metadata
license: apache-2.0
base_model: onlplab/alephbert-base
tags:
- generated_from_trainer
datasets:
- nemo_corpus
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: aleph_bert-finetuned-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: nemo_corpus
type: nemo_corpus
config: flat_token
split: validation
args: flat_token
metrics:
- name: Precision
type: precision
value: 0.8333333333333334
- name: Recall
type: recall
value: 0.8262454434993924
- name: F1
type: f1
value: 0.8297742525930445
- name: Accuracy
type: accuracy
value: 0.9739268365222564
aleph_bert-finetuned-ner
This model is a fine-tuned version of onlplab/alephbert-base on the nemo_corpus dataset. It achieves the following results on the evaluation set:
- Loss: 0.1408
- Precision: 0.8333
- Recall: 0.8262
- F1: 0.8298
- Accuracy: 0.9739
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 |
|---|---|---|---|---|---|---|---|
| 0.042 | 1.0 | 618 | 0.1317 | 0.8198 | 0.8068 | 0.8132 | 0.9720 |
| 0.0185 | 2.0 | 1236 | 0.1367 | 0.8224 | 0.8214 | 0.8219 | 0.9714 |
| 0.0185 | 3.0 | 1854 | 0.1408 | 0.8333 | 0.8262 | 0.8298 | 0.9739 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1+cpu
- Datasets 2.15.0
- Tokenizers 0.15.0