Model save

README.md

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/codebert-base](https://huggingface.co/microsoft/codebert-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 10.1658
+- Loss: 8.7942
 
 ## Model description
 
@@ -45,9 +45,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 5    | 13.8406         |
-| No log        | 2.0   | 10   | 11.1498         |
-| No log        | 3.0   | 15   | 10.1658         |
+| No log        | 1.0   | 5    | 12.0574         |
+| No log        | 2.0   | 10   | 9.6990          |
+| No log        | 3.0   | 15   | 8.7942          |
 
 
 ### Framework versions

config.json

@@ -12,6 +12,7 @@
   "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
+  "is_decoder": true,
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
   "model_type": "roberta",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5de2523c6b8d97e6832fc1b29efddad5f7bfd4ed5655bbe6a5cf95f619aff769
+oid sha256:d3023329406183d1d4edd47bcbd535ef5406883740192bd462ee780271f07397
 size 498813948