metadata
license: apache-2.0
base_model: bert-base-multilingual-cased
tags:
- generated_from_trainer
datasets:
- ner
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: my_awesome_wnut_model
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: ner
type: ner
config: indian_names
split: train
args: indian_names
metrics:
- name: Precision
type: precision
value: 0.9950245302230862
- name: Recall
type: recall
value: 0.9949324324324325
- name: F1
type: f1
value: 0.9949784791965567
- name: Accuracy
type: accuracy
value: 0.9976269686240996
my_awesome_wnut_model
This model is a fine-tuned version of bert-base-multilingual-cased on the ner dataset. It achieves the following results on the evaluation set:
- Loss: 0.0019
- Precision: 0.9950
- Recall: 0.9949
- F1: 0.9950
- Accuracy: 0.9976
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
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
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0679 | 1.0 | 688 | 0.0131 | 0.9998 | 0.9826 | 0.9911 | 0.9920 |
| 0.0331 | 2.0 | 1376 | 0.0085 | 0.9998 | 0.9826 | 0.9911 | 0.9921 |
| 0.0248 | 3.0 | 2064 | 0.0057 | 0.9999 | 0.9826 | 0.9912 | 0.9921 |
| 0.0155 | 4.0 | 2752 | 0.0026 | 0.9948 | 0.9936 | 0.9942 | 0.9969 |
| 0.0103 | 5.0 | 3440 | 0.0019 | 0.9950 | 0.9949 | 0.9950 | 0.9976 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3