metadata
license: apache-2.0
base_model: distilroberta-base
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: RoBERTa_conll_epoch_6
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: conll2003
type: conll2003
config: conll2003
split: validation
args: conll2003
metrics:
- name: Precision
type: precision
value: 0.9445551128818062
- name: Recall
type: recall
value: 0.9575900370245709
- name: F1
type: f1
value: 0.9510279124185191
- name: Accuracy
type: accuracy
value: 0.9882943143812709
RoBERTa_conll_epoch_6
This model is a fine-tuned version of distilroberta-base on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0763
- Precision: 0.9446
- Recall: 0.9576
- F1: 0.9510
- Accuracy: 0.9883
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: 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: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0787 | 1.0 | 1756 | 0.0740 | 0.8954 | 0.9281 | 0.9115 | 0.9813 |
| 0.0459 | 2.0 | 3512 | 0.0770 | 0.9288 | 0.9416 | 0.9351 | 0.9846 |
| 0.0241 | 3.0 | 5268 | 0.0613 | 0.9354 | 0.9504 | 0.9428 | 0.9867 |
| 0.0155 | 4.0 | 7024 | 0.0615 | 0.9404 | 0.9536 | 0.9469 | 0.9884 |
| 0.0073 | 5.0 | 8780 | 0.0744 | 0.9420 | 0.9567 | 0.9493 | 0.9879 |
| 0.0036 | 6.0 | 10536 | 0.0763 | 0.9446 | 0.9576 | 0.9510 | 0.9883 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1