029cc32dcf57d00a524d1098a0408135352b1292a49491e7a56c
+size 859

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8389d089ed8baaf3e2ea77f17adf23334a04abd902651985f329bab5e7197e0
+oid sha256:529cb2eb4cd376aecefb5f156bfce9951a1b84daaeb2278ab49f8d85f638529d
 size 327745472