metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-ner-word-embedding-model
results: []
datasets:
- lsoni/combined_tweetner7_word_embedding_augmented_dataset
bert-finetuned-ner-word-embedding-model
This model is a fine-tuned version of bert-base-cased on the lsoni/combined_tweetner7_word_embedding_augmented_dataset (combined training dataset tweetner7(train_2021)+augmented dataset(train_2021) using word embedding technique). and it uses evaluation dataset the lsoni/combined_tweetner7_word_embedding_augmented_dataset_eval (combined training dataset tweetner7(validation_2021)+augmented eval dataset(validation_2021) using word embedding technique). It achieves the following results on the evaluation set:
- Loss: 0.5447
- Precision: 0.6541
- Recall: 0.4910
- F1: 0.5610
- Accuracy: 0.8623
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 |
|---|---|---|---|---|---|---|---|
| 0.7226 | 1.0 | 624 | 0.5818 | 0.7102 | 0.4474 | 0.5490 | 0.8628 |
| 0.5246 | 2.0 | 1248 | 0.5462 | 0.6465 | 0.4807 | 0.5514 | 0.8615 |
| 0.4558 | 3.0 | 1872 | 0.5447 | 0.6541 | 0.4910 | 0.5610 | 0.8623 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.12.1
- Datasets 2.10.1
- Tokenizers 0.12.1