Liberty-L/Multiple_Choice_swag

README.md

@@ -1,10 +1,8 @@
 ---
 license: apache-2.0
-base_model: stevhliu/my_awesome_swag_model
+base_model: Liberty-L/Multiple_Choice_swag
 tags:
 - generated_from_trainer
-metrics:
-- accuracy
 model-index:
 - name: Multiple_Choice_swag
   results: []
@@ -15,10 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Multiple_Choice_swag
 
-This model is a fine-tuned version of [stevhliu/my_awesome_swag_model](https://huggingface.co/stevhliu/my_awesome_swag_model) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.5318
-- Accuracy: 0.6518
+This model is a fine-tuned version of [Liberty-L/Multiple_Choice_swag](https://huggingface.co/Liberty-L/Multiple_Choice_swag) on an unknown dataset.
 
 ## Model description
 
@@ -45,19 +40,9 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 20
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 4
+- num_epochs: 3
 - mixed_precision_training: Native AMP
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.0901        | 1.0   | 1271 | 1.0109          | 0.5989   |
-| 0.7717        | 2.0   | 2542 | 0.9707          | 0.6421   |
-| 0.4571        | 3.0   | 3813 | 1.2411          | 0.6574   |
-| 0.2495        | 4.0   | 5084 | 1.5318          | 0.6518   |
-
-
 ### Framework versions
 
 - Transformers 4.35.2

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "stevhliu/my_awesome_swag_model",
+  "_name_or_path": "Liberty-L/Multiple_Choice_swag",
   "architectures": [
     "BertForMultipleChoice"
   ],

runs/Nov29_09-04-22_d1be63285eed/events.out.tfevents.1701248663.d1be63285eed.208.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bb617fbc075c8cd48c6d8226dbf81efcd159cdb6b911256c372d851f8e2fd19
+size 6684

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80f10c833c6b1fba2f2d94e91d10a03b6be3caf6ccbb7b0157fc76185d46a06f
+oid sha256:6ce6fdd685c0ba5c66cd3d239e461bd354cb079deef29cea5863e010800e1713
 size 4600