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: 6.3882
+- Loss: 6.7301
 
 ## Model description
 
@@ -46,9 +46,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.7828        | 1.0   | 2334 | 6.6475          |
-| 2.4551        | 2.0   | 4668 | 6.3229          |
-| 2.251         | 3.0   | 7002 | 6.3729          |
+| 2.7896        | 1.0   | 2334 | 6.9630          |
+| 2.339         | 2.0   | 4668 | 6.7607          |
+| 2.1997        | 3.0   | 7002 | 6.6722          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:240995cbf046bb24187d2eb8fef9f88e5479c26a02993c354195da83dca8e40d
+oid sha256:3ae2b2ebcc3b4e9e46f49a1de0ddca3a200236e398acbcf94760cafe3107ad7f
 size 327657928

runs/Apr17_12-40-27_Cs-Mac/events.out.tfevents.1713328831.Cs-Mac.1261.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:492ed5284e2455198bef395a20f87073f2a5b412507eaeb057e4b641b5600fec
-size 8470
+oid sha256:d0b39bfa3737909b6e1c179409fa5b92d723b8a73d010d50fee2e46e47d9d5b5
+size 9095

runs/Apr17_12-40-27_Cs-Mac/events.out.tfevents.1713335522.Cs-Mac.1261.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23766071813b93126ec753d939ee95d724d84902127ca19c5b13349b70da54c2
+size 359