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: 3.7802
-- Validation Loss: 3.6283
-- Epoch: 2
+- Train Loss: 3.7044
+- Validation Loss: 3.5885
+- Epoch: 3
 
 ## Model description
 
@@ -45,6 +45,7 @@ The following hyperparameters were used during training:
 | 4.2091     | 3.8246          | 0     |
 | 3.9001     | 3.6943          | 1     |
 | 3.7802     | 3.6283          | 2     |
+| 3.7044     | 3.5885          | 3     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1678035374.93e6156f4d8a.591.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fea238eb646efedb0615784d861a6439421b167cc7422857901dde24512079a7
-size 958137
+oid sha256:ed0d1817be1fcecfa3766443bd9d8d1d535f0d7b77d6092a5494d96923505c36
+size 958205

logs/validation/events.out.tfevents.1678035458.93e6156f4d8a.591.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fcbff1db59e82b9198cd13e95d2251c1c283ae1856a33f16c3c2774b01dc992
-size 506
+oid sha256:ae97e92a2e23f5479c82b444d30b9edc5ed77ec50aa47f8aa29513597e43b85b
+size 662

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19d3fb7e6f688c3e86ee357f760034924916d856a3a1a556ce9967bc4b2303cb
+oid sha256:00259230411e9da89460809296a3260c27a9ab52cb24eea362c42292115508d3
 size 327745496