End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.8989
+- Loss: 4.0107
 
 ## Model description
 
@@ -34,21 +34,21 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 5e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3.0
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.7931        | 1.0   | 1869 | 2.9649          |
-| 2.5928        | 2.0   | 3738 | 2.9091          |
-| 2.5501        | 3.0   | 5607 | 2.8989          |
+| 4.7831        | 1.0   | 865  | 4.2478          |
+| 4.1995        | 2.0   | 1730 | 4.0627          |
+| 4.0165        | 3.0   | 2595 | 4.0107          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96c51e9613466050d353aee6d34da66e75990dff37837fa8414be93c5743ff50
+oid sha256:2466fb0c97b606dc8a76aa25f4109054897f08b11ada6727362cdd48c3a27173
 size 327657928

runs/Apr17_01-20-45_AnnMacBook-Pro.local/events.out.tfevents.1713288057.AnnMacBook-Pro.local.1045.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4297436a842568efd62298c63b1d0e0c16532c5af1e8c0233c8261611ee20043
-size 6583
+oid sha256:b5da5ba4ea1cc7347c16da4c3ac0001d1517e5271083aa0f5dafe41e59d7011d
+size 7208

runs/Apr17_01-20-45_AnnMacBook-Pro.local/events.out.tfevents.1713290677.AnnMacBook-Pro.local.1045.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5020be3556a0ca31702df1fcdbd3aeb21b37ef6ae137cb9f3638c7dc60163e1b
+size 359