Training in progress epoch 11

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: 3.4202
-- Validation Loss: 3.5090
-- Epoch: 10
+- Train Loss: 3.3915
+- Validation Loss: 3.5002
+- Epoch: 11
 
 ## Model description
 
@@ -53,6 +53,7 @@ The following hyperparameters were used during training:
 | 3.4848     | 3.5205          | 8     |
 | 3.4528     | 3.5129          | 9     |
 | 3.4202     | 3.5090          | 10    |
+| 3.3915     | 3.5002          | 11    |
 
 
 ### 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 sha256:00117fdd0b3307717fe60a53fa1d04c44df9947cd8b209459040abf7eab29848
-size 958681
+oid sha256:b21665d05ecdfa2dabe82a1202a04e29d0465c4a156c629c4cbb00c62892e737
+size 958749

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:709c8f9006868b1f89f8e9e4c0c64d1e5209518ff34c319e8ed40eed66433ffa
-size 1754
+oid sha256:6425edcb99b47f975d183f7e4dd2e2d9c78635c00286de9587017429f67b76d4
+size 1910

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e14a6a401f6e1cba9705afe2bd195174f5ac8f86c36ece092e69beb00be6ba4
+oid sha256:949f461e62cf9f18458d2bf66827a5be4d71d0dc720323ace136c104eb2aee52
 size 327745496