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: 3.6445
+- Loss: 3.6439
 
 ## Model description
 
@@ -41,14 +41,15 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 3.0
+- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 3.761         | 1.0   | 2334 | 3.6677          |
-| 3.6486        | 2.0   | 4668 | 3.6473          |
-| 3.605         | 3.0   | 7002 | 3.6445          |
+| 3.7609        | 1.0   | 2334 | 3.6672          |
+| 3.6483        | 2.0   | 4668 | 3.6468          |
+| 3.6047        | 3.0   | 7002 | 3.6439          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c72de254194abdc82b8b0c645a491374b6303e9d67a35518828e800627ca58e9
+oid sha256:09303794cc504211a1798e1a48c7ef49bd06aae28b0008b656d7ba277d13d72d
 size 327657928