upload

README.md

@@ -3,49 +3,49 @@ license: apache-2.0
 tags:
 - generated_from_trainer
 datasets:
-- cynthiachan/FeedRef2022
+- cynthiachan/FeedRef_10pct
 metrics:
 - precision
 - recall
 - f1
 - accuracy
 model-index:
-- name: training_2
+- name: training_3
   results:
   - task:
       name: Token Classification
       type: token-classification
     dataset:
-      name: cynthiachan/FeedRef2022
-      type: cynthiachan/FeedRef2022
-      args: FeedRef2022
+      name: cynthiachan/FeedRef_10pct
+      type: cynthiachan/FeedRef_10pct
+      args: FeedRef_10pct
     metrics:
     - name: Precision
       type: precision
-      value: 0.25
+      value: 0.6786570743405276
     - name: Recall
       type: recall
-      value: 0.14814814814814814
+      value: 0.8372781065088757
     - name: F1
       type: f1
-      value: 0.18604651162790697
+      value: 0.7496688741721853
     - name: Accuracy
       type: accuracy
-      value: 0.8611532625189682
+      value: 0.9678051829961355
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# training_2
+# training_3
 
-This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the cynthiachan/FeedRef2022 dataset.
+This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the cynthiachan/FeedRef_10pct dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5555
-- Precision: 0.25
-- Recall: 0.1481
-- F1: 0.1860
-- Accuracy: 0.8612
+- Loss: 0.1302
+- Precision: 0.6787
+- Recall: 0.8373
+- F1: 0.7497
+- Accuracy: 0.9678
 
 ## Model description
 
@@ -74,6 +74,16 @@ The following hyperparameters were used during training:
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.3927        | 0.37  | 500  | 0.2362          | 0.2854    | 0.4112 | 0.3370 | 0.9431   |
+| 0.1994        | 0.75  | 1000 | 0.1656          | 0.4762    | 0.6509 | 0.55   | 0.9550   |
+| 0.1541        | 1.12  | 1500 | 0.1437          | 0.5608    | 0.7367 | 0.6368 | 0.9602   |
+| 0.1275        | 1.5   | 2000 | 0.1497          | 0.6090    | 0.7604 | 0.6763 | 0.9638   |
+| 0.1184        | 1.87  | 2500 | 0.1302          | 0.6787    | 0.8373 | 0.7497 | 0.9678   |
+| 0.0753        | 2.25  | 3000 | 0.1375          | 0.7454    | 0.8314 | 0.7860 | 0.9698   |
+| 0.0613        | 2.62  | 3500 | 0.1465          | 0.8254    | 0.8669 | 0.8456 | 0.9736   |
+| 0.0577        | 3.0   | 4000 | 0.1334          | 0.8144    | 0.8698 | 0.8412 | 0.9746   |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2e1c462c9e9e3ac32eea2cc5924686a7236090f1586ef54fd23bf380ef37353
+oid sha256:3de499157bfdea2ea7b3d46af18b32df3bad9bf8a4d0f35f2adab2ed92203b8d
 size 431054001

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5faab74df443fa0453f8907d153de8e2ec05432295de822c202d6c068b807c1c
-size 3311
+oid sha256:424071fcbc8dac0d86ad6e221e9f19de6c334bd1b93afb168b98b0a75cb7a6b6
+size 3247