Training in progress epoch 4

README.md

@@ -14,9 +14,9 @@ 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: 3.7072
-- Validation Loss: 3.5896
-- Epoch: 3
+- Train Loss: 3.6501
+- Validation Loss: 3.5631
+- Epoch: 4
 
 ## Model description
 
@@ -46,6 +46,7 @@ The following hyperparameters were used during training:
 | 3.9016     | 3.7030          | 1     |
 | 3.7804     | 3.6243          | 2     |
 | 3.7072     | 3.5896          | 3     |
+| 3.6501     | 3.5631          | 4     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1677528702.c85f1f2dca13.1180.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0808891938be8d969e6d925cb83c5ac2c9f15ffb18d803b260bf92b7bc64fe1
-size 958205
+oid sha256:2ba222e6a88ab72e02fe294bc5b3bfefae7a686f97f1d4635a5744cbdf8f5424
+size 958273

logs/validation/events.out.tfevents.1677528776.c85f1f2dca13.1180.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72ad430bbd65f195920223c8dbcb3c9a33b1e40c05ddfdac18fcd7afbd5207e3
-size 662
+oid sha256:5043c9710de9d4b482c764104f0df55c51ccf0f86b55fca63fb2d481fd0f4396
+size 818

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdb1c99faa1e8ddf226bf230cac48f52f9fc87a85c4fd3fb8d609e10e2aa6946
+oid sha256:1e975c9517acb4a4cc6c3bd2f46a35371e7feec112cc9ca70f3119296949f085
 size 327745496