asahi417 commited on
Commit
f87b7fa
1 Parent(s): 2b41268

model update

Browse files
Files changed (2) hide show
  1. README.md +6 -6
  2. metric_summary.json +1 -1
README.md CHANGED
@@ -18,13 +18,13 @@ model-index:
18
  metrics:
19
  - name: F1
20
  type: f1
21
- value: 0.1494388659184879
22
  - name: F1 (macro)
23
  type: f1_macro
24
- value: 0.07391536194788544
25
  - name: Accuracy
26
  type: accuracy
27
- value: 0.1494388659184879
28
  pipeline_tag: text-classification
29
  widget:
30
  - 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:
37
  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.
38
  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:
39
 
40
- - F1 (micro): 0.1494388659184879
41
- - F1 (macro): 0.07391536194788544
42
- - Accuracy: 0.1494388659184879
43
 
44
 
45
  ### Usage
 
18
  metrics:
19
  - name: F1
20
  type: f1
21
+ value: 0.8948611931482575
22
  - name: F1 (macro)
23
  type: f1_macro
24
+ value: 0.800952410284692
25
  - name: Accuracy
26
  type: accuracy
27
+ value: 0.8948611931482575
28
  pipeline_tag: text-classification
29
  widget:
30
  - 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
  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.
38
  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:
39
 
40
+ - F1 (micro): 0.8948611931482575
41
+ - F1 (macro): 0.800952410284692
42
+ - Accuracy: 0.8948611931482575
43
 
44
 
45
  ### Usage
metric_summary.json CHANGED
@@ -1 +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}
 
1
+ {"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}