metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- fin
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: distilbert-base-uncased-finetuned-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: fin
type: fin
config: fin
split: validation
args: fin
metrics:
- name: Precision
type: precision
value: 0.9288256227758007
- name: Recall
type: recall
value: 0.9354838709677419
- name: F1
type: f1
value: 0.9321428571428573
- name: Accuracy
type: accuracy
value: 0.9919932574799831
distilbert-base-uncased-finetuned-ner
This model is a fine-tuned version of distilbert-base-uncased on the fin dataset. It achieves the following results on the evaluation set:
- Loss: 0.0485
- Precision: 0.9288
- Recall: 0.9355
- F1: 0.9321
- Accuracy: 0.9920
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: 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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 64 | 0.0876 | 0.7519 | 0.6953 | 0.7225 | 0.9768 |
| No log | 2.0 | 128 | 0.0536 | 0.9091 | 0.8602 | 0.8840 | 0.9869 |
| No log | 3.0 | 192 | 0.0485 | 0.9288 | 0.9355 | 0.9321 | 0.9920 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1