End of training

README.md

@@ -1,10 +1,13 @@
 ---
 license: apache-2.0
-base_model: sakgoyal/NLP_HW3
+base_model: bert-base-uncased
 tags:
 - generated_from_trainer
 datasets:
 - cosmos_qa
+metrics:
+- accuracy
+- f1
 model-index:
 - name: NLP_HW3
   results: []
@@ -15,7 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # NLP_HW3
 
-This model is a fine-tuned version of [sakgoyal/NLP_HW3](https://huggingface.co/sakgoyal/NLP_HW3) on the cosmos_qa dataset.
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the cosmos_qa dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.7752
+- Accuracy: 0.6057
+- F1: 0.6056
 
 ## Model description
 
@@ -40,7 +47,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 3
 
 ### Training results
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:894368055674aa2dfdb39eda2101149d88303ec7e9341e33e90f6cfb83a2bf45
+oid sha256:6a6dd018b5b41acb64438d633fd0c4e858e9df1bd2b3ceff13c0f73ff485fd42
 size 437955572

runs/Dec01_01-18-17_cb1792bfa14b/events.out.tfevents.1701393515.cb1792bfa14b.47.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af4f8c5547076af73847abcbbcd15d0a8333e747d8b6fcd70b06a47d5b5e8929
-size 5611
+oid sha256:4d3a532ca4c6ef52fdfd6f66d83d29ebb7ad330d8c95e8ff2e694144c0fe6464
+size 5965

runs/Dec01_01-18-17_cb1792bfa14b/events.out.tfevents.1701397911.cb1792bfa14b.47.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d3f2f880c857ab0ea6f58c625ce9c0a5c6e46c91ae9366fdbe3d3b61f4b8aa0
+size 457