Training in progress epoch 0

README.md

@@ -15,8 +15,8 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 3.4825
-- Validation Loss: 2.5437
+- Train Loss: 2.4680
+- Validation Loss: 2.3857
 - Epoch: 0
 
 ## Model description
@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 3.4825     | 2.5437          | 0     |
+| 2.4680     | 2.3857          | 0     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1710467074.631c28982693.3409.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c64045ce95d034fb0a19ac8a7c2ba5228ab3a1f090a30f40e2a07922bda9528f
+size 1834984

logs/validation/events.out.tfevents.1710467774.631c28982693.3409.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:713c6637843ccd1729c1bca9454fdfed80db8705ddbd3a5f627e4b9116020dae
+size 231

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7040ee6842cf32a77a3b98c41ea249543bb6a96a44feadaf9e0a82f015e83e0
+oid sha256:3d10ed3deb5c99fe94ea4f09786af540c1e7cec4589a5bf76964ee8039a547ac
 size 497935440