model update

README.md

@@ -18,13 +18,13 @@ model-index:
     metrics:
     - name: F1
       type: f1
-      value: 0.1494388659184879
+      value: 0.8948611931482575
     - name: F1 (macro)
       type: f1_macro
-      value: 0.07391536194788544
+      value: 0.800952410284692
     - name: Accuracy
       type: accuracy
-      value: 0.1494388659184879
+      value: 0.8948611931482575
 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-dec2021](https://huggingface.co/cardiffnlp/twitter-roberta-base-dec2021) on the [tweet_topic_single](https://huggingface.co/datasets/cardiffnlp/tweet_topic_single). This model is fine-tuned on `train_all` 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): 0.1494388659184879
-- F1 (macro): 0.07391536194788544
-- Accuracy: 0.1494388659184879
+- F1 (micro): 0.8948611931482575
+- F1 (macro): 0.800952410284692
+- Accuracy: 0.8948611931482575
 
 
 ### Usage

metric_summary.json

@@ -1 +1 @@
-{"test/eval_loss": 1.7828656435012817, "test/eval_f1": 0.1494388659184879, "test/eval_f1_macro": 0.07391536194788544, "test/eval_accuracy": 0.1494388659184879, "test/eval_runtime": 18.3207, "test/eval_samples_per_second": 92.409, "test/eval_steps_per_second": 11.572}
+{"test/eval_loss": 0.6357476115226746, "test/eval_f1": 0.8948611931482575, "test/eval_f1_macro": 0.800952410284692, "test/eval_accuracy": 0.8948611931482575, "test/eval_runtime": 14.2067, "test/eval_samples_per_second": 119.169, "test/eval_steps_per_second": 14.923}