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: 5.7513
+- Loss: 0.5084
 
 ## Model description
 
@@ -44,14 +44,13 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 2
-- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 7.1619        | 1.0   | 256  | 5.7933          |
-| 6.2992        | 2.0   | 512  | 5.7513          |
+| 0.266         | 1.0   | 250  | 0.5155          |
+| 0.0461        | 2.0   | 500  | 0.5084          |
 
 
 ### Framework versions

runs/Dec26_12-18-09_4f87fa13cf4f/events.out.tfevents.1735215491.4f87fa13cf4f.23195.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0ecd9a28153c3b05537ac4c78b9e851d3c0f7dcf08b5def55bc0dd0d8bb9956
-size 6022
+oid sha256:0a9ec314435f2285f70edce96136b4421574a620529addb5086325f6b059de5c
+size 6647

runs/Dec26_12-18-09_4f87fa13cf4f/events.out.tfevents.1735215724.4f87fa13cf4f.23195.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85219975c29831aa1a7a2535922a4e8fb19fc70e6835ff72193d79e4bb647477
+size 359