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: 3.6347
+- Loss: 2.9394
 
 ## Model description
 
@@ -46,9 +46,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 125  | 3.6471          |
-| No log        | 2.0   | 250  | 3.6365          |
-| No log        | 3.0   | 375  | 3.6347          |
+| No log        | 1.0   | 177  | 2.9673          |
+| No log        | 2.0   | 354  | 2.9395          |
+| 3.1294        | 3.0   | 531  | 2.9394          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8e9164fc6051223417bfe18988418bab4dcced42e06e27654279317693b9e50
+oid sha256:a1c646328816d4815451c7f2eca91b113097e0442d898d7111b8cf54f08f6744
 size 327657928

runs/Jun17_01-09-39_e5d34939601d/events.out.tfevents.1718586597.e5d34939601d.3802.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d5b810ff4de38ab0b04b1e18b544cf918d98c9816f29b8b5529a9bb4be6fd4d
-size 5942
+oid sha256:9e70d0ecec0eaad0c8071c52898ecc49cb0359a3e2b3eba7e65d306a96d92b15
+size 6567

runs/Jun17_01-09-39_e5d34939601d/events.out.tfevents.1718586745.e5d34939601d.3802.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5960452d5489e4bc6d7ffc5e21168a92ef6a2ea538325e8315966469af5cd41
+size 359