metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- tweetner7
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-ner-base-model
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: tweetner7
type: tweetner7
args: tweetner7
metrics:
- name: Precision
type: precision
value: 0.6853448275862069
- name: Recall
type: recall
value: 0.6456852791878173
- name: F1
type: f1
value: 0.6649242028227914
- name: Accuracy
type: accuracy
value: 0.8757089711532597
bert-finetuned-ner-base-model
This model is a fine-tuned version of bert-base-cased on the tweetner7 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4160
- Precision: 0.6853
- Recall: 0.6457
- F1: 0.6649
- Accuracy: 0.8757
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: 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 results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 312 | 0.4339 | 0.7365 | 0.5931 | 0.6571 | 0.8731 |
0.5311 | 2.0 | 624 | 0.4190 | 0.7348 | 0.6069 | 0.6647 | 0.8763 |
0.5311 | 3.0 | 936 | 0.4160 | 0.6853 | 0.6457 | 0.6649 | 0.8757 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.12.1
- Datasets 2.10.1
- Tokenizers 0.12.1