Training in progress epoch 33

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: 1.8750
-- Validation Loss: 4.3550
-- Epoch: 32
+- Train Loss: 1.8480
+- Validation Loss: 4.3697
+- Epoch: 33
 
 ## Model description
 
@@ -76,6 +76,7 @@ The following hyperparameters were used during training:
 | 1.9373     | 4.3288          | 30    |
 | 1.9159     | 4.3262          | 31    |
 | 1.8750     | 4.3550          | 32    |
+| 1.8480     | 4.3697          | 33    |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1711718173.e7f3963a7819.156.2.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f9d45b86cb1cea6f6a149af9a80f46cb8746f7415ee520cf9e00548d4db9212
-size 968106
+oid sha256:49c736ffbc0460e8fd2094ad2fe0b431265c2f61638857d6b4002d85aab3ef84
+size 968174

logs/validation/events.out.tfevents.1711718177.e7f3963a7819.156.3.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c4f531ebe2f749f4c2cad985adcd0844d1b7206a85b51e5b58513e2b8dcf5d6
-size 5224
+oid sha256:36776353a10c0d28bb7cd22ef56cffd5cc0e2c56fe70385a3ca5d386e3d3170a
+size 5380

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bad858a628407f4a1321f2a4e494e10996c2f4e8b682826fa0b22a86e44c22a9
+oid sha256:5e17129a869afd702070d8028cc05ebc7e5b437f8c41fb0163f955918d812e82
 size 327745472