model update

README.md

@@ -18,13 +18,13 @@ model-index:
     metrics:
     - name: F1
       type: f1
-      value: 0.3963378617838157
+      value: 0.8901358535144713
     - name: F1 (macro)
       type: f1_macro
-      value: 0.09461364918217709
+      value: 0.7760246189555473
     - name: Accuracy
       type: accuracy
-      value: 0.3963378617838157
+      value: 0.8901358535144713
 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_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): 0.3963378617838157
-- F1 (macro): 0.09461364918217709
-- Accuracy: 0.3963378617838157
+- F1 (micro): 0.8901358535144713
+- F1 (macro): 0.7760246189555473
+- Accuracy: 0.8901358535144713
 
 
 ### Usage

metric_summary.json

@@ -1 +1 @@
-{"test/eval_loss": 1.6966838836669922, "test/eval_f1": 0.3963378617838157, "test/eval_f1_macro": 0.09461364918217709, "test/eval_accuracy": 0.3963378617838157, "test/eval_runtime": 18.3065, "test/eval_samples_per_second": 92.481, "test/eval_steps_per_second": 11.581}
+{"test/eval_loss": 0.6905829310417175, "test/eval_f1": 0.8901358535144713, "test/eval_f1_macro": 0.7760246189555473, "test/eval_accuracy": 0.8901358535144713, "test/eval_runtime": 9.5159, "test/eval_samples_per_second": 177.914, "test/eval_steps_per_second": 22.279}