Training in progress epoch 2

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: 1.8442
-- Validation Loss: 1.5438
-- Epoch: 1
+- Train Loss: 1.5898
+- Validation Loss: 1.3760
+- Epoch: 2
 
 ## Model description
 
@@ -45,6 +45,7 @@ The following hyperparameters were used during training:
 |:----------:|:---------------:|:-----:|
 | 2.6143     | 1.9087          | 0     |
 | 1.8442     | 1.5438          | 1     |
+| 1.5898     | 1.3760          | 2     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1706272717.a084be297aa3.270.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17370f7f5e0d07774856e9f7986c6a7db109751bdfdedf6bee79cbf74e8f7a7b
-size 965998
+oid sha256:19e21ec01343c340f78ca7390e5c732bc804104199538a20a8cab8ec8a8de820
+size 966066

logs/validation/events.out.tfevents.1706272784.a084be297aa3.270.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff6172e36686098ccc0cbd8acf596f28ca8ee3ea2970d105f7f29eb49f619832
-size 387
+oid sha256:f98735394bddd9fff7f2d1b9d393c95e2c54ae277e62970ee56de8b797768a39
+size 543

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20fa195f0d4184b734b24815712a09b19b7f0725f0627ec83d915314fbf12b14
+oid sha256:6a1116c28d4d8760a4b03ef246629bc888940c766b50c97798fe72ba8bdf841e
 size 327745472