Training completed for 3@lr:0.0005!

README.md

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [ml6team/gpt2-small-german-finetune-oscar](https://huggingface.co/ml6team/gpt2-small-german-finetune-oscar) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.2704
+- Loss: 4.4805
 
 ## Model description
 
@@ -33,19 +33,21 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
+- learning_rate: 0.0005
 - 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: 1
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 4.8197        | 1.0   | 210  | 4.2704          |
+| 4.4964        | 1.0   | 210  | 4.2323          |
+| 3.4962        | 2.0   | 420  | 4.2861          |
+| 2.5871        | 3.0   | 630  | 4.4805          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:888293497ada01a28c2c9c187c190faf3a1ec9960f68c691ac9d65719847e869
+oid sha256:7c5bece9bd08a867f6a81e4507b0866f7415859a2b38cd1c279969a77bfe2158
 size 497774208

runs/Feb21_21-23-34_7ae86bb689ec/events.out.tfevents.1708550623.7ae86bb689ec.167.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:798d3e96d1c83318f9b0ce528e6ccf8765ff86f66f075c4cf682ebde47bf5ab0
+size 138535

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8faab9c9f86b2774c660512c42cadc8fd375d651f1c46e4de54e3f1a227a2f1
+oid sha256:cf84a81cd823c6c6144fcbfa203d262f2691ac3d4fc6b7445c646cb19ca3fd90
 size 4920