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: 3.9016
-- Validation Loss: 3.7030
-- Epoch: 1
+- Train Loss: 3.7804
+- Validation Loss: 3.6243
+- Epoch: 2
 
 ## Model description
 
@@ -44,6 +44,7 @@ The following hyperparameters were used during training:
 |:----------:|:---------------:|:-----:|
 | 4.2103     | 3.8318          | 0     |
 | 3.9016     | 3.7030          | 1     |
+| 3.7804     | 3.6243          | 2     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1677528702.c85f1f2dca13.1180.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc1b58e2b90bae254d2474d9761cdddb0c0acb8cbbd097585f7723ee4c8b6192
-size 958069
+oid sha256:c4cb51940a39202030222fa17fcc462fef2c7150373bfb6d37a35cb61a0976d5
+size 958137

logs/validation/events.out.tfevents.1677528776.c85f1f2dca13.1180.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53e971143ca1acb91ebede263717aee051048e457e4721a59a0e895925a72778
-size 350
+oid sha256:a0e6a262e4897b3938163ab458cae53d21147d56bcc457c273240005f99eb799
+size 506

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f03fa513e6edc2e8fc64e9f99e08b408ae2f3c96557e556f129c8fb0e50fd23c
+oid sha256:9c36b035e908af0faa828d2f6690ed76d3bd3d0a735daf07295a8f78d16bba1e
 size 327745496