Training in progress epoch 6

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: 3.4803
-- Validation Loss: 3.4643
-- Epoch: 5
+- Train Loss: 3.4027
+- Validation Loss: 3.4068
+- Epoch: 6
 
 ## Model description
 
@@ -49,6 +49,7 @@ The following hyperparameters were used during training:
 | 3.6677     | 3.6006          | 3     |
 | 3.5681     | 3.5272          | 4     |
 | 3.4803     | 3.4643          | 5     |
+| 3.4027     | 3.4068          | 6     |
 
 
 ### 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 sha256:7e89eebc2c610583e4c2ee54a5d58de11e81d4e79a86c971d5ba636d9185ace6
-size 969378
+oid sha256:ca3e28416e4e8e3fa10f4ad72263a92eeca69c039a4925777ca66bc386ce6db9
+size 969446

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:b6674c5802a9c31d142b5b736363f953df8c449696353881735336b643da4842
-size 1016
+oid sha256:2b78919599e3fa21895846d7bc47c422966d65afbfe4c9eadb642f97d7223529
+size 1173

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d29f8da5f7b86170b971be988aa7200b8be0365660942fc934ae8cdf4efda64a
+oid sha256:44fbf372843dbcf579677346555ec8232fa96e9033ec9f9e446e3706e87fcadf
 size 327745472