model update
Browse files- README.md +6 -6
- best_run_hyperparameters.json +1 -1
- metric.json +1 -1
README.md
CHANGED
@@ -17,13 +17,13 @@ model-index:
|
|
17 |
metrics:
|
18 |
- name: Micro F1 (tweet_eval/offensive)
|
19 |
type: micro_f1_tweet_eval/offensive
|
20 |
-
value: 0.
|
21 |
- name: Macro F1 (tweet_eval/offensive)
|
22 |
type: micro_f1_tweet_eval/offensive
|
23 |
-
value: 0.
|
24 |
- name: Accuracy (tweet_eval/offensive)
|
25 |
type: accuracy_tweet_eval/offensive
|
26 |
-
value: 0.
|
27 |
pipeline_tag: text-classification
|
28 |
widget:
|
29 |
- text: Get the all-analog Classic Vinyl Edition of "Takin Off" Album from {@herbiehancock@} via {@bluenoterecords@} link below {{URL}}
|
@@ -50,9 +50,9 @@ Training split is `train` and parameters have been tuned on the validation split
|
|
50 |
|
51 |
Following metrics are achieved on the test split `test` ([link](https://huggingface.co/cardiffnlp/twitter-roberta-base-2021-124m-offensive/raw/main/metric.json)).
|
52 |
|
53 |
-
- F1 (micro): 0.
|
54 |
-
- F1 (macro): 0.
|
55 |
-
- Accuracy: 0.
|
56 |
|
57 |
### Usage
|
58 |
Install tweetnlp via pip.
|
|
|
17 |
metrics:
|
18 |
- name: Micro F1 (tweet_eval/offensive)
|
19 |
type: micro_f1_tweet_eval/offensive
|
20 |
+
value: 0.858139534883721
|
21 |
- name: Macro F1 (tweet_eval/offensive)
|
22 |
type: micro_f1_tweet_eval/offensive
|
23 |
+
value: 0.8232706055154664
|
24 |
- name: Accuracy (tweet_eval/offensive)
|
25 |
type: accuracy_tweet_eval/offensive
|
26 |
+
value: 0.858139534883721
|
27 |
pipeline_tag: text-classification
|
28 |
widget:
|
29 |
- text: Get the all-analog Classic Vinyl Edition of "Takin Off" Album from {@herbiehancock@} via {@bluenoterecords@} link below {{URL}}
|
|
|
50 |
|
51 |
Following metrics are achieved on the test split `test` ([link](https://huggingface.co/cardiffnlp/twitter-roberta-base-2021-124m-offensive/raw/main/metric.json)).
|
52 |
|
53 |
+
- F1 (micro): 0.858139534883721
|
54 |
+
- F1 (macro): 0.8232706055154664
|
55 |
+
- Accuracy: 0.858139534883721
|
56 |
|
57 |
### Usage
|
58 |
Install tweetnlp via pip.
|
best_run_hyperparameters.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"learning_rate":
|
|
|
1 |
+
{"learning_rate": 1.1208547084229388e-05, "num_train_epochs": 2, "per_device_train_batch_size": 32}
|
metric.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"eval_loss": 0.
|
|
|
1 |
+
{"eval_loss": 0.35168176889419556, "eval_f1": 0.858139534883721, "eval_f1_macro": 0.8232706055154664, "eval_accuracy": 0.858139534883721, "eval_runtime": 4.9862, "eval_samples_per_second": 172.477, "eval_steps_per_second": 21.66}
|