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: 3.3769
-- Validation Loss: 3.2633
-- Epoch: 2
+- Train Loss: 3.3345
+- Validation Loss: 3.2376
+- Epoch: 3
 
 ## Model description
 
@@ -45,6 +45,7 @@ The following hyperparameters were used during training:
 | 3.5754     | 3.3649          | 0     |
 | 3.4385     | 3.3004          | 1     |
 | 3.3769     | 3.2633          | 2     |
+| 3.3345     | 3.2376          | 3     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1683022044.n4u5u9iqtn.316.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0f4a044f7a1ae6632bb04f10afa9af4ea8268b3811ff85a77aafafc9c616afe
-size 890777
+oid sha256:bc843c39cf27d8a679ea59f11c6c59c657180716cd94d7f418c46636c20408e5
+size 890845

logs/validation/events.out.tfevents.1683023524.n4u5u9iqtn.316.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b1a1f306b11237e5369dd87608ad50d5503bd5edcafe40389f878a3a08e534b
-size 509
+oid sha256:f0b139db48d50daf8ebd4b3eb80d1229dfef2542c69e4d7ab5551955a3b216b6
+size 666

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8eb20da1ed4a2af0d7220f7d7e83c2165b3c2c10287a5cac2cce972147ab144d
+oid sha256:1aaf6f9dfde5c0634f53eea7ca6eca430ec3d811790599a5cf0b0cc0ae1e71b9
 size 327745472