Training in progress epoch 39

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: 2.3181
-- Validation Loss: 3.0315
-- Epoch: 38
+- Train Loss: 2.2992
+- Validation Loss: 3.0302
+- Epoch: 39
 
 ## Model description
 
@@ -82,6 +82,7 @@ The following hyperparameters were used during training:
 | 2.3568     | 3.0363          | 36    |
 | 2.3376     | 3.0359          | 37    |
 | 2.3181     | 3.0315          | 38    |
+| 2.2992     | 3.0302          | 39    |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1713025433.Tianissimo-Laptop.639.4.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d597bd0822b3980c0ff9f4a3bc2f9771d2cdb1a102043e023b07a7c85054a98
-size 971622
+oid sha256:4d839c4a7d2bb4c9eb6288d2a12e76a8ea694cb2adb90cb6a40a1ee817c2a986
+size 971690

logs/validation/events.out.tfevents.1713025911.Tianissimo-Laptop.639.5.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1adb377734d228d673aa9995ac80eda1a0a3a88c22af6dfd25482a7f61253793
-size 6197
+oid sha256:3ee16b3240475367a9243b004669ca041d2c1724846bba4cf593cb42a108494a
+size 6354

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e69b297831d773d61e967a6f1951da524795404d7bb875953c83112f2031ae14
+oid sha256:240a325f2f9dbb9e1cee32066a369f8da684d17e1c9b11305a664818f41c1953
 size 327745472