nc33
/

my_awesome_wnut_model

Token Classification

generated_from_trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

nc33 commited on Feb 8, 2023

Commit

c98d27f

•

1 Parent(s): 3ae25b1

update model card README.md

Files changed (1) hide show

README.md +13 -13

README.md CHANGED Viewed

@@ -1,5 +1,5 @@
 ---
-license: apache-2.0
 tags:
 - generated_from_trainer
 datasets:
@@ -24,16 +24,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.49644128113879005
     - name: Recall
       type: recall
-      value: 0.25857275254865614
     - name: F1
       type: f1
-      value: 0.3400365630712979
     - name: Accuracy
       type: accuracy
-      value: 0.9386516181437305
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -41,13 +41,13 @@ should probably proofread and complete it, then remove this comment. -->
 # my_awesome_wnut_model
-This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the wnut_17 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2892
-- Precision: 0.4964
-- Recall: 0.2586
-- F1: 0.3400
-- Accuracy: 0.9387
 ## Model description
@@ -78,8 +78,8 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 213  | 0.3054          | 0.3875    | 0.1613 | 0.2277 | 0.9344   |
-| No log        | 2.0   | 426  | 0.2892          | 0.4964    | 0.2586 | 0.3400 | 0.9387   |
 ### Framework versions

 ---
+license: mit
 tags:
 - generated_from_trainer
 datasets:
     metrics:
     - name: Precision
       type: precision
+      value: 0.5606523955147809
     - name: Recall
       type: recall
+      value: 0.5097312326227988
     - name: F1
       type: f1
+      value: 0.5339805825242718
     - name: Accuracy
       type: accuracy
+      value: 0.9501154142087714
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 # my_awesome_wnut_model
+This model is a fine-tuned version of [facebook/muppet-roberta-base](https://huggingface.co/facebook/muppet-roberta-base) on the wnut_17 dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.2298
+- Precision: 0.5607
+- Recall: 0.5097
+- F1: 0.5340
+- Accuracy: 0.9501
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 213  | 0.2331          | 0.5333    | 0.4310 | 0.4767 | 0.9459   |
+| No log        | 2.0   | 426  | 0.2298          | 0.5607    | 0.5097 | 0.5340 | 0.9501   |
 ### Framework versions