Upload model

README.md

@@ -1,6 +1,4 @@
 ---
-license: mit
-base_model: gpt2
 tags:
 - generated_from_keras_callback
 model-index:
@@ -13,10 +11,10 @@ probably proofread and complete it, then remove this comment. -->
 
 # ingredients_compatibility_GPT2_S
 
-This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
+This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.1444
-- Validation Loss: 1.1261
+- Train Loss: 1.0598
+- Validation Loss: 1.0803
 - Epoch: 2
 
 ## Model description
@@ -43,9 +41,9 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 1.6923     | 1.2859          | 0     |
-| 1.2248     | 1.1706          | 1     |
-| 1.1444     | 1.1261          | 2     |
+| 1.1289     | 1.1003          | 0     |
+| 1.0880     | 1.0893          | 1     |
+| 1.0598     | 1.0803          | 2     |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2",
+  "_name_or_path": "Gracoy/ingredients_compatibility_GPT2_S",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f77f239cf595e1891c60f728f24b1bd097d99fc41b8edb19a201d5fea1dbf1f7
+oid sha256:9e1b874292da3cf071c99b02418f0c99df9c02f3e5cdea79225ac3d4ba8ffded
 size 370269264