Model save

README.md

@@ -1,5 +1,7 @@
 ---
 library_name: transformers
+license: apache-2.0
+base_model: google-bert/bert-base-uncased
 tags:
 - generated_from_trainer
 metrics:
@@ -17,13 +19,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert-crossencoder-kl_divergence
 
-This model was trained from scratch on an unknown dataset.
+This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1204
-- Accuracy: 0.5502
-- Precision: 0.5596
-- Recall: 0.5502
-- F1: 0.5535
+- Loss: 0.9919
+- Accuracy: 0.6084
+- Precision: 0.6124
+- Recall: 0.6084
+- F1: 0.6099
 
 ## Model description
 
@@ -55,13 +57,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
-| 1.2351        | 1.0   | 78   | 1.2300          | 0.4919   | 0.3751    | 0.4919 | 0.4053 |
-| 0.9913        | 2.0   | 156  | 1.0451          | 0.5663   | 0.6022    | 0.5663 | 0.5500 |
-| 0.8534        | 3.0   | 234  | 0.9740          | 0.5696   | 0.5770    | 0.5696 | 0.5722 |
-| 0.7072        | 4.0   | 312  | 0.9896          | 0.5696   | 0.5879    | 0.5696 | 0.5731 |
-| 0.4947        | 5.0   | 390  | 1.0259          | 0.5858   | 0.5791    | 0.5858 | 0.5799 |
-| 0.4163        | 6.0   | 468  | 1.0736          | 0.5663   | 0.5713    | 0.5663 | 0.5675 |
-| 0.3163        | 7.0   | 546  | 1.1204          | 0.5502   | 0.5596    | 0.5502 | 0.5535 |
+| 1.282         | 1.0   | 78   | 1.2172          | 0.4951   | 0.3948    | 0.4951 | 0.4061 |
+| 1.0377        | 2.0   | 156  | 1.0246          | 0.5793   | 0.6114    | 0.5793 | 0.5550 |
+| 0.9037        | 3.0   | 234  | 0.9440          | 0.6084   | 0.6178    | 0.6084 | 0.6015 |
+| 0.7861        | 4.0   | 312  | 0.9381          | 0.6343   | 0.6425    | 0.6343 | 0.6356 |
+| 0.5607        | 5.0   | 390  | 0.9718          | 0.6052   | 0.6114    | 0.6052 | 0.6034 |
+| 0.4532        | 6.0   | 468  | 0.9680          | 0.6278   | 0.6290    | 0.6278 | 0.6275 |
+| 0.3763        | 7.0   | 546  | 0.9919          | 0.6084   | 0.6124    | 0.6084 | 0.6099 |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "./output1/bert-crossencoder-kl_divergence",
+  "_name_or_path": "google-bert/bert-base-uncased",
   "architectures": [
     "BertForSequenceClassification"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fa30a82b8ed772e898e32118bdcaa6622a64a1b95c1ab0823f69e2bfcb3e230
-size 437966000
+oid sha256:a8449a8f1a74c7ce4a0d4bac4ea9ebd5305708dc5f4a844c29c3c9aa79a5de0d
+size 437964800