End of training

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the recipe_nlg dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5084
+- Loss: 3.2698
 
 ## Model description
 
@@ -43,14 +43,22 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.266         | 1.0   | 250  | 0.5155          |
-| 0.0461        | 2.0   | 500  | 0.5084          |
+| 5.1949        | 1.0   | 250  | 4.0810          |
+| 4.1778        | 2.0   | 500  | 3.6780          |
+| 3.8053        | 3.0   | 750  | 3.5167          |
+| 3.5679        | 4.0   | 1000 | 3.4106          |
+| 3.4079        | 5.0   | 1250 | 3.3506          |
+| 3.279         | 6.0   | 1500 | 3.3068          |
+| 3.212         | 7.0   | 1750 | 3.2812          |
+| 3.104         | 8.0   | 2000 | 3.2761          |
+| 3.0673        | 9.0   | 2250 | 3.2732          |
+| 3.0507        | 10.0  | 2500 | 3.2698          |
 
 
 ### Framework versions

runs/Dec26_12-35-22_4f87fa13cf4f/events.out.tfevents.1735216524.4f87fa13cf4f.26541.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0836532aa2d2c83254f7c0fa80a5d14be2dd9fcc0530bf01e4b760564d4212f
-size 9879
+oid sha256:f1bcc5d9c1125c451913acd9b1a7bac428a159b6d3a956f7ccce91f4b5aa0870
+size 10504

runs/Dec26_12-35-22_4f87fa13cf4f/events.out.tfevents.1735217626.4f87fa13cf4f.26541.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14a31ca6f33e360732b71426608855fc0338ad86149734fd1cd20d49a09f45a3
+size 359