Model save

README.md

@@ -1,8 +1,8 @@
 ---
 license: mit
+base_model: gpt2
 tags:
 - generated_from_trainer
-base_model: gpt2
 model-index:
 - name: gpt2-evy
   results: []
@@ -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: 1.5376
+- Loss: 1.4186
 
 ## Model description
 
@@ -46,21 +46,21 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 4    | 1.8527          |
-| No log        | 2.0   | 8    | 1.7549          |
-| No log        | 3.0   | 12   | 1.6785          |
-| No log        | 4.0   | 16   | 1.6300          |
-| No log        | 5.0   | 20   | 1.6319          |
-| No log        | 6.0   | 24   | 1.5804          |
-| No log        | 7.0   | 28   | 1.5599          |
-| No log        | 8.0   | 32   | 1.5557          |
-| No log        | 9.0   | 36   | 1.5414          |
-| No log        | 10.0  | 40   | 1.5376          |
+| No log        | 1.0   | 9    | 1.7574          |
+| No log        | 2.0   | 18   | 1.5780          |
+| No log        | 3.0   | 27   | 1.5400          |
+| No log        | 4.0   | 36   | 1.4815          |
+| No log        | 5.0   | 45   | 1.4667          |
+| No log        | 6.0   | 54   | 1.4414          |
+| No log        | 7.0   | 63   | 1.4372          |
+| No log        | 8.0   | 72   | 1.4265          |
+| No log        | 9.0   | 81   | 1.4201          |
+| No log        | 10.0  | 90   | 1.4186          |
 
 
 ### Framework versions
 
-- Transformers 4.40.1
+- Transformers 4.40.2
 - Pytorch 2.2.1+cu121
 - Datasets 2.19.1
 - Tokenizers 0.19.1

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 50256,
   "eos_token_id": 50256,
-  "transformers_version": "4.40.1"
+  "transformers_version": "4.40.2"
 }