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: 0.4145
+- Loss: 0.9874
 
 ## Model description
 
@@ -40,22 +40,15 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 1    | 0.6217          |
-| No log        | 2.0   | 2    | 0.4846          |
-| No log        | 3.0   | 3    | 0.4594          |
-| No log        | 4.0   | 4    | 0.4476          |
-| No log        | 5.0   | 5    | 0.4384          |
-| No log        | 6.0   | 6    | 0.4307          |
-| No log        | 7.0   | 7    | 0.4243          |
-| No log        | 8.0   | 8    | 0.4194          |
-| No log        | 9.0   | 9    | 0.4161          |
-| No log        | 10.0  | 10   | 0.4145          |
+| 1.7585        | 1.0   | 720  | 1.1284          |
+| 1.2462        | 2.0   | 1440 | 1.0144          |
+| 1.1005        | 3.0   | 2160 | 0.9874          |
 
 
 ### Framework versions

runs/Apr01_05-11-34_bf6476b9fe27/events.out.tfevents.1711948312.bf6476b9fe27.2340.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0564d93bc35d07616b3777500da81e563f883b3c9eea466a659f2a457ead11c
-size 6548
+oid sha256:e949a339912f89fa6a47e0e8b8db6508df645c14068d14edebcb00a2fcc8a721
+size 6902