Training in progress epoch 2

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: 3.1607
-- Validation Loss: 3.0962
-- Epoch: 1
+- Train Loss: 3.1005
+- Validation Loss: 3.0664
+- Epoch: 2
 
 ## Model description
 
@@ -44,6 +44,7 @@ The following hyperparameters were used during training:
 |:----------:|:---------------:|:-----:|
 | 3.2907     | 3.1500          | 0     |
 | 3.1607     | 3.0962          | 1     |
+| 3.1005     | 3.0664          | 2     |
 
 
 ### 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 sha256:886586eb96b5948ced36e1cec54541ebd6cf7181fc3a77a7fa70bdcc51c20e98
-size 7214156
+oid sha256:a7ff653909227ee4b41132ce4a564c7d1df9ef8d3fdeea0e40702ca77877b1b5
+size 7214224

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac8f57f6eefdb61fe943201427aa00d6796e977e6af2293b6b133e538a078779
-size 350
+oid sha256:f6c47bec090b6d77665bb647da6e3738bcc64aa1261f08464d79a7ff7485cf3d
+size 507

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d797fd25dc191250b518d15462b6e97d5e708926b37d91958c2c6df6cd07680
+oid sha256:7e58152ce587da88476208ceb16420eedf3d130a7b459e0f0716e9a77c4afd87
 size 327744824