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: 2.4196
+- Loss: 2.3429
 
 ## Model description
 
@@ -46,9 +46,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
-| 2.4697        | 1.0   | 21105 | 2.5521          |
-| 2.3148        | 2.0   | 42210 | 2.4484          |
-| 2.2695        | 3.0   | 63315 | 2.4196          |
+| 2.5071        | 1.0   | 21455 | 2.4640          |
+| 2.3554        | 2.0   | 42910 | 2.3673          |
+| 2.3024        | 3.0   | 64365 | 2.3429          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbc0232d11513481afd51ed0c62ae9dd5064e2ab1f0b2f199ee48b3f44f3c354
+oid sha256:232e24d0bb96fec62f9c49936ce2138e73b4732f9469d818d99b7a7421817e09
 size 327657928

runs/Apr06_16-29-20_PCLAB/events.out.tfevents.1712392161.PCLAB.1888.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b28a39922912350db063a5e70bf4725aab0f1db14f8f829ddbbdaec0740b14ff
-size 32923
+oid sha256:08a34fca91ad8be729d9bd8e6ea03e716d8f00a385bef5fbd8358b4d18d6ec2c
+size 33559

runs/Apr06_16-29-20_PCLAB/events.out.tfevents.1712409017.PCLAB.1888.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f78093180f4e8ac7a5834b6b49fc5b51094f34e27ea4538c061f8f2b0d2467b
+size 316