Training in progress epoch 3

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: 3.7804
-- Validation Loss: 3.6243
-- Epoch: 2
+- Train Loss: 3.7072
+- Validation Loss: 3.5896
+- Epoch: 3
 
 ## Model description
 
@@ -45,6 +45,7 @@ The following hyperparameters were used during training:
 | 4.2103     | 3.8318          | 0     |
 | 3.9016     | 3.7030          | 1     |
 | 3.7804     | 3.6243          | 2     |
+| 3.7072     | 3.5896          | 3     |
 
 
 ### 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:c4cb51940a39202030222fa17fcc462fef2c7150373bfb6d37a35cb61a0976d5
-size 958137
+oid sha256:c0808891938be8d969e6d925cb83c5ac2c9f15ffb18d803b260bf92b7bc64fe1
+size 958205

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0e6a262e4897b3938163ab458cae53d21147d56bcc457c273240005f99eb799
-size 506
+oid sha256:72ad430bbd65f195920223c8dbcb3c9a33b1e40c05ddfdac18fcd7afbd5207e3
+size 662

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c36b035e908af0faa828d2f6690ed76d3bd3d0a735daf07295a8f78d16bba1e
+oid sha256:fdb1c99faa1e8ddf226bf230cac48f52f9fc87a85c4fd3fb8d609e10e2aa6946
 size 327745496