metadata
license: mit
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bpmn-task-extractor
results: []
bpmn-task-extractor
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5015
- Precision: 0.625
- Recall: 0.5
- F1: 0.5556
- Accuracy: 0.8202
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: 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 1 | 1.6651 | 0.0 | 0.0 | 0.0 | 0.2584 |
| No log | 2.0 | 2 | 1.1847 | 0.1818 | 0.1 | 0.1290 | 0.6517 |
| No log | 3.0 | 3 | 0.9826 | 0.5556 | 0.25 | 0.3448 | 0.6966 |
| No log | 4.0 | 4 | 0.8535 | 0.5556 | 0.25 | 0.3448 | 0.6966 |
| No log | 5.0 | 5 | 0.7485 | 0.7 | 0.35 | 0.4667 | 0.7303 |
| No log | 6.0 | 6 | 0.6552 | 0.5833 | 0.35 | 0.4375 | 0.7528 |
| No log | 7.0 | 7 | 0.5839 | 0.5 | 0.35 | 0.4118 | 0.7753 |
| No log | 8.0 | 8 | 0.5431 | 0.6429 | 0.45 | 0.5294 | 0.7978 |
| No log | 9.0 | 9 | 0.5158 | 0.625 | 0.5 | 0.5556 | 0.8202 |
| No log | 10.0 | 10 | 0.5015 | 0.625 | 0.5 | 0.5556 | 0.8202 |
Framework versions
- Transformers 4.21.3
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1