Training in progress epoch 42

README.md

@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 4.7204
-- Validation Loss: 6.7753
-- Epoch: 35
+- Train Loss: 4.0755
+- Validation Loss: 6.6162
+- Epoch: 42
 
 ## Model description
 
@@ -78,6 +78,13 @@ The following hyperparameters were used during training:
 | 4.8658     | 6.8038          | 33    |
 | 4.7845     | 6.8157          | 34    |
 | 4.7204     | 6.7753          | 35    |
+| 4.6609     | 6.7670          | 36    |
+| 4.5092     | 6.7305          | 37    |
+| 4.4266     | 6.7136          | 38    |
+| 4.3334     | 6.6761          | 39    |
+| 4.1928     | 6.6554          | 40    |
+| 4.1157     | 6.6311          | 41    |
+| 4.0755     | 6.6162          | 42    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44ff0c6009b2acf23b7c4a8b66d19875f0e51fcf452e09f5620e3ec6ed3baa50
+oid sha256:0061bf5e78e35a9d5e2071917cc1302f90be6b6912b7fb7513b9cb73c530e8e2
 size 351244368