Training in progress epoch 34

README.md

@@ -15,9 +15,9 @@ 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: 2.4184
-- Validation Loss: 3.0449
-- Epoch: 33
+- Train Loss: 2.3973
+- Validation Loss: 3.0265
+- Epoch: 34
 
 ## Model description
 
@@ -77,6 +77,7 @@ The following hyperparameters were used during training:
 | 2.4613     | 3.0414          | 31    |
 | 2.4394     | 3.0331          | 32    |
 | 2.4184     | 3.0449          | 33    |
+| 2.3973     | 3.0265          | 34    |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1713025433.Tianissimo-Laptop.639.4.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b75fa886a100cff814b30ec3e0c909454e2edd4640ba063b8f210a7b5a24d151
-size 971282
+oid sha256:a4b53af7d060c59c1c96ad2c49d60d2897ab124e293a51668c1990b55472c08c
+size 971350

logs/validation/events.out.tfevents.1713025911.Tianissimo-Laptop.639.5.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85c54742d96c01107bed8aaa9f3fd637196bdd3486d756de5ad3e5a5140a9bd7
-size 5412
+oid sha256:d62dbb0c2992eb06fa91f83642e1bf578f8127fcf237b14de27b428e990e5539
+size 5569

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1476fa908c3fbcea361528f57812a1f115325e7e6a915d246ae251f05d2d8362
+oid sha256:3352606d11780f680b6c41932d319d67bac03e16a81b9da71fde57f49c64e199
 size 327745472