Training in progress epoch 1

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: 4.2115
-- Validation Loss: 3.8231
-- Epoch: 0
+- Train Loss: 3.9010
+- Validation Loss: 3.6933
+- Epoch: 1
 
 ## Model description
 
@@ -43,6 +43,7 @@ The following hyperparameters were used during training:
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
 | 4.2115     | 3.8231          | 0     |
+| 3.9010     | 3.6933          | 1     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1678021991.9e351507b647.573.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:023b134d5724f49029562d630122e3820b5945f36b7a47e5d99cdd9bf331d962
-size 958001
+oid sha256:53b7339591bfa311b1445cd8f2079362295a28ed209df41116554087df1929bf
+size 958069

logs/validation/events.out.tfevents.1678022084.9e351507b647.573.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cab56a343ecbe2f528b536bb34342efb76b44988e3a47307c05e4f0b83d2cb23
-size 194
+oid sha256:39b9293f34f133bd0ba97614f35805264988c06f111044f77709aaaacc6cf54c
+size 350

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df9442dd436c86ba9f01ec93880f4016ce47208ebd7b0f58105cf94fbae2c54e
+oid sha256:aa5cc44410713121aa7abd270d4de8d8e1c0c81c99b9982c6361ec3391ebed78
 size 327745496