Training in progress epoch 0

README.md

@@ -14,8 +14,8 @@ 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: 3.3197
-- Validation Loss: 3.7701
+- Train Loss: 3.3277
+- Validation Loss: 3.7689
 - Epoch: 0
 
 ## Model description
@@ -42,7 +42,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 3.3197     | 3.7701          | 0     |
+| 3.3277     | 3.7689          | 0     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1652677088.2034682a36f5.116.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84aeb9e214f4555e755f9698e4cadfba4da69ab64889536cc1171240369e8a83
+size 1201155

logs/validation/events.out.tfevents.1652677459.2034682a36f5.116.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ed250513113d26a394514afb2afabf1be0d90300fa4ca5771782886cd443054
+size 193

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3709cecea1ca1d8604cf4e895141e6255747f0942d85d3dac6f5f135c6c5db0c
+oid sha256:6c9fdf529cbdb72f66d63735ba1547232e659319bc2ab7b3d8f40f797af53bce
 size 327745496