Training in progress epoch 40

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: 2.2992
-- Validation Loss: 3.0302
-- Epoch: 39
+- Train Loss: 2.2809
+- Validation Loss: 3.0305
+- Epoch: 40
 
 ## Model description
 
@@ -83,6 +83,7 @@ The following hyperparameters were used during training:
 | 2.3376     | 3.0359          | 37    |
 | 2.3181     | 3.0315          | 38    |
 | 2.2992     | 3.0302          | 39    |
+| 2.2809     | 3.0305          | 40    |
 
 
 ### 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 sha256:4d839c4a7d2bb4c9eb6288d2a12e76a8ea694cb2adb90cb6a40a1ee817c2a986
-size 971690
+oid sha256:d5bb20f0a65c1834f46970362e58c1d2fb83e73f20e6e518bc7c19b31c853f9d
+size 971758

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ee16b3240475367a9243b004669ca041d2c1724846bba4cf593cb42a108494a
-size 6354
+oid sha256:4dda123fbfe9b72ce364cecf542cf5cba71e18a49c6d7faecc5b3129b67ec7bd
+size 6511

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:240a325f2f9dbb9e1cee32066a369f8da684d17e1c9b11305a664818f41c1953
+oid sha256:e7bc6c3da8e8ea61a32a1f03a3ee13178b5c9fcd7bf56adee10d7dd8c9b101c7
 size 327745472