Training in progress epoch 3

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: 3.7841
-- Validation Loss: 3.7018
-- Epoch: 2
+- Train Loss: 3.6901
+- Validation Loss: 3.6474
+- Epoch: 3
 
 ## Model description
 
@@ -46,6 +46,7 @@ The following hyperparameters were used during training:
 | 4.2051     | 3.9133          | 0     |
 | 3.9132     | 3.7845          | 1     |
 | 3.7841     | 3.7018          | 2     |
+| 3.6901     | 3.6474          | 3     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1702556598.a1848e09f30f.211.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a60f180a0430d4ab4563fdff821d467e2347e3de0fcf135e732805602a7a38f3
-size 870199
+oid sha256:87e84e9c4e6c332ec1661c991736d5a2f28c68a28b80eee500b038cc163a9543
+size 870267

logs/validation/events.out.tfevents.1702557803.a1848e09f30f.211.2.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3778a4858b363773d5704ac2c387e7ecd9b7c67f6376d0a9c74ef7adb27dd28a
-size 544
+oid sha256:1424355a30817eb70b73a7af05a1ca0e34c47ef24fe9d9a07a134587e1d2209b
+size 701

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c544c54943315634452a99dbc4ea5e21e30acfed8f109443e0958447839d4c84
+oid sha256:ff251d1551cebf91cc12951a2521c9fad087973b86fce1cc62ba1a4d20e7dace
 size 327745472