model update

README.md

@@ -18,13 +18,13 @@ model-index:
     metrics:
     - name: F1
       type: f1
-      value: 0.10513880685174248
+      value: 0.8759598346131128
     - name: F1 (macro)
       type: f1_macro
-      value: 0.031712096917869234
+      value: 0.7462751206081605
     - name: Accuracy
       type: accuracy
-      value: 0.10513880685174247
+      value: 0.8759598346131128
 pipeline_tag: text-classification
 widget:
 - text: "I'm sure the {@Tampa Bay Lightning@} would’ve rather faced the Flyers but man does their experience versus the Blue Jackets this year and last help them a lot versus this Islanders team. Another meat grinder upcoming for the good guys"
@@ -37,9 +37,9 @@ widget:
 This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base-dec2020](https://huggingface.co/cardiffnlp/twitter-roberta-base-dec2020) on the [tweet_topic_single](https://huggingface.co/datasets/cardiffnlp/tweet_topic_single). This model is fine-tuned on `train_2020` split and validated on `test_2021` split of tweet_topic.
 Fine-tuning script can be found [here](https://huggingface.co/datasets/cardiffnlp/tweet_topic_single/blob/main/lm_finetuning.py). It achieves the following results on the test_2021 set:
 
-- F1 (micro): 0.10513880685174248
-- F1 (macro): 0.031712096917869234
-- Accuracy: 0.10513880685174247
+- F1 (micro): 0.8759598346131128
+- F1 (macro): 0.7462751206081605
+- Accuracy: 0.8759598346131128
 
 
 ### Usage

metric_summary.json

@@ -1 +1 @@
-{"test/eval_loss": 2.0848724842071533, "test/eval_f1": 0.10513880685174248, "test/eval_f1_macro": 0.031712096917869234, "test/eval_accuracy": 0.10513880685174247, "test/eval_runtime": 13.4668, "test/eval_samples_per_second": 125.716, "test/eval_steps_per_second": 15.742}
+{"test/eval_loss": 0.6779355406761169, "test/eval_f1": 0.8759598346131128, "test/eval_f1_macro": 0.7462751206081605, "test/eval_accuracy": 0.8759598346131128, "test/eval_runtime": 9.5683, "test/eval_samples_per_second": 176.938, "test/eval_steps_per_second": 22.156}