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: 3.2907
-- Validation Loss: 3.1500
-- Epoch: 0
+- Train Loss: 3.1607
+- Validation Loss: 3.0962
+- Epoch: 1
 
 ## Model description
 
@@ -43,6 +43,7 @@ The following hyperparameters were used during training:
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
 | 3.2907     | 3.1500          | 0     |
+| 3.1607     | 3.0962          | 1     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1651596636.93dc2b7f2684.33.2.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c1a52dbab0c3012971f3af6394aabaa18c00f3f1d5289a75801f08835de511c
-size 7214088
+oid sha256:886586eb96b5948ced36e1cec54541ebd6cf7181fc3a77a7fa70bdcc51c20e98
+size 7214156

logs/validation/events.out.tfevents.1651598324.93dc2b7f2684.33.3.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1686112a7631bed6369bb49d1c7fd26260e593ab745afea15036c5192cf9f61
-size 194
+oid sha256:ac8f57f6eefdb61fe943201427aa00d6796e977e6af2293b6b133e538a078779
+size 350

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8de3d93ef17644c1d8834229772531be6f6e034fc40c8adbe2686894be1d287
+oid sha256:6d797fd25dc191250b518d15462b6e97d5e708926b37d91958c2c6df6cd07680
 size 327744824