Tommert25
/

multibertfinetuned1107

Token Classification

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

Tommert25 commited on Jul 26, 2023

Commit

4ec31e2

•

1 Parent(s): a63c735

update model card README.md

Files changed (1) hide show

README.md +12 -12

README.md CHANGED Viewed

@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [bert-base-multilingual-uncased](https://huggingface.co/bert-base-multilingual-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4896
-- Precision: 0.6282
-- Recall: 0.5688
-- F1: 0.5970
-- Accuracy: 0.8756
 ## Model description
@@ -44,8 +44,8 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 32
-- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -55,11 +55,11 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 73   | 0.5149          | 0.5414    | 0.4527 | 0.4931 | 0.8510   |
-| No log        | 2.0   | 146  | 0.6092          | 0.57      | 0.5005 | 0.5330 | 0.8464   |
-| No log        | 3.0   | 219  | 0.4896          | 0.6282    | 0.5688 | 0.5970 | 0.8756   |
-| No log        | 4.0   | 292  | 0.5196          | 0.6420    | 0.6176 | 0.6295 | 0.8764   |
-| No log        | 5.0   | 365  | 0.5270          | 0.6479    | 0.6176 | 0.6324 | 0.8786   |
 ### Framework versions

 This model is a fine-tuned version of [bert-base-multilingual-uncased](https://huggingface.co/bert-base-multilingual-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.5977
+- Precision: 0.6463
+- Recall: 0.6078
+- F1: 0.6264
+- Accuracy: 0.8835
 ## Model description
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 145  | 0.6113          | 0.6550    | 0.5854 | 0.6182 | 0.8735   |
+| No log        | 2.0   | 290  | 0.6457          | 0.6270    | 0.5659 | 0.5949 | 0.8705   |
+| No log        | 3.0   | 435  | 0.5977          | 0.6463    | 0.6078 | 0.6264 | 0.8835   |
+| 0.1409        | 4.0   | 580  | 0.6095          | 0.6752    | 0.6449 | 0.6597 | 0.8865   |
+| 0.1409        | 5.0   | 725  | 0.6566          | 0.6680    | 0.6380 | 0.6527 | 0.8851   |
 ### Framework versions