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 [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0944
+- Loss: 0.0734
 
 ## Model description
 
@@ -42,16 +42,18 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant_with_warmup
-- num_epochs: 3
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.5546        | 1.0   | 125  | 0.5135          |
-| 0.1353        | 2.0   | 250  | 0.1289          |
-| 0.1044        | 3.0   | 375  | 0.0944          |
+| 0.4809        | 1.0   | 125  | 0.3920          |
+| 0.1042        | 2.0   | 250  | 0.0983          |
+| 0.0846        | 3.0   | 375  | 0.0799          |
+| 0.0761        | 4.0   | 500  | 0.0739          |
+| 0.0763        | 5.0   | 625  | 0.0734          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f4c28a56210c0d157e9f2fe5494a0c49e9c1d719180feda33ad64c43e622c37
+oid sha256:c16796de9aa6e54f0eccb5fe62d8d9cb8fd74a72cf30463540cbb1342d319b19
 size 441688704