rubinho
/

bert-finetuned-ner

Token Classification

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

rubinho commited on Nov 3, 2023

Commit

c0098da

•

1 Parent(s): ac6d7e0

Training complete

Files changed (3) hide show

README.md +11 -11
pytorch_model.bin +1 -1
training_args.bin +2 -2

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-cased](https://huggingface.co/bert-base-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3761
-- Precision: 0.5592
-- Recall: 0.4856
-- F1: 0.5198
-- Accuracy: 0.9258
 ## Model description
@@ -43,11 +43,11 @@ More information needed
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 3.6298652877725645e-06
-- train_batch_size: 32
 - eval_batch_size: 8
 - seed: 42
-- optimizer: Adam with betas=(0.9509822023671163,0.947724818069466) and epsilon=1.3490158743843502e-09
 - lr_scheduler_type: linear
 - num_epochs: 3
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 107  | 0.3711          | 0.5635    | 0.4988 | 0.5292 | 0.9264   |
-| No log        | 2.0   | 214  | 0.3694          | 0.55      | 0.4868 | 0.5165 | 0.9257   |
-| No log        | 3.0   | 321  | 0.3761          | 0.5592    | 0.4856 | 0.5198 | 0.9258   |
 ### Framework versions

 This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.4784
+- Precision: 0.5557
+- Recall: 0.4892
+- F1: 0.5204
+- Accuracy: 0.9252
 ## Model description
 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 3
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 425  | 0.3611          | 0.4908    | 0.5084 | 0.4994 | 0.9233   |
+| No log        | 2.0   | 850  | 0.4981          | 0.5770    | 0.4569 | 0.5100 | 0.9221   |
+| No log        | 3.0   | 1275 | 0.4784          | 0.5557    | 0.4892 | 0.5204 | 0.9252   |
 ### Framework versions

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1967978dd904ee28d3d96788ec7c1a9efdcd5a38d186cf210d07fdd53192429a
 size 430986854

 version https://git-lfs.github.com/spec/v1
+oid sha256:d84f854e80f752c3e532e63b823ab19b1799b9d8a839cba2238e86ee26ef4a99
 size 430986854

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef233d8a5ccd008fb40272efb6f012b5d6449bcafa954139cd699975a2206017
-size 4536

 version https://git-lfs.github.com/spec/v1
+oid sha256:8a299ea467838db79676bee189cffd08d5fd25335d97857ecc1e79a61ad2fc37
+size 4472